2130 files changed, 71549 insertions, 37027 deletions

diff --git a/Documentation/controllers/cpuacct.txt b/Documentation/controllers/cpuacct.txt
new file mode 100644
index 000000000000..bb775fbe43d7
--- /dev/null
+++ b/Documentation/controllers/cpuacct.txt
@@ -0,0 +1,32 @@
+CPU Accounting Controller
+-------------------------
+
+The CPU accounting controller is used to group tasks using cgroups and
+account the CPU usage of these groups of tasks.
+
+The CPU accounting controller supports multi-hierarchy groups. An accounting
+group accumulates the CPU usage of all of its child groups and the tasks
+directly present in its group.
+
+Accounting groups can be created by first mounting the cgroup filesystem.
+
+# mkdir /cgroups
+# mount -t cgroup -ocpuacct none /cgroups
+
+With the above step, the initial or the parent accounting group
+becomes visible at /cgroups. At bootup, this group includes all the
+tasks in the system. /cgroups/tasks lists the tasks in this cgroup.
+/cgroups/cpuacct.usage gives the CPU time (in nanoseconds) obtained by
+this group which is essentially the CPU time obtained by all the tasks
+in the system.
+
+New accounting groups can be created under the parent group /cgroups.
+
+# cd /cgroups
+# mkdir g1
+# echo $$ > g1
+
+The above steps create a new group g1 and move the current shell
+process (bash) into it. CPU time consumed by this bash and its children
+can be obtained from g1/cpuacct.usage and the same is accumulated in
+/cgroups/cpuacct.usage also.
diff --git a/Documentation/feature-removal-schedule.txt b/Documentation/feature-removal-schedule.txt
index c28a2ac88f9d..72c6fb0f31ae 100644
--- a/Documentation/feature-removal-schedule.txt
+++ b/Documentation/feature-removal-schedule.txt
@@ -343,3 +343,11 @@ When:	2.6.29 (ideally) or 2.6.30 (more likely)
 Why:	Deprecated by the new (standard) device driver binding model. Use
 	i2c_driver->probe() and ->remove() instead.
 Who:	Jean Delvare <khali@linux-fr.org>
+
+---------------------------
+
+What:	fscher and fscpos drivers
+When:	June 2009
+Why:	Deprecated by the new fschmd driver.
+Who:	Hans de Goede <hdegoede@redhat.com>
+	Jean Delvare <khali@linux-fr.org>
diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt
index bb1b0dd3bfcb..71df353e367c 100644
--- a/Documentation/filesystems/proc.txt
+++ b/Documentation/filesystems/proc.txt
@@ -1339,10 +1339,13 @@ nmi_watchdog
 
 Enables/Disables the NMI watchdog on x86 systems.  When the value is non-zero
 the NMI watchdog is enabled and will continuously test all online cpus to
-determine whether or not they are still functioning properly.
+determine whether or not they are still functioning properly. Currently,
+passing "nmi_watchdog=" parameter at boot time is required for this function
+to work.
 
-Because the NMI watchdog shares registers with oprofile, by disabling the NMI
-watchdog, oprofile may have more registers to utilize.
+If LAPIC NMI watchdog method is in use (nmi_watchdog=2 kernel parameter), the
+NMI watchdog shares registers with oprofile. By disabling the NMI watchdog,
+oprofile may have more registers to utilize.
 
 msgmni
 ------
diff --git a/Documentation/filesystems/xfs.txt b/Documentation/filesystems/xfs.txt
index 0a1668ba2600..9878f50d6ed6 100644
--- a/Documentation/filesystems/xfs.txt
+++ b/Documentation/filesystems/xfs.txt
@@ -229,10 +229,6 @@ The following sysctls are available for the XFS filesystem:
 	ISGID bit is cleared if the irix_sgid_inherit compatibility sysctl
 	is set.
 
-  fs.xfs.restrict_chown		(Min: 0  Default: 1  Max: 1)
-  	Controls whether unprivileged users can use chown to "give away"
-	a file to another user.
-
   fs.xfs.inherit_sync		(Min: 0  Default: 1  Max: 1)
 	Setting this to "1" will cause the "sync" flag set
 	by the xfs_io(8) chattr command on a directory to be
diff --git a/Documentation/ftrace.txt b/Documentation/ftrace.txt
index 9cc4d685dde5..35a78bc6651d 100644
--- a/Documentation/ftrace.txt
+++ b/Documentation/ftrace.txt
@@ -82,7 +82,7 @@ of ftrace. Here is a list of some of the key files:
 		tracer is not adding more data, they will display
 		the same information every time they are read.
 
-  iter_ctrl: This file lets the user control the amount of data
+  trace_options: This file lets the user control the amount of data
 		that is displayed in one of the above output
 		files.
 
@@ -94,10 +94,10 @@ of ftrace. Here is a list of some of the key files:
 		only be recorded if the latency is greater than
 		the value in this file. (in microseconds)
 
-  trace_entries: This sets or displays the number of bytes each CPU
+  buffer_size_kb: This sets or displays the number of kilobytes each CPU
 		buffer can hold. The tracer buffers are the same size
 		for each CPU. The displayed number is the size of the
-		 CPU buffer and not total size of all buffers. The
+		CPU buffer and not total size of all buffers. The
 		trace buffers are allocated in pages (blocks of memory
 		that the kernel uses for allocation, usually 4 KB in size).
 		If the last page allocated has room for more bytes
@@ -316,23 +316,23 @@ The above is mostly meaningful for kernel developers.
   The rest is the same as the 'trace' file.
 
 
-iter_ctrl
----------
+trace_options
+-------------
 
-The iter_ctrl file is used to control what gets printed in the trace
+The trace_options file is used to control what gets printed in the trace
 output. To see what is available, simply cat the file:
 
-  cat /debug/tracing/iter_ctrl
+  cat /debug/tracing/trace_options
   print-parent nosym-offset nosym-addr noverbose noraw nohex nobin \
- noblock nostacktrace nosched-tree
+ noblock nostacktrace nosched-tree nouserstacktrace nosym-userobj
 
 To disable one of the options, echo in the option prepended with "no".
 
-  echo noprint-parent > /debug/tracing/iter_ctrl
+  echo noprint-parent > /debug/tracing/trace_options
 
 To enable an option, leave off the "no".
 
-  echo sym-offset > /debug/tracing/iter_ctrl
+  echo sym-offset > /debug/tracing/trace_options
 
 Here are the available options:
 
@@ -378,6 +378,20 @@ Here are the available options:
 		When a trace is recorded, so is the stack of functions.
 		This allows for back traces of trace sites.
 
+  userstacktrace - This option changes the trace.
+		   It records a stacktrace of the current userspace thread.
+
+  sym-userobj - when user stacktrace are enabled, look up which object the
+		address belongs to, and print a relative address
+		This is especially useful when ASLR is on, otherwise you don't
+		get a chance to resolve the address to object/file/line after the app is no
+		longer running
+
+		The lookup is performed when you read trace,trace_pipe,latency_trace. Example:
+
+		a.out-1623  [000] 40874.465068: /root/a.out[+0x480] <-/root/a.out[+0
+x494] <- /root/a.out[+0x4a8] <- /lib/libc-2.7.so[+0x1e1a6]
+
   sched-tree - TBD (any users??)
 
 
@@ -1299,41 +1313,29 @@ trace entries
 -------------
 
 Having too much or not enough data can be troublesome in diagnosing
-an issue in the kernel. The file trace_entries is used to modify
+an issue in the kernel. The file buffer_size_kb is used to modify
 the size of the internal trace buffers. The number listed
 is the number of entries that can be recorded per CPU. To know
 the full size, multiply the number of possible CPUS with the
 number of entries.
 
- # cat /debug/tracing/trace_entries
-65620
+ # cat /debug/tracing/buffer_size_kb
+1408 (units kilobytes)
 
 Note, to modify this, you must have tracing completely disabled. To do that,
 echo "nop" into the current_tracer. If the current_tracer is not set
 to "nop", an EINVAL error will be returned.
 
  # echo nop > /debug/tracing/current_tracer
- # echo 100000 > /debug/tracing/trace_entries
- # cat /debug/tracing/trace_entries
-100045
-
-
-Notice that we echoed in 100,000 but the size is 100,045. The entries
-are held in individual pages. It allocates the number of pages it takes
-to fulfill the request. If more entries may fit on the last page
-then they will be added.
-
- # echo 1 > /debug/tracing/trace_entries
- # cat /debug/tracing/trace_entries
-85
-
-This shows us that 85 entries can fit in a single page.
+ # echo 10000 > /debug/tracing/buffer_size_kb
+ # cat /debug/tracing/buffer_size_kb
+10000 (units kilobytes)
 
 The number of pages which will be allocated is limited to a percentage
 of available memory. Allocating too much will produce an error.
 
- # echo 1000000000000 > /debug/tracing/trace_entries
+ # echo 1000000000000 > /debug/tracing/buffer_size_kb
 -bash: echo: write error: Cannot allocate memory
- # cat /debug/tracing/trace_entries
+ # cat /debug/tracing/buffer_size_kb
 85
 
diff --git a/Documentation/hwmon/it87 b/Documentation/hwmon/it87
index 042c0415140b..659315d98e00 100644
--- a/Documentation/hwmon/it87
+++ b/Documentation/hwmon/it87
@@ -26,6 +26,10 @@ Supported chips:
     Datasheet: Publicly available at the ITE website
                http://www.ite.com.tw/product_info/file/pc/IT8718F_V0.2.zip
                http://www.ite.com.tw/product_info/file/pc/IT8718F_V0%203_(for%20C%20version).zip
+  * IT8720F
+    Prefix: 'it8720'
+    Addresses scanned: from Super I/O config space (8 I/O ports)
+    Datasheet: Not yet publicly available.
   * SiS950   [clone of IT8705F]
     Prefix: 'it87'
     Addresses scanned: from Super I/O config space (8 I/O ports)
@@ -71,7 +75,7 @@ Description
 -----------
 
 This driver implements support for the IT8705F, IT8712F, IT8716F,
-IT8718F, IT8726F and SiS950 chips.
+IT8718F, IT8720F, IT8726F and SiS950 chips.
 
 These chips are 'Super I/O chips', supporting floppy disks, infrared ports,
 joysticks and other miscellaneous stuff. For hardware monitoring, they
@@ -84,19 +88,19 @@ the IT8716F and late IT8712F have 6. They are shared with other functions
 though, so the functionality may not be available on a given system.
 The driver dumbly assume it is there.
 
-The IT8718F also features VID inputs (up to 8 pins) but the value is
-stored in the Super-I/O configuration space. Due to technical limitations,
+The IT8718F and IT8720F also features VID inputs (up to 8 pins) but the value
+is stored in the Super-I/O configuration space. Due to technical limitations,
 this value can currently only be read once at initialization time, so
 the driver won't notice and report changes in the VID value. The two
 upper VID bits share their pins with voltage inputs (in5 and in6) so you
 can't have both on a given board.
 
-The IT8716F, IT8718F and later IT8712F revisions have support for
+The IT8716F, IT8718F, IT8720F and later IT8712F revisions have support for
 2 additional fans. The additional fans are supported by the driver.
 
-The IT8716F and IT8718F, and late IT8712F and IT8705F also have optional
-16-bit tachometer counters for fans 1 to 3. This is better (no more fan
-clock divider mess) but not compatible with the older chips and
+The IT8716F, IT8718F and IT8720F, and late IT8712F and IT8705F also have
+optional 16-bit tachometer counters for fans 1 to 3. This is better (no more
+fan clock divider mess) but not compatible with the older chips and
 revisions. The 16-bit tachometer mode is enabled by the driver when one
 of the above chips is detected.
 
@@ -122,7 +126,7 @@ zero'; this is important for negative voltage measurements. All voltage
 inputs can measure voltages between 0 and 4.08 volts, with a resolution of
 0.016 volt. The battery voltage in8 does not have limit registers.
 
-The VID lines (IT8712F/IT8716F/IT8718F) encode the core voltage value:
+The VID lines (IT8712F/IT8716F/IT8718F/IT8720F) encode the core voltage value:
 the voltage level your processor should work with. This is hardcoded by
 the mainboard and/or processor itself. It is a value in volts.
 
diff --git a/Documentation/hwmon/lm70 b/Documentation/hwmon/lm70
index 2bdd3feebf53..0d240291e3cc 100644
--- a/Documentation/hwmon/lm70
+++ b/Documentation/hwmon/lm70
@@ -1,9 +1,11 @@
 Kernel driver lm70
 ==================
 
-Supported chip:
+Supported chips:
   * National Semiconductor LM70
     Datasheet: http://www.national.com/pf/LM/LM70.html
+  * Texas Instruments TMP121/TMP123
+    Information: http://focus.ti.com/docs/prod/folders/print/tmp121.html
 
 Author:
         Kaiwan N Billimoria <kaiwan@designergraphix.com>
@@ -25,6 +27,14 @@ complement digital temperature (sent via the SIO line), is available in the
 driver for interpretation. This driver makes use of the kernel's in-core
 SPI support.
 
+As a real (in-tree) example of this "SPI protocol driver" interfacing
+with a "SPI master controller driver", see drivers/spi/spi_lm70llp.c
+and its associated documentation.
+
+The TMP121/TMP123 are very similar; main differences are 4 wire SPI inter-
+face (read only) and 13-bit temperature data (0.0625 degrees celsius reso-
+lution).
+
 Thanks to
 ---------
 Jean Delvare <khali@linux-fr.org> for mentoring the hwmon-side driver
diff --git a/Documentation/hwmon/ltc4245 b/Documentation/hwmon/ltc4245
new file mode 100644
index 000000000000..bae7a3adc5d8
--- /dev/null
+++ b/Documentation/hwmon/ltc4245
@@ -0,0 +1,81 @@
+Kernel driver ltc4245
+=====================
+
+Supported chips:
+  * Linear Technology LTC4245
+    Prefix: 'ltc4245'
+    Addresses scanned: 0x20-0x3f
+    Datasheet:
+        http://www.linear.com/pc/downloadDocument.do?navId=H0,C1,C1003,C1006,C1140,P19392,D13517
+
+Author: Ira W. Snyder <iws@ovro.caltech.edu>
+
+
+Description
+-----------
+
+The LTC4245 controller allows a board to be safely inserted and removed
+from a live backplane in multiple supply systems such as CompactPCI and
+PCI Express.
+
+
+Usage Notes
+-----------
+
+This driver does not probe for LTC4245 devices, due to the fact that some
+of the possible addresses are unfriendly to probing. You will need to use
+the "force" parameter to tell the driver where to find the device.
+
+Example: the following will load the driver for an LTC4245 at address 0x23
+on I2C bus #1:
+$ modprobe ltc4245 force=1,0x23
+
+
+Sysfs entries
+-------------
+
+The LTC4245 has built-in limits for over and under current warnings. This
+makes it very likely that the reference circuit will be used.
+
+This driver uses the values in the datasheet to change the register values
+into the values specified in the sysfs-interface document. The current readings
+rely on the sense resistors listed in Table 2: "Sense Resistor Values".
+
+in1_input		12v input voltage (mV)
+in2_input		5v  input voltage (mV)
+in3_input		3v  input voltage (mV)
+in4_input		Vee (-12v) input voltage (mV)
+
+in1_min_alarm		12v input undervoltage alarm
+in2_min_alarm		5v  input undervoltage alarm
+in3_min_alarm		3v  input undervoltage alarm
+in4_min_alarm		Vee (-12v) input undervoltage alarm
+
+curr1_input		12v current (mA)
+curr2_input		5v  current (mA)
+curr3_input		3v  current (mA)
+curr4_input		Vee (-12v) current (mA)
+
+curr1_max_alarm		12v overcurrent alarm
+curr2_max_alarm		5v  overcurrent alarm
+curr3_max_alarm		3v  overcurrent alarm
+curr4_max_alarm		Vee (-12v) overcurrent alarm
+
+in5_input		12v output voltage (mV)
+in6_input		5v  output voltage (mV)
+in7_input		3v  output voltage (mV)
+in8_input		Vee (-12v) output voltage (mV)
+
+in5_min_alarm		12v output undervoltage alarm
+in6_min_alarm		5v  output undervoltage alarm
+in7_min_alarm		3v  output undervoltage alarm
+in8_min_alarm		Vee (-12v) output undervoltage alarm
+
+in9_input		GPIO #1 voltage data
+in10_input		GPIO #2 voltage data
+in11_input		GPIO #3 voltage data
+
+power1_input		12v power usage (mW)
+power2_input		5v  power usage (mW)
+power3_input		3v  power usage (mW)
+power4_input		Vee (-12v) power usage (mW)
diff --git a/Documentation/kbuild/makefiles.txt b/Documentation/kbuild/makefiles.txt
index 7a7753321a26..51104f9194a5 100644
--- a/Documentation/kbuild/makefiles.txt
+++ b/Documentation/kbuild/makefiles.txt
@@ -383,6 +383,20 @@ more details, with real examples.
 	to prerequisites are referenced with $(src) (because they are not
 	generated files).
 
+    $(kecho)
+	echoing information to user in a rule is often a good practice
+	but when execution "make -s" one does not expect to see any output
+	except for warnings/errors.
+	To support this kbuild define $(kecho) which will echo out the
+	text following $(kecho) to stdout except if "make -s" is used.
+
+	Example:
+		#arch/blackfin/boot/Makefile
+		$(obj)/vmImage: $(obj)/vmlinux.gz
+			$(call if_changed,uimage)
+			@$(kecho) 'Kernel: $@ is ready'
+
+
 --- 3.11 $(CC) support functions
 
 	The kernel may be built with several different versions of
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index e0f346d201ed..374baa116a4e 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -90,6 +90,7 @@ parameter is applicable:
 	SWSUSP	Software suspend (hibernation) is enabled.
 	SUSPEND	System suspend states are enabled.
 	TS	Appropriate touchscreen support is enabled.
+	UMS	USB Mass Storage support is enabled.
 	USB	USB support is enabled.
 	USBHID	USB Human Interface Device support is enabled.
 	V4L	Video For Linux support is enabled.
@@ -149,7 +150,8 @@ and is between 256 and 4096 characters. It is defined in the file
 			default: 0
 
 	acpi_sleep=	[HW,ACPI] Sleep options
-			Format: { s3_bios, s3_mode, s3_beep, s4_nohwsig, old_ordering }
+			Format: { s3_bios, s3_mode, s3_beep, s4_nohwsig,
+				  old_ordering, s4_nonvs }
 			See Documentation/power/video.txt for s3_bios and s3_mode.
 			s3_beep is for debugging; it makes the PC's speaker beep
 			as soon as the kernel's real-mode entry point is called.
@@ -159,6 +161,8 @@ and is between 256 and 4096 characters. It is defined in the file
 			control method, wrt putting devices into low power
 			states, to be enforced (the ACPI 2.0 ordering of _PTS is
 			used by default).
+			s4_nonvs prevents the kernel from saving/restoring the
+			ACPI NVS memory during hibernation.
 
 	acpi_sci=	[HW,ACPI] ACPI System Control Interrupt trigger mode
 			Format: { level | edge | high | low }
@@ -750,6 +754,14 @@ and is between 256 and 4096 characters. It is defined in the file
 			parameter will force ia64_sal_cache_flush to call
 			ia64_pal_cache_flush instead of SAL_CACHE_FLUSH.
 
+	ftrace=[tracer]
+			[ftrace] will set and start the specified tracer
+			as early as possible in order to facilitate early
+			boot debugging.
+
+	ftrace_dump_on_oops
+			[ftrace] will dump the trace buffers on oops.
+
 	gamecon.map[2|3]=
 			[HW,JOY] Multisystem joystick and NES/SNES/PSX pad
 			support via parallel port (up to 5 devices per port)
@@ -811,6 +823,9 @@ and is between 256 and 4096 characters. It is defined in the file
 
 	hlt		[BUGS=ARM,SH]
 
+	hvc_iucv=	[S390] Number of z/VM IUCV Hypervisor console (HVC)
+			       back-ends. Valid parameters: 0..8
+
 	i8042.debug	[HW] Toggle i8042 debug mode
 	i8042.direct	[HW] Put keyboard port into non-translated mode
 	i8042.dumbkbd	[HW] Pretend that controller can only read data from
@@ -898,6 +913,10 @@ and is between 256 and 4096 characters. It is defined in the file
 
 	inttest=	[IA64]
 
+	iomem=		Disable strict checking of access to MMIO memory
+		strict	regions from userspace.
+		relaxed
+
 	iommu=		[x86]
 		off
 		force
@@ -1393,7 +1412,20 @@ and is between 256 and 4096 characters. It is defined in the file
 			when a NMI is triggered.
 			Format: [state][,regs][,debounce][,die]
 
-	nmi_watchdog=	[KNL,BUGS=X86-32] Debugging features for SMP kernels
+	nmi_watchdog=	[KNL,BUGS=X86-32,X86-64] Debugging features for SMP kernels
+			Format: [panic,][num]
+			Valid num: 0,1,2
+			0 - turn nmi_watchdog off
+			1 - use the IO-APIC timer for the NMI watchdog
+			2 - use the local APIC for the NMI watchdog using
+			a performance counter. Note: This will use one performance
+			counter and the local APIC's performance vector.
+			When panic is specified panic when an NMI watchdog timeout occurs.
+			This is useful when you use a panic=... timeout and need the box
+			quickly up again.
+			Instead of 1 and 2 it is possible to use the following
+			symbolic names: lapic and ioapic
+			Example: nmi_watchdog=2 or nmi_watchdog=panic,lapic
 
 	no387		[BUGS=X86-32] Tells the kernel to use the 387 maths
 			emulation library even if a 387 maths coprocessor
@@ -1626,6 +1658,17 @@ and is between 256 and 4096 characters. It is defined in the file
 		nomsi		[MSI] If the PCI_MSI kernel config parameter is
 				enabled, this kernel boot option can be used to
 				disable the use of MSI interrupts system-wide.
+		noioapicquirk	[APIC] Disable all boot interrupt quirks.
+				Safety option to keep boot IRQs enabled. This
+				should never be necessary.
+		ioapicreroute	[APIC] Enable rerouting of boot IRQs to the
+				primary IO-APIC for bridges that cannot disable
+				boot IRQs. This fixes a source of spurious IRQs
+				when the system masks IRQs.
+		noioapicreroute	[APIC] Disable workaround that uses the
+				boot IRQ equivalent of an IRQ that connects to
+				a chipset where boot IRQs cannot be disabled.
+				The opposite of ioapicreroute.
 		biosirq		[X86-32] Use PCI BIOS calls to get the interrupt
 				routing table. These calls are known to be buggy
 				on several machines and they hang the machine
@@ -2249,12 +2292,27 @@ and is between 256 and 4096 characters. It is defined in the file
 			See comment before function dc390_setup() in
 			drivers/scsi/tmscsim.c.
 
+	topology=	[S390]
+			Format: {off | on}
+			Specify if the kernel should make use of the cpu
+			topology informations if the hardware supports these.
+			The scheduler will make use of these informations and
+			e.g. base its process migration decisions on it.
+			Default is off.
+
 	tp720=		[HW,PS2]
 
 	trix=		[HW,OSS] MediaTrix AudioTrix Pro
 			Format:
 			<io>,<irq>,<dma>,<dma2>,<sb_io>,<sb_irq>,<sb_dma>,<mpu_io>,<mpu_irq>
 
+	tsc=		Disable clocksource-must-verify flag for TSC.
+			Format: <string>
+			[x86] reliable: mark tsc clocksource as reliable, this
+			disables clocksource verification at runtime.
+			Used to enable high-resolution timer mode on older
+			hardware, and in virtualized environment.
+
 	turbografx.map[2|3]=	[HW,JOY]
 			TurboGraFX parallel port interface
 			Format:
@@ -2311,6 +2369,34 @@ and is between 256 and 4096 characters. It is defined in the file
 	usbhid.mousepoll=
 			[USBHID] The interval which mice are to be polled at.
 
+	usb-storage.delay_use=
+			[UMS] The delay in seconds before a new device is
+			scanned for Logical Units (default 5).
+
+	usb-storage.quirks=
+			[UMS] A list of quirks entries to supplement or
+			override the built-in unusual_devs list.  List
+			entries are separated by commas.  Each entry has
+			the form VID:PID:Flags where VID and PID are Vendor
+			and Product ID values (4-digit hex numbers) and
+			Flags is a set of characters, each corresponding
+			to a common usb-storage quirk flag as follows:
+				c = FIX_CAPACITY (decrease the reported
+					device capacity by one sector);
+				i = IGNORE_DEVICE (don't bind to this
+					device);
+				l = NOT_LOCKABLE (don't try to lock and
+					unlock ejectable media);
+				m = MAX_SECTORS_64 (don't transfer more
+					than 64 sectors = 32 KB at a time);
+				r = IGNORE_RESIDUE (the device reports
+					bogus residue values);
+				s = SINGLE_LUN (the device has only one
+					Logical Unit);
+				w = NO_WP_DETECT (don't test whether the
+					medium is write-protected).
+			Example: quirks=0419:aaf5:rl,0421:0433:rc
+
 	add_efi_memmap	[EFI; x86-32,X86-64] Include EFI memory map in
 			kernel's map of available physical RAM.
 
diff --git a/Documentation/kmsg/s390/hvc_iucv b/Documentation/kmsg/s390/hvc_iucv
new file mode 100644
index 000000000000..0040eb18b950
--- /dev/null
+++ b/Documentation/kmsg/s390/hvc_iucv
@@ -0,0 +1,50 @@
+/*?
+ * Text: "The z/VM IUCV Hypervisor console cannot be used without z/VM.\n"
+ * Severity: Warning
+ * Description:
+ * On Linux instances that run in environments other than the z/VM hypervisor,
+ * z/VM IUCV is not available and the z/VM IUCV Hypervisor console cannot be
+ * used.
+ * User action:
+ * If the system does not run on a z/VM guest virtual machine,
+ * ignore this message.
+ */
+
+/*?
+ * Text: "Could not create new z/VM IUCV HVC backend rc=%d.\n"
+ * Severity: Error
+ * Parameter:
+ *   @1: Return code of the operation that has failed.
+ * Description:
+ * The driver initialization has failed to allocate a new z/VM IUCV HVC
+ * back-end. A common cause might be that there are not sufficient memory
+ * available.
+ * User action:
+ * Enure that the z/VM guest virtual machine has sufficient memory.
+ */
+
+/*?
+ * Text: "Could not register iucv handler (rc=%d).\n"
+ * Severity: Error
+ * Parameter:
+ *   @1: Return code from the IUCV registration.
+ * Description:
+ * The driver initialization has failed to register its z/VM IUCV callbacks to
+ * handle z/VM IUCV connections, and sending/receiving of IUCV messages.
+ * User action:
+ * Typically there might be additional IUCV error messages at the Linux kernel
+ * startup. Check the system log files.
+ */
+
+/*?
+ * Text: "Not enough memory for driver initialization (rs=%d).\n"
+ * Severity: Error
+ * Parameter:
+ *   @1: Memory allocation has failed: 1 = kmem_cache; and 2 = mempool.
+ * Description:
+ * The z/VM IUCV Hypervisor console back-end initialization has faild, because
+ * of a general memory allocation failure.
+ * User action:
+ * Ensure that the z/VM guest virtual machine has sufficient memory.
+ * See the your Linux distributor manuals for minimum system requirements.
+ */
diff --git a/Documentation/local_ops.txt b/Documentation/local_ops.txt
index f4f8b1c6c8ba..23045b8b50f0 100644
--- a/Documentation/local_ops.txt
+++ b/Documentation/local_ops.txt
@@ -149,7 +149,7 @@ static void do_test_timer(unsigned long data)
 	int cpu;
 
 	/* Increment the counters */
-	on_each_cpu(test_each, NULL, 0, 1);
+	on_each_cpu(test_each, NULL, 1);
 	/* Read all the counters */
 	printk("Counters read from CPU %d\n", smp_processor_id());
 	for_each_online_cpu(cpu) {
diff --git a/Documentation/lockstat.txt b/Documentation/lockstat.txt
index 4ba4664ce5c3..9cb9138f7a79 100644
--- a/Documentation/lockstat.txt
+++ b/Documentation/lockstat.txt
@@ -71,35 +71,50 @@ Look at the current lock statistics:
 
 # less /proc/lock_stat
 
-01 lock_stat version 0.2
+01 lock_stat version 0.3
 02 -----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
 03                               class name    con-bounces    contentions   waittime-min   waittime-max waittime-total    acq-bounces   acquisitions   holdtime-min   holdtime-max holdtime-total
 04 -----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
 05
-06               &inode->i_data.tree_lock-W:            15          21657           0.18     1093295.30 11547131054.85             58          10415           0.16          87.51        6387.60
-07               &inode->i_data.tree_lock-R:             0              0           0.00           0.00           0.00          23302         231198           0.25           8.45       98023.38
-08               --------------------------
-09                 &inode->i_data.tree_lock              0          [<ffffffff8027c08f>] add_to_page_cache+0x5f/0x190
-10
-11 ...............................................................................................................................................................................................
-12
-13                              dcache_lock:          1037           1161           0.38          45.32         774.51           6611         243371           0.15         306.48       77387.24
-14                              -----------
-15                              dcache_lock            180          [<ffffffff802c0d7e>] sys_getcwd+0x11e/0x230
-16                              dcache_lock            165          [<ffffffff802c002a>] d_alloc+0x15a/0x210
-17                              dcache_lock             33          [<ffffffff8035818d>] _atomic_dec_and_lock+0x4d/0x70
-18                              dcache_lock              1          [<ffffffff802beef8>] shrink_dcache_parent+0x18/0x130
+06                          &mm->mmap_sem-W:           233            538 18446744073708       22924.27      607243.51           1342          45806           1.71        8595.89     1180582.34
+07                          &mm->mmap_sem-R:           205            587 18446744073708       28403.36      731975.00           1940         412426           0.58      187825.45     6307502.88
+08                          ---------------
+09                            &mm->mmap_sem            487          [<ffffffff8053491f>] do_page_fault+0x466/0x928
+10                            &mm->mmap_sem            179          [<ffffffff802a6200>] sys_mprotect+0xcd/0x21d
+11                            &mm->mmap_sem            279          [<ffffffff80210a57>] sys_mmap+0x75/0xce
+12                            &mm->mmap_sem             76          [<ffffffff802a490b>] sys_munmap+0x32/0x59
+13                          ---------------
+14                            &mm->mmap_sem            270          [<ffffffff80210a57>] sys_mmap+0x75/0xce
+15                            &mm->mmap_sem            431          [<ffffffff8053491f>] do_page_fault+0x466/0x928
+16                            &mm->mmap_sem            138          [<ffffffff802a490b>] sys_munmap+0x32/0x59
+17                            &mm->mmap_sem            145          [<ffffffff802a6200>] sys_mprotect+0xcd/0x21d
+18
+19 ...............................................................................................................................................................................................
+20
+21                              dcache_lock:           621            623           0.52         118.26        1053.02           6745          91930           0.29         316.29      118423.41
+22                              -----------
+23                              dcache_lock            179          [<ffffffff80378274>] _atomic_dec_and_lock+0x34/0x54
+24                              dcache_lock            113          [<ffffffff802cc17b>] d_alloc+0x19a/0x1eb
+25                              dcache_lock             99          [<ffffffff802ca0dc>] d_rehash+0x1b/0x44
+26                              dcache_lock            104          [<ffffffff802cbca0>] d_instantiate+0x36/0x8a
+27                              -----------
+28                              dcache_lock            192          [<ffffffff80378274>] _atomic_dec_and_lock+0x34/0x54
+29                              dcache_lock             98          [<ffffffff802ca0dc>] d_rehash+0x1b/0x44
+30                              dcache_lock             72          [<ffffffff802cc17b>] d_alloc+0x19a/0x1eb
+31                              dcache_lock            112          [<ffffffff802cbca0>] d_instantiate+0x36/0x8a
 
 This excerpt shows the first two lock class statistics. Line 01 shows the
 output version - each time the format changes this will be updated. Line 02-04
-show the header with column descriptions. Lines 05-10 and 13-18 show the actual
+show the header with column descriptions. Lines 05-18 and 20-31 show the actual
 statistics. These statistics come in two parts; the actual stats separated by a
-short separator (line 08, 14) from the contention points.
+short separator (line 08, 13) from the contention points.
 
-The first lock (05-10) is a read/write lock, and shows two lines above the
+The first lock (05-18) is a read/write lock, and shows two lines above the
 short separator. The contention points don't match the column descriptors,
-they have two: contentions and [<IP>] symbol.
+they have two: contentions and [<IP>] symbol. The second set of contention
+points are the points we're contending with.
 
+The integer part of the time values is in us.
 
 View the top contending locks:
 
diff --git a/Documentation/markers.txt b/Documentation/markers.txt
index 089f6138fcd9..6d275e4ef385 100644
--- a/Documentation/markers.txt
+++ b/Documentation/markers.txt
@@ -70,6 +70,20 @@ a printk warning which identifies the inconsistency:
 
 "Format mismatch for probe probe_name (format), marker (format)"
 
+Another way to use markers is to simply define the marker without generating any
+function call to actually call into the marker. This is useful in combination
+with tracepoint probes in a scheme like this :
+
+void probe_tracepoint_name(unsigned int arg1, struct task_struct *tsk);
+
+DEFINE_MARKER_TP(marker_eventname, tracepoint_name, probe_tracepoint_name,
+	"arg1 %u pid %d");
+
+notrace void probe_tracepoint_name(unsigned int arg1, struct task_struct *tsk)
+{
+	struct marker *marker = &GET_MARKER(kernel_irq_entry);
+	/* write data to trace buffers ... */
+}
 
 * Probe / marker example
 
diff --git a/Documentation/nmi_watchdog.txt b/Documentation/nmi_watchdog.txt
index 90aa4531cb67..bf9f80a98282 100644
--- a/Documentation/nmi_watchdog.txt
+++ b/Documentation/nmi_watchdog.txt
@@ -69,6 +69,11 @@ to the overall system performance.
 On x86 nmi_watchdog is disabled by default so you have to enable it with
 a boot time parameter.
 
+It's possible to disable the NMI watchdog in run-time by writing "0" to
+/proc/sys/kernel/nmi_watchdog. Writing "1" to the same file will re-enable
+the NMI watchdog. Notice that you still need to use "nmi_watchdog=" parameter
+at boot time.
+
 NOTE: In kernels prior to 2.4.2-ac18 the NMI-oopser is enabled unconditionally
 on x86 SMP boxes.
 
diff --git a/Documentation/scheduler/sched-arch.txt b/Documentation/scheduler/sched-arch.txt
index 941615a9769b..d43dbcbd163b 100644
--- a/Documentation/scheduler/sched-arch.txt
+++ b/Documentation/scheduler/sched-arch.txt
@@ -8,7 +8,7 @@ Context switch
 By default, the switch_to arch function is called with the runqueue
 locked. This is usually not a problem unless switch_to may need to
 take the runqueue lock. This is usually due to a wake up operation in
-the context switch. See include/asm-ia64/system.h for an example.
+the context switch. See arch/ia64/include/asm/system.h for an example.
 
 To request the scheduler call switch_to with the runqueue unlocked,
 you must `#define __ARCH_WANT_UNLOCKED_CTXSW` in a header file
@@ -23,7 +23,7 @@ disabled. Interrupts may be enabled over the call if it is likely to
 introduce a significant interrupt latency by adding the line
 `#define __ARCH_WANT_INTERRUPTS_ON_CTXSW` in the same place as for
 unlocked context switches. This define also implies
-`__ARCH_WANT_UNLOCKED_CTXSW`. See include/asm-arm/system.h for an
+`__ARCH_WANT_UNLOCKED_CTXSW`. See arch/arm/include/asm/system.h for an
 example.
 
 
diff --git a/Documentation/spi/spi-lm70llp b/Documentation/spi/spi-lm70llp
index 154bd02220b9..34a9cfd746bd 100644
--- a/Documentation/spi/spi-lm70llp
+++ b/Documentation/spi/spi-lm70llp
@@ -13,10 +13,20 @@ Description
 This driver provides glue code connecting a National Semiconductor LM70 LLP
 temperature sensor evaluation board to the kernel's SPI core subsystem.
 
+This is a SPI master controller driver. It can be used in conjunction with
+(layered under) the LM70 logical driver (a "SPI protocol driver").
 In effect, this driver turns the parallel port interface on the eval board
 into a SPI bus with a single device, which will be driven by the generic
 LM70 driver (drivers/hwmon/lm70.c).
 
+
+Hardware Interfacing
+--------------------
+The schematic for this particular board (the LM70EVAL-LLP) is
+available (on page 4) here:
+
+  http://www.national.com/appinfo/tempsensors/files/LM70LLPEVALmanual.pdf
+
 The hardware interfacing on the LM70 LLP eval board is as follows:
 
    Parallel                 LM70 LLP
diff --git a/Documentation/tracepoints.txt b/Documentation/tracepoints.txt
index 5d354e167494..2d42241a25c3 100644
--- a/Documentation/tracepoints.txt
+++ b/Documentation/tracepoints.txt
@@ -3,28 +3,30 @@
 			    Mathieu Desnoyers
 
 
-This document introduces Linux Kernel Tracepoints and their use. It provides
-examples of how to insert tracepoints in the kernel and connect probe functions
-to them and provides some examples of probe functions.
+This document introduces Linux Kernel Tracepoints and their use. It
+provides examples of how to insert tracepoints in the kernel and
+connect probe functions to them and provides some examples of probe
+functions.
 
 
 * Purpose of tracepoints
 
-A tracepoint placed in code provides a hook to call a function (probe) that you
-can provide at runtime. A tracepoint can be "on" (a probe is connected to it) or
-"off" (no probe is attached). When a tracepoint is "off" it has no effect,
-except for adding a tiny time penalty (checking a condition for a branch) and
-space penalty (adding a few bytes for the function call at the end of the
-instrumented function and adds a data structure in a separate section).  When a
-tracepoint is "on", the function you provide is called each time the tracepoint
-is executed, in the execution context of the caller. When the function provided
-ends its execution, it returns to the caller (continuing from the tracepoint
-site).
+A tracepoint placed in code provides a hook to call a function (probe)
+that you can provide at runtime. A tracepoint can be "on" (a probe is
+connected to it) or "off" (no probe is attached). When a tracepoint is
+"off" it has no effect, except for adding a tiny time penalty
+(checking a condition for a branch) and space penalty (adding a few
+bytes for the function call at the end of the instrumented function
+and adds a data structure in a separate section).  When a tracepoint
+is "on", the function you provide is called each time the tracepoint
+is executed, in the execution context of the caller. When the function
+provided ends its execution, it returns to the caller (continuing from
+the tracepoint site).
 
 You can put tracepoints at important locations in the code. They are
 lightweight hooks that can pass an arbitrary number of parameters,
-which prototypes are described in a tracepoint declaration placed in a header
-file.
+which prototypes are described in a tracepoint declaration placed in a
+header file.
 
 They can be used for tracing and performance accounting.
 
@@ -42,7 +44,7 @@ In include/trace/subsys.h :
 
 #include <linux/tracepoint.h>
 
-DEFINE_TRACE(subsys_eventname,
+DECLARE_TRACE(subsys_eventname,
 	TPPTOTO(int firstarg, struct task_struct *p),
 	TPARGS(firstarg, p));
 
@@ -50,6 +52,8 @@ In subsys/file.c (where the tracing statement must be added) :
 
 #include <trace/subsys.h>
 
+DEFINE_TRACE(subsys_eventname);
+
 void somefct(void)
 {
 	...
@@ -61,31 +65,41 @@ Where :
 - subsys_eventname is an identifier unique to your event
     - subsys is the name of your subsystem.
     - eventname is the name of the event to trace.
-- TPPTOTO(int firstarg, struct task_struct *p) is the prototype of the function
-  called by this tracepoint.
-- TPARGS(firstarg, p) are the parameters names, same as found in the prototype.
 
-Connecting a function (probe) to a tracepoint is done by providing a probe
-(function to call) for the specific tracepoint through
-register_trace_subsys_eventname().  Removing a probe is done through
-unregister_trace_subsys_eventname(); it will remove the probe sure there is no
-caller left using the probe when it returns. Probe removal is preempt-safe
-because preemption is disabled around the probe call. See the "Probe example"
-section below for a sample probe module.
-
-The tracepoint mechanism supports inserting multiple instances of the same
-tracepoint, but a single definition must be made of a given tracepoint name over
-all the kernel to make sure no type conflict will occur. Name mangling of the
-tracepoints is done using the prototypes to make sure typing is correct.
-Verification of probe type correctness is done at the registration site by the
-compiler. Tracepoints can be put in inline functions, inlined static functions,
-and unrolled loops as well as regular functions.
-
-The naming scheme "subsys_event" is suggested here as a convention intended
-to limit collisions. Tracepoint names are global to the kernel: they are
-considered as being the same whether they are in the core kernel image or in
-modules.
+- TPPTOTO(int firstarg, struct task_struct *p) is the prototype of the
+  function called by this tracepoint.
 
+- TPARGS(firstarg, p) are the parameters names, same as found in the
+  prototype.
+
+Connecting a function (probe) to a tracepoint is done by providing a
+probe (function to call) for the specific tracepoint through
+register_trace_subsys_eventname().  Removing a probe is done through
+unregister_trace_subsys_eventname(); it will remove the probe.
+
+tracepoint_synchronize_unregister() must be called before the end of
+the module exit function to make sure there is no caller left using
+the probe. This, and the fact that preemption is disabled around the
+probe call, make sure that probe removal and module unload are safe.
+See the "Probe example" section below for a sample probe module.
+
+The tracepoint mechanism supports inserting multiple instances of the
+same tracepoint, but a single definition must be made of a given
+tracepoint name over all the kernel to make sure no type conflict will
+occur. Name mangling of the tracepoints is done using the prototypes
+to make sure typing is correct. Verification of probe type correctness
+is done at the registration site by the compiler. Tracepoints can be
+put in inline functions, inlined static functions, and unrolled loops
+as well as regular functions.
+
+The naming scheme "subsys_event" is suggested here as a convention
+intended to limit collisions. Tracepoint names are global to the
+kernel: they are considered as being the same whether they are in the
+core kernel image or in modules.
+
+If the tracepoint has to be used in kernel modules, an
+EXPORT_TRACEPOINT_SYMBOL_GPL() or EXPORT_TRACEPOINT_SYMBOL() can be
+used to export the defined tracepoints.
 
 * Probe / tracepoint example
 
diff --git a/Documentation/usb/power-management.txt b/Documentation/usb/power-management.txt
index e48ea1d51010..ad642615ad4c 100644
--- a/Documentation/usb/power-management.txt
+++ b/Documentation/usb/power-management.txt
@@ -313,11 +313,13 @@ three of the methods listed above.  In addition, a driver indicates
 that it supports autosuspend by setting the .supports_autosuspend flag
 in its usb_driver structure.  It is then responsible for informing the
 USB core whenever one of its interfaces becomes busy or idle.  The
-driver does so by calling these three functions:
+driver does so by calling these five functions:
 
 	int  usb_autopm_get_interface(struct usb_interface *intf);
 	void usb_autopm_put_interface(struct usb_interface *intf);
 	int  usb_autopm_set_interface(struct usb_interface *intf);
+	int  usb_autopm_get_interface_async(struct usb_interface *intf);
+	void usb_autopm_put_interface_async(struct usb_interface *intf);
 
 The functions work by maintaining a counter in the usb_interface
 structure.  When intf->pm_usage_count is > 0 then the interface is
@@ -330,10 +332,12 @@ associated with the device itself rather than any of its interfaces.
 This field is used only by the USB core.)
 
 The driver owns intf->pm_usage_count; it can modify the value however
-and whenever it likes.  A nice aspect of the usb_autopm_* routines is
-that the changes they make are protected by the usb_device structure's
-PM mutex (udev->pm_mutex); however drivers may change pm_usage_count
-without holding the mutex.
+and whenever it likes.  A nice aspect of the non-async usb_autopm_*
+routines is that the changes they make are protected by the usb_device
+structure's PM mutex (udev->pm_mutex); however drivers may change
+pm_usage_count without holding the mutex.  Drivers using the async
+routines are responsible for their own synchronization and mutual
+exclusion.
 
 	usb_autopm_get_interface() increments pm_usage_count and
 	attempts an autoresume if the new value is > 0 and the
@@ -348,6 +352,14 @@ without holding the mutex.
 	is suspended, and it attempts an autosuspend if the value is
 	<= 0 and the device isn't suspended.
 
+	usb_autopm_get_interface_async() and
+	usb_autopm_put_interface_async() do almost the same things as
+	their non-async counterparts.  The differences are: they do
+	not acquire the PM mutex, and they use a workqueue to do their
+	jobs.  As a result they can be called in an atomic context,
+	such as an URB's completion handler, but when they return the
+	device will not generally not yet be in the desired state.
+
 There also are a couple of utility routines drivers can use:
 
 	usb_autopm_enable() sets pm_usage_cnt to 0 and then calls
diff --git a/Documentation/x86/boot.txt b/Documentation/x86/boot.txt
index 83c0033ee9e0..804d9b1a46ef 100644
--- a/Documentation/x86/boot.txt
+++ b/Documentation/x86/boot.txt
@@ -349,7 +349,7 @@ Protocol:	2.00+
 	3  SYSLINUX
 	4  EtherBoot
 	5  ELILO
-	7  GRuB
+	7  GRUB
 	8  U-BOOT
 	9  Xen
 	A  Gujin
diff --git a/Documentation/x86/x86_64/boot-options.txt b/Documentation/x86/x86_64/boot-options.txt
index f6d561a1a9b2..34c13040a718 100644
--- a/Documentation/x86/x86_64/boot-options.txt
+++ b/Documentation/x86/x86_64/boot-options.txt
@@ -79,17 +79,6 @@ Timing
   Report when timer interrupts are lost because some code turned off
   interrupts for too long.
 
-  nmi_watchdog=NUMBER[,panic]
-  NUMBER can be:
-  0 don't use an NMI watchdog
-  1 use the IO-APIC timer for the NMI watchdog
-  2 use the local APIC for the NMI watchdog using a performance counter. Note
-  This will use one performance counter and the local APIC's performance
-  vector.
-  When panic is specified panic when an NMI watchdog timeout occurs.
-  This is useful when you use a panic=... timeout and need the box
-  quickly up again.
-
   nohpet
   Don't use the HPET timer.
 
diff --git a/Documentation/x86/x86_64/mm.txt b/Documentation/x86/x86_64/mm.txt
index efce75097369..29b52b14d0b4 100644
--- a/Documentation/x86/x86_64/mm.txt
+++ b/Documentation/x86/x86_64/mm.txt
@@ -6,7 +6,7 @@ Virtual memory map with 4 level page tables:
 0000000000000000 - 00007fffffffffff (=47 bits) user space, different per mm
 hole caused by [48:63] sign extension
 ffff800000000000 - ffff80ffffffffff (=40 bits) guard hole
-ffff810000000000 - ffffc0ffffffffff (=46 bits) direct mapping of all phys. memory
+ffff880000000000 - ffffc0ffffffffff (=57 TB) direct mapping of all phys. memory
 ffffc10000000000 - ffffc1ffffffffff (=40 bits) hole
 ffffc20000000000 - ffffe1ffffffffff (=45 bits) vmalloc/ioremap space
 ffffe20000000000 - ffffe2ffffffffff (=40 bits) virtual memory map (1TB)
diff --git a/MAINTAINERS b/MAINTAINERS
index 8f2b67ea0549..f79a60e79c51 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -2979,6 +2979,7 @@ MUSB MULTIPOINT HIGH SPEED DUAL-ROLE CONTROLLER
 P:	Felipe Balbi
 M:	felipe.balbi@nokia.com
 L:	linux-usb@vger.kernel.org
+T:	git gitorious.org:/musb/mainline.git
 S:	Maintained
 
 MYRICOM MYRI-10G 10GbE DRIVER (MYRI10GE)
@@ -3759,6 +3760,15 @@ M:	drzeus-sdhci@drzeus.cx
 L:	sdhci-devel@list.drzeus.cx
 S:	Maintained
 
+SECURITY SUBSYSTEM
+F:	security/
+P:	James Morris
+M:	jmorris@namei.org
+L:	linux-kernel@vger.kernel.org
+L:	linux-security-module@vger.kernel.org (suggested Cc:)
+T:	git kernel.org:pub/scm/linux/kernel/git/jmorris/security-testing-2.6.git
+S:	Supported
+
 SECURITY CONTACT
 P:	Security Officers
 M:	security@kernel.org
diff --git a/Makefile b/Makefile
index 9a49960f7aad..3af8595520cc 100644
--- a/Makefile
+++ b/Makefile
@@ -205,13 +205,14 @@ ifeq ($(ARCH),x86_64)
         SRCARCH := x86
 endif
 
-# Where to locate arch specific headers
+# Additional ARCH settings for sparc
 ifeq ($(ARCH),sparc64)
-       hdr-arch  := sparc
-else
-       hdr-arch  := $(SRCARCH)
+       SRCARCH := sparc
 endif
 
+# Where to locate arch specific headers
+hdr-arch  := $(SRCARCH)
+
 KCONFIG_CONFIG	?= .config
 
 # SHELL used by kbuild
@@ -336,7 +337,7 @@ LINUXINCLUDE    := -Iinclude \
                    -I$(srctree)/arch/$(hdr-arch)/include               \
                    -include include/linux/autoconf.h
 
-KBUILD_CPPFLAGS := -D__KERNEL__ $(LINUXINCLUDE)
+KBUILD_CPPFLAGS := -D__KERNEL__
 
 KBUILD_CFLAGS   := -Wall -Wundef -Wstrict-prototypes -Wno-trigraphs \
 		   -fno-strict-aliasing -fno-common \
@@ -926,7 +927,7 @@ PHONY += prepare archprepare prepare0 prepare1 prepare2 prepare3
 # 2) Create the include2 directory, used for the second asm symlink
 prepare3: include/config/kernel.release
 ifneq ($(KBUILD_SRC),)
-	@echo '  Using $(srctree) as source for kernel'
+	@$(kecho) '  Using $(srctree) as source for kernel'
 	$(Q)if [ -f $(srctree)/.config -o -d $(srctree)/include/config ]; then \
 		echo "  $(srctree) is not clean, please run 'make mrproper'";\
 		echo "  in the '$(srctree)' directory.";\
@@ -983,7 +984,7 @@ endef
 # directory for generated filesas used by some architectures.
 define create-symlink
 	if [ ! -L include/asm ]; then                                      \
-			echo '  SYMLINK $@ -> include/asm-$(SRCARCH)';     \
+			$(kecho) '  SYMLINK $@ -> include/asm-$(SRCARCH)'; \
 			if [ ! -d include/asm-$(SRCARCH) ]; then           \
 				mkdir -p include/asm-$(SRCARCH);           \
 			fi;                                                \
@@ -1096,7 +1097,7 @@ all: modules
 PHONY += modules
 modules: $(vmlinux-dirs) $(if $(KBUILD_BUILTIN),vmlinux)
 	$(Q)$(AWK) '!x[$$0]++' $(vmlinux-dirs:%=$(objtree)/%/modules.order) > $(objtree)/modules.order
-	@echo '  Building modules, stage 2.';
+	@$(kecho) '  Building modules, stage 2.';
 	$(Q)$(MAKE) -f $(srctree)/scripts/Makefile.modpost
 	$(Q)$(MAKE) -f $(srctree)/scripts/Makefile.fwinst obj=firmware __fw_modbuild
 
@@ -1360,7 +1361,7 @@ $(module-dirs): crmodverdir $(objtree)/Module.symvers
 	$(Q)$(MAKE) $(build)=$(patsubst _module_%,%,$@)
 
 modules: $(module-dirs)
-	@echo '  Building modules, stage 2.';
+	@$(kecho) '  Building modules, stage 2.';
 	$(Q)$(MAKE) -f $(srctree)/scripts/Makefile.modpost
 
 PHONY += modules_install
@@ -1409,123 +1410,12 @@ endif # KBUILD_EXTMOD
 
 # Generate tags for editors
 # ---------------------------------------------------------------------------
+quiet_cmd_tags = GEN     $@
+      cmd_tags = $(CONFIG_SHELL) $(srctree)/scripts/tags.sh $@
 
-#We want __srctree to totally vanish out when KBUILD_OUTPUT is not set
-#(which is the most common case IMHO) to avoid unneeded clutter in the big tags file.
-#Adding $(srctree) adds about 20M on i386 to the size of the output file!
-
-ifeq ($(src),$(obj))
-__srctree =
-else
-__srctree = $(srctree)/
-endif
-
-ifeq ($(ALLSOURCE_ARCHS),)
-ifeq ($(ARCH),um)
-ALLINCLUDE_ARCHS := $(ARCH) $(SUBARCH)
-else
-ALLINCLUDE_ARCHS := $(SRCARCH)
-endif
-else
-#Allow user to specify only ALLSOURCE_PATHS on the command line, keeping existing behaviour.
-ALLINCLUDE_ARCHS := $(ALLSOURCE_ARCHS)
-endif
-
-ALLSOURCE_ARCHS := $(SRCARCH)
-
-define find-sources
-        ( for arch in $(ALLSOURCE_ARCHS) ; do \
-	       find $(__srctree)arch/$${arch} $(RCS_FIND_IGNORE) \
-		    -wholename $(__srctree)arch/$${arch}/include/asm -type d -prune \
-	            -o -name $1 -print; \
-	  done ; \
-	  find $(__srctree)security/selinux/include $(RCS_FIND_IGNORE) \
-	       -name $1 -print; \
-	  find $(__srctree)include $(RCS_FIND_IGNORE) \
-	       \( -name config -o -name 'asm-*' \) -prune \
-	       -o -name $1 -print; \
-	  for arch in $(ALLINCLUDE_ARCHS) ; do \
-	       test -e $(__srctree)include/asm-$${arch} && \
-                 find $(__srctree)include/asm-$${arch} $(RCS_FIND_IGNORE) \
-	            -name $1 -print; \
-	       test -e $(__srctree)arch/$${arch}/include/asm && \
-	         find $(__srctree)arch/$${arch}/include/asm $(RCS_FIND_IGNORE) \
-	            -name $1 -print; \
-	  done ; \
-	  find $(__srctree)include/asm-generic $(RCS_FIND_IGNORE) \
-	       -name $1 -print; \
-	  find $(__srctree) $(RCS_FIND_IGNORE) \
-	       \( -name include -o -name arch -o -name '.tmp_*' \) -prune -o \
-	       -name $1 -print; \
-	  )
-endef
-
-define all-sources
-	$(call find-sources,'*.[chS]')
-endef
-define all-kconfigs
-	$(call find-sources,'Kconfig*')
-endef
-define all-defconfigs
-	$(call find-sources,'defconfig')
-endef
-
-define xtags
-	if $1 --version 2>&1 | grep -iq exuberant; then \
-	    $(all-sources) | xargs $1 -a \
-		-I __initdata,__exitdata,__acquires,__releases \
-		-I __read_mostly,____cacheline_aligned,____cacheline_aligned_in_smp,____cacheline_internodealigned_in_smp \
-		-I EXPORT_SYMBOL,EXPORT_SYMBOL_GPL \
-		--extra=+f --c-kinds=+px \
-		--regex-asm='/^ENTRY\(([^)]*)\).*/\1/'; \
-	    $(all-kconfigs) | xargs $1 -a \
-		--langdef=kconfig \
-		--language-force=kconfig \
-		--regex-kconfig='/^[[:blank:]]*(menu|)config[[:blank:]]+([[:alnum:]_]+)/\2/'; \
-	    $(all-defconfigs) | xargs -r $1 -a \
-		--langdef=dotconfig \
-		--language-force=dotconfig \
-		--regex-dotconfig='/^#?[[:blank:]]*(CONFIG_[[:alnum:]_]+)/\1/'; \
-	elif $1 --version 2>&1 | grep -iq emacs; then \
-	    $(all-sources) | xargs $1 -a; \
-	    $(all-kconfigs) | xargs $1 -a \
-		--regex='/^[ \t]*\(\(menu\)*config\)[ \t]+\([a-zA-Z0-9_]+\)/\3/'; \
-	    $(all-defconfigs) | xargs -r $1 -a \
-		--regex='/^#?[ \t]?\(CONFIG_[a-zA-Z0-9_]+\)/\1/'; \
-	else \
-	    $(all-sources) | xargs $1 -a; \
-	fi
-endef
-
-quiet_cmd_cscope-file = FILELST cscope.files
-      cmd_cscope-file = (echo \-k; echo \-q; $(all-sources)) > cscope.files
-
-quiet_cmd_cscope = MAKE    cscope.out
-      cmd_cscope = cscope -b -f cscope.out
-
-cscope: FORCE
-	$(call cmd,cscope-file)
-	$(call cmd,cscope)
-
-quiet_cmd_TAGS = MAKE   $@
-define cmd_TAGS
-	rm -f $@; \
-	$(call xtags,etags)
-endef
-
-TAGS: FORCE
-	$(call cmd,TAGS)
-
-quiet_cmd_tags = MAKE   $@
-define cmd_tags
-	rm -f $@; \
-	$(call xtags,ctags)
-endef
-
-tags: FORCE
+tags TAGS cscope: FORCE
 	$(call cmd,tags)
 
-
 # Scripts to check various things for consistency
 # ---------------------------------------------------------------------------
 
@@ -1638,7 +1528,7 @@ cmd_crmodverdir = $(Q)mkdir -p $(MODVERDIR) \
                   $(if $(KBUILD_MODULES),; rm -f $(MODVERDIR)/*)
 
 a_flags = -Wp,-MD,$(depfile) $(KBUILD_AFLAGS) $(AFLAGS_KERNEL) \
-	  $(NOSTDINC_FLAGS) $(KBUILD_CPPFLAGS) \
+	  $(NOSTDINC_FLAGS) $(LINUXINCLUDE) $(KBUILD_CPPFLAGS) \
 	  $(modkern_aflags) $(EXTRA_AFLAGS) $(AFLAGS_$(basetarget).o)
 
 quiet_cmd_as_o_S = AS      $@
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 9722f8bb506c..4546f8b2ce8c 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -201,6 +201,7 @@ choice
 
 config ARCH_AAEC2000
 	bool "Agilent AAEC-2000 based"
+	select CPU_ARM920T
 	select ARM_AMBA
 	select HAVE_CLK
 	help
@@ -210,6 +211,7 @@ config ARCH_INTEGRATOR
 	bool "ARM Ltd. Integrator family"
 	select ARM_AMBA
 	select HAVE_CLK
+	select COMMON_CLKDEV
 	select ICST525
 	help
 	  Support for ARM's Integrator platform.
@@ -218,6 +220,7 @@ config ARCH_REALVIEW
 	bool "ARM Ltd. RealView family"
 	select ARM_AMBA
 	select HAVE_CLK
+	select COMMON_CLKDEV
 	select ICST307
 	select GENERIC_TIME
 	select GENERIC_CLOCKEVENTS
@@ -229,6 +232,7 @@ config ARCH_VERSATILE
 	select ARM_AMBA
 	select ARM_VIC
 	select HAVE_CLK
+	select COMMON_CLKDEV
 	select ICST307
 	select GENERIC_TIME
 	select GENERIC_CLOCKEVENTS
@@ -243,22 +247,15 @@ config ARCH_AT91
 	  This enables support for systems based on the Atmel AT91RM9200,
 	  AT91SAM9 and AT91CAP9 processors.
 
-config ARCH_CLPS7500
-	bool "Cirrus CL-PS7500FE"
-	select TIMER_ACORN
-	select ISA
-	select NO_IOPORT
-	select ARCH_SPARSEMEM_ENABLE
-	help
-	  Support for the Cirrus Logic PS7500FE system-on-a-chip.
-
 config ARCH_CLPS711X
 	bool "Cirrus Logic CLPS711x/EP721x-based"
+	select CPU_ARM720T
 	help
 	  Support for Cirrus Logic 711x/721x based boards.
 
 config ARCH_EBSA110
 	bool "EBSA-110"
+	select CPU_SA110
 	select ISA
 	select NO_IOPORT
 	help
@@ -269,16 +266,19 @@ config ARCH_EBSA110
 
 config ARCH_EP93XX
 	bool "EP93xx-based"
+	select CPU_ARM920T
 	select ARM_AMBA
 	select ARM_VIC
 	select GENERIC_GPIO
 	select HAVE_CLK
+	select COMMON_CLKDEV
 	select ARCH_REQUIRE_GPIOLIB
 	help
 	  This enables support for the Cirrus EP93xx series of CPUs.
 
 config ARCH_FOOTBRIDGE
 	bool "FootBridge"
+	select CPU_SA110
 	select FOOTBRIDGE
 	help
 	  Support for systems based on the DC21285 companion chip
@@ -286,18 +286,21 @@ config ARCH_FOOTBRIDGE
 
 config ARCH_NETX
 	bool "Hilscher NetX based"
+	select CPU_ARM926T
 	select ARM_VIC
 	help
 	  This enables support for systems based on the Hilscher NetX Soc
 
 config ARCH_H720X
 	bool "Hynix HMS720x-based"
+	select CPU_ARM720T
 	select ISA_DMA_API
 	help
 	  This enables support for systems based on the Hynix HMS720x
 
 config ARCH_IMX
 	bool "IMX"
+	select CPU_ARM920T
 	select GENERIC_GPIO
 	select GENERIC_TIME
 	select GENERIC_CLOCKEVENTS
@@ -307,6 +310,7 @@ config ARCH_IMX
 config ARCH_IOP13XX
 	bool "IOP13xx-based"
 	depends on MMU
+	select CPU_XSC3
 	select PLAT_IOP
 	select PCI
 	select ARCH_SUPPORTS_MSI
@@ -317,6 +321,7 @@ config ARCH_IOP13XX
 config ARCH_IOP32X
 	bool "IOP32x-based"
 	depends on MMU
+	select CPU_XSCALE
 	select PLAT_IOP
 	select PCI
 	select GENERIC_GPIO
@@ -328,6 +333,7 @@ config ARCH_IOP32X
 config ARCH_IOP33X
 	bool "IOP33x-based"
 	depends on MMU
+	select CPU_XSCALE
 	select PLAT_IOP
 	select PCI
 	select GENERIC_GPIO
@@ -338,6 +344,7 @@ config ARCH_IOP33X
 config ARCH_IXP23XX
  	bool "IXP23XX-based"
 	depends on MMU
+	select CPU_XSC3
  	select PCI
 	help
 	  Support for Intel's IXP23xx (XScale) family of processors.
@@ -345,6 +352,7 @@ config ARCH_IXP23XX
 config ARCH_IXP2000
 	bool "IXP2400/2800-based"
 	depends on MMU
+	select CPU_XSCALE
 	select PCI
 	help
 	  Support for Intel's IXP2400/2800 (XScale) family of processors.
@@ -352,6 +360,7 @@ config ARCH_IXP2000
 config ARCH_IXP4XX
 	bool "IXP4xx-based"
 	depends on MMU
+	select CPU_XSCALE
 	select GENERIC_GPIO
 	select GENERIC_TIME
 	select GENERIC_CLOCKEVENTS
@@ -361,6 +370,7 @@ config ARCH_IXP4XX
 
 config ARCH_L7200
 	bool "LinkUp-L7200"
+	select CPU_ARM720T
 	select FIQ
 	help
 	  Say Y here if you intend to run this kernel on a LinkUp Systems
@@ -374,6 +384,7 @@ config ARCH_L7200
 
 config ARCH_KIRKWOOD
 	bool "Marvell Kirkwood"
+	select CPU_FEROCEON
 	select PCI
 	select GENERIC_TIME
 	select GENERIC_CLOCKEVENTS
@@ -384,6 +395,7 @@ config ARCH_KIRKWOOD
 
 config ARCH_KS8695
 	bool "Micrel/Kendin KS8695"
+	select CPU_ARM922T
 	select GENERIC_GPIO
 	help
 	  Support for Micrel/Kendin KS8695 "Centaur" (ARM922T) based
@@ -391,6 +403,7 @@ config ARCH_KS8695
 
 config ARCH_NS9XXX
 	bool "NetSilicon NS9xxx"
+	select CPU_ARM926T
 	select GENERIC_GPIO
 	select GENERIC_TIME
 	select GENERIC_CLOCKEVENTS
@@ -403,6 +416,7 @@ config ARCH_NS9XXX
 
 config ARCH_LOKI
 	bool "Marvell Loki (88RC8480)"
+	select CPU_FEROCEON
 	select GENERIC_TIME
 	select GENERIC_CLOCKEVENTS
 	select PLAT_ORION
@@ -411,6 +425,7 @@ config ARCH_LOKI
 
 config ARCH_MV78XX0
 	bool "Marvell MV78xx0"
+	select CPU_FEROCEON
 	select PCI
 	select GENERIC_TIME
 	select GENERIC_CLOCKEVENTS
@@ -432,6 +447,7 @@ config ARCH_MXC
 config ARCH_ORION5X
 	bool "Marvell Orion"
 	depends on MMU
+	select CPU_FEROCEON
 	select PCI
 	select GENERIC_GPIO
 	select GENERIC_TIME
@@ -444,6 +460,7 @@ config ARCH_ORION5X
 
 config ARCH_PNX4008
 	bool "Philips Nexperia PNX4008 Mobile"
+	select CPU_ARM926T
 	select HAVE_CLK
 	help
 	  This enables support for Philips PNX4008 mobile platform.
@@ -454,6 +471,7 @@ config ARCH_PXA
 	select ARCH_MTD_XIP
 	select GENERIC_GPIO
 	select HAVE_CLK
+	select COMMON_CLKDEV
 	select ARCH_REQUIRE_GPIOLIB
 	select GENERIC_TIME
 	select GENERIC_CLOCKEVENTS
@@ -477,6 +495,7 @@ config ARCH_RPC
 
 config ARCH_SA1100
 	bool "SA1100-based"
+	select CPU_SA1100
 	select ISA
 	select ARCH_SPARSEMEM_ENABLE
 	select ARCH_MTD_XIP
@@ -500,6 +519,7 @@ config ARCH_S3C2410
 
 config ARCH_SHARK
 	bool "Shark"
+	select CPU_SA110
 	select ISA
 	select ISA_DMA
 	select ZONE_DMA
@@ -510,6 +530,7 @@ config ARCH_SHARK
 
 config ARCH_LH7A40X
 	bool "Sharp LH7A40X"
+	select CPU_ARM922T
 	select ARCH_DISCONTIGMEM_ENABLE if !LH7A40X_CONTIGMEM
 	select ARCH_SPARSEMEM_ENABLE if !LH7A40X_CONTIGMEM
 	help
@@ -520,6 +541,7 @@ config ARCH_LH7A40X
 
 config ARCH_DAVINCI
 	bool "TI DaVinci"
+	select CPU_ARM926T
 	select GENERIC_TIME
 	select GENERIC_CLOCKEVENTS
 	select GENERIC_GPIO
@@ -541,6 +563,7 @@ config ARCH_OMAP
 
 config ARCH_MSM
 	bool "Qualcomm MSM"
+	select CPU_V6
 	select GENERIC_TIME
 	select GENERIC_CLOCKEVENTS
 	help
@@ -549,6 +572,13 @@ config ARCH_MSM
 	  interface to the ARM9 modem processor which runs the baseband stack
 	  and controls some vital subsystems (clock and power control, etc).
 
+config ARCH_W90X900
+	bool "Nuvoton W90X900 CPU"
+	select CPU_ARM926T
+	help
+		Support for Nuvoton (Winbond logic dept.) ARM9 processor,You
+		can login www.mcuos.com or www.nuvoton.com to know more.
+
 endchoice
 
 source "arch/arm/mach-clps711x/Kconfig"
@@ -627,6 +657,8 @@ source "arch/arm/mach-ks8695/Kconfig"
 
 source "arch/arm/mach-msm/Kconfig"
 
+source "arch/arm/mach-w90x900/Kconfig"
+
 # Definitions to make life easier
 config ARCH_ACORN
 	bool
@@ -781,7 +813,7 @@ config HOTPLUG_CPU
 
 config LOCAL_TIMERS
 	bool "Use local timer interrupts"
-	depends on SMP && (REALVIEW_EB_ARM11MP || MACH_REALVIEW_PB11MP)
+	depends on SMP && (REALVIEW_EB_ARM11MP || MACH_REALVIEW_PB11MP || REALVIEW_EB_A9MP)
 	default y
 	help
 	  Enable support for local timers on SMP platforms, rather then the
diff --git a/arch/arm/Makefile b/arch/arm/Makefile
index bd6e28115ebb..69d3038b35e3 100644
--- a/arch/arm/Makefile
+++ b/arch/arm/Makefile
@@ -96,7 +96,6 @@ textofs-y	:= 0x00008000
 
  machine-$(CONFIG_ARCH_RPC)	   := rpc
  machine-$(CONFIG_ARCH_EBSA110)	   := ebsa110
- machine-$(CONFIG_ARCH_CLPS7500)   := clps7500
  machine-$(CONFIG_FOOTBRIDGE)	   := footbridge
  machine-$(CONFIG_ARCH_SHARK)	   := shark
  machine-$(CONFIG_ARCH_SA1100)	   := sa1100
@@ -144,6 +143,7 @@ endif
  machine-$(CONFIG_ARCH_MSM)	   := msm
  machine-$(CONFIG_ARCH_LOKI)       := loki
  machine-$(CONFIG_ARCH_MV78XX0)    := mv78xx0
+ machine-$(CONFIG_ARCH_W90X900)    := w90x900
 
 ifeq ($(CONFIG_ARCH_EBSA110),y)
 # This is what happens if you forget the IOCS16 line.
diff --git a/arch/arm/boot/compressed/Makefile b/arch/arm/boot/compressed/Makefile
index c47f2a3f8f8f..fbe5eef1f6c9 100644
--- a/arch/arm/boot/compressed/Makefile
+++ b/arch/arm/boot/compressed/Makefile
@@ -23,10 +23,6 @@ ifeq ($(CONFIG_ARCH_L7200),y)
 OBJS		+= head-l7200.o
 endif
 
-ifeq ($(CONFIG_ARCH_CLPS7500),y)
-HEAD		= head-clps7500.o
-endif
-
 ifeq ($(CONFIG_ARCH_P720T),y)
 # Borrow this code from SA1100
 OBJS		+= head-sa1100.o
diff --git a/arch/arm/boot/compressed/head-clps7500.S b/arch/arm/boot/compressed/head-clps7500.S
deleted file mode 100644
index 4f3c78ac30a0..000000000000
--- a/arch/arm/boot/compressed/head-clps7500.S
+++ /dev/null
@@ -1,86 +0,0 @@
-/*
- * linux/arch/arm/boot/compressed/head-clps7500.S
- *
- * Copyright (C) 1999, 2000, 2001 Nexus Electronics Ltd
- */
-
-
-		/* There are three different ways the kernel can be
-		   booted on a 7500 system: from Angel (loaded in RAM), from
-		   16-bit ROM or from 32-bit Flash.  Luckily, a single kernel
-		   image does for them all. */
-		/* This branch is taken if the CPU memory width matches the
-		   actual device in use.  The default at power on is 16 bits
-		   so we must be prepared for a mismatch. */
-		.section ".start", "ax"
-2:
-		b	1f
-		.word	0xffff
-		.word	0xb632		@ mov r11, #0x03200000
-		.word	0xe3a0
-		.word	0x0000		@ mov r0, #0
-		.word	0xe3a0
-		.word	0x0080		@ strb r0, [r11, #0x80]
-		.word	0xe5cb
-		.word	0xf000		@ mov pc, #0
-		.word	0xe3a0
-1:
-		adr	r1, 2b
-		teq	r1, #0
-		bne	.Langel
-		/* This is a direct-from-ROM boot.  Copy the kernel into 
-		   RAM and run it there. */
-		mov	r0, #0x30
-		mcr	p15, 0, r0, c1, c0, 0
-		mov	r0, #0x13
-		msr	cpsr_cxsf, r0
-		mov	r12, #0x03000000	@ point to LEDs
-		orr	r12, r12, #0x00020000
-		orr	r12, r12, #0xba00
-		mov	r0, #0x5500
-		str	r0, [r12]
-		mov	r0, #0x10000000
-		orr	r0, r0, #0x8000
-		mov	r4, r0
-		ldr	r2, =_end
-2:
-		ldr	r3, [r1], #4
-		str	r3, [r0], #4
-		teq	r0, r2
-		bne	2b
-		mov	r0, #0xff00
-		str	r0, [r12]
-1:	
-		mov	r12, #0x03000000	@ point to LEDs
-		orr	r12, r12, #0x00020000
-		orr	r12, r12, #0xba00
-		mov	r0, #0xfe00
-		str	r0, [r12]
-
-		adr	lr, 1f
-		mov	r0, #0
-		mov	r1, #14		/* MACH_TYPE_CLPS7500 */
-		mov	pc, lr
-.Langel:
-#ifdef CONFIG_ANGELBOOT
-		/* Call Angel to switch into SVC mode. */
-		mov	r0, #0x17
-		swi	0x123456
-#endif
-		/* Ensure all interrupts are off and MMU disabled */
-		mrs	r0, cpsr
-		orr	r0, r0, #0xc0
-		msr	cpsr_cxsf, r0
-
-		adr	lr, 1b
-		orr	lr, lr, #0x10000000
-		mov	r0, #0x30		@ MMU off
-		mcr	p15, 0, r0, c1, c0, 0
-		mov	r0, r0
-	 	mov	pc, lr
-
-		.ltorg
-
-1:
-/* And the rest */
-#include "head.S"
diff --git a/arch/arm/boot/compressed/head.S b/arch/arm/boot/compressed/head.S
index 84a1e0496a3c..77d614232d81 100644
--- a/arch/arm/boot/compressed/head.S
+++ b/arch/arm/boot/compressed/head.S
@@ -624,6 +624,12 @@ proc_types:
 		b	__armv4_mmu_cache_off
 		b	__armv4_mmu_cache_flush
 
+		.word	0x56056930
+		.word	0xff0ffff0		@ PXA935
+		b	__armv4_mmu_cache_on
+		b	__armv4_mmu_cache_off
+		b	__armv4_mmu_cache_flush
+
 		.word	0x56050000		@ Feroceon
 		.word	0xff0f0000
 		b	__armv4_mmu_cache_on
@@ -717,6 +723,9 @@ __armv7_mmu_cache_off:
 		bl	__armv7_mmu_cache_flush
 		mov	r0, #0
 		mcr	p15, 0, r0, c8, c7, 0	@ invalidate whole TLB
+		mcr	p15, 0, r0, c7, c5, 6	@ invalidate BTC
+		mcr	p15, 0, r0, c7, c10, 4	@ DSB
+		mcr	p15, 0, r0, c7, c5, 4	@ ISB
 		mov	pc, r12
 
 __arm6_mmu_cache_off:
@@ -778,12 +787,13 @@ __armv6_mmu_cache_flush:
 __armv7_mmu_cache_flush:
 		mrc	p15, 0, r10, c0, c1, 5	@ read ID_MMFR1
 		tst	r10, #0xf << 16		@ hierarchical cache (ARMv7)
-		beq	hierarchical
 		mov	r10, #0
+		beq	hierarchical
 		mcr	p15, 0, r10, c7, c14, 0	@ clean+invalidate D
 		b	iflush
 hierarchical:
-		stmfd	sp!, {r0-r5, r7, r9-r11}
+		mcr	p15, 0, r10, c7, c10, 5	@ DMB
+		stmfd	sp!, {r0-r5, r7, r9, r11}
 		mrc	p15, 1, r0, c0, c0, 1	@ read clidr
 		ands	r3, r0, #0x7000000	@ extract loc from clidr
 		mov	r3, r3, lsr #23		@ left align loc bit field
@@ -820,12 +830,14 @@ skip:
 		cmp	r3, r10
 		bgt	loop1
 finished:
+		ldmfd	sp!, {r0-r5, r7, r9, r11}
 		mov	r10, #0			@ swith back to cache level 0
 		mcr	p15, 2, r10, c0, c0, 0	@ select current cache level in cssr
-		ldmfd	sp!, {r0-r5, r7, r9-r11}
 iflush:
+		mcr	p15, 0, r10, c7, c10, 4	@ DSB
 		mcr	p15, 0, r10, c7, c5, 0	@ invalidate I+BTB
-		mcr	p15, 0, r10, c7, c10, 4	@ drain WB
+		mcr	p15, 0, r10, c7, c10, 4	@ DSB
+		mcr	p15, 0, r10, c7, c5, 4	@ ISB
 		mov	pc, lr
 
 __armv5tej_mmu_cache_flush:
diff --git a/arch/arm/boot/compressed/misc.c b/arch/arm/boot/compressed/misc.c
index 65ce8fff29db..3fc08413fff0 100644
--- a/arch/arm/boot/compressed/misc.c
+++ b/arch/arm/boot/compressed/misc.c
@@ -86,6 +86,8 @@ static void putstr(const char *ptr)
 
 #define __ptr_t void *
 
+#define memzero(s,n) __memzero(s,n)
+
 /*
  * Optimised C version of memzero for the ARM.
  */
diff --git a/arch/arm/common/Kconfig b/arch/arm/common/Kconfig
index 86b5e6982660..a2cd9beaf37d 100644
--- a/arch/arm/common/Kconfig
+++ b/arch/arm/common/Kconfig
@@ -33,3 +33,6 @@ config SHARPSL_PM
 
 config SHARP_SCOOP
 	bool
+
+config COMMON_CLKDEV
+	bool
diff --git a/arch/arm/common/Makefile b/arch/arm/common/Makefile
index 325e4b6a6afb..7cb7961d81cb 100644
--- a/arch/arm/common/Makefile
+++ b/arch/arm/common/Makefile
@@ -17,3 +17,4 @@ obj-$(CONFIG_SHARP_SCOOP)	+= scoop.o
 obj-$(CONFIG_ARCH_IXP2000)	+= uengine.o
 obj-$(CONFIG_ARCH_IXP23XX)	+= uengine.o
 obj-$(CONFIG_PCI_HOST_ITE8152)  += it8152.o
+obj-$(CONFIG_COMMON_CLKDEV)	+= clkdev.o
diff --git a/arch/arm/common/clkdev.c b/arch/arm/common/clkdev.c
new file mode 100644
index 000000000000..17a17b49a45b
--- /dev/null
+++ b/arch/arm/common/clkdev.c
@@ -0,0 +1,128 @@
+/*
+ *  arch/arm/common/clkdev.c
+ *
+ *  Copyright (C) 2008 Russell King.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Helper for the clk API to assist looking up a struct clk.
+ */
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/device.h>
+#include <linux/list.h>
+#include <linux/errno.h>
+#include <linux/err.h>
+#include <linux/string.h>
+#include <linux/mutex.h>
+
+#include <asm/clkdev.h>
+#include <mach/clkdev.h>
+
+static LIST_HEAD(clocks);
+static DEFINE_MUTEX(clocks_mutex);
+
+static struct clk *clk_find(const char *dev_id, const char *con_id)
+{
+	struct clk_lookup *p;
+	struct clk *clk = NULL;
+	int match, best = 0;
+
+	list_for_each_entry(p, &clocks, node) {
+		if ((p->dev_id && !dev_id) || (p->con_id && !con_id))
+			continue;
+		match = 0;
+		if (p->dev_id)
+			match += 2 * (strcmp(p->dev_id, dev_id) == 0);
+		if (p->con_id)
+			match += 1 * (strcmp(p->con_id, con_id) == 0);
+		if (match == 0)
+			continue;
+
+		if (match > best) {
+			clk = p->clk;
+			best = match;
+		}
+	}
+	return clk;
+}
+
+struct clk *clk_get(struct device *dev, const char *con_id)
+{
+	const char *dev_id = dev ? dev_name(dev) : NULL;
+	struct clk *clk;
+
+	mutex_lock(&clocks_mutex);
+	clk = clk_find(dev_id, con_id);
+	if (clk && !__clk_get(clk))
+		clk = NULL;
+	mutex_unlock(&clocks_mutex);
+
+	return clk ? clk : ERR_PTR(-ENOENT);
+}
+EXPORT_SYMBOL(clk_get);
+
+void clk_put(struct clk *clk)
+{
+	__clk_put(clk);
+}
+EXPORT_SYMBOL(clk_put);
+
+void clkdev_add(struct clk_lookup *cl)
+{
+	mutex_lock(&clocks_mutex);
+	list_add_tail(&cl->node, &clocks);
+	mutex_unlock(&clocks_mutex);
+}
+EXPORT_SYMBOL(clkdev_add);
+
+#define MAX_DEV_ID	20
+#define MAX_CON_ID	16
+
+struct clk_lookup_alloc {
+	struct clk_lookup cl;
+	char	dev_id[MAX_DEV_ID];
+	char	con_id[MAX_CON_ID];
+};
+
+struct clk_lookup *clkdev_alloc(struct clk *clk, const char *con_id,
+	const char *dev_fmt, ...)
+{
+	struct clk_lookup_alloc *cla;
+
+	cla = kzalloc(sizeof(*cla), GFP_KERNEL);
+	if (!cla)
+		return NULL;
+
+	cla->cl.clk = clk;
+	if (con_id) {
+		strlcpy(cla->con_id, con_id, sizeof(cla->con_id));
+		cla->cl.con_id = cla->con_id;
+	}
+
+	if (dev_fmt) {
+		va_list ap;
+
+		va_start(ap, dev_fmt);
+		vscnprintf(cla->dev_id, sizeof(cla->dev_id), dev_fmt, ap);
+		cla->cl.dev_id = cla->dev_id;
+		va_end(ap);
+	}
+
+	return &cla->cl;
+}
+EXPORT_SYMBOL(clkdev_alloc);
+
+/*
+ * clkdev_drop - remove a clock dynamically allocated
+ */
+void clkdev_drop(struct clk_lookup *cl)
+{
+	mutex_lock(&clocks_mutex);
+	list_del(&cl->node);
+	mutex_unlock(&clocks_mutex);
+	kfree(cl);
+}
+EXPORT_SYMBOL(clkdev_drop);
diff --git a/arch/arm/common/locomo.c b/arch/arm/common/locomo.c
index 7c6b4b99a2df..2293f0ce061e 100644
--- a/arch/arm/common/locomo.c
+++ b/arch/arm/common/locomo.c
@@ -1108,6 +1108,7 @@ void locomo_frontlight_set(struct locomo_dev *dev, int duty, int vr, int bpwf)
 	locomo_writel(bpwf | LOCOMO_ALC_EN, lchip->base + LOCOMO_FRONTLIGHT + LOCOMO_ALS);
 	spin_unlock_irqrestore(&lchip->lock, flags);
 }
+EXPORT_SYMBOL(locomo_frontlight_set);
 
 /*
  *	LoCoMo "Register Access Bus."
diff --git a/arch/arm/configs/h5000_defconfig b/arch/arm/configs/h5000_defconfig
new file mode 100644
index 000000000000..649baa370495
--- /dev/null
+++ b/arch/arm/configs/h5000_defconfig
@@ -0,0 +1,996 @@
+#
+# Automatically generated make config: don't edit
+# Linux kernel version: 2.6.27-rc6
+# Tue Sep 16 16:13:48 2008
+#
+CONFIG_ARM=y
+CONFIG_SYS_SUPPORTS_APM_EMULATION=y
+CONFIG_GENERIC_GPIO=y
+CONFIG_GENERIC_TIME=y
+CONFIG_GENERIC_CLOCKEVENTS=y
+CONFIG_MMU=y
+# CONFIG_NO_IOPORT is not set
+CONFIG_GENERIC_HARDIRQS=y
+CONFIG_STACKTRACE_SUPPORT=y
+CONFIG_HAVE_LATENCYTOP_SUPPORT=y
+CONFIG_LOCKDEP_SUPPORT=y
+CONFIG_TRACE_IRQFLAGS_SUPPORT=y
+CONFIG_HARDIRQS_SW_RESEND=y
+CONFIG_GENERIC_IRQ_PROBE=y
+CONFIG_RWSEM_GENERIC_SPINLOCK=y
+# CONFIG_ARCH_HAS_ILOG2_U32 is not set
+# CONFIG_ARCH_HAS_ILOG2_U64 is not set
+CONFIG_GENERIC_HWEIGHT=y
+CONFIG_GENERIC_CALIBRATE_DELAY=y
+CONFIG_ARCH_SUPPORTS_AOUT=y
+CONFIG_ZONE_DMA=y
+CONFIG_ARCH_MTD_XIP=y
+CONFIG_GENERIC_HARDIRQS_NO__DO_IRQ=y
+CONFIG_VECTORS_BASE=0xffff0000
+CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config"
+
+#
+# General setup
+#
+CONFIG_EXPERIMENTAL=y
+CONFIG_BROKEN_ON_SMP=y
+CONFIG_INIT_ENV_ARG_LIMIT=32
+CONFIG_LOCALVERSION=""
+CONFIG_LOCALVERSION_AUTO=y
+CONFIG_SWAP=y
+CONFIG_SYSVIPC=y
+CONFIG_SYSVIPC_SYSCTL=y
+# CONFIG_POSIX_MQUEUE is not set
+# CONFIG_BSD_PROCESS_ACCT is not set
+# CONFIG_TASKSTATS is not set
+# CONFIG_AUDIT is not set
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_LOG_BUF_SHIFT=16
+# CONFIG_CGROUPS is not set
+CONFIG_GROUP_SCHED=y
+CONFIG_FAIR_GROUP_SCHED=y
+# CONFIG_RT_GROUP_SCHED is not set
+CONFIG_USER_SCHED=y
+# CONFIG_CGROUP_SCHED is not set
+# CONFIG_SYSFS_DEPRECATED_V2 is not set
+# CONFIG_RELAY is not set
+# CONFIG_NAMESPACES is not set
+# CONFIG_BLK_DEV_INITRD is not set
+# CONFIG_CC_OPTIMIZE_FOR_SIZE is not set
+CONFIG_SYSCTL=y
+CONFIG_EMBEDDED=y
+# CONFIG_UID16 is not set
+CONFIG_SYSCTL_SYSCALL=y
+CONFIG_KALLSYMS=y
+# CONFIG_KALLSYMS_ALL is not set
+# CONFIG_KALLSYMS_EXTRA_PASS is not set
+CONFIG_HOTPLUG=y
+CONFIG_PRINTK=y
+CONFIG_BUG=y
+CONFIG_ELF_CORE=y
+CONFIG_COMPAT_BRK=y
+CONFIG_BASE_FULL=y
+CONFIG_FUTEX=y
+CONFIG_ANON_INODES=y
+CONFIG_EPOLL=y
+CONFIG_SIGNALFD=y
+CONFIG_TIMERFD=y
+CONFIG_EVENTFD=y
+CONFIG_SHMEM=y
+CONFIG_VM_EVENT_COUNTERS=y
+CONFIG_SLAB=y
+# CONFIG_SLUB is not set
+# CONFIG_SLOB is not set
+# CONFIG_PROFILING is not set
+# CONFIG_MARKERS is not set
+CONFIG_HAVE_OPROFILE=y
+# CONFIG_KPROBES is not set
+# CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS is not set
+# CONFIG_HAVE_IOREMAP_PROT is not set
+CONFIG_HAVE_KPROBES=y
+CONFIG_HAVE_KRETPROBES=y
+# CONFIG_HAVE_ARCH_TRACEHOOK is not set
+# CONFIG_HAVE_DMA_ATTRS is not set
+# CONFIG_USE_GENERIC_SMP_HELPERS is not set
+CONFIG_HAVE_CLK=y
+# CONFIG_PROC_PAGE_MONITOR is not set
+CONFIG_HAVE_GENERIC_DMA_COHERENT=y
+CONFIG_SLABINFO=y
+CONFIG_RT_MUTEXES=y
+# CONFIG_TINY_SHMEM is not set
+CONFIG_BASE_SMALL=0
+CONFIG_MODULES=y
+# CONFIG_MODULE_FORCE_LOAD is not set
+CONFIG_MODULE_UNLOAD=y
+CONFIG_MODULE_FORCE_UNLOAD=y
+# CONFIG_MODVERSIONS is not set
+# CONFIG_MODULE_SRCVERSION_ALL is not set
+CONFIG_KMOD=y
+CONFIG_BLOCK=y
+# CONFIG_LBD is not set
+# CONFIG_BLK_DEV_IO_TRACE is not set
+# CONFIG_LSF is not set
+# CONFIG_BLK_DEV_BSG is not set
+# CONFIG_BLK_DEV_INTEGRITY is not set
+
+#
+# IO Schedulers
+#
+CONFIG_IOSCHED_NOOP=y
+CONFIG_IOSCHED_AS=y
+CONFIG_IOSCHED_DEADLINE=y
+# CONFIG_IOSCHED_CFQ is not set
+CONFIG_DEFAULT_AS=y
+# CONFIG_DEFAULT_DEADLINE is not set
+# CONFIG_DEFAULT_CFQ is not set
+# CONFIG_DEFAULT_NOOP is not set
+CONFIG_DEFAULT_IOSCHED="anticipatory"
+CONFIG_CLASSIC_RCU=y
+
+#
+# System Type
+#
+# CONFIG_ARCH_AAEC2000 is not set
+# CONFIG_ARCH_INTEGRATOR is not set
+# CONFIG_ARCH_REALVIEW is not set
+# CONFIG_ARCH_VERSATILE is not set
+# CONFIG_ARCH_AT91 is not set
+# CONFIG_ARCH_CLPS7500 is not set
+# CONFIG_ARCH_CLPS711X is not set
+# CONFIG_ARCH_EBSA110 is not set
+# CONFIG_ARCH_EP93XX is not set
+# CONFIG_ARCH_FOOTBRIDGE is not set
+# CONFIG_ARCH_NETX is not set
+# CONFIG_ARCH_H720X is not set
+# CONFIG_ARCH_IMX is not set
+# CONFIG_ARCH_IOP13XX is not set
+# CONFIG_ARCH_IOP32X is not set
+# CONFIG_ARCH_IOP33X is not set
+# CONFIG_ARCH_IXP23XX is not set
+# CONFIG_ARCH_IXP2000 is not set
+# CONFIG_ARCH_IXP4XX is not set
+# CONFIG_ARCH_L7200 is not set
+# CONFIG_ARCH_KIRKWOOD is not set
+# CONFIG_ARCH_KS8695 is not set
+# CONFIG_ARCH_NS9XXX is not set
+# CONFIG_ARCH_LOKI is not set
+# CONFIG_ARCH_MV78XX0 is not set
+# CONFIG_ARCH_MXC is not set
+# CONFIG_ARCH_ORION5X is not set
+# CONFIG_ARCH_PNX4008 is not set
+CONFIG_ARCH_PXA=y
+# CONFIG_ARCH_RPC is not set
+# CONFIG_ARCH_SA1100 is not set
+# CONFIG_ARCH_S3C2410 is not set
+# CONFIG_ARCH_SHARK is not set
+# CONFIG_ARCH_LH7A40X is not set
+# CONFIG_ARCH_DAVINCI is not set
+# CONFIG_ARCH_OMAP is not set
+# CONFIG_ARCH_MSM7X00A is not set
+
+#
+# Intel PXA2xx/PXA3xx Implementations
+#
+# CONFIG_ARCH_GUMSTIX is not set
+# CONFIG_ARCH_LUBBOCK is not set
+# CONFIG_MACH_LOGICPD_PXA270 is not set
+# CONFIG_MACH_MAINSTONE is not set
+# CONFIG_ARCH_PXA_IDP is not set
+# CONFIG_PXA_SHARPSL is not set
+# CONFIG_ARCH_PXA_ESERIES is not set
+CONFIG_MACH_H5000=y
+# CONFIG_MACH_TRIZEPS4 is not set
+# CONFIG_MACH_EM_X270 is not set
+# CONFIG_MACH_COLIBRI is not set
+# CONFIG_MACH_ZYLONITE is not set
+# CONFIG_MACH_LITTLETON is not set
+# CONFIG_MACH_TAVOREVB is not set
+# CONFIG_MACH_SAAR is not set
+# CONFIG_MACH_ARMCORE is not set
+# CONFIG_MACH_MAGICIAN is not set
+# CONFIG_MACH_PCM027 is not set
+# CONFIG_ARCH_PXA_PALM is not set
+# CONFIG_PXA_EZX is not set
+CONFIG_PXA25x=y
+# CONFIG_PXA_PWM is not set
+
+#
+# Boot options
+#
+
+#
+# Power management
+#
+
+#
+# Processor Type
+#
+CONFIG_CPU_32=y
+CONFIG_CPU_XSCALE=y
+CONFIG_CPU_32v5=y
+CONFIG_CPU_ABRT_EV5T=y
+CONFIG_CPU_PABRT_NOIFAR=y
+CONFIG_CPU_CACHE_VIVT=y
+CONFIG_CPU_TLB_V4WBI=y
+CONFIG_CPU_CP15=y
+CONFIG_CPU_CP15_MMU=y
+
+#
+# Processor Features
+#
+CONFIG_ARM_THUMB=y
+# CONFIG_CPU_DCACHE_DISABLE is not set
+# CONFIG_OUTER_CACHE is not set
+# CONFIG_IWMMXT is not set
+CONFIG_XSCALE_PMU=y
+
+#
+# Bus support
+#
+# CONFIG_PCI_SYSCALL is not set
+# CONFIG_ARCH_SUPPORTS_MSI is not set
+# CONFIG_PCCARD is not set
+
+#
+# Kernel Features
+#
+CONFIG_TICK_ONESHOT=y
+# CONFIG_NO_HZ is not set
+# CONFIG_HIGH_RES_TIMERS is not set
+CONFIG_GENERIC_CLOCKEVENTS_BUILD=y
+# CONFIG_PREEMPT is not set
+CONFIG_HZ=100
+CONFIG_AEABI=y
+CONFIG_OABI_COMPAT=y
+CONFIG_ARCH_FLATMEM_HAS_HOLES=y
+# CONFIG_ARCH_DISCONTIGMEM_ENABLE is not set
+CONFIG_SELECT_MEMORY_MODEL=y
+CONFIG_FLATMEM_MANUAL=y
+# CONFIG_DISCONTIGMEM_MANUAL is not set
+# CONFIG_SPARSEMEM_MANUAL is not set
+CONFIG_FLATMEM=y
+CONFIG_FLAT_NODE_MEM_MAP=y
+# CONFIG_SPARSEMEM_STATIC is not set
+# CONFIG_SPARSEMEM_VMEMMAP_ENABLE is not set
+CONFIG_PAGEFLAGS_EXTENDED=y
+CONFIG_SPLIT_PTLOCK_CPUS=4096
+# CONFIG_RESOURCES_64BIT is not set
+CONFIG_ZONE_DMA_FLAG=1
+CONFIG_BOUNCE=y
+CONFIG_VIRT_TO_BUS=y
+CONFIG_ALIGNMENT_TRAP=y
+
+#
+# Boot options
+#
+CONFIG_ZBOOT_ROM_TEXT=0x0
+CONFIG_ZBOOT_ROM_BSS=0x0
+CONFIG_CMDLINE="keepinitrd"
+# CONFIG_XIP_KERNEL is not set
+CONFIG_KEXEC=y
+CONFIG_ATAGS_PROC=y
+
+#
+# CPU Frequency scaling
+#
+# CONFIG_CPU_FREQ is not set
+
+#
+# Floating point emulation
+#
+
+#
+# At least one emulation must be selected
+#
+CONFIG_FPE_NWFPE=y
+# CONFIG_FPE_NWFPE_XP is not set
+# CONFIG_FPE_FASTFPE is not set
+
+#
+# Userspace binary formats
+#
+CONFIG_BINFMT_ELF=y
+# CONFIG_BINFMT_AOUT is not set
+# CONFIG_BINFMT_MISC is not set
+
+#
+# Power management options
+#
+CONFIG_PM=y
+# CONFIG_PM_DEBUG is not set
+CONFIG_PM_SLEEP=y
+CONFIG_SUSPEND=y
+CONFIG_SUSPEND_FREEZER=y
+CONFIG_APM_EMULATION=y
+CONFIG_ARCH_SUSPEND_POSSIBLE=y
+CONFIG_NET=y
+
+#
+# Networking options
+#
+CONFIG_PACKET=y
+CONFIG_PACKET_MMAP=y
+CONFIG_UNIX=y
+# CONFIG_NET_KEY is not set
+CONFIG_INET=y
+CONFIG_IP_MULTICAST=y
+# CONFIG_IP_ADVANCED_ROUTER is not set
+CONFIG_IP_FIB_HASH=y
+CONFIG_IP_PNP=y
+# CONFIG_IP_PNP_DHCP is not set
+# CONFIG_IP_PNP_BOOTP is not set
+# CONFIG_IP_PNP_RARP is not set
+# CONFIG_NET_IPIP is not set
+# CONFIG_NET_IPGRE is not set
+# CONFIG_IP_MROUTE is not set
+# CONFIG_ARPD is not set
+# CONFIG_SYN_COOKIES is not set
+# CONFIG_INET_AH is not set
+# CONFIG_INET_ESP is not set
+# CONFIG_INET_IPCOMP is not set
+# CONFIG_INET_XFRM_TUNNEL is not set
+# CONFIG_INET_TUNNEL is not set
+# CONFIG_INET_XFRM_MODE_TRANSPORT is not set
+# CONFIG_INET_XFRM_MODE_TUNNEL is not set
+# CONFIG_INET_XFRM_MODE_BEET is not set
+# CONFIG_INET_LRO is not set
+# CONFIG_INET_DIAG is not set
+# CONFIG_TCP_CONG_ADVANCED is not set
+CONFIG_TCP_CONG_CUBIC=y
+CONFIG_DEFAULT_TCP_CONG="cubic"
+# CONFIG_TCP_MD5SIG is not set
+# CONFIG_IPV6 is not set
+# CONFIG_NETWORK_SECMARK is not set
+# CONFIG_NETFILTER is not set
+# CONFIG_IP_DCCP is not set
+# CONFIG_IP_SCTP is not set
+# CONFIG_TIPC is not set
+# CONFIG_ATM is not set
+# CONFIG_BRIDGE is not set
+# CONFIG_VLAN_8021Q is not set
+# CONFIG_DECNET is not set
+# CONFIG_LLC2 is not set
+# CONFIG_IPX is not set
+# CONFIG_ATALK is not set
+# CONFIG_X25 is not set
+# CONFIG_LAPB is not set
+# CONFIG_ECONET is not set
+# CONFIG_WAN_ROUTER is not set
+# CONFIG_NET_SCHED is not set
+
+#
+# Network testing
+#
+# CONFIG_NET_PKTGEN is not set
+# CONFIG_HAMRADIO is not set
+# CONFIG_CAN is not set
+# CONFIG_IRDA is not set
+# CONFIG_BT is not set
+# CONFIG_AF_RXRPC is not set
+
+#
+# Wireless
+#
+# CONFIG_CFG80211 is not set
+# CONFIG_WIRELESS_EXT is not set
+# CONFIG_MAC80211 is not set
+# CONFIG_IEEE80211 is not set
+# CONFIG_RFKILL is not set
+# CONFIG_NET_9P is not set
+
+#
+# Device Drivers
+#
+
+#
+# Generic Driver Options
+#
+CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
+CONFIG_STANDALONE=y
+CONFIG_PREVENT_FIRMWARE_BUILD=y
+CONFIG_FW_LOADER=y
+CONFIG_FIRMWARE_IN_KERNEL=y
+CONFIG_EXTRA_FIRMWARE=""
+# CONFIG_DEBUG_DRIVER is not set
+# CONFIG_DEBUG_DEVRES is not set
+# CONFIG_SYS_HYPERVISOR is not set
+# CONFIG_CONNECTOR is not set
+CONFIG_MTD=y
+# CONFIG_MTD_DEBUG is not set
+# CONFIG_MTD_CONCAT is not set
+CONFIG_MTD_PARTITIONS=y
+# CONFIG_MTD_REDBOOT_PARTS is not set
+# CONFIG_MTD_CMDLINE_PARTS is not set
+# CONFIG_MTD_AFS_PARTS is not set
+# CONFIG_MTD_AR7_PARTS is not set
+
+#
+# User Modules And Translation Layers
+#
+# CONFIG_MTD_CHAR is not set
+CONFIG_MTD_BLKDEVS=y
+CONFIG_MTD_BLOCK=y
+# CONFIG_FTL is not set
+# CONFIG_NFTL is not set
+# CONFIG_INFTL is not set
+# CONFIG_RFD_FTL is not set
+# CONFIG_SSFDC is not set
+# CONFIG_MTD_OOPS is not set
+
+#
+# RAM/ROM/Flash chip drivers
+#
+CONFIG_MTD_CFI=y
+# CONFIG_MTD_JEDECPROBE is not set
+CONFIG_MTD_GEN_PROBE=y
+CONFIG_MTD_CFI_ADV_OPTIONS=y
+CONFIG_MTD_CFI_NOSWAP=y
+# CONFIG_MTD_CFI_BE_BYTE_SWAP is not set
+# CONFIG_MTD_CFI_LE_BYTE_SWAP is not set
+CONFIG_MTD_CFI_GEOMETRY=y
+CONFIG_MTD_MAP_BANK_WIDTH_1=y
+CONFIG_MTD_MAP_BANK_WIDTH_2=y
+CONFIG_MTD_MAP_BANK_WIDTH_4=y
+# CONFIG_MTD_MAP_BANK_WIDTH_8 is not set
+# CONFIG_MTD_MAP_BANK_WIDTH_16 is not set
+# CONFIG_MTD_MAP_BANK_WIDTH_32 is not set
+CONFIG_MTD_CFI_I1=y
+CONFIG_MTD_CFI_I2=y
+# CONFIG_MTD_CFI_I4 is not set
+# CONFIG_MTD_CFI_I8 is not set
+# CONFIG_MTD_OTP is not set
+CONFIG_MTD_CFI_INTELEXT=y
+# CONFIG_MTD_CFI_AMDSTD is not set
+# CONFIG_MTD_CFI_STAA is not set
+CONFIG_MTD_CFI_UTIL=y
+# CONFIG_MTD_RAM is not set
+# CONFIG_MTD_ROM is not set
+# CONFIG_MTD_ABSENT is not set
+# CONFIG_MTD_XIP is not set
+
+#
+# Mapping drivers for chip access
+#
+# CONFIG_MTD_COMPLEX_MAPPINGS is not set
+CONFIG_MTD_PHYSMAP=y
+CONFIG_MTD_PHYSMAP_START=0x8000000
+CONFIG_MTD_PHYSMAP_LEN=0x0
+CONFIG_MTD_PHYSMAP_BANKWIDTH=2
+# CONFIG_MTD_PXA2XX is not set
+# CONFIG_MTD_ARM_INTEGRATOR is not set
+# CONFIG_MTD_SHARP_SL is not set
+# CONFIG_MTD_PLATRAM is not set
+
+#
+# Self-contained MTD device drivers
+#
+# CONFIG_MTD_SLRAM is not set
+# CONFIG_MTD_PHRAM is not set
+# CONFIG_MTD_MTDRAM is not set
+# CONFIG_MTD_BLOCK2MTD is not set
+
+#
+# Disk-On-Chip Device Drivers
+#
+# CONFIG_MTD_DOC2000 is not set
+# CONFIG_MTD_DOC2001 is not set
+# CONFIG_MTD_DOC2001PLUS is not set
+# CONFIG_MTD_NAND is not set
+# CONFIG_MTD_ONENAND is not set
+
+#
+# UBI - Unsorted block images
+#
+# CONFIG_MTD_UBI is not set
+# CONFIG_PARPORT is not set
+CONFIG_BLK_DEV=y
+# CONFIG_BLK_DEV_COW_COMMON is not set
+# CONFIG_BLK_DEV_LOOP is not set
+# CONFIG_BLK_DEV_NBD is not set
+# CONFIG_BLK_DEV_RAM is not set
+# CONFIG_CDROM_PKTCDVD is not set
+# CONFIG_ATA_OVER_ETH is not set
+CONFIG_MISC_DEVICES=y
+# CONFIG_EEPROM_93CX6 is not set
+# CONFIG_ENCLOSURE_SERVICES is not set
+CONFIG_HAVE_IDE=y
+# CONFIG_IDE is not set
+
+#
+# SCSI device support
+#
+# CONFIG_RAID_ATTRS is not set
+# CONFIG_SCSI is not set
+# CONFIG_SCSI_DMA is not set
+# CONFIG_SCSI_NETLINK is not set
+# CONFIG_ATA is not set
+# CONFIG_MD is not set
+# CONFIG_NETDEVICES is not set
+# CONFIG_ISDN is not set
+
+#
+# Input device support
+#
+CONFIG_INPUT=y
+# CONFIG_INPUT_FF_MEMLESS is not set
+# CONFIG_INPUT_POLLDEV is not set
+
+#
+# Userland interfaces
+#
+# CONFIG_INPUT_MOUSEDEV is not set
+# CONFIG_INPUT_JOYDEV is not set
+# CONFIG_INPUT_EVDEV is not set
+# CONFIG_INPUT_EVBUG is not set
+# CONFIG_INPUT_APMPOWER is not set
+
+#
+# Input Device Drivers
+#
+# CONFIG_INPUT_KEYBOARD is not set
+# CONFIG_INPUT_MOUSE is not set
+# CONFIG_INPUT_JOYSTICK is not set
+# CONFIG_INPUT_TABLET is not set
+# CONFIG_INPUT_TOUCHSCREEN is not set
+# CONFIG_INPUT_MISC is not set
+
+#
+# Hardware I/O ports
+#
+# CONFIG_SERIO is not set
+# CONFIG_GAMEPORT is not set
+
+#
+# Character devices
+#
+CONFIG_VT=y
+CONFIG_CONSOLE_TRANSLATIONS=y
+CONFIG_VT_CONSOLE=y
+CONFIG_HW_CONSOLE=y
+# CONFIG_VT_HW_CONSOLE_BINDING is not set
+CONFIG_DEVKMEM=y
+# CONFIG_SERIAL_NONSTANDARD is not set
+
+#
+# Serial drivers
+#
+# CONFIG_SERIAL_8250 is not set
+
+#
+# Non-8250 serial port support
+#
+CONFIG_SERIAL_PXA=y
+CONFIG_SERIAL_PXA_CONSOLE=y
+CONFIG_SERIAL_CORE=y
+CONFIG_SERIAL_CORE_CONSOLE=y
+CONFIG_UNIX98_PTYS=y
+CONFIG_LEGACY_PTYS=y
+CONFIG_LEGACY_PTY_COUNT=32
+# CONFIG_IPMI_HANDLER is not set
+# CONFIG_HW_RANDOM is not set
+# CONFIG_NVRAM is not set
+# CONFIG_R3964 is not set
+# CONFIG_RAW_DRIVER is not set
+# CONFIG_TCG_TPM is not set
+# CONFIG_I2C is not set
+# CONFIG_SPI is not set
+CONFIG_ARCH_REQUIRE_GPIOLIB=y
+CONFIG_GPIOLIB=y
+# CONFIG_DEBUG_GPIO is not set
+# CONFIG_GPIO_SYSFS is not set
+
+#
+# I2C GPIO expanders:
+#
+
+#
+# PCI GPIO expanders:
+#
+
+#
+# SPI GPIO expanders:
+#
+# CONFIG_W1 is not set
+# CONFIG_POWER_SUPPLY is not set
+# CONFIG_HWMON is not set
+# CONFIG_WATCHDOG is not set
+
+#
+# Sonics Silicon Backplane
+#
+CONFIG_SSB_POSSIBLE=y
+# CONFIG_SSB is not set
+
+#
+# Multifunction device drivers
+#
+# CONFIG_MFD_CORE is not set
+# CONFIG_MFD_SM501 is not set
+# CONFIG_HTC_EGPIO is not set
+# CONFIG_HTC_PASIC3 is not set
+# CONFIG_MFD_TMIO is not set
+# CONFIG_MFD_T7L66XB is not set
+# CONFIG_MFD_TC6387XB is not set
+# CONFIG_MFD_TC6393XB is not set
+
+#
+# Multimedia devices
+#
+
+#
+# Multimedia core support
+#
+# CONFIG_VIDEO_DEV is not set
+# CONFIG_DVB_CORE is not set
+# CONFIG_VIDEO_MEDIA is not set
+
+#
+# Multimedia drivers
+#
+# CONFIG_DAB is not set
+
+#
+# Graphics support
+#
+# CONFIG_VGASTATE is not set
+# CONFIG_VIDEO_OUTPUT_CONTROL is not set
+# CONFIG_FB is not set
+# CONFIG_BACKLIGHT_LCD_SUPPORT is not set
+
+#
+# Display device support
+#
+# CONFIG_DISPLAY_SUPPORT is not set
+
+#
+# Console display driver support
+#
+# CONFIG_VGA_CONSOLE is not set
+CONFIG_DUMMY_CONSOLE=y
+# CONFIG_SOUND is not set
+# CONFIG_HID_SUPPORT is not set
+CONFIG_USB_SUPPORT=y
+CONFIG_USB_ARCH_HAS_HCD=y
+# CONFIG_USB_ARCH_HAS_OHCI is not set
+# CONFIG_USB_ARCH_HAS_EHCI is not set
+# CONFIG_USB is not set
+# CONFIG_USB_OTG_WHITELIST is not set
+# CONFIG_USB_OTG_BLACKLIST_HUB is not set
+# CONFIG_USB_MUSB_HDRC is not set
+# CONFIG_USB_GADGET_MUSB_HDRC is not set
+
+#
+# NOTE: USB_STORAGE enables SCSI, and 'SCSI disk support'
+#
+CONFIG_USB_GADGET=y
+# CONFIG_USB_GADGET_DEBUG is not set
+# CONFIG_USB_GADGET_DEBUG_FILES is not set
+CONFIG_USB_GADGET_SELECTED=y
+# CONFIG_USB_GADGET_AMD5536UDC is not set
+# CONFIG_USB_GADGET_ATMEL_USBA is not set
+# CONFIG_USB_GADGET_FSL_USB2 is not set
+# CONFIG_USB_GADGET_NET2280 is not set
+CONFIG_USB_GADGET_PXA25X=y
+CONFIG_USB_PXA25X=y
+CONFIG_USB_PXA25X_SMALL=y
+# CONFIG_USB_GADGET_M66592 is not set
+# CONFIG_USB_GADGET_PXA27X is not set
+# CONFIG_USB_GADGET_GOKU is not set
+# CONFIG_USB_GADGET_LH7A40X is not set
+# CONFIG_USB_GADGET_OMAP is not set
+# CONFIG_USB_GADGET_S3C2410 is not set
+# CONFIG_USB_GADGET_AT91 is not set
+# CONFIG_USB_GADGET_DUMMY_HCD is not set
+# CONFIG_USB_GADGET_DUALSPEED is not set
+# CONFIG_USB_ZERO is not set
+CONFIG_USB_ETH=y
+# CONFIG_USB_ETH_RNDIS is not set
+# CONFIG_USB_GADGETFS is not set
+# CONFIG_USB_FILE_STORAGE is not set
+# CONFIG_USB_G_SERIAL is not set
+# CONFIG_USB_MIDI_GADGET is not set
+# CONFIG_USB_G_PRINTER is not set
+# CONFIG_USB_CDC_COMPOSITE is not set
+# CONFIG_MMC is not set
+# CONFIG_NEW_LEDS is not set
+CONFIG_RTC_LIB=y
+CONFIG_RTC_CLASS=y
+CONFIG_RTC_HCTOSYS=y
+CONFIG_RTC_HCTOSYS_DEVICE="rtc0"
+# CONFIG_RTC_DEBUG is not set
+
+#
+# RTC interfaces
+#
+CONFIG_RTC_INTF_SYSFS=y
+CONFIG_RTC_INTF_PROC=y
+CONFIG_RTC_INTF_DEV=y
+# CONFIG_RTC_INTF_DEV_UIE_EMUL is not set
+# CONFIG_RTC_DRV_TEST is not set
+
+#
+# SPI RTC drivers
+#
+
+#
+# Platform RTC drivers
+#
+# CONFIG_RTC_DRV_CMOS is not set
+# CONFIG_RTC_DRV_DS1511 is not set
+# CONFIG_RTC_DRV_DS1553 is not set
+# CONFIG_RTC_DRV_DS1742 is not set
+# CONFIG_RTC_DRV_STK17TA8 is not set
+# CONFIG_RTC_DRV_M48T86 is not set
+# CONFIG_RTC_DRV_M48T59 is not set
+# CONFIG_RTC_DRV_V3020 is not set
+
+#
+# on-CPU RTC drivers
+#
+CONFIG_RTC_DRV_SA1100=y
+# CONFIG_DMADEVICES is not set
+
+#
+# Voltage and Current regulators
+#
+# CONFIG_REGULATOR is not set
+# CONFIG_REGULATOR_FIXED_VOLTAGE is not set
+# CONFIG_REGULATOR_VIRTUAL_CONSUMER is not set
+# CONFIG_REGULATOR_BQ24022 is not set
+# CONFIG_UIO is not set
+
+#
+# File systems
+#
+CONFIG_EXT2_FS=y
+# CONFIG_EXT2_FS_XATTR is not set
+# CONFIG_EXT2_FS_XIP is not set
+# CONFIG_EXT3_FS is not set
+# CONFIG_EXT4DEV_FS is not set
+# CONFIG_REISERFS_FS is not set
+# CONFIG_JFS_FS is not set
+# CONFIG_FS_POSIX_ACL is not set
+# CONFIG_XFS_FS is not set
+# CONFIG_OCFS2_FS is not set
+CONFIG_DNOTIFY=y
+CONFIG_INOTIFY=y
+CONFIG_INOTIFY_USER=y
+# CONFIG_QUOTA is not set
+# CONFIG_AUTOFS_FS is not set
+# CONFIG_AUTOFS4_FS is not set
+# CONFIG_FUSE_FS is not set
+
+#
+# CD-ROM/DVD Filesystems
+#
+# CONFIG_ISO9660_FS is not set
+# CONFIG_UDF_FS is not set
+
+#
+# DOS/FAT/NT Filesystems
+#
+# CONFIG_MSDOS_FS is not set
+# CONFIG_VFAT_FS is not set
+# CONFIG_NTFS_FS is not set
+
+#
+# Pseudo filesystems
+#
+CONFIG_PROC_FS=y
+CONFIG_PROC_SYSCTL=y
+CONFIG_SYSFS=y
+CONFIG_TMPFS=y
+# CONFIG_TMPFS_POSIX_ACL is not set
+# CONFIG_HUGETLB_PAGE is not set
+# CONFIG_CONFIGFS_FS is not set
+
+#
+# Miscellaneous filesystems
+#
+# CONFIG_ADFS_FS is not set
+# CONFIG_AFFS_FS is not set
+# CONFIG_HFS_FS is not set
+# CONFIG_HFSPLUS_FS is not set
+# CONFIG_BEFS_FS is not set
+# CONFIG_BFS_FS is not set
+# CONFIG_EFS_FS is not set
+CONFIG_JFFS2_FS=y
+CONFIG_JFFS2_FS_DEBUG=0
+CONFIG_JFFS2_FS_WRITEBUFFER=y
+# CONFIG_JFFS2_FS_WBUF_VERIFY is not set
+# CONFIG_JFFS2_SUMMARY is not set
+# CONFIG_JFFS2_FS_XATTR is not set
+CONFIG_JFFS2_COMPRESSION_OPTIONS=y
+CONFIG_JFFS2_ZLIB=y
+# CONFIG_JFFS2_LZO is not set
+CONFIG_JFFS2_RTIME=y
+# CONFIG_JFFS2_RUBIN is not set
+# CONFIG_JFFS2_CMODE_NONE is not set
+CONFIG_JFFS2_CMODE_PRIORITY=y
+# CONFIG_JFFS2_CMODE_SIZE is not set
+# CONFIG_JFFS2_CMODE_FAVOURLZO is not set
+# CONFIG_CRAMFS is not set
+# CONFIG_VXFS_FS is not set
+# CONFIG_MINIX_FS is not set
+# CONFIG_OMFS_FS is not set
+# CONFIG_HPFS_FS is not set
+# CONFIG_QNX4FS_FS is not set
+# CONFIG_ROMFS_FS is not set
+# CONFIG_SYSV_FS is not set
+# CONFIG_UFS_FS is not set
+# CONFIG_NETWORK_FILESYSTEMS is not set
+
+#
+# Partition Types
+#
+# CONFIG_PARTITION_ADVANCED is not set
+CONFIG_MSDOS_PARTITION=y
+# CONFIG_NLS is not set
+# CONFIG_DLM is not set
+
+#
+# Kernel hacking
+#
+CONFIG_PRINTK_TIME=y
+CONFIG_ENABLE_WARN_DEPRECATED=y
+CONFIG_ENABLE_MUST_CHECK=y
+CONFIG_FRAME_WARN=1024
+# CONFIG_MAGIC_SYSRQ is not set
+# CONFIG_UNUSED_SYMBOLS is not set
+# CONFIG_DEBUG_FS is not set
+# CONFIG_HEADERS_CHECK is not set
+CONFIG_DEBUG_KERNEL=y
+# CONFIG_DEBUG_SHIRQ is not set
+CONFIG_DETECT_SOFTLOCKUP=y
+# CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC is not set
+CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC_VALUE=0
+# CONFIG_SCHED_DEBUG is not set
+# CONFIG_SCHEDSTATS is not set
+# CONFIG_TIMER_STATS is not set
+# CONFIG_DEBUG_OBJECTS is not set
+# CONFIG_DEBUG_SLAB is not set
+# CONFIG_DEBUG_RT_MUTEXES is not set
+# CONFIG_RT_MUTEX_TESTER is not set
+# CONFIG_DEBUG_SPINLOCK is not set
+# CONFIG_DEBUG_MUTEXES is not set
+# CONFIG_DEBUG_LOCK_ALLOC is not set
+# CONFIG_PROVE_LOCKING is not set
+# CONFIG_LOCK_STAT is not set
+# CONFIG_DEBUG_SPINLOCK_SLEEP is not set
+# CONFIG_DEBUG_LOCKING_API_SELFTESTS is not set
+# CONFIG_DEBUG_KOBJECT is not set
+# CONFIG_DEBUG_BUGVERBOSE is not set
+# CONFIG_DEBUG_INFO is not set
+# CONFIG_DEBUG_VM is not set
+# CONFIG_DEBUG_WRITECOUNT is not set
+# CONFIG_DEBUG_MEMORY_INIT is not set
+# CONFIG_DEBUG_LIST is not set
+# CONFIG_DEBUG_SG is not set
+CONFIG_FRAME_POINTER=y
+# CONFIG_BOOT_PRINTK_DELAY is not set
+# CONFIG_RCU_TORTURE_TEST is not set
+# CONFIG_BACKTRACE_SELF_TEST is not set
+# CONFIG_FAULT_INJECTION is not set
+# CONFIG_LATENCYTOP is not set
+CONFIG_SYSCTL_SYSCALL_CHECK=y
+CONFIG_HAVE_FTRACE=y
+CONFIG_HAVE_DYNAMIC_FTRACE=y
+# CONFIG_FTRACE is not set
+# CONFIG_IRQSOFF_TRACER is not set
+# CONFIG_SCHED_TRACER is not set
+# CONFIG_CONTEXT_SWITCH_TRACER is not set
+# CONFIG_SAMPLES is not set
+CONFIG_HAVE_ARCH_KGDB=y
+# CONFIG_KGDB is not set
+# CONFIG_DEBUG_USER is not set
+# CONFIG_DEBUG_ERRORS is not set
+# CONFIG_DEBUG_STACK_USAGE is not set
+# CONFIG_DEBUG_LL is not set
+
+#
+# Security options
+#
+# CONFIG_KEYS is not set
+# CONFIG_SECURITY is not set
+# CONFIG_SECURITY_FILE_CAPABILITIES is not set
+CONFIG_CRYPTO=y
+
+#
+# Crypto core or helper
+#
+CONFIG_CRYPTO_ALGAPI=y
+CONFIG_CRYPTO_HASH=y
+CONFIG_CRYPTO_MANAGER=y
+# CONFIG_CRYPTO_GF128MUL is not set
+# CONFIG_CRYPTO_NULL is not set
+# CONFIG_CRYPTO_CRYPTD is not set
+# CONFIG_CRYPTO_AUTHENC is not set
+# CONFIG_CRYPTO_TEST is not set
+
+#
+# Authenticated Encryption with Associated Data
+#
+# CONFIG_CRYPTO_CCM is not set
+# CONFIG_CRYPTO_GCM is not set
+# CONFIG_CRYPTO_SEQIV is not set
+
+#
+# Block modes
+#
+# CONFIG_CRYPTO_CBC is not set
+# CONFIG_CRYPTO_CTR is not set
+# CONFIG_CRYPTO_CTS is not set
+# CONFIG_CRYPTO_ECB is not set
+# CONFIG_CRYPTO_LRW is not set
+# CONFIG_CRYPTO_PCBC is not set
+# CONFIG_CRYPTO_XTS is not set
+
+#
+# Hash modes
+#
+CONFIG_CRYPTO_HMAC=y
+# CONFIG_CRYPTO_XCBC is not set
+
+#
+# Digest
+#
+# CONFIG_CRYPTO_CRC32C is not set
+# CONFIG_CRYPTO_MD4 is not set
+CONFIG_CRYPTO_MD5=y
+# CONFIG_CRYPTO_MICHAEL_MIC is not set
+# CONFIG_CRYPTO_RMD128 is not set
+# CONFIG_CRYPTO_RMD160 is not set
+# CONFIG_CRYPTO_RMD256 is not set
+# CONFIG_CRYPTO_RMD320 is not set
+CONFIG_CRYPTO_SHA1=y
+# CONFIG_CRYPTO_SHA256 is not set
+# CONFIG_CRYPTO_SHA512 is not set
+# CONFIG_CRYPTO_TGR192 is not set
+# CONFIG_CRYPTO_WP512 is not set
+
+#
+# Ciphers
+#
+# CONFIG_CRYPTO_AES is not set
+# CONFIG_CRYPTO_ANUBIS is not set
+# CONFIG_CRYPTO_ARC4 is not set
+# CONFIG_CRYPTO_BLOWFISH is not set
+# CONFIG_CRYPTO_CAMELLIA is not set
+# CONFIG_CRYPTO_CAST5 is not set
+# CONFIG_CRYPTO_CAST6 is not set
+CONFIG_CRYPTO_DES=y
+# CONFIG_CRYPTO_FCRYPT is not set
+# CONFIG_CRYPTO_KHAZAD is not set
+# CONFIG_CRYPTO_SALSA20 is not set
+# CONFIG_CRYPTO_SEED is not set
+# CONFIG_CRYPTO_SERPENT is not set
+# CONFIG_CRYPTO_TEA is not set
+# CONFIG_CRYPTO_TWOFISH is not set
+
+#
+# Compression
+#
+CONFIG_CRYPTO_DEFLATE=y
+# CONFIG_CRYPTO_LZO is not set
+# CONFIG_CRYPTO_HW is not set
+
+#
+# Library routines
+#
+CONFIG_BITREVERSE=y
+# CONFIG_GENERIC_FIND_FIRST_BIT is not set
+# CONFIG_GENERIC_FIND_NEXT_BIT is not set
+CONFIG_CRC_CCITT=y
+# CONFIG_CRC16 is not set
+# CONFIG_CRC_T10DIF is not set
+# CONFIG_CRC_ITU_T is not set
+CONFIG_CRC32=y
+# CONFIG_CRC7 is not set
+# CONFIG_LIBCRC32C is not set
+CONFIG_ZLIB_INFLATE=y
+CONFIG_ZLIB_DEFLATE=y
+CONFIG_PLIST=y
+CONFIG_HAS_IOMEM=y
+CONFIG_HAS_IOPORT=y
+CONFIG_HAS_DMA=y
diff --git a/arch/arm/configs/neocore926_defconfig b/arch/arm/configs/neocore926_defconfig
new file mode 100644
index 000000000000..325f1e105f69
--- /dev/null
+++ b/arch/arm/configs/neocore926_defconfig
@@ -0,0 +1,1302 @@
+#
+# Automatically generated make config: don't edit
+# Linux kernel version: 2.6.27-rc1
+# Tue Jul 29 10:46:54 2008
+#
+CONFIG_ARM=y
+CONFIG_SYS_SUPPORTS_APM_EMULATION=y
+CONFIG_GENERIC_GPIO=y
+CONFIG_GENERIC_TIME=y
+CONFIG_GENERIC_CLOCKEVENTS=y
+CONFIG_MMU=y
+# CONFIG_NO_IOPORT is not set
+CONFIG_GENERIC_HARDIRQS=y
+CONFIG_STACKTRACE_SUPPORT=y
+CONFIG_HAVE_LATENCYTOP_SUPPORT=y
+CONFIG_LOCKDEP_SUPPORT=y
+CONFIG_TRACE_IRQFLAGS_SUPPORT=y
+CONFIG_HARDIRQS_SW_RESEND=y
+CONFIG_GENERIC_IRQ_PROBE=y
+CONFIG_RWSEM_GENERIC_SPINLOCK=y
+# CONFIG_ARCH_HAS_ILOG2_U32 is not set
+# CONFIG_ARCH_HAS_ILOG2_U64 is not set
+CONFIG_GENERIC_HWEIGHT=y
+CONFIG_GENERIC_CALIBRATE_DELAY=y
+CONFIG_ARCH_SUPPORTS_AOUT=y
+CONFIG_ZONE_DMA=y
+CONFIG_GENERIC_HARDIRQS_NO__DO_IRQ=y
+CONFIG_VECTORS_BASE=0xffff0000
+CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config"
+
+#
+# General setup
+#
+CONFIG_EXPERIMENTAL=y
+CONFIG_BROKEN_ON_SMP=y
+CONFIG_INIT_ENV_ARG_LIMIT=32
+CONFIG_LOCALVERSION=""
+# CONFIG_LOCALVERSION_AUTO is not set
+# CONFIG_SWAP is not set
+CONFIG_SYSVIPC=y
+CONFIG_SYSVIPC_SYSCTL=y
+# CONFIG_POSIX_MQUEUE is not set
+# CONFIG_BSD_PROCESS_ACCT is not set
+# CONFIG_TASKSTATS is not set
+# CONFIG_AUDIT is not set
+# CONFIG_IKCONFIG is not set
+CONFIG_LOG_BUF_SHIFT=17
+# CONFIG_CGROUPS is not set
+# CONFIG_GROUP_SCHED is not set
+# CONFIG_SYSFS_DEPRECATED_V2 is not set
+# CONFIG_RELAY is not set
+CONFIG_NAMESPACES=y
+# CONFIG_UTS_NS is not set
+# CONFIG_IPC_NS is not set
+# CONFIG_USER_NS is not set
+# CONFIG_PID_NS is not set
+CONFIG_BLK_DEV_INITRD=y
+CONFIG_INITRAMFS_SOURCE=""
+CONFIG_CC_OPTIMIZE_FOR_SIZE=y
+CONFIG_SYSCTL=y
+# CONFIG_EMBEDDED is not set
+CONFIG_UID16=y
+CONFIG_SYSCTL_SYSCALL=y
+CONFIG_SYSCTL_SYSCALL_CHECK=y
+CONFIG_KALLSYMS=y
+# CONFIG_KALLSYMS_EXTRA_PASS is not set
+CONFIG_HOTPLUG=y
+CONFIG_PRINTK=y
+CONFIG_BUG=y
+CONFIG_ELF_CORE=y
+# CONFIG_COMPAT_BRK is not set
+CONFIG_BASE_FULL=y
+CONFIG_FUTEX=y
+CONFIG_ANON_INODES=y
+CONFIG_EPOLL=y
+CONFIG_SIGNALFD=y
+CONFIG_TIMERFD=y
+CONFIG_EVENTFD=y
+CONFIG_SHMEM=y
+CONFIG_VM_EVENT_COUNTERS=y
+CONFIG_SLUB_DEBUG=y
+# CONFIG_SLAB is not set
+CONFIG_SLUB=y
+# CONFIG_SLOB is not set
+# CONFIG_PROFILING is not set
+# CONFIG_MARKERS is not set
+CONFIG_HAVE_OPROFILE=y
+# CONFIG_KPROBES is not set
+# CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS is not set
+# CONFIG_HAVE_IOREMAP_PROT is not set
+CONFIG_HAVE_KPROBES=y
+CONFIG_HAVE_KRETPROBES=y
+# CONFIG_HAVE_ARCH_TRACEHOOK is not set
+# CONFIG_HAVE_DMA_ATTRS is not set
+# CONFIG_USE_GENERIC_SMP_HELPERS is not set
+CONFIG_HAVE_CLK=y
+CONFIG_PROC_PAGE_MONITOR=y
+CONFIG_HAVE_GENERIC_DMA_COHERENT=y
+CONFIG_SLABINFO=y
+CONFIG_RT_MUTEXES=y
+# CONFIG_TINY_SHMEM is not set
+CONFIG_BASE_SMALL=0
+CONFIG_MODULES=y
+# CONFIG_MODULE_FORCE_LOAD is not set
+CONFIG_MODULE_UNLOAD=y
+# CONFIG_MODULE_FORCE_UNLOAD is not set
+# CONFIG_MODVERSIONS is not set
+# CONFIG_MODULE_SRCVERSION_ALL is not set
+CONFIG_KMOD=y
+CONFIG_BLOCK=y
+# CONFIG_LBD is not set
+# CONFIG_BLK_DEV_IO_TRACE is not set
+# CONFIG_LSF is not set
+# CONFIG_BLK_DEV_BSG is not set
+# CONFIG_BLK_DEV_INTEGRITY is not set
+
+#
+# IO Schedulers
+#
+CONFIG_IOSCHED_NOOP=y
+# CONFIG_IOSCHED_AS is not set
+# CONFIG_IOSCHED_DEADLINE is not set
+# CONFIG_IOSCHED_CFQ is not set
+# CONFIG_DEFAULT_AS is not set
+# CONFIG_DEFAULT_DEADLINE is not set
+# CONFIG_DEFAULT_CFQ is not set
+CONFIG_DEFAULT_NOOP=y
+CONFIG_DEFAULT_IOSCHED="noop"
+CONFIG_CLASSIC_RCU=y
+
+#
+# System Type
+#
+# CONFIG_ARCH_AAEC2000 is not set
+# CONFIG_ARCH_INTEGRATOR is not set
+# CONFIG_ARCH_REALVIEW is not set
+# CONFIG_ARCH_VERSATILE is not set
+CONFIG_ARCH_AT91=y
+# CONFIG_ARCH_CLPS7500 is not set
+# CONFIG_ARCH_CLPS711X is not set
+# CONFIG_ARCH_EBSA110 is not set
+# CONFIG_ARCH_EP93XX is not set
+# CONFIG_ARCH_FOOTBRIDGE is not set
+# CONFIG_ARCH_NETX is not set
+# CONFIG_ARCH_H720X is not set
+# CONFIG_ARCH_IMX is not set
+# CONFIG_ARCH_IOP13XX is not set
+# CONFIG_ARCH_IOP32X is not set
+# CONFIG_ARCH_IOP33X is not set
+# CONFIG_ARCH_IXP23XX is not set
+# CONFIG_ARCH_IXP2000 is not set
+# CONFIG_ARCH_IXP4XX is not set
+# CONFIG_ARCH_L7200 is not set
+# CONFIG_ARCH_KIRKWOOD is not set
+# CONFIG_ARCH_KS8695 is not set
+# CONFIG_ARCH_NS9XXX is not set
+# CONFIG_ARCH_LOKI is not set
+# CONFIG_ARCH_MV78XX0 is not set
+# CONFIG_ARCH_MXC is not set
+# CONFIG_ARCH_ORION5X is not set
+# CONFIG_ARCH_PNX4008 is not set
+# CONFIG_ARCH_PXA is not set
+# CONFIG_ARCH_RPC is not set
+# CONFIG_ARCH_SA1100 is not set
+# CONFIG_ARCH_S3C2410 is not set
+# CONFIG_ARCH_SHARK is not set
+# CONFIG_ARCH_LH7A40X is not set
+# CONFIG_ARCH_DAVINCI is not set
+# CONFIG_ARCH_OMAP is not set
+# CONFIG_ARCH_MSM7X00A is not set
+
+#
+# Boot options
+#
+
+#
+# Power management
+#
+
+#
+# Atmel AT91 System-on-Chip
+#
+# CONFIG_ARCH_AT91RM9200 is not set
+# CONFIG_ARCH_AT91SAM9260 is not set
+# CONFIG_ARCH_AT91SAM9261 is not set
+CONFIG_ARCH_AT91SAM9263=y
+# CONFIG_ARCH_AT91SAM9RL is not set
+# CONFIG_ARCH_AT91SAM9G20 is not set
+# CONFIG_ARCH_AT91CAP9 is not set
+# CONFIG_ARCH_AT91X40 is not set
+CONFIG_AT91_PMC_UNIT=y
+
+#
+# AT91SAM9263 Board Type
+#
+# CONFIG_MACH_AT91SAM9263EK is not set
+# CONFIG_MACH_USB_A9263 is not set
+CONFIG_MACH_NEOCORE926=y
+
+#
+# AT91 Board Options
+#
+CONFIG_MTD_AT91_DATAFLASH_CARD=y
+
+#
+# AT91 Feature Selections
+#
+# CONFIG_AT91_PROGRAMMABLE_CLOCKS is not set
+CONFIG_AT91_TIMER_HZ=100
+CONFIG_AT91_EARLY_DBGU=y
+# CONFIG_AT91_EARLY_USART0 is not set
+# CONFIG_AT91_EARLY_USART1 is not set
+# CONFIG_AT91_EARLY_USART2 is not set
+# CONFIG_AT91_EARLY_USART3 is not set
+# CONFIG_AT91_EARLY_USART4 is not set
+# CONFIG_AT91_EARLY_USART5 is not set
+
+#
+# Processor Type
+#
+CONFIG_CPU_32=y
+CONFIG_CPU_ARM926T=y
+CONFIG_CPU_32v5=y
+CONFIG_CPU_ABRT_EV5TJ=y
+CONFIG_CPU_PABRT_NOIFAR=y
+CONFIG_CPU_CACHE_VIVT=y
+CONFIG_CPU_COPY_V4WB=y
+CONFIG_CPU_TLB_V4WBI=y
+CONFIG_CPU_CP15=y
+CONFIG_CPU_CP15_MMU=y
+
+#
+# Processor Features
+#
+CONFIG_ARM_THUMB=y
+# CONFIG_CPU_ICACHE_DISABLE is not set
+# CONFIG_CPU_DCACHE_DISABLE is not set
+# CONFIG_CPU_DCACHE_WRITETHROUGH is not set
+# CONFIG_CPU_CACHE_ROUND_ROBIN is not set
+# CONFIG_OUTER_CACHE is not set
+
+#
+# Bus support
+#
+# CONFIG_PCI_SYSCALL is not set
+# CONFIG_ARCH_SUPPORTS_MSI is not set
+# CONFIG_PCCARD is not set
+
+#
+# Kernel Features
+#
+# CONFIG_TICK_ONESHOT is not set
+# CONFIG_NO_HZ is not set
+# CONFIG_HIGH_RES_TIMERS is not set
+CONFIG_GENERIC_CLOCKEVENTS_BUILD=y
+# CONFIG_PREEMPT is not set
+CONFIG_HZ=100
+# CONFIG_AEABI is not set
+# CONFIG_ARCH_DISCONTIGMEM_ENABLE is not set
+CONFIG_SELECT_MEMORY_MODEL=y
+CONFIG_FLATMEM_MANUAL=y
+# CONFIG_DISCONTIGMEM_MANUAL is not set
+# CONFIG_SPARSEMEM_MANUAL is not set
+CONFIG_FLATMEM=y
+CONFIG_FLAT_NODE_MEM_MAP=y
+# CONFIG_SPARSEMEM_STATIC is not set
+# CONFIG_SPARSEMEM_VMEMMAP_ENABLE is not set
+CONFIG_PAGEFLAGS_EXTENDED=y
+CONFIG_SPLIT_PTLOCK_CPUS=4096
+# CONFIG_RESOURCES_64BIT is not set
+CONFIG_ZONE_DMA_FLAG=1
+CONFIG_BOUNCE=y
+CONFIG_VIRT_TO_BUS=y
+# CONFIG_LEDS is not set
+CONFIG_ALIGNMENT_TRAP=y
+
+#
+# Boot options
+#
+CONFIG_ZBOOT_ROM_TEXT=0x0
+CONFIG_ZBOOT_ROM_BSS=0x0
+CONFIG_CMDLINE=""
+# CONFIG_XIP_KERNEL is not set
+# CONFIG_KEXEC is not set
+
+#
+# Floating point emulation
+#
+
+#
+# At least one emulation must be selected
+#
+CONFIG_FPE_NWFPE=y
+# CONFIG_FPE_NWFPE_XP is not set
+# CONFIG_FPE_FASTFPE is not set
+# CONFIG_VFP is not set
+
+#
+# Userspace binary formats
+#
+CONFIG_BINFMT_ELF=y
+# CONFIG_BINFMT_AOUT is not set
+# CONFIG_BINFMT_MISC is not set
+# CONFIG_ARTHUR is not set
+
+#
+# Power management options
+#
+# CONFIG_PM is not set
+CONFIG_ARCH_SUSPEND_POSSIBLE=y
+
+#
+# Networking
+#
+CONFIG_NET=y
+
+#
+# Networking options
+#
+CONFIG_PACKET=y
+# CONFIG_PACKET_MMAP is not set
+CONFIG_UNIX=y
+CONFIG_XFRM=y
+# CONFIG_XFRM_USER is not set
+# CONFIG_XFRM_SUB_POLICY is not set
+# CONFIG_XFRM_MIGRATE is not set
+# CONFIG_XFRM_STATISTICS is not set
+CONFIG_NET_KEY=y
+# CONFIG_NET_KEY_MIGRATE is not set
+CONFIG_INET=y
+# CONFIG_IP_MULTICAST is not set
+# CONFIG_IP_ADVANCED_ROUTER is not set
+CONFIG_IP_FIB_HASH=y
+CONFIG_IP_PNP=y
+CONFIG_IP_PNP_DHCP=y
+CONFIG_IP_PNP_BOOTP=y
+CONFIG_IP_PNP_RARP=y
+CONFIG_NET_IPIP=y
+# CONFIG_NET_IPGRE is not set
+# CONFIG_ARPD is not set
+# CONFIG_SYN_COOKIES is not set
+# CONFIG_INET_AH is not set
+# CONFIG_INET_ESP is not set
+# CONFIG_INET_IPCOMP is not set
+# CONFIG_INET_XFRM_TUNNEL is not set
+CONFIG_INET_TUNNEL=y
+CONFIG_INET_XFRM_MODE_TRANSPORT=y
+CONFIG_INET_XFRM_MODE_TUNNEL=y
+CONFIG_INET_XFRM_MODE_BEET=y
+# CONFIG_INET_LRO is not set
+CONFIG_INET_DIAG=y
+CONFIG_INET_TCP_DIAG=y
+# CONFIG_TCP_CONG_ADVANCED is not set
+CONFIG_TCP_CONG_CUBIC=y
+CONFIG_DEFAULT_TCP_CONG="cubic"
+# CONFIG_TCP_MD5SIG is not set
+CONFIG_IPV6=y
+# CONFIG_IPV6_PRIVACY is not set
+# CONFIG_IPV6_ROUTER_PREF is not set
+# CONFIG_IPV6_OPTIMISTIC_DAD is not set
+# CONFIG_INET6_AH is not set
+# CONFIG_INET6_ESP is not set
+# CONFIG_INET6_IPCOMP is not set
+# CONFIG_IPV6_MIP6 is not set
+# CONFIG_INET6_XFRM_TUNNEL is not set
+# CONFIG_INET6_TUNNEL is not set
+CONFIG_INET6_XFRM_MODE_TRANSPORT=y
+CONFIG_INET6_XFRM_MODE_TUNNEL=y
+CONFIG_INET6_XFRM_MODE_BEET=y
+# CONFIG_INET6_XFRM_MODE_ROUTEOPTIMIZATION is not set
+CONFIG_IPV6_SIT=y
+CONFIG_IPV6_NDISC_NODETYPE=y
+# CONFIG_IPV6_TUNNEL is not set
+# CONFIG_IPV6_MULTIPLE_TABLES is not set
+# CONFIG_IPV6_MROUTE is not set
+# CONFIG_NETWORK_SECMARK is not set
+# CONFIG_NETFILTER is not set
+# CONFIG_IP_DCCP is not set
+# CONFIG_IP_SCTP is not set
+# CONFIG_TIPC is not set
+# CONFIG_ATM is not set
+# CONFIG_BRIDGE is not set
+# CONFIG_VLAN_8021Q is not set
+# CONFIG_DECNET is not set
+# CONFIG_LLC2 is not set
+# CONFIG_IPX is not set
+# CONFIG_ATALK is not set
+# CONFIG_X25 is not set
+# CONFIG_LAPB is not set
+# CONFIG_ECONET is not set
+# CONFIG_WAN_ROUTER is not set
+# CONFIG_NET_SCHED is not set
+
+#
+# Network testing
+#
+# CONFIG_NET_PKTGEN is not set
+# CONFIG_HAMRADIO is not set
+# CONFIG_CAN is not set
+# CONFIG_IRDA is not set
+# CONFIG_BT is not set
+# CONFIG_AF_RXRPC is not set
+
+#
+# Wireless
+#
+# CONFIG_CFG80211 is not set
+# CONFIG_WIRELESS_EXT is not set
+# CONFIG_MAC80211 is not set
+# CONFIG_IEEE80211 is not set
+# CONFIG_RFKILL is not set
+# CONFIG_NET_9P is not set
+
+#
+# Device Drivers
+#
+
+#
+# Generic Driver Options
+#
+CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
+CONFIG_STANDALONE=y
+# CONFIG_PREVENT_FIRMWARE_BUILD is not set
+CONFIG_FW_LOADER=y
+CONFIG_FIRMWARE_IN_KERNEL=y
+CONFIG_EXTRA_FIRMWARE=""
+# CONFIG_SYS_HYPERVISOR is not set
+# CONFIG_CONNECTOR is not set
+CONFIG_MTD=y
+# CONFIG_MTD_DEBUG is not set
+# CONFIG_MTD_CONCAT is not set
+CONFIG_MTD_PARTITIONS=y
+# CONFIG_MTD_REDBOOT_PARTS is not set
+# CONFIG_MTD_CMDLINE_PARTS is not set
+# CONFIG_MTD_AFS_PARTS is not set
+# CONFIG_MTD_AR7_PARTS is not set
+
+#
+# User Modules And Translation Layers
+#
+CONFIG_MTD_CHAR=y
+CONFIG_MTD_BLKDEVS=y
+CONFIG_MTD_BLOCK=y
+# CONFIG_FTL is not set
+CONFIG_NFTL=y
+CONFIG_NFTL_RW=y
+# CONFIG_INFTL is not set
+# CONFIG_RFD_FTL is not set
+# CONFIG_SSFDC is not set
+# CONFIG_MTD_OOPS is not set
+
+#
+# RAM/ROM/Flash chip drivers
+#
+# CONFIG_MTD_CFI is not set
+# CONFIG_MTD_JEDECPROBE is not set
+CONFIG_MTD_MAP_BANK_WIDTH_1=y
+CONFIG_MTD_MAP_BANK_WIDTH_2=y
+CONFIG_MTD_MAP_BANK_WIDTH_4=y
+# CONFIG_MTD_MAP_BANK_WIDTH_8 is not set
+# CONFIG_MTD_MAP_BANK_WIDTH_16 is not set
+# CONFIG_MTD_MAP_BANK_WIDTH_32 is not set
+CONFIG_MTD_CFI_I1=y
+CONFIG_MTD_CFI_I2=y
+# CONFIG_MTD_CFI_I4 is not set
+# CONFIG_MTD_CFI_I8 is not set
+# CONFIG_MTD_RAM is not set
+# CONFIG_MTD_ROM is not set
+# CONFIG_MTD_ABSENT is not set
+
+#
+# Mapping drivers for chip access
+#
+# CONFIG_MTD_COMPLEX_MAPPINGS is not set
+# CONFIG_MTD_PLATRAM is not set
+
+#
+# Self-contained MTD device drivers
+#
+# CONFIG_MTD_DATAFLASH is not set
+# CONFIG_MTD_M25P80 is not set
+# CONFIG_MTD_SLRAM is not set
+# CONFIG_MTD_PHRAM is not set
+# CONFIG_MTD_MTDRAM is not set
+CONFIG_MTD_BLOCK2MTD=y
+
+#
+# Disk-On-Chip Device Drivers
+#
+# CONFIG_MTD_DOC2000 is not set
+# CONFIG_MTD_DOC2001 is not set
+# CONFIG_MTD_DOC2001PLUS is not set
+CONFIG_MTD_NAND=y
+CONFIG_MTD_NAND_VERIFY_WRITE=y
+CONFIG_MTD_NAND_ECC_SMC=y
+# CONFIG_MTD_NAND_MUSEUM_IDS is not set
+CONFIG_MTD_NAND_IDS=y
+# CONFIG_MTD_NAND_DISKONCHIP is not set
+CONFIG_MTD_NAND_ATMEL=y
+CONFIG_MTD_NAND_ATMEL_ECC_HW=y
+# CONFIG_MTD_NAND_ATMEL_ECC_SOFT is not set
+# CONFIG_MTD_NAND_ATMEL_ECC_NONE is not set
+# CONFIG_MTD_NAND_NANDSIM is not set
+CONFIG_MTD_NAND_PLATFORM=y
+# CONFIG_MTD_ALAUDA is not set
+# CONFIG_MTD_ONENAND is not set
+
+#
+# UBI - Unsorted block images
+#
+# CONFIG_MTD_UBI is not set
+# CONFIG_PARPORT is not set
+CONFIG_BLK_DEV=y
+# CONFIG_BLK_DEV_COW_COMMON is not set
+CONFIG_BLK_DEV_LOOP=y
+# CONFIG_BLK_DEV_CRYPTOLOOP is not set
+CONFIG_BLK_DEV_NBD=y
+# CONFIG_BLK_DEV_UB is not set
+# CONFIG_BLK_DEV_RAM is not set
+# CONFIG_CDROM_PKTCDVD is not set
+# CONFIG_ATA_OVER_ETH is not set
+CONFIG_MISC_DEVICES=y
+CONFIG_ATMEL_PWM=y
+CONFIG_ATMEL_TCLIB=y
+CONFIG_ATMEL_TCB_CLKSRC=y
+CONFIG_ATMEL_TCB_CLKSRC_BLOCK=0
+# CONFIG_EEPROM_93CX6 is not set
+# CONFIG_ATMEL_SSC is not set
+# CONFIG_ENCLOSURE_SERVICES is not set
+CONFIG_HAVE_IDE=y
+# CONFIG_IDE is not set
+
+#
+# SCSI device support
+#
+# CONFIG_RAID_ATTRS is not set
+CONFIG_SCSI=y
+CONFIG_SCSI_DMA=y
+# CONFIG_SCSI_TGT is not set
+# CONFIG_SCSI_NETLINK is not set
+CONFIG_SCSI_PROC_FS=y
+
+#
+# SCSI support type (disk, tape, CD-ROM)
+#
+# CONFIG_BLK_DEV_SD is not set
+# CONFIG_CHR_DEV_ST is not set
+# CONFIG_CHR_DEV_OSST is not set
+# CONFIG_BLK_DEV_SR is not set
+CONFIG_CHR_DEV_SG=y
+# CONFIG_CHR_DEV_SCH is not set
+
+#
+# Some SCSI devices (e.g. CD jukebox) support multiple LUNs
+#
+# CONFIG_SCSI_MULTI_LUN is not set
+# CONFIG_SCSI_CONSTANTS is not set
+# CONFIG_SCSI_LOGGING is not set
+# CONFIG_SCSI_SCAN_ASYNC is not set
+CONFIG_SCSI_WAIT_SCAN=m
+
+#
+# SCSI Transports
+#
+# CONFIG_SCSI_SPI_ATTRS is not set
+# CONFIG_SCSI_FC_ATTRS is not set
+# CONFIG_SCSI_ISCSI_ATTRS is not set
+# CONFIG_SCSI_SAS_LIBSAS is not set
+# CONFIG_SCSI_SRP_ATTRS is not set
+CONFIG_SCSI_LOWLEVEL=y
+# CONFIG_ISCSI_TCP is not set
+# CONFIG_SCSI_DEBUG is not set
+# CONFIG_SCSI_DH is not set
+# CONFIG_ATA is not set
+# CONFIG_MD is not set
+CONFIG_NETDEVICES=y
+# CONFIG_DUMMY is not set
+# CONFIG_BONDING is not set
+# CONFIG_MACVLAN is not set
+# CONFIG_EQUALIZER is not set
+# CONFIG_TUN is not set
+# CONFIG_VETH is not set
+CONFIG_PHYLIB=y
+
+#
+# MII PHY device drivers
+#
+# CONFIG_MARVELL_PHY is not set
+# CONFIG_DAVICOM_PHY is not set
+# CONFIG_QSEMI_PHY is not set
+# CONFIG_LXT_PHY is not set
+# CONFIG_CICADA_PHY is not set
+# CONFIG_VITESSE_PHY is not set
+CONFIG_SMSC_PHY=y
+# CONFIG_BROADCOM_PHY is not set
+# CONFIG_ICPLUS_PHY is not set
+# CONFIG_REALTEK_PHY is not set
+# CONFIG_FIXED_PHY is not set
+# CONFIG_MDIO_BITBANG is not set
+CONFIG_NET_ETHERNET=y
+# CONFIG_MII is not set
+CONFIG_MACB=y
+# CONFIG_AX88796 is not set
+# CONFIG_SMC91X is not set
+# CONFIG_DM9000 is not set
+# CONFIG_ENC28J60 is not set
+# CONFIG_IBM_NEW_EMAC_ZMII is not set
+# CONFIG_IBM_NEW_EMAC_RGMII is not set
+# CONFIG_IBM_NEW_EMAC_TAH is not set
+# CONFIG_IBM_NEW_EMAC_EMAC4 is not set
+# CONFIG_B44 is not set
+# CONFIG_NETDEV_1000 is not set
+# CONFIG_NETDEV_10000 is not set
+
+#
+# Wireless LAN
+#
+# CONFIG_WLAN_PRE80211 is not set
+# CONFIG_WLAN_80211 is not set
+# CONFIG_IWLWIFI_LEDS is not set
+
+#
+# USB Network Adapters
+#
+# CONFIG_USB_CATC is not set
+# CONFIG_USB_KAWETH is not set
+# CONFIG_USB_PEGASUS is not set
+# CONFIG_USB_RTL8150 is not set
+# CONFIG_USB_USBNET is not set
+# CONFIG_WAN is not set
+# CONFIG_PPP is not set
+# CONFIG_SLIP is not set
+# CONFIG_NETCONSOLE is not set
+# CONFIG_NETPOLL is not set
+# CONFIG_NET_POLL_CONTROLLER is not set
+# CONFIG_ISDN is not set
+
+#
+# Input device support
+#
+CONFIG_INPUT=y
+# CONFIG_INPUT_FF_MEMLESS is not set
+# CONFIG_INPUT_POLLDEV is not set
+
+#
+# Userland interfaces
+#
+CONFIG_INPUT_MOUSEDEV=y
+# CONFIG_INPUT_MOUSEDEV_PSAUX is not set
+CONFIG_INPUT_MOUSEDEV_SCREEN_X=1024
+CONFIG_INPUT_MOUSEDEV_SCREEN_Y=768
+# CONFIG_INPUT_JOYDEV is not set
+CONFIG_INPUT_EVDEV=y
+# CONFIG_INPUT_EVBUG is not set
+
+#
+# Input Device Drivers
+#
+CONFIG_INPUT_KEYBOARD=y
+CONFIG_KEYBOARD_ATKBD=y
+# CONFIG_KEYBOARD_SUNKBD is not set
+# CONFIG_KEYBOARD_LKKBD is not set
+# CONFIG_KEYBOARD_XTKBD is not set
+# CONFIG_KEYBOARD_NEWTON is not set
+# CONFIG_KEYBOARD_STOWAWAY is not set
+# CONFIG_KEYBOARD_GPIO is not set
+CONFIG_INPUT_MOUSE=y
+CONFIG_MOUSE_PS2=y
+CONFIG_MOUSE_PS2_ALPS=y
+CONFIG_MOUSE_PS2_LOGIPS2PP=y
+CONFIG_MOUSE_PS2_SYNAPTICS=y
+CONFIG_MOUSE_PS2_LIFEBOOK=y
+CONFIG_MOUSE_PS2_TRACKPOINT=y
+# CONFIG_MOUSE_PS2_TOUCHKIT is not set
+# CONFIG_MOUSE_SERIAL is not set
+# CONFIG_MOUSE_APPLETOUCH is not set
+# CONFIG_MOUSE_VSXXXAA is not set
+# CONFIG_MOUSE_GPIO is not set
+# CONFIG_INPUT_JOYSTICK is not set
+# CONFIG_INPUT_TABLET is not set
+CONFIG_INPUT_TOUCHSCREEN=y
+CONFIG_TOUCHSCREEN_ADS7846=y
+# CONFIG_TOUCHSCREEN_FUJITSU is not set
+# CONFIG_TOUCHSCREEN_GUNZE is not set
+# CONFIG_TOUCHSCREEN_ELO is not set
+# CONFIG_TOUCHSCREEN_MTOUCH is not set
+# CONFIG_TOUCHSCREEN_INEXIO is not set
+# CONFIG_TOUCHSCREEN_MK712 is not set
+# CONFIG_TOUCHSCREEN_PENMOUNT is not set
+# CONFIG_TOUCHSCREEN_TOUCHRIGHT is not set
+# CONFIG_TOUCHSCREEN_TOUCHWIN is not set
+# CONFIG_TOUCHSCREEN_UCB1400 is not set
+# CONFIG_TOUCHSCREEN_USB_COMPOSITE is not set
+# CONFIG_TOUCHSCREEN_TOUCHIT213 is not set
+# CONFIG_INPUT_MISC is not set
+
+#
+# Hardware I/O ports
+#
+CONFIG_SERIO=y
+CONFIG_SERIO_SERPORT=y
+CONFIG_SERIO_LIBPS2=y
+# CONFIG_SERIO_RAW is not set
+# CONFIG_GAMEPORT is not set
+
+#
+# Character devices
+#
+CONFIG_VT=y
+CONFIG_CONSOLE_TRANSLATIONS=y
+CONFIG_VT_CONSOLE=y
+CONFIG_HW_CONSOLE=y
+CONFIG_VT_HW_CONSOLE_BINDING=y
+# CONFIG_DEVKMEM is not set
+CONFIG_SERIAL_NONSTANDARD=y
+# CONFIG_N_HDLC is not set
+# CONFIG_RISCOM8 is not set
+# CONFIG_SPECIALIX is not set
+# CONFIG_RIO is not set
+# CONFIG_STALDRV is not set
+
+#
+# Serial drivers
+#
+# CONFIG_SERIAL_8250 is not set
+
+#
+# Non-8250 serial port support
+#
+CONFIG_SERIAL_ATMEL=y
+CONFIG_SERIAL_ATMEL_CONSOLE=y
+# CONFIG_SERIAL_ATMEL_PDC is not set
+# CONFIG_SERIAL_ATMEL_TTYAT is not set
+CONFIG_SERIAL_CORE=y
+CONFIG_SERIAL_CORE_CONSOLE=y
+CONFIG_UNIX98_PTYS=y
+CONFIG_LEGACY_PTYS=y
+CONFIG_LEGACY_PTY_COUNT=256
+# CONFIG_IPMI_HANDLER is not set
+# CONFIG_HW_RANDOM is not set
+# CONFIG_NVRAM is not set
+# CONFIG_R3964 is not set
+# CONFIG_RAW_DRIVER is not set
+# CONFIG_TCG_TPM is not set
+CONFIG_I2C=y
+CONFIG_I2C_BOARDINFO=y
+CONFIG_I2C_CHARDEV=y
+
+#
+# I2C Hardware Bus support
+#
+
+#
+# I2C system bus drivers (mostly embedded / system-on-chip)
+#
+# CONFIG_I2C_GPIO is not set
+# CONFIG_I2C_OCORES is not set
+# CONFIG_I2C_SIMTEC is not set
+
+#
+# External I2C/SMBus adapter drivers
+#
+# CONFIG_I2C_PARPORT_LIGHT is not set
+# CONFIG_I2C_TAOS_EVM is not set
+# CONFIG_I2C_TINY_USB is not set
+
+#
+# Other I2C/SMBus bus drivers
+#
+# CONFIG_I2C_PCA_PLATFORM is not set
+# CONFIG_I2C_STUB is not set
+
+#
+# Miscellaneous I2C Chip support
+#
+# CONFIG_DS1682 is not set
+# CONFIG_AT24 is not set
+# CONFIG_SENSORS_EEPROM is not set
+# CONFIG_SENSORS_PCF8574 is not set
+# CONFIG_PCF8575 is not set
+# CONFIG_SENSORS_PCA9539 is not set
+# CONFIG_SENSORS_PCF8591 is not set
+# CONFIG_SENSORS_MAX6875 is not set
+# CONFIG_SENSORS_TSL2550 is not set
+# CONFIG_I2C_DEBUG_CORE is not set
+# CONFIG_I2C_DEBUG_ALGO is not set
+# CONFIG_I2C_DEBUG_BUS is not set
+# CONFIG_I2C_DEBUG_CHIP is not set
+CONFIG_SPI=y
+CONFIG_SPI_MASTER=y
+
+#
+# SPI Master Controller Drivers
+#
+CONFIG_SPI_ATMEL=y
+# CONFIG_SPI_BITBANG is not set
+
+#
+# SPI Protocol Masters
+#
+# CONFIG_SPI_AT25 is not set
+# CONFIG_SPI_SPIDEV is not set
+# CONFIG_SPI_TLE62X0 is not set
+# CONFIG_W1 is not set
+# CONFIG_POWER_SUPPLY is not set
+# CONFIG_HWMON is not set
+# CONFIG_WATCHDOG is not set
+
+#
+# Sonics Silicon Backplane
+#
+CONFIG_SSB_POSSIBLE=y
+# CONFIG_SSB is not set
+
+#
+# Multifunction device drivers
+#
+# CONFIG_MFD_CORE is not set
+# CONFIG_MFD_SM501 is not set
+# CONFIG_HTC_PASIC3 is not set
+
+#
+# Multimedia devices
+#
+
+#
+# Multimedia core support
+#
+# CONFIG_VIDEO_DEV is not set
+# CONFIG_DVB_CORE is not set
+# CONFIG_VIDEO_MEDIA is not set
+
+#
+# Multimedia drivers
+#
+# CONFIG_DAB is not set
+
+#
+# Graphics support
+#
+# CONFIG_VGASTATE is not set
+CONFIG_VIDEO_OUTPUT_CONTROL=y
+CONFIG_FB=y
+# CONFIG_FIRMWARE_EDID is not set
+# CONFIG_FB_DDC is not set
+CONFIG_FB_CFB_FILLRECT=y
+CONFIG_FB_CFB_COPYAREA=y
+CONFIG_FB_CFB_IMAGEBLIT=y
+# CONFIG_FB_CFB_REV_PIXELS_IN_BYTE is not set
+# CONFIG_FB_SYS_FILLRECT is not set
+# CONFIG_FB_SYS_COPYAREA is not set
+# CONFIG_FB_SYS_IMAGEBLIT is not set
+# CONFIG_FB_FOREIGN_ENDIAN is not set
+# CONFIG_FB_SYS_FOPS is not set
+# CONFIG_FB_SVGALIB is not set
+# CONFIG_FB_MACMODES is not set
+# CONFIG_FB_BACKLIGHT is not set
+# CONFIG_FB_MODE_HELPERS is not set
+# CONFIG_FB_TILEBLITTING is not set
+
+#
+# Frame buffer hardware drivers
+#
+# CONFIG_FB_S1D13XXX is not set
+CONFIG_FB_ATMEL=y
+# CONFIG_FB_VIRTUAL is not set
+CONFIG_BACKLIGHT_LCD_SUPPORT=y
+CONFIG_LCD_CLASS_DEVICE=y
+# CONFIG_LCD_LTV350QV is not set
+# CONFIG_LCD_ILI9320 is not set
+# CONFIG_LCD_VGG2432A4 is not set
+# CONFIG_LCD_PLATFORM is not set
+CONFIG_BACKLIGHT_CLASS_DEVICE=y
+CONFIG_BACKLIGHT_ATMEL_LCDC=y
+# CONFIG_BACKLIGHT_ATMEL_PWM is not set
+# CONFIG_BACKLIGHT_CORGI is not set
+
+#
+# Display device support
+#
+# CONFIG_DISPLAY_SUPPORT is not set
+
+#
+# Console display driver support
+#
+# CONFIG_VGA_CONSOLE is not set
+CONFIG_DUMMY_CONSOLE=y
+CONFIG_FRAMEBUFFER_CONSOLE=y
+CONFIG_FRAMEBUFFER_CONSOLE_DETECT_PRIMARY=y
+# CONFIG_FRAMEBUFFER_CONSOLE_ROTATION is not set
+# CONFIG_FONTS is not set
+CONFIG_FONT_8x8=y
+CONFIG_FONT_8x16=y
+CONFIG_LOGO=y
+CONFIG_LOGO_LINUX_MONO=y
+CONFIG_LOGO_LINUX_VGA16=y
+CONFIG_LOGO_LINUX_CLUT224=y
+# CONFIG_SOUND is not set
+CONFIG_HID_SUPPORT=y
+CONFIG_HID=y
+CONFIG_HID_DEBUG=y
+# CONFIG_HIDRAW is not set
+
+#
+# USB Input Devices
+#
+CONFIG_USB_HID=y
+# CONFIG_USB_HIDINPUT_POWERBOOK is not set
+# CONFIG_HID_FF is not set
+# CONFIG_USB_HIDDEV is not set
+CONFIG_USB_SUPPORT=y
+CONFIG_USB_ARCH_HAS_HCD=y
+CONFIG_USB_ARCH_HAS_OHCI=y
+# CONFIG_USB_ARCH_HAS_EHCI is not set
+CONFIG_USB=y
+# CONFIG_USB_DEBUG is not set
+# CONFIG_USB_ANNOUNCE_NEW_DEVICES is not set
+
+#
+# Miscellaneous USB options
+#
+CONFIG_USB_DEVICEFS=y
+CONFIG_USB_DEVICE_CLASS=y
+# CONFIG_USB_DYNAMIC_MINORS is not set
+# CONFIG_USB_OTG is not set
+
+#
+# USB Host Controller Drivers
+#
+# CONFIG_USB_C67X00_HCD is not set
+# CONFIG_USB_ISP116X_HCD is not set
+# CONFIG_USB_ISP1760_HCD is not set
+CONFIG_USB_OHCI_HCD=y
+# CONFIG_USB_OHCI_BIG_ENDIAN_DESC is not set
+# CONFIG_USB_OHCI_BIG_ENDIAN_MMIO is not set
+CONFIG_USB_OHCI_LITTLE_ENDIAN=y
+# CONFIG_USB_SL811_HCD is not set
+# CONFIG_USB_R8A66597_HCD is not set
+
+#
+# USB Device Class drivers
+#
+# CONFIG_USB_ACM is not set
+# CONFIG_USB_PRINTER is not set
+# CONFIG_USB_WDM is not set
+
+#
+# NOTE: USB_STORAGE enables SCSI, and 'SCSI disk support'
+#
+
+#
+# may also be needed; see USB_STORAGE Help for more information
+#
+CONFIG_USB_STORAGE=y
+# CONFIG_USB_STORAGE_DEBUG is not set
+# CONFIG_USB_STORAGE_DATAFAB is not set
+# CONFIG_USB_STORAGE_FREECOM is not set
+# CONFIG_USB_STORAGE_ISD200 is not set
+# CONFIG_USB_STORAGE_DPCM is not set
+# CONFIG_USB_STORAGE_USBAT is not set
+# CONFIG_USB_STORAGE_SDDR09 is not set
+# CONFIG_USB_STORAGE_SDDR55 is not set
+# CONFIG_USB_STORAGE_JUMPSHOT is not set
+# CONFIG_USB_STORAGE_ALAUDA is not set
+# CONFIG_USB_STORAGE_ONETOUCH is not set
+# CONFIG_USB_STORAGE_KARMA is not set
+# CONFIG_USB_STORAGE_CYPRESS_ATACB is not set
+# CONFIG_USB_LIBUSUAL is not set
+
+#
+# USB Imaging devices
+#
+# CONFIG_USB_MDC800 is not set
+# CONFIG_USB_MICROTEK is not set
+CONFIG_USB_MON=y
+
+#
+# USB port drivers
+#
+# CONFIG_USB_SERIAL is not set
+
+#
+# USB Miscellaneous drivers
+#
+# CONFIG_USB_EMI62 is not set
+# CONFIG_USB_EMI26 is not set
+# CONFIG_USB_ADUTUX is not set
+# CONFIG_USB_AUERSWALD is not set
+# CONFIG_USB_RIO500 is not set
+# CONFIG_USB_LEGOTOWER is not set
+# CONFIG_USB_LCD is not set
+# CONFIG_USB_BERRY_CHARGE is not set
+# CONFIG_USB_LED is not set
+# CONFIG_USB_CYPRESS_CY7C63 is not set
+# CONFIG_USB_CYTHERM is not set
+# CONFIG_USB_PHIDGET is not set
+# CONFIG_USB_IDMOUSE is not set
+# CONFIG_USB_FTDI_ELAN is not set
+# CONFIG_USB_APPLEDISPLAY is not set
+# CONFIG_USB_LD is not set
+# CONFIG_USB_TRANCEVIBRATOR is not set
+# CONFIG_USB_IOWARRIOR is not set
+# CONFIG_USB_TEST is not set
+# CONFIG_USB_ISIGHTFW is not set
+# CONFIG_USB_GADGET is not set
+CONFIG_MMC=y
+# CONFIG_MMC_DEBUG is not set
+# CONFIG_MMC_UNSAFE_RESUME is not set
+
+#
+# MMC/SD Card Drivers
+#
+CONFIG_MMC_BLOCK=y
+CONFIG_MMC_BLOCK_BOUNCE=y
+CONFIG_SDIO_UART=y
+# CONFIG_MMC_TEST is not set
+
+#
+# MMC/SD Host Controller Drivers
+#
+# CONFIG_MMC_SDHCI is not set
+CONFIG_MMC_AT91=y
+# CONFIG_MMC_SPI is not set
+# CONFIG_NEW_LEDS is not set
+CONFIG_RTC_LIB=y
+# CONFIG_RTC_CLASS is not set
+# CONFIG_DMADEVICES is not set
+# CONFIG_UIO is not set
+
+#
+# File systems
+#
+CONFIG_EXT2_FS=y
+# CONFIG_EXT2_FS_XATTR is not set
+# CONFIG_EXT2_FS_XIP is not set
+# CONFIG_EXT3_FS is not set
+# CONFIG_EXT4DEV_FS is not set
+# CONFIG_REISERFS_FS is not set
+# CONFIG_JFS_FS is not set
+# CONFIG_FS_POSIX_ACL is not set
+# CONFIG_XFS_FS is not set
+# CONFIG_OCFS2_FS is not set
+# CONFIG_DNOTIFY is not set
+# CONFIG_INOTIFY is not set
+# CONFIG_QUOTA is not set
+CONFIG_AUTOFS_FS=y
+# CONFIG_AUTOFS4_FS is not set
+# CONFIG_FUSE_FS is not set
+
+#
+# CD-ROM/DVD Filesystems
+#
+# CONFIG_ISO9660_FS is not set
+# CONFIG_UDF_FS is not set
+
+#
+# DOS/FAT/NT Filesystems
+#
+CONFIG_FAT_FS=y
+# CONFIG_MSDOS_FS is not set
+CONFIG_VFAT_FS=y
+CONFIG_FAT_DEFAULT_CODEPAGE=437
+CONFIG_FAT_DEFAULT_IOCHARSET="iso8859-1"
+# CONFIG_NTFS_FS is not set
+
+#
+# Pseudo filesystems
+#
+CONFIG_PROC_FS=y
+CONFIG_PROC_SYSCTL=y
+CONFIG_SYSFS=y
+CONFIG_TMPFS=y
+# CONFIG_TMPFS_POSIX_ACL is not set
+# CONFIG_HUGETLB_PAGE is not set
+# CONFIG_CONFIGFS_FS is not set
+
+#
+# Miscellaneous filesystems
+#
+# CONFIG_ADFS_FS is not set
+# CONFIG_AFFS_FS is not set
+# CONFIG_HFS_FS is not set
+# CONFIG_HFSPLUS_FS is not set
+# CONFIG_BEFS_FS is not set
+# CONFIG_BFS_FS is not set
+# CONFIG_EFS_FS is not set
+CONFIG_JFFS2_FS=y
+CONFIG_JFFS2_FS_DEBUG=0
+CONFIG_JFFS2_FS_WRITEBUFFER=y
+CONFIG_JFFS2_FS_WBUF_VERIFY=y
+# CONFIG_JFFS2_SUMMARY is not set
+# CONFIG_JFFS2_FS_XATTR is not set
+# CONFIG_JFFS2_COMPRESSION_OPTIONS is not set
+CONFIG_JFFS2_ZLIB=y
+# CONFIG_JFFS2_LZO is not set
+CONFIG_JFFS2_RTIME=y
+# CONFIG_JFFS2_RUBIN is not set
+# CONFIG_CRAMFS is not set
+# CONFIG_VXFS_FS is not set
+# CONFIG_MINIX_FS is not set
+# CONFIG_OMFS_FS is not set
+# CONFIG_HPFS_FS is not set
+# CONFIG_QNX4FS_FS is not set
+# CONFIG_ROMFS_FS is not set
+# CONFIG_SYSV_FS is not set
+# CONFIG_UFS_FS is not set
+CONFIG_NETWORK_FILESYSTEMS=y
+CONFIG_NFS_FS=y
+# CONFIG_NFS_V3 is not set
+# CONFIG_NFS_V4 is not set
+CONFIG_ROOT_NFS=y
+# CONFIG_NFSD is not set
+CONFIG_LOCKD=y
+CONFIG_NFS_COMMON=y
+CONFIG_SUNRPC=y
+# CONFIG_RPCSEC_GSS_KRB5 is not set
+# CONFIG_RPCSEC_GSS_SPKM3 is not set
+# CONFIG_SMB_FS is not set
+# CONFIG_CIFS is not set
+# CONFIG_NCP_FS is not set
+# CONFIG_CODA_FS is not set
+# CONFIG_AFS_FS is not set
+
+#
+# Partition Types
+#
+# CONFIG_PARTITION_ADVANCED is not set
+CONFIG_MSDOS_PARTITION=y
+CONFIG_NLS=y
+CONFIG_NLS_DEFAULT="iso8859-1"
+# CONFIG_NLS_CODEPAGE_437 is not set
+# CONFIG_NLS_CODEPAGE_737 is not set
+# CONFIG_NLS_CODEPAGE_775 is not set
+# CONFIG_NLS_CODEPAGE_850 is not set
+# CONFIG_NLS_CODEPAGE_852 is not set
+# CONFIG_NLS_CODEPAGE_855 is not set
+# CONFIG_NLS_CODEPAGE_857 is not set
+# CONFIG_NLS_CODEPAGE_860 is not set
+# CONFIG_NLS_CODEPAGE_861 is not set
+# CONFIG_NLS_CODEPAGE_862 is not set
+# CONFIG_NLS_CODEPAGE_863 is not set
+# CONFIG_NLS_CODEPAGE_864 is not set
+# CONFIG_NLS_CODEPAGE_865 is not set
+# CONFIG_NLS_CODEPAGE_866 is not set
+# CONFIG_NLS_CODEPAGE_869 is not set
+# CONFIG_NLS_CODEPAGE_936 is not set
+# CONFIG_NLS_CODEPAGE_950 is not set
+# CONFIG_NLS_CODEPAGE_932 is not set
+# CONFIG_NLS_CODEPAGE_949 is not set
+# CONFIG_NLS_CODEPAGE_874 is not set
+# CONFIG_NLS_ISO8859_8 is not set
+# CONFIG_NLS_CODEPAGE_1250 is not set
+# CONFIG_NLS_CODEPAGE_1251 is not set
+# CONFIG_NLS_ASCII is not set
+# CONFIG_NLS_ISO8859_1 is not set
+# CONFIG_NLS_ISO8859_2 is not set
+# CONFIG_NLS_ISO8859_3 is not set
+# CONFIG_NLS_ISO8859_4 is not set
+# CONFIG_NLS_ISO8859_5 is not set
+# CONFIG_NLS_ISO8859_6 is not set
+# CONFIG_NLS_ISO8859_7 is not set
+# CONFIG_NLS_ISO8859_9 is not set
+# CONFIG_NLS_ISO8859_13 is not set
+# CONFIG_NLS_ISO8859_14 is not set
+# CONFIG_NLS_ISO8859_15 is not set
+# CONFIG_NLS_KOI8_R is not set
+# CONFIG_NLS_KOI8_U is not set
+# CONFIG_NLS_UTF8 is not set
+# CONFIG_DLM is not set
+
+#
+# Kernel hacking
+#
+# CONFIG_PRINTK_TIME is not set
+# CONFIG_ENABLE_WARN_DEPRECATED is not set
+# CONFIG_ENABLE_MUST_CHECK is not set
+CONFIG_FRAME_WARN=1024
+# CONFIG_MAGIC_SYSRQ is not set
+# CONFIG_UNUSED_SYMBOLS is not set
+# CONFIG_DEBUG_FS is not set
+# CONFIG_HEADERS_CHECK is not set
+# CONFIG_DEBUG_KERNEL is not set
+# CONFIG_SLUB_DEBUG_ON is not set
+# CONFIG_SLUB_STATS is not set
+CONFIG_DEBUG_BUGVERBOSE=y
+CONFIG_DEBUG_MEMORY_INIT=y
+CONFIG_FRAME_POINTER=y
+# CONFIG_LATENCYTOP is not set
+CONFIG_HAVE_FTRACE=y
+CONFIG_HAVE_DYNAMIC_FTRACE=y
+# CONFIG_FTRACE is not set
+# CONFIG_IRQSOFF_TRACER is not set
+# CONFIG_SCHED_TRACER is not set
+# CONFIG_CONTEXT_SWITCH_TRACER is not set
+# CONFIG_SAMPLES is not set
+CONFIG_HAVE_ARCH_KGDB=y
+# CONFIG_DEBUG_USER is not set
+
+#
+# Security options
+#
+# CONFIG_KEYS is not set
+# CONFIG_SECURITY is not set
+# CONFIG_SECURITY_FILE_CAPABILITIES is not set
+CONFIG_CRYPTO=y
+
+#
+# Crypto core or helper
+#
+# CONFIG_CRYPTO_MANAGER is not set
+# CONFIG_CRYPTO_GF128MUL is not set
+# CONFIG_CRYPTO_NULL is not set
+# CONFIG_CRYPTO_CRYPTD is not set
+# CONFIG_CRYPTO_AUTHENC is not set
+# CONFIG_CRYPTO_TEST is not set
+
+#
+# Authenticated Encryption with Associated Data
+#
+# CONFIG_CRYPTO_CCM is not set
+# CONFIG_CRYPTO_GCM is not set
+# CONFIG_CRYPTO_SEQIV is not set
+
+#
+# Block modes
+#
+# CONFIG_CRYPTO_CBC is not set
+# CONFIG_CRYPTO_CTR is not set
+# CONFIG_CRYPTO_CTS is not set
+# CONFIG_CRYPTO_ECB is not set
+# CONFIG_CRYPTO_LRW is not set
+# CONFIG_CRYPTO_PCBC is not set
+# CONFIG_CRYPTO_XTS is not set
+
+#
+# Hash modes
+#
+# CONFIG_CRYPTO_HMAC is not set
+# CONFIG_CRYPTO_XCBC is not set
+
+#
+# Digest
+#
+# CONFIG_CRYPTO_CRC32C is not set
+# CONFIG_CRYPTO_MD4 is not set
+# CONFIG_CRYPTO_MD5 is not set
+# CONFIG_CRYPTO_MICHAEL_MIC is not set
+# CONFIG_CRYPTO_RMD128 is not set
+# CONFIG_CRYPTO_RMD160 is not set
+# CONFIG_CRYPTO_RMD256 is not set
+# CONFIG_CRYPTO_RMD320 is not set
+# CONFIG_CRYPTO_SHA1 is not set
+# CONFIG_CRYPTO_SHA256 is not set
+# CONFIG_CRYPTO_SHA512 is not set
+# CONFIG_CRYPTO_TGR192 is not set
+# CONFIG_CRYPTO_WP512 is not set
+
+#
+# Ciphers
+#
+# CONFIG_CRYPTO_AES is not set
+# CONFIG_CRYPTO_ANUBIS is not set
+# CONFIG_CRYPTO_ARC4 is not set
+# CONFIG_CRYPTO_BLOWFISH is not set
+# CONFIG_CRYPTO_CAMELLIA is not set
+# CONFIG_CRYPTO_CAST5 is not set
+# CONFIG_CRYPTO_CAST6 is not set
+# CONFIG_CRYPTO_DES is not set
+# CONFIG_CRYPTO_FCRYPT is not set
+# CONFIG_CRYPTO_KHAZAD is not set
+# CONFIG_CRYPTO_SALSA20 is not set
+# CONFIG_CRYPTO_SEED is not set
+# CONFIG_CRYPTO_SERPENT is not set
+# CONFIG_CRYPTO_TEA is not set
+# CONFIG_CRYPTO_TWOFISH is not set
+
+#
+# Compression
+#
+# CONFIG_CRYPTO_DEFLATE is not set
+# CONFIG_CRYPTO_LZO is not set
+# CONFIG_CRYPTO_HW is not set
+
+#
+# Library routines
+#
+CONFIG_BITREVERSE=y
+# CONFIG_GENERIC_FIND_FIRST_BIT is not set
+# CONFIG_GENERIC_FIND_NEXT_BIT is not set
+# CONFIG_CRC_CCITT is not set
+# CONFIG_CRC16 is not set
+# CONFIG_CRC_T10DIF is not set
+# CONFIG_CRC_ITU_T is not set
+CONFIG_CRC32=y
+# CONFIG_CRC7 is not set
+# CONFIG_LIBCRC32C is not set
+CONFIG_ZLIB_INFLATE=y
+CONFIG_ZLIB_DEFLATE=y
+CONFIG_PLIST=y
+CONFIG_HAS_IOMEM=y
+CONFIG_HAS_IOPORT=y
+CONFIG_HAS_DMA=y
diff --git a/arch/arm/configs/realview-smp_defconfig b/arch/arm/configs/realview-smp_defconfig
index 0c09b23167ec..cd29824d791c 100644
--- a/arch/arm/configs/realview-smp_defconfig
+++ b/arch/arm/configs/realview-smp_defconfig
@@ -1,84 +1,111 @@
 #
 # Automatically generated make config: don't edit
-# Linux kernel version: 2.6.19-rc3
-# Wed Oct 25 14:12:00 2006
+# Linux kernel version: 2.6.28-rc2
+# Mon Nov 10 14:41:47 2008
 #
 CONFIG_ARM=y
-# CONFIG_GENERIC_TIME is not set
+CONFIG_SYS_SUPPORTS_APM_EMULATION=y
+# CONFIG_GENERIC_GPIO is not set
+CONFIG_GENERIC_TIME=y
+CONFIG_GENERIC_CLOCKEVENTS=y
 CONFIG_MMU=y
+# CONFIG_NO_IOPORT is not set
 CONFIG_GENERIC_HARDIRQS=y
+CONFIG_STACKTRACE_SUPPORT=y
+CONFIG_LOCKDEP_SUPPORT=y
 CONFIG_TRACE_IRQFLAGS_SUPPORT=y
 CONFIG_HARDIRQS_SW_RESEND=y
 CONFIG_GENERIC_IRQ_PROBE=y
 CONFIG_RWSEM_GENERIC_SPINLOCK=y
+# CONFIG_ARCH_HAS_ILOG2_U32 is not set
+# CONFIG_ARCH_HAS_ILOG2_U64 is not set
 CONFIG_GENERIC_HWEIGHT=y
 CONFIG_GENERIC_CALIBRATE_DELAY=y
+CONFIG_GENERIC_HARDIRQS_NO__DO_IRQ=y
 CONFIG_VECTORS_BASE=0xffff0000
 CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config"
 
 #
-# Code maturity level options
+# General setup
 #
 CONFIG_EXPERIMENTAL=y
 CONFIG_LOCK_KERNEL=y
 CONFIG_INIT_ENV_ARG_LIMIT=32
-
-#
-# General setup
-#
 CONFIG_LOCALVERSION=""
 CONFIG_LOCALVERSION_AUTO=y
 # CONFIG_SWAP is not set
 CONFIG_SYSVIPC=y
-# CONFIG_IPC_NS is not set
+CONFIG_SYSVIPC_SYSCTL=y
 # CONFIG_POSIX_MQUEUE is not set
 # CONFIG_BSD_PROCESS_ACCT is not set
 # CONFIG_TASKSTATS is not set
-# CONFIG_UTS_NS is not set
 # CONFIG_AUDIT is not set
 # CONFIG_IKCONFIG is not set
-# CONFIG_CPUSETS is not set
+CONFIG_LOG_BUF_SHIFT=14
+# CONFIG_CGROUPS is not set
+# CONFIG_GROUP_SCHED is not set
+CONFIG_SYSFS_DEPRECATED=y
+CONFIG_SYSFS_DEPRECATED_V2=y
 # CONFIG_RELAY is not set
-CONFIG_INITRAMFS_SOURCE=""
+CONFIG_NAMESPACES=y
+# CONFIG_UTS_NS is not set
+# CONFIG_IPC_NS is not set
+# CONFIG_USER_NS is not set
+# CONFIG_PID_NS is not set
+# CONFIG_BLK_DEV_INITRD is not set
 CONFIG_CC_OPTIMIZE_FOR_SIZE=y
 CONFIG_SYSCTL=y
 # CONFIG_EMBEDDED is not set
 CONFIG_UID16=y
-# CONFIG_SYSCTL_SYSCALL is not set
+CONFIG_SYSCTL_SYSCALL=y
 CONFIG_KALLSYMS=y
-CONFIG_KALLSYMS_ALL=y
+# CONFIG_KALLSYMS_ALL is not set
 # CONFIG_KALLSYMS_EXTRA_PASS is not set
 CONFIG_HOTPLUG=y
 CONFIG_PRINTK=y
 CONFIG_BUG=y
 CONFIG_ELF_CORE=y
+CONFIG_COMPAT_BRK=y
 CONFIG_BASE_FULL=y
 CONFIG_FUTEX=y
+CONFIG_ANON_INODES=y
 CONFIG_EPOLL=y
+CONFIG_SIGNALFD=y
+CONFIG_TIMERFD=y
+CONFIG_EVENTFD=y
 CONFIG_SHMEM=y
-CONFIG_SLAB=y
+CONFIG_AIO=y
 CONFIG_VM_EVENT_COUNTERS=y
+CONFIG_SLAB=y
+# CONFIG_SLUB is not set
+# CONFIG_SLOB is not set
+# CONFIG_PROFILING is not set
+# CONFIG_MARKERS is not set
+CONFIG_HAVE_OPROFILE=y
+# CONFIG_KPROBES is not set
+CONFIG_HAVE_KPROBES=y
+CONFIG_HAVE_KRETPROBES=y
+CONFIG_USE_GENERIC_SMP_HELPERS=y
+CONFIG_HAVE_CLK=y
+CONFIG_HAVE_GENERIC_DMA_COHERENT=y
+CONFIG_SLABINFO=y
 CONFIG_RT_MUTEXES=y
 # CONFIG_TINY_SHMEM is not set
 CONFIG_BASE_SMALL=0
-# CONFIG_SLOB is not set
-
-#
-# Loadable module support
-#
 CONFIG_MODULES=y
+# CONFIG_MODULE_FORCE_LOAD is not set
 CONFIG_MODULE_UNLOAD=y
 # CONFIG_MODULE_FORCE_UNLOAD is not set
 # CONFIG_MODVERSIONS is not set
 # CONFIG_MODULE_SRCVERSION_ALL is not set
-# CONFIG_KMOD is not set
+CONFIG_KMOD=y
 CONFIG_STOP_MACHINE=y
-
-#
-# Block layer
-#
 CONFIG_BLOCK=y
+# CONFIG_LBD is not set
 # CONFIG_BLK_DEV_IO_TRACE is not set
+# CONFIG_LSF is not set
+# CONFIG_BLK_DEV_BSG is not set
+# CONFIG_BLK_DEV_INTEGRITY is not set
 
 #
 # IO Schedulers
@@ -92,6 +119,8 @@ CONFIG_DEFAULT_DEADLINE=y
 # CONFIG_DEFAULT_CFQ is not set
 # CONFIG_DEFAULT_NOOP is not set
 CONFIG_DEFAULT_IOSCHED="deadline"
+CONFIG_CLASSIC_RCU=y
+# CONFIG_FREEZER is not set
 
 #
 # System Type
@@ -103,19 +132,26 @@ CONFIG_ARCH_REALVIEW=y
 # CONFIG_ARCH_AT91 is not set
 # CONFIG_ARCH_CLPS7500 is not set
 # CONFIG_ARCH_CLPS711X is not set
-# CONFIG_ARCH_CO285 is not set
 # CONFIG_ARCH_EBSA110 is not set
 # CONFIG_ARCH_EP93XX is not set
 # CONFIG_ARCH_FOOTBRIDGE is not set
 # CONFIG_ARCH_NETX is not set
 # CONFIG_ARCH_H720X is not set
 # CONFIG_ARCH_IMX is not set
+# CONFIG_ARCH_IOP13XX is not set
 # CONFIG_ARCH_IOP32X is not set
 # CONFIG_ARCH_IOP33X is not set
-# CONFIG_ARCH_IXP4XX is not set
-# CONFIG_ARCH_IXP2000 is not set
 # CONFIG_ARCH_IXP23XX is not set
+# CONFIG_ARCH_IXP2000 is not set
+# CONFIG_ARCH_IXP4XX is not set
 # CONFIG_ARCH_L7200 is not set
+# CONFIG_ARCH_KIRKWOOD is not set
+# CONFIG_ARCH_KS8695 is not set
+# CONFIG_ARCH_NS9XXX is not set
+# CONFIG_ARCH_LOKI is not set
+# CONFIG_ARCH_MV78XX0 is not set
+# CONFIG_ARCH_MXC is not set
+# CONFIG_ARCH_ORION5X is not set
 # CONFIG_ARCH_PNX4008 is not set
 # CONFIG_ARCH_PXA is not set
 # CONFIG_ARCH_RPC is not set
@@ -123,13 +159,29 @@ CONFIG_ARCH_REALVIEW=y
 # CONFIG_ARCH_S3C2410 is not set
 # CONFIG_ARCH_SHARK is not set
 # CONFIG_ARCH_LH7A40X is not set
+# CONFIG_ARCH_DAVINCI is not set
 # CONFIG_ARCH_OMAP is not set
+# CONFIG_ARCH_MSM is not set
+
+#
+# Boot options
+#
+
+#
+# Power management
+#
 
 #
 # RealView platform type
 #
 CONFIG_MACH_REALVIEW_EB=y
-CONFIG_REALVIEW_MPCORE=y
+# CONFIG_REALVIEW_EB_A9MP is not set
+CONFIG_REALVIEW_EB_ARM11MP=y
+# CONFIG_REALVIEW_EB_ARM11MP_REVB is not set
+CONFIG_MACH_REALVIEW_PB11MP=y
+# CONFIG_MACH_REALVIEW_PB1176 is not set
+# CONFIG_MACH_REALVIEW_PBA8 is not set
+CONFIG_REALVIEW_HIGH_PHYS_OFFSET=y
 
 #
 # Processor Type
@@ -138,12 +190,15 @@ CONFIG_CPU_32=y
 # CONFIG_CPU_ARM926T is not set
 CONFIG_CPU_V6=y
 CONFIG_CPU_32v6K=y
+# CONFIG_CPU_V7 is not set
 CONFIG_CPU_32v6=y
 CONFIG_CPU_ABRT_EV6=y
+CONFIG_CPU_PABRT_NOIFAR=y
 CONFIG_CPU_CACHE_V6=y
 CONFIG_CPU_CACHE_VIPT=y
 CONFIG_CPU_COPY_V6=y
 CONFIG_CPU_TLB_V6=y
+CONFIG_CPU_HAS_ASID=y
 CONFIG_CPU_CP15=y
 CONFIG_CPU_CP15_MMU=y
 
@@ -153,9 +208,10 @@ CONFIG_CPU_CP15_MMU=y
 CONFIG_ARM_THUMB=y
 # CONFIG_CPU_ICACHE_DISABLE is not set
 # CONFIG_CPU_DCACHE_DISABLE is not set
-# CONFIG_CPU_DCACHE_WRITETHROUGH is not set
 # CONFIG_CPU_BPREDICT_DISABLE is not set
 CONFIG_HAS_TLS_REG=y
+CONFIG_OUTER_CACHE=y
+CONFIG_CACHE_L2X0=y
 CONFIG_ARM_GIC=y
 CONFIG_ICST307=y
 
@@ -163,32 +219,44 @@ CONFIG_ICST307=y
 # Bus support
 #
 CONFIG_ARM_AMBA=y
-
-#
-# PCCARD (PCMCIA/CardBus) support
-#
+# CONFIG_PCI_SYSCALL is not set
+# CONFIG_ARCH_SUPPORTS_MSI is not set
 # CONFIG_PCCARD is not set
 
 #
 # Kernel Features
 #
+# CONFIG_NO_HZ is not set
+# CONFIG_HIGH_RES_TIMERS is not set
+CONFIG_GENERIC_CLOCKEVENTS_BUILD=y
 CONFIG_SMP=y
+CONFIG_VMSPLIT_3G=y
+# CONFIG_VMSPLIT_2G is not set
+# CONFIG_VMSPLIT_1G is not set
+CONFIG_PAGE_OFFSET=0xC0000000
 CONFIG_NR_CPUS=4
 CONFIG_HOTPLUG_CPU=y
 CONFIG_LOCAL_TIMERS=y
 # CONFIG_PREEMPT is not set
 CONFIG_HZ=100
-# CONFIG_AEABI is not set
-# CONFIG_ARCH_DISCONTIGMEM_ENABLE is not set
+CONFIG_AEABI=y
+CONFIG_OABI_COMPAT=y
+CONFIG_ARCH_FLATMEM_HAS_HOLES=y
+# CONFIG_ARCH_SPARSEMEM_DEFAULT is not set
+# CONFIG_ARCH_SELECT_MEMORY_MODEL is not set
 CONFIG_SELECT_MEMORY_MODEL=y
 CONFIG_FLATMEM_MANUAL=y
 # CONFIG_DISCONTIGMEM_MANUAL is not set
 # CONFIG_SPARSEMEM_MANUAL is not set
 CONFIG_FLATMEM=y
 CONFIG_FLAT_NODE_MEM_MAP=y
-# CONFIG_SPARSEMEM_STATIC is not set
+CONFIG_PAGEFLAGS_EXTENDED=y
 CONFIG_SPLIT_PTLOCK_CPUS=4
 # CONFIG_RESOURCES_64BIT is not set
+# CONFIG_PHYS_ADDR_T_64BIT is not set
+CONFIG_ZONE_DMA_FLAG=0
+CONFIG_VIRT_TO_BUS=y
+CONFIG_UNEVICTABLE_LRU=y
 CONFIG_ALIGNMENT_TRAP=y
 
 #
@@ -198,6 +266,12 @@ CONFIG_ZBOOT_ROM_TEXT=0x0
 CONFIG_ZBOOT_ROM_BSS=0x0
 CONFIG_CMDLINE="root=/dev/nfs nfsroot=10.1.69.3:/work/nfsroot ip=dhcp console=ttyAMA0 mem=128M"
 # CONFIG_XIP_KERNEL is not set
+# CONFIG_KEXEC is not set
+
+#
+# CPU Power Management
+#
+# CONFIG_CPU_IDLE is not set
 
 #
 # Floating point emulation
@@ -206,8 +280,7 @@ CONFIG_CMDLINE="root=/dev/nfs nfsroot=10.1.69.3:/work/nfsroot ip=dhcp console=tt
 #
 # At least one emulation must be selected
 #
-CONFIG_FPE_NWFPE=y
-# CONFIG_FPE_NWFPE_XP is not set
+# CONFIG_FPE_NWFPE is not set
 # CONFIG_FPE_FASTFPE is not set
 CONFIG_VFP=y
 
@@ -215,28 +288,29 @@ CONFIG_VFP=y
 # Userspace binary formats
 #
 CONFIG_BINFMT_ELF=y
+# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
+CONFIG_HAVE_AOUT=y
 # CONFIG_BINFMT_AOUT is not set
 # CONFIG_BINFMT_MISC is not set
-# CONFIG_ARTHUR is not set
 
 #
 # Power management options
 #
 # CONFIG_PM is not set
-# CONFIG_APM is not set
-
-#
-# Networking
-#
+CONFIG_ARCH_SUSPEND_POSSIBLE=y
 CONFIG_NET=y
 
 #
 # Networking options
 #
-# CONFIG_NETDEBUG is not set
 CONFIG_PACKET=y
 # CONFIG_PACKET_MMAP is not set
 CONFIG_UNIX=y
+CONFIG_XFRM=y
+# CONFIG_XFRM_USER is not set
+# CONFIG_XFRM_SUB_POLICY is not set
+# CONFIG_XFRM_MIGRATE is not set
+# CONFIG_XFRM_STATISTICS is not set
 # CONFIG_NET_KEY is not set
 CONFIG_INET=y
 # CONFIG_IP_MULTICAST is not set
@@ -255,36 +329,25 @@ CONFIG_IP_PNP_BOOTP=y
 # CONFIG_INET_IPCOMP is not set
 # CONFIG_INET_XFRM_TUNNEL is not set
 # CONFIG_INET_TUNNEL is not set
-# CONFIG_INET_XFRM_MODE_TRANSPORT is not set
-# CONFIG_INET_XFRM_MODE_TUNNEL is not set
-# CONFIG_INET_XFRM_MODE_BEET is not set
+CONFIG_INET_XFRM_MODE_TRANSPORT=y
+CONFIG_INET_XFRM_MODE_TUNNEL=y
+CONFIG_INET_XFRM_MODE_BEET=y
+# CONFIG_INET_LRO is not set
 CONFIG_INET_DIAG=y
 CONFIG_INET_TCP_DIAG=y
 # CONFIG_TCP_CONG_ADVANCED is not set
 CONFIG_TCP_CONG_CUBIC=y
 CONFIG_DEFAULT_TCP_CONG="cubic"
+# CONFIG_TCP_MD5SIG is not set
 # CONFIG_IPV6 is not set
-# CONFIG_INET6_XFRM_TUNNEL is not set
-# CONFIG_INET6_TUNNEL is not set
 # CONFIG_NETWORK_SECMARK is not set
 # CONFIG_NETFILTER is not set
-
-#
-# DCCP Configuration (EXPERIMENTAL)
-#
 # CONFIG_IP_DCCP is not set
-
-#
-# SCTP Configuration (EXPERIMENTAL)
-#
 # CONFIG_IP_SCTP is not set
-
-#
-# TIPC Configuration (EXPERIMENTAL)
-#
 # CONFIG_TIPC is not set
 # CONFIG_ATM is not set
 # CONFIG_BRIDGE is not set
+# CONFIG_NET_DSA is not set
 # CONFIG_VLAN_8021Q is not set
 # CONFIG_DECNET is not set
 # CONFIG_LLC2 is not set
@@ -294,10 +357,6 @@ CONFIG_DEFAULT_TCP_CONG="cubic"
 # CONFIG_LAPB is not set
 # CONFIG_ECONET is not set
 # CONFIG_WAN_ROUTER is not set
-
-#
-# QoS and/or fair queueing
-#
 # CONFIG_NET_SCHED is not set
 
 #
@@ -305,9 +364,14 @@ CONFIG_DEFAULT_TCP_CONG="cubic"
 #
 # CONFIG_NET_PKTGEN is not set
 # CONFIG_HAMRADIO is not set
+# CONFIG_CAN is not set
 # CONFIG_IRDA is not set
 # CONFIG_BT is not set
-# CONFIG_IEEE80211 is not set
+# CONFIG_AF_RXRPC is not set
+# CONFIG_PHONET is not set
+# CONFIG_WIRELESS is not set
+# CONFIG_RFKILL is not set
+# CONFIG_NET_9P is not set
 
 #
 # Device Drivers
@@ -316,38 +380,37 @@ CONFIG_DEFAULT_TCP_CONG="cubic"
 #
 # Generic Driver Options
 #
+CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_STANDALONE=y
 CONFIG_PREVENT_FIRMWARE_BUILD=y
-# CONFIG_FW_LOADER is not set
+CONFIG_FW_LOADER=y
+CONFIG_FIRMWARE_IN_KERNEL=y
+CONFIG_EXTRA_FIRMWARE=""
 # CONFIG_DEBUG_DRIVER is not set
+# CONFIG_DEBUG_DEVRES is not set
 # CONFIG_SYS_HYPERVISOR is not set
-
-#
-# Connector - unified userspace <-> kernelspace linker
-#
 # CONFIG_CONNECTOR is not set
-
-#
-# Memory Technology Devices (MTD)
-#
 CONFIG_MTD=y
 # CONFIG_MTD_DEBUG is not set
-# CONFIG_MTD_CONCAT is not set
+CONFIG_MTD_CONCAT=y
 CONFIG_MTD_PARTITIONS=y
 # CONFIG_MTD_REDBOOT_PARTS is not set
 CONFIG_MTD_CMDLINE_PARTS=y
 # CONFIG_MTD_AFS_PARTS is not set
+# CONFIG_MTD_AR7_PARTS is not set
 
 #
 # User Modules And Translation Layers
 #
 CONFIG_MTD_CHAR=y
+CONFIG_MTD_BLKDEVS=y
 CONFIG_MTD_BLOCK=y
 # CONFIG_FTL is not set
 # CONFIG_NFTL is not set
 # CONFIG_INFTL is not set
 # CONFIG_RFD_FTL is not set
 # CONFIG_SSFDC is not set
+# CONFIG_MTD_OOPS is not set
 
 #
 # RAM/ROM/Flash chip drivers
@@ -373,7 +436,6 @@ CONFIG_MTD_CFI_UTIL=y
 # CONFIG_MTD_RAM is not set
 # CONFIG_MTD_ROM is not set
 # CONFIG_MTD_ABSENT is not set
-# CONFIG_MTD_OBSOLETE_CHIPS is not set
 
 #
 # Mapping drivers for chip access
@@ -397,115 +459,73 @@ CONFIG_MTD_ARM_INTEGRATOR=y
 # CONFIG_MTD_DOC2000 is not set
 # CONFIG_MTD_DOC2001 is not set
 # CONFIG_MTD_DOC2001PLUS is not set
-
-#
-# NAND Flash Device Drivers
-#
 # CONFIG_MTD_NAND is not set
-
-#
-# OneNAND Flash Device Drivers
-#
 # CONFIG_MTD_ONENAND is not set
 
 #
-# Parallel port support
+# UBI - Unsorted block images
 #
+# CONFIG_MTD_UBI is not set
 # CONFIG_PARPORT is not set
-
-#
-# Plug and Play support
-#
-
-#
-# Block devices
-#
+CONFIG_BLK_DEV=y
 # CONFIG_BLK_DEV_COW_COMMON is not set
 # CONFIG_BLK_DEV_LOOP is not set
 # CONFIG_BLK_DEV_NBD is not set
 # CONFIG_BLK_DEV_RAM is not set
-CONFIG_BLK_DEV_INITRD=y
 # CONFIG_CDROM_PKTCDVD is not set
 # CONFIG_ATA_OVER_ETH is not set
+CONFIG_MISC_DEVICES=y
+# CONFIG_EEPROM_93CX6 is not set
+# CONFIG_ENCLOSURE_SERVICES is not set
+CONFIG_HAVE_IDE=y
+# CONFIG_IDE is not set
 
 #
 # SCSI device support
 #
 # CONFIG_RAID_ATTRS is not set
 # CONFIG_SCSI is not set
+# CONFIG_SCSI_DMA is not set
 # CONFIG_SCSI_NETLINK is not set
-
-#
-# Multi-device support (RAID and LVM)
-#
+# CONFIG_ATA is not set
 # CONFIG_MD is not set
-
-#
-# Fusion MPT device support
-#
-# CONFIG_FUSION is not set
-
-#
-# IEEE 1394 (FireWire) support
-#
-
-#
-# I2O device support
-#
-
-#
-# Network device support
-#
 CONFIG_NETDEVICES=y
 # CONFIG_DUMMY is not set
 # CONFIG_BONDING is not set
+# CONFIG_MACVLAN is not set
 # CONFIG_EQUALIZER is not set
 # CONFIG_TUN is not set
-
-#
-# PHY device support
-#
+# CONFIG_VETH is not set
 # CONFIG_PHYLIB is not set
-
-#
-# Ethernet (10 or 100Mbit)
-#
 CONFIG_NET_ETHERNET=y
 CONFIG_MII=y
+# CONFIG_AX88796 is not set
 CONFIG_SMC91X=y
 # CONFIG_DM9000 is not set
-
-#
-# Ethernet (1000 Mbit)
-#
-
-#
-# Ethernet (10000 Mbit)
-#
-
-#
-# Token Ring devices
-#
-
-#
-# Wireless LAN (non-hamradio)
-#
-# CONFIG_NET_RADIO is not set
-
-#
-# Wan interfaces
-#
+CONFIG_SMC911X=y
+# CONFIG_IBM_NEW_EMAC_ZMII is not set
+# CONFIG_IBM_NEW_EMAC_RGMII is not set
+# CONFIG_IBM_NEW_EMAC_TAH is not set
+# CONFIG_IBM_NEW_EMAC_EMAC4 is not set
+# CONFIG_IBM_NEW_EMAC_NO_FLOW_CTRL is not set
+# CONFIG_IBM_NEW_EMAC_MAL_CLR_ICINTSTAT is not set
+# CONFIG_IBM_NEW_EMAC_MAL_COMMON_ERR is not set
+# CONFIG_B44 is not set
+# CONFIG_NETDEV_1000 is not set
+# CONFIG_NETDEV_10000 is not set
+
+#
+# Wireless LAN
+#
+# CONFIG_WLAN_PRE80211 is not set
+# CONFIG_WLAN_80211 is not set
+# CONFIG_IWLWIFI_LEDS is not set
 # CONFIG_WAN is not set
 # CONFIG_PPP is not set
 # CONFIG_SLIP is not set
-# CONFIG_SHAPER is not set
 # CONFIG_NETCONSOLE is not set
 # CONFIG_NETPOLL is not set
 # CONFIG_NET_POLL_CONTROLLER is not set
-
-#
-# ISDN subsystem
-#
 # CONFIG_ISDN is not set
 
 #
@@ -513,6 +533,7 @@ CONFIG_SMC91X=y
 #
 CONFIG_INPUT=y
 # CONFIG_INPUT_FF_MEMLESS is not set
+# CONFIG_INPUT_POLLDEV is not set
 
 #
 # Userland interfaces
@@ -522,7 +543,6 @@ CONFIG_INPUT_MOUSEDEV_PSAUX=y
 CONFIG_INPUT_MOUSEDEV_SCREEN_X=1024
 CONFIG_INPUT_MOUSEDEV_SCREEN_Y=768
 # CONFIG_INPUT_JOYDEV is not set
-# CONFIG_INPUT_TSDEV is not set
 # CONFIG_INPUT_EVDEV is not set
 # CONFIG_INPUT_EVBUG is not set
 
@@ -538,9 +558,16 @@ CONFIG_KEYBOARD_ATKBD=y
 # CONFIG_KEYBOARD_STOWAWAY is not set
 CONFIG_INPUT_MOUSE=y
 CONFIG_MOUSE_PS2=y
+CONFIG_MOUSE_PS2_ALPS=y
+CONFIG_MOUSE_PS2_LOGIPS2PP=y
+CONFIG_MOUSE_PS2_SYNAPTICS=y
+CONFIG_MOUSE_PS2_LIFEBOOK=y
+CONFIG_MOUSE_PS2_TRACKPOINT=y
+# CONFIG_MOUSE_PS2_TOUCHKIT is not set
 # CONFIG_MOUSE_SERIAL is not set
 # CONFIG_MOUSE_VSXXXAA is not set
 # CONFIG_INPUT_JOYSTICK is not set
+# CONFIG_INPUT_TABLET is not set
 # CONFIG_INPUT_TOUCHSCREEN is not set
 # CONFIG_INPUT_MISC is not set
 
@@ -558,9 +585,11 @@ CONFIG_SERIO_LIBPS2=y
 # Character devices
 #
 CONFIG_VT=y
+CONFIG_CONSOLE_TRANSLATIONS=y
 CONFIG_VT_CONSOLE=y
 CONFIG_HW_CONSOLE=y
 # CONFIG_VT_HW_CONSOLE_BINDING is not set
+CONFIG_DEVKMEM=y
 # CONFIG_SERIAL_NONSTANDARD is not set
 
 #
@@ -579,97 +608,91 @@ CONFIG_SERIAL_CORE_CONSOLE=y
 CONFIG_UNIX98_PTYS=y
 CONFIG_LEGACY_PTYS=y
 CONFIG_LEGACY_PTY_COUNT=16
-
-#
-# IPMI
-#
 # CONFIG_IPMI_HANDLER is not set
-
-#
-# Watchdog Cards
-#
-# CONFIG_WATCHDOG is not set
 # CONFIG_HW_RANDOM is not set
 # CONFIG_NVRAM is not set
-# CONFIG_DTLK is not set
 # CONFIG_R3964 is not set
-
-#
-# Ftape, the floppy tape device driver
-#
 # CONFIG_RAW_DRIVER is not set
-
-#
-# TPM devices
-#
 # CONFIG_TCG_TPM is not set
-
-#
-# I2C support
-#
 # CONFIG_I2C is not set
-
-#
-# SPI support
-#
 # CONFIG_SPI is not set
-# CONFIG_SPI_MASTER is not set
-
-#
-# Dallas's 1-wire bus
-#
 # CONFIG_W1 is not set
-
-#
-# Hardware Monitoring support
-#
+# CONFIG_POWER_SUPPLY is not set
 # CONFIG_HWMON is not set
-# CONFIG_HWMON_VID is not set
-
-#
-# Misc devices
-#
-# CONFIG_SGI_IOC4 is not set
-# CONFIG_TIFM_CORE is not set
+# CONFIG_THERMAL is not set
+# CONFIG_THERMAL_HWMON is not set
+# CONFIG_WATCHDOG is not set
 
 #
-# LED devices
+# Sonics Silicon Backplane
 #
-# CONFIG_NEW_LEDS is not set
+CONFIG_SSB_POSSIBLE=y
+# CONFIG_SSB is not set
 
 #
-# LED drivers
+# Multifunction device drivers
 #
+# CONFIG_MFD_CORE is not set
+# CONFIG_MFD_SM501 is not set
+# CONFIG_HTC_PASIC3 is not set
+# CONFIG_MFD_TMIO is not set
+# CONFIG_MFD_T7L66XB is not set
+# CONFIG_MFD_TC6387XB is not set
+# CONFIG_MFD_WM8400 is not set
 
 #
-# LED Triggers
+# Multimedia devices
 #
 
 #
-# Multimedia devices
+# Multimedia core support
 #
 # CONFIG_VIDEO_DEV is not set
+# CONFIG_DVB_CORE is not set
+# CONFIG_VIDEO_MEDIA is not set
 
 #
-# Digital Video Broadcasting Devices
+# Multimedia drivers
 #
-# CONFIG_DVB is not set
+# CONFIG_DAB is not set
 
 #
 # Graphics support
 #
-# CONFIG_FIRMWARE_EDID is not set
+# CONFIG_VGASTATE is not set
+# CONFIG_VIDEO_OUTPUT_CONTROL is not set
 CONFIG_FB=y
+# CONFIG_FIRMWARE_EDID is not set
+# CONFIG_FB_DDC is not set
+# CONFIG_FB_BOOT_VESA_SUPPORT is not set
 CONFIG_FB_CFB_FILLRECT=y
 CONFIG_FB_CFB_COPYAREA=y
 CONFIG_FB_CFB_IMAGEBLIT=y
+# CONFIG_FB_CFB_REV_PIXELS_IN_BYTE is not set
+# CONFIG_FB_SYS_FILLRECT is not set
+# CONFIG_FB_SYS_COPYAREA is not set
+# CONFIG_FB_SYS_IMAGEBLIT is not set
+# CONFIG_FB_FOREIGN_ENDIAN is not set
+# CONFIG_FB_SYS_FOPS is not set
+# CONFIG_FB_SVGALIB is not set
 # CONFIG_FB_MACMODES is not set
 # CONFIG_FB_BACKLIGHT is not set
 # CONFIG_FB_MODE_HELPERS is not set
 # CONFIG_FB_TILEBLITTING is not set
+
+#
+# Frame buffer hardware drivers
+#
 CONFIG_FB_ARMCLCD=y
 # CONFIG_FB_S1D13XXX is not set
 # CONFIG_FB_VIRTUAL is not set
+# CONFIG_FB_METRONOME is not set
+# CONFIG_BACKLIGHT_LCD_SUPPORT is not set
+
+#
+# Display device support
+#
+# CONFIG_DISPLAY_SUPPORT is not set
 
 #
 # Console display driver support
@@ -677,28 +700,17 @@ CONFIG_FB_ARMCLCD=y
 # CONFIG_VGA_CONSOLE is not set
 CONFIG_DUMMY_CONSOLE=y
 CONFIG_FRAMEBUFFER_CONSOLE=y
+# CONFIG_FRAMEBUFFER_CONSOLE_DETECT_PRIMARY is not set
 # CONFIG_FRAMEBUFFER_CONSOLE_ROTATION is not set
 # CONFIG_FONTS is not set
 CONFIG_FONT_8x8=y
 CONFIG_FONT_8x16=y
-
-#
-# Logo configuration
-#
 CONFIG_LOGO=y
 # CONFIG_LOGO_LINUX_MONO is not set
 # CONFIG_LOGO_LINUX_VGA16 is not set
 CONFIG_LOGO_LINUX_CLUT224=y
-# CONFIG_BACKLIGHT_LCD_SUPPORT is not set
-
-#
-# Sound
-#
 CONFIG_SOUND=y
-
-#
-# Advanced Linux Sound Architecture
-#
+CONFIG_SOUND_OSS_CORE=y
 CONFIG_SND=y
 CONFIG_SND_TIMER=y
 CONFIG_SND_PCM=y
@@ -712,100 +724,65 @@ CONFIG_SND_SUPPORT_OLD_API=y
 CONFIG_SND_VERBOSE_PROCFS=y
 # CONFIG_SND_VERBOSE_PRINTK is not set
 # CONFIG_SND_DEBUG is not set
-
-#
-# Generic devices
-#
-CONFIG_SND_AC97_CODEC=m
-CONFIG_SND_AC97_BUS=m
-# CONFIG_SND_DUMMY is not set
-# CONFIG_SND_MTPAV is not set
-# CONFIG_SND_SERIAL_U16550 is not set
-# CONFIG_SND_MPU401 is not set
-
-#
-# ALSA ARM devices
-#
-CONFIG_SND_ARMAACI=m
-
-#
-# Open Sound System
-#
+CONFIG_SND_VMASTER=y
+CONFIG_SND_AC97_CODEC=y
+# CONFIG_SND_DRIVERS is not set
+CONFIG_SND_ARM=y
+CONFIG_SND_ARMAACI=y
+# CONFIG_SND_SOC is not set
 # CONFIG_SOUND_PRIME is not set
-
-#
-# USB support
-#
-CONFIG_USB_ARCH_HAS_HCD=y
-# CONFIG_USB_ARCH_HAS_OHCI is not set
-# CONFIG_USB_ARCH_HAS_EHCI is not set
-# CONFIG_USB is not set
-
-#
-# NOTE: USB_STORAGE enables SCSI, and 'SCSI disk support'
-#
-
-#
-# USB Gadget Support
-#
-# CONFIG_USB_GADGET is not set
-
-#
-# MMC/SD Card support
-#
+CONFIG_AC97_BUS=y
+# CONFIG_HID_SUPPORT is not set
+# CONFIG_USB_SUPPORT is not set
 CONFIG_MMC=y
 # CONFIG_MMC_DEBUG is not set
-CONFIG_MMC_BLOCK=y
-CONFIG_MMC_ARMMMCI=y
-# CONFIG_MMC_TIFM_SD is not set
+# CONFIG_MMC_UNSAFE_RESUME is not set
 
 #
-# Real Time Clock
+# MMC/SD/SDIO Card Drivers
 #
-CONFIG_RTC_LIB=y
-CONFIG_RTC_CLASS=y
-CONFIG_RTC_HCTOSYS=y
-CONFIG_RTC_HCTOSYS_DEVICE="rtc0"
-# CONFIG_RTC_DEBUG is not set
+CONFIG_MMC_BLOCK=y
+CONFIG_MMC_BLOCK_BOUNCE=y
+# CONFIG_SDIO_UART is not set
+# CONFIG_MMC_TEST is not set
 
 #
-# RTC interfaces
+# MMC/SD/SDIO Host Controller Drivers
 #
-CONFIG_RTC_INTF_SYSFS=y
-CONFIG_RTC_INTF_PROC=y
-CONFIG_RTC_INTF_DEV=y
-CONFIG_RTC_INTF_DEV_UIE_EMUL=y
+CONFIG_MMC_ARMMMCI=y
+# CONFIG_MMC_SDHCI is not set
+# CONFIG_MEMSTICK is not set
+# CONFIG_ACCESSIBILITY is not set
+# CONFIG_NEW_LEDS is not set
+CONFIG_RTC_LIB=y
+# CONFIG_RTC_CLASS is not set
+# CONFIG_DMADEVICES is not set
 
 #
-# RTC drivers
+# Voltage and Current regulators
 #
-# CONFIG_RTC_DRV_DS1553 is not set
-# CONFIG_RTC_DRV_DS1742 is not set
-# CONFIG_RTC_DRV_M48T86 is not set
-CONFIG_RTC_DRV_PL031=y
-# CONFIG_RTC_DRV_TEST is not set
-# CONFIG_RTC_DRV_V3020 is not set
+# CONFIG_REGULATOR is not set
+# CONFIG_REGULATOR_FIXED_VOLTAGE is not set
+# CONFIG_REGULATOR_VIRTUAL_CONSUMER is not set
+# CONFIG_REGULATOR_BQ24022 is not set
+# CONFIG_UIO is not set
 
 #
 # File systems
 #
-CONFIG_EXT2_FS=y
-# CONFIG_EXT2_FS_XATTR is not set
-# CONFIG_EXT2_FS_XIP is not set
+# CONFIG_EXT2_FS is not set
 # CONFIG_EXT3_FS is not set
-# CONFIG_EXT4DEV_FS is not set
+# CONFIG_EXT4_FS is not set
 # CONFIG_REISERFS_FS is not set
 # CONFIG_JFS_FS is not set
 # CONFIG_FS_POSIX_ACL is not set
+CONFIG_FILE_LOCKING=y
 # CONFIG_XFS_FS is not set
-# CONFIG_GFS2_FS is not set
 # CONFIG_OCFS2_FS is not set
-# CONFIG_MINIX_FS is not set
-# CONFIG_ROMFS_FS is not set
+CONFIG_DNOTIFY=y
 CONFIG_INOTIFY=y
-# CONFIG_INOTIFY_USER is not set
+CONFIG_INOTIFY_USER=y
 # CONFIG_QUOTA is not set
-CONFIG_DNOTIFY=y
 # CONFIG_AUTOFS_FS is not set
 # CONFIG_AUTOFS4_FS is not set
 # CONFIG_FUSE_FS is not set
@@ -831,11 +808,11 @@ CONFIG_FAT_DEFAULT_IOCHARSET="iso8859-1"
 #
 CONFIG_PROC_FS=y
 CONFIG_PROC_SYSCTL=y
+CONFIG_PROC_PAGE_MONITOR=y
 CONFIG_SYSFS=y
 CONFIG_TMPFS=y
 # CONFIG_TMPFS_POSIX_ACL is not set
 # CONFIG_HUGETLB_PAGE is not set
-CONFIG_RAMFS=y
 # CONFIG_CONFIGFS_FS is not set
 
 #
@@ -848,29 +825,28 @@ CONFIG_RAMFS=y
 # CONFIG_BEFS_FS is not set
 # CONFIG_BFS_FS is not set
 # CONFIG_EFS_FS is not set
-# CONFIG_JFFS_FS is not set
 # CONFIG_JFFS2_FS is not set
 CONFIG_CRAMFS=y
 # CONFIG_VXFS_FS is not set
+# CONFIG_MINIX_FS is not set
+# CONFIG_OMFS_FS is not set
 # CONFIG_HPFS_FS is not set
 # CONFIG_QNX4FS_FS is not set
+# CONFIG_ROMFS_FS is not set
 # CONFIG_SYSV_FS is not set
 # CONFIG_UFS_FS is not set
-
-#
-# Network File Systems
-#
+CONFIG_NETWORK_FILESYSTEMS=y
 CONFIG_NFS_FS=y
 CONFIG_NFS_V3=y
 # CONFIG_NFS_V3_ACL is not set
 # CONFIG_NFS_V4 is not set
-# CONFIG_NFS_DIRECTIO is not set
-# CONFIG_NFSD is not set
 CONFIG_ROOT_NFS=y
+# CONFIG_NFSD is not set
 CONFIG_LOCKD=y
 CONFIG_LOCKD_V4=y
 CONFIG_NFS_COMMON=y
 CONFIG_SUNRPC=y
+# CONFIG_SUNRPC_REGISTER_V4 is not set
 # CONFIG_RPCSEC_GSS_KRB5 is not set
 # CONFIG_RPCSEC_GSS_SPKM3 is not set
 # CONFIG_SMB_FS is not set
@@ -878,17 +854,12 @@ CONFIG_SUNRPC=y
 # CONFIG_NCP_FS is not set
 # CONFIG_CODA_FS is not set
 # CONFIG_AFS_FS is not set
-# CONFIG_9P_FS is not set
 
 #
 # Partition Types
 #
 # CONFIG_PARTITION_ADVANCED is not set
 CONFIG_MSDOS_PARTITION=y
-
-#
-# Native Language Support
-#
 CONFIG_NLS=y
 CONFIG_NLS_DEFAULT="iso8859-1"
 CONFIG_NLS_CODEPAGE_437=y
@@ -929,64 +900,177 @@ CONFIG_NLS_ISO8859_1=y
 # CONFIG_NLS_KOI8_R is not set
 # CONFIG_NLS_KOI8_U is not set
 # CONFIG_NLS_UTF8 is not set
-
-#
-# Profiling support
-#
-# CONFIG_PROFILING is not set
+# CONFIG_DLM is not set
 
 #
 # Kernel hacking
 #
 # CONFIG_PRINTK_TIME is not set
-# CONFIG_ENABLE_MUST_CHECK is not set
+CONFIG_ENABLE_WARN_DEPRECATED=y
+CONFIG_ENABLE_MUST_CHECK=y
+CONFIG_FRAME_WARN=1024
 CONFIG_MAGIC_SYSRQ=y
 # CONFIG_UNUSED_SYMBOLS is not set
+# CONFIG_DEBUG_FS is not set
+# CONFIG_HEADERS_CHECK is not set
 CONFIG_DEBUG_KERNEL=y
-CONFIG_LOG_BUF_SHIFT=14
+# CONFIG_DEBUG_SHIRQ is not set
 CONFIG_DETECT_SOFTLOCKUP=y
+# CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC is not set
+CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC_VALUE=0
+# CONFIG_SCHED_DEBUG is not set
 # CONFIG_SCHEDSTATS is not set
+# CONFIG_TIMER_STATS is not set
+# CONFIG_DEBUG_OBJECTS is not set
 # CONFIG_DEBUG_SLAB is not set
 # CONFIG_DEBUG_RT_MUTEXES is not set
 # CONFIG_RT_MUTEX_TESTER is not set
-CONFIG_DEBUG_SPINLOCK=y
-CONFIG_DEBUG_MUTEXES=y
-CONFIG_DEBUG_RWSEMS=y
+# CONFIG_DEBUG_SPINLOCK is not set
+# CONFIG_DEBUG_MUTEXES is not set
+# CONFIG_DEBUG_LOCK_ALLOC is not set
+# CONFIG_PROVE_LOCKING is not set
+# CONFIG_LOCK_STAT is not set
 # CONFIG_DEBUG_SPINLOCK_SLEEP is not set
 # CONFIG_DEBUG_LOCKING_API_SELFTESTS is not set
 # CONFIG_DEBUG_KOBJECT is not set
 CONFIG_DEBUG_BUGVERBOSE=y
 # CONFIG_DEBUG_INFO is not set
-# CONFIG_DEBUG_FS is not set
 # CONFIG_DEBUG_VM is not set
+# CONFIG_DEBUG_WRITECOUNT is not set
+CONFIG_DEBUG_MEMORY_INIT=y
 # CONFIG_DEBUG_LIST is not set
+# CONFIG_DEBUG_SG is not set
 CONFIG_FRAME_POINTER=y
-# CONFIG_UNWIND_INFO is not set
-CONFIG_FORCED_INLINING=y
-# CONFIG_HEADERS_CHECK is not set
+# CONFIG_BOOT_PRINTK_DELAY is not set
 # CONFIG_RCU_TORTURE_TEST is not set
+# CONFIG_RCU_CPU_STALL_DETECTOR is not set
+# CONFIG_BACKTRACE_SELF_TEST is not set
+# CONFIG_DEBUG_BLOCK_EXT_DEVT is not set
+# CONFIG_FAULT_INJECTION is not set
+# CONFIG_SYSCTL_SYSCALL_CHECK is not set
+CONFIG_NOP_TRACER=y
+CONFIG_HAVE_FTRACE=y
+CONFIG_HAVE_DYNAMIC_FTRACE=y
+# CONFIG_FTRACE is not set
+# CONFIG_IRQSOFF_TRACER is not set
+# CONFIG_SCHED_TRACER is not set
+# CONFIG_CONTEXT_SWITCH_TRACER is not set
+# CONFIG_BOOT_TRACER is not set
+# CONFIG_STACK_TRACER is not set
+# CONFIG_DYNAMIC_PRINTK_DEBUG is not set
+# CONFIG_SAMPLES is not set
+CONFIG_HAVE_ARCH_KGDB=y
+# CONFIG_KGDB is not set
 CONFIG_DEBUG_USER=y
 CONFIG_DEBUG_ERRORS=y
-CONFIG_DEBUG_LL=y
-# CONFIG_DEBUG_ICEDCC is not set
+# CONFIG_DEBUG_STACK_USAGE is not set
+# CONFIG_DEBUG_LL is not set
 
 #
 # Security options
 #
 # CONFIG_KEYS is not set
 # CONFIG_SECURITY is not set
+# CONFIG_SECURITYFS is not set
+# CONFIG_SECURITY_FILE_CAPABILITIES is not set
+CONFIG_CRYPTO=y
+
+#
+# Crypto core or helper
+#
+# CONFIG_CRYPTO_FIPS is not set
+# CONFIG_CRYPTO_MANAGER is not set
+# CONFIG_CRYPTO_GF128MUL is not set
+# CONFIG_CRYPTO_NULL is not set
+# CONFIG_CRYPTO_CRYPTD is not set
+# CONFIG_CRYPTO_AUTHENC is not set
+# CONFIG_CRYPTO_TEST is not set
+
+#
+# Authenticated Encryption with Associated Data
+#
+# CONFIG_CRYPTO_CCM is not set
+# CONFIG_CRYPTO_GCM is not set
+# CONFIG_CRYPTO_SEQIV is not set
+
+#
+# Block modes
+#
+# CONFIG_CRYPTO_CBC is not set
+# CONFIG_CRYPTO_CTR is not set
+# CONFIG_CRYPTO_CTS is not set
+# CONFIG_CRYPTO_ECB is not set
+# CONFIG_CRYPTO_LRW is not set
+# CONFIG_CRYPTO_PCBC is not set
+# CONFIG_CRYPTO_XTS is not set
+
+#
+# Hash modes
+#
+# CONFIG_CRYPTO_HMAC is not set
+# CONFIG_CRYPTO_XCBC is not set
+
+#
+# Digest
+#
+# CONFIG_CRYPTO_CRC32C is not set
+# CONFIG_CRYPTO_MD4 is not set
+# CONFIG_CRYPTO_MD5 is not set
+# CONFIG_CRYPTO_MICHAEL_MIC is not set
+# CONFIG_CRYPTO_RMD128 is not set
+# CONFIG_CRYPTO_RMD160 is not set
+# CONFIG_CRYPTO_RMD256 is not set
+# CONFIG_CRYPTO_RMD320 is not set
+# CONFIG_CRYPTO_SHA1 is not set
+# CONFIG_CRYPTO_SHA256 is not set
+# CONFIG_CRYPTO_SHA512 is not set
+# CONFIG_CRYPTO_TGR192 is not set
+# CONFIG_CRYPTO_WP512 is not set
+
+#
+# Ciphers
+#
+# CONFIG_CRYPTO_AES is not set
+# CONFIG_CRYPTO_ANUBIS is not set
+# CONFIG_CRYPTO_ARC4 is not set
+# CONFIG_CRYPTO_BLOWFISH is not set
+# CONFIG_CRYPTO_CAMELLIA is not set
+# CONFIG_CRYPTO_CAST5 is not set
+# CONFIG_CRYPTO_CAST6 is not set
+# CONFIG_CRYPTO_DES is not set
+# CONFIG_CRYPTO_FCRYPT is not set
+# CONFIG_CRYPTO_KHAZAD is not set
+# CONFIG_CRYPTO_SALSA20 is not set
+# CONFIG_CRYPTO_SEED is not set
+# CONFIG_CRYPTO_SERPENT is not set
+# CONFIG_CRYPTO_TEA is not set
+# CONFIG_CRYPTO_TWOFISH is not set
+
+#
+# Compression
+#
+# CONFIG_CRYPTO_DEFLATE is not set
+# CONFIG_CRYPTO_LZO is not set
 
 #
-# Cryptographic options
+# Random Number Generation
 #
-# CONFIG_CRYPTO is not set
+# CONFIG_CRYPTO_ANSI_CPRNG is not set
+# CONFIG_CRYPTO_HW is not set
 
 #
 # Library routines
 #
+CONFIG_BITREVERSE=y
 # CONFIG_CRC_CCITT is not set
 # CONFIG_CRC16 is not set
+# CONFIG_CRC_T10DIF is not set
+# CONFIG_CRC_ITU_T is not set
 CONFIG_CRC32=y
+# CONFIG_CRC7 is not set
 # CONFIG_LIBCRC32C is not set
 CONFIG_ZLIB_INFLATE=y
 CONFIG_PLIST=y
+CONFIG_HAS_IOMEM=y
+CONFIG_HAS_IOPORT=y
+CONFIG_HAS_DMA=y
diff --git a/arch/arm/configs/realview_defconfig b/arch/arm/configs/realview_defconfig
index 907e54344dad..7e253f58ed18 100644
--- a/arch/arm/configs/realview_defconfig
+++ b/arch/arm/configs/realview_defconfig
@@ -1,105 +1,204 @@
 #
 # Automatically generated make config: don't edit
-# Linux kernel version: 2.6.14-rc2
-# Thu Sep 29 14:50:10 2005
+# Linux kernel version: 2.6.28-rc2
+# Mon Nov 10 14:39:48 2008
 #
 CONFIG_ARM=y
+CONFIG_SYS_SUPPORTS_APM_EMULATION=y
+# CONFIG_GENERIC_GPIO is not set
+CONFIG_GENERIC_TIME=y
+CONFIG_GENERIC_CLOCKEVENTS=y
 CONFIG_MMU=y
-CONFIG_UID16=y
+# CONFIG_NO_IOPORT is not set
+CONFIG_GENERIC_HARDIRQS=y
+CONFIG_STACKTRACE_SUPPORT=y
+CONFIG_HAVE_LATENCYTOP_SUPPORT=y
+CONFIG_LOCKDEP_SUPPORT=y
+CONFIG_TRACE_IRQFLAGS_SUPPORT=y
+CONFIG_HARDIRQS_SW_RESEND=y
+CONFIG_GENERIC_IRQ_PROBE=y
 CONFIG_RWSEM_GENERIC_SPINLOCK=y
+# CONFIG_ARCH_HAS_ILOG2_U32 is not set
+# CONFIG_ARCH_HAS_ILOG2_U64 is not set
+CONFIG_GENERIC_HWEIGHT=y
 CONFIG_GENERIC_CALIBRATE_DELAY=y
+CONFIG_GENERIC_HARDIRQS_NO__DO_IRQ=y
+CONFIG_VECTORS_BASE=0xffff0000
+CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config"
 
 #
-# Code maturity level options
+# General setup
 #
-# CONFIG_EXPERIMENTAL is not set
-CONFIG_CLEAN_COMPILE=y
+CONFIG_EXPERIMENTAL=y
 CONFIG_BROKEN_ON_SMP=y
 CONFIG_INIT_ENV_ARG_LIMIT=32
-
-#
-# General setup
-#
 CONFIG_LOCALVERSION=""
 CONFIG_LOCALVERSION_AUTO=y
 # CONFIG_SWAP is not set
 CONFIG_SYSVIPC=y
+CONFIG_SYSVIPC_SYSCTL=y
+# CONFIG_POSIX_MQUEUE is not set
 # CONFIG_BSD_PROCESS_ACCT is not set
-CONFIG_SYSCTL=y
+# CONFIG_TASKSTATS is not set
 # CONFIG_AUDIT is not set
-CONFIG_HOTPLUG=y
-CONFIG_KOBJECT_UEVENT=y
 # CONFIG_IKCONFIG is not set
-CONFIG_INITRAMFS_SOURCE=""
+CONFIG_LOG_BUF_SHIFT=14
+# CONFIG_CGROUPS is not set
+# CONFIG_GROUP_SCHED is not set
+CONFIG_SYSFS_DEPRECATED=y
+CONFIG_SYSFS_DEPRECATED_V2=y
+# CONFIG_RELAY is not set
+CONFIG_NAMESPACES=y
+# CONFIG_UTS_NS is not set
+# CONFIG_IPC_NS is not set
+# CONFIG_USER_NS is not set
+# CONFIG_PID_NS is not set
+# CONFIG_BLK_DEV_INITRD is not set
+CONFIG_CC_OPTIMIZE_FOR_SIZE=y
+CONFIG_SYSCTL=y
 # CONFIG_EMBEDDED is not set
+CONFIG_UID16=y
+CONFIG_SYSCTL_SYSCALL=y
 CONFIG_KALLSYMS=y
 # CONFIG_KALLSYMS_ALL is not set
 # CONFIG_KALLSYMS_EXTRA_PASS is not set
+CONFIG_HOTPLUG=y
 CONFIG_PRINTK=y
 CONFIG_BUG=y
+CONFIG_ELF_CORE=y
+CONFIG_COMPAT_BRK=y
 CONFIG_BASE_FULL=y
 CONFIG_FUTEX=y
+CONFIG_ANON_INODES=y
 CONFIG_EPOLL=y
-CONFIG_CC_OPTIMIZE_FOR_SIZE=y
+CONFIG_SIGNALFD=y
+CONFIG_TIMERFD=y
+CONFIG_EVENTFD=y
 CONFIG_SHMEM=y
-CONFIG_CC_ALIGN_FUNCTIONS=0
-CONFIG_CC_ALIGN_LABELS=0
-CONFIG_CC_ALIGN_LOOPS=0
-CONFIG_CC_ALIGN_JUMPS=0
+CONFIG_AIO=y
+CONFIG_VM_EVENT_COUNTERS=y
+CONFIG_SLAB=y
+# CONFIG_SLUB is not set
+# CONFIG_SLOB is not set
+# CONFIG_PROFILING is not set
+# CONFIG_MARKERS is not set
+CONFIG_HAVE_OPROFILE=y
+# CONFIG_KPROBES is not set
+CONFIG_HAVE_KPROBES=y
+CONFIG_HAVE_KRETPROBES=y
+CONFIG_HAVE_CLK=y
+CONFIG_HAVE_GENERIC_DMA_COHERENT=y
+CONFIG_SLABINFO=y
+CONFIG_RT_MUTEXES=y
 # CONFIG_TINY_SHMEM is not set
 CONFIG_BASE_SMALL=0
-
-#
-# Loadable module support
-#
 CONFIG_MODULES=y
+# CONFIG_MODULE_FORCE_LOAD is not set
 CONFIG_MODULE_UNLOAD=y
-CONFIG_OBSOLETE_MODPARM=y
+# CONFIG_MODULE_FORCE_UNLOAD is not set
+# CONFIG_MODVERSIONS is not set
 # CONFIG_MODULE_SRCVERSION_ALL is not set
-# CONFIG_KMOD is not set
+CONFIG_KMOD=y
+CONFIG_BLOCK=y
+# CONFIG_LBD is not set
+# CONFIG_BLK_DEV_IO_TRACE is not set
+# CONFIG_LSF is not set
+# CONFIG_BLK_DEV_BSG is not set
+# CONFIG_BLK_DEV_INTEGRITY is not set
+
+#
+# IO Schedulers
+#
+CONFIG_IOSCHED_NOOP=y
+# CONFIG_IOSCHED_AS is not set
+CONFIG_IOSCHED_DEADLINE=y
+# CONFIG_IOSCHED_CFQ is not set
+# CONFIG_DEFAULT_AS is not set
+CONFIG_DEFAULT_DEADLINE=y
+# CONFIG_DEFAULT_CFQ is not set
+# CONFIG_DEFAULT_NOOP is not set
+CONFIG_DEFAULT_IOSCHED="deadline"
+CONFIG_CLASSIC_RCU=y
+# CONFIG_FREEZER is not set
 
 #
 # System Type
 #
+# CONFIG_ARCH_AAEC2000 is not set
+# CONFIG_ARCH_INTEGRATOR is not set
+CONFIG_ARCH_REALVIEW=y
+# CONFIG_ARCH_VERSATILE is not set
+# CONFIG_ARCH_AT91 is not set
 # CONFIG_ARCH_CLPS7500 is not set
 # CONFIG_ARCH_CLPS711X is not set
-# CONFIG_ARCH_CO285 is not set
 # CONFIG_ARCH_EBSA110 is not set
+# CONFIG_ARCH_EP93XX is not set
 # CONFIG_ARCH_FOOTBRIDGE is not set
-# CONFIG_ARCH_INTEGRATOR is not set
-# CONFIG_ARCH_IOP3XX is not set
-# CONFIG_ARCH_IXP4XX is not set
+# CONFIG_ARCH_NETX is not set
+# CONFIG_ARCH_H720X is not set
+# CONFIG_ARCH_IMX is not set
+# CONFIG_ARCH_IOP13XX is not set
+# CONFIG_ARCH_IOP32X is not set
+# CONFIG_ARCH_IOP33X is not set
+# CONFIG_ARCH_IXP23XX is not set
 # CONFIG_ARCH_IXP2000 is not set
+# CONFIG_ARCH_IXP4XX is not set
 # CONFIG_ARCH_L7200 is not set
+# CONFIG_ARCH_KIRKWOOD is not set
+# CONFIG_ARCH_KS8695 is not set
+# CONFIG_ARCH_NS9XXX is not set
+# CONFIG_ARCH_LOKI is not set
+# CONFIG_ARCH_MV78XX0 is not set
+# CONFIG_ARCH_MXC is not set
+# CONFIG_ARCH_ORION5X is not set
+# CONFIG_ARCH_PNX4008 is not set
 # CONFIG_ARCH_PXA is not set
 # CONFIG_ARCH_RPC is not set
 # CONFIG_ARCH_SA1100 is not set
 # CONFIG_ARCH_S3C2410 is not set
 # CONFIG_ARCH_SHARK is not set
 # CONFIG_ARCH_LH7A40X is not set
+# CONFIG_ARCH_DAVINCI is not set
 # CONFIG_ARCH_OMAP is not set
-# CONFIG_ARCH_VERSATILE is not set
-CONFIG_ARCH_REALVIEW=y
-# CONFIG_ARCH_IMX is not set
-# CONFIG_ARCH_H720X is not set
-# CONFIG_ARCH_AAEC2000 is not set
+# CONFIG_ARCH_MSM is not set
+
+#
+# Boot options
+#
+
+#
+# Power management
+#
 
 #
 # RealView platform type
 #
 CONFIG_MACH_REALVIEW_EB=y
+# CONFIG_REALVIEW_EB_A9MP is not set
+CONFIG_REALVIEW_EB_ARM11MP=y
+# CONFIG_REALVIEW_EB_ARM11MP_REVB is not set
+CONFIG_MACH_REALVIEW_PB11MP=y
+CONFIG_MACH_REALVIEW_PB1176=y
+# CONFIG_MACH_REALVIEW_PBA8 is not set
 
 #
 # Processor Type
 #
 CONFIG_CPU_32=y
-CONFIG_CPU_ARM926T=y
-# CONFIG_CPU_V6 is not set
-CONFIG_CPU_32v5=y
-CONFIG_CPU_ABRT_EV5TJ=y
-CONFIG_CPU_CACHE_VIVT=y
-CONFIG_CPU_COPY_V4WB=y
-CONFIG_CPU_TLB_V4WBI=y
+# CONFIG_CPU_ARM926T is not set
+CONFIG_CPU_V6=y
+# CONFIG_CPU_32v6K is not set
+# CONFIG_CPU_V7 is not set
+CONFIG_CPU_32v6=y
+CONFIG_CPU_ABRT_EV6=y
+CONFIG_CPU_PABRT_NOIFAR=y
+CONFIG_CPU_CACHE_V6=y
+CONFIG_CPU_CACHE_VIPT=y
+CONFIG_CPU_COPY_V6=y
+CONFIG_CPU_TLB_V6=y
+CONFIG_CPU_HAS_ASID=y
+CONFIG_CPU_CP15=y
+CONFIG_CPU_CP15_MMU=y
 
 #
 # Processor Features
@@ -107,8 +206,9 @@ CONFIG_CPU_TLB_V4WBI=y
 CONFIG_ARM_THUMB=y
 # CONFIG_CPU_ICACHE_DISABLE is not set
 # CONFIG_CPU_DCACHE_DISABLE is not set
-# CONFIG_CPU_DCACHE_WRITETHROUGH is not set
-# CONFIG_CPU_CACHE_ROUND_ROBIN is not set
+# CONFIG_CPU_BPREDICT_DISABLE is not set
+CONFIG_OUTER_CACHE=y
+CONFIG_CACHE_L2X0=y
 CONFIG_ARM_GIC=y
 CONFIG_ICST307=y
 
@@ -116,20 +216,41 @@ CONFIG_ICST307=y
 # Bus support
 #
 CONFIG_ARM_AMBA=y
-CONFIG_ISA_DMA_API=y
-
-#
-# PCCARD (PCMCIA/CardBus) support
-#
+# CONFIG_PCI_SYSCALL is not set
+# CONFIG_ARCH_SUPPORTS_MSI is not set
 # CONFIG_PCCARD is not set
 
 #
 # Kernel Features
 #
-# CONFIG_ARCH_DISCONTIGMEM_ENABLE is not set
+# CONFIG_NO_HZ is not set
+# CONFIG_HIGH_RES_TIMERS is not set
+CONFIG_GENERIC_CLOCKEVENTS_BUILD=y
+# CONFIG_SMP is not set
+CONFIG_VMSPLIT_3G=y
+# CONFIG_VMSPLIT_2G is not set
+# CONFIG_VMSPLIT_1G is not set
+CONFIG_PAGE_OFFSET=0xC0000000
+# CONFIG_PREEMPT is not set
+CONFIG_HZ=100
+CONFIG_AEABI=y
+CONFIG_OABI_COMPAT=y
+CONFIG_ARCH_FLATMEM_HAS_HOLES=y
+# CONFIG_ARCH_SPARSEMEM_DEFAULT is not set
+# CONFIG_ARCH_SELECT_MEMORY_MODEL is not set
+CONFIG_SELECT_MEMORY_MODEL=y
+CONFIG_FLATMEM_MANUAL=y
+# CONFIG_DISCONTIGMEM_MANUAL is not set
+# CONFIG_SPARSEMEM_MANUAL is not set
 CONFIG_FLATMEM=y
 CONFIG_FLAT_NODE_MEM_MAP=y
-# CONFIG_SPARSEMEM_STATIC is not set
+CONFIG_PAGEFLAGS_EXTENDED=y
+CONFIG_SPLIT_PTLOCK_CPUS=4
+# CONFIG_RESOURCES_64BIT is not set
+# CONFIG_PHYS_ADDR_T_64BIT is not set
+CONFIG_ZONE_DMA_FLAG=0
+CONFIG_VIRT_TO_BUS=y
+CONFIG_UNEVICTABLE_LRU=y
 CONFIG_ALIGNMENT_TRAP=y
 
 #
@@ -139,6 +260,12 @@ CONFIG_ZBOOT_ROM_TEXT=0x0
 CONFIG_ZBOOT_ROM_BSS=0x0
 CONFIG_CMDLINE="root=/dev/nfs nfsroot=10.1.69.3:/work/nfsroot ip=dhcp console=ttyAMA0 mem=128M"
 # CONFIG_XIP_KERNEL is not set
+# CONFIG_KEXEC is not set
+
+#
+# CPU Power Management
+#
+# CONFIG_CPU_IDLE is not set
 
 #
 # Floating point emulation
@@ -147,26 +274,24 @@ CONFIG_CMDLINE="root=/dev/nfs nfsroot=10.1.69.3:/work/nfsroot ip=dhcp console=tt
 #
 # At least one emulation must be selected
 #
-CONFIG_FPE_NWFPE=y
-# CONFIG_FPE_NWFPE_XP is not set
-# CONFIG_VFP is not set
+# CONFIG_FPE_NWFPE is not set
+# CONFIG_FPE_FASTFPE is not set
+CONFIG_VFP=y
 
 #
 # Userspace binary formats
 #
 CONFIG_BINFMT_ELF=y
+# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
+CONFIG_HAVE_AOUT=y
 # CONFIG_BINFMT_AOUT is not set
 # CONFIG_BINFMT_MISC is not set
-# CONFIG_ARTHUR is not set
 
 #
 # Power management options
 #
 # CONFIG_PM is not set
-
-#
-# Networking
-#
+CONFIG_ARCH_SUSPEND_POSSIBLE=y
 CONFIG_NET=y
 
 #
@@ -175,6 +300,11 @@ CONFIG_NET=y
 CONFIG_PACKET=y
 # CONFIG_PACKET_MMAP is not set
 CONFIG_UNIX=y
+CONFIG_XFRM=y
+# CONFIG_XFRM_USER is not set
+# CONFIG_XFRM_SUB_POLICY is not set
+# CONFIG_XFRM_MIGRATE is not set
+# CONFIG_XFRM_STATISTICS is not set
 # CONFIG_NET_KEY is not set
 CONFIG_INET=y
 # CONFIG_IP_MULTICAST is not set
@@ -186,34 +316,56 @@ CONFIG_IP_PNP_BOOTP=y
 # CONFIG_IP_PNP_RARP is not set
 # CONFIG_NET_IPIP is not set
 # CONFIG_NET_IPGRE is not set
+# CONFIG_ARPD is not set
 # CONFIG_SYN_COOKIES is not set
 # CONFIG_INET_AH is not set
 # CONFIG_INET_ESP is not set
 # CONFIG_INET_IPCOMP is not set
+# CONFIG_INET_XFRM_TUNNEL is not set
 # CONFIG_INET_TUNNEL is not set
+CONFIG_INET_XFRM_MODE_TRANSPORT=y
+CONFIG_INET_XFRM_MODE_TUNNEL=y
+CONFIG_INET_XFRM_MODE_BEET=y
+# CONFIG_INET_LRO is not set
 CONFIG_INET_DIAG=y
 CONFIG_INET_TCP_DIAG=y
 # CONFIG_TCP_CONG_ADVANCED is not set
-CONFIG_TCP_CONG_BIC=y
+CONFIG_TCP_CONG_CUBIC=y
+CONFIG_DEFAULT_TCP_CONG="cubic"
+# CONFIG_TCP_MD5SIG is not set
 # CONFIG_IPV6 is not set
+# CONFIG_NETWORK_SECMARK is not set
 # CONFIG_NETFILTER is not set
+# CONFIG_IP_DCCP is not set
+# CONFIG_IP_SCTP is not set
+# CONFIG_TIPC is not set
+# CONFIG_ATM is not set
 # CONFIG_BRIDGE is not set
+# CONFIG_NET_DSA is not set
 # CONFIG_VLAN_8021Q is not set
 # CONFIG_DECNET is not set
 # CONFIG_LLC2 is not set
 # CONFIG_IPX is not set
 # CONFIG_ATALK is not set
+# CONFIG_X25 is not set
+# CONFIG_LAPB is not set
+# CONFIG_ECONET is not set
+# CONFIG_WAN_ROUTER is not set
 # CONFIG_NET_SCHED is not set
-# CONFIG_NET_CLS_ROUTE is not set
 
 #
 # Network testing
 #
 # CONFIG_NET_PKTGEN is not set
 # CONFIG_HAMRADIO is not set
+# CONFIG_CAN is not set
 # CONFIG_IRDA is not set
 # CONFIG_BT is not set
-# CONFIG_IEEE80211 is not set
+# CONFIG_AF_RXRPC is not set
+# CONFIG_PHONET is not set
+# CONFIG_WIRELESS is not set
+# CONFIG_RFKILL is not set
+# CONFIG_NET_9P is not set
 
 #
 # Device Drivers
@@ -222,30 +374,37 @@ CONFIG_TCP_CONG_BIC=y
 #
 # Generic Driver Options
 #
+CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_STANDALONE=y
 CONFIG_PREVENT_FIRMWARE_BUILD=y
-# CONFIG_FW_LOADER is not set
+CONFIG_FW_LOADER=y
+CONFIG_FIRMWARE_IN_KERNEL=y
+CONFIG_EXTRA_FIRMWARE=""
 # CONFIG_DEBUG_DRIVER is not set
-
-#
-# Memory Technology Devices (MTD)
-#
+# CONFIG_DEBUG_DEVRES is not set
+# CONFIG_SYS_HYPERVISOR is not set
+# CONFIG_CONNECTOR is not set
 CONFIG_MTD=y
 # CONFIG_MTD_DEBUG is not set
-# CONFIG_MTD_CONCAT is not set
+CONFIG_MTD_CONCAT=y
 CONFIG_MTD_PARTITIONS=y
 # CONFIG_MTD_REDBOOT_PARTS is not set
 CONFIG_MTD_CMDLINE_PARTS=y
 # CONFIG_MTD_AFS_PARTS is not set
+# CONFIG_MTD_AR7_PARTS is not set
 
 #
 # User Modules And Translation Layers
 #
 CONFIG_MTD_CHAR=y
+CONFIG_MTD_BLKDEVS=y
 CONFIG_MTD_BLOCK=y
 # CONFIG_FTL is not set
 # CONFIG_NFTL is not set
 # CONFIG_INFTL is not set
+# CONFIG_RFD_FTL is not set
+# CONFIG_SSFDC is not set
+# CONFIG_MTD_OOPS is not set
 
 #
 # RAM/ROM/Flash chip drivers
@@ -266,7 +425,6 @@ CONFIG_MTD_CFI_I2=y
 # CONFIG_MTD_CFI_I8 is not set
 CONFIG_MTD_CFI_INTELEXT=y
 CONFIG_MTD_CFI_AMDSTD=y
-CONFIG_MTD_CFI_AMDSTD_RETRY=0
 # CONFIG_MTD_CFI_STAA is not set
 CONFIG_MTD_CFI_UTIL=y
 # CONFIG_MTD_RAM is not set
@@ -279,7 +437,6 @@ CONFIG_MTD_CFI_UTIL=y
 # CONFIG_MTD_COMPLEX_MAPPINGS is not set
 # CONFIG_MTD_PHYSMAP is not set
 CONFIG_MTD_ARM_INTEGRATOR=y
-# CONFIG_MTD_EDB7312 is not set
 # CONFIG_MTD_PLATRAM is not set
 
 #
@@ -288,7 +445,7 @@ CONFIG_MTD_ARM_INTEGRATOR=y
 # CONFIG_MTD_SLRAM is not set
 # CONFIG_MTD_PHRAM is not set
 # CONFIG_MTD_MTDRAM is not set
-# CONFIG_MTD_BLKMTD is not set
+# CONFIG_MTD_BLOCK2MTD is not set
 
 #
 # Disk-On-Chip Device Drivers
@@ -296,121 +453,81 @@ CONFIG_MTD_ARM_INTEGRATOR=y
 # CONFIG_MTD_DOC2000 is not set
 # CONFIG_MTD_DOC2001 is not set
 # CONFIG_MTD_DOC2001PLUS is not set
-
-#
-# NAND Flash Device Drivers
-#
 # CONFIG_MTD_NAND is not set
+# CONFIG_MTD_ONENAND is not set
 
 #
-# Parallel port support
+# UBI - Unsorted block images
 #
+# CONFIG_MTD_UBI is not set
 # CONFIG_PARPORT is not set
-
-#
-# Plug and Play support
-#
-
-#
-# Block devices
-#
+CONFIG_BLK_DEV=y
 # CONFIG_BLK_DEV_COW_COMMON is not set
 # CONFIG_BLK_DEV_LOOP is not set
 # CONFIG_BLK_DEV_NBD is not set
 # CONFIG_BLK_DEV_RAM is not set
-CONFIG_BLK_DEV_RAM_COUNT=16
 # CONFIG_CDROM_PKTCDVD is not set
-
-#
-# IO Schedulers
-#
-CONFIG_IOSCHED_NOOP=y
-# CONFIG_IOSCHED_AS is not set
-CONFIG_IOSCHED_DEADLINE=y
-# CONFIG_IOSCHED_CFQ is not set
 # CONFIG_ATA_OVER_ETH is not set
+CONFIG_MISC_DEVICES=y
+# CONFIG_EEPROM_93CX6 is not set
+# CONFIG_ENCLOSURE_SERVICES is not set
+CONFIG_HAVE_IDE=y
+# CONFIG_IDE is not set
 
 #
 # SCSI device support
 #
 # CONFIG_RAID_ATTRS is not set
 # CONFIG_SCSI is not set
-
-#
-# Multi-device support (RAID and LVM)
-#
+# CONFIG_SCSI_DMA is not set
+# CONFIG_SCSI_NETLINK is not set
+# CONFIG_ATA is not set
 # CONFIG_MD is not set
-
-#
-# Fusion MPT device support
-#
-# CONFIG_FUSION is not set
-
-#
-# IEEE 1394 (FireWire) support
-#
-
-#
-# I2O device support
-#
-
-#
-# Network device support
-#
 CONFIG_NETDEVICES=y
 # CONFIG_DUMMY is not set
 # CONFIG_BONDING is not set
+# CONFIG_MACVLAN is not set
 # CONFIG_EQUALIZER is not set
 # CONFIG_TUN is not set
-
-#
-# PHY device support
-#
+# CONFIG_VETH is not set
 # CONFIG_PHYLIB is not set
-
-#
-# Ethernet (10 or 100Mbit)
-#
 CONFIG_NET_ETHERNET=y
 CONFIG_MII=y
+# CONFIG_AX88796 is not set
 CONFIG_SMC91X=y
 # CONFIG_DM9000 is not set
-
-#
-# Ethernet (1000 Mbit)
-#
-
-#
-# Ethernet (10000 Mbit)
-#
-
-#
-# Token Ring devices
-#
-
-#
-# Wireless LAN (non-hamradio)
-#
-# CONFIG_NET_RADIO is not set
-
-#
-# Wan interfaces
-#
+CONFIG_SMC911X=y
+# CONFIG_IBM_NEW_EMAC_ZMII is not set
+# CONFIG_IBM_NEW_EMAC_RGMII is not set
+# CONFIG_IBM_NEW_EMAC_TAH is not set
+# CONFIG_IBM_NEW_EMAC_EMAC4 is not set
+# CONFIG_IBM_NEW_EMAC_NO_FLOW_CTRL is not set
+# CONFIG_IBM_NEW_EMAC_MAL_CLR_ICINTSTAT is not set
+# CONFIG_IBM_NEW_EMAC_MAL_COMMON_ERR is not set
+# CONFIG_B44 is not set
+# CONFIG_NETDEV_1000 is not set
+# CONFIG_NETDEV_10000 is not set
+
+#
+# Wireless LAN
+#
+# CONFIG_WLAN_PRE80211 is not set
+# CONFIG_WLAN_80211 is not set
+# CONFIG_IWLWIFI_LEDS is not set
 # CONFIG_WAN is not set
 # CONFIG_PPP is not set
 # CONFIG_SLIP is not set
+# CONFIG_NETCONSOLE is not set
 # CONFIG_NETPOLL is not set
 # CONFIG_NET_POLL_CONTROLLER is not set
-
-#
-# ISDN subsystem
-#
 # CONFIG_ISDN is not set
 
 #
 # Input device support
 #
 CONFIG_INPUT=y
+# CONFIG_INPUT_FF_MEMLESS is not set
+# CONFIG_INPUT_POLLDEV is not set
 
 #
 # Userland interfaces
@@ -420,7 +537,6 @@ CONFIG_INPUT_MOUSEDEV_PSAUX=y
 CONFIG_INPUT_MOUSEDEV_SCREEN_X=1024
 CONFIG_INPUT_MOUSEDEV_SCREEN_Y=768
 # CONFIG_INPUT_JOYDEV is not set
-# CONFIG_INPUT_TSDEV is not set
 # CONFIG_INPUT_EVDEV is not set
 # CONFIG_INPUT_EVBUG is not set
 
@@ -433,11 +549,19 @@ CONFIG_KEYBOARD_ATKBD=y
 # CONFIG_KEYBOARD_LKKBD is not set
 # CONFIG_KEYBOARD_XTKBD is not set
 # CONFIG_KEYBOARD_NEWTON is not set
+# CONFIG_KEYBOARD_STOWAWAY is not set
 CONFIG_INPUT_MOUSE=y
 CONFIG_MOUSE_PS2=y
+CONFIG_MOUSE_PS2_ALPS=y
+CONFIG_MOUSE_PS2_LOGIPS2PP=y
+CONFIG_MOUSE_PS2_SYNAPTICS=y
+CONFIG_MOUSE_PS2_LIFEBOOK=y
+CONFIG_MOUSE_PS2_TRACKPOINT=y
+# CONFIG_MOUSE_PS2_TOUCHKIT is not set
 # CONFIG_MOUSE_SERIAL is not set
 # CONFIG_MOUSE_VSXXXAA is not set
 # CONFIG_INPUT_JOYSTICK is not set
+# CONFIG_INPUT_TABLET is not set
 # CONFIG_INPUT_TOUCHSCREEN is not set
 # CONFIG_INPUT_MISC is not set
 
@@ -455,8 +579,11 @@ CONFIG_SERIO_LIBPS2=y
 # Character devices
 #
 CONFIG_VT=y
+CONFIG_CONSOLE_TRANSLATIONS=y
 CONFIG_VT_CONSOLE=y
 CONFIG_HW_CONSOLE=y
+# CONFIG_VT_HW_CONSOLE_BINDING is not set
+CONFIG_DEVKMEM=y
 # CONFIG_SERIAL_NONSTANDARD is not set
 
 #
@@ -475,73 +602,91 @@ CONFIG_SERIAL_CORE_CONSOLE=y
 CONFIG_UNIX98_PTYS=y
 CONFIG_LEGACY_PTYS=y
 CONFIG_LEGACY_PTY_COUNT=16
-
-#
-# IPMI
-#
 # CONFIG_IPMI_HANDLER is not set
-
-#
-# Watchdog Cards
-#
-# CONFIG_WATCHDOG is not set
+# CONFIG_HW_RANDOM is not set
 # CONFIG_NVRAM is not set
-# CONFIG_RTC is not set
-# CONFIG_DTLK is not set
 # CONFIG_R3964 is not set
-
-#
-# Ftape, the floppy tape device driver
-#
 # CONFIG_RAW_DRIVER is not set
-
-#
-# TPM devices
-#
-
-#
-# I2C support
-#
+# CONFIG_TCG_TPM is not set
 # CONFIG_I2C is not set
+# CONFIG_SPI is not set
+# CONFIG_W1 is not set
+# CONFIG_POWER_SUPPLY is not set
+# CONFIG_HWMON is not set
+# CONFIG_THERMAL is not set
+# CONFIG_THERMAL_HWMON is not set
+# CONFIG_WATCHDOG is not set
 
 #
-# Hardware Monitoring support
+# Sonics Silicon Backplane
 #
-# CONFIG_HWMON is not set
-# CONFIG_HWMON_VID is not set
+CONFIG_SSB_POSSIBLE=y
+# CONFIG_SSB is not set
 
 #
-# Misc devices
+# Multifunction device drivers
 #
+# CONFIG_MFD_CORE is not set
+# CONFIG_MFD_SM501 is not set
+# CONFIG_HTC_PASIC3 is not set
+# CONFIG_MFD_TMIO is not set
+# CONFIG_MFD_T7L66XB is not set
+# CONFIG_MFD_TC6387XB is not set
+# CONFIG_MFD_WM8400 is not set
 
 #
-# Multimedia Capabilities Port drivers
+# Multimedia devices
 #
 
 #
-# Multimedia devices
+# Multimedia core support
 #
 # CONFIG_VIDEO_DEV is not set
+# CONFIG_DVB_CORE is not set
+# CONFIG_VIDEO_MEDIA is not set
 
 #
-# Digital Video Broadcasting Devices
+# Multimedia drivers
 #
-# CONFIG_DVB is not set
+# CONFIG_DAB is not set
 
 #
 # Graphics support
 #
+# CONFIG_VGASTATE is not set
+# CONFIG_VIDEO_OUTPUT_CONTROL is not set
 CONFIG_FB=y
+# CONFIG_FIRMWARE_EDID is not set
+# CONFIG_FB_DDC is not set
+# CONFIG_FB_BOOT_VESA_SUPPORT is not set
 CONFIG_FB_CFB_FILLRECT=y
 CONFIG_FB_CFB_COPYAREA=y
 CONFIG_FB_CFB_IMAGEBLIT=y
-CONFIG_FB_SOFT_CURSOR=y
+# CONFIG_FB_CFB_REV_PIXELS_IN_BYTE is not set
+# CONFIG_FB_SYS_FILLRECT is not set
+# CONFIG_FB_SYS_COPYAREA is not set
+# CONFIG_FB_SYS_IMAGEBLIT is not set
+# CONFIG_FB_FOREIGN_ENDIAN is not set
+# CONFIG_FB_SYS_FOPS is not set
+# CONFIG_FB_SVGALIB is not set
 # CONFIG_FB_MACMODES is not set
+# CONFIG_FB_BACKLIGHT is not set
 # CONFIG_FB_MODE_HELPERS is not set
 # CONFIG_FB_TILEBLITTING is not set
+
+#
+# Frame buffer hardware drivers
+#
 CONFIG_FB_ARMCLCD=y
 # CONFIG_FB_S1D13XXX is not set
 # CONFIG_FB_VIRTUAL is not set
+# CONFIG_FB_METRONOME is not set
+# CONFIG_BACKLIGHT_LCD_SUPPORT is not set
+
+#
+# Display device support
+#
+# CONFIG_DISPLAY_SUPPORT is not set
 
 #
 # Console display driver support
@@ -549,27 +694,17 @@ CONFIG_FB_ARMCLCD=y
 # CONFIG_VGA_CONSOLE is not set
 CONFIG_DUMMY_CONSOLE=y
 CONFIG_FRAMEBUFFER_CONSOLE=y
+# CONFIG_FRAMEBUFFER_CONSOLE_DETECT_PRIMARY is not set
+# CONFIG_FRAMEBUFFER_CONSOLE_ROTATION is not set
 # CONFIG_FONTS is not set
 CONFIG_FONT_8x8=y
 CONFIG_FONT_8x16=y
-
-#
-# Logo configuration
-#
 CONFIG_LOGO=y
 # CONFIG_LOGO_LINUX_MONO is not set
 # CONFIG_LOGO_LINUX_VGA16 is not set
 CONFIG_LOGO_LINUX_CLUT224=y
-# CONFIG_BACKLIGHT_LCD_SUPPORT is not set
-
-#
-# Sound
-#
 CONFIG_SOUND=y
-
-#
-# Advanced Linux Sound Architecture
-#
+CONFIG_SOUND_OSS_CORE=y
 CONFIG_SND=y
 CONFIG_SND_TIMER=y
 CONFIG_SND_PCM=y
@@ -577,59 +712,71 @@ CONFIG_SND_PCM=y
 CONFIG_SND_OSSEMUL=y
 CONFIG_SND_MIXER_OSS=y
 CONFIG_SND_PCM_OSS=y
+CONFIG_SND_PCM_OSS_PLUGINS=y
+# CONFIG_SND_DYNAMIC_MINORS is not set
+CONFIG_SND_SUPPORT_OLD_API=y
+CONFIG_SND_VERBOSE_PROCFS=y
 # CONFIG_SND_VERBOSE_PRINTK is not set
 # CONFIG_SND_DEBUG is not set
-
-#
-# Generic devices
-#
-# CONFIG_SND_DUMMY is not set
-# CONFIG_SND_MTPAV is not set
-# CONFIG_SND_SERIAL_U16550 is not set
-# CONFIG_SND_MPU401 is not set
-
-#
-# ALSA ARM devices
-#
-# CONFIG_SND_ARMAACI is not set
-
-#
-# Open Sound System
-#
+CONFIG_SND_VMASTER=y
+CONFIG_SND_AC97_CODEC=y
+# CONFIG_SND_DRIVERS is not set
+CONFIG_SND_ARM=y
+CONFIG_SND_ARMAACI=y
+# CONFIG_SND_SOC is not set
 # CONFIG_SOUND_PRIME is not set
+CONFIG_AC97_BUS=y
+# CONFIG_HID_SUPPORT is not set
+# CONFIG_USB_SUPPORT is not set
+CONFIG_MMC=y
+# CONFIG_MMC_DEBUG is not set
+# CONFIG_MMC_UNSAFE_RESUME is not set
 
 #
-# USB support
+# MMC/SD/SDIO Card Drivers
 #
-CONFIG_USB_ARCH_HAS_HCD=y
-# CONFIG_USB_ARCH_HAS_OHCI is not set
-# CONFIG_USB is not set
+CONFIG_MMC_BLOCK=y
+CONFIG_MMC_BLOCK_BOUNCE=y
+# CONFIG_SDIO_UART is not set
+# CONFIG_MMC_TEST is not set
 
 #
-# USB Gadget Support
+# MMC/SD/SDIO Host Controller Drivers
 #
-# CONFIG_USB_GADGET is not set
+CONFIG_MMC_ARMMMCI=y
+# CONFIG_MMC_SDHCI is not set
+# CONFIG_MEMSTICK is not set
+# CONFIG_ACCESSIBILITY is not set
+# CONFIG_NEW_LEDS is not set
+CONFIG_RTC_LIB=y
+# CONFIG_RTC_CLASS is not set
+# CONFIG_DMADEVICES is not set
 
 #
-# MMC/SD Card support
+# Voltage and Current regulators
 #
-# CONFIG_MMC is not set
+# CONFIG_REGULATOR is not set
+# CONFIG_REGULATOR_FIXED_VOLTAGE is not set
+# CONFIG_REGULATOR_VIRTUAL_CONSUMER is not set
+# CONFIG_REGULATOR_BQ24022 is not set
+# CONFIG_UIO is not set
 
 #
 # File systems
 #
 # CONFIG_EXT2_FS is not set
 # CONFIG_EXT3_FS is not set
-# CONFIG_JBD is not set
+# CONFIG_EXT4_FS is not set
 # CONFIG_REISERFS_FS is not set
 # CONFIG_JFS_FS is not set
 # CONFIG_FS_POSIX_ACL is not set
+CONFIG_FILE_LOCKING=y
 # CONFIG_XFS_FS is not set
-# CONFIG_MINIX_FS is not set
-# CONFIG_ROMFS_FS is not set
+# CONFIG_OCFS2_FS is not set
+CONFIG_DNOTIFY=y
 CONFIG_INOTIFY=y
+CONFIG_INOTIFY_USER=y
 # CONFIG_QUOTA is not set
-CONFIG_DNOTIFY=y
 # CONFIG_AUTOFS_FS is not set
 # CONFIG_AUTOFS4_FS is not set
 # CONFIG_FUSE_FS is not set
@@ -654,51 +801,59 @@ CONFIG_FAT_DEFAULT_IOCHARSET="iso8859-1"
 # Pseudo filesystems
 #
 CONFIG_PROC_FS=y
+CONFIG_PROC_SYSCTL=y
+CONFIG_PROC_PAGE_MONITOR=y
 CONFIG_SYSFS=y
 CONFIG_TMPFS=y
+# CONFIG_TMPFS_POSIX_ACL is not set
 # CONFIG_HUGETLB_PAGE is not set
-CONFIG_RAMFS=y
-# CONFIG_RELAYFS_FS is not set
+# CONFIG_CONFIGFS_FS is not set
 
 #
 # Miscellaneous filesystems
 #
+# CONFIG_ADFS_FS is not set
+# CONFIG_AFFS_FS is not set
+# CONFIG_HFS_FS is not set
 # CONFIG_HFSPLUS_FS is not set
-# CONFIG_JFFS_FS is not set
+# CONFIG_BEFS_FS is not set
+# CONFIG_BFS_FS is not set
+# CONFIG_EFS_FS is not set
 # CONFIG_JFFS2_FS is not set
 CONFIG_CRAMFS=y
 # CONFIG_VXFS_FS is not set
+# CONFIG_MINIX_FS is not set
+# CONFIG_OMFS_FS is not set
 # CONFIG_HPFS_FS is not set
 # CONFIG_QNX4FS_FS is not set
+# CONFIG_ROMFS_FS is not set
 # CONFIG_SYSV_FS is not set
 # CONFIG_UFS_FS is not set
-
-#
-# Network File Systems
-#
+CONFIG_NETWORK_FILESYSTEMS=y
 CONFIG_NFS_FS=y
 CONFIG_NFS_V3=y
 # CONFIG_NFS_V3_ACL is not set
-# CONFIG_NFSD is not set
+# CONFIG_NFS_V4 is not set
 CONFIG_ROOT_NFS=y
+# CONFIG_NFSD is not set
 CONFIG_LOCKD=y
 CONFIG_LOCKD_V4=y
 CONFIG_NFS_COMMON=y
 CONFIG_SUNRPC=y
+# CONFIG_SUNRPC_REGISTER_V4 is not set
+# CONFIG_RPCSEC_GSS_KRB5 is not set
+# CONFIG_RPCSEC_GSS_SPKM3 is not set
 # CONFIG_SMB_FS is not set
 # CONFIG_CIFS is not set
 # CONFIG_NCP_FS is not set
 # CONFIG_CODA_FS is not set
+# CONFIG_AFS_FS is not set
 
 #
 # Partition Types
 #
 # CONFIG_PARTITION_ADVANCED is not set
 CONFIG_MSDOS_PARTITION=y
-
-#
-# Native Language Support
-#
 CONFIG_NLS=y
 CONFIG_NLS_DEFAULT="iso8859-1"
 CONFIG_NLS_CODEPAGE_437=y
@@ -739,26 +894,71 @@ CONFIG_NLS_ISO8859_1=y
 # CONFIG_NLS_KOI8_R is not set
 # CONFIG_NLS_KOI8_U is not set
 # CONFIG_NLS_UTF8 is not set
+# CONFIG_DLM is not set
 
 #
 # Kernel hacking
 #
 # CONFIG_PRINTK_TIME is not set
-CONFIG_DEBUG_KERNEL=y
+CONFIG_ENABLE_WARN_DEPRECATED=y
+CONFIG_ENABLE_MUST_CHECK=y
+CONFIG_FRAME_WARN=1024
 CONFIG_MAGIC_SYSRQ=y
-CONFIG_LOG_BUF_SHIFT=14
+# CONFIG_UNUSED_SYMBOLS is not set
+# CONFIG_DEBUG_FS is not set
+# CONFIG_HEADERS_CHECK is not set
+CONFIG_DEBUG_KERNEL=y
+# CONFIG_DEBUG_SHIRQ is not set
 CONFIG_DETECT_SOFTLOCKUP=y
+# CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC is not set
+CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC_VALUE=0
+# CONFIG_SCHED_DEBUG is not set
 # CONFIG_SCHEDSTATS is not set
+# CONFIG_TIMER_STATS is not set
+# CONFIG_DEBUG_OBJECTS is not set
 # CONFIG_DEBUG_SLAB is not set
+# CONFIG_DEBUG_RT_MUTEXES is not set
+# CONFIG_RT_MUTEX_TESTER is not set
 # CONFIG_DEBUG_SPINLOCK is not set
+# CONFIG_DEBUG_MUTEXES is not set
+# CONFIG_DEBUG_LOCK_ALLOC is not set
+# CONFIG_PROVE_LOCKING is not set
+# CONFIG_LOCK_STAT is not set
 # CONFIG_DEBUG_SPINLOCK_SLEEP is not set
+# CONFIG_DEBUG_LOCKING_API_SELFTESTS is not set
 # CONFIG_DEBUG_KOBJECT is not set
 CONFIG_DEBUG_BUGVERBOSE=y
 # CONFIG_DEBUG_INFO is not set
-# CONFIG_DEBUG_FS is not set
+# CONFIG_DEBUG_VM is not set
+# CONFIG_DEBUG_WRITECOUNT is not set
+CONFIG_DEBUG_MEMORY_INIT=y
+# CONFIG_DEBUG_LIST is not set
+# CONFIG_DEBUG_SG is not set
 CONFIG_FRAME_POINTER=y
+# CONFIG_BOOT_PRINTK_DELAY is not set
+# CONFIG_RCU_TORTURE_TEST is not set
+# CONFIG_RCU_CPU_STALL_DETECTOR is not set
+# CONFIG_BACKTRACE_SELF_TEST is not set
+# CONFIG_DEBUG_BLOCK_EXT_DEVT is not set
+# CONFIG_FAULT_INJECTION is not set
+# CONFIG_LATENCYTOP is not set
+# CONFIG_SYSCTL_SYSCALL_CHECK is not set
+CONFIG_NOP_TRACER=y
+CONFIG_HAVE_FTRACE=y
+CONFIG_HAVE_DYNAMIC_FTRACE=y
+# CONFIG_FTRACE is not set
+# CONFIG_IRQSOFF_TRACER is not set
+# CONFIG_SCHED_TRACER is not set
+# CONFIG_CONTEXT_SWITCH_TRACER is not set
+# CONFIG_BOOT_TRACER is not set
+# CONFIG_STACK_TRACER is not set
+# CONFIG_DYNAMIC_PRINTK_DEBUG is not set
+# CONFIG_SAMPLES is not set
+CONFIG_HAVE_ARCH_KGDB=y
+# CONFIG_KGDB is not set
 CONFIG_DEBUG_USER=y
 CONFIG_DEBUG_ERRORS=y
+# CONFIG_DEBUG_STACK_USAGE is not set
 # CONFIG_DEBUG_LL is not set
 
 #
@@ -766,21 +966,106 @@ CONFIG_DEBUG_ERRORS=y
 #
 # CONFIG_KEYS is not set
 # CONFIG_SECURITY is not set
+# CONFIG_SECURITYFS is not set
+# CONFIG_SECURITY_FILE_CAPABILITIES is not set
+CONFIG_CRYPTO=y
+
+#
+# Crypto core or helper
+#
+# CONFIG_CRYPTO_FIPS is not set
+# CONFIG_CRYPTO_MANAGER is not set
+# CONFIG_CRYPTO_GF128MUL is not set
+# CONFIG_CRYPTO_NULL is not set
+# CONFIG_CRYPTO_CRYPTD is not set
+# CONFIG_CRYPTO_AUTHENC is not set
+# CONFIG_CRYPTO_TEST is not set
+
+#
+# Authenticated Encryption with Associated Data
+#
+# CONFIG_CRYPTO_CCM is not set
+# CONFIG_CRYPTO_GCM is not set
+# CONFIG_CRYPTO_SEQIV is not set
+
+#
+# Block modes
+#
+# CONFIG_CRYPTO_CBC is not set
+# CONFIG_CRYPTO_CTR is not set
+# CONFIG_CRYPTO_CTS is not set
+# CONFIG_CRYPTO_ECB is not set
+# CONFIG_CRYPTO_LRW is not set
+# CONFIG_CRYPTO_PCBC is not set
+# CONFIG_CRYPTO_XTS is not set
+
+#
+# Hash modes
+#
+# CONFIG_CRYPTO_HMAC is not set
+# CONFIG_CRYPTO_XCBC is not set
+
+#
+# Digest
+#
+# CONFIG_CRYPTO_CRC32C is not set
+# CONFIG_CRYPTO_MD4 is not set
+# CONFIG_CRYPTO_MD5 is not set
+# CONFIG_CRYPTO_MICHAEL_MIC is not set
+# CONFIG_CRYPTO_RMD128 is not set
+# CONFIG_CRYPTO_RMD160 is not set
+# CONFIG_CRYPTO_RMD256 is not set
+# CONFIG_CRYPTO_RMD320 is not set
+# CONFIG_CRYPTO_SHA1 is not set
+# CONFIG_CRYPTO_SHA256 is not set
+# CONFIG_CRYPTO_SHA512 is not set
+# CONFIG_CRYPTO_TGR192 is not set
+# CONFIG_CRYPTO_WP512 is not set
+
+#
+# Ciphers
+#
+# CONFIG_CRYPTO_AES is not set
+# CONFIG_CRYPTO_ANUBIS is not set
+# CONFIG_CRYPTO_ARC4 is not set
+# CONFIG_CRYPTO_BLOWFISH is not set
+# CONFIG_CRYPTO_CAMELLIA is not set
+# CONFIG_CRYPTO_CAST5 is not set
+# CONFIG_CRYPTO_CAST6 is not set
+# CONFIG_CRYPTO_DES is not set
+# CONFIG_CRYPTO_FCRYPT is not set
+# CONFIG_CRYPTO_KHAZAD is not set
+# CONFIG_CRYPTO_SALSA20 is not set
+# CONFIG_CRYPTO_SEED is not set
+# CONFIG_CRYPTO_SERPENT is not set
+# CONFIG_CRYPTO_TEA is not set
+# CONFIG_CRYPTO_TWOFISH is not set
 
 #
-# Cryptographic options
+# Compression
 #
-# CONFIG_CRYPTO is not set
+# CONFIG_CRYPTO_DEFLATE is not set
+# CONFIG_CRYPTO_LZO is not set
 
 #
-# Hardware crypto devices
+# Random Number Generation
 #
+# CONFIG_CRYPTO_ANSI_CPRNG is not set
+# CONFIG_CRYPTO_HW is not set
 
 #
 # Library routines
 #
+CONFIG_BITREVERSE=y
 # CONFIG_CRC_CCITT is not set
 # CONFIG_CRC16 is not set
+# CONFIG_CRC_T10DIF is not set
+# CONFIG_CRC_ITU_T is not set
 CONFIG_CRC32=y
+# CONFIG_CRC7 is not set
 # CONFIG_LIBCRC32C is not set
 CONFIG_ZLIB_INFLATE=y
+CONFIG_PLIST=y
+CONFIG_HAS_IOMEM=y
+CONFIG_HAS_IOPORT=y
+CONFIG_HAS_DMA=y
diff --git a/arch/arm/include/asm/bitops.h b/arch/arm/include/asm/bitops.h
index 9a1db20e032a..63a481fbbed4 100644
--- a/arch/arm/include/asm/bitops.h
+++ b/arch/arm/include/asm/bitops.h
@@ -237,6 +237,7 @@ extern int _find_next_bit_be(const unsigned long *p, int size, int offset);
 #if __LINUX_ARM_ARCH__ < 5
 
 #include <asm-generic/bitops/ffz.h>
+#include <asm-generic/bitops/__fls.h>
 #include <asm-generic/bitops/__ffs.h>
 #include <asm-generic/bitops/fls.h>
 #include <asm-generic/bitops/ffs.h>
@@ -277,16 +278,19 @@ static inline int constant_fls(int x)
  * the clz instruction for much better code efficiency.
  */
 
-#define __fls(x) \
-	( __builtin_constant_p(x) ? constant_fls(x) : \
-	  ({ int __r; asm("clz\t%0, %1" : "=r"(__r) : "r"(x) : "cc"); 32-__r; }) )
-
-/* Implement fls() in C so that 64-bit args are suitably truncated */
 static inline int fls(int x)
 {
-	return __fls(x);
+	int ret;
+
+	if (__builtin_constant_p(x))
+	       return constant_fls(x);
+
+	asm("clz\t%0, %1" : "=r" (ret) : "r" (x) : "cc");
+       	ret = 32 - ret;
+	return ret;
 }
 
+#define __fls(x) (fls(x) - 1)
 #define ffs(x) ({ unsigned long __t = (x); fls(__t & -__t); })
 #define __ffs(x) (ffs(x) - 1)
 #define ffz(x) __ffs( ~(x) )
diff --git a/arch/arm/include/asm/cacheflush.h b/arch/arm/include/asm/cacheflush.h
index de6c59f814a1..6cbd8fdc9f1f 100644
--- a/arch/arm/include/asm/cacheflush.h
+++ b/arch/arm/include/asm/cacheflush.h
@@ -10,11 +10,11 @@
 #ifndef _ASMARM_CACHEFLUSH_H
 #define _ASMARM_CACHEFLUSH_H
 
-#include <linux/sched.h>
 #include <linux/mm.h>
 
 #include <asm/glue.h>
 #include <asm/shmparam.h>
+#include <asm/cachetype.h>
 
 #define CACHE_COLOUR(vaddr)	((vaddr & (SHMLBA - 1)) >> PAGE_SHIFT)
 
@@ -296,16 +296,6 @@ static inline void outer_flush_range(unsigned long start, unsigned long end)
 #endif
 
 /*
- * flush_cache_vmap() is used when creating mappings (eg, via vmap,
- * vmalloc, ioremap etc) in kernel space for pages.  Since the
- * direct-mappings of these pages may contain cached data, we need
- * to do a full cache flush to ensure that writebacks don't corrupt
- * data placed into these pages via the new mappings.
- */
-#define flush_cache_vmap(start, end)		flush_cache_all()
-#define flush_cache_vunmap(start, end)		flush_cache_all()
-
-/*
  * Copy user data from/to a page which is mapped into a different
  * processes address space.  Really, we want to allow our "user
  * space" model to handle this.
@@ -444,4 +434,29 @@ static inline void flush_ioremap_region(unsigned long phys, void __iomem *virt,
 	dmac_inv_range(start, start + size);
 }
 
+/*
+ * flush_cache_vmap() is used when creating mappings (eg, via vmap,
+ * vmalloc, ioremap etc) in kernel space for pages.  On non-VIPT
+ * caches, since the direct-mappings of these pages may contain cached
+ * data, we need to do a full cache flush to ensure that writebacks
+ * don't corrupt data placed into these pages via the new mappings.
+ */
+static inline void flush_cache_vmap(unsigned long start, unsigned long end)
+{
+	if (!cache_is_vipt_nonaliasing())
+		flush_cache_all();
+	else
+		/*
+		 * set_pte_at() called from vmap_pte_range() does not
+		 * have a DSB after cleaning the cache line.
+		 */
+		dsb();
+}
+
+static inline void flush_cache_vunmap(unsigned long start, unsigned long end)
+{
+	if (!cache_is_vipt_nonaliasing())
+		flush_cache_all();
+}
+
 #endif
diff --git a/arch/arm/include/asm/clkdev.h b/arch/arm/include/asm/clkdev.h
new file mode 100644
index 000000000000..b6ec7c627b39
--- /dev/null
+++ b/arch/arm/include/asm/clkdev.h
@@ -0,0 +1,30 @@
+/*
+ *  arch/arm/include/asm/clkdev.h
+ *
+ *  Copyright (C) 2008 Russell King.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Helper for the clk API to assist looking up a struct clk.
+ */
+#ifndef __ASM_CLKDEV_H
+#define __ASM_CLKDEV_H
+
+struct clk;
+
+struct clk_lookup {
+	struct list_head	node;
+	const char		*dev_id;
+	const char		*con_id;
+	struct clk		*clk;
+};
+
+struct clk_lookup *clkdev_alloc(struct clk *clk, const char *con_id,
+	const char *dev_fmt, ...);
+
+void clkdev_add(struct clk_lookup *cl);
+void clkdev_drop(struct clk_lookup *cl);
+
+#endif
diff --git a/arch/arm/include/asm/dma.h b/arch/arm/include/asm/dma.h
index 75154b193117..df5638f3643a 100644
--- a/arch/arm/include/asm/dma.h
+++ b/arch/arm/include/asm/dma.h
@@ -1,12 +1,7 @@
 #ifndef __ASM_ARM_DMA_H
 #define __ASM_ARM_DMA_H
 
-typedef unsigned int dmach_t;
-
-#include <linux/spinlock.h>
-#include <asm/system.h>
-#include <asm/scatterlist.h>
-#include <mach/dma.h>
+#include <asm/memory.h>
 
 /*
  * This is the maximum virtual address which can be DMA'd from.
@@ -15,6 +10,19 @@ typedef unsigned int dmach_t;
 #define MAX_DMA_ADDRESS	0xffffffff
 #endif
 
+#ifdef CONFIG_ISA_DMA_API
+/*
+ * This is used to support drivers written for the x86 ISA DMA API.
+ * It should not be re-used except for that purpose.
+ */
+#include <linux/spinlock.h>
+#include <asm/system.h>
+#include <asm/scatterlist.h>
+
+typedef unsigned int dmach_t;
+
+#include <mach/isa-dma.h>
+
 /*
  * DMA modes
  */
@@ -140,4 +148,6 @@ extern int isa_dma_bridge_buggy;
 #define isa_dma_bridge_buggy    (0)
 #endif
 
-#endif /* _ARM_DMA_H */
+#endif /* CONFIG_ISA_DMA_API */
+
+#endif /* __ASM_ARM_DMA_H */
diff --git a/arch/arm/include/asm/hardware/iomd.h b/arch/arm/include/asm/hardware/iomd.h
index 9c5afbd71a69..f9ee69e4f53e 100644
--- a/arch/arm/include/asm/hardware/iomd.h
+++ b/arch/arm/include/asm/hardware/iomd.h
@@ -32,19 +32,11 @@
 #define IOMD_KARTRX	(0x004)
 #define IOMD_KCTRL	(0x008)
 
-#ifdef CONFIG_ARCH_CLPS7500
-#define IOMD_IOLINES	(0x00C)
-#endif
-
 #define IOMD_IRQSTATA	(0x010)
 #define IOMD_IRQREQA	(0x014)
 #define IOMD_IRQCLRA	(0x014)
 #define IOMD_IRQMASKA	(0x018)
 
-#ifdef CONFIG_ARCH_CLPS7500
-#define IOMD_SUSMODE	(0x01C)
-#endif
-
 #define IOMD_IRQSTATB	(0x020)
 #define IOMD_IRQREQB	(0x024)
 #define IOMD_IRQMASKB	(0x028)
@@ -53,10 +45,6 @@
 #define IOMD_FIQREQ	(0x034)
 #define IOMD_FIQMASK	(0x038)
 
-#ifdef CONFIG_ARCH_CLPS7500
-#define IOMD_CLKCTL	(0x03C)
-#endif
-
 #define IOMD_T0CNTL	(0x040)
 #define IOMD_T0LTCHL	(0x040)
 #define IOMD_T0CNTH	(0x044)
@@ -71,18 +59,6 @@
 #define IOMD_T1GO	(0x058)
 #define IOMD_T1LATCH	(0x05c)
 
-#ifdef CONFIG_ARCH_CLPS7500
-#define IOMD_IRQSTATC	(0x060)
-#define IOMD_IRQREQC	(0x064)
-#define IOMD_IRQMASKC	(0x068)
-
-#define IOMD_VIDMUX	(0x06c)
-
-#define IOMD_IRQSTATD	(0x070)
-#define IOMD_IRQREQD	(0x074)
-#define IOMD_IRQMASKD	(0x078)
-#endif
-
 #define IOMD_ROMCR0	(0x080)
 #define IOMD_ROMCR1	(0x084)
 #ifdef CONFIG_ARCH_RPC
@@ -100,11 +76,6 @@
 #define IOMD_MOUSEY	(0x0A4)
 #endif
 
-#ifdef CONFIG_ARCH_CLPS7500
-#define IOMD_MSEDAT	(0x0A8)
-#define IOMD_MSECTL	(0x0Ac)
-#endif
-
 #ifdef CONFIG_ARCH_RPC
 #define IOMD_DMATCR	(0x0C0)
 #endif
@@ -113,18 +84,6 @@
 #ifdef CONFIG_ARCH_RPC
 #define IOMD_DMAEXT	(0x0CC)
 #endif
-#ifdef CONFIG_ARCH_CLPS7500
-#define IOMD_ASTCR	(0x0CC)
-#define IOMD_DRAMCR	(0x0D0)
-#define IOMD_SELFREF	(0x0D4)
-#define IOMD_ATODICR	(0x0E0)
-#define IOMD_ATODSR	(0x0E4)
-#define IOMD_ATODCC	(0x0E8)
-#define IOMD_ATODCNT1	(0x0EC)
-#define IOMD_ATODCNT2	(0x0F0)
-#define IOMD_ATODCNT3	(0x0F4)
-#define IOMD_ATODCNT4	(0x0F8)
-#endif
 
 #ifdef CONFIG_ARCH_RPC
 #define DMA_EXT_IO0	1
diff --git a/arch/arm/include/asm/hwcap.h b/arch/arm/include/asm/hwcap.h
index 81f4c899a555..bda489f9f017 100644
--- a/arch/arm/include/asm/hwcap.h
+++ b/arch/arm/include/asm/hwcap.h
@@ -16,6 +16,7 @@
 #define HWCAP_IWMMXT	512
 #define HWCAP_CRUNCH	1024
 #define HWCAP_THUMBEE	2048
+#define HWCAP_NEON	4096
 
 #if defined(__KERNEL__) && !defined(__ASSEMBLY__)
 /*
diff --git a/arch/arm/include/asm/io.h b/arch/arm/include/asm/io.h
index a8094451be57..d2a59cfc30ce 100644
--- a/arch/arm/include/asm/io.h
+++ b/arch/arm/include/asm/io.h
@@ -80,6 +80,14 @@ extern void __iounmap(volatile void __iomem *addr);
 extern void __readwrite_bug(const char *fn);
 
 /*
+ * A typesafe __io() helper
+ */
+static inline void __iomem *__typesafe_io(unsigned long addr)
+{
+	return (void __iomem *)addr;
+}
+
+/*
  * Now, pick up the machine-defined IO definitions
  */
 #include <mach/io.h>
diff --git a/arch/arm/include/asm/irq.h b/arch/arm/include/asm/irq.h
index a0009aa5d157..328f14a8b790 100644
--- a/arch/arm/include/asm/irq.h
+++ b/arch/arm/include/asm/irq.h
@@ -7,10 +7,6 @@
 #define irq_canonicalize(i)	(i)
 #endif
 
-#ifndef NR_IRQS
-#define NR_IRQS	128
-#endif
-
 /*
  * Use this value to indicate lack of interrupt
  * capability
diff --git a/arch/arm/include/asm/memory.h b/arch/arm/include/asm/memory.h
index 77764301844b..0202a7c20e62 100644
--- a/arch/arm/include/asm/memory.h
+++ b/arch/arm/include/asm/memory.h
@@ -112,10 +112,8 @@
  * private definitions which should NOT be used outside memory.h
  * files.  Use virt_to_phys/phys_to_virt/__pa/__va instead.
  */
-#ifndef __virt_to_phys
 #define __virt_to_phys(x)	((x) - PAGE_OFFSET + PHYS_OFFSET)
 #define __phys_to_virt(x)	((x) - PHYS_OFFSET + PAGE_OFFSET)
-#endif
 
 /*
  * Convert a physical address to a Page Frame Number and back
@@ -180,6 +178,11 @@ static inline void *phys_to_virt(unsigned long x)
  * memory.  Use of these is *deprecated* (and that doesn't mean
  * use the __ prefixed forms instead.)  See dma-mapping.h.
  */
+#ifndef __virt_to_bus
+#define __virt_to_bus	__virt_to_phys
+#define __bus_to_virt	__phys_to_virt
+#endif
+
 static inline __deprecated unsigned long virt_to_bus(void *x)
 {
 	return __virt_to_bus((unsigned long)x);
diff --git a/arch/arm/include/asm/mmu_context.h b/arch/arm/include/asm/mmu_context.h
index 0559f37c2a27..263fed05ea33 100644
--- a/arch/arm/include/asm/mmu_context.h
+++ b/arch/arm/include/asm/mmu_context.h
@@ -14,6 +14,7 @@
 #define __ASM_ARM_MMU_CONTEXT_H
 
 #include <linux/compiler.h>
+#include <linux/sched.h>
 #include <asm/cacheflush.h>
 #include <asm/cachetype.h>
 #include <asm/proc-fns.h>
diff --git a/arch/arm/include/asm/page.h b/arch/arm/include/asm/page.h
index bed1c0a00368..f341c9dbd662 100644
--- a/arch/arm/include/asm/page.h
+++ b/arch/arm/include/asm/page.h
@@ -108,32 +108,38 @@
 #error Unknown user operations model
 #endif
 
+struct page;
+
 struct cpu_user_fns {
-	void (*cpu_clear_user_page)(void *p, unsigned long user);
-	void (*cpu_copy_user_page)(void *to, const void *from,
-				   unsigned long user);
+	void (*cpu_clear_user_highpage)(struct page *page, unsigned long vaddr);
+	void (*cpu_copy_user_highpage)(struct page *to, struct page *from,
+			unsigned long vaddr);
 };
 
 #ifdef MULTI_USER
 extern struct cpu_user_fns cpu_user;
 
-#define __cpu_clear_user_page	cpu_user.cpu_clear_user_page
-#define __cpu_copy_user_page	cpu_user.cpu_copy_user_page
+#define __cpu_clear_user_highpage	cpu_user.cpu_clear_user_highpage
+#define __cpu_copy_user_highpage	cpu_user.cpu_copy_user_highpage
 
 #else
 
-#define __cpu_clear_user_page	__glue(_USER,_clear_user_page)
-#define __cpu_copy_user_page	__glue(_USER,_copy_user_page)
+#define __cpu_clear_user_highpage	__glue(_USER,_clear_user_highpage)
+#define __cpu_copy_user_highpage	__glue(_USER,_copy_user_highpage)
 
-extern void __cpu_clear_user_page(void *p, unsigned long user);
-extern void __cpu_copy_user_page(void *to, const void *from,
-				 unsigned long user);
+extern void __cpu_clear_user_highpage(struct page *page, unsigned long vaddr);
+extern void __cpu_copy_user_highpage(struct page *to, struct page *from,
+			unsigned long vaddr);
 #endif
 
-#define clear_user_page(addr,vaddr,pg)	 __cpu_clear_user_page(addr, vaddr)
-#define copy_user_page(to,from,vaddr,pg) __cpu_copy_user_page(to, from, vaddr)
+#define clear_user_highpage(page,vaddr)		\
+	 __cpu_clear_user_highpage(page, vaddr)
+
+#define __HAVE_ARCH_COPY_USER_HIGHPAGE
+#define copy_user_highpage(to,from,vaddr,vma)	\
+	__cpu_copy_user_highpage(to, from, vaddr)
 
-#define clear_page(page)	memzero((void *)(page), PAGE_SIZE)
+#define clear_page(page)	memset((void *)(page), 0, PAGE_SIZE)
 extern void copy_page(void *to, const void *from);
 
 #undef STRICT_MM_TYPECHECKS
diff --git a/arch/arm/include/asm/processor.h b/arch/arm/include/asm/processor.h
index 517a4d6ffc74..1845892260e7 100644
--- a/arch/arm/include/asm/processor.h
+++ b/arch/arm/include/asm/processor.h
@@ -23,7 +23,7 @@
 #include <asm/types.h>
 
 #ifdef __KERNEL__
-#define STACK_TOP	((current->personality == PER_LINUX_32BIT) ? \
+#define STACK_TOP	((current->personality & ADDR_LIMIT_32BIT) ? \
 			 TASK_SIZE : TASK_SIZE_26)
 #define STACK_TOP_MAX	TASK_SIZE
 #endif
@@ -64,7 +64,7 @@ struct thread_struct {
 ({									\
 	unsigned long *stack = (unsigned long *)sp;			\
 	set_fs(USER_DS);						\
-	memzero(regs->uregs, sizeof(regs->uregs));			\
+	memset(regs->uregs, 0, sizeof(regs->uregs));			\
 	if (current->personality & ADDR_LIMIT_32BIT)			\
 		regs->ARM_cpsr = USR_MODE;				\
 	else								\
diff --git a/arch/arm/include/asm/setup.h b/arch/arm/include/asm/setup.h
index a65413ba121d..f2cd18a0932b 100644
--- a/arch/arm/include/asm/setup.h
+++ b/arch/arm/include/asm/setup.h
@@ -209,9 +209,11 @@ struct meminfo {
 	struct membank bank[NR_BANKS];
 };
 
+extern struct meminfo meminfo;
+
 #define for_each_nodebank(iter,mi,no)			\
-	for (iter = 0; iter < mi->nr_banks; iter++)	\
-		if (mi->bank[iter].node == no)
+	for (iter = 0; iter < (mi)->nr_banks; iter++)	\
+		if ((mi)->bank[iter].node == no)
 
 #define bank_pfn_start(bank)	__phys_to_pfn((bank)->start)
 #define bank_pfn_end(bank)	__phys_to_pfn((bank)->start + (bank)->size)
diff --git a/arch/arm/include/asm/smp.h b/arch/arm/include/asm/smp.h
index 727b5c042e52..fad70da5911d 100644
--- a/arch/arm/include/asm/smp.h
+++ b/arch/arm/include/asm/smp.h
@@ -114,7 +114,7 @@ extern void local_timer_interrupt(void);
 /*
  * Stop a local timer interrupt.
  */
-extern void local_timer_stop(unsigned int cpu);
+extern void local_timer_stop(void);
 
 /*
  * Platform provides this to acknowledge a local timer IRQ
@@ -123,7 +123,7 @@ extern int local_timer_ack(void);
 
 #else
 
-static inline void local_timer_stop(unsigned int cpu)
+static inline void local_timer_stop(void)
 {
 }
 
@@ -132,7 +132,7 @@ static inline void local_timer_stop(unsigned int cpu)
 /*
  * Setup a local timer interrupt for a CPU.
  */
-extern void local_timer_setup(unsigned int cpu);
+extern void local_timer_setup(void);
 
 /*
  * show local interrupt info
diff --git a/arch/arm/include/asm/string.h b/arch/arm/include/asm/string.h
index e50c4a39b699..cf4f3aad0fc1 100644
--- a/arch/arm/include/asm/string.h
+++ b/arch/arm/include/asm/string.h
@@ -21,7 +21,6 @@ extern void * memmove(void *, const void *, __kernel_size_t);
 #define __HAVE_ARCH_MEMCHR
 extern void * memchr(const void *, int, __kernel_size_t);
 
-#define __HAVE_ARCH_MEMZERO
 #define __HAVE_ARCH_MEMSET
 extern void * memset(void *, int, __kernel_size_t);
 
@@ -39,12 +38,4 @@ extern void __memzero(void *ptr, __kernel_size_t n);
 		(__p);							\
 	})
 
-#define memzero(p,n) 							\
-	({ 								\
-	 	void *__p = (p); size_t __n = n;			\
-	 	if ((__n) != 0) 					\
-	 		__memzero((__p),(__n)); 			\
-	 	(__p); 							\
-	 })
-
 #endif
diff --git a/arch/arm/include/asm/system.h b/arch/arm/include/asm/system.h
index 568020b34e3e..811be55f338e 100644
--- a/arch/arm/include/asm/system.h
+++ b/arch/arm/include/asm/system.h
@@ -3,8 +3,6 @@
 
 #ifdef __KERNEL__
 
-#include <asm/memory.h>
-
 #define CPU_ARCH_UNKNOWN	0
 #define CPU_ARCH_ARMv3		1
 #define CPU_ARCH_ARMv4		2
diff --git a/arch/arm/include/asm/uaccess.h b/arch/arm/include/asm/uaccess.h
index e98ec60b3400..7897464e0c24 100644
--- a/arch/arm/include/asm/uaccess.h
+++ b/arch/arm/include/asm/uaccess.h
@@ -11,7 +11,8 @@
 /*
  * User space memory access functions
  */
-#include <linux/sched.h>
+#include <linux/string.h>
+#include <linux/thread_info.h>
 #include <asm/errno.h>
 #include <asm/memory.h>
 #include <asm/domain.h>
@@ -400,7 +401,7 @@ static inline unsigned long __must_check copy_from_user(void *to, const void __u
 	if (access_ok(VERIFY_READ, from, n))
 		n = __copy_from_user(to, from, n);
 	else /* security hole - plug it */
-		memzero(to, n);
+		memset(to, 0, n);
 	return n;
 }
 
diff --git a/arch/arm/kernel/armksyms.c b/arch/arm/kernel/armksyms.c
index c74f766ffc12..53d0037a1e9d 100644
--- a/arch/arm/kernel/armksyms.c
+++ b/arch/arm/kernel/armksyms.c
@@ -8,6 +8,7 @@
  * published by the Free Software Foundation.
  */
 #include <linux/module.h>
+#include <linux/sched.h>
 #include <linux/string.h>
 #include <linux/cryptohash.h>
 #include <linux/delay.h>
diff --git a/arch/arm/kernel/ecard.c b/arch/arm/kernel/ecard.c
index 60c079d85355..eed2f795e1b3 100644
--- a/arch/arm/kernel/ecard.c
+++ b/arch/arm/kernel/ecard.c
@@ -817,7 +817,7 @@ static struct expansion_card *__init ecard_alloc_card(int type, int slot)
 	ec->dma = NO_DMA;
 	ec->ops = &ecard_default_ops;
 
-	snprintf(ec->dev.bus_id, sizeof(ec->dev.bus_id), "ecard%d", slot);
+	dev_set_name(&ec->dev, "ecard%d", slot);
 	ec->dev.parent = NULL;
 	ec->dev.bus = &ecard_bus_type;
 	ec->dev.dma_mask = &ec->dma_mask;
diff --git a/arch/arm/kernel/head-common.S b/arch/arm/kernel/head-common.S
index bde52df1c668..991952c644d1 100644
--- a/arch/arm/kernel/head-common.S
+++ b/arch/arm/kernel/head-common.S
@@ -18,7 +18,7 @@
 __switch_data:
 	.long	__mmap_switched
 	.long	__data_loc			@ r4
-	.long	__data_start			@ r5
+	.long	_data				@ r5
 	.long	__bss_start			@ r6
 	.long	_end				@ r7
 	.long	processor_id			@ r4
diff --git a/arch/arm/kernel/module.c b/arch/arm/kernel/module.c
index b8d965dcd6fd..dab48f27263f 100644
--- a/arch/arm/kernel/module.c
+++ b/arch/arm/kernel/module.c
@@ -21,6 +21,7 @@
 #include <linux/string.h>
 
 #include <asm/pgtable.h>
+#include <asm/sections.h>
 
 #ifdef CONFIG_XIP_KERNEL
 /*
@@ -29,9 +30,8 @@
  * MODULES_VADDR is redefined here and not in asm/memory.h to avoid
  * recompiling the whole kernel when CONFIG_XIP_KERNEL is turned on/off.
  */
-extern void _etext;
 #undef MODULES_VADDR
-#define MODULES_VADDR	(((unsigned long)&_etext + ~PGDIR_MASK) & PGDIR_MASK)
+#define MODULES_VADDR	(((unsigned long)_etext + ~PGDIR_MASK) & PGDIR_MASK)
 #endif
 
 #ifdef CONFIG_MMU
diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c
index 1f1eecca7f55..7049815d66d5 100644
--- a/arch/arm/kernel/setup.c
+++ b/arch/arm/kernel/setup.c
@@ -29,6 +29,7 @@
 #include <asm/cputype.h>
 #include <asm/elf.h>
 #include <asm/procinfo.h>
+#include <asm/sections.h>
 #include <asm/setup.h>
 #include <asm/mach-types.h>
 #include <asm/cacheflush.h>
@@ -59,9 +60,8 @@ static int __init fpe_setup(char *line)
 __setup("fpe=", fpe_setup);
 #endif
 
-extern void paging_init(struct meminfo *, struct machine_desc *desc);
+extern void paging_init(struct machine_desc *desc);
 extern void reboot_setup(char *str);
-extern void _text, _etext, __data_start, _edata, _end;
 
 unsigned int processor_id;
 EXPORT_SYMBOL(processor_id);
@@ -112,7 +112,6 @@ static struct stack stacks[NR_CPUS];
 char elf_platform[ELF_PLATFORM_SIZE];
 EXPORT_SYMBOL(elf_platform);
 
-static struct meminfo meminfo __initdata = { 0, };
 static const char *cpu_name;
 static const char *machine_name;
 static char __initdata command_line[COMMAND_LINE_SIZE];
@@ -367,21 +366,34 @@ static struct machine_desc * __init setup_machine(unsigned int nr)
 	return list;
 }
 
-static void __init arm_add_memory(unsigned long start, unsigned long size)
+static int __init arm_add_memory(unsigned long start, unsigned long size)
 {
-	struct membank *bank;
+	struct membank *bank = &meminfo.bank[meminfo.nr_banks];
+
+	if (meminfo.nr_banks >= NR_BANKS) {
+		printk(KERN_CRIT "NR_BANKS too low, "
+			"ignoring memory at %#lx\n", start);
+		return -EINVAL;
+	}
 
 	/*
 	 * Ensure that start/size are aligned to a page boundary.
 	 * Size is appropriately rounded down, start is rounded up.
 	 */
 	size -= start & ~PAGE_MASK;
-
-	bank = &meminfo.bank[meminfo.nr_banks++];
-
 	bank->start = PAGE_ALIGN(start);
 	bank->size  = size & PAGE_MASK;
 	bank->node  = PHYS_TO_NID(start);
+
+	/*
+	 * Check whether this memory region has non-zero size or
+	 * invalid node number.
+	 */
+	if (bank->size == 0 || bank->node >= MAX_NUMNODES)
+		return -EINVAL;
+
+	meminfo.nr_banks++;
+	return 0;
 }
 
 /*
@@ -472,10 +484,10 @@ request_standard_resources(struct meminfo *mi, struct machine_desc *mdesc)
 	struct resource *res;
 	int i;
 
-	kernel_code.start   = virt_to_phys(&_text);
-	kernel_code.end     = virt_to_phys(&_etext - 1);
-	kernel_data.start   = virt_to_phys(&__data_start);
-	kernel_data.end     = virt_to_phys(&_end - 1);
+	kernel_code.start   = virt_to_phys(_text);
+	kernel_code.end     = virt_to_phys(_etext - 1);
+	kernel_data.start   = virt_to_phys(_data);
+	kernel_data.end     = virt_to_phys(_end - 1);
 
 	for (i = 0; i < mi->nr_banks; i++) {
 		if (mi->bank[i].size == 0)
@@ -539,14 +551,7 @@ __tagtable(ATAG_CORE, parse_tag_core);
 
 static int __init parse_tag_mem32(const struct tag *tag)
 {
-	if (meminfo.nr_banks >= NR_BANKS) {
-		printk(KERN_WARNING
-		       "Ignoring memory bank 0x%08x size %dKB\n",
-			tag->u.mem.start, tag->u.mem.size / 1024);
-		return -EINVAL;
-	}
-	arm_add_memory(tag->u.mem.start, tag->u.mem.size);
-	return 0;
+	return arm_add_memory(tag->u.mem.start, tag->u.mem.size);
 }
 
 __tagtable(ATAG_MEM, parse_tag_mem32);
@@ -710,15 +715,15 @@ void __init setup_arch(char **cmdline_p)
 		parse_tags(tags);
 	}
 
-	init_mm.start_code = (unsigned long) &_text;
-	init_mm.end_code   = (unsigned long) &_etext;
-	init_mm.end_data   = (unsigned long) &_edata;
-	init_mm.brk	   = (unsigned long) &_end;
+	init_mm.start_code = (unsigned long) _text;
+	init_mm.end_code   = (unsigned long) _etext;
+	init_mm.end_data   = (unsigned long) _edata;
+	init_mm.brk	   = (unsigned long) _end;
 
 	memcpy(boot_command_line, from, COMMAND_LINE_SIZE);
 	boot_command_line[COMMAND_LINE_SIZE-1] = '\0';
 	parse_cmdline(cmdline_p, from);
-	paging_init(&meminfo, mdesc);
+	paging_init(mdesc);
 	request_standard_resources(&meminfo, mdesc);
 
 #ifdef CONFIG_SMP
@@ -772,6 +777,8 @@ static const char *hwcap_str[] = {
 	"java",
 	"iwmmxt",
 	"crunch",
+	"thumbee",
+	"neon",
 	NULL
 };
 
diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index e42a749a56dd..019237d21622 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -181,7 +181,7 @@ int __cpuexit __cpu_disable(void)
 	/*
 	 * Stop the local timer for this CPU.
 	 */
-	local_timer_stop(cpu);
+	local_timer_stop();
 
 	/*
 	 * Flush user cache and TLB mappings, and then remove this CPU
@@ -284,7 +284,7 @@ asmlinkage void __cpuinit secondary_start_kernel(void)
 	/*
 	 * Setup local timer for this CPU.
 	 */
-	local_timer_setup(cpu);
+	local_timer_setup();
 
 	calibrate_delay();
 
diff --git a/arch/arm/kernel/thumbee.c b/arch/arm/kernel/thumbee.c
index df3f6b7ebcea..9cb7aaca159f 100644
--- a/arch/arm/kernel/thumbee.c
+++ b/arch/arm/kernel/thumbee.c
@@ -25,7 +25,7 @@
 /*
  * Access to the ThumbEE Handler Base register
  */
-static inline unsigned long teehbr_read()
+static inline unsigned long teehbr_read(void)
 {
 	unsigned long v;
 	asm("mrc	p14, 6, %0, c1, c0, 0\n" : "=r" (v));
diff --git a/arch/arm/kernel/vmlinux.lds.S b/arch/arm/kernel/vmlinux.lds.S
index 4898bdcfe7dd..00216071eaf7 100644
--- a/arch/arm/kernel/vmlinux.lds.S
+++ b/arch/arm/kernel/vmlinux.lds.S
@@ -119,7 +119,7 @@ SECTIONS
 #endif
 
 	.data : AT(__data_loc) {
-		__data_start = .;	/* address in memory */
+		_data = .;		/* address in memory */
 
 		/*
 		 * first, the init task union, aligned
diff --git a/arch/arm/lib/Makefile b/arch/arm/lib/Makefile
index 30351cd4560d..866f84a586ff 100644
--- a/arch/arm/lib/Makefile
+++ b/arch/arm/lib/Makefile
@@ -38,7 +38,6 @@ else
 endif
 
 lib-$(CONFIG_ARCH_RPC)		+= ecard.o io-acorn.o floppydma.o
-lib-$(CONFIG_ARCH_CLPS7500)	+= io-acorn.o
 lib-$(CONFIG_ARCH_L7200)	+= io-acorn.o
 lib-$(CONFIG_ARCH_SHARK)	+= io-shark.o
 
diff --git a/arch/arm/lib/memset.S b/arch/arm/lib/memset.S
index 761eefa76243..650d5923ab83 100644
--- a/arch/arm/lib/memset.S
+++ b/arch/arm/lib/memset.S
@@ -25,7 +25,7 @@
 	add	r2, r2, r3		@ 1 (r2 = r2 - (4 - r3))
 /*
  * The pointer is now aligned and the length is adjusted.  Try doing the
- * memzero again.
+ * memset again.
  */
 
 ENTRY(memset)
diff --git a/arch/arm/mach-aaec2000/Makefile b/arch/arm/mach-aaec2000/Makefile
index a8e462f58bc9..20ec83896c37 100644
--- a/arch/arm/mach-aaec2000/Makefile
+++ b/arch/arm/mach-aaec2000/Makefile
@@ -3,7 +3,7 @@
 #
 
 # Common support (must be linked before board specific support)
-obj-y += core.o clock.o
+obj-y += core.o
 
 # Specific board support
 obj-$(CONFIG_MACH_AAED2000) += aaed2000.o
diff --git a/arch/arm/mach-aaec2000/clock.c b/arch/arm/mach-aaec2000/clock.c
deleted file mode 100644
index e10ee158d720..000000000000
--- a/arch/arm/mach-aaec2000/clock.c
+++ /dev/null
@@ -1,99 +0,0 @@
-/*
- *  linux/arch/arm/mach-aaec2000/clock.c
- *
- *  Copyright (C) 2005 Nicolas Bellido Y Ortega
- *
- *  Based on linux/arch/arm/mach-integrator/clock.c
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#include <linux/module.h>
-#include <linux/kernel.h>
-#include <linux/list.h>
-#include <linux/errno.h>
-#include <linux/err.h>
-#include <linux/string.h>
-#include <linux/clk.h>
-#include <linux/mutex.h>
-
-#include "clock.h"
-
-static LIST_HEAD(clocks);
-static DEFINE_MUTEX(clocks_mutex);
-
-struct clk *clk_get(struct device *dev, const char *id)
-{
-	struct clk *p, *clk = ERR_PTR(-ENOENT);
-
-	mutex_lock(&clocks_mutex);
-	list_for_each_entry(p, &clocks, node) {
-		if (strcmp(id, p->name) == 0 && try_module_get(p->owner)) {
-			clk = p;
-			break;
-		}
-	}
-	mutex_unlock(&clocks_mutex);
-
-	return clk;
-}
-EXPORT_SYMBOL(clk_get);
-
-void clk_put(struct clk *clk)
-{
-	module_put(clk->owner);
-}
-EXPORT_SYMBOL(clk_put);
-
-int clk_enable(struct clk *clk)
-{
-	return 0;
-}
-EXPORT_SYMBOL(clk_enable);
-
-void clk_disable(struct clk *clk)
-{
-}
-EXPORT_SYMBOL(clk_disable);
-
-unsigned long clk_get_rate(struct clk *clk)
-{
-	return clk->rate;
-}
-EXPORT_SYMBOL(clk_get_rate);
-
-long clk_round_rate(struct clk *clk, unsigned long rate)
-{
-	return rate;
-}
-EXPORT_SYMBOL(clk_round_rate);
-
-int clk_set_rate(struct clk *clk, unsigned long rate)
-{
-	return 0;
-}
-EXPORT_SYMBOL(clk_set_rate);
-
-int clk_register(struct clk *clk)
-{
-	mutex_lock(&clocks_mutex);
-	list_add(&clk->node, &clocks);
-	mutex_unlock(&clocks_mutex);
-	return 0;
-}
-EXPORT_SYMBOL(clk_register);
-
-void clk_unregister(struct clk *clk)
-{
-	mutex_lock(&clocks_mutex);
-	list_del(&clk->node);
-	mutex_unlock(&clocks_mutex);
-}
-EXPORT_SYMBOL(clk_unregister);
-
-static int __init clk_init(void)
-{
-	return 0;
-}
-arch_initcall(clk_init);
diff --git a/arch/arm/mach-aaec2000/clock.h b/arch/arm/mach-aaec2000/clock.h
deleted file mode 100644
index d4bb74ff613f..000000000000
--- a/arch/arm/mach-aaec2000/clock.h
+++ /dev/null
@@ -1,23 +0,0 @@
-/*
- *  linux/arch/arm/mach-aaec2000/clock.h
- *
- *  Copyright (C) 2005 Nicolas Bellido Y Ortega
- *
- *  Based on linux/arch/arm/mach-integrator/clock.h
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-struct module;
-
-struct clk {
-	struct list_head	node;
-	unsigned long		rate;
-	struct module		*owner;
-	const char		*name;
-	void			*data;
-};
-
-int clk_register(struct clk *clk);
-void clk_unregister(struct clk *clk);
diff --git a/arch/arm/mach-aaec2000/core.c b/arch/arm/mach-aaec2000/core.c
index dfb26bc23d1a..b5c5fc6ba3a9 100644
--- a/arch/arm/mach-aaec2000/core.c
+++ b/arch/arm/mach-aaec2000/core.c
@@ -19,6 +19,7 @@
 #include <linux/interrupt.h>
 #include <linux/timex.h>
 #include <linux/signal.h>
+#include <linux/clk.h>
 
 #include <mach/hardware.h>
 #include <asm/irq.h>
@@ -30,7 +31,6 @@
 #include <asm/mach/map.h>
 
 #include "core.h"
-#include "clock.h"
 
 /*
  * Common I/O mapping:
@@ -212,7 +212,7 @@ static struct clcd_board clcd_plat_data = {
 
 static struct amba_device clcd_device = {
 	.dev		= {
-		.bus_id			= "mb:16",
+		.init_name		= "mb:16",
 		.coherent_dma_mask	= ~0,
 		.platform_data		= &clcd_plat_data,
 	},
@@ -229,9 +229,28 @@ static struct amba_device *amba_devs[] __initdata = {
 	&clcd_device,
 };
 
-static struct clk aaec2000_clcd_clk = {
-	.name = "CLCDCLK",
-};
+void clk_disable(struct clk *clk)
+{
+}
+
+int clk_set_rate(struct clk *clk, unsigned long rate)
+{
+	return 0;
+}
+
+int clk_enable(struct clk *clk)
+{
+	return 0;
+}
+
+struct clk *clk_get(struct device *dev, const char *id)
+{
+	return dev && strcmp(dev_name(dev), "mb:16") == 0 ? NULL : ERR_PTR(-ENOENT);
+}
+
+void clk_put(struct clk *clk)
+{
+}
 
 void __init aaec2000_set_clcd_plat_data(struct aaec2000_clcd_info *clcd)
 {
@@ -265,8 +284,6 @@ static int __init aaec2000_init(void)
 {
 	int i;
 
-	clk_register(&aaec2000_clcd_clk);
-
 	for (i = 0; i < ARRAY_SIZE(amba_devs); i++) {
 		struct amba_device *d = amba_devs[i];
 		amba_device_register(d, &iomem_resource);
diff --git a/arch/arm/mach-aaec2000/include/mach/dma.h b/arch/arm/mach-aaec2000/include/mach/dma.h
deleted file mode 100644
index 2da846c72fe7..000000000000
--- a/arch/arm/mach-aaec2000/include/mach/dma.h
+++ /dev/null
@@ -1,9 +0,0 @@
-/*
- *  arch/arm/mach-aaec2000/include/mach/dma.h
- *
- *  Copyright (c) 2005 Nicolas Bellido Y Ortega
- *
- *  This program is free software; you can redistribute it and/or modify
- *  it under the terms of the GNU General Public License version 2 as
- *  published by the Free Software Foundation.
- */
diff --git a/arch/arm/mach-aaec2000/include/mach/io.h b/arch/arm/mach-aaec2000/include/mach/io.h
index c87c24de1110..ab4fe5d20eaf 100644
--- a/arch/arm/mach-aaec2000/include/mach/io.h
+++ b/arch/arm/mach-aaec2000/include/mach/io.h
@@ -6,15 +6,13 @@
 #ifndef __ASM_ARM_ARCH_IO_H
 #define __ASM_ARM_ARCH_IO_H
 
-#include <mach/hardware.h>
-
 #define IO_SPACE_LIMIT 0xffffffff
 
 /*
  * We don't actually have real ISA nor PCI buses, but there is so many
  * drivers out there that might just work if we fake them...
  */
-#define __io(a)			((void __iomem *)(a))
-#define __mem_pci(a)		(a)
+#define __io(a)		__typesafe_io(a)
+#define __mem_pci(a)	(a)
 
 #endif
diff --git a/arch/arm/mach-aaec2000/include/mach/memory.h b/arch/arm/mach-aaec2000/include/mach/memory.h
index 56ae900a482e..c00822543d9f 100644
--- a/arch/arm/mach-aaec2000/include/mach/memory.h
+++ b/arch/arm/mach-aaec2000/include/mach/memory.h
@@ -14,9 +14,6 @@
 
 #define PHYS_OFFSET	UL(0xf0000000)
 
-#define __virt_to_bus(x)	__virt_to_phys(x)
-#define __bus_to_virt(x)	__phys_to_virt(x)
-
 /*
  * The nodes are the followings:
  *
diff --git a/arch/arm/mach-at91/Kconfig b/arch/arm/mach-at91/Kconfig
index 5aafb2e2ca7a..323b47f2b52f 100644
--- a/arch/arm/mach-at91/Kconfig
+++ b/arch/arm/mach-at91/Kconfig
@@ -7,36 +7,43 @@ choice
 
 config ARCH_AT91RM9200
 	bool "AT91RM9200"
+	select CPU_ARM920T
 	select GENERIC_TIME
 	select GENERIC_CLOCKEVENTS
 
 config ARCH_AT91SAM9260
 	bool "AT91SAM9260 or AT91SAM9XE"
+	select CPU_ARM926T
 	select GENERIC_TIME
 	select GENERIC_CLOCKEVENTS
 
 config ARCH_AT91SAM9261
 	bool "AT91SAM9261"
+	select CPU_ARM926T
 	select GENERIC_TIME
 	select GENERIC_CLOCKEVENTS
 
 config ARCH_AT91SAM9263
 	bool "AT91SAM9263"
+	select CPU_ARM926T
 	select GENERIC_TIME
 	select GENERIC_CLOCKEVENTS
 
 config ARCH_AT91SAM9RL
 	bool "AT91SAM9RL"
+	select CPU_ARM926T
 	select GENERIC_TIME
 	select GENERIC_CLOCKEVENTS
 
 config ARCH_AT91SAM9G20
 	bool "AT91SAM9G20"
+	select CPU_ARM926T
 	select GENERIC_TIME
 	select GENERIC_CLOCKEVENTS
 
 config ARCH_AT91CAP9
 	bool "AT91CAP9"
+	select CPU_ARM926T
 	select GENERIC_TIME
 	select GENERIC_CLOCKEVENTS
 
@@ -235,6 +242,12 @@ config MACH_USB_A9263
 	  Select this if you are using a Calao Systems USB-A9263.
 	  <http://www.calao-systems.com>
 
+config MACH_NEOCORE926
+	bool "Adeneo NEOCORE926"
+	depends on ARCH_AT91SAM9263
+	help
+	  Select this if you are using the Adeneo Neocore 926 board.
+
 endif
 
 # ----------------------------------------------------------
@@ -302,7 +315,7 @@ comment "AT91 Board Options"
 
 config MTD_AT91_DATAFLASH_CARD
 	bool "Enable DataFlash Card support"
-	depends on (ARCH_AT91RM9200DK || MACH_AT91RM9200EK || MACH_AT91SAM9260EK || MACH_AT91SAM9261EK || MACH_AT91SAM9263EK || MACH_AT91SAM9G20EK || MACH_ECBAT91 || MACH_SAM9_L9260 || MACH_AT91CAP9ADK)
+	depends on (ARCH_AT91RM9200DK || MACH_AT91RM9200EK || MACH_AT91SAM9260EK || MACH_AT91SAM9261EK || MACH_AT91SAM9263EK || MACH_AT91SAM9G20EK || MACH_ECBAT91 || MACH_SAM9_L9260 || MACH_AT91CAP9ADK || MACH_NEOCORE926)
 	help
 	  Enable support for the DataFlash card.
 
diff --git a/arch/arm/mach-at91/Makefile b/arch/arm/mach-at91/Makefile
index cca612d97ca2..c69ff237fd14 100644
--- a/arch/arm/mach-at91/Makefile
+++ b/arch/arm/mach-at91/Makefile
@@ -11,12 +11,12 @@ obj-$(CONFIG_AT91_PMC_UNIT)	+= clock.o
 
 # CPU-specific support
 obj-$(CONFIG_ARCH_AT91RM9200)	+= at91rm9200.o at91rm9200_time.o at91rm9200_devices.o
-obj-$(CONFIG_ARCH_AT91SAM9260)	+= at91sam9260.o at91sam926x_time.o at91sam9260_devices.o
-obj-$(CONFIG_ARCH_AT91SAM9261)	+= at91sam9261.o at91sam926x_time.o at91sam9261_devices.o
-obj-$(CONFIG_ARCH_AT91SAM9263)	+= at91sam9263.o at91sam926x_time.o at91sam9263_devices.o
-obj-$(CONFIG_ARCH_AT91SAM9RL)	+= at91sam9rl.o at91sam926x_time.o at91sam9rl_devices.o
-obj-$(CONFIG_ARCH_AT91SAM9G20)	+= at91sam9260.o at91sam926x_time.o at91sam9260_devices.o
-obj-$(CONFIG_ARCH_AT91CAP9)	+= at91cap9.o at91sam926x_time.o at91cap9_devices.o
+obj-$(CONFIG_ARCH_AT91SAM9260)	+= at91sam9260.o at91sam926x_time.o at91sam9260_devices.o sam9_smc.o
+obj-$(CONFIG_ARCH_AT91SAM9261)	+= at91sam9261.o at91sam926x_time.o at91sam9261_devices.o sam9_smc.o
+obj-$(CONFIG_ARCH_AT91SAM9263)	+= at91sam9263.o at91sam926x_time.o at91sam9263_devices.o sam9_smc.o
+obj-$(CONFIG_ARCH_AT91SAM9RL)	+= at91sam9rl.o at91sam926x_time.o at91sam9rl_devices.o sam9_smc.o
+obj-$(CONFIG_ARCH_AT91SAM9G20)	+= at91sam9260.o at91sam926x_time.o at91sam9260_devices.o  sam9_smc.o
+obj-$(CONFIG_ARCH_AT91CAP9)	+= at91cap9.o at91sam926x_time.o at91cap9_devices.o sam9_smc.o
 obj-$(CONFIG_ARCH_AT91X40)	+= at91x40.o at91x40_time.o
 
 # AT91RM9200 board-specific support
@@ -47,6 +47,7 @@ obj-$(CONFIG_MACH_AT91SAM9261EK) += board-sam9261ek.o
 # AT91SAM9263 board-specific support
 obj-$(CONFIG_MACH_AT91SAM9263EK) += board-sam9263ek.o
 obj-$(CONFIG_MACH_USB_A9263)	+= board-usb-a9263.o
+obj-$(CONFIG_MACH_NEOCORE926)	+= board-neocore926.o
 
 # AT91SAM9RL board-specific support
 obj-$(CONFIG_MACH_AT91SAM9RLEK)	+= board-sam9rlek.o
diff --git a/arch/arm/mach-at91/at91cap9.c b/arch/arm/mach-at91/at91cap9.c
index 0fc0adaebd58..0a38c69fdbc4 100644
--- a/arch/arm/mach-at91/at91cap9.c
+++ b/arch/arm/mach-at91/at91cap9.c
@@ -17,6 +17,8 @@
 
 #include <asm/mach/arch.h>
 #include <asm/mach/map.h>
+
+#include <mach/cpu.h>
 #include <mach/at91cap9.h>
 #include <mach/at91_pmc.h>
 #include <mach/at91_rstc.h>
@@ -317,6 +319,12 @@ void __init at91cap9_initialize(unsigned long main_clock)
 
 	/* Register GPIO subsystem */
 	at91_gpio_init(at91cap9_gpio, 4);
+
+	/* Remember the silicon revision */
+	if (cpu_is_at91cap9_revB())
+		system_rev = 0xB;
+	else if (cpu_is_at91cap9_revC())
+		system_rev = 0xC;
 }
 
 /* --------------------------------------------------------------------
diff --git a/arch/arm/mach-at91/at91cap9_devices.c b/arch/arm/mach-at91/at91cap9_devices.c
index 5ebd4273d353..9eca2209cde6 100644
--- a/arch/arm/mach-at91/at91cap9_devices.c
+++ b/arch/arm/mach-at91/at91cap9_devices.c
@@ -13,6 +13,7 @@
  */
 #include <asm/mach/arch.h>
 #include <asm/mach/map.h>
+#include <asm/mach/irq.h>
 
 #include <linux/dma-mapping.h>
 #include <linux/platform_device.h>
@@ -21,6 +22,7 @@
 #include <video/atmel_lcdc.h>
 
 #include <mach/board.h>
+#include <mach/cpu.h>
 #include <mach/gpio.h>
 #include <mach/at91cap9.h>
 #include <mach/at91cap9_matrix.h>
@@ -69,6 +71,9 @@ void __init at91_add_device_usbh(struct at91_usbh_data *data)
 	if (!data)
 		return;
 
+	if (cpu_is_at91cap9_revB())
+		set_irq_type(AT91CAP9_ID_UHP, IRQ_TYPE_LEVEL_HIGH);
+
 	/* Enable VBus control for UHP ports */
 	for (i = 0; i < data->ports; i++) {
 		if (data->vbus_pin[i])
@@ -151,8 +156,13 @@ static struct platform_device at91_usba_udc_device = {
 
 void __init at91_add_device_usba(struct usba_platform_data *data)
 {
-	at91_sys_write(AT91_MATRIX_UDPHS, AT91_MATRIX_SELECT_UDPHS |
-					  AT91_MATRIX_UDPHS_BYPASS_LOCK);
+	if (cpu_is_at91cap9_revB()) {
+		set_irq_type(AT91CAP9_ID_UDPHS, IRQ_TYPE_LEVEL_HIGH);
+		at91_sys_write(AT91_MATRIX_UDPHS, AT91_MATRIX_SELECT_UDPHS |
+						  AT91_MATRIX_UDPHS_BYPASS_LOCK);
+	}
+	else
+		at91_sys_write(AT91_MATRIX_UDPHS, AT91_MATRIX_SELECT_UDPHS);
 
 	/*
 	 * Invalid pins are 0 on AT91, but the usba driver is shared
@@ -406,28 +416,13 @@ static struct platform_device at91cap9_nand_device = {
 
 void __init at91_add_device_nand(struct atmel_nand_data *data)
 {
-	unsigned long csa, mode;
+	unsigned long csa;
 
 	if (!data)
 		return;
 
 	csa = at91_sys_read(AT91_MATRIX_EBICSA);
-	at91_sys_write(AT91_MATRIX_EBICSA, csa | AT91_MATRIX_EBI_CS3A_SMC_SMARTMEDIA | AT91_MATRIX_EBI_VDDIOMSEL_3_3V);
-
-	/* set the bus interface characteristics */
-	at91_sys_write(AT91_SMC_SETUP(3), AT91_SMC_NWESETUP_(2) | AT91_SMC_NCS_WRSETUP_(1)
-			| AT91_SMC_NRDSETUP_(2) | AT91_SMC_NCS_RDSETUP_(1));
-
-	at91_sys_write(AT91_SMC_PULSE(3), AT91_SMC_NWEPULSE_(4) | AT91_SMC_NCS_WRPULSE_(6)
-			| AT91_SMC_NRDPULSE_(4) | AT91_SMC_NCS_RDPULSE_(6));
-
-	at91_sys_write(AT91_SMC_CYCLE(3), AT91_SMC_NWECYCLE_(8) | AT91_SMC_NRDCYCLE_(8));
-
-	if (data->bus_width_16)
-		mode = AT91_SMC_DBW_16;
-	else
-		mode = AT91_SMC_DBW_8;
-	at91_sys_write(AT91_SMC_MODE(3), mode | AT91_SMC_READMODE | AT91_SMC_WRITEMODE | AT91_SMC_EXNWMODE_DISABLE | AT91_SMC_TDF_(1));
+	at91_sys_write(AT91_MATRIX_EBICSA, csa | AT91_MATRIX_EBI_CS3A_SMC_SMARTMEDIA);
 
 	/* enable pin */
 	if (data->enable_pin)
@@ -865,6 +860,9 @@ void __init at91_add_device_lcdc(struct atmel_lcdfb_info *data)
 	if (!data)
 		return;
 
+	if (cpu_is_at91cap9_revB())
+		set_irq_type(AT91CAP9_ID_LCDC, IRQ_TYPE_LEVEL_HIGH);
+
 	at91_set_A_periph(AT91_PIN_PC1, 0);	/* LCDHSYNC */
 	at91_set_A_periph(AT91_PIN_PC2, 0);	/* LCDDOTCK */
 	at91_set_A_periph(AT91_PIN_PC3, 0);	/* LCDDEN */
diff --git a/arch/arm/mach-at91/at91sam9260_devices.c b/arch/arm/mach-at91/at91sam9260_devices.c
index 7774d17dde74..fdde1ea21b07 100644
--- a/arch/arm/mach-at91/at91sam9260_devices.c
+++ b/arch/arm/mach-at91/at91sam9260_devices.c
@@ -313,7 +313,7 @@ static struct platform_device at91sam9260_nand_device = {
 
 void __init at91_add_device_nand(struct atmel_nand_data *data)
 {
-	unsigned long csa, mode;
+	unsigned long csa;
 
 	if (!data)
 		return;
@@ -321,42 +321,6 @@ void __init at91_add_device_nand(struct atmel_nand_data *data)
 	csa = at91_sys_read(AT91_MATRIX_EBICSA);
 	at91_sys_write(AT91_MATRIX_EBICSA, csa | AT91_MATRIX_CS3A_SMC_SMARTMEDIA);
 
-	if (cpu_is_at91sam9260()) {
-		/* Timing for sam9260 */
-		/* set the bus interface characteristics */
-		at91_sys_write(AT91_SMC_SETUP(3), AT91_SMC_NWESETUP_(1) | AT91_SMC_NCS_WRSETUP_(0)
-				| AT91_SMC_NRDSETUP_(1) | AT91_SMC_NCS_RDSETUP_(0));
-
-		at91_sys_write(AT91_SMC_PULSE(3), AT91_SMC_NWEPULSE_(3) | AT91_SMC_NCS_WRPULSE_(3)
-				| AT91_SMC_NRDPULSE_(3) | AT91_SMC_NCS_RDPULSE_(3));
-
-		at91_sys_write(AT91_SMC_CYCLE(3), AT91_SMC_NWECYCLE_(5) | AT91_SMC_NRDCYCLE_(5));
-
-		if (data->bus_width_16)
-			mode = AT91_SMC_DBW_16;
-		else
-			mode = AT91_SMC_DBW_8;
-		at91_sys_write(AT91_SMC_MODE(3), mode | AT91_SMC_READMODE | AT91_SMC_WRITEMODE | AT91_SMC_EXNWMODE_DISABLE | AT91_SMC_TDF_(2));
-	}
-
-	if (cpu_is_at91sam9g20()) {
-		/* Timing for sam9g20 */
-		/* set the bus interface characteristics */
-		at91_sys_write(AT91_SMC_SETUP(3), AT91_SMC_NWESETUP_(2) | AT91_SMC_NCS_WRSETUP_(0)
-				| AT91_SMC_NRDSETUP_(2) | AT91_SMC_NCS_RDSETUP_(0));
-
-		at91_sys_write(AT91_SMC_PULSE(3), AT91_SMC_NWEPULSE_(4) | AT91_SMC_NCS_WRPULSE_(4)
-				| AT91_SMC_NRDPULSE_(4) | AT91_SMC_NCS_RDPULSE_(4));
-
-		at91_sys_write(AT91_SMC_CYCLE(3), AT91_SMC_NWECYCLE_(7) | AT91_SMC_NRDCYCLE_(7));
-
-		if (data->bus_width_16)
-			mode = AT91_SMC_DBW_16;
-		else
-			mode = AT91_SMC_DBW_8;
-		at91_sys_write(AT91_SMC_MODE(3), mode | AT91_SMC_READMODE | AT91_SMC_WRITEMODE | AT91_SMC_EXNWMODE_DISABLE | AT91_SMC_TDF_(3));
-	}
-
 	/* enable pin */
 	if (data->enable_pin)
 		at91_set_gpio_output(data->enable_pin, 1);
diff --git a/arch/arm/mach-at91/at91sam9261_devices.c b/arch/arm/mach-at91/at91sam9261_devices.c
index 6b89172310c7..17289756f80f 100644
--- a/arch/arm/mach-at91/at91sam9261_devices.c
+++ b/arch/arm/mach-at91/at91sam9261_devices.c
@@ -223,7 +223,7 @@ static struct platform_device atmel_nand_device = {
 
 void __init at91_add_device_nand(struct atmel_nand_data *data)
 {
-	unsigned long csa, mode;
+	unsigned long csa;
 
 	if (!data)
 		return;
@@ -231,21 +231,6 @@ void __init at91_add_device_nand(struct atmel_nand_data *data)
 	csa = at91_sys_read(AT91_MATRIX_EBICSA);
 	at91_sys_write(AT91_MATRIX_EBICSA, csa | AT91_MATRIX_CS3A_SMC_SMARTMEDIA);
 
-	/* set the bus interface characteristics */
-	at91_sys_write(AT91_SMC_SETUP(3), AT91_SMC_NWESETUP_(1) | AT91_SMC_NCS_WRSETUP_(0)
-			| AT91_SMC_NRDSETUP_(1) | AT91_SMC_NCS_RDSETUP_(0));
-
-	at91_sys_write(AT91_SMC_PULSE(3), AT91_SMC_NWEPULSE_(3) | AT91_SMC_NCS_WRPULSE_(3)
-			| AT91_SMC_NRDPULSE_(3) | AT91_SMC_NCS_RDPULSE_(3));
-
-	at91_sys_write(AT91_SMC_CYCLE(3), AT91_SMC_NWECYCLE_(5) | AT91_SMC_NRDCYCLE_(5));
-
-	if (data->bus_width_16)
-		mode = AT91_SMC_DBW_16;
-	else
-		mode = AT91_SMC_DBW_8;
-	at91_sys_write(AT91_SMC_MODE(3), mode | AT91_SMC_READMODE | AT91_SMC_WRITEMODE | AT91_SMC_EXNWMODE_DISABLE | AT91_SMC_TDF_(2));
-
 	/* enable pin */
 	if (data->enable_pin)
 		at91_set_gpio_output(data->enable_pin, 1);
diff --git a/arch/arm/mach-at91/at91sam9263_devices.c b/arch/arm/mach-at91/at91sam9263_devices.c
index 8b884083f76d..b753cb879d8e 100644
--- a/arch/arm/mach-at91/at91sam9263_devices.c
+++ b/arch/arm/mach-at91/at91sam9263_devices.c
@@ -382,7 +382,7 @@ static struct platform_device at91sam9263_nand_device = {
 
 void __init at91_add_device_nand(struct atmel_nand_data *data)
 {
-	unsigned long csa, mode;
+	unsigned long csa;
 
 	if (!data)
 		return;
@@ -390,21 +390,6 @@ void __init at91_add_device_nand(struct atmel_nand_data *data)
 	csa = at91_sys_read(AT91_MATRIX_EBI0CSA);
 	at91_sys_write(AT91_MATRIX_EBI0CSA, csa | AT91_MATRIX_EBI0_CS3A_SMC_SMARTMEDIA);
 
-	/* set the bus interface characteristics */
-	at91_sys_write(AT91_SMC_SETUP(3), AT91_SMC_NWESETUP_(1) | AT91_SMC_NCS_WRSETUP_(0)
-			| AT91_SMC_NRDSETUP_(1) | AT91_SMC_NCS_RDSETUP_(0));
-
-	at91_sys_write(AT91_SMC_PULSE(3), AT91_SMC_NWEPULSE_(3) | AT91_SMC_NCS_WRPULSE_(3)
-			| AT91_SMC_NRDPULSE_(3) | AT91_SMC_NCS_RDPULSE_(3));
-
-	at91_sys_write(AT91_SMC_CYCLE(3), AT91_SMC_NWECYCLE_(5) | AT91_SMC_NRDCYCLE_(5));
-
-	if (data->bus_width_16)
-		mode = AT91_SMC_DBW_16;
-	else
-		mode = AT91_SMC_DBW_8;
-	at91_sys_write(AT91_SMC_MODE(3), mode | AT91_SMC_READMODE | AT91_SMC_WRITEMODE | AT91_SMC_EXNWMODE_DISABLE | AT91_SMC_TDF_(2));
-
 	/* enable pin */
 	if (data->enable_pin)
 		at91_set_gpio_output(data->enable_pin, 1);
diff --git a/arch/arm/mach-at91/at91sam9rl_devices.c b/arch/arm/mach-at91/at91sam9rl_devices.c
index 87deb1e1b529..145324f4ec56 100644
--- a/arch/arm/mach-at91/at91sam9rl_devices.c
+++ b/arch/arm/mach-at91/at91sam9rl_devices.c
@@ -232,17 +232,6 @@ void __init at91_add_device_nand(struct atmel_nand_data *data)
 	csa = at91_sys_read(AT91_MATRIX_EBICSA);
 	at91_sys_write(AT91_MATRIX_EBICSA, csa | AT91_MATRIX_CS3A_SMC_SMARTMEDIA);
 
-	/* set the bus interface characteristics */
-	at91_sys_write(AT91_SMC_SETUP(3), AT91_SMC_NWESETUP_(1) | AT91_SMC_NCS_WRSETUP_(0)
-			| AT91_SMC_NRDSETUP_(1) | AT91_SMC_NCS_RDSETUP_(0));
-
-	at91_sys_write(AT91_SMC_PULSE(3), AT91_SMC_NWEPULSE_(3) | AT91_SMC_NCS_WRPULSE_(3)
-			| AT91_SMC_NRDPULSE_(3) | AT91_SMC_NCS_RDPULSE_(3));
-
-	at91_sys_write(AT91_SMC_CYCLE(3), AT91_SMC_NWECYCLE_(5) | AT91_SMC_NRDCYCLE_(5));
-
-	at91_sys_write(AT91_SMC_MODE(3), AT91_SMC_DBW_8 | AT91_SMC_READMODE | AT91_SMC_WRITEMODE | AT91_SMC_EXNWMODE_DISABLE | AT91_SMC_TDF_(2));
-
 	/* enable pin */
 	if (data->enable_pin)
 		at91_set_gpio_output(data->enable_pin, 1);
diff --git a/arch/arm/mach-at91/board-cam60.c b/arch/arm/mach-at91/board-cam60.c
index cdddca54b938..d3ba29c5d8c8 100644
--- a/arch/arm/mach-at91/board-cam60.c
+++ b/arch/arm/mach-at91/board-cam60.c
@@ -39,7 +39,9 @@
 
 #include <mach/board.h>
 #include <mach/gpio.h>
+#include <mach/at91sam9_smc.h>
 
+#include "sam9_smc.h"
 #include "generic.h"
 
 
@@ -151,6 +153,32 @@ static struct atmel_nand_data __initdata cam60_nand_data = {
 	.partition_info	= nand_partitions,
 };
 
+static struct sam9_smc_config __initdata cam60_nand_smc_config = {
+	.ncs_read_setup		= 0,
+	.nrd_setup		= 1,
+	.ncs_write_setup	= 0,
+	.nwe_setup		= 1,
+
+	.ncs_read_pulse		= 3,
+	.nrd_pulse		= 3,
+	.ncs_write_pulse	= 3,
+	.nwe_pulse		= 3,
+
+	.read_cycle		= 5,
+	.write_cycle		= 5,
+
+	.mode			= AT91_SMC_READMODE | AT91_SMC_WRITEMODE | AT91_SMC_EXNWMODE_DISABLE | AT91_SMC_DBW_8,
+	.tdf_cycles		= 2,
+};
+
+static void __init cam60_add_device_nand(void)
+{
+	/* configure chip-select 3 (NAND) */
+	sam9_smc_configure(3, &cam60_nand_smc_config);
+
+	at91_add_device_nand(&cam60_nand_data);
+}
+
 
 static void __init cam60_board_init(void)
 {
@@ -165,7 +193,7 @@ static void __init cam60_board_init(void)
 	at91_set_gpio_output(AT91_PIN_PB18, 1);
 	at91_add_device_usbh(&cam60_usbh_data);
 	/* NAND */
-	at91_add_device_nand(&cam60_nand_data);
+	cam60_add_device_nand();
 }
 
 MACHINE_START(CAM60, "KwikByte CAM60")
diff --git a/arch/arm/mach-at91/board-cap9adk.c b/arch/arm/mach-at91/board-cap9adk.c
index 201b89392dcc..83a1a0fef47b 100644
--- a/arch/arm/mach-at91/board-cap9adk.c
+++ b/arch/arm/mach-at91/board-cap9adk.c
@@ -36,17 +36,16 @@
 #include <mach/hardware.h>
 #include <asm/setup.h>
 #include <asm/mach-types.h>
-#include <asm/irq.h>
 
 #include <asm/mach/arch.h>
 #include <asm/mach/map.h>
-#include <asm/mach/irq.h>
 
 #include <mach/board.h>
 #include <mach/gpio.h>
 #include <mach/at91cap9_matrix.h>
 #include <mach/at91sam9_smc.h>
 
+#include "sam9_smc.h"
 #include "generic.h"
 
 
@@ -195,6 +194,43 @@ static struct atmel_nand_data __initdata cap9adk_nand_data = {
 #endif
 };
 
+static struct sam9_smc_config __initdata cap9adk_nand_smc_config = {
+	.ncs_read_setup		= 1,
+	.nrd_setup		= 2,
+	.ncs_write_setup	= 1,
+	.nwe_setup		= 2,
+
+	.ncs_read_pulse		= 6,
+	.nrd_pulse		= 4,
+	.ncs_write_pulse	= 6,
+	.nwe_pulse		= 4,
+
+	.read_cycle		= 8,
+	.write_cycle		= 8,
+
+	.mode			= AT91_SMC_READMODE | AT91_SMC_WRITEMODE | AT91_SMC_EXNWMODE_DISABLE,
+	.tdf_cycles		= 1,
+};
+
+static void __init cap9adk_add_device_nand(void)
+{
+	unsigned long csa;
+
+	csa = at91_sys_read(AT91_MATRIX_EBICSA);
+	at91_sys_write(AT91_MATRIX_EBICSA, csa | AT91_MATRIX_EBI_VDDIOMSEL_3_3V);
+
+	/* setup bus-width (8 or 16) */
+	if (cap9adk_nand_data.bus_width_16)
+		cap9adk_nand_smc_config.mode |= AT91_SMC_DBW_16;
+	else
+		cap9adk_nand_smc_config.mode |= AT91_SMC_DBW_8;
+
+	/* configure chip-select 3 (NAND) */
+	sam9_smc_configure(3, &cap9adk_nand_smc_config);
+
+	at91_add_device_nand(&cap9adk_nand_data);
+}
+
 
 /*
  * NOR flash
@@ -234,6 +270,24 @@ static struct platform_device cap9adk_nor_flash = {
 	.num_resources	= ARRAY_SIZE(nor_flash_resources),
 };
 
+static struct sam9_smc_config __initdata cap9adk_nor_smc_config = {
+	.ncs_read_setup		= 2,
+	.nrd_setup		= 4,
+	.ncs_write_setup	= 2,
+	.nwe_setup		= 4,
+
+	.ncs_read_pulse		= 10,
+	.nrd_pulse		= 8,
+	.ncs_write_pulse	= 10,
+	.nwe_pulse		= 8,
+
+	.read_cycle		= 16,
+	.write_cycle		= 16,
+
+	.mode			= AT91_SMC_READMODE | AT91_SMC_WRITEMODE | AT91_SMC_EXNWMODE_DISABLE | AT91_SMC_BAT_WRITE | AT91_SMC_DBW_16,
+	.tdf_cycles		= 1,
+};
+
 static __init void cap9adk_add_device_nor(void)
 {
 	unsigned long csa;
@@ -241,18 +295,8 @@ static __init void cap9adk_add_device_nor(void)
 	csa = at91_sys_read(AT91_MATRIX_EBICSA);
 	at91_sys_write(AT91_MATRIX_EBICSA, csa | AT91_MATRIX_EBI_VDDIOMSEL_3_3V);
 
-	/* set the bus interface characteristics */
-	at91_sys_write(AT91_SMC_SETUP(0), AT91_SMC_NWESETUP_(4) | AT91_SMC_NCS_WRSETUP_(2)
-			| AT91_SMC_NRDSETUP_(4) | AT91_SMC_NCS_RDSETUP_(2));
-
-	at91_sys_write(AT91_SMC_PULSE(0), AT91_SMC_NWEPULSE_(8) | AT91_SMC_NCS_WRPULSE_(10)
-			| AT91_SMC_NRDPULSE_(8) | AT91_SMC_NCS_RDPULSE_(10));
-
-	at91_sys_write(AT91_SMC_CYCLE(0), AT91_SMC_NWECYCLE_(16) | AT91_SMC_NRDCYCLE_(16));
-
-	at91_sys_write(AT91_SMC_MODE(0), AT91_SMC_READMODE | AT91_SMC_WRITEMODE
-			| AT91_SMC_EXNWMODE_DISABLE | AT91_SMC_BAT_WRITE
-			| AT91_SMC_DBW_16 | AT91_SMC_TDF_(1));
+	/* configure chip-select 0 (NOR) */
+	sam9_smc_configure(0, &cap9adk_nor_smc_config);
 
 	platform_device_register(&cap9adk_nor_flash);
 }
@@ -330,10 +374,8 @@ static void __init cap9adk_board_init(void)
 	/* Serial */
 	at91_add_device_serial();
 	/* USB Host */
-	set_irq_type(AT91CAP9_ID_UHP, IRQ_TYPE_LEVEL_HIGH);
 	at91_add_device_usbh(&cap9adk_usbh_data);
 	/* USB HS */
-	set_irq_type(AT91CAP9_ID_UDPHS, IRQ_TYPE_LEVEL_HIGH);
 	at91_add_device_usba(&cap9adk_usba_udc_data);
 	/* SPI */
 	at91_add_device_spi(cap9adk_spi_devices, ARRAY_SIZE(cap9adk_spi_devices));
@@ -344,13 +386,12 @@ static void __init cap9adk_board_init(void)
 	/* Ethernet */
 	at91_add_device_eth(&cap9adk_macb_data);
 	/* NAND */
-	at91_add_device_nand(&cap9adk_nand_data);
+	cap9adk_add_device_nand();
 	/* NOR Flash */
 	cap9adk_add_device_nor();
 	/* I2C */
 	at91_add_device_i2c(NULL, 0);
 	/* LCD Controller */
-	set_irq_type(AT91CAP9_ID_LCDC, IRQ_TYPE_LEVEL_HIGH);
 	at91_add_device_lcdc(&cap9adk_lcdc_data);
 	/* AC97 */
 	at91_add_device_ac97(&cap9adk_ac97_data);
diff --git a/arch/arm/mach-at91/board-neocore926.c b/arch/arm/mach-at91/board-neocore926.c
new file mode 100644
index 000000000000..9ba7ba2cc3b1
--- /dev/null
+++ b/arch/arm/mach-at91/board-neocore926.c
@@ -0,0 +1,397 @@
+/*
+ * linux/arch/arm/mach-at91/board-neocore926.c
+ *
+ *  Copyright (C) 2005 SAN People
+ *  Copyright (C) 2007 Atmel Corporation
+ *  Copyright (C) 2008 ADENEO.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ */
+
+#include <linux/types.h>
+#include <linux/init.h>
+#include <linux/mm.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/spi/spi.h>
+#include <linux/spi/ads7846.h>
+#include <linux/fb.h>
+#include <linux/gpio_keys.h>
+#include <linux/input.h>
+
+#include <video/atmel_lcdc.h>
+
+#include <asm/setup.h>
+#include <asm/mach-types.h>
+#include <asm/irq.h>
+#include <asm/sizes.h>
+
+#include <asm/mach/arch.h>
+#include <asm/mach/map.h>
+#include <asm/mach/irq.h>
+
+#include <mach/hardware.h>
+#include <mach/board.h>
+#include <mach/gpio.h>
+#include <mach/at91sam9_smc.h>
+
+#include "sam9_smc.h"
+#include "generic.h"
+
+
+static void __init neocore926_map_io(void)
+{
+	/* Initialize processor: 20 MHz crystal */
+	at91sam9263_initialize(20000000);
+
+	/* DGBU on ttyS0. (Rx & Tx only) */
+	at91_register_uart(0, 0, 0);
+
+	/* USART0 on ttyS1. (Rx, Tx, RTS, CTS) */
+	at91_register_uart(AT91SAM9263_ID_US0, 1, ATMEL_UART_CTS | ATMEL_UART_RTS);
+
+	/* set serial console to ttyS0 (ie, DBGU) */
+	at91_set_serial_console(0);
+}
+
+static void __init neocore926_init_irq(void)
+{
+	at91sam9263_init_interrupts(NULL);
+}
+
+
+/*
+ * USB Host port
+ */
+static struct at91_usbh_data __initdata neocore926_usbh_data = {
+	.ports		= 2,
+	.vbus_pin	= { AT91_PIN_PA24, AT91_PIN_PA21 },
+};
+
+/*
+ * USB Device port
+ */
+static struct at91_udc_data __initdata neocore926_udc_data = {
+	.vbus_pin	= AT91_PIN_PA25,
+	.pullup_pin	= 0,		/* pull-up driven by UDC */
+};
+
+
+/*
+ * ADS7846 Touchscreen
+ */
+#if defined(CONFIG_TOUCHSCREEN_ADS7846) || defined(CONFIG_TOUCHSCREEN_ADS7846_MODULE)
+static int ads7843_pendown_state(void)
+{
+	return !at91_get_gpio_value(AT91_PIN_PA15);	/* Touchscreen PENIRQ */
+}
+
+static struct ads7846_platform_data ads_info = {
+	.model			= 7843,
+	.x_min			= 150,
+	.x_max			= 3830,
+	.y_min			= 190,
+	.y_max			= 3830,
+	.vref_delay_usecs	= 100,
+	.x_plate_ohms		= 450,
+	.y_plate_ohms		= 250,
+	.pressure_max		= 15000,
+	.debounce_max		= 1,
+	.debounce_rep		= 0,
+	.debounce_tol		= (~0),
+	.get_pendown_state	= ads7843_pendown_state,
+};
+
+static void __init neocore926_add_device_ts(void)
+{
+	at91_set_B_periph(AT91_PIN_PA15, 1);	/* External IRQ1, with pullup */
+	at91_set_gpio_input(AT91_PIN_PC13, 1);	/* Touchscreen BUSY signal */
+}
+#else
+static void __init neocore926_add_device_ts(void) {}
+#endif
+
+/*
+ * SPI devices.
+ */
+static struct spi_board_info neocore926_spi_devices[] = {
+#if defined(CONFIG_MTD_AT91_DATAFLASH_CARD)
+	{	/* DataFlash card */
+		.modalias	= "mtd_dataflash",
+		.chip_select	= 0,
+		.max_speed_hz	= 15 * 1000 * 1000,
+		.bus_num	= 0,
+	},
+#endif
+#if defined(CONFIG_TOUCHSCREEN_ADS7846) || defined(CONFIG_TOUCHSCREEN_ADS7846_MODULE)
+	{
+		.modalias	= "ads7846",
+		.chip_select	= 1,
+		.max_speed_hz	= 125000 * 16,
+		.bus_num	= 0,
+		.platform_data	= &ads_info,
+		.irq		= AT91SAM9263_ID_IRQ1,
+	},
+#endif
+};
+
+
+/*
+ * MCI (SD/MMC)
+ */
+static struct at91_mmc_data __initdata neocore926_mmc_data = {
+	.wire4		= 1,
+	.det_pin	= AT91_PIN_PE18,
+	.wp_pin		= AT91_PIN_PE19,
+};
+
+
+/*
+ * MACB Ethernet device
+ */
+static struct at91_eth_data __initdata neocore926_macb_data = {
+	.phy_irq_pin	= AT91_PIN_PE31,
+	.is_rmii	= 1,
+};
+
+
+/*
+ * NAND flash
+ */
+static struct mtd_partition __initdata neocore926_nand_partition[] = {
+	{
+		.name	= "Linux Kernel",	/* "Partition 1", */
+		.offset	= 0,
+		.size	= SZ_8M,
+	},
+	{
+		.name	= "Filesystem",		/* "Partition 2", */
+		.offset	= MTDPART_OFS_NXTBLK,
+		.size	= SZ_32M,
+	},
+	{
+		.name	= "Free",		/* "Partition 3", */
+		.offset	= MTDPART_OFS_NXTBLK,
+		.size	= MTDPART_SIZ_FULL,
+	},
+};
+
+static struct mtd_partition * __init nand_partitions(int size, int *num_partitions)
+{
+	*num_partitions = ARRAY_SIZE(neocore926_nand_partition);
+	return neocore926_nand_partition;
+}
+
+static struct atmel_nand_data __initdata neocore926_nand_data = {
+	.ale			= 21,
+	.cle			= 22,
+	.rdy_pin		= AT91_PIN_PB19,
+	.rdy_pin_active_low	= 1,
+	.enable_pin		= AT91_PIN_PD15,
+	.partition_info		= nand_partitions,
+};
+
+static struct sam9_smc_config __initdata neocore926_nand_smc_config = {
+	.ncs_read_setup		= 0,
+	.nrd_setup		= 1,
+	.ncs_write_setup	= 0,
+	.nwe_setup		= 1,
+
+	.ncs_read_pulse		= 4,
+	.nrd_pulse		= 4,
+	.ncs_write_pulse	= 4,
+	.nwe_pulse		= 4,
+
+	.read_cycle		= 6,
+	.write_cycle		= 6,
+
+	.mode			= AT91_SMC_READMODE | AT91_SMC_WRITEMODE | AT91_SMC_EXNWMODE_DISABLE | AT91_SMC_DBW_8,
+	.tdf_cycles		= 2,
+};
+
+static void __init neocore926_add_device_nand(void)
+{
+	/* configure chip-select 3 (NAND) */
+	sam9_smc_configure(3, &neocore926_nand_smc_config);
+
+	at91_add_device_nand(&neocore926_nand_data);
+}
+
+
+/*
+ * LCD Controller
+ */
+#if defined(CONFIG_FB_ATMEL) || defined(CONFIG_FB_ATMEL_MODULE)
+static struct fb_videomode at91_tft_vga_modes[] = {
+	{
+		.name		= "TX09D50VM1CCA @ 60",
+		.refresh	= 60,
+		.xres		= 240,		.yres		= 320,
+		.pixclock	= KHZ2PICOS(5000),
+
+		.left_margin	= 1,		.right_margin	= 33,
+		.upper_margin	= 1,		.lower_margin	= 0,
+		.hsync_len	= 5,		.vsync_len	= 1,
+
+		.sync		= FB_SYNC_HOR_HIGH_ACT | FB_SYNC_VERT_HIGH_ACT,
+		.vmode		= FB_VMODE_NONINTERLACED,
+	},
+};
+
+static struct fb_monspecs at91fb_default_monspecs = {
+	.manufacturer	= "HIT",
+	.monitor	= "TX09D70VM1CCA",
+
+	.modedb		= at91_tft_vga_modes,
+	.modedb_len	= ARRAY_SIZE(at91_tft_vga_modes),
+	.hfmin		= 15000,
+	.hfmax		= 64000,
+	.vfmin		= 50,
+	.vfmax		= 150,
+};
+
+#define AT91SAM9263_DEFAULT_LCDCON2 (ATMEL_LCDC_MEMOR_LITTLE \
+					| ATMEL_LCDC_DISTYPE_TFT \
+					| ATMEL_LCDC_CLKMOD_ALWAYSACTIVE)
+
+static void at91_lcdc_power_control(int on)
+{
+	at91_set_gpio_value(AT91_PIN_PA30, on);
+}
+
+/* Driver datas */
+static struct atmel_lcdfb_info __initdata neocore926_lcdc_data = {
+	.lcdcon_is_backlight		= true,
+	.default_bpp			= 16,
+	.default_dmacon			= ATMEL_LCDC_DMAEN,
+	.default_lcdcon2		= AT91SAM9263_DEFAULT_LCDCON2,
+	.default_monspecs		= &at91fb_default_monspecs,
+	.atmel_lcdfb_power_control	= at91_lcdc_power_control,
+	.guard_time			= 1,
+	.lcd_wiring_mode		= ATMEL_LCDC_WIRING_RGB555,
+};
+
+#else
+static struct atmel_lcdfb_info __initdata neocore926_lcdc_data;
+#endif
+
+
+/*
+ * GPIO Buttons
+ */
+#if defined(CONFIG_KEYBOARD_GPIO) || defined(CONFIG_KEYBOARD_GPIO_MODULE)
+static struct gpio_keys_button neocore926_buttons[] = {
+	{	/* BP1, "leftclic" */
+		.code		= BTN_LEFT,
+		.gpio		= AT91_PIN_PC5,
+		.active_low	= 1,
+		.desc		= "left_click",
+		.wakeup		= 1,
+	},
+	{	/* BP2, "rightclic" */
+		.code		= BTN_RIGHT,
+		.gpio		= AT91_PIN_PC4,
+		.active_low	= 1,
+		.desc		= "right_click",
+		.wakeup		= 1,
+	},
+};
+
+static struct gpio_keys_platform_data neocore926_button_data = {
+	.buttons	= neocore926_buttons,
+	.nbuttons	= ARRAY_SIZE(neocore926_buttons),
+};
+
+static struct platform_device neocore926_button_device = {
+	.name		= "gpio-keys",
+	.id		= -1,
+	.num_resources	= 0,
+	.dev		= {
+		.platform_data	= &neocore926_button_data,
+	}
+};
+
+static void __init neocore926_add_device_buttons(void)
+{
+	at91_set_GPIO_periph(AT91_PIN_PC5, 0);	/* left button */
+	at91_set_deglitch(AT91_PIN_PC5, 1);
+	at91_set_GPIO_periph(AT91_PIN_PC4, 0);	/* right button */
+	at91_set_deglitch(AT91_PIN_PC4, 1);
+
+	platform_device_register(&neocore926_button_device);
+}
+#else
+static void __init neocore926_add_device_buttons(void) {}
+#endif
+
+
+/*
+ * AC97
+ */
+static struct atmel_ac97_data neocore926_ac97_data = {
+	.reset_pin	= AT91_PIN_PA13,
+};
+
+
+static void __init neocore926_board_init(void)
+{
+	/* Serial */
+	at91_add_device_serial();
+
+	/* USB Host */
+	at91_add_device_usbh(&neocore926_usbh_data);
+
+	/* USB Device */
+	at91_add_device_udc(&neocore926_udc_data);
+
+	/* SPI */
+	at91_set_gpio_output(AT91_PIN_PE20, 1);		/* select spi0 clock */
+	at91_add_device_spi(neocore926_spi_devices, ARRAY_SIZE(neocore926_spi_devices));
+
+	/* Touchscreen */
+	neocore926_add_device_ts();
+
+	/* MMC */
+	at91_add_device_mmc(1, &neocore926_mmc_data);
+
+	/* Ethernet */
+	at91_add_device_eth(&neocore926_macb_data);
+
+	/* NAND */
+	neocore926_add_device_nand();
+
+	/* I2C */
+	at91_add_device_i2c(NULL, 0);
+
+	/* LCD Controller */
+	at91_add_device_lcdc(&neocore926_lcdc_data);
+
+	/* Push Buttons */
+	neocore926_add_device_buttons();
+
+	/* AC97 */
+	at91_add_device_ac97(&neocore926_ac97_data);
+}
+
+MACHINE_START(NEOCORE926, "ADENEO NEOCORE 926")
+	/* Maintainer: ADENEO */
+	.phys_io	= AT91_BASE_SYS,
+	.io_pg_offst	= (AT91_VA_BASE_SYS >> 18) & 0xfffc,
+	.boot_params	= AT91_SDRAM_BASE + 0x100,
+	.timer		= &at91sam926x_timer,
+	.map_io		= neocore926_map_io,
+	.init_irq	= neocore926_init_irq,
+	.init_machine	= neocore926_board_init,
+MACHINE_END
diff --git a/arch/arm/mach-at91/board-qil-a9260.c b/arch/arm/mach-at91/board-qil-a9260.c
index cfb4571a2e27..4cff9a7e61d2 100644
--- a/arch/arm/mach-at91/board-qil-a9260.c
+++ b/arch/arm/mach-at91/board-qil-a9260.c
@@ -41,8 +41,10 @@
 #include <mach/hardware.h>
 #include <mach/board.h>
 #include <mach/gpio.h>
+#include <mach/at91sam9_smc.h>
 #include <mach/at91_shdwc.h>
 
+#include "sam9_smc.h"
 #include "generic.h"
 
 
@@ -147,13 +149,34 @@ static struct atmel_nand_data __initdata ek_nand_data = {
 	.rdy_pin	= AT91_PIN_PC13,
 	.enable_pin	= AT91_PIN_PC14,
 	.partition_info	= nand_partitions,
-#if defined(CONFIG_MTD_NAND_ATMEL_BUSWIDTH_16)
-	.bus_width_16	= 1,
-#else
-	.bus_width_16	= 0,
-#endif
 };
 
+static struct sam9_smc_config __initdata ek_nand_smc_config = {
+	.ncs_read_setup		= 0,
+	.nrd_setup		= 1,
+	.ncs_write_setup	= 0,
+	.nwe_setup		= 1,
+
+	.ncs_read_pulse		= 3,
+	.nrd_pulse		= 3,
+	.ncs_write_pulse	= 3,
+	.nwe_pulse		= 3,
+
+	.read_cycle		= 5,
+	.write_cycle		= 5,
+
+	.mode			= AT91_SMC_READMODE | AT91_SMC_WRITEMODE | AT91_SMC_EXNWMODE_DISABLE | AT91_SMC_DBW_8,
+	.tdf_cycles		= 2,
+};
+
+static void __init ek_add_device_nand(void)
+{
+	/* configure chip-select 3 (NAND) */
+	sam9_smc_configure(3, &ek_nand_smc_config);
+
+	at91_add_device_nand(&ek_nand_data);
+}
+
 /*
  * MCI (SD/MMC)
  */
@@ -227,7 +250,7 @@ static void __init ek_board_init(void)
 	/* SPI */
 	at91_add_device_spi(ek_spi_devices, ARRAY_SIZE(ek_spi_devices));
 	/* NAND */
-	at91_add_device_nand(&ek_nand_data);
+	ek_add_device_nand();
 	/* I2C */
 	at91_add_device_i2c(NULL, 0);
 	/* Ethernet */
diff --git a/arch/arm/mach-at91/board-sam9-l9260.c b/arch/arm/mach-at91/board-sam9-l9260.c
index 99bb4cc23a09..b48346977534 100644
--- a/arch/arm/mach-at91/board-sam9-l9260.c
+++ b/arch/arm/mach-at91/board-sam9-l9260.c
@@ -38,7 +38,9 @@
 
 #include <mach/board.h>
 #include <mach/gpio.h>
+#include <mach/at91sam9_smc.h>
 
+#include "sam9_smc.h"
 #include "generic.h"
 
 
@@ -148,13 +150,34 @@ static struct atmel_nand_data __initdata ek_nand_data = {
 	.rdy_pin	= AT91_PIN_PC13,
 	.enable_pin	= AT91_PIN_PC14,
 	.partition_info	= nand_partitions,
-#if defined(CONFIG_MTD_NAND_ATMEL_BUSWIDTH_16)
-	.bus_width_16	= 1,
-#else
-	.bus_width_16	= 0,
-#endif
 };
 
+static struct sam9_smc_config __initdata ek_nand_smc_config = {
+	.ncs_read_setup		= 0,
+	.nrd_setup		= 1,
+	.ncs_write_setup	= 0,
+	.nwe_setup		= 1,
+
+	.ncs_read_pulse		= 3,
+	.nrd_pulse		= 3,
+	.ncs_write_pulse	= 3,
+	.nwe_pulse		= 3,
+
+	.read_cycle		= 5,
+	.write_cycle		= 5,
+
+	.mode			= AT91_SMC_READMODE | AT91_SMC_WRITEMODE | AT91_SMC_EXNWMODE_DISABLE | AT91_SMC_DBW_8,
+	.tdf_cycles		= 2,
+};
+
+static void __init ek_add_device_nand(void)
+{
+	/* configure chip-select 3 (NAND) */
+	sam9_smc_configure(3, &ek_nand_smc_config);
+
+	at91_add_device_nand(&ek_nand_data);
+}
+
 
 /*
  * MCI (SD/MMC)
@@ -178,7 +201,7 @@ static void __init ek_board_init(void)
 	/* SPI */
 	at91_add_device_spi(ek_spi_devices, ARRAY_SIZE(ek_spi_devices));
 	/* NAND */
-	at91_add_device_nand(&ek_nand_data);
+	ek_add_device_nand();
 	/* Ethernet */
 	at91_add_device_eth(&ek_macb_data);
 	/* MMC */
diff --git a/arch/arm/mach-at91/board-sam9260ek.c b/arch/arm/mach-at91/board-sam9260ek.c
index b49eb6e4918a..93a0f8b100eb 100644
--- a/arch/arm/mach-at91/board-sam9260ek.c
+++ b/arch/arm/mach-at91/board-sam9260ek.c
@@ -42,7 +42,10 @@
 #include <mach/hardware.h>
 #include <mach/board.h>
 #include <mach/gpio.h>
+#include <mach/at91sam9_smc.h>
+#include <mach/at91_shdwc.h>
 
+#include "sam9_smc.h"
 #include "generic.h"
 
 
@@ -195,6 +198,38 @@ static struct atmel_nand_data __initdata ek_nand_data = {
 #endif
 };
 
+static struct sam9_smc_config __initdata ek_nand_smc_config = {
+	.ncs_read_setup		= 0,
+	.nrd_setup		= 1,
+	.ncs_write_setup	= 0,
+	.nwe_setup		= 1,
+
+	.ncs_read_pulse		= 3,
+	.nrd_pulse		= 3,
+	.ncs_write_pulse	= 3,
+	.nwe_pulse		= 3,
+
+	.read_cycle		= 5,
+	.write_cycle		= 5,
+
+	.mode			= AT91_SMC_READMODE | AT91_SMC_WRITEMODE | AT91_SMC_EXNWMODE_DISABLE,
+	.tdf_cycles		= 2,
+};
+
+static void __init ek_add_device_nand(void)
+{
+	/* setup bus-width (8 or 16) */
+	if (ek_nand_data.bus_width_16)
+		ek_nand_smc_config.mode |= AT91_SMC_DBW_16;
+	else
+		ek_nand_smc_config.mode |= AT91_SMC_DBW_8;
+
+	/* configure chip-select 3 (NAND) */
+	sam9_smc_configure(3, &ek_nand_smc_config);
+
+	at91_add_device_nand(&ek_nand_data);
+}
+
 
 /*
  * MCI (SD/MMC)
@@ -303,7 +338,7 @@ static void __init ek_board_init(void)
 	/* SPI */
 	at91_add_device_spi(ek_spi_devices, ARRAY_SIZE(ek_spi_devices));
 	/* NAND */
-	at91_add_device_nand(&ek_nand_data);
+	ek_add_device_nand();
 	/* Ethernet */
 	at91_add_device_eth(&ek_macb_data);
 	/* MMC */
diff --git a/arch/arm/mach-at91/board-sam9261ek.c b/arch/arm/mach-at91/board-sam9261ek.c
index 4977409d4fc6..d5266da55311 100644
--- a/arch/arm/mach-at91/board-sam9261ek.c
+++ b/arch/arm/mach-at91/board-sam9261ek.c
@@ -47,7 +47,9 @@
 #include <mach/board.h>
 #include <mach/gpio.h>
 #include <mach/at91sam9_smc.h>
+#include <mach/at91_shdwc.h>
 
+#include "sam9_smc.h"
 #include "generic.h"
 
 
@@ -76,7 +78,7 @@ static void __init ek_init_irq(void)
  * DM9000 ethernet device
  */
 #if defined(CONFIG_DM9000)
-static struct resource at91sam9261_dm9000_resource[] = {
+static struct resource dm9000_resource[] = {
 	[0] = {
 		.start	= AT91_CHIPSELECT_2,
 		.end	= AT91_CHIPSELECT_2 + 3,
@@ -98,27 +100,42 @@ static struct dm9000_plat_data dm9000_platdata = {
 	.flags		= DM9000_PLATF_16BITONLY,
 };
 
-static struct platform_device at91sam9261_dm9000_device = {
+static struct platform_device dm9000_device = {
 	.name		= "dm9000",
 	.id		= 0,
-	.num_resources	= ARRAY_SIZE(at91sam9261_dm9000_resource),
-	.resource	= at91sam9261_dm9000_resource,
+	.num_resources	= ARRAY_SIZE(dm9000_resource),
+	.resource	= dm9000_resource,
 	.dev		= {
 		.platform_data	= &dm9000_platdata,
 	}
 };
 
+/*
+ * SMC timings for the DM9000.
+ * Note: These timings were calculated for MASTER_CLOCK = 100000000 according to the DM9000 timings.
+ */
+static struct sam9_smc_config __initdata dm9000_smc_config = {
+	.ncs_read_setup		= 0,
+	.nrd_setup		= 2,
+	.ncs_write_setup	= 0,
+	.nwe_setup		= 2,
+
+	.ncs_read_pulse		= 8,
+	.nrd_pulse		= 4,
+	.ncs_write_pulse	= 8,
+	.nwe_pulse		= 4,
+
+	.read_cycle		= 16,
+	.write_cycle		= 16,
+
+	.mode			= AT91_SMC_READMODE | AT91_SMC_WRITEMODE | AT91_SMC_EXNWMODE_DISABLE | AT91_SMC_BAT_WRITE | AT91_SMC_DBW_16,
+	.tdf_cycles		= 1,
+};
+
 static void __init ek_add_device_dm9000(void)
 {
-	/*
-	 * Configure Chip-Select 2 on SMC for the DM9000.
-	 * Note: These timings were calculated for MASTER_CLOCK = 100000000
-	 *  according to the DM9000 timings.
-	 */
-	at91_sys_write(AT91_SMC_SETUP(2), AT91_SMC_NWESETUP_(2) | AT91_SMC_NCS_WRSETUP_(0) | AT91_SMC_NRDSETUP_(2) | AT91_SMC_NCS_RDSETUP_(0));
-	at91_sys_write(AT91_SMC_PULSE(2), AT91_SMC_NWEPULSE_(4) | AT91_SMC_NCS_WRPULSE_(8) | AT91_SMC_NRDPULSE_(4) | AT91_SMC_NCS_RDPULSE_(8));
-	at91_sys_write(AT91_SMC_CYCLE(2), AT91_SMC_NWECYCLE_(16) | AT91_SMC_NRDCYCLE_(16));
-	at91_sys_write(AT91_SMC_MODE(2), AT91_SMC_READMODE | AT91_SMC_WRITEMODE | AT91_SMC_EXNWMODE_DISABLE | AT91_SMC_BAT_WRITE | AT91_SMC_DBW_16 | AT91_SMC_TDF_(1));
+	/* Configure chip-select 2 (DM9000) */
+	sam9_smc_configure(2, &dm9000_smc_config);
 
 	/* Configure Reset signal as output */
 	at91_set_gpio_output(AT91_PIN_PC10, 0);
@@ -126,7 +143,7 @@ static void __init ek_add_device_dm9000(void)
 	/* Configure Interrupt pin as input, no pull-up */
 	at91_set_gpio_input(AT91_PIN_PC11, 0);
 
-	platform_device_register(&at91sam9261_dm9000_device);
+	platform_device_register(&dm9000_device);
 }
 #else
 static void __init ek_add_device_dm9000(void) {}
@@ -197,6 +214,39 @@ static struct atmel_nand_data __initdata ek_nand_data = {
 #endif
 };
 
+static struct sam9_smc_config __initdata ek_nand_smc_config = {
+	.ncs_read_setup		= 0,
+	.nrd_setup		= 1,
+	.ncs_write_setup	= 0,
+	.nwe_setup		= 1,
+
+	.ncs_read_pulse		= 3,
+	.nrd_pulse		= 3,
+	.ncs_write_pulse	= 3,
+	.nwe_pulse		= 3,
+
+	.read_cycle		= 5,
+	.write_cycle		= 5,
+
+	.mode			= AT91_SMC_READMODE | AT91_SMC_WRITEMODE | AT91_SMC_EXNWMODE_DISABLE,
+	.tdf_cycles		= 2,
+};
+
+static void __init ek_add_device_nand(void)
+{
+	/* setup bus-width (8 or 16) */
+	if (ek_nand_data.bus_width_16)
+		ek_nand_smc_config.mode |= AT91_SMC_DBW_16;
+	else
+		ek_nand_smc_config.mode |= AT91_SMC_DBW_8;
+
+	/* configure chip-select 3 (NAND) */
+	sam9_smc_configure(3, &ek_nand_smc_config);
+
+	at91_add_device_nand(&ek_nand_data);
+}
+
+
 /*
  * ADS7846 Touchscreen
  */
@@ -525,7 +575,7 @@ static void __init ek_board_init(void)
 	/* I2C */
 	at91_add_device_i2c(NULL, 0);
 	/* NAND */
-	at91_add_device_nand(&ek_nand_data);
+	ek_add_device_nand();
 	/* DM9000 ethernet */
 	ek_add_device_dm9000();
 
diff --git a/arch/arm/mach-at91/board-sam9263ek.c b/arch/arm/mach-at91/board-sam9263ek.c
index 8354015c6a23..57d52528f224 100644
--- a/arch/arm/mach-at91/board-sam9263ek.c
+++ b/arch/arm/mach-at91/board-sam9263ek.c
@@ -46,7 +46,9 @@
 #include <mach/board.h>
 #include <mach/gpio.h>
 #include <mach/at91sam9_smc.h>
+#include <mach/at91_shdwc.h>
 
+#include "sam9_smc.h"
 #include "generic.h"
 
 
@@ -203,6 +205,38 @@ static struct atmel_nand_data __initdata ek_nand_data = {
 #endif
 };
 
+static struct sam9_smc_config __initdata ek_nand_smc_config = {
+	.ncs_read_setup		= 0,
+	.nrd_setup		= 1,
+	.ncs_write_setup	= 0,
+	.nwe_setup		= 1,
+
+	.ncs_read_pulse		= 3,
+	.nrd_pulse		= 3,
+	.ncs_write_pulse	= 3,
+	.nwe_pulse		= 3,
+
+	.read_cycle		= 5,
+	.write_cycle		= 5,
+
+	.mode			= AT91_SMC_READMODE | AT91_SMC_WRITEMODE | AT91_SMC_EXNWMODE_DISABLE,
+	.tdf_cycles		= 2,
+};
+
+static void __init ek_add_device_nand(void)
+{
+	/* setup bus-width (8 or 16) */
+	if (ek_nand_data.bus_width_16)
+		ek_nand_smc_config.mode |= AT91_SMC_DBW_16;
+	else
+		ek_nand_smc_config.mode |= AT91_SMC_DBW_8;
+
+	/* configure chip-select 3 (NAND) */
+	sam9_smc_configure(3, &ek_nand_smc_config);
+
+	at91_add_device_nand(&ek_nand_data);
+}
+
 
 /*
  * I2C devices
@@ -385,7 +419,7 @@ static void __init ek_board_init(void)
 	/* Ethernet */
 	at91_add_device_eth(&ek_macb_data);
 	/* NAND */
-	at91_add_device_nand(&ek_nand_data);
+	ek_add_device_nand();
 	/* I2C */
 	at91_add_device_i2c(ek_i2c_devices, ARRAY_SIZE(ek_i2c_devices));
 	/* LCD Controller */
diff --git a/arch/arm/mach-at91/board-sam9g20ek.c b/arch/arm/mach-at91/board-sam9g20ek.c
index b588ead14d68..81439fe6fb3d 100644
--- a/arch/arm/mach-at91/board-sam9g20ek.c
+++ b/arch/arm/mach-at91/board-sam9g20ek.c
@@ -37,7 +37,9 @@
 
 #include <mach/board.h>
 #include <mach/gpio.h>
+#include <mach/at91sam9_smc.h>
 
+#include "sam9_smc.h"
 #include "generic.h"
 
 
@@ -156,6 +158,38 @@ static struct atmel_nand_data __initdata ek_nand_data = {
 #endif
 };
 
+static struct sam9_smc_config __initdata ek_nand_smc_config = {
+	.ncs_read_setup		= 0,
+	.nrd_setup		= 2,
+	.ncs_write_setup	= 0,
+	.nwe_setup		= 2,
+
+	.ncs_read_pulse		= 4,
+	.nrd_pulse		= 4,
+	.ncs_write_pulse	= 4,
+	.nwe_pulse		= 4,
+
+	.read_cycle		= 7,
+	.write_cycle		= 7,
+
+	.mode			= AT91_SMC_READMODE | AT91_SMC_WRITEMODE | AT91_SMC_EXNWMODE_DISABLE,
+	.tdf_cycles		= 3,
+};
+
+static void __init ek_add_device_nand(void)
+{
+	/* setup bus-width (8 or 16) */
+	if (ek_nand_data.bus_width_16)
+		ek_nand_smc_config.mode |= AT91_SMC_DBW_16;
+	else
+		ek_nand_smc_config.mode |= AT91_SMC_DBW_8;
+
+	/* configure chip-select 3 (NAND) */
+	sam9_smc_configure(3, &ek_nand_smc_config);
+
+	at91_add_device_nand(&ek_nand_data);
+}
+
 
 /*
  * MCI (SD/MMC)
@@ -195,7 +229,7 @@ static void __init ek_board_init(void)
 	/* SPI */
 	at91_add_device_spi(ek_spi_devices, ARRAY_SIZE(ek_spi_devices));
 	/* NAND */
-	at91_add_device_nand(&ek_nand_data);
+	ek_add_device_nand();
 	/* Ethernet */
 	at91_add_device_eth(&ek_macb_data);
 	/* MMC */
diff --git a/arch/arm/mach-at91/board-sam9rlek.c b/arch/arm/mach-at91/board-sam9rlek.c
index 270851864308..9b937ee4815a 100644
--- a/arch/arm/mach-at91/board-sam9rlek.c
+++ b/arch/arm/mach-at91/board-sam9rlek.c
@@ -29,8 +29,9 @@
 #include <mach/hardware.h>
 #include <mach/board.h>
 #include <mach/gpio.h>
-#include <mach/at91sam9_smc.h>
+#include <mach/at91_shdwc.h>
 
+#include "sam9_smc.h"
 #include "generic.h"
 
 
@@ -103,9 +104,34 @@ static struct atmel_nand_data __initdata ek_nand_data = {
 	.rdy_pin	= AT91_PIN_PD17,
 	.enable_pin	= AT91_PIN_PB6,
 	.partition_info	= nand_partitions,
-	.bus_width_16	= 0,
 };
 
+static struct sam9_smc_config __initdata ek_nand_smc_config = {
+	.ncs_read_setup		= 0,
+	.nrd_setup		= 1,
+	.ncs_write_setup	= 0,
+	.nwe_setup		= 1,
+
+	.ncs_read_pulse		= 3,
+	.nrd_pulse		= 3,
+	.ncs_write_pulse	= 3,
+	.nwe_pulse		= 3,
+
+	.read_cycle		= 5,
+	.write_cycle		= 5,
+
+	.mode			= AT91_SMC_READMODE | AT91_SMC_WRITEMODE | AT91_SMC_EXNWMODE_DISABLE | AT91_SMC_DBW_8,
+	.tdf_cycles		= 2,
+};
+
+static void __init ek_add_device_nand(void)
+{
+	/* configure chip-select 3 (NAND) */
+	sam9_smc_configure(3, &ek_nand_smc_config);
+
+	at91_add_device_nand(&ek_nand_data);
+}
+
 
 /*
  * SPI devices
@@ -188,7 +214,7 @@ static void __init ek_board_init(void)
 	/* I2C */
 	at91_add_device_i2c(NULL, 0);
 	/* NAND */
-	at91_add_device_nand(&ek_nand_data);
+	ek_add_device_nand();
 	/* SPI */
 	at91_add_device_spi(ek_spi_devices, ARRAY_SIZE(ek_spi_devices));
 	/* MMC */
diff --git a/arch/arm/mach-at91/board-usb-a9260.c b/arch/arm/mach-at91/board-usb-a9260.c
index 7c350357333a..d13304c0bc45 100644
--- a/arch/arm/mach-at91/board-usb-a9260.c
+++ b/arch/arm/mach-at91/board-usb-a9260.c
@@ -41,8 +41,10 @@
 #include <mach/hardware.h>
 #include <mach/board.h>
 #include <mach/gpio.h>
+#include <mach/at91sam9_smc.h>
 #include <mach/at91_shdwc.h>
 
+#include "sam9_smc.h"
 #include "generic.h"
 
 
@@ -121,13 +123,34 @@ static struct atmel_nand_data __initdata ek_nand_data = {
 	.rdy_pin	= AT91_PIN_PC13,
 	.enable_pin	= AT91_PIN_PC14,
 	.partition_info	= nand_partitions,
-#if defined(CONFIG_MTD_NAND_ATMEL_BUSWIDTH_16)
-	.bus_width_16	= 1,
-#else
-	.bus_width_16	= 0,
-#endif
 };
 
+static struct sam9_smc_config __initdata ek_nand_smc_config = {
+	.ncs_read_setup		= 0,
+	.nrd_setup		= 1,
+	.ncs_write_setup	= 0,
+	.nwe_setup		= 1,
+
+	.ncs_read_pulse		= 3,
+	.nrd_pulse		= 3,
+	.ncs_write_pulse	= 3,
+	.nwe_pulse		= 3,
+
+	.read_cycle		= 5,
+	.write_cycle		= 5,
+
+	.mode			= AT91_SMC_READMODE | AT91_SMC_WRITEMODE | AT91_SMC_EXNWMODE_DISABLE | AT91_SMC_DBW_8,
+	.tdf_cycles		= 2,
+};
+
+static void __init ek_add_device_nand(void)
+{
+	/* configure chip-select 3 (NAND) */
+	sam9_smc_configure(3, &ek_nand_smc_config);
+
+	at91_add_device_nand(&ek_nand_data);
+}
+
 /*
  * GPIO Buttons
  */
@@ -189,7 +212,7 @@ static void __init ek_board_init(void)
 	/* USB Device */
 	at91_add_device_udc(&ek_udc_data);
 	/* NAND */
-	at91_add_device_nand(&ek_nand_data);
+	ek_add_device_nand();
 	/* I2C */
 	at91_add_device_i2c(NULL, 0);
 	/* Ethernet */
diff --git a/arch/arm/mach-at91/board-usb-a9263.c b/arch/arm/mach-at91/board-usb-a9263.c
index 391b566c4571..d96405b7d578 100644
--- a/arch/arm/mach-at91/board-usb-a9263.c
+++ b/arch/arm/mach-at91/board-usb-a9263.c
@@ -40,8 +40,10 @@
 #include <mach/hardware.h>
 #include <mach/board.h>
 #include <mach/gpio.h>
+#include <mach/at91sam9_smc.h>
 #include <mach/at91_shdwc.h>
 
+#include "sam9_smc.h"
 #include "generic.h"
 
 
@@ -134,13 +136,35 @@ static struct atmel_nand_data __initdata ek_nand_data = {
 	.rdy_pin	= AT91_PIN_PA22,
 	.enable_pin	= AT91_PIN_PD15,
 	.partition_info	= nand_partitions,
-#if defined(CONFIG_MTD_NAND_ATMEL_BUSWIDTH_16)
-	.bus_width_16	= 1,
-#else
-	.bus_width_16	= 0,
-#endif
 };
 
+static struct sam9_smc_config __initdata ek_nand_smc_config = {
+	.ncs_read_setup		= 0,
+	.nrd_setup		= 1,
+	.ncs_write_setup	= 0,
+	.nwe_setup		= 1,
+
+	.ncs_read_pulse		= 3,
+	.nrd_pulse		= 3,
+	.ncs_write_pulse	= 3,
+	.nwe_pulse		= 3,
+
+	.read_cycle		= 5,
+	.write_cycle		= 5,
+
+	.mode			= AT91_SMC_READMODE | AT91_SMC_WRITEMODE | AT91_SMC_EXNWMODE_DISABLE | AT91_SMC_DBW_8,
+	.tdf_cycles		= 2,
+};
+
+static void __init ek_add_device_nand(void)
+{
+	/* configure chip-select 3 (NAND) */
+	sam9_smc_configure(3, &ek_nand_smc_config);
+
+	at91_add_device_nand(&ek_nand_data);
+}
+
+
 /*
  * GPIO Buttons
  */
@@ -206,7 +230,7 @@ static void __init ek_board_init(void)
 	/* Ethernet */
 	at91_add_device_eth(&ek_macb_data);
 	/* NAND */
-	at91_add_device_nand(&ek_nand_data);
+	ek_add_device_nand();
 	/* I2C */
 	at91_add_device_i2c(NULL, 0);
 	/* Push Buttons */
diff --git a/arch/arm/mach-at91/include/mach/at91_pmc.h b/arch/arm/mach-at91/include/mach/at91_pmc.h
index 2e3f2894b704..9561e33b8a9a 100644
--- a/arch/arm/mach-at91/include/mach/at91_pmc.h
+++ b/arch/arm/mach-at91/include/mach/at91_pmc.h
@@ -23,6 +23,7 @@
 #define		AT91_PMC_PCK		(1 <<  0)		/* Processor Clock */
 #define		AT91RM9200_PMC_UDP	(1 <<  1)		/* USB Devcice Port Clock [AT91RM9200 only] */
 #define		AT91RM9200_PMC_MCKUDP	(1 <<  2)		/* USB Device Port Master Clock Automatic Disable on Suspend [AT91RM9200 only] */
+#define		AT91CAP9_PMC_DDR	(1 <<  2)		/* DDR Clock [AT91CAP9 revC only] */
 #define		AT91RM9200_PMC_UHP	(1 <<  4)		/* USB Host Port Clock [AT91RM9200 only] */
 #define		AT91SAM926x_PMC_UHP	(1 <<  6)		/* USB Host Port Clock [AT91SAM926x only] */
 #define		AT91CAP9_PMC_UHP	(1 <<  6)		/* USB Host Port Clock [AT91CAP9 only] */
@@ -102,10 +103,16 @@
 #define		AT91_PMC_LOCKB		(1 <<  2)		/* PLLB Lock */
 #define		AT91_PMC_MCKRDY		(1 <<  3)		/* Master Clock */
 #define		AT91_PMC_LOCKU		(1 <<  6)		/* UPLL Lock [AT91CAP9 only] */
+#define		AT91_PMC_OSCSEL		(1 <<  7)		/* Slow Clock Oscillator [AT91CAP9 revC only] */
 #define		AT91_PMC_PCK0RDY	(1 <<  8)		/* Programmable Clock 0 */
 #define		AT91_PMC_PCK1RDY	(1 <<  9)		/* Programmable Clock 1 */
 #define		AT91_PMC_PCK2RDY	(1 << 10)		/* Programmable Clock 2 */
 #define		AT91_PMC_PCK3RDY	(1 << 11)		/* Programmable Clock 3 */
 #define	AT91_PMC_IMR		(AT91_PMC + 0x6c)	/* Interrupt Mask Register */
 
+#define AT91_PMC_PROT		(AT91_PMC + 0xe4)	/* Protect Register [AT91CAP9 revC only] */
+#define		AT91_PMC_PROTKEY	0x504d4301	/* Activation Code */
+
+#define AT91_PMC_VER		(AT91_PMC + 0xfc)	/* PMC Module Version [AT91CAP9 only] */
+
 #endif
diff --git a/arch/arm/mach-at91/include/mach/at91cap9.h b/arch/arm/mach-at91/include/mach/at91cap9.h
index 4a4b64135a92..d8c1ededaa75 100644
--- a/arch/arm/mach-at91/include/mach/at91cap9.h
+++ b/arch/arm/mach-at91/include/mach/at91cap9.h
@@ -101,7 +101,9 @@
 #define AT91_RTT	(0xfffffd20 - AT91_BASE_SYS)
 #define AT91_PIT	(0xfffffd30 - AT91_BASE_SYS)
 #define AT91_WDT	(0xfffffd40 - AT91_BASE_SYS)
-#define AT91_GPBR	(0xfffffd50 - AT91_BASE_SYS)
+#define AT91_GPBR	(cpu_is_at91cap9_revB() ?	\
+			(0xfffffd50 - AT91_BASE_SYS) :	\
+			(0xfffffd60 - AT91_BASE_SYS))
 
 #define AT91_USART0	AT91CAP9_BASE_US0
 #define AT91_USART1	AT91CAP9_BASE_US1
diff --git a/arch/arm/mach-at91/include/mach/cpu.h b/arch/arm/mach-at91/include/mach/cpu.h
index dbfd9f73f80b..c554c3e4d553 100644
--- a/arch/arm/mach-at91/include/mach/cpu.h
+++ b/arch/arm/mach-at91/include/mach/cpu.h
@@ -49,6 +49,17 @@ static inline unsigned long at91_arch_identify(void)
 	return (at91_sys_read(AT91_DBGU_CIDR) & AT91_CIDR_ARCH);
 }
 
+#ifdef CONFIG_ARCH_AT91CAP9
+#include <mach/at91_pmc.h>
+
+#define ARCH_REVISION_CAP9_B	0x399
+#define ARCH_REVISION_CAP9_C	0x601
+
+static inline unsigned long at91cap9_rev_identify(void)
+{
+	return (at91_sys_read(AT91_PMC_VER));
+}
+#endif
 
 #ifdef CONFIG_ARCH_AT91RM9200
 #define cpu_is_at91rm9200()	(at91_cpu_identify() == ARCH_ID_AT91RM9200)
@@ -90,8 +101,12 @@ static inline unsigned long at91_arch_identify(void)
 
 #ifdef CONFIG_ARCH_AT91CAP9
 #define cpu_is_at91cap9()	(at91_cpu_identify() == ARCH_ID_AT91CAP9)
+#define cpu_is_at91cap9_revB()	(at91cap9_rev_identify() == ARCH_REVISION_CAP9_B)
+#define cpu_is_at91cap9_revC()	(at91cap9_rev_identify() == ARCH_REVISION_CAP9_C)
 #else
 #define cpu_is_at91cap9()	(0)
+#define cpu_is_at91cap9_revB()	(0)
+#define cpu_is_at91cap9_revC()	(0)
 #endif
 
 /*
diff --git a/arch/arm/mach-at91/include/mach/dma.h b/arch/arm/mach-at91/include/mach/dma.h
deleted file mode 100644
index e4f90c177616..000000000000
--- a/arch/arm/mach-at91/include/mach/dma.h
+++ /dev/null
@@ -1,19 +0,0 @@
-/*
- * arch/arm/mach-at91/include/mach/dma.h
- *
- *  Copyright (C) 2003 SAN People
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
- */
diff --git a/arch/arm/mach-at91/include/mach/io.h b/arch/arm/mach-at91/include/mach/io.h
index 1611bd03f528..0b0cccc46e68 100644
--- a/arch/arm/mach-at91/include/mach/io.h
+++ b/arch/arm/mach-at91/include/mach/io.h
@@ -23,8 +23,8 @@
 
 #define IO_SPACE_LIMIT		0xFFFFFFFF
 
-#define __io(a)			((void __iomem *)(a))
-#define __mem_pci(a)		(a)
+#define __io(a)		__typesafe_io(a)
+#define __mem_pci(a)	(a)
 
 
 #ifndef __ASSEMBLY__
diff --git a/arch/arm/mach-at91/include/mach/memory.h b/arch/arm/mach-at91/include/mach/memory.h
index 9dd1b8c79b08..14f4ef4b6a9e 100644
--- a/arch/arm/mach-at91/include/mach/memory.h
+++ b/arch/arm/mach-at91/include/mach/memory.h
@@ -25,15 +25,4 @@
 
 #define PHYS_OFFSET	(AT91_SDRAM_BASE)
 
-
-/*
- * Virtual view <-> DMA view memory address translations
- * virt_to_bus: Used to translate the virtual address to an
- *              address suitable to be passed to set_dma_addr
- * bus_to_virt: Used to convert an address for DMA operations
- *              to an address that the kernel can use.
- */
-#define __virt_to_bus(x) __virt_to_phys(x)
-#define __bus_to_virt(x) __phys_to_virt(x)
-
 #endif
diff --git a/arch/arm/mach-at91/sam9_smc.c b/arch/arm/mach-at91/sam9_smc.c
new file mode 100644
index 000000000000..5eab6aa621d0
--- /dev/null
+++ b/arch/arm/mach-at91/sam9_smc.c
@@ -0,0 +1,47 @@
+/*
+ * linux/arch/arm/mach-at91/sam9_smc.c
+ *
+ * Copyright (C) 2008 Andrew Victor
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/module.h>
+#include <linux/io.h>
+
+#include <mach/at91sam9_smc.h>
+
+#include "sam9_smc.h"
+
+void __init sam9_smc_configure(int cs, struct sam9_smc_config* config)
+{
+	/* Setup register */
+	at91_sys_write(AT91_SMC_SETUP(cs),
+		  AT91_SMC_NWESETUP_(config->nwe_setup)
+		| AT91_SMC_NCS_WRSETUP_(config->ncs_write_setup)
+		| AT91_SMC_NRDSETUP_(config->nrd_setup)
+		| AT91_SMC_NCS_RDSETUP_(config->ncs_read_setup)
+	);
+
+	/* Pulse register */
+	at91_sys_write(AT91_SMC_PULSE(cs),
+		  AT91_SMC_NWEPULSE_(config->nwe_pulse)
+		| AT91_SMC_NCS_WRPULSE_(config->ncs_write_pulse)
+                | AT91_SMC_NRDPULSE_(config->nrd_pulse)
+		| AT91_SMC_NCS_RDPULSE_(config->ncs_read_pulse)
+	);
+
+	/* Cycle register */
+	at91_sys_write(AT91_SMC_CYCLE(cs),
+		  AT91_SMC_NWECYCLE_(config->write_cycle)
+		| AT91_SMC_NRDCYCLE_(config->read_cycle)
+	);
+
+	/* Mode register */
+	at91_sys_write(AT91_SMC_MODE(cs),
+		  config->mode
+		| AT91_SMC_TDF_(config->tdf_cycles)
+	);
+}
diff --git a/arch/arm/mach-at91/sam9_smc.h b/arch/arm/mach-at91/sam9_smc.h
new file mode 100644
index 000000000000..bf72cfb3455b
--- /dev/null
+++ b/arch/arm/mach-at91/sam9_smc.h
@@ -0,0 +1,33 @@
+/*
+ * linux/arch/arm/mach-at91/sam9_smc.
+ *
+ * Copyright (C) 2008 Andrew Victor
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+struct sam9_smc_config {
+	/* Setup register */
+	u8 ncs_read_setup;
+	u8 nrd_setup;
+	u8 ncs_write_setup;
+	u8 nwe_setup;
+
+	/* Pulse register */
+	u8 ncs_read_pulse;
+	u8 nrd_pulse;
+	u8 ncs_write_pulse;
+	u8 nwe_pulse;
+
+	/* Cycle register */
+	u16 read_cycle;
+	u16 write_cycle;
+
+	/* Mode register */
+	u32 mode;
+	u8 tdf_cycles:4;
+};
+
+extern void __init sam9_smc_configure(int cs, struct sam9_smc_config* config);
diff --git a/arch/arm/mach-clps711x/include/mach/dma.h b/arch/arm/mach-clps711x/include/mach/dma.h
deleted file mode 100644
index 0d620e869536..000000000000
--- a/arch/arm/mach-clps711x/include/mach/dma.h
+++ /dev/null
@@ -1,19 +0,0 @@
-/*
- *  arch/arm/mach-clps711x/include/mach/dma.h
- *
- *  Copyright (C) 1997,1998 Russell King
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
- */
diff --git a/arch/arm/mach-clps711x/include/mach/io.h b/arch/arm/mach-clps711x/include/mach/io.h
index 4c8440087679..2e0b3ced8f07 100644
--- a/arch/arm/mach-clps711x/include/mach/io.h
+++ b/arch/arm/mach-clps711x/include/mach/io.h
@@ -20,12 +20,10 @@
 #ifndef __ASM_ARM_ARCH_IO_H
 #define __ASM_ARM_ARCH_IO_H
 
-#include <mach/hardware.h>
-
 #define IO_SPACE_LIMIT 0xffffffff
 
-#define __io(a)			((void __iomem *)(a))
-#define __mem_pci(a)		(a)
+#define __io(a)		__typesafe_io(a)
+#define __mem_pci(a)	(a)
 
 /*
  * We don't support ins[lb]/outs[lb].  Make them fault.
diff --git a/arch/arm/mach-clps711x/include/mach/memory.h b/arch/arm/mach-clps711x/include/mach/memory.h
index 98ec30c97bbe..e522b20bcbc2 100644
--- a/arch/arm/mach-clps711x/include/mach/memory.h
+++ b/arch/arm/mach-clps711x/include/mach/memory.h
@@ -26,25 +26,7 @@
  */
 #define PHYS_OFFSET	UL(0xc0000000)
 
-/*
- * Virtual view <-> DMA view memory address translations
- * virt_to_bus: Used to translate the virtual address to an
- *              address suitable to be passed to set_dma_addr
- * bus_to_virt: Used to convert an address for DMA operations
- *              to an address that the kernel can use.
- */
-
-#if defined(CONFIG_ARCH_CDB89712)
-
-#define __virt_to_bus(x)	(x)
-#define __bus_to_virt(x)	(x)
-
-#elif defined (CONFIG_ARCH_AUTCPU12)
-
-#define __virt_to_bus(x)	(x)
-#define __bus_to_virt(x)	(x)
-
-#else
+#if !defined(CONFIG_ARCH_CDB89712) && !defined (CONFIG_ARCH_AUTCPU12)
 
 #define __virt_to_bus(x)	((x) - PAGE_OFFSET)
 #define __bus_to_virt(x)	((x) + PAGE_OFFSET)
diff --git a/arch/arm/mach-clps7500/Makefile b/arch/arm/mach-clps7500/Makefile
deleted file mode 100644
index 4bd8ebd70e7b..000000000000
--- a/arch/arm/mach-clps7500/Makefile
+++ /dev/null
@@ -1,11 +0,0 @@
-#
-# Makefile for the linux kernel.
-#
-
-# Object file lists.
-
-obj-y			:= core.o
-obj-m			:=
-obj-n			:=
-obj-			:=
-
diff --git a/arch/arm/mach-clps7500/Makefile.boot b/arch/arm/mach-clps7500/Makefile.boot
deleted file mode 100644
index fe16506c1540..000000000000
--- a/arch/arm/mach-clps7500/Makefile.boot
+++ /dev/null
@@ -1,2 +0,0 @@
-   zreladdr-y	:= 0x10008000
-
diff --git a/arch/arm/mach-clps7500/core.c b/arch/arm/mach-clps7500/core.c
deleted file mode 100644
index 7e247c04d41c..000000000000
--- a/arch/arm/mach-clps7500/core.c
+++ /dev/null
@@ -1,395 +0,0 @@
-/*
- *  linux/arch/arm/mach-clps7500/core.c
- *
- *  Copyright (C) 1998 Russell King
- *  Copyright (C) 1999 Nexus Electronics Ltd
- *
- * Extra MM routines for CL7500 architecture
- */
-#include <linux/kernel.h>
-#include <linux/types.h>
-#include <linux/interrupt.h>
-#include <linux/irq.h>
-#include <linux/list.h>
-#include <linux/sched.h>
-#include <linux/init.h>
-#include <linux/device.h>
-#include <linux/serial_8250.h>
-#include <linux/io.h>
-
-#include <asm/mach/arch.h>
-#include <asm/mach/map.h>
-#include <asm/mach/irq.h>
-#include <asm/mach/time.h>
-
-#include <mach/hardware.h>
-#include <asm/hardware/iomd.h>
-#include <asm/irq.h>
-#include <asm/mach-types.h>
-
-unsigned int vram_size;
-
-static void cl7500_ack_irq_a(unsigned int irq)
-{
-	unsigned int val, mask;
-
-	mask = 1 << irq;
-	val = iomd_readb(IOMD_IRQMASKA);
-	iomd_writeb(val & ~mask, IOMD_IRQMASKA);
-	iomd_writeb(mask, IOMD_IRQCLRA);
-}
-
-static void cl7500_mask_irq_a(unsigned int irq)
-{
-	unsigned int val, mask;
-
-	mask = 1 << irq;
-	val = iomd_readb(IOMD_IRQMASKA);
-	iomd_writeb(val & ~mask, IOMD_IRQMASKA);
-}
-
-static void cl7500_unmask_irq_a(unsigned int irq)
-{
-	unsigned int val, mask;
-
-	mask = 1 << irq;
-	val = iomd_readb(IOMD_IRQMASKA);
-	iomd_writeb(val | mask, IOMD_IRQMASKA);
-}
-
-static struct irq_chip clps7500_a_chip = {
-	.ack	= cl7500_ack_irq_a,
-	.mask	= cl7500_mask_irq_a,
-	.unmask	= cl7500_unmask_irq_a,
-};
-
-static void cl7500_mask_irq_b(unsigned int irq)
-{
-	unsigned int val, mask;
-
-	mask = 1 << (irq & 7);
-	val = iomd_readb(IOMD_IRQMASKB);
-	iomd_writeb(val & ~mask, IOMD_IRQMASKB);
-}
-
-static void cl7500_unmask_irq_b(unsigned int irq)
-{
-	unsigned int val, mask;
-
-	mask = 1 << (irq & 7);
-	val = iomd_readb(IOMD_IRQMASKB);
-	iomd_writeb(val | mask, IOMD_IRQMASKB);
-}
-
-static struct irq_chip clps7500_b_chip = {
-	.ack	= cl7500_mask_irq_b,
-	.mask	= cl7500_mask_irq_b,
-	.unmask	= cl7500_unmask_irq_b,
-};
-
-static void cl7500_mask_irq_c(unsigned int irq)
-{
-	unsigned int val, mask;
-
-	mask = 1 << (irq & 7);
-	val = iomd_readb(IOMD_IRQMASKC);
-	iomd_writeb(val & ~mask, IOMD_IRQMASKC);
-}
-
-static void cl7500_unmask_irq_c(unsigned int irq)
-{
-	unsigned int val, mask;
-
-	mask = 1 << (irq & 7);
-	val = iomd_readb(IOMD_IRQMASKC);
-	iomd_writeb(val | mask, IOMD_IRQMASKC);
-}
-
-static struct irq_chip clps7500_c_chip = {
-	.ack	= cl7500_mask_irq_c,
-	.mask	= cl7500_mask_irq_c,
-	.unmask	= cl7500_unmask_irq_c,
-};
-
-static void cl7500_mask_irq_d(unsigned int irq)
-{
-	unsigned int val, mask;
-
-	mask = 1 << (irq & 7);
-	val = iomd_readb(IOMD_IRQMASKD);
-	iomd_writeb(val & ~mask, IOMD_IRQMASKD);
-}
-
-static void cl7500_unmask_irq_d(unsigned int irq)
-{
-	unsigned int val, mask;
-
-	mask = 1 << (irq & 7);
-	val = iomd_readb(IOMD_IRQMASKD);
-	iomd_writeb(val | mask, IOMD_IRQMASKD);
-}
-
-static struct irq_chip clps7500_d_chip = {
-	.ack	= cl7500_mask_irq_d,
-	.mask	= cl7500_mask_irq_d,
-	.unmask	= cl7500_unmask_irq_d,
-};
-
-static void cl7500_mask_irq_dma(unsigned int irq)
-{
-	unsigned int val, mask;
-
-	mask = 1 << (irq & 7);
-	val = iomd_readb(IOMD_DMAMASK);
-	iomd_writeb(val & ~mask, IOMD_DMAMASK);
-}
-
-static void cl7500_unmask_irq_dma(unsigned int irq)
-{
-	unsigned int val, mask;
-
-	mask = 1 << (irq & 7);
-	val = iomd_readb(IOMD_DMAMASK);
-	iomd_writeb(val | mask, IOMD_DMAMASK);
-}
-
-static struct irq_chip clps7500_dma_chip = {
-	.ack	= cl7500_mask_irq_dma,
-	.mask	= cl7500_mask_irq_dma,
-	.unmask	= cl7500_unmask_irq_dma,
-};
-
-static void cl7500_mask_irq_fiq(unsigned int irq)
-{
-	unsigned int val, mask;
-
-	mask = 1 << (irq & 7);
-	val = iomd_readb(IOMD_FIQMASK);
-	iomd_writeb(val & ~mask, IOMD_FIQMASK);
-}
-
-static void cl7500_unmask_irq_fiq(unsigned int irq)
-{
-	unsigned int val, mask;
-
-	mask = 1 << (irq & 7);
-	val = iomd_readb(IOMD_FIQMASK);
-	iomd_writeb(val | mask, IOMD_FIQMASK);
-}
-
-static struct irq_chip clps7500_fiq_chip = {
-	.ack	= cl7500_mask_irq_fiq,
-	.mask	= cl7500_mask_irq_fiq,
-	.unmask	= cl7500_unmask_irq_fiq,
-};
-
-static void cl7500_no_action(unsigned int irq)
-{
-}
-
-static struct irq_chip clps7500_no_chip = {
-	.ack	= cl7500_no_action,
-	.mask	= cl7500_no_action,
-	.unmask	= cl7500_no_action,
-};
-
-static struct irqaction irq_isa = {
-	.handler = no_action,
-	.mask = CPU_MASK_NONE,
-	.name = "isa",
-};
-
-static void __init clps7500_init_irq(void)
-{
-	unsigned int irq, flags;
-
-	iomd_writeb(0, IOMD_IRQMASKA);
-	iomd_writeb(0, IOMD_IRQMASKB);
-	iomd_writeb(0, IOMD_FIQMASK);
-	iomd_writeb(0, IOMD_DMAMASK);
-
-	for (irq = 0; irq < NR_IRQS; irq++) {
-		flags = IRQF_VALID;
-
-		if (irq <= 6 || (irq >= 9 && irq <= 15) ||
-		    (irq >= 48 && irq <= 55))
-			flags |= IRQF_PROBE;
-
-		switch (irq) {
-		case 0 ... 7:
-			set_irq_chip(irq, &clps7500_a_chip);
-			set_irq_handler(irq, handle_level_irq);
-			set_irq_flags(irq, flags);
-			break;
-
-		case 8 ... 15:
-			set_irq_chip(irq, &clps7500_b_chip);
-			set_irq_handler(irq, handle_level_irq);
-			set_irq_flags(irq, flags);
-			break;
-
-		case 16 ... 22:
-			set_irq_chip(irq, &clps7500_dma_chip);
-			set_irq_handler(irq, handle_level_irq);
-			set_irq_flags(irq, flags);
-			break;
-
-		case 24 ... 31:
-			set_irq_chip(irq, &clps7500_c_chip);
-			set_irq_handler(irq, handle_level_irq);
-			set_irq_flags(irq, flags);
-			break;
-
-		case 40 ... 47:
-			set_irq_chip(irq, &clps7500_d_chip);
-			set_irq_handler(irq, handle_level_irq);
-			set_irq_flags(irq, flags);
-			break;
-
-		case 48 ... 55:
-			set_irq_chip(irq, &clps7500_no_chip);
-			set_irq_handler(irq, handle_level_irq);
-			set_irq_flags(irq, flags);
-			break;
-
-		case 64 ... 72:
-			set_irq_chip(irq, &clps7500_fiq_chip);
-			set_irq_handler(irq, handle_level_irq);
-			set_irq_flags(irq, flags);
-			break;
-		}
-	}
-
-	setup_irq(IRQ_ISA, &irq_isa);
-}
-
-static struct map_desc cl7500_io_desc[] __initdata = {
-	{ 	/* IO space	*/
-		.virtual	= (unsigned long)IO_BASE,
-		.pfn		= __phys_to_pfn(IO_START),
-		.length		= IO_SIZE,
-		.type		= MT_DEVICE
-	}, {	/* ISA space	*/
-		.virtual	= ISA_BASE,
-		.pfn		= __phys_to_pfn(ISA_START),
-		.length		= ISA_SIZE,
-		.type		= MT_DEVICE
-	}, {	/* Flash	*/
-		.virtual	= CLPS7500_FLASH_BASE,
-		.pfn		= __phys_to_pfn(CLPS7500_FLASH_START),
-		.length		= CLPS7500_FLASH_SIZE,
-		.type		= MT_DEVICE
-	}, {	/* LED		*/
-		.virtual	= LED_BASE,
-		.pfn		= __phys_to_pfn(LED_START),
-		.length		= LED_SIZE,
-		.type		= MT_DEVICE
-	}
-};
-
-static void __init clps7500_map_io(void)
-{
-	iotable_init(cl7500_io_desc, ARRAY_SIZE(cl7500_io_desc));
-}
-
-extern void ioctime_init(void);
-extern unsigned long ioc_timer_gettimeoffset(void);
-
-static irqreturn_t
-clps7500_timer_interrupt(int irq, void *dev_id)
-{
-	timer_tick();
-
-	/* Why not using do_leds interface?? */
-	{
-		/* Twinkle the lights. */
-		static int count, state = 0xff00;
-		if (count-- == 0) {
-			state ^= 0x100;
-			count = 25;
-			*((volatile unsigned int *)LED_ADDRESS) = state;
-		}
-	}
-
-	return IRQ_HANDLED;
-}
-
-static struct irqaction clps7500_timer_irq = {
-	.name		= "CLPS7500 Timer Tick",
-	.flags		= IRQF_DISABLED | IRQF_TIMER | IRQF_IRQPOLL,
-	.handler	= clps7500_timer_interrupt,
-};
-
-/*
- * Set up timer interrupt.
- */
-static void __init clps7500_timer_init(void)
-{
-	ioctime_init();
-	setup_irq(IRQ_TIMER, &clps7500_timer_irq);
-}
-
-static struct sys_timer clps7500_timer = {
-	.init		= clps7500_timer_init,
-	.offset		= ioc_timer_gettimeoffset,
-};
-
-static struct plat_serial8250_port serial_platform_data[] = {
-	{
-		.mapbase	= 0x03010fe0,
-		.irq		= 10,
-		.uartclk	= 1843200,
-		.regshift	= 2,
-		.iotype		= UPIO_MEM,
-		.flags		= UPF_BOOT_AUTOCONF | UPF_IOREMAP | UPF_SKIP_TEST,
-	},
-	{
-		.mapbase	= 0x03010be0,
-		.irq		= 0,
-		.uartclk	= 1843200,
-		.regshift	= 2,
-		.iotype		= UPIO_MEM,
-		.flags		= UPF_BOOT_AUTOCONF | UPF_IOREMAP | UPF_SKIP_TEST,
-	},
-	{
-		.iobase		= ISASLOT_IO + 0x2e8,
-		.irq		= 41,
-		.uartclk	= 1843200,
-		.regshift	= 0,
-		.iotype		= UPIO_PORT,
-		.flags		= UPF_BOOT_AUTOCONF | UPF_SKIP_TEST,
-	},
-	{
-		.iobase		= ISASLOT_IO + 0x3e8,
-		.irq		= 40,
-		.uartclk	= 1843200,
-		.regshift	= 0,
-		.iotype		= UPIO_PORT,
-		.flags		= UPF_BOOT_AUTOCONF | UPF_SKIP_TEST,
-	},
-	{ },
-};
-
-static struct platform_device serial_device = {
-	.name			= "serial8250",
-	.id			= PLAT8250_DEV_PLATFORM,
-	.dev			= {
-		.platform_data	= serial_platform_data,
-	},
-};
-
-static void __init clps7500_init(void)
-{
-	platform_device_register(&serial_device);
-}
-
-MACHINE_START(CLPS7500, "CL-PS7500")
-	/* Maintainer: Philip Blundell */
-	.phys_io	= 0x03000000,
-	.io_pg_offst	= ((0xe0000000) >> 18) & 0xfffc,
-	.map_io		= clps7500_map_io,
-	.init_irq	= clps7500_init_irq,
-	.init_machine	= clps7500_init,
-	.timer		= &clps7500_timer,
-MACHINE_END
-
diff --git a/arch/arm/mach-clps7500/include/mach/acornfb.h b/arch/arm/mach-clps7500/include/mach/acornfb.h
deleted file mode 100644
index aea6330c9745..000000000000
--- a/arch/arm/mach-clps7500/include/mach/acornfb.h
+++ /dev/null
@@ -1,33 +0,0 @@
-#define acornfb_valid_pixrate(var) (var->pixclock >= 39325 && var->pixclock <= 40119)
-
-static inline void
-acornfb_vidc20_find_rates(struct vidc_timing *vidc,
-			  struct fb_var_screeninfo *var)
-{
-	u_int bandwidth;
-  
-	vidc->control |= VIDC20_CTRL_PIX_CK;
-
-	/* Calculate bandwidth */
-	bandwidth = var->pixclock * 8 / var->bits_per_pixel;
-
-	/* Encode bandwidth as VIDC20 setting */
-	if (bandwidth > 16667*2)
-		vidc->control |= VIDC20_CTRL_FIFO_16;
-	else if (bandwidth > 13333*2)
-		vidc->control |= VIDC20_CTRL_FIFO_20;
-	else if (bandwidth > 11111*2)
-		vidc->control |= VIDC20_CTRL_FIFO_24;
-	else
-		vidc->control |= VIDC20_CTRL_FIFO_28;
-
-	vidc->pll_ctl  = 0x2020;
-}
-
-#ifdef CONFIG_CHRONTEL_7003
-#define acornfb_default_control()	VIDC20_CTRL_PIX_HCLK
-#else
-#define acornfb_default_control()	VIDC20_CTRL_PIX_VCLK
-#endif
-
-#define acornfb_default_econtrol()	VIDC20_ECTL_DAC | VIDC20_ECTL_REG(3) | VIDC20_ECTL_ECK
diff --git a/arch/arm/mach-clps7500/include/mach/debug-macro.S b/arch/arm/mach-clps7500/include/mach/debug-macro.S
deleted file mode 100644
index af4104e7e84a..000000000000
--- a/arch/arm/mach-clps7500/include/mach/debug-macro.S
+++ /dev/null
@@ -1,21 +0,0 @@
-/* arch/arm/mach-clps7500/include/mach/debug-macro.S
- *
- * Debugging macro include header
- *
- *  Copyright (C) 1994-1999 Russell King
- *  Moved from linux/arch/arm/kernel/debug.S by Ben Dooks
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
-*/
-
-		.macro	addruart,rx
-		mov	\rx, #0xe0000000
-		orr	\rx, \rx, #0x00010000
-		orr	\rx, \rx, #0x00000be0
-		.endm
-
-#define UART_SHIFT	2
-#include <asm/hardware/debug-8250.S>
diff --git a/arch/arm/mach-clps7500/include/mach/dma.h b/arch/arm/mach-clps7500/include/mach/dma.h
deleted file mode 100644
index 63fcde505498..000000000000
--- a/arch/arm/mach-clps7500/include/mach/dma.h
+++ /dev/null
@@ -1,21 +0,0 @@
-/*
- * arch/arm/mach-clps7500/include/mach/dma.h
- *
- * Copyright (C) 1999 Nexus Electronics Ltd.
- */
-
-#ifndef __ASM_ARCH_DMA_H
-#define __ASM_ARCH_DMA_H
-
-/* DMA is not yet implemented! It should be the same as acorn, copy over.. */
-
-/*
- * This is the maximum DMA address that can be DMAd to.
- * There should not be more than (0xd0000000 - 0xc0000000)
- * bytes of RAM.
- */
-#define MAX_DMA_ADDRESS		0xd0000000
-
-#define DMA_S0			0
-
-#endif /* _ASM_ARCH_DMA_H */
diff --git a/arch/arm/mach-clps7500/include/mach/entry-macro.S b/arch/arm/mach-clps7500/include/mach/entry-macro.S
deleted file mode 100644
index 4e7e54144093..000000000000
--- a/arch/arm/mach-clps7500/include/mach/entry-macro.S
+++ /dev/null
@@ -1,16 +0,0 @@
-#include <mach/hardware.h>
-#include <asm/hardware/entry-macro-iomd.S>
-
-	.equ	ioc_base_high, IOC_BASE & 0xff000000
-	.equ	ioc_base_low, IOC_BASE & 0x00ff0000
-
-	.macro  get_irqnr_preamble, base, tmp
-	mov	\base, #ioc_base_high		@ point at IOC
-	.if	ioc_base_low
-	orr	\base, \base, #ioc_base_low
-	.endif
-	.endm
-
-	.macro  arch_ret_to_user, tmp1, tmp2
-	.endm
-
diff --git a/arch/arm/mach-clps7500/include/mach/hardware.h b/arch/arm/mach-clps7500/include/mach/hardware.h
deleted file mode 100644
index a6ad1d44badf..000000000000
--- a/arch/arm/mach-clps7500/include/mach/hardware.h
+++ /dev/null
@@ -1,67 +0,0 @@
-/*
- * arch/arm/mach-clps7500/include/mach/hardware.h
- *
- * Copyright (C) 1996-1999 Russell King.
- * Copyright (C) 1999 Nexus Electronics Ltd.
- *
- * This file contains the hardware definitions of the 
- * CL7500 evaluation board.
- */
-#ifndef __ASM_ARCH_HARDWARE_H
-#define __ASM_ARCH_HARDWARE_H
-
-#include <mach/memory.h>
-#include <asm/hardware/iomd.h>
-
-#ifdef __ASSEMBLY__
-#define IOMEM(x) x
-#else
-#define IOMEM(x) ((void __iomem *)(x))
-#endif
-
-/*
- * What hardware must be present
- */
-#define HAS_IOMD
-#define HAS_VIDC20
-
-/* Hardware addresses of major areas.
- *  *_START is the physical address
- *  *_SIZE  is the size of the region
- *  *_BASE  is the virtual address
- */
-
-#define IO_START		0x03000000	/* I/O */
-#define IO_SIZE			0x01000000
-#define IO_BASE			IOMEM(0xe0000000)
-
-#define ISA_START		0x0c000000	/* ISA */
-#define ISA_SIZE		0x00010000
-#define ISA_BASE		0xe1000000
-
-#define CLPS7500_FLASH_START	0x01000000	/* XXX */
-#define CLPS7500_FLASH_SIZE	0x01000000
-#define CLPS7500_FLASH_BASE	0xe2000000
-
-#define LED_START		0x0302B000
-#define LED_SIZE		0x00001000
-#define LED_BASE		0xe3000000
-#define LED_ADDRESS		(LED_BASE + 0xa00)
-
-/* Let's define SCREEN_START for CL7500, even though it's a lie. */
-#define SCREEN_START		0x02000000	/* VRAM */
-#define SCREEN_END		0xdfc00000
-#define SCREEN_BASE		0xdf800000
-
-#define VIDC_BASE		(void __iomem *)0xe0400000
-#define IOMD_BASE		IOMEM(0xe0200000)
-#define IOC_BASE		IOMEM(0xe0200000)
-#define FLOPPYDMA_BASE		IOMEM(0xe002a000)
-#define PCIO_BASE		IOMEM(0xe0010000)
-
-#define vidc_writel(val)	__raw_writel(val, VIDC_BASE)
-
-/* in/out bias for the ISA slot region */
-#define ISASLOT_IO		0x80400000
-
-#endif
diff --git a/arch/arm/mach-clps7500/include/mach/io.h b/arch/arm/mach-clps7500/include/mach/io.h
deleted file mode 100644
index 2ff2860889ed..000000000000
--- a/arch/arm/mach-clps7500/include/mach/io.h
+++ /dev/null
@@ -1,255 +0,0 @@
-/*
- * arch/arm/mach-clps7500/include/mach/io.h
- *  from arch/arm/mach-rpc/include/mach/io.h
- *
- * Copyright (C) 1997 Russell King
- *
- * Modifications:
- *  06-Dec-1997	RMK	Created.
- */
-#ifndef __ASM_ARM_ARCH_IO_H
-#define __ASM_ARM_ARCH_IO_H
-
-#include <mach/hardware.h>
-
-#define IO_SPACE_LIMIT 0xffffffff
-
-/*
- * GCC is totally crap at loading/storing data.  We try to persuade it
- * to do the right thing by using these whereever possible instead of
- * the above.
- */
-#define __arch_base_getb(b,o)			\
- ({						\
-	unsigned int v, r = (b);		\
-	__asm__ __volatile__(			\
-		"ldrb	%0, [%1, %2]"		\
-		: "=r" (v)			\
-		: "r" (r), "Ir" (o));		\
-	v;					\
- })
-
-#define __arch_base_getl(b,o)			\
- ({						\
-	unsigned int v, r = (b);		\
-	__asm__ __volatile__(			\
-		"ldr	%0, [%1, %2]"		\
-		: "=r" (v)			\
-		: "r" (r), "Ir" (o));		\
-	v;					\
- })
-
-#define __arch_base_putb(v,b,o)			\
- ({						\
-	unsigned int r = (b);			\
-	__asm__ __volatile__(			\
-		"strb	%0, [%1, %2]"		\
-		:				\
-		: "r" (v), "r" (r), "Ir" (o));	\
- })
-
-#define __arch_base_putl(v,b,o)			\
- ({						\
-	unsigned int r = (b);			\
-	__asm__ __volatile__(			\
-		"str	%0, [%1, %2]"		\
-		:				\
-		: "r" (v), "r" (r), "Ir" (o));	\
- })
-
-/*
- * We use two different types of addressing - PC style addresses, and ARM
- * addresses.  PC style accesses the PC hardware with the normal PC IO
- * addresses, eg 0x3f8 for serial#1.  ARM addresses are 0x80000000+
- * and are translated to the start of IO.  Note that all addresses are
- * shifted left!
- */
-#define __PORT_PCIO(x)	(!((x) & 0x80000000))
-
-/*
- * Dynamic IO functions - let the compiler
- * optimize the expressions
- */
-static inline void __outb (unsigned int value, unsigned int port)
-{
-	unsigned long temp;
-	__asm__ __volatile__(
-	"tst	%2, #0x80000000\n\t"
-	"mov	%0, %4\n\t"
-	"addeq	%0, %0, %3\n\t"
-	"strb	%1, [%0, %2, lsl #2]	@ outb"
-	: "=&r" (temp)
-	: "r" (value), "r" (port), "Ir" (PCIO_BASE - IO_BASE), "Ir" (IO_BASE)
-	: "cc");
-}
-
-static inline void __outw (unsigned int value, unsigned int port)
-{
-	unsigned long temp;
-	__asm__ __volatile__(
-	"tst	%2, #0x80000000\n\t"
-	"mov	%0, %4\n\t"
-	"addeq	%0, %0, %3\n\t"
-	"str	%1, [%0, %2, lsl #2]	@ outw"
-	: "=&r" (temp)
-	: "r" (value|value<<16), "r" (port), "Ir" (PCIO_BASE - IO_BASE), "Ir" (IO_BASE)
-	: "cc");
-}
-
-static inline void __outl (unsigned int value, unsigned int port)
-{
-	unsigned long temp;
-	__asm__ __volatile__(
-	"tst	%2, #0x80000000\n\t"
-	"mov	%0, %4\n\t"
-	"addeq	%0, %0, %3\n\t"
-	"str	%1, [%0, %2, lsl #2]	@ outl"
-	: "=&r" (temp)
-	: "r" (value), "r" (port), "Ir" (PCIO_BASE - IO_BASE), "Ir" (IO_BASE)
-	: "cc");
-}
-
-#define DECLARE_DYN_IN(sz,fnsuffix,instr)					\
-static inline unsigned sz __in##fnsuffix (unsigned int port)		\
-{										\
-	unsigned long temp, value;						\
-	__asm__ __volatile__(							\
-	"tst	%2, #0x80000000\n\t"						\
-	"mov	%0, %4\n\t"							\
-	"addeq	%0, %0, %3\n\t"							\
-	"ldr" instr "	%1, [%0, %2, lsl #2]	@ in" #fnsuffix			\
-	: "=&r" (temp), "=r" (value)						\
-	: "r" (port), "Ir" (PCIO_BASE - IO_BASE), "Ir" (IO_BASE)		\
-	: "cc");								\
-	return (unsigned sz)value;						\
-}
-
-static inline unsigned int __ioaddr (unsigned int port)			\
-{										\
-	if (__PORT_PCIO(port))							\
-		return (unsigned int)(PCIO_BASE + (port << 2));			\
-	else									\
-		return (unsigned int)(IO_BASE + (port << 2));			\
-}
-
-#define DECLARE_IO(sz,fnsuffix,instr)	\
-	DECLARE_DYN_IN(sz,fnsuffix,instr)
-
-DECLARE_IO(char,b,"b")
-DECLARE_IO(short,w,"")
-DECLARE_IO(int,l,"")
-
-#undef DECLARE_IO
-#undef DECLARE_DYN_IN
-
-/*
- * Constant address IO functions
- *
- * These have to be macros for the 'J' constraint to work -
- * +/-4096 immediate operand.
- */
-#define __outbc(value,port)							\
-({										\
-	if (__PORT_PCIO((port)))						\
-		__asm__ __volatile__(						\
-		"strb	%0, [%1, %2]	@ outbc"				\
-		: : "r" (value), "r" (PCIO_BASE), "Jr" ((port) << 2));		\
-	else									\
-		__asm__ __volatile__(						\
-		"strb	%0, [%1, %2]	@ outbc"				\
-		: : "r" (value), "r" (IO_BASE), "r" ((port) << 2));		\
-})
-
-#define __inbc(port)								\
-({										\
-	unsigned char result;							\
-	if (__PORT_PCIO((port)))						\
-		__asm__ __volatile__(						\
-		"ldrb	%0, [%1, %2]	@ inbc"					\
-		: "=r" (result) : "r" (PCIO_BASE), "Jr" ((port) << 2));		\
-	else									\
-		__asm__ __volatile__(						\
-		"ldrb	%0, [%1, %2]	@ inbc"					\
-		: "=r" (result) : "r" (IO_BASE), "r" ((port) << 2));		\
-	result;									\
-})
-
-#define __outwc(value,port)							\
-({										\
-	unsigned long v = value;						\
-	if (__PORT_PCIO((port)))						\
-		__asm__ __volatile__(						\
-		"str	%0, [%1, %2]	@ outwc"				\
-		: : "r" (v|v<<16), "r" (PCIO_BASE), "Jr" ((port) << 2));	\
-	else									\
-		__asm__ __volatile__(						\
-		"str	%0, [%1, %2]	@ outwc"				\
-		: : "r" (v|v<<16), "r" (IO_BASE), "r" ((port) << 2));		\
-})
-
-#define __inwc(port)								\
-({										\
-	unsigned short result;							\
-	if (__PORT_PCIO((port)))						\
-		__asm__ __volatile__(						\
-		"ldr	%0, [%1, %2]	@ inwc"					\
-		: "=r" (result) : "r" (PCIO_BASE), "Jr" ((port) << 2));		\
-	else									\
-		__asm__ __volatile__(						\
-		"ldr	%0, [%1, %2]	@ inwc"					\
-		: "=r" (result) : "r" (IO_BASE), "r" ((port) << 2));		\
-	result & 0xffff;							\
-})
-
-#define __outlc(value,port)							\
-({										\
-	unsigned long v = value;						\
-	if (__PORT_PCIO((port)))						\
-		__asm__ __volatile__(						\
-		"str	%0, [%1, %2]	@ outlc"				\
-		: : "r" (v), "r" (PCIO_BASE), "Jr" ((port) << 2));		\
-	else									\
-		__asm__ __volatile__(						\
-		"str	%0, [%1, %2]	@ outlc"				\
-		: : "r" (v), "r" (IO_BASE), "r" ((port) << 2));			\
-})
-
-#define __inlc(port)								\
-({										\
-	unsigned long result;							\
-	if (__PORT_PCIO((port)))						\
-		__asm__ __volatile__(						\
-		"ldr	%0, [%1, %2]	@ inlc"					\
-		: "=r" (result) : "r" (PCIO_BASE), "Jr" ((port) << 2));		\
-	else									\
-		__asm__ __volatile__(						\
-		"ldr	%0, [%1, %2]	@ inlc"					\
-		: "=r" (result) : "r" (IO_BASE), "r" ((port) << 2));		\
-	result;									\
-})
-
-#define __ioaddrc(port)								\
-	(__PORT_PCIO((port)) ? PCIO_BASE + ((port) << 2) : IO_BASE + ((port) << 2))
-
-#define inb(p)	 	(__builtin_constant_p((p)) ? __inbc(p)    : __inb(p))
-#define inw(p)	 	(__builtin_constant_p((p)) ? __inwc(p)    : __inw(p))
-#define inl(p)	 	(__builtin_constant_p((p)) ? __inlc(p)    : __inl(p))
-#define outb(v,p)	(__builtin_constant_p((p)) ? __outbc(v,p) : __outb(v,p))
-#define outw(v,p)	(__builtin_constant_p((p)) ? __outwc(v,p) : __outw(v,p))
-#define outl(v,p)	(__builtin_constant_p((p)) ? __outlc(v,p) : __outl(v,p))
-#define __ioaddr(p)	(__builtin_constant_p((p)) ? __ioaddr(p)  : __ioaddrc(p))
-/* the following macro is deprecated */
-#define ioaddr(port)			__ioaddr((port))
-
-#define insb(p,d,l)	__raw_readsb(__ioaddr(p),d,l)
-#define insw(p,d,l)	__raw_readsw(__ioaddr(p),d,l)
-
-#define outsb(p,d,l)	__raw_writesb(__ioaddr(p),d,l)
-#define outsw(p,d,l)	__raw_writesw(__ioaddr(p),d,l)
-
-/*
- * 1:1 mapping for ioremapped regions.
- */
-#define __mem_pci(x)	(x)
-
-#endif
diff --git a/arch/arm/mach-clps7500/include/mach/irq.h b/arch/arm/mach-clps7500/include/mach/irq.h
deleted file mode 100644
index d02fcf28ee05..000000000000
--- a/arch/arm/mach-clps7500/include/mach/irq.h
+++ /dev/null
@@ -1,32 +0,0 @@
-/*
- * arch/arm/mach-clps7500/include/mach/irq.h
- *
- * Copyright (C) 1996 Russell King
- * Copyright (C) 1999, 2001 Nexus Electronics Ltd.
- *
- * Changelog:
- *   10-10-1996	RMK	Brought up to date with arch-sa110eval
- *   22-08-1998	RMK	Restructured IRQ routines
- *   11-08-1999	PJB	Created ARM7500 version, derived from RiscPC code
- */
-
-#include <linux/io.h>
-#include <asm/hardware/iomd.h>
-
-static inline int fixup_irq(unsigned int irq)
-{
-	if (irq == IRQ_ISA) {
-		int isabits = *((volatile unsigned int *)0xe002b700);
-		if (isabits == 0) {
-			printk("Spurious ISA IRQ!\n");
-			return irq;
-		}
-		irq = IRQ_ISA_BASE;
-		while (!(isabits & 1)) {
-			irq++;
-			isabits >>= 1;
-		}
-	}
-
-	return irq;
-}
diff --git a/arch/arm/mach-clps7500/include/mach/irqs.h b/arch/arm/mach-clps7500/include/mach/irqs.h
deleted file mode 100644
index bee66b487f59..000000000000
--- a/arch/arm/mach-clps7500/include/mach/irqs.h
+++ /dev/null
@@ -1,66 +0,0 @@
-/*
- * arch/arm/mach-clps7500/include/mach/irqs.h
- *
- * Copyright (C) 1999 Nexus Electronics Ltd
- */
-
-#define IRQ_INT2		0
-#define IRQ_INT1		2
-#define IRQ_VSYNCPULSE		3
-#define IRQ_POWERON		4
-#define IRQ_TIMER0		5
-#define IRQ_TIMER1		6
-#define IRQ_FORCE		7
-#define IRQ_INT8		8
-#define IRQ_ISA			9
-#define IRQ_INT6		10
-#define IRQ_INT5		11
-#define IRQ_INT4		12
-#define IRQ_INT3		13
-#define IRQ_KEYBOARDTX		14
-#define IRQ_KEYBOARDRX		15
-
-#define IRQ_DMA0		16
-#define IRQ_DMA1		17
-#define IRQ_DMA2		18
-#define IRQ_DMA3		19
-#define IRQ_DMAS0		20
-#define IRQ_DMAS1		21
-
-#define IRQ_IOP0		24
-#define IRQ_IOP1		25
-#define IRQ_IOP2		26
-#define IRQ_IOP3		27
-#define IRQ_IOP4		28
-#define IRQ_IOP5		29
-#define IRQ_IOP6		30
-#define IRQ_IOP7		31
-
-#define IRQ_MOUSERX		40
-#define IRQ_MOUSETX		41
-#define IRQ_ADC			42
-#define IRQ_EVENT1		43
-#define IRQ_EVENT2		44
-
-#define IRQ_ISA_BASE		48
-#define IRQ_ISA_3		48
-#define IRQ_ISA_4		49
-#define IRQ_ISA_5		50
-#define IRQ_ISA_7		51
-#define IRQ_ISA_9		52
-#define IRQ_ISA_10		53
-#define IRQ_ISA_11		54
-#define IRQ_ISA_14		55	
-
-#define FIQ_INT9		0
-#define FIQ_INT5		1
-#define FIQ_INT6		4
-#define FIQ_INT8		6
-#define FIQ_FORCE		7
-
-/*
- * This is the offset of the FIQ "IRQ" numbers
- */
-#define FIQ_START		64
-
-#define IRQ_TIMER		IRQ_TIMER0
diff --git a/arch/arm/mach-clps7500/include/mach/memory.h b/arch/arm/mach-clps7500/include/mach/memory.h
deleted file mode 100644
index 87b32db470c8..000000000000
--- a/arch/arm/mach-clps7500/include/mach/memory.h
+++ /dev/null
@@ -1,43 +0,0 @@
-/*
- * arch/arm/mach-clps7500/include/mach/memory.h
- *
- * Copyright (c) 1996,1997,1998 Russell King.
- *
- * Changelog:
- *  20-Oct-1996	RMK	Created
- *  31-Dec-1997	RMK	Fixed definitions to reduce warnings
- *  11-Jan-1998	RMK	Uninlined to reduce hits on cache
- *  08-Feb-1998	RMK	Added __virt_to_bus and __bus_to_virt
- *  21-Mar-1999	RMK	Renamed to memory.h
- *		RMK	Added TASK_SIZE and PAGE_OFFSET
- */
-#ifndef __ASM_ARCH_MEMORY_H
-#define __ASM_ARCH_MEMORY_H
-
-/*
- * Physical DRAM offset.
- */
-#define PHYS_OFFSET	UL(0x10000000)
-
-/*
- * These are exactly the same on the RiscPC as the
- * physical memory view.
- */
-#define __virt_to_bus(x) __virt_to_phys(x)
-#define __bus_to_virt(x) __phys_to_virt(x)
-
-/*
- * Cache flushing area - ROM
- */
-#define FLUSH_BASE_PHYS		0x00000000
-#define FLUSH_BASE		0xdf000000
-
-/*
- * Sparsemem support.  Each section is a maximum of 64MB.  The sections
- * are offset by 128MB and can cover 128MB, so that gives us a maximum
- * of 29 physmem bits.
- */
-#define MAX_PHYSMEM_BITS	29
-#define SECTION_SIZE_BITS	26
-
-#endif
diff --git a/arch/arm/mach-clps7500/include/mach/system.h b/arch/arm/mach-clps7500/include/mach/system.h
deleted file mode 100644
index 6d325fbe8b08..000000000000
--- a/arch/arm/mach-clps7500/include/mach/system.h
+++ /dev/null
@@ -1,23 +0,0 @@
-/*
- * arch/arm/mach-clps7500/include/mach/system.h
- *
- * Copyright (c) 1999 Nexus Electronics Ltd.
- */
-#ifndef __ASM_ARCH_SYSTEM_H
-#define __ASM_ARCH_SYSTEM_H
-
-#include <linux/io.h>
-#include <asm/hardware/iomd.h>
-
-static inline void arch_idle(void)
-{
-	iomd_writeb(0, IOMD_SUSMODE);
-}
-
-#define arch_reset(mode)			\
-	do {					\
-		iomd_writeb(0, IOMD_ROMCR0);	\
-		cpu_reset(0);			\
-	} while (0)
-
-#endif
diff --git a/arch/arm/mach-clps7500/include/mach/timex.h b/arch/arm/mach-clps7500/include/mach/timex.h
deleted file mode 100644
index dfaa9b425757..000000000000
--- a/arch/arm/mach-clps7500/include/mach/timex.h
+++ /dev/null
@@ -1,13 +0,0 @@
-/*
- * arch/arm/mach-clps7500/include/mach/timex.h
- *
- * CL7500 architecture timex specifications
- *
- * Copyright (C) 1999 Nexus Electronics Ltd
- */
-
-/*
- * On the ARM7500, the clock ticks at 2MHz.
- */
-#define CLOCK_TICK_RATE		2000000
-
diff --git a/arch/arm/mach-clps7500/include/mach/uncompress.h b/arch/arm/mach-clps7500/include/mach/uncompress.h
deleted file mode 100644
index d7d0af4b49fc..000000000000
--- a/arch/arm/mach-clps7500/include/mach/uncompress.h
+++ /dev/null
@@ -1,35 +0,0 @@
-/*
- * arch/arm/mach-clps7500/include/mach/uncompress.h
- *
- * Copyright (C) 1999, 2000 Nexus Electronics Ltd.
- */
-#define BASE 0x03010000
-#define SERBASE (BASE + (0x2f8 << 2))
-
-static inline void putc(char c)
-{
-	while (!(*((volatile unsigned int *)(SERBASE + 0x14)) & 0x20))
-		barrier();
-
-	*((volatile unsigned int *)(SERBASE)) = c;
-}
-
-static inline void flush(void)
-{
-}
-
-static __inline__ void arch_decomp_setup(void)
-{
-	int baud = 3686400 / (9600 * 32);
-
-	*((volatile unsigned int *)(SERBASE + 0xC)) = 0x80;
-	*((volatile unsigned int *)(SERBASE + 0x0)) = baud & 0xff;
-	*((volatile unsigned int *)(SERBASE + 0x4)) = (baud & 0xff00) >> 8;
-	*((volatile unsigned int *)(SERBASE + 0xC)) = 3; /* 8 bits */
-	*((volatile unsigned int *)(SERBASE + 0x10)) = 3; /* DTR, RTS */
-}
-
-/*
- * nothing to do
- */
-#define arch_decomp_wdog()
diff --git a/arch/arm/mach-clps7500/include/mach/vmalloc.h b/arch/arm/mach-clps7500/include/mach/vmalloc.h
deleted file mode 100644
index 8fc5406d1b6d..000000000000
--- a/arch/arm/mach-clps7500/include/mach/vmalloc.h
+++ /dev/null
@@ -1,4 +0,0 @@
-/*
- * arch/arm/mach-clps7500/include/mach/vmalloc.h
- */
-#define VMALLOC_END       (PAGE_OFFSET + 0x1c000000)
diff --git a/arch/arm/mach-davinci/include/mach/dma.h b/arch/arm/mach-davinci/include/mach/dma.h
deleted file mode 100644
index 8e2f2d0ba667..000000000000
--- a/arch/arm/mach-davinci/include/mach/dma.h
+++ /dev/null
@@ -1,16 +0,0 @@
-/*
- * DaVinci DMA definitions
- *
- * Author: Kevin Hilman, MontaVista Software, Inc. <source@mvista.com>
- *
- * 2007 (c) MontaVista Software, Inc. This file is licensed under
- * the terms of the GNU General Public License version 2. This program
- * is licensed "as is" without any warranty of any kind, whether express
- * or implied.
- */
-#ifndef __ASM_ARCH_DMA_H
-#define __ASM_ARCH_DMA_H
-
-#define MAX_DMA_ADDRESS			0xffffffff
-
-#endif /* __ASM_ARCH_DMA_H */
diff --git a/arch/arm/mach-davinci/include/mach/io.h b/arch/arm/mach-davinci/include/mach/io.h
index b78ee9140496..a48795fd2417 100644
--- a/arch/arm/mach-davinci/include/mach/io.h
+++ b/arch/arm/mach-davinci/include/mach/io.h
@@ -29,8 +29,7 @@
  * We don't actually have real ISA nor PCI buses, but there is so many
  * drivers out there that might just work if we fake them...
  */
-#define PCIO_BASE               0
-#define __io(a)			((void __iomem *)(PCIO_BASE + (a)))
+#define __io(a)			__typesafe_io(a)
 #define __mem_pci(a)		(a)
 #define __mem_isa(a)		(a)
 
diff --git a/arch/arm/mach-davinci/include/mach/memory.h b/arch/arm/mach-davinci/include/mach/memory.h
index dd1625c23cf4..86c25c7f3ce3 100644
--- a/arch/arm/mach-davinci/include/mach/memory.h
+++ b/arch/arm/mach-davinci/include/mach/memory.h
@@ -52,13 +52,8 @@ __arch_adjust_zones(int node, unsigned long *size, unsigned long *holes)
         if ((meminfo.bank[0].size >> 20) > 128) __arch_adjust_zones(node, zone_size, holes)
 
 #define ISA_DMA_THRESHOLD	(PHYS_OFFSET + (128<<20) - 1)
+#define MAX_DMA_ADDRESS		(PAGE_OFFSET + (128<<20))
 
 #endif
 
-/*
- * Bus address is physical address
- */
-#define __virt_to_bus(x)	__virt_to_phys(x)
-#define __bus_to_virt(x)	__phys_to_virt(x)
-
 #endif /* __ASM_ARCH_MEMORY_H */
diff --git a/arch/arm/mach-davinci/include/mach/vmalloc.h b/arch/arm/mach-davinci/include/mach/vmalloc.h
index b98bd9e92fd6..ad51625b6609 100644
--- a/arch/arm/mach-davinci/include/mach/vmalloc.h
+++ b/arch/arm/mach-davinci/include/mach/vmalloc.h
@@ -8,7 +8,6 @@
  * is licensed "as is" without any warranty of any kind, whether express
  * or implied.
  */
-#include <asm/memory.h>
 #include <mach/io.h>
 
 /* Allow vmalloc range until the IO virtual range minus a 2M "hole" */
diff --git a/arch/arm/mach-ebsa110/include/mach/dma.h b/arch/arm/mach-ebsa110/include/mach/dma.h
deleted file mode 100644
index 780a04c8bbe9..000000000000
--- a/arch/arm/mach-ebsa110/include/mach/dma.h
+++ /dev/null
@@ -1,11 +0,0 @@
-/*
- *  arch/arm/mach-ebsa110/include/mach/dma.h
- *
- *  Copyright (C) 1997,1998 Russell King
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- *  EBSA110 DMA definitions
- */
diff --git a/arch/arm/mach-ebsa110/include/mach/memory.h b/arch/arm/mach-ebsa110/include/mach/memory.h
index eea4b75b657b..0ca66d080c69 100644
--- a/arch/arm/mach-ebsa110/include/mach/memory.h
+++ b/arch/arm/mach-ebsa110/include/mach/memory.h
@@ -22,13 +22,6 @@
 #define PHYS_OFFSET	UL(0x00000000)
 
 /*
- * We keep this 1:1 so that we don't interfere
- * with the PCMCIA memory regions
- */
-#define __virt_to_bus(x)	(x)
-#define __bus_to_virt(x)	(x)
-
-/*
  * Cache flushing area - SRAM
  */
 #define FLUSH_BASE_PHYS		0x40000000
diff --git a/arch/arm/mach-ep93xx/Kconfig b/arch/arm/mach-ep93xx/Kconfig
index 5a1b8c05c958..56bddcef6905 100644
--- a/arch/arm/mach-ep93xx/Kconfig
+++ b/arch/arm/mach-ep93xx/Kconfig
@@ -33,6 +33,12 @@ config MACH_EDB9307
 	  Say 'Y' here if you want your kernel to support the Cirrus
 	  Logic EDB9307 Evaluation Board.
 
+config MACH_EDB9307A
+	bool "Support Cirrus Logic EDB9307A"
+	help
+	  Say 'Y' here if you want your kernel to support the Cirrus
+	  Logic EDB9307A Evaluation Board.
+
 config MACH_EDB9312
 	bool "Support Cirrus Logic EDB9312"
 	help
diff --git a/arch/arm/mach-ep93xx/Makefile b/arch/arm/mach-ep93xx/Makefile
index c1252ca9648e..944e42d51646 100644
--- a/arch/arm/mach-ep93xx/Makefile
+++ b/arch/arm/mach-ep93xx/Makefile
@@ -10,6 +10,7 @@ obj-$(CONFIG_MACH_ADSSPHERE)	+= adssphere.o
 obj-$(CONFIG_MACH_EDB9302)	+= edb9302.o
 obj-$(CONFIG_MACH_EDB9302A)	+= edb9302a.o
 obj-$(CONFIG_MACH_EDB9307)	+= edb9307.o
+obj-$(CONFIG_MACH_EDB9307A)	+= edb9307a.o
 obj-$(CONFIG_MACH_EDB9312)	+= edb9312.o
 obj-$(CONFIG_MACH_EDB9315)	+= edb9315.o
 obj-$(CONFIG_MACH_EDB9315A)	+= edb9315a.o
diff --git a/arch/arm/mach-ep93xx/clock.c b/arch/arm/mach-ep93xx/clock.c
index 8c9f2491dccc..96049283a10a 100644
--- a/arch/arm/mach-ep93xx/clock.c
+++ b/arch/arm/mach-ep93xx/clock.c
@@ -16,11 +16,12 @@
 #include <linux/module.h>
 #include <linux/string.h>
 #include <linux/io.h>
+
+#include <asm/clkdev.h>
 #include <asm/div64.h>
 #include <mach/hardware.h>
 
 struct clk {
-	char		*name;
 	unsigned long	rate;
 	int		users;
 	u32		enable_reg;
@@ -28,53 +29,33 @@ struct clk {
 };
 
 static struct clk clk_uart = {
-	.name		= "UARTCLK",
 	.rate		= 14745600,
 };
-static struct clk clk_pll1 = {
-	.name		= "pll1",
-};
-static struct clk clk_f = {
-	.name		= "fclk",
-};
-static struct clk clk_h = {
-	.name		= "hclk",
-};
-static struct clk clk_p = {
-	.name		= "pclk",
-};
-static struct clk clk_pll2 = {
-	.name		= "pll2",
-};
+static struct clk clk_pll1;
+static struct clk clk_f;
+static struct clk clk_h;
+static struct clk clk_p;
+static struct clk clk_pll2;
 static struct clk clk_usb_host = {
-	.name		= "usb_host",
 	.enable_reg	= EP93XX_SYSCON_CLOCK_CONTROL,
 	.enable_mask	= EP93XX_SYSCON_CLOCK_USH_EN,
 };
 
-
-static struct clk *clocks[] = {
-	&clk_uart,
-	&clk_pll1,
-	&clk_f,
-	&clk_h,
-	&clk_p,
-	&clk_pll2,
-	&clk_usb_host,
+#define INIT_CK(dev,con,ck)					\
+	{ .dev_id = dev, .con_id = con, .clk = ck }
+
+static struct clk_lookup clocks[] = {
+	INIT_CK("apb:uart1", NULL, &clk_uart),
+	INIT_CK("apb:uart2", NULL, &clk_uart),
+	INIT_CK("apb:uart3", NULL, &clk_uart),
+	INIT_CK(NULL, "pll1", &clk_pll1),
+	INIT_CK(NULL, "fclk", &clk_f),
+	INIT_CK(NULL, "hclk", &clk_h),
+	INIT_CK(NULL, "pclk", &clk_p),
+	INIT_CK(NULL, "pll2", &clk_pll2),
+	INIT_CK(NULL, "usb_host", &clk_usb_host),
 };
 
-struct clk *clk_get(struct device *dev, const char *id)
-{
-	int i;
-
-	for (i = 0; i < ARRAY_SIZE(clocks); i++) {
-		if (!strcmp(clocks[i]->name, id))
-			return clocks[i];
-	}
-
-	return ERR_PTR(-ENOENT);
-}
-EXPORT_SYMBOL(clk_get);
 
 int clk_enable(struct clk *clk)
 {
@@ -106,12 +87,6 @@ unsigned long clk_get_rate(struct clk *clk)
 }
 EXPORT_SYMBOL(clk_get_rate);
 
-void clk_put(struct clk *clk)
-{
-}
-EXPORT_SYMBOL(clk_put);
-
-
 
 static char fclk_divisors[] = { 1, 2, 4, 8, 16, 1, 1, 1 };
 static char hclk_divisors[] = { 1, 2, 4, 5, 6, 8, 16, 32 };
@@ -138,6 +113,7 @@ static unsigned long calc_pll_rate(u32 config_word)
 static int __init ep93xx_clock_init(void)
 {
 	u32 value;
+	int i;
 
 	value = __raw_readl(EP93XX_SYSCON_CLOCK_SET1);
 	if (!(value & 0x00800000)) {			/* PLL1 bypassed?  */
@@ -165,6 +141,8 @@ static int __init ep93xx_clock_init(void)
 		clk_f.rate / 1000000, clk_h.rate / 1000000,
 		clk_p.rate / 1000000);
 
+	for (i = 0; i < ARRAY_SIZE(clocks); i++)
+		clkdev_add(&clocks[i]);
 	return 0;
 }
 arch_initcall(ep93xx_clock_init);
diff --git a/arch/arm/mach-ep93xx/core.c b/arch/arm/mach-ep93xx/core.c
index 48345fb34613..6d9152de6074 100644
--- a/arch/arm/mach-ep93xx/core.c
+++ b/arch/arm/mach-ep93xx/core.c
@@ -34,6 +34,8 @@
 #include <linux/amba/bus.h>
 #include <linux/amba/serial.h>
 #include <linux/io.h>
+#include <linux/i2c.h>
+#include <linux/i2c-gpio.h>
 
 #include <asm/types.h>
 #include <asm/setup.h>
@@ -153,12 +155,14 @@ static unsigned char gpio_int_unmasked[3];
 static unsigned char gpio_int_enabled[3];
 static unsigned char gpio_int_type1[3];
 static unsigned char gpio_int_type2[3];
+static unsigned char gpio_int_debouce[3];
 
 /* Port ordering is: A B F */
 static const u8 int_type1_register_offset[3]	= { 0x90, 0xac, 0x4c };
 static const u8 int_type2_register_offset[3]	= { 0x94, 0xb0, 0x50 };
 static const u8 eoi_register_offset[3]		= { 0x98, 0xb4, 0x54 };
 static const u8 int_en_register_offset[3]	= { 0x9c, 0xb8, 0x58 };
+static const u8 int_debounce_register_offset[3]	= { 0xa8, 0xc4, 0x64 };
 
 void ep93xx_gpio_update_int_params(unsigned port)
 {
@@ -181,6 +185,22 @@ void ep93xx_gpio_int_mask(unsigned line)
 	gpio_int_unmasked[line >> 3] &= ~(1 << (line & 7));
 }
 
+void ep93xx_gpio_int_debounce(unsigned int irq, int enable)
+{
+	int line = irq_to_gpio(irq);
+	int port = line >> 3;
+	int port_mask = 1 << (line & 7);
+
+	if (enable)
+		gpio_int_debouce[port] |= port_mask;
+	else
+		gpio_int_debouce[port] &= ~port_mask;
+
+	__raw_writeb(gpio_int_debouce[port],
+		EP93XX_GPIO_REG(int_debounce_register_offset[port]));
+}
+EXPORT_SYMBOL(ep93xx_gpio_int_debounce);
+
 /*************************************************************************
  * EP93xx IRQ handling
  *************************************************************************/
@@ -389,7 +409,7 @@ static struct amba_pl010_data ep93xx_uart_data = {
 
 static struct amba_device uart1_device = {
 	.dev		= {
-		.bus_id		= "apb:uart1",
+		.init_name	= "apb:uart1",
 		.platform_data	= &ep93xx_uart_data,
 	},
 	.res		= {
@@ -403,7 +423,7 @@ static struct amba_device uart1_device = {
 
 static struct amba_device uart2_device = {
 	.dev		= {
-		.bus_id		= "apb:uart2",
+		.init_name	= "apb:uart2",
 		.platform_data	= &ep93xx_uart_data,
 	},
 	.res		= {
@@ -417,7 +437,7 @@ static struct amba_device uart2_device = {
 
 static struct amba_device uart3_device = {
 	.dev		= {
-		.bus_id		= "apb:uart3",
+		.init_name	= "apb:uart3",
 		.platform_data	= &ep93xx_uart_data,
 	},
 	.res		= {
@@ -497,6 +517,26 @@ void __init ep93xx_register_eth(struct ep93xx_eth_data *data, int copy_addr)
 	platform_device_register(&ep93xx_eth_device);
 }
 
+static struct i2c_gpio_platform_data ep93xx_i2c_data = {
+	.sda_pin		= EP93XX_GPIO_LINE_EEDAT,
+	.sda_is_open_drain	= 0,
+	.scl_pin		= EP93XX_GPIO_LINE_EECLK,
+	.scl_is_open_drain	= 0,
+	.udelay			= 2,
+};
+
+static struct platform_device ep93xx_i2c_device = {
+	.name			= "i2c-gpio",
+	.id			= 0,
+	.dev.platform_data	= &ep93xx_i2c_data,
+};
+
+void __init ep93xx_register_i2c(struct i2c_board_info *devices, int num)
+{
+	i2c_register_board_info(0, devices, num);
+	platform_device_register(&ep93xx_i2c_device);
+}
+
 extern void ep93xx_gpio_init(void);
 
 void __init ep93xx_init_devices(void)
diff --git a/arch/arm/mach-ep93xx/edb9307a.c b/arch/arm/mach-ep93xx/edb9307a.c
new file mode 100644
index 000000000000..bbbe4c1fd502
--- /dev/null
+++ b/arch/arm/mach-ep93xx/edb9307a.c
@@ -0,0 +1,67 @@
+/*
+ * arch/arm/mach-ep93xx/edb9307a.c
+ * Cirrus Logic EDB9307A support.
+ *
+ * Copyright (C) 2008 H Hartley Sweeten <hsweeten@visionengravers.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or (at
+ * your option) any later version.
+ */
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/mm.h>
+#include <linux/sched.h>
+#include <linux/interrupt.h>
+#include <linux/ioport.h>
+#include <linux/mtd/physmap.h>
+#include <linux/platform_device.h>
+#include <linux/io.h>
+#include <mach/hardware.h>
+#include <asm/mach-types.h>
+#include <asm/mach/arch.h>
+
+static struct physmap_flash_data edb9307a_flash_data = {
+	.width		= 2,
+};
+
+static struct resource edb9307a_flash_resource = {
+	.start		= EP93XX_CS6_PHYS_BASE,
+	.end		= EP93XX_CS6_PHYS_BASE + SZ_16M - 1,
+	.flags		= IORESOURCE_MEM,
+};
+
+static struct platform_device edb9307a_flash = {
+	.name		= "physmap-flash",
+	.id		= 0,
+	.dev		= {
+		.platform_data	= &edb9307a_flash_data,
+	},
+	.num_resources	= 1,
+	.resource	= &edb9307a_flash_resource,
+};
+
+static struct ep93xx_eth_data edb9307a_eth_data = {
+	.phy_id		= 1,
+};
+
+static void __init edb9307a_init_machine(void)
+{
+	ep93xx_init_devices();
+	platform_device_register(&edb9307a_flash);
+
+	ep93xx_register_eth(&edb9307a_eth_data, 1);
+}
+
+MACHINE_START(EDB9307A, "Cirrus Logic EDB9307A Evaluation Board")
+	/* Maintainer: H Hartley Sweeten <hsweeten@visionengravers.com> */
+	.phys_io	= EP93XX_APB_PHYS_BASE,
+	.io_pg_offst	= ((EP93XX_APB_VIRT_BASE) >> 18) & 0xfffc,
+	.boot_params	= EP93XX_SDCE0_PHYS_BASE + 0x100,
+	.map_io		= ep93xx_map_io,
+	.init_irq	= ep93xx_init_irq,
+	.timer		= &ep93xx_timer,
+	.init_machine	= edb9307a_init_machine,
+MACHINE_END
diff --git a/arch/arm/mach-ep93xx/include/mach/clkdev.h b/arch/arm/mach-ep93xx/include/mach/clkdev.h
new file mode 100644
index 000000000000..04b37a89801c
--- /dev/null
+++ b/arch/arm/mach-ep93xx/include/mach/clkdev.h
@@ -0,0 +1,7 @@
+#ifndef __ASM_MACH_CLKDEV_H
+#define __ASM_MACH_CLKDEV_H
+
+#define __clk_get(clk) ({ 1; })
+#define __clk_put(clk) do { } while (0)
+
+#endif
diff --git a/arch/arm/mach-ep93xx/include/mach/dma.h b/arch/arm/mach-ep93xx/include/mach/dma.h
deleted file mode 100644
index d0fa9656e92f..000000000000
--- a/arch/arm/mach-ep93xx/include/mach/dma.h
+++ /dev/null
@@ -1,3 +0,0 @@
-/*
- * arch/arm/mach-ep93xx/include/mach/dma.h
- */
diff --git a/arch/arm/mach-ep93xx/include/mach/gpio.h b/arch/arm/mach-ep93xx/include/mach/gpio.h
index f7020414c5df..0a1498ae899a 100644
--- a/arch/arm/mach-ep93xx/include/mach/gpio.h
+++ b/arch/arm/mach-ep93xx/include/mach/gpio.h
@@ -99,6 +99,8 @@
 /* maximum value for irq capable line identifiers */
 #define EP93XX_GPIO_LINE_MAX_IRQ	EP93XX_GPIO_LINE_F(7)
 
+extern void ep93xx_gpio_int_debounce(unsigned int irq, int enable);
+
 /* new generic GPIO API - see Documentation/gpio.txt */
 
 #include <asm-generic/gpio.h>
diff --git a/arch/arm/mach-ep93xx/include/mach/io.h b/arch/arm/mach-ep93xx/include/mach/io.h
index 1ab9a90ad339..fd5f081cc8b7 100644
--- a/arch/arm/mach-ep93xx/include/mach/io.h
+++ b/arch/arm/mach-ep93xx/include/mach/io.h
@@ -4,5 +4,5 @@
 
 #define IO_SPACE_LIMIT		0xffffffff
 
-#define __io(p)			((void __iomem *)(p))
-#define __mem_pci(p)		(p)
+#define __io(p)		__typesafe_io(p)
+#define __mem_pci(p)	(p)
diff --git a/arch/arm/mach-ep93xx/include/mach/memory.h b/arch/arm/mach-ep93xx/include/mach/memory.h
index f1b633590752..5c80c3c8158d 100644
--- a/arch/arm/mach-ep93xx/include/mach/memory.h
+++ b/arch/arm/mach-ep93xx/include/mach/memory.h
@@ -7,8 +7,4 @@
 
 #define PHYS_OFFSET		UL(0x00000000)
 
-#define __bus_to_virt(x)	__phys_to_virt(x)
-#define __virt_to_bus(x)	__virt_to_phys(x)
-
-
 #endif
diff --git a/arch/arm/mach-ep93xx/include/mach/platform.h b/arch/arm/mach-ep93xx/include/mach/platform.h
index db2489d3bda7..88f7e88f152f 100644
--- a/arch/arm/mach-ep93xx/include/mach/platform.h
+++ b/arch/arm/mach-ep93xx/include/mach/platform.h
@@ -14,6 +14,7 @@ void ep93xx_map_io(void);
 void ep93xx_init_irq(void);
 void ep93xx_init_time(unsigned long);
 void ep93xx_register_eth(struct ep93xx_eth_data *data, int copy_addr);
+void ep93xx_register_i2c(struct i2c_board_info *devices, int num);
 void ep93xx_init_devices(void);
 extern struct sys_timer ep93xx_timer;
 
diff --git a/arch/arm/mach-footbridge/include/mach/hardware.h b/arch/arm/mach-footbridge/include/mach/hardware.h
index ffaea90486f9..51dd902043ad 100644
--- a/arch/arm/mach-footbridge/include/mach/hardware.h
+++ b/arch/arm/mach-footbridge/include/mach/hardware.h
@@ -12,8 +12,6 @@
 #ifndef __ASM_ARCH_HARDWARE_H
 #define __ASM_ARCH_HARDWARE_H
 
-#include <mach/memory.h>
-
 /*   Virtual      Physical	Size
  * 0xff800000	0x40000000	1MB	X-Bus
  * 0xff000000	0x7c000000	1MB	PCI I/O space
@@ -28,9 +26,6 @@
 #define XBUS_SIZE		0x00100000
 #define XBUS_BASE		0xff800000
 
-#define PCIO_SIZE		0x00100000
-#define PCIO_BASE		0xff000000
-
 #define ARMCSR_SIZE		0x00100000
 #define ARMCSR_BASE		0xfe000000
 
@@ -91,10 +86,11 @@
 #define CPLD_FLASH_WR_ENABLE	1
 
 #ifndef __ASSEMBLY__
-extern void gpio_modify_op(int mask, int set);
-extern void gpio_modify_io(int mask, int in);
-extern int  gpio_read(void);
-extern void cpld_modify(int mask, int set);
+extern spinlock_t nw_gpio_lock;
+extern void nw_gpio_modify_op(unsigned int mask, unsigned int set);
+extern void nw_gpio_modify_io(unsigned int mask, unsigned int in);
+extern unsigned int nw_gpio_read(void);
+extern void nw_cpld_modify(unsigned int mask, unsigned int set);
 #endif
 
 #define pcibios_assign_all_busses()	1
diff --git a/arch/arm/mach-footbridge/include/mach/io.h b/arch/arm/mach-footbridge/include/mach/io.h
index a7b066239996..101a4fe90bde 100644
--- a/arch/arm/mach-footbridge/include/mach/io.h
+++ b/arch/arm/mach-footbridge/include/mach/io.h
@@ -14,7 +14,8 @@
 #ifndef __ASM_ARM_ARCH_IO_H
 #define __ASM_ARM_ARCH_IO_H
 
-#include <mach/hardware.h>
+#define PCIO_SIZE		0x00100000
+#define PCIO_BASE		0xff000000
 
 #define IO_SPACE_LIMIT 0xffff
 
diff --git a/arch/arm/mach-footbridge/include/mach/dma.h b/arch/arm/mach-footbridge/include/mach/isa-dma.h
index 62afd213effb..5bd4a0d338a8 100644
--- a/arch/arm/mach-footbridge/include/mach/dma.h
+++ b/arch/arm/mach-footbridge/include/mach/isa-dma.h
@@ -1,5 +1,5 @@
 /*
- *  arch/arm/mach-footbridge/include/mach/dma.h
+ *  arch/arm/mach-footbridge/include/mach/isa-dma.h
  *
  *  Architecture DMA routines
  *
diff --git a/arch/arm/mach-footbridge/include/mach/memory.h b/arch/arm/mach-footbridge/include/mach/memory.h
index 6ae2f1a07ab9..cb16e59d87b6 100644
--- a/arch/arm/mach-footbridge/include/mach/memory.h
+++ b/arch/arm/mach-footbridge/include/mach/memory.h
@@ -30,9 +30,18 @@
 extern unsigned long __virt_to_bus(unsigned long);
 extern unsigned long __bus_to_virt(unsigned long);
 #endif
+#define __virt_to_bus	__virt_to_bus
+#define __bus_to_virt	__bus_to_virt
 
 #elif defined(CONFIG_FOOTBRIDGE_HOST)
 
+/*
+ * The footbridge is programmed to expose the system RAM at the corresponding
+ * address.  So, if PAGE_OFFSET is 0xc0000000, RAM appears at 0xe0000000.
+ * If 0x80000000, then its exposed at 0xa0000000 on the bus. etc.
+ * The only requirement is that the RAM isn't placed at bus address 0 which
+ * would clash with VGA cards.
+ */
 #define __virt_to_bus(x)	((x) - 0xe0000000)
 #define __bus_to_virt(x)	((x) + 0xe0000000)
 
diff --git a/arch/arm/mach-footbridge/netwinder-hw.c b/arch/arm/mach-footbridge/netwinder-hw.c
index 00b0ddcac283..4164d9020704 100644
--- a/arch/arm/mach-footbridge/netwinder-hw.c
+++ b/arch/arm/mach-footbridge/netwinder-hw.c
@@ -67,13 +67,14 @@ static inline void wb977_ww(int reg, int val)
 /*
  * This is a lock for accessing ports GP1_IO_BASE and GP2_IO_BASE
  */
-DEFINE_SPINLOCK(gpio_lock);
+DEFINE_SPINLOCK(nw_gpio_lock);
+EXPORT_SYMBOL(nw_gpio_lock);
 
 static unsigned int current_gpio_op;
 static unsigned int current_gpio_io;
 static unsigned int current_cpld;
 
-void gpio_modify_op(int mask, int set)
+void nw_gpio_modify_op(unsigned int mask, unsigned int set)
 {
 	unsigned int new_gpio, changed;
 
@@ -86,6 +87,7 @@ void gpio_modify_op(int mask, int set)
 	if (changed & 0xff00)
 		outb(new_gpio >> 8, GP2_IO_BASE);
 }
+EXPORT_SYMBOL(nw_gpio_modify_op);
 
 static inline void __gpio_modify_io(int mask, int in)
 {
@@ -118,7 +120,7 @@ static inline void __gpio_modify_io(int mask, int in)
 	}
 }
 
-void gpio_modify_io(int mask, int in)
+void nw_gpio_modify_io(unsigned int mask, unsigned int in)
 {
 	/* Open up the SuperIO chip */
 	wb977_open();
@@ -128,11 +130,13 @@ void gpio_modify_io(int mask, int in)
 	/* Close up the EFER gate */
 	wb977_close();
 }
+EXPORT_SYMBOL(nw_gpio_modify_io);
 
-int gpio_read(void)
+unsigned int nw_gpio_read(void)
 {
 	return inb(GP1_IO_BASE) | inb(GP2_IO_BASE) << 8;
 }
+EXPORT_SYMBOL(nw_gpio_read);
 
 /*
  * Initialise the Winbond W83977F global registers
@@ -322,9 +326,9 @@ static inline void wb977_init_gpio(void)
 	/*
 	 * Set Group1/Group2 outputs
 	 */
-	spin_lock_irqsave(&gpio_lock, flags);
-	gpio_modify_op(-1, GPIO_RED_LED | GPIO_FAN);
-	spin_unlock_irqrestore(&gpio_lock, flags);
+	spin_lock_irqsave(&nw_gpio_lock, flags);
+	nw_gpio_modify_op(-1, GPIO_RED_LED | GPIO_FAN);
+	spin_unlock_irqrestore(&nw_gpio_lock, flags);
 }
 
 /*
@@ -359,34 +363,35 @@ static void __init wb977_init(void)
 	wb977_close();
 }
 
-void cpld_modify(int mask, int set)
+void nw_cpld_modify(unsigned int mask, unsigned int set)
 {
 	int msk;
 
 	current_cpld = (current_cpld & ~mask) | set;
 
-	gpio_modify_io(GPIO_DATA | GPIO_IOCLK | GPIO_IOLOAD, 0);
-	gpio_modify_op(GPIO_IOLOAD, 0);
+	nw_gpio_modify_io(GPIO_DATA | GPIO_IOCLK | GPIO_IOLOAD, 0);
+	nw_gpio_modify_op(GPIO_IOLOAD, 0);
 
 	for (msk = 8; msk; msk >>= 1) {
 		int bit = current_cpld & msk;
 
-		gpio_modify_op(GPIO_DATA | GPIO_IOCLK, bit ? GPIO_DATA : 0);
-		gpio_modify_op(GPIO_IOCLK, GPIO_IOCLK);
+		nw_gpio_modify_op(GPIO_DATA | GPIO_IOCLK, bit ? GPIO_DATA : 0);
+		nw_gpio_modify_op(GPIO_IOCLK, GPIO_IOCLK);
 	}
 
-	gpio_modify_op(GPIO_IOCLK|GPIO_DATA, 0);
-	gpio_modify_op(GPIO_IOLOAD|GPIO_DSCLK, GPIO_IOLOAD|GPIO_DSCLK);
-	gpio_modify_op(GPIO_IOLOAD, 0);
+	nw_gpio_modify_op(GPIO_IOCLK|GPIO_DATA, 0);
+	nw_gpio_modify_op(GPIO_IOLOAD|GPIO_DSCLK, GPIO_IOLOAD|GPIO_DSCLK);
+	nw_gpio_modify_op(GPIO_IOLOAD, 0);
 }
+EXPORT_SYMBOL(nw_cpld_modify);
 
 static void __init cpld_init(void)
 {
 	unsigned long flags;
 
-	spin_lock_irqsave(&gpio_lock, flags);
-	cpld_modify(-1, CPLD_UNMUTE | CPLD_7111_DISABLE);
-	spin_unlock_irqrestore(&gpio_lock, flags);
+	spin_lock_irqsave(&nw_gpio_lock, flags);
+	nw_cpld_modify(-1, CPLD_UNMUTE | CPLD_7111_DISABLE);
+	spin_unlock_irqrestore(&nw_gpio_lock, flags);
 }
 
 static unsigned char rwa_unlock[] __initdata =
@@ -596,12 +601,6 @@ static void __init rwa010_init(void)
 	rwa010_soundblaster_reset();
 }
 
-EXPORT_SYMBOL(gpio_lock);
-EXPORT_SYMBOL(gpio_modify_op);
-EXPORT_SYMBOL(gpio_modify_io);
-EXPORT_SYMBOL(cpld_modify);
-EXPORT_SYMBOL(gpio_read);
-
 /*
  * Initialise any other hardware after we've got the PCI bus
  * initialised.  We may need the PCI bus to talk to this other
@@ -616,9 +615,9 @@ static int __init nw_hw_init(void)
 		cpld_init();
 		rwa010_init();
 
-		spin_lock_irqsave(&gpio_lock, flags);
-		gpio_modify_op(GPIO_RED_LED|GPIO_GREEN_LED, DEFAULT_LEDS);
-		spin_unlock_irqrestore(&gpio_lock, flags);
+		spin_lock_irqsave(&nw_gpio_lock, flags);
+		nw_gpio_modify_op(GPIO_RED_LED|GPIO_GREEN_LED, DEFAULT_LEDS);
+		spin_unlock_irqrestore(&nw_gpio_lock, flags);
 	}
 	return 0;
 }
diff --git a/arch/arm/mach-footbridge/netwinder-leds.c b/arch/arm/mach-footbridge/netwinder-leds.c
index d91a4f4a32dc..00269fe0be8a 100644
--- a/arch/arm/mach-footbridge/netwinder-leds.c
+++ b/arch/arm/mach-footbridge/netwinder-leds.c
@@ -32,7 +32,6 @@ static char led_state;
 static char hw_led_state;
 
 static DEFINE_SPINLOCK(leds_lock);
-extern spinlock_t gpio_lock;
 
 static void netwinder_leds_event(led_event_t evt)
 {
@@ -121,9 +120,9 @@ static void netwinder_leds_event(led_event_t evt)
 	spin_unlock_irqrestore(&leds_lock, flags);
 
 	if  (led_state & LED_STATE_ENABLED) {
-		spin_lock_irqsave(&gpio_lock, flags);
-		gpio_modify_op(GPIO_RED_LED | GPIO_GREEN_LED, hw_led_state);
-		spin_unlock_irqrestore(&gpio_lock, flags);
+		spin_lock_irqsave(&nw_gpio_lock, flags);
+		nw_gpio_modify_op(GPIO_RED_LED | GPIO_GREEN_LED, hw_led_state);
+		spin_unlock_irqrestore(&nw_gpio_lock, flags);
 	}
 }
 
diff --git a/arch/arm/mach-h720x/include/mach/io.h b/arch/arm/mach-h720x/include/mach/io.h
index 1dab74ce88c6..2c8659c21a93 100644
--- a/arch/arm/mach-h720x/include/mach/io.h
+++ b/arch/arm/mach-h720x/include/mach/io.h
@@ -14,11 +14,9 @@
 #ifndef __ASM_ARM_ARCH_IO_H
 #define __ASM_ARM_ARCH_IO_H
 
-#include <mach/hardware.h>
-
 #define IO_SPACE_LIMIT 0xffffffff
 
-#define __io(a)		((void __iomem *)(a))
+#define __io(a)		__typesafe_io(a)
 #define __mem_pci(a)	(a)
 
 #endif
diff --git a/arch/arm/mach-h720x/include/mach/dma.h b/arch/arm/mach-h720x/include/mach/isa-dma.h
index 0a9d86ee84fe..3eafb3f163c0 100644
--- a/arch/arm/mach-h720x/include/mach/dma.h
+++ b/arch/arm/mach-h720x/include/mach/isa-dma.h
@@ -1,5 +1,5 @@
 /*
- * arch/arm/mach-h720x/include/mach/dma.h
+ * arch/arm/mach-h720x/include/mach/isa-dma.h
  *
  * Architecture DMA routes
  *
@@ -8,13 +8,6 @@
 #ifndef __ASM_ARCH_DMA_H
 #define __ASM_ARCH_DMA_H
 
-/*
- * This is the maximum DMA address that can be DMAd to.
- * There should not be more than (0xd0000000 - 0xc0000000)
- * bytes of RAM.
- */
-#define MAX_DMA_ADDRESS		0xd0000000
-
 #if defined (CONFIG_CPU_H7201)
 #define MAX_DMA_CHANNELS	3
 #elif defined (CONFIG_CPU_H7202)
diff --git a/arch/arm/mach-h720x/include/mach/memory.h b/arch/arm/mach-h720x/include/mach/memory.h
index cb26f49cc4e1..ef4c1e26f18e 100644
--- a/arch/arm/mach-h720x/include/mach/memory.h
+++ b/arch/arm/mach-h720x/include/mach/memory.h
@@ -7,23 +7,13 @@
 #ifndef __ASM_ARCH_MEMORY_H
 #define __ASM_ARCH_MEMORY_H
 
-/*
- * Page offset:
- *    ( 0xc0000000UL )
- */
 #define PHYS_OFFSET	UL(0x40000000)
-
 /*
- * Virtual view <-> DMA view memory address translations
- * virt_to_bus: Used to translate the virtual address to an
- *              address suitable to be passed to set_dma_addr
- * bus_to_virt: Used to convert an address for DMA operations
- *              to an address that the kernel can use.
- *
- * There is something to do here later !, Mar 2000, Jungjun Kim
+ * This is the maximum DMA address that can be DMAd to.
+ * There should not be more than (0xd0000000 - 0xc0000000)
+ * bytes of RAM.
  */
-
-#define __virt_to_bus(x)	__virt_to_phys(x)
-#define __bus_to_virt(x)	__phys_to_virt(x)
+#define ISA_DMA_THRESHOLD	(PHYS_OFFSET + SZ_256M - 1)
+#define MAX_DMA_ADDRESS		(PAGE_OFFSET + SZ_256M)
 
 #endif
diff --git a/arch/arm/mach-imx/dma.c b/arch/arm/mach-imx/dma.c
index c10810c936b3..1536583eece0 100644
--- a/arch/arm/mach-imx/dma.c
+++ b/arch/arm/mach-imx/dma.c
@@ -28,10 +28,11 @@
 #include <linux/interrupt.h>
 #include <linux/errno.h>
 
+#include <asm/scatterlist.h>
 #include <asm/system.h>
 #include <asm/irq.h>
 #include <mach/hardware.h>
-#include <asm/dma.h>
+#include <mach/dma.h>
 #include <mach/imx-dma.h>
 
 struct imx_dma_channel imx_dma_channels[IMX_DMA_CHANNELS];
@@ -138,7 +139,7 @@ imx_dma_setup_sg_base(imx_dmach_t dma_ch,
 int
 imx_dma_setup_single(imx_dmach_t dma_ch, dma_addr_t dma_address,
 		     unsigned int dma_length, unsigned int dev_addr,
-		     dmamode_t dmamode)
+		     unsigned int dmamode)
 {
 	struct imx_dma_channel *imxdma = &imx_dma_channels[dma_ch];
 
@@ -223,7 +224,7 @@ imx_dma_setup_single(imx_dmach_t dma_ch, dma_addr_t dma_address,
 int
 imx_dma_setup_sg(imx_dmach_t dma_ch,
 		 struct scatterlist *sg, unsigned int sgcount, unsigned int dma_length,
-		 unsigned int dev_addr, dmamode_t dmamode)
+		 unsigned int dev_addr, unsigned int dmamode)
 {
 	int res;
 	struct imx_dma_channel *imxdma = &imx_dma_channels[dma_ch];
diff --git a/arch/arm/mach-imx/include/mach/imx-dma.h b/arch/arm/mach-imx/include/mach/imx-dma.h
index 44d89c35539a..bbe54df7f0de 100644
--- a/arch/arm/mach-imx/include/mach/imx-dma.h
+++ b/arch/arm/mach-imx/include/mach/imx-dma.h
@@ -18,7 +18,7 @@
  * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
  */
 
-#include <asm/dma.h>
+#include <mach/dma.h>
 
 #ifndef __ASM_ARCH_IMX_DMA_H
 #define __ASM_ARCH_IMX_DMA_H
@@ -48,7 +48,7 @@ struct imx_dma_channel {
 	void (*irq_handler) (int, void *);
 	void (*err_handler) (int, void *, int errcode);
 	void *data;
-	dmamode_t  dma_mode;
+	unsigned int  dma_mode;
 	struct scatterlist *sg;
 	unsigned int sgbc;
 	unsigned int sgcount;
@@ -66,14 +66,18 @@ extern struct imx_dma_channel imx_dma_channels[IMX_DMA_CHANNELS];
 /* The type to distinguish channel numbers parameter from ordinal int type */
 typedef int imx_dmach_t;
 
+#define DMA_MODE_READ		0
+#define DMA_MODE_WRITE		1
+#define DMA_MODE_MASK		1
+
 int
 imx_dma_setup_single(imx_dmach_t dma_ch, dma_addr_t dma_address,
-		unsigned int dma_length, unsigned int dev_addr, dmamode_t dmamode);
+		unsigned int dma_length, unsigned int dev_addr, unsigned int dmamode);
 
 int
 imx_dma_setup_sg(imx_dmach_t dma_ch,
 		 struct scatterlist *sg, unsigned int sgcount, unsigned int dma_length,
-		 unsigned int dev_addr, dmamode_t dmamode);
+		 unsigned int dev_addr, unsigned int dmamode);
 
 int
 imx_dma_setup_handlers(imx_dmach_t dma_ch,
diff --git a/arch/arm/mach-imx/include/mach/io.h b/arch/arm/mach-imx/include/mach/io.h
index c50c5fa6fb81..9e197ae4590f 100644
--- a/arch/arm/mach-imx/include/mach/io.h
+++ b/arch/arm/mach-imx/include/mach/io.h
@@ -20,11 +20,9 @@
 #ifndef __ASM_ARM_ARCH_IO_H
 #define __ASM_ARM_ARCH_IO_H
 
-#include <mach/hardware.h>
-
 #define IO_SPACE_LIMIT 0xffffffff
 
-#define __io(a)		((void __iomem *)(a))
+#define __io(a)		__typesafe_io(a)
 #define __mem_pci(a)	(a)
 
 #endif
diff --git a/arch/arm/mach-imx/include/mach/memory.h b/arch/arm/mach-imx/include/mach/memory.h
index 5c453063c0ed..a93df7cba694 100644
--- a/arch/arm/mach-imx/include/mach/memory.h
+++ b/arch/arm/mach-imx/include/mach/memory.h
@@ -23,14 +23,4 @@
 
 #define PHYS_OFFSET	UL(0x08000000)
 
-/*
- * Virtual view <-> DMA view memory address translations
- * virt_to_bus: Used to translate the virtual address to an
- *              address suitable to be passed to set_dma_addr
- * bus_to_virt: Used to convert an address for DMA operations
- *              to an address that the kernel can use.
- */
-#define __virt_to_bus(x)	(x - PAGE_OFFSET + PHYS_OFFSET)
-#define __bus_to_virt(x)	(x - PHYS_OFFSET + PAGE_OFFSET)
-
 #endif
diff --git a/arch/arm/mach-integrator/clock.c b/arch/arm/mach-integrator/clock.c
index 8d761fdd2ecd..989ecf5f5c46 100644
--- a/arch/arm/mach-integrator/clock.c
+++ b/arch/arm/mach-integrator/clock.c
@@ -10,42 +10,12 @@
  */
 #include <linux/module.h>
 #include <linux/kernel.h>
-#include <linux/list.h>
 #include <linux/errno.h>
-#include <linux/err.h>
-#include <linux/string.h>
 #include <linux/clk.h>
 #include <linux/mutex.h>
 
-#include <asm/hardware/icst525.h>
-
-#include "clock.h"
-
-static LIST_HEAD(clocks);
-static DEFINE_MUTEX(clocks_mutex);
-
-struct clk *clk_get(struct device *dev, const char *id)
-{
-	struct clk *p, *clk = ERR_PTR(-ENOENT);
-
-	mutex_lock(&clocks_mutex);
-	list_for_each_entry(p, &clocks, node) {
-		if (strcmp(id, p->name) == 0 && try_module_get(p->owner)) {
-			clk = p;
-			break;
-		}
-	}
-	mutex_unlock(&clocks_mutex);
-
-	return clk;
-}
-EXPORT_SYMBOL(clk_get);
-
-void clk_put(struct clk *clk)
-{
-	module_put(clk->owner);
-}
-EXPORT_SYMBOL(clk_put);
+#include <asm/clkdev.h>
+#include <mach/clkdev.h>
 
 int clk_enable(struct clk *clk)
 {
@@ -67,7 +37,6 @@ EXPORT_SYMBOL(clk_get_rate);
 long clk_round_rate(struct clk *clk, unsigned long rate)
 {
 	struct icst525_vco vco;
-
 	vco = icst525_khz_to_vco(clk->params, rate / 1000);
 	return icst525_khz(clk->params, vco) * 1000;
 }
@@ -76,56 +45,15 @@ EXPORT_SYMBOL(clk_round_rate);
 int clk_set_rate(struct clk *clk, unsigned long rate)
 {
 	int ret = -EIO;
+
 	if (clk->setvco) {
 		struct icst525_vco vco;
 
 		vco = icst525_khz_to_vco(clk->params, rate / 1000);
 		clk->rate = icst525_khz(clk->params, vco) * 1000;
-
-		printk("Clock %s: setting VCO reg params: S=%d R=%d V=%d\n",
-			clk->name, vco.s, vco.r, vco.v);
-
 		clk->setvco(clk, vco);
 		ret = 0;
 	}
-	return 0;
+	return ret;
 }
 EXPORT_SYMBOL(clk_set_rate);
-
-/*
- * These are fixed clocks.
- */
-static struct clk kmi_clk = {
-	.name	= "KMIREFCLK",
-	.rate	= 24000000,
-};
-
-static struct clk uart_clk = {
-	.name	= "UARTCLK",
-	.rate	= 14745600,
-};
-
-int clk_register(struct clk *clk)
-{
-	mutex_lock(&clocks_mutex);
-	list_add(&clk->node, &clocks);
-	mutex_unlock(&clocks_mutex);
-	return 0;
-}
-EXPORT_SYMBOL(clk_register);
-
-void clk_unregister(struct clk *clk)
-{
-	mutex_lock(&clocks_mutex);
-	list_del(&clk->node);
-	mutex_unlock(&clocks_mutex);
-}
-EXPORT_SYMBOL(clk_unregister);
-
-static int __init clk_init(void)
-{
-	clk_register(&kmi_clk);
-	clk_register(&uart_clk);
-	return 0;
-}
-arch_initcall(clk_init);
diff --git a/arch/arm/mach-integrator/clock.h b/arch/arm/mach-integrator/clock.h
index 09e6328ceba9..e69de29bb2d1 100644
--- a/arch/arm/mach-integrator/clock.h
+++ b/arch/arm/mach-integrator/clock.h
@@ -1,25 +0,0 @@
-/*
- *  linux/arch/arm/mach-integrator/clock.h
- *
- *  Copyright (C) 2004 ARM Limited.
- *  Written by Deep Blue Solutions Limited.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-struct module;
-struct icst525_params;
-
-struct clk {
-	struct list_head	node;
-	unsigned long		rate;
-	struct module		*owner;
-	const char		*name;
-	const struct icst525_params *params;
-	void			*data;
-	void			(*setvco)(struct clk *, struct icst525_vco vco);
-};
-
-int clk_register(struct clk *clk);
-void clk_unregister(struct clk *clk);
diff --git a/arch/arm/mach-integrator/core.c b/arch/arm/mach-integrator/core.c
index 595b7392ee4e..6f8872913073 100644
--- a/arch/arm/mach-integrator/core.c
+++ b/arch/arm/mach-integrator/core.c
@@ -21,6 +21,8 @@
 #include <linux/amba/serial.h>
 #include <linux/io.h>
 
+#include <asm/clkdev.h>
+#include <mach/clkdev.h>
 #include <mach/hardware.h>
 #include <asm/irq.h>
 #include <asm/hardware/arm_timer.h>
@@ -35,7 +37,7 @@ static struct amba_pl010_data integrator_uart_data;
 
 static struct amba_device rtc_device = {
 	.dev		= {
-		.bus_id	= "mb:15",
+		.init_name = "mb:15",
 	},
 	.res		= {
 		.start	= INTEGRATOR_RTC_BASE,
@@ -48,7 +50,7 @@ static struct amba_device rtc_device = {
 
 static struct amba_device uart0_device = {
 	.dev		= {
-		.bus_id	= "mb:16",
+		.init_name = "mb:16",
 		.platform_data = &integrator_uart_data,
 	},
 	.res		= {
@@ -62,7 +64,7 @@ static struct amba_device uart0_device = {
 
 static struct amba_device uart1_device = {
 	.dev		= {
-		.bus_id	= "mb:17",
+		.init_name = "mb:17",
 		.platform_data = &integrator_uart_data,
 	},
 	.res		= {
@@ -76,7 +78,7 @@ static struct amba_device uart1_device = {
 
 static struct amba_device kmi0_device = {
 	.dev		= {
-		.bus_id	= "mb:18",
+		.init_name = "mb:18",
 	},
 	.res		= {
 		.start	= KMI0_BASE,
@@ -89,7 +91,7 @@ static struct amba_device kmi0_device = {
 
 static struct amba_device kmi1_device = {
 	.dev		= {
-		.bus_id	= "mb:19",
+		.init_name = "mb:19",
 	},
 	.res		= {
 		.start	= KMI1_BASE,
@@ -108,10 +110,43 @@ static struct amba_device *amba_devs[] __initdata = {
 	&kmi1_device,
 };
 
+/*
+ * These are fixed clocks.
+ */
+static struct clk clk24mhz = {
+	.rate	= 24000000,
+};
+
+static struct clk uartclk = {
+	.rate	= 14745600,
+};
+
+static struct clk_lookup lookups[] __initdata = {
+	{	/* UART0 */
+		.dev_id		= "mb:16",
+		.clk		= &uartclk,
+	}, {	/* UART1 */
+		.dev_id		= "mb:17",
+		.clk		= &uartclk,
+	}, {	/* KMI0 */
+		.dev_id		= "mb:18",
+		.clk		= &clk24mhz,
+	}, {	/* KMI1 */
+		.dev_id		= "mb:19",
+		.clk		= &clk24mhz,
+	}, {	/* MMCI - IntegratorCP */
+		.dev_id		= "mb:1c",
+		.clk		= &uartclk,
+	}
+};
+
 static int __init integrator_init(void)
 {
 	int i;
 
+	for (i = 0; i < ARRAY_SIZE(lookups); i++)
+		clkdev_add(&lookups[i]);
+
 	for (i = 0; i < ARRAY_SIZE(amba_devs); i++) {
 		struct amba_device *d = amba_devs[i];
 		amba_device_register(d, &iomem_resource);
diff --git a/arch/arm/mach-integrator/impd1.c b/arch/arm/mach-integrator/impd1.c
index 172299a78302..0058c937719e 100644
--- a/arch/arm/mach-integrator/impd1.c
+++ b/arch/arm/mach-integrator/impd1.c
@@ -22,13 +22,13 @@
 #include <linux/amba/clcd.h>
 #include <linux/io.h>
 
+#include <asm/clkdev.h>
+#include <mach/clkdev.h>
 #include <asm/hardware/icst525.h>
 #include <mach/lm.h>
 #include <mach/impd1.h>
 #include <asm/sizes.h>
 
-#include "clock.h"
-
 static int module_id;
 
 module_param_named(lmid, module_id, int, 0444);
@@ -37,6 +37,7 @@ MODULE_PARM_DESC(lmid, "logic module stack position");
 struct impd1_module {
 	void __iomem	*base;
 	struct clk	vcos[2];
+	struct clk_lookup *clks[3];
 };
 
 static const struct icst525_params impd1_vco_params = {
@@ -339,9 +340,8 @@ static struct impd1_device impd1_devs[] = {
 	}
 };
 
-static const char *impd1_vconames[2] = {
-	"CLCDCLK",
-	"AUXVCO2",
+static struct clk fixed_14745600 = {
+	.rate = 14745600,
 };
 
 static int impd1_probe(struct lm_device *dev)
@@ -374,14 +374,20 @@ static int impd1_probe(struct lm_device *dev)
 
 	for (i = 0; i < ARRAY_SIZE(impd1->vcos); i++) {
 		impd1->vcos[i].owner = THIS_MODULE,
-		impd1->vcos[i].name = impd1_vconames[i],
 		impd1->vcos[i].params = &impd1_vco_params,
 		impd1->vcos[i].data = impd1,
 		impd1->vcos[i].setvco = impd1_setvco;
-
-		clk_register(&impd1->vcos[i]);
 	}
 
+	impd1->clks[0] = clkdev_alloc(&impd1->vcos[0], NULL, "lm%x:01000",
+					dev->id);
+	impd1->clks[1] = clkdev_alloc(&fixed_14745600, NULL, "lm%x:00100",
+					dev->id);
+	impd1->clks[2] = clkdev_alloc(&fixed_14745600, NULL, "lm%x:00200",
+					dev->id);
+	for (i = 0; i < ARRAY_SIZE(impd1->clks); i++)
+		clkdev_add(impd1->clks[i]);
+
 	for (i = 0; i < ARRAY_SIZE(impd1_devs); i++) {
 		struct impd1_device *idev = impd1_devs + i;
 		struct amba_device *d;
@@ -434,8 +440,8 @@ static void impd1_remove(struct lm_device *dev)
 
 	device_for_each_child(&dev->dev, NULL, impd1_remove_one);
 
-	for (i = 0; i < ARRAY_SIZE(impd1->vcos); i++)
-		clk_unregister(&impd1->vcos[i]);
+	for (i = 0; i < ARRAY_SIZE(impd1->clks); i++)
+		clkdev_drop(impd1->clks[i]);
 
 	lm_set_drvdata(dev, NULL);
 
diff --git a/arch/arm/mach-integrator/include/mach/clkdev.h b/arch/arm/mach-integrator/include/mach/clkdev.h
new file mode 100644
index 000000000000..9293e410832a
--- /dev/null
+++ b/arch/arm/mach-integrator/include/mach/clkdev.h
@@ -0,0 +1,25 @@
+#ifndef __ASM_MACH_CLKDEV_H
+#define __ASM_MACH_CLKDEV_H
+
+#include <linux/module.h>
+#include <asm/hardware/icst525.h>
+
+struct clk {
+	unsigned long		rate;
+	struct module		*owner;
+	const struct icst525_params *params;
+	void			*data;
+	void			(*setvco)(struct clk *, struct icst525_vco vco);
+};
+
+static inline int __clk_get(struct clk *clk)
+{
+	return try_module_get(clk->owner);
+}
+
+static inline void __clk_put(struct clk *clk)
+{
+	module_put(clk->owner);
+}
+
+#endif
diff --git a/arch/arm/mach-integrator/include/mach/dma.h b/arch/arm/mach-integrator/include/mach/dma.h
deleted file mode 100644
index fbebe85a2db7..000000000000
--- a/arch/arm/mach-integrator/include/mach/dma.h
+++ /dev/null
@@ -1,19 +0,0 @@
-/*
- *  arch/arm/mach-integrator/include/mach/dma.h
- *
- *  Copyright (C) 1997,1998 Russell King
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
- */
diff --git a/arch/arm/mach-integrator/include/mach/memory.h b/arch/arm/mach-integrator/include/mach/memory.h
index be7e63c21d25..2b2e7a110724 100644
--- a/arch/arm/mach-integrator/include/mach/memory.h
+++ b/arch/arm/mach-integrator/include/mach/memory.h
@@ -24,16 +24,9 @@
  * Physical DRAM offset.
  */
 #define PHYS_OFFSET	UL(0x00000000)
-#define BUS_OFFSET	UL(0x80000000)
 
-/*
- * Virtual view <-> DMA view memory address translations
- * virt_to_bus: Used to translate the virtual address to an
- *              address suitable to be passed to set_dma_addr
- * bus_to_virt: Used to convert an address for DMA operations
- *              to an address that the kernel can use.
- */
-#define __virt_to_bus(x)	(x - PAGE_OFFSET + BUS_OFFSET)
-#define __bus_to_virt(x)	(x - BUS_OFFSET + PAGE_OFFSET)
+#define BUS_OFFSET	UL(0x80000000)
+#define __virt_to_bus(x)	((x) - PAGE_OFFSET + BUS_OFFSET)
+#define __bus_to_virt(x)	((x) - BUS_OFFSET + PAGE_OFFSET)
 
 #endif
diff --git a/arch/arm/mach-integrator/integrator_cp.c b/arch/arm/mach-integrator/integrator_cp.c
index 88026ccd5ac9..4ac04055c2ea 100644
--- a/arch/arm/mach-integrator/integrator_cp.c
+++ b/arch/arm/mach-integrator/integrator_cp.c
@@ -21,6 +21,8 @@
 #include <linux/amba/clcd.h>
 #include <linux/io.h>
 
+#include <asm/clkdev.h>
+#include <mach/clkdev.h>
 #include <mach/hardware.h>
 #include <asm/irq.h>
 #include <asm/setup.h>
@@ -38,7 +40,6 @@
 #include <asm/mach/time.h>
 
 #include "common.h"
-#include "clock.h"
 
 #define INTCP_PA_MMC_BASE		0x1c000000
 #define INTCP_PA_AACI_BASE		0x1d000000
@@ -289,15 +290,16 @@ static void cp_auxvco_set(struct clk *clk, struct icst525_vco vco)
 	writel(0, CM_LOCK);
 }
 
-static struct clk cp_clcd_clk = {
-	.name	= "CLCDCLK",
+static struct clk cp_auxclk = {
 	.params	= &cp_auxvco_params,
 	.setvco = cp_auxvco_set,
 };
 
-static struct clk cp_mmci_clk = {
-	.name	= "MCLK",
-	.rate	= 14745600,
+static struct clk_lookup cp_lookups[] = {
+	{	/* CLCD */
+		.dev_id		= "mb:c0",
+		.clk		= &cp_auxclk,
+	},
 };
 
 /*
@@ -405,7 +407,7 @@ static struct mmc_platform_data mmc_data = {
 
 static struct amba_device mmc_device = {
 	.dev		= {
-		.bus_id	= "mb:1c",
+		.init_name = "mb:1c",
 		.platform_data = &mmc_data,
 	},
 	.res		= {
@@ -419,7 +421,7 @@ static struct amba_device mmc_device = {
 
 static struct amba_device aaci_device = {
 	.dev		= {
-		.bus_id	= "mb:1d",
+		.init_name = "mb:1d",
 	},
 	.res		= {
 		.start	= INTCP_PA_AACI_BASE,
@@ -530,7 +532,7 @@ static struct clcd_board clcd_data = {
 
 static struct amba_device clcd_device = {
 	.dev		= {
-		.bus_id	= "mb:c0",
+		.init_name = "mb:c0",
 		.coherent_dma_mask = ~0,
 		.platform_data = &clcd_data,
 	},
@@ -554,8 +556,8 @@ static void __init intcp_init(void)
 {
 	int i;
 
-	clk_register(&cp_clcd_clk);
-	clk_register(&cp_mmci_clk);
+	for (i = 0; i < ARRAY_SIZE(cp_lookups); i++)
+		clkdev_add(&cp_lookups[i]);
 
 	platform_add_devices(intcp_devs, ARRAY_SIZE(intcp_devs));
 
diff --git a/arch/arm/mach-iop13xx/include/mach/dma.h b/arch/arm/mach-iop13xx/include/mach/dma.h
deleted file mode 100644
index d79846fbb394..000000000000
--- a/arch/arm/mach-iop13xx/include/mach/dma.h
+++ /dev/null
@@ -1,3 +0,0 @@
-#ifndef _IOP13XX_DMA_H
-#define _IOP13XX_DMA_H
-#endif
diff --git a/arch/arm/mach-iop13xx/include/mach/memory.h b/arch/arm/mach-iop13xx/include/mach/memory.h
index b82602d529bf..e012bf13c955 100644
--- a/arch/arm/mach-iop13xx/include/mach/memory.h
+++ b/arch/arm/mach-iop13xx/include/mach/memory.h
@@ -16,18 +16,6 @@
 #define IOP13XX_PMMR_P_START (IOP13XX_PMMR_PHYS_MEM_BASE)
 #define IOP13XX_PMMR_P_END   (IOP13XX_PMMR_PHYS_MEM_BASE + IOP13XX_PMMR_SIZE)
 
-/*
- * Virtual view <-> PCI DMA view memory address translations
- * virt_to_bus: Used to translate the virtual address to an
- *		address suitable to be passed to set_dma_addr
- * bus_to_virt: Used to convert an address for DMA operations
- *		to an address that the kernel can use.
- */
-
-/* RAM has 1:1 mapping on the PCIe/x Busses */
-#define __virt_to_bus(x)	(__virt_to_phys(x))
-#define __bus_to_virt(x)	(__phys_to_virt(x))
-
 static inline dma_addr_t __virt_to_lbus(unsigned long x)
 {
 	return x + IOP13XX_PMMR_PHYS_MEM_BASE - IOP13XX_PMMR_VIRT_MEM_BASE;
@@ -55,7 +43,7 @@ static inline unsigned long __lbus_to_virt(dma_addr_t x)
 		if (is_lbus_device(dev) && __is_lbus_dma(__dma))	\
 			__virt = __lbus_to_virt(__dma);			\
 		else							\
-			__virt = __bus_to_virt(__dma);			\
+			__virt = __phys_to_virt(__dma);			\
 		(void *)__virt;						\
 	})
 
@@ -66,7 +54,7 @@ static inline unsigned long __lbus_to_virt(dma_addr_t x)
 		if (is_lbus_device(dev) && __is_lbus_virt(__virt))	\
 			__dma = __virt_to_lbus(__virt);			\
 		else							\
-			__dma = __virt_to_bus(__virt);			\
+			__dma = __virt_to_phys(__virt);			\
 		__dma;							\
 	})
 
diff --git a/arch/arm/mach-iop13xx/include/mach/timex.h b/arch/arm/mach-iop13xx/include/mach/timex.h
index 5b1f1c8a8270..45fb2745bb54 100644
--- a/arch/arm/mach-iop13xx/include/mach/timex.h
+++ b/arch/arm/mach-iop13xx/include/mach/timex.h
@@ -1,3 +1 @@
-#include <mach/hardware.h>
-
 #define CLOCK_TICK_RATE (100 * HZ)
diff --git a/arch/arm/mach-iop32x/include/mach/dma.h b/arch/arm/mach-iop32x/include/mach/dma.h
deleted file mode 100644
index f8bd817f205d..000000000000
--- a/arch/arm/mach-iop32x/include/mach/dma.h
+++ /dev/null
@@ -1,9 +0,0 @@
-/*
- * arch/arm/mach-iop32x/include/mach/dma.h
- *
- * Copyright (C) 2004 Intel Corp.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
diff --git a/arch/arm/mach-iop32x/include/mach/io.h b/arch/arm/mach-iop32x/include/mach/io.h
index ce54705ba3d4..339e5854728b 100644
--- a/arch/arm/mach-iop32x/include/mach/io.h
+++ b/arch/arm/mach-iop32x/include/mach/io.h
@@ -11,7 +11,7 @@
 #ifndef __IO_H
 #define __IO_H
 
-#include <mach/hardware.h>
+#include <asm/hardware/iop3xx.h>
 
 extern void __iomem *__iop3xx_ioremap(unsigned long cookie, size_t size,
 	unsigned int mtype);
diff --git a/arch/arm/mach-iop32x/include/mach/memory.h b/arch/arm/mach-iop32x/include/mach/memory.h
index 42cd4bf3148c..c30f6450ad50 100644
--- a/arch/arm/mach-iop32x/include/mach/memory.h
+++ b/arch/arm/mach-iop32x/include/mach/memory.h
@@ -5,22 +5,9 @@
 #ifndef __MEMORY_H
 #define __MEMORY_H
 
-#include <mach/hardware.h>
-
 /*
  * Physical DRAM offset.
  */
 #define PHYS_OFFSET	UL(0xa0000000)
 
-/*
- * Virtual view <-> PCI DMA view memory address translations
- * virt_to_bus: Used to translate the virtual address to an
- *		address suitable to be passed to set_dma_addr
- * bus_to_virt: Used to convert an address for DMA operations
- *		to an address that the kernel can use.
- */
-#define __virt_to_bus(x)	(__virt_to_phys(x))
-#define __bus_to_virt(x)	(__phys_to_virt(x))
-
-
 #endif
diff --git a/arch/arm/mach-iop32x/include/mach/system.h b/arch/arm/mach-iop32x/include/mach/system.h
index 20f923e54f46..32d9e5b0a28d 100644
--- a/arch/arm/mach-iop32x/include/mach/system.h
+++ b/arch/arm/mach-iop32x/include/mach/system.h
@@ -7,8 +7,9 @@
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
  */
-
 #include <asm/mach-types.h>
+#include <asm/hardware/iop3xx.h>
+#include <mach/n2100.h>
 
 static inline void arch_idle(void)
 {
diff --git a/arch/arm/mach-iop32x/include/mach/timex.h b/arch/arm/mach-iop32x/include/mach/timex.h
index a541afced3cb..7262ab81419d 100644
--- a/arch/arm/mach-iop32x/include/mach/timex.h
+++ b/arch/arm/mach-iop32x/include/mach/timex.h
@@ -3,7 +3,4 @@
  *
  * IOP32x architecture timex specifications
  */
-
-#include <mach/hardware.h>
-
 #define CLOCK_TICK_RATE		(100 * HZ)
diff --git a/arch/arm/mach-iop33x/include/mach/dma.h b/arch/arm/mach-iop33x/include/mach/dma.h
deleted file mode 100644
index d8b42232931d..000000000000
--- a/arch/arm/mach-iop33x/include/mach/dma.h
+++ /dev/null
@@ -1,9 +0,0 @@
-/*
- * arch/arm/mach-iop33x/include/mach/dma.h
- *
- * Copyright (C) 2004 Intel Corp.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
diff --git a/arch/arm/mach-iop33x/include/mach/io.h b/arch/arm/mach-iop33x/include/mach/io.h
index 158874631217..e99a7ed6d050 100644
--- a/arch/arm/mach-iop33x/include/mach/io.h
+++ b/arch/arm/mach-iop33x/include/mach/io.h
@@ -11,7 +11,7 @@
 #ifndef __IO_H
 #define __IO_H
 
-#include <mach/hardware.h>
+#include <asm/hardware/iop3xx.h>
 
 extern void __iomem *__iop3xx_ioremap(unsigned long cookie, size_t size,
 	unsigned int mtype);
diff --git a/arch/arm/mach-iop33x/include/mach/memory.h b/arch/arm/mach-iop33x/include/mach/memory.h
index 2cef0bbb354f..a30a96aa6d2d 100644
--- a/arch/arm/mach-iop33x/include/mach/memory.h
+++ b/arch/arm/mach-iop33x/include/mach/memory.h
@@ -5,22 +5,9 @@
 #ifndef __MEMORY_H
 #define __MEMORY_H
 
-#include <mach/hardware.h>
-
 /*
  * Physical DRAM offset.
  */
 #define PHYS_OFFSET	UL(0x00000000)
 
-/*
- * Virtual view <-> PCI DMA view memory address translations
- * virt_to_bus: Used to translate the virtual address to an
- *		address suitable to be passed to set_dma_addr
- * bus_to_virt: Used to convert an address for DMA operations
- *		to an address that the kernel can use.
- */
-#define __virt_to_bus(x)	(__virt_to_phys(x))
-#define __bus_to_virt(x)	(__phys_to_virt(x))
-
-
 #endif
diff --git a/arch/arm/mach-iop33x/include/mach/system.h b/arch/arm/mach-iop33x/include/mach/system.h
index 7bf3bfb49446..0cb3ad862acd 100644
--- a/arch/arm/mach-iop33x/include/mach/system.h
+++ b/arch/arm/mach-iop33x/include/mach/system.h
@@ -7,6 +7,7 @@
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
  */
+#include <asm/hardware/iop3xx.h>
 
 static inline void arch_idle(void)
 {
diff --git a/arch/arm/mach-iop33x/include/mach/timex.h b/arch/arm/mach-iop33x/include/mach/timex.h
index c75760844d49..54c589091d6e 100644
--- a/arch/arm/mach-iop33x/include/mach/timex.h
+++ b/arch/arm/mach-iop33x/include/mach/timex.h
@@ -3,7 +3,4 @@
  *
  * IOP3xx architecture timex specifications
  */
-
-#include <mach/hardware.h>
-
 #define CLOCK_TICK_RATE		(100 * HZ)
diff --git a/arch/arm/mach-ixp2000/include/mach/dma.h b/arch/arm/mach-ixp2000/include/mach/dma.h
deleted file mode 100644
index 26063d60f622..000000000000
--- a/arch/arm/mach-ixp2000/include/mach/dma.h
+++ /dev/null
@@ -1,9 +0,0 @@
-/*
- * arch/arm/mach-ixp2000/include/mach/dma.h
- *
- * Copyright (C) 2002 Intel Corp.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
diff --git a/arch/arm/mach-ixp2000/include/mach/memory.h b/arch/arm/mach-ixp2000/include/mach/memory.h
index 241529a7c52d..aee7eb8a71b2 100644
--- a/arch/arm/mach-ixp2000/include/mach/memory.h
+++ b/arch/arm/mach-ixp2000/include/mach/memory.h
@@ -15,13 +15,6 @@
 
 #define PHYS_OFFSET	UL(0x00000000)
 
-/*
- * Virtual view <-> DMA view memory address translations
- * virt_to_bus: Used to translate the virtual address to an
- *		address suitable to be passed to set_dma_addr
- * bus_to_virt: Used to convert an address for DMA operations
- *		to an address that the kernel can use.
- */
 #include <mach/ixp2000-regs.h>
 
 #define __virt_to_bus(v) \
diff --git a/arch/arm/mach-ixp23xx/include/mach/dma.h b/arch/arm/mach-ixp23xx/include/mach/dma.h
deleted file mode 100644
index 8886544b93f7..000000000000
--- a/arch/arm/mach-ixp23xx/include/mach/dma.h
+++ /dev/null
@@ -1,3 +0,0 @@
-/*
- * arch/arm/mach-ixp23xx/include/mach/dma.h
- */
diff --git a/arch/arm/mach-ixp23xx/include/mach/io.h b/arch/arm/mach-ixp23xx/include/mach/io.h
index 305ea1808c71..fd9ef8e519f7 100644
--- a/arch/arm/mach-ixp23xx/include/mach/io.h
+++ b/arch/arm/mach-ixp23xx/include/mach/io.h
@@ -20,8 +20,6 @@
 #define __io(p)		((void __iomem*)((p) + IXP23XX_PCI_IO_VIRT))
 #define __mem_pci(a)	(a)
 
-#include <linux/kernel.h>	/* For BUG */
-
 static inline void __iomem *
 ixp23xx_ioremap(unsigned long addr, unsigned long size, unsigned int mtype)
 {
diff --git a/arch/arm/mach-ixp23xx/include/mach/memory.h b/arch/arm/mach-ixp23xx/include/mach/memory.h
index 9d40115f7ebe..fdd138706c70 100644
--- a/arch/arm/mach-ixp23xx/include/mach/memory.h
+++ b/arch/arm/mach-ixp23xx/include/mach/memory.h
@@ -19,16 +19,6 @@
  */
 #define PHYS_OFFSET		(0x00000000)
 
-
-/*
- * Virtual view <-> DMA view memory address translations
- * virt_to_bus: Used to translate the virtual address to an
- *		address suitable to be passed to set_dma_addr
- * bus_to_virt: Used to convert an address for DMA operations
- *		to an address that the kernel can use.
- */
-#ifndef __ASSEMBLY__
-
 #define __virt_to_bus(v)						\
 	({ unsigned int ret;						\
 	ret = ((__virt_to_phys(v) - 0x00000000) +			\
@@ -43,6 +33,3 @@
 #define arch_is_coherent()	1
 
 #endif
-
-
-#endif
diff --git a/arch/arm/mach-ixp4xx/include/mach/dma.h b/arch/arm/mach-ixp4xx/include/mach/dma.h
deleted file mode 100644
index 00c5070c0201..000000000000
--- a/arch/arm/mach-ixp4xx/include/mach/dma.h
+++ /dev/null
@@ -1,21 +0,0 @@
-/*
- * arch/arm/mach-ixp4xx/include/mach/dma.h
- *
- * Copyright (C) 2001-2004 MontaVista Software, Inc.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- */
-#ifndef __ASM_ARCH_DMA_H
-#define __ASM_ARCH_DMA_H
-
-#include <linux/device.h>
-#include <asm/page.h>
-#include <asm/sizes.h>
-#include <mach/hardware.h>
-
-#define MAX_DMA_ADDRESS		(PAGE_OFFSET + SZ_64M)
-
-#endif /* _ASM_ARCH_DMA_H */
diff --git a/arch/arm/mach-ixp4xx/include/mach/io.h b/arch/arm/mach-ixp4xx/include/mach/io.h
index 319948e31bec..ce63048d45eb 100644
--- a/arch/arm/mach-ixp4xx/include/mach/io.h
+++ b/arch/arm/mach-ixp4xx/include/mach/io.h
@@ -49,8 +49,6 @@ extern int ixp4xx_pci_write(u32 addr, u32 cmd, u32 data);
 
 #else
 
-#include <linux/mm.h>
-
 /*
  * In the case of using indirect PCI, we simply return the actual PCI
  * address and our read/write implementation use that to drive the 
@@ -241,7 +239,7 @@ __ixp4xx_readsl(const volatile void __iomem *bus_addr, u32 *vaddr, u32 count)
 
 #ifndef CONFIG_PCI
 
-#define	__io(v)		v
+#define	__io(v)		__typesafe_io(v)
 
 #else
 
diff --git a/arch/arm/mach-ixp4xx/include/mach/memory.h b/arch/arm/mach-ixp4xx/include/mach/memory.h
index c4d2830ac987..98f5e5e20980 100644
--- a/arch/arm/mach-ixp4xx/include/mach/memory.h
+++ b/arch/arm/mach-ixp4xx/include/mach/memory.h
@@ -22,19 +22,8 @@ void ixp4xx_adjust_zones(int node, unsigned long *size, unsigned long *holes);
 	ixp4xx_adjust_zones(node, size, holes)
 
 #define ISA_DMA_THRESHOLD (SZ_64M - 1)
+#define MAX_DMA_ADDRESS		(PAGE_OFFSET + SZ_64M)
 
 #endif
 
-/*
- * Virtual view <-> DMA view memory address translations
- * virt_to_bus: Used to translate the virtual address to an
- *		address suitable to be passed to set_dma_addr
- * bus_to_virt: Used to convert an address for DMA operations
- *		to an address that the kernel can use.
- *
- * These are dummies for now.
- */
-#define __virt_to_bus(x)	 __virt_to_phys(x)
-#define __bus_to_virt(x)	 __phys_to_virt(x)
-
 #endif
diff --git a/arch/arm/mach-kirkwood/include/mach/dma.h b/arch/arm/mach-kirkwood/include/mach/dma.h
deleted file mode 100644
index 40a8c178f10d..000000000000
--- a/arch/arm/mach-kirkwood/include/mach/dma.h
+++ /dev/null
@@ -1 +0,0 @@
-/* empty */
diff --git a/arch/arm/mach-kirkwood/include/mach/memory.h b/arch/arm/mach-kirkwood/include/mach/memory.h
index b5fb34bdccd5..45431e131465 100644
--- a/arch/arm/mach-kirkwood/include/mach/memory.h
+++ b/arch/arm/mach-kirkwood/include/mach/memory.h
@@ -7,8 +7,4 @@
 
 #define PHYS_OFFSET		UL(0x00000000)
 
-#define __virt_to_bus(x)	__virt_to_phys(x)
-#define __bus_to_virt(x)	__phys_to_virt(x)
-
-
 #endif
diff --git a/arch/arm/mach-ks8695/include/mach/dma.h b/arch/arm/mach-ks8695/include/mach/dma.h
deleted file mode 100644
index 561206280089..000000000000
--- a/arch/arm/mach-ks8695/include/mach/dma.h
+++ /dev/null
@@ -1,17 +0,0 @@
-/*
- * arch/arm/mach-ks8695/include/mach/dma.h
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
- */
diff --git a/arch/arm/mach-ks8695/include/mach/io.h b/arch/arm/mach-ks8695/include/mach/io.h
index f364f24ffe1e..a7a63ac3ba4e 100644
--- a/arch/arm/mach-ks8695/include/mach/io.h
+++ b/arch/arm/mach-ks8695/include/mach/io.h
@@ -13,7 +13,7 @@
 
 #define IO_SPACE_LIMIT		0xffffffff
 
-#define __io(a)			((void __iomem *)(a))
-#define __mem_pci(a)		(a)
+#define __io(a)		__typesafe_io(a)
+#define __mem_pci(a)	(a)
 
 #endif
diff --git a/arch/arm/mach-ks8695/include/mach/memory.h b/arch/arm/mach-ks8695/include/mach/memory.h
index 8fbc4c76c38b..6d5887cf5742 100644
--- a/arch/arm/mach-ks8695/include/mach/memory.h
+++ b/arch/arm/mach-ks8695/include/mach/memory.h
@@ -37,11 +37,6 @@ extern struct bus_type platform_bus_type;
 					(dma_addr_t)__virt_to_phys(x) : (dma_addr_t)__virt_to_bus(x); })
 #define __arch_page_to_dma(dev, x)	__arch_virt_to_dma(dev, page_address(x))
 
-#else
-
-#define __virt_to_bus(x)	__virt_to_phys(x)
-#define __bus_to_virt(x)	__phys_to_virt(x)
-
 #endif
 
 #endif
diff --git a/arch/arm/mach-l7200/include/mach/dma.h b/arch/arm/mach-l7200/include/mach/dma.h
deleted file mode 100644
index c7e48bd4590c..000000000000
--- a/arch/arm/mach-l7200/include/mach/dma.h
+++ /dev/null
@@ -1,23 +0,0 @@
-/*
- * arch/arm/mach-l7200/include/mach/dma.h
- *
- * Copyright (C) 2000 Steve Hill (sjhill@cotw.com)
- *
- * Changelog:
- *  08-29-2000	SJH	Created
- */
-#ifndef __ASM_ARCH_DMA_H
-#define __ASM_ARCH_DMA_H
-
-/* DMA is not yet implemented! It should be the same as acorn, copy over.. */
-
-/*
- * This is the maximum DMA address that can be DMAd to.
- * There should not be more than (0xd0000000 - 0xc0000000)
- * bytes of RAM.
- */
-#define MAX_DMA_ADDRESS         0xd0000000
-
-#define DMA_S0                  0
-
-#endif /* _ASM_ARCH_DMA_H */
diff --git a/arch/arm/mach-l7200/include/mach/io.h b/arch/arm/mach-l7200/include/mach/io.h
index d432ba9e5dff..a770a89fb708 100644
--- a/arch/arm/mach-l7200/include/mach/io.h
+++ b/arch/arm/mach-l7200/include/mach/io.h
@@ -10,18 +10,12 @@
 #ifndef __ASM_ARM_ARCH_IO_H
 #define __ASM_ARM_ARCH_IO_H
 
-#include <mach/hardware.h>
-
 #define IO_SPACE_LIMIT 0xffffffff
 
 /*
  * There are not real ISA nor PCI buses, so we fake it.
  */
-static inline void __iomem *__io(unsigned long addr)
-{
-	return (void __iomem *)addr;
-}
-#define __io(a)	__io(a)
-#define __mem_pci(a)		(a)
+#define __io(a)		__typesafe_io(a)
+#define __mem_pci(a)	(a)
 
 #endif
diff --git a/arch/arm/mach-l7200/include/mach/memory.h b/arch/arm/mach-l7200/include/mach/memory.h
index f338cf3ffd93..9fb40ed2f03b 100644
--- a/arch/arm/mach-l7200/include/mach/memory.h
+++ b/arch/arm/mach-l7200/include/mach/memory.h
@@ -17,9 +17,6 @@
  */
 #define PHYS_OFFSET     UL(0xf0000000)
 
-#define __virt_to_bus(x) __virt_to_phys(x)
-#define __bus_to_virt(x) __phys_to_virt(x)
-
 /*
  * Cache flushing area - ROM
  */
diff --git a/arch/arm/mach-lh7a40x/clcd.c b/arch/arm/mach-lh7a40x/clcd.c
index a2a543258fc3..c472b9e8b37c 100644
--- a/arch/arm/mach-lh7a40x/clcd.c
+++ b/arch/arm/mach-lh7a40x/clcd.c
@@ -207,7 +207,7 @@ static struct clcd_board clcd_platform_data = {
 static struct amba_device name##_device = {			\
 	.dev = {						\
 		.coherent_dma_mask = ~0,			\
-		.bus_id	= busid,				\
+		.init_name = busid,				\
 		.platform_data = plat,				\
 		},						\
 	.res = {						\
diff --git a/arch/arm/mach-lh7a40x/clocks.c b/arch/arm/mach-lh7a40x/clocks.c
index 4fb23ac6b5ac..6182f5410b4d 100644
--- a/arch/arm/mach-lh7a40x/clocks.c
+++ b/arch/arm/mach-lh7a40x/clocks.c
@@ -14,21 +14,14 @@
 #include <linux/err.h>
 
 struct module;
-struct icst525_params;
 
 struct clk {
 	struct list_head node;
 	unsigned long rate;
 	struct module *owner;
 	const char *name;
-//	void *data;
-//	const struct icst525_params *params;
-//	void (*setvco)(struct clk *, struct icst525_vco vco);
 };
 
-int clk_register(struct clk *clk);
-void clk_unregister(struct clk *clk);
-
 /* ----- */
 
 #define MAINDIV1(c)	(((c) >>  7) & 0x0f)
@@ -79,31 +72,15 @@ unsigned int pclkfreq_get (void)
 
 /* ----- */
 
-static LIST_HEAD(clocks);
-static DECLARE_MUTEX(clocks_sem);
-
 struct clk *clk_get (struct device *dev, const char *id)
 {
-	struct clk *p;
-	struct clk *clk = ERR_PTR(-ENOENT);
-
-	down (&clocks_sem);
-	list_for_each_entry (p, &clocks, node) {
-		if (strcmp (id, p->name) == 0
-		    && try_module_get(p->owner)) {
-			clk = p;
-			break;
-		}
-	}
-	up (&clocks_sem);
-
-	return clk;
+	return dev && strcmp(dev_name(dev), "cldc-lh7a40x") == 0
+		 ? NULL : ERR_PTR(-ENOENT);
 }
 EXPORT_SYMBOL(clk_get);
 
 void clk_put (struct clk *clk)
 {
-	module_put(clk->owner);
 }
 EXPORT_SYMBOL(clk_put);
 
@@ -118,20 +95,9 @@ void clk_disable (struct clk *clk)
 }
 EXPORT_SYMBOL(clk_disable);
 
-int clk_use (struct clk *clk)
-{
-	return 0;
-}
-EXPORT_SYMBOL(clk_use);
-
-void clk_unuse (struct clk *clk)
-{
-}
-EXPORT_SYMBOL(clk_unuse);
-
 unsigned long clk_get_rate (struct clk *clk)
 {
-	return clk->rate;
+	return 0;
 }
 EXPORT_SYMBOL(clk_get_rate);
 
@@ -143,56 +109,6 @@ EXPORT_SYMBOL(clk_round_rate);
 
 int clk_set_rate (struct clk *clk, unsigned long rate)
 {
-	int ret = -EIO;
-	return ret;
+	return -EIO;
 }
 EXPORT_SYMBOL(clk_set_rate);
-
-#if 0
-/*
- * These are fixed clocks.
- */
-static struct clk kmi_clk = {
-	.name	= "KMIREFCLK",
-	.rate	= 24000000,
-};
-
-static struct clk uart_clk = {
-	.name	= "UARTCLK",
-	.rate	= 24000000,
-};
-
-static struct clk mmci_clk = {
-	.name	= "MCLK",
-	.rate	= 33000000,
-};
-#endif
-
-static struct clk clcd_clk = {
-	.name	= "CLCDCLK",
-	.rate	= 0,
-};
-
-int clk_register (struct clk *clk)
-{
-	down (&clocks_sem);
-	list_add (&clk->node, &clocks);
-	up (&clocks_sem);
-	return 0;
-}
-EXPORT_SYMBOL(clk_register);
-
-void clk_unregister (struct clk *clk)
-{
-	down (&clocks_sem);
-	list_del (&clk->node);
-	up (&clocks_sem);
-}
-EXPORT_SYMBOL(clk_unregister);
-
-static int __init clk_init (void)
-{
-	clk_register(&clcd_clk);
-	return 0;
-}
-arch_initcall(clk_init);
diff --git a/arch/arm/mach-lh7a40x/include/mach/io.h b/arch/arm/mach-lh7a40x/include/mach/io.h
index 031d26f9163c..6ece45911cbc 100644
--- a/arch/arm/mach-lh7a40x/include/mach/io.h
+++ b/arch/arm/mach-lh7a40x/include/mach/io.h
@@ -11,12 +11,10 @@
 #ifndef __ASM_ARCH_IO_H
 #define __ASM_ARCH_IO_H
 
-#include <mach/hardware.h>
-
 #define IO_SPACE_LIMIT 0xffffffff
 
 /* No ISA or PCI bus on this machine. */
-#define __io(a)			((void __iomem *)(a))
-#define __mem_pci(a)		(a)
+#define __io(a)		__typesafe_io(a)
+#define __mem_pci(a)	(a)
 
 #endif /* __ASM_ARCH_IO_H */
diff --git a/arch/arm/mach-lh7a40x/include/mach/memory.h b/arch/arm/mach-lh7a40x/include/mach/memory.h
index 1da14ff66c93..189d20e543e7 100644
--- a/arch/arm/mach-lh7a40x/include/mach/memory.h
+++ b/arch/arm/mach-lh7a40x/include/mach/memory.h
@@ -19,16 +19,6 @@
  */
 #define PHYS_OFFSET	UL(0xc0000000)
 
-/*
- * Virtual view <-> DMA view memory address translations
- * virt_to_bus: Used to translate the virtual address to an
- *		address suitable to be passed to set_dma_addr
- * bus_to_virt: Used to convert an address for DMA operations
- *		to an address that the kernel can use.
- */
-#define __virt_to_bus(x)	 __virt_to_phys(x)
-#define __bus_to_virt(x)	 __phys_to_virt(x)
-
 #ifdef CONFIG_DISCONTIGMEM
 
 /*
diff --git a/arch/arm/mach-loki/include/mach/dma.h b/arch/arm/mach-loki/include/mach/dma.h
deleted file mode 100644
index 40a8c178f10d..000000000000
--- a/arch/arm/mach-loki/include/mach/dma.h
+++ /dev/null
@@ -1 +0,0 @@
-/* empty */
diff --git a/arch/arm/mach-loki/include/mach/memory.h b/arch/arm/mach-loki/include/mach/memory.h
index a39533ab489d..2ed7e6e732c2 100644
--- a/arch/arm/mach-loki/include/mach/memory.h
+++ b/arch/arm/mach-loki/include/mach/memory.h
@@ -7,8 +7,4 @@
 
 #define PHYS_OFFSET		UL(0x00000000)
 
-#define __virt_to_bus(x)	__virt_to_phys(x)
-#define __bus_to_virt(x)	__phys_to_virt(x)
-
-
 #endif
diff --git a/arch/arm/mach-msm/include/mach/io.h b/arch/arm/mach-msm/include/mach/io.h
index c6a2feb268b0..aab964591db4 100644
--- a/arch/arm/mach-msm/include/mach/io.h
+++ b/arch/arm/mach-msm/include/mach/io.h
@@ -23,11 +23,7 @@
 
 void __iomem *__msm_ioremap(unsigned long phys_addr, size_t size, unsigned int mtype);
 
-static inline void __iomem *__io(unsigned long addr)
-{
-	return (void __iomem *)addr;
-}
-#define __io(a)         __io(a)
+#define __io(a)		__typesafe_io(a)
 #define __mem_pci(a)    (a)
 
 #endif
diff --git a/arch/arm/mach-msm/include/mach/memory.h b/arch/arm/mach-msm/include/mach/memory.h
index 63fd47f2e62e..f4698baec976 100644
--- a/arch/arm/mach-msm/include/mach/memory.h
+++ b/arch/arm/mach-msm/include/mach/memory.h
@@ -19,9 +19,5 @@
 /* physical offset of RAM */
 #define PHYS_OFFSET		UL(0x10000000)
 
-/* bus address and physical addresses are identical */
-#define __virt_to_bus(x)	__virt_to_phys(x)
-#define __bus_to_virt(x)	__phys_to_virt(x)
-
 #endif
 
diff --git a/arch/arm/mach-mv78xx0/include/mach/dma.h b/arch/arm/mach-mv78xx0/include/mach/dma.h
deleted file mode 100644
index 40a8c178f10d..000000000000
--- a/arch/arm/mach-mv78xx0/include/mach/dma.h
+++ /dev/null
@@ -1 +0,0 @@
-/* empty */
diff --git a/arch/arm/mach-mv78xx0/include/mach/memory.h b/arch/arm/mach-mv78xx0/include/mach/memory.h
index 9e47a140ff7a..e663042d307f 100644
--- a/arch/arm/mach-mv78xx0/include/mach/memory.h
+++ b/arch/arm/mach-mv78xx0/include/mach/memory.h
@@ -7,8 +7,4 @@
 
 #define PHYS_OFFSET		UL(0x00000000)
 
-#define __virt_to_bus(x)	__virt_to_phys(x)
-#define __bus_to_virt(x)	__phys_to_virt(x)
-
-
 #endif
diff --git a/arch/arm/mach-netx/fb.c b/arch/arm/mach-netx/fb.c
index 24c79650f9f3..ea8fa8898fe8 100644
--- a/arch/arm/mach-netx/fb.c
+++ b/arch/arm/mach-netx/fb.c
@@ -22,14 +22,11 @@
 #include <linux/dma-mapping.h>
 #include <linux/amba/bus.h>
 #include <linux/amba/clcd.h>
+#include <linux/err.h>
 
 #include <mach/netx-regs.h>
 #include <mach/hardware.h>
 
-struct clk {};
-
-static struct clk fb_clk;
-
 static struct clcd_panel *netx_panel;
 
 void netx_clcd_enable(struct clcd_fb *fb)
@@ -85,7 +82,7 @@ int clk_enable(struct clk *clk)
 
 struct clk *clk_get(struct device *dev, const char *id)
 {
-	return &fb_clk;
+	return dev && strcmp(dev_name(dev), "fb") == 0 ? NULL : ERR_PTR(-ENOENT);
 }
 
 void clk_put(struct clk *clk)
@@ -94,7 +91,7 @@ void clk_put(struct clk *clk)
 
 static struct amba_device fb_device = {
 	.dev		= {
-		.bus_id	= "fb",
+		.init_name = "fb",
 		.coherent_dma_mask = ~0,
 	},
 	.res		= {
diff --git a/arch/arm/mach-netx/include/mach/dma.h b/arch/arm/mach-netx/include/mach/dma.h
deleted file mode 100644
index 690b3ebc43ac..000000000000
--- a/arch/arm/mach-netx/include/mach/dma.h
+++ /dev/null
@@ -1,21 +0,0 @@
-/*
- *  arch/arm/mach-netx/include/mach/dma.h
- *
- * Copyright (C) 2005 Sascha Hauer <s.hauer@pengutronix.de>, Pengutronix
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2
- * as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
- */
-
-#define MAX_DMA_CHANNELS 0
-#define MAX_DMA_ADDRESS ~0
diff --git a/arch/arm/mach-netx/include/mach/io.h b/arch/arm/mach-netx/include/mach/io.h
index 468b92a82585..c3921cb3b6a6 100644
--- a/arch/arm/mach-netx/include/mach/io.h
+++ b/arch/arm/mach-netx/include/mach/io.h
@@ -22,7 +22,7 @@
 
 #define IO_SPACE_LIMIT 0xffffffff
 
-#define __io(a)         ((void __iomem *)(a))
+#define __io(a)		__typesafe_io(a)
 #define __mem_pci(a)            (a)
 
 #endif
diff --git a/arch/arm/mach-netx/include/mach/memory.h b/arch/arm/mach-netx/include/mach/memory.h
index 53745a1378de..9a363f297f90 100644
--- a/arch/arm/mach-netx/include/mach/memory.h
+++ b/arch/arm/mach-netx/include/mach/memory.h
@@ -22,15 +22,5 @@
 
 #define PHYS_OFFSET UL(0x80000000)
 
-/*
- * Virtual view <-> DMA view memory address translations
- * virt_to_bus: Used to translate the virtual address to an
- *              address suitable to be passed to set_dma_addr
- * bus_to_virt: Used to convert an address for DMA operations
- *              to an address that the kernel can use.
- */
-#define __virt_to_bus(x)         __virt_to_phys(x)
-#define __bus_to_virt(x)         __phys_to_virt(x)
-
 #endif
 
diff --git a/arch/arm/mach-ns9xxx/include/mach/dma.h b/arch/arm/mach-ns9xxx/include/mach/dma.h
deleted file mode 100644
index 3f50d8c9e5c7..000000000000
--- a/arch/arm/mach-ns9xxx/include/mach/dma.h
+++ /dev/null
@@ -1,14 +0,0 @@
-/*
- * arch/arm/mach-ns9xxx/include/mach/dma.h
- *
- * Copyright (C) 2006 by Digi International Inc.
- * All rights reserved.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published by
- * the Free Software Foundation.
- */
-#ifndef __ASM_ARCH_DMA_H
-#define __ASM_ARCH_DMA_H
-
-#endif /* ifndef __ASM_ARCH_DMA_H */
diff --git a/arch/arm/mach-ns9xxx/include/mach/hardware.h b/arch/arm/mach-ns9xxx/include/mach/hardware.h
index 6dbb2030f563..76631128e11c 100644
--- a/arch/arm/mach-ns9xxx/include/mach/hardware.h
+++ b/arch/arm/mach-ns9xxx/include/mach/hardware.h
@@ -11,8 +11,6 @@
 #ifndef __ASM_ARCH_HARDWARE_H
 #define __ASM_ARCH_HARDWARE_H
 
-#include <asm/memory.h>
-
 /*
  * NetSilicon NS9xxx internal mapping:
  *
diff --git a/arch/arm/mach-ns9xxx/include/mach/io.h b/arch/arm/mach-ns9xxx/include/mach/io.h
index 027bf649645a..f08451d2e1bc 100644
--- a/arch/arm/mach-ns9xxx/include/mach/io.h
+++ b/arch/arm/mach-ns9xxx/include/mach/io.h
@@ -13,7 +13,7 @@
 
 #define IO_SPACE_LIMIT  0xffffffff /* XXX */
 
-#define __io(a)         ((void __iomem *)(a))
+#define __io(a)		__typesafe_io(a)
 #define __mem_pci(a)    (a)
 #define __mem_isa(a)    (IO_BASE + (a))
 
diff --git a/arch/arm/mach-ns9xxx/include/mach/memory.h b/arch/arm/mach-ns9xxx/include/mach/memory.h
index 649ee6235b94..6107193adbfe 100644
--- a/arch/arm/mach-ns9xxx/include/mach/memory.h
+++ b/arch/arm/mach-ns9xxx/include/mach/memory.h
@@ -21,7 +21,4 @@
 
 #define PHYS_OFFSET	UL(0x00000000)
 
-#define __virt_to_bus(x) __virt_to_phys(x)
-#define __bus_to_virt(x) __phys_to_virt(x)
-
 #endif
diff --git a/arch/arm/mach-omap1/Kconfig b/arch/arm/mach-omap1/Kconfig
index 79f0b1f8497b..10a301e32434 100644
--- a/arch/arm/mach-omap1/Kconfig
+++ b/arch/arm/mach-omap1/Kconfig
@@ -4,16 +4,19 @@ comment "OMAP Core Type"
 config ARCH_OMAP730
 	depends on ARCH_OMAP1
 	bool "OMAP730 Based System"
+	select CPU_ARM926T
 	select ARCH_OMAP_OTG
 
 config ARCH_OMAP15XX
 	depends on ARCH_OMAP1
 	default y
 	bool "OMAP15xx Based System"
+	select CPU_ARM925T
 
 config ARCH_OMAP16XX
 	depends on ARCH_OMAP1
 	bool "OMAP16xx Based System"
+	select CPU_ARM926T
 	select ARCH_OMAP_OTG
 
 comment "OMAP Board Type"
diff --git a/arch/arm/mach-omap1/io.c b/arch/arm/mach-omap1/io.c
index b3bd8ca85118..4c3e582f3d3c 100644
--- a/arch/arm/mach-omap1/io.c
+++ b/arch/arm/mach-omap1/io.c
@@ -128,7 +128,7 @@ void __init omap1_map_common_io(void)
  * Common low-level hardware init for omap1. This should only get called from
  * board specific init.
  */
-void __init omap1_init_common_hw()
+void __init omap1_init_common_hw(void)
 {
 	/* REVISIT: Refer to OMAP5910 Errata, Advisory SYS_1: "Timeout Abort
 	 * on a Posted Write in the TIPB Bridge".
diff --git a/arch/arm/mach-orion5x/include/mach/dma.h b/arch/arm/mach-orion5x/include/mach/dma.h
deleted file mode 100644
index 40a8c178f10d..000000000000
--- a/arch/arm/mach-orion5x/include/mach/dma.h
+++ /dev/null
@@ -1 +0,0 @@
-/* empty */
diff --git a/arch/arm/mach-orion5x/include/mach/io.h b/arch/arm/mach-orion5x/include/mach/io.h
index f24b2513f7f3..c47b033bd999 100644
--- a/arch/arm/mach-orion5x/include/mach/io.h
+++ b/arch/arm/mach-orion5x/include/mach/io.h
@@ -38,14 +38,9 @@ __arch_iounmap(void __iomem *addr)
 		__iounmap(addr);
 }
 
-static inline void __iomem *__io(unsigned long addr)
-{
-	return (void __iomem *)addr;
-}
-
 #define __arch_ioremap(p, s, m)	__arch_ioremap(p, s, m)
 #define __arch_iounmap(a)	__arch_iounmap(a)
-#define __io(a)			__io(a)
+#define __io(a)			__typesafe_io(a)
 #define __mem_pci(a)		(a)
 
 
diff --git a/arch/arm/mach-orion5x/include/mach/memory.h b/arch/arm/mach-orion5x/include/mach/memory.h
index 54dd76b013f2..52a2955d0f87 100644
--- a/arch/arm/mach-orion5x/include/mach/memory.h
+++ b/arch/arm/mach-orion5x/include/mach/memory.h
@@ -9,8 +9,4 @@
 
 #define PHYS_OFFSET	UL(0x00000000)
 
-#define __virt_to_bus(x)	__virt_to_phys(x)
-#define __bus_to_virt(x)	__phys_to_virt(x)
-
-
 #endif
diff --git a/arch/arm/mach-pnx4008/dma.c b/arch/arm/mach-pnx4008/dma.c
index ac2f70eddb9e..425f7188505e 100644
--- a/arch/arm/mach-pnx4008/dma.c
+++ b/arch/arm/mach-pnx4008/dma.c
@@ -25,9 +25,8 @@
 
 #include <asm/system.h>
 #include <mach/hardware.h>
-#include <asm/dma.h>
+#include <mach/dma.h>
 #include <asm/dma-mapping.h>
-#include <asm/mach/dma.h>
 #include <mach/clock.h>
 
 static struct dma_channel {
diff --git a/arch/arm/mach-pnx4008/include/mach/dma.h b/arch/arm/mach-pnx4008/include/mach/dma.h
index 5442d04fc575..f094bf8bfb18 100644
--- a/arch/arm/mach-pnx4008/include/mach/dma.h
+++ b/arch/arm/mach-pnx4008/include/mach/dma.h
@@ -16,8 +16,6 @@
 
 #include "platform.h"
 
-#define MAX_DMA_ADDRESS		0xffffffff
-
 #define MAX_DMA_CHANNELS	8
 
 #define DMAC_BASE		IO_ADDRESS(PNX4008_DMA_CONFIG_BASE)
diff --git a/arch/arm/mach-pnx4008/include/mach/io.h b/arch/arm/mach-pnx4008/include/mach/io.h
index c6206f25839d..cbf0904540ea 100644
--- a/arch/arm/mach-pnx4008/include/mach/io.h
+++ b/arch/arm/mach-pnx4008/include/mach/io.h
@@ -15,7 +15,7 @@
 
 #define IO_SPACE_LIMIT 0xffffffff
 
-#define __io(a)			((void __iomem *)(a))
-#define __mem_pci(a)		(a)
+#define __io(a)		__typesafe_io(a)
+#define __mem_pci(a)	(a)
 
 #endif
diff --git a/arch/arm/mach-pnx4008/include/mach/memory.h b/arch/arm/mach-pnx4008/include/mach/memory.h
index 5789a2d16f5a..0e8770081058 100644
--- a/arch/arm/mach-pnx4008/include/mach/memory.h
+++ b/arch/arm/mach-pnx4008/include/mach/memory.h
@@ -16,9 +16,6 @@
 /*
  * Physical DRAM offset.
  */
-#define PHYS_OFFSET     (0x80000000)
-
-#define __virt_to_bus(x) ((x) - PAGE_OFFSET + PHYS_OFFSET)
-#define __bus_to_virt(x) ((x) + PAGE_OFFSET - PHYS_OFFSET)
+#define PHYS_OFFSET	UL(0x80000000)
 
 #endif
diff --git a/arch/arm/mach-pxa/Kconfig b/arch/arm/mach-pxa/Kconfig
index a062235e83a8..6755c7d6bb31 100644
--- a/arch/arm/mach-pxa/Kconfig
+++ b/arch/arm/mach-pxa/Kconfig
@@ -19,6 +19,9 @@ config CPU_PXA320
 config CPU_PXA930
 	bool "PXA930 (codename Tavor-P)"
 
+config CPU_PXA935
+	bool "PXA935 (codename Tavor-P65)"
+
 endmenu
 
 endif
@@ -199,6 +202,10 @@ config MACH_E800
 config TRIZEPS_PXA
 	bool "PXA based Keith und Koep Trizeps DIMM-Modules"
 
+config MACH_H5000
+	bool "HP iPAQ h5000"
+	select PXA25x
+
 config MACH_TRIZEPS4
 	bool "Keith und Koep Trizeps4 DIMM-Module"
 	depends on TRIZEPS_PXA
@@ -283,7 +290,6 @@ config MACH_MIOA701
 	bool "Mitac Mio A701 Support"
 	select PXA27x
 	select IWMMXT
-	select LEDS_GPIO
 	select HAVE_PWM
 	select GPIO_SYSFS
 	help
@@ -386,16 +392,25 @@ endmenu
 
 config PXA25x
 	bool
+	select CPU_XSCALE
 	help
 	  Select code specific to PXA21x/25x/26x variants
 
 config PXA27x
 	bool
+	select CPU_XSCALE
 	help
 	  Select code specific to PXA27x variants
 
+config CPU_PXA26x
+	bool
+	select PXA25x
+	help
+	  Select code specific to PXA26x (codename Dalhart)
+
 config PXA3xx
 	bool
+	select CPU_XSC3
 	help
 	  Select code specific to PXA3xx variants
 
diff --git a/arch/arm/mach-pxa/Makefile b/arch/arm/mach-pxa/Makefile
index d64c68b232e3..dc184eae5109 100644
--- a/arch/arm/mach-pxa/Makefile
+++ b/arch/arm/mach-pxa/Makefile
@@ -35,6 +35,7 @@ obj-$(CONFIG_MACH_MP900C)	+= mp900.o
 obj-$(CONFIG_ARCH_PXA_IDP)	+= idp.o
 obj-$(CONFIG_MACH_TRIZEPS4)	+= trizeps4.o
 obj-$(CONFIG_MACH_COLIBRI)	+= colibri.o
+obj-$(CONFIG_MACH_H5000)	+= h5000.o
 obj-$(CONFIG_PXA_SHARP_C7xx)	+= corgi.o sharpsl_pm.o corgi_pm.o
 obj-$(CONFIG_PXA_SHARP_Cxx00)	+= spitz.o sharpsl_pm.o spitz_pm.o
 obj-$(CONFIG_CORGI_SSP_DEPRECATED)	+= corgi_ssp.o corgi_lcd.o
diff --git a/arch/arm/mach-pxa/clock.c b/arch/arm/mach-pxa/clock.c
index ca8e20538157..40b774084514 100644
--- a/arch/arm/mach-pxa/clock.c
+++ b/arch/arm/mach-pxa/clock.c
@@ -12,53 +12,16 @@
 #include <linux/platform_device.h>
 #include <linux/delay.h>
 
+#include <asm/clkdev.h>
 #include <mach/pxa2xx-regs.h>
-#include <mach/pxa2xx-gpio.h>
 #include <mach/hardware.h>
 
 #include "devices.h"
 #include "generic.h"
 #include "clock.h"
 
-static LIST_HEAD(clocks);
-static DEFINE_MUTEX(clocks_mutex);
 static DEFINE_SPINLOCK(clocks_lock);
 
-static struct clk *clk_lookup(struct device *dev, const char *id)
-{
-	struct clk *p;
-
-	list_for_each_entry(p, &clocks, node)
-		if (strcmp(id, p->name) == 0 && p->dev == dev)
-			return p;
-
-	return NULL;
-}
-
-struct clk *clk_get(struct device *dev, const char *id)
-{
-	struct clk *p, *clk = ERR_PTR(-ENOENT);
-
-	mutex_lock(&clocks_mutex);
-	p = clk_lookup(dev, id);
-	if (!p)
-		p = clk_lookup(NULL, id);
-	if (p)
-		clk = p;
-	mutex_unlock(&clocks_mutex);
-
-	if (!IS_ERR(clk) && clk->ops == NULL)
-		clk = clk->other;
-
-	return clk;
-}
-EXPORT_SYMBOL(clk_get);
-
-void clk_put(struct clk *clk)
-{
-}
-EXPORT_SYMBOL(clk_put);
-
 int clk_enable(struct clk *clk)
 {
 	unsigned long flags;
@@ -116,37 +79,27 @@ const struct clkops clk_cken_ops = {
 	.disable	= clk_cken_disable,
 };
 
-void clks_register(struct clk *clks, size_t num)
+void clks_register(struct clk_lookup *clks, size_t num)
 {
 	int i;
 
-	mutex_lock(&clocks_mutex);
 	for (i = 0; i < num; i++)
-		list_add(&clks[i].node, &clocks);
-	mutex_unlock(&clocks_mutex);
+		clkdev_add(&clks[i]);
 }
 
 int clk_add_alias(char *alias, struct device *alias_dev, char *id,
 	struct device *dev)
 {
-	struct clk *r = clk_lookup(dev, id);
-	struct clk *new;
+	struct clk *r = clk_get(dev, id);
+	struct clk_lookup *l;
 
 	if (!r)
 		return -ENODEV;
 
-	new = kzalloc(sizeof(struct clk), GFP_KERNEL);
-
-	if (!new)
-		return -ENOMEM;
-
-	new->name = alias;
-	new->dev = alias_dev;
-	new->other = r;
-
-	mutex_lock(&clocks_mutex);
-	list_add(&new->node, &clocks);
-	mutex_unlock(&clocks_mutex);
-
+	l = clkdev_alloc(r, alias, alias_dev ? dev_name(alias_dev) : NULL);
+	clk_put(r);
+	if (!l)
+		return -ENODEV;
+	clkdev_add(l);
 	return 0;
 }
diff --git a/arch/arm/mach-pxa/clock.h b/arch/arm/mach-pxa/clock.h
index 73be795fe3bf..4e9c613c6767 100644
--- a/arch/arm/mach-pxa/clock.h
+++ b/arch/arm/mach-pxa/clock.h
@@ -1,6 +1,4 @@
-#include <linux/list.h>
-
-struct clk;
+#include <asm/clkdev.h>
 
 struct clkops {
 	void			(*enable)(struct clk *);
@@ -9,9 +7,6 @@ struct clkops {
 };
 
 struct clk {
-	struct list_head	node;
-	const char		*name;
-	struct device		*dev;
 	const struct clkops	*ops;
 	unsigned long		rate;
 	unsigned int		cken;
@@ -20,41 +15,31 @@ struct clk {
 	struct clk		*other;
 };
 
-#define INIT_CKEN(_name, _cken, _rate, _delay, _dev)	\
+#define INIT_CLKREG(_clk,_devname,_conname)		\
 	{						\
-		.name	= _name,			\
-		.dev	= _dev,				\
+		.clk		= _clk,			\
+		.dev_id		= _devname,		\
+		.con_id		= _conname,		\
+	}
+
+#define DEFINE_CKEN(_name, _cken, _rate, _delay)	\
+struct clk clk_##_name = {				\
 		.ops	= &clk_cken_ops,		\
 		.rate	= _rate,			\
 		.cken	= CKEN_##_cken,			\
 		.delay	= _delay,			\
 	}
 
-#define INIT_CK(_name, _cken, _ops, _dev)		\
-	{						\
-		.name	= _name,			\
-		.dev	= _dev,				\
+#define DEFINE_CK(_name, _cken, _ops)			\
+struct clk clk_##_name = {				\
 		.ops	= _ops,				\
 		.cken	= CKEN_##_cken,			\
 	}
 
-/*
- * This is a placeholder to alias one clock device+name pair
- * to another struct clk.
- */
-#define INIT_CKOTHER(_name, _other, _dev)		\
-	{						\
-		.name	= _name,			\
-		.dev	= _dev,				\
-		.other	= _other,			\
-	}
-
-#define INIT_CLK(_name, _ops, _rate, _delay, _dev)      \
-	{                                               \
-		.name   = _name,                        \
-		.dev    = _dev,                         \
-		.ops    = _ops,                         \
-		.rate   = _rate,                        \
+#define DEFINE_CLK(_name, _ops, _rate, _delay)		\
+struct clk clk_##_name = {				\
+		.ops	= _ops, 			\
+		.rate	= _rate,			\
 		.delay	= _delay,			\
 	}
 
@@ -64,20 +49,16 @@ void clk_cken_enable(struct clk *clk);
 void clk_cken_disable(struct clk *clk);
 
 #ifdef CONFIG_PXA3xx
-#define PXA3xx_CKEN(_name, _cken, _rate, _delay, _dev)	\
-	{						\
-		.name	= _name,			\
-		.dev	= _dev,				\
+#define DEFINE_PXA3_CKEN(_name, _cken, _rate, _delay)	\
+struct clk clk_##_name = {				\
 		.ops	= &clk_pxa3xx_cken_ops,		\
 		.rate	= _rate,			\
 		.cken	= CKEN_##_cken,			\
 		.delay	= _delay,			\
 	}
 
-#define PXA3xx_CK(_name, _cken, _ops, _dev)		\
-	{						\
-		.name	= _name,			\
-		.dev	= _dev,				\
+#define DEFINE_PXA3_CK(_name, _cken, _ops)		\
+struct clk clk_##_name = {				\
 		.ops	= _ops,				\
 		.cken	= CKEN_##_cken,			\
 	}
@@ -87,7 +68,7 @@ extern void clk_pxa3xx_cken_enable(struct clk *);
 extern void clk_pxa3xx_cken_disable(struct clk *);
 #endif
 
-void clks_register(struct clk *clks, size_t num);
+void clks_register(struct clk_lookup *clks, size_t num);
 int clk_add_alias(char *alias, struct device *alias_dev, char *id,
 	struct device *dev);
 
diff --git a/arch/arm/mach-pxa/cm-x300.c b/arch/arm/mach-pxa/cm-x300.c
index deb46cd144bf..ff0c577cd1ac 100644
--- a/arch/arm/mach-pxa/cm-x300.c
+++ b/arch/arm/mach-pxa/cm-x300.c
@@ -31,7 +31,6 @@
 #include <mach/mfp-pxa300.h>
 
 #include <mach/hardware.h>
-#include <mach/gpio.h>
 #include <mach/pxafb.h>
 #include <mach/mmc.h>
 #include <mach/ohci.h>
@@ -137,6 +136,10 @@ static mfp_cfg_t cm_x300_mfp_cfg[] __initdata = {
 	GPIO82_GPIO | MFP_PULL_HIGH,	/* MMC CD */
 	GPIO85_GPIO,			/* MMC WP */
 	GPIO99_GPIO,			/* Ethernet IRQ */
+
+	/* Standard I2C */
+	GPIO21_I2C_SCL,
+	GPIO22_I2C_SDA,
 };
 
 #if defined(CONFIG_DM9000) || defined(CONFIG_DM9000_MODULE)
diff --git a/arch/arm/mach-pxa/corgi.c b/arch/arm/mach-pxa/corgi.c
index 65558d6aa220..c5e28a46b292 100644
--- a/arch/arm/mach-pxa/corgi.c
+++ b/arch/arm/mach-pxa/corgi.c
@@ -19,6 +19,7 @@
 #include <linux/fs.h>
 #include <linux/interrupt.h>
 #include <linux/mmc/host.h>
+#include <linux/mtd/physmap.h>
 #include <linux/pm.h>
 #include <linux/gpio.h>
 #include <linux/backlight.h>
@@ -541,11 +542,42 @@ err_free_1:
 static inline void corgi_init_spi(void) {}
 #endif
 
+static struct mtd_partition sharpsl_rom_parts[] = {
+	{
+		.name	="Boot PROM Filesystem",
+		.offset	= 0x00120000,
+		.size	= MTDPART_SIZ_FULL,
+	},
+};
+
+static struct physmap_flash_data sharpsl_rom_data = {
+	.width		= 2,
+	.nr_parts	= ARRAY_SIZE(sharpsl_rom_parts),
+	.parts		= sharpsl_rom_parts,
+};
+
+static struct resource sharpsl_rom_resources[] = {
+	{
+		.start	= 0x00000000,
+		.end	= 0x007fffff,
+		.flags	= IORESOURCE_MEM,
+	},
+};
+
+static struct platform_device sharpsl_rom_device = {
+	.name	= "physmap-flash",
+	.id	= -1,
+	.resource = sharpsl_rom_resources,
+	.num_resources = ARRAY_SIZE(sharpsl_rom_resources),
+	.dev.platform_data = &sharpsl_rom_data,
+};
+
 static struct platform_device *devices[] __initdata = {
 	&corgiscoop_device,
 	&corgifb_device,
 	&corgikbd_device,
 	&corgiled_device,
+	&sharpsl_rom_device,
 };
 
 static void corgi_poweroff(void)
diff --git a/arch/arm/mach-pxa/cpufreq-pxa2xx.c b/arch/arm/mach-pxa/cpufreq-pxa2xx.c
index 1f272ea83f36..771dd4eac935 100644
--- a/arch/arm/mach-pxa/cpufreq-pxa2xx.c
+++ b/arch/arm/mach-pxa/cpufreq-pxa2xx.c
@@ -64,7 +64,7 @@ typedef struct {
 
 /* Define the refresh period in mSec for the SDRAM and the number of rows */
 #define SDRAM_TREF	64	/* standard 64ms SDRAM */
-#define SDRAM_ROWS	4096	/* 64MB=8192 32MB=4096 */
+static unsigned int sdram_rows;
 
 #define CCLKCFG_TURBO		0x1
 #define CCLKCFG_FCS		0x2
@@ -73,6 +73,9 @@ typedef struct {
 #define MDREFR_DB2_MASK		(MDREFR_K2DB2 | MDREFR_K1DB2)
 #define MDREFR_DRI_MASK		0xFFF
 
+#define MDCNFG_DRAC2(mdcnfg) (((mdcnfg) >> 21) & 0x3)
+#define MDCNFG_DRAC0(mdcnfg) (((mdcnfg) >> 5) & 0x3)
+
 /*
  * PXA255 definitions
  */
@@ -109,6 +112,10 @@ static struct cpufreq_frequency_table
 static struct cpufreq_frequency_table
 	pxa255_turbo_freq_table[NUM_PXA25x_TURBO_FREQS+1];
 
+static unsigned int pxa255_turbo_table;
+module_param(pxa255_turbo_table, uint, 0);
+MODULE_PARM_DESC(pxa255_turbo_table, "Selects the frequency table (0 = run table, !0 = turbo table)");
+
 /*
  * PXA270 definitions
  *
@@ -158,22 +165,16 @@ static struct cpufreq_frequency_table
 
 extern unsigned get_clk_frequency_khz(int info);
 
-static void find_freq_tables(struct cpufreq_policy *policy,
-			     struct cpufreq_frequency_table **freq_table,
+static void find_freq_tables(struct cpufreq_frequency_table **freq_table,
 			     pxa_freqs_t **pxa_freqs)
 {
 	if (cpu_is_pxa25x()) {
-		if (policy->policy == CPUFREQ_POLICY_PERFORMANCE) {
+		if (!pxa255_turbo_table) {
 			*pxa_freqs = pxa255_run_freqs;
 			*freq_table = pxa255_run_freq_table;
-		} else if (policy->policy == CPUFREQ_POLICY_POWERSAVE) {
+		} else {
 			*pxa_freqs = pxa255_turbo_freqs;
 			*freq_table = pxa255_turbo_freq_table;
-		} else {
-			printk("CPU PXA: Unknown policy found. "
-			       "Using CPUFREQ_POLICY_PERFORMANCE\n");
-			*pxa_freqs = pxa255_run_freqs;
-			*freq_table = pxa255_run_freq_table;
 		}
 	}
 	if (cpu_is_pxa27x()) {
@@ -194,14 +195,28 @@ static void pxa27x_guess_max_freq(void)
 	}
 }
 
+static void init_sdram_rows(void)
+{
+	uint32_t mdcnfg = MDCNFG;
+	unsigned int drac2 = 0, drac0 = 0;
+
+	if (mdcnfg & (MDCNFG_DE2 | MDCNFG_DE3))
+		drac2 = MDCNFG_DRAC2(mdcnfg);
+
+	if (mdcnfg & (MDCNFG_DE0 | MDCNFG_DE1))
+		drac0 = MDCNFG_DRAC0(mdcnfg);
+
+	sdram_rows = 1 << (11 + max(drac0, drac2));
+}
+
 static u32 mdrefr_dri(unsigned int freq)
 {
 	u32 dri = 0;
 
 	if (cpu_is_pxa25x())
-		dri = ((freq * SDRAM_TREF) / (SDRAM_ROWS * 32));
+		dri = ((freq * SDRAM_TREF) / (sdram_rows * 32));
 	if (cpu_is_pxa27x())
-		dri = ((freq * SDRAM_TREF) / (SDRAM_ROWS - 31)) / 32;
+		dri = ((freq * SDRAM_TREF) / (sdram_rows - 31)) / 32;
 	return dri;
 }
 
@@ -212,7 +227,7 @@ static int pxa_verify_policy(struct cpufreq_policy *policy)
 	pxa_freqs_t *pxa_freqs;
 	int ret;
 
-	find_freq_tables(policy, &pxa_freqs_table, &pxa_freqs);
+	find_freq_tables(&pxa_freqs_table, &pxa_freqs);
 	ret = cpufreq_frequency_table_verify(policy, pxa_freqs_table);
 
 	if (freq_debug)
@@ -240,7 +255,7 @@ static int pxa_set_target(struct cpufreq_policy *policy,
 	unsigned int unused, preset_mdrefr, postset_mdrefr, cclkcfg;
 
 	/* Get the current policy */
-	find_freq_tables(policy, &pxa_freqs_table, &pxa_freq_settings);
+	find_freq_tables(&pxa_freqs_table, &pxa_freq_settings);
 
 	/* Lookup the next frequency */
 	if (cpufreq_frequency_table_target(policy, pxa_freqs_table,
@@ -329,11 +344,15 @@ static __init int pxa_cpufreq_init(struct cpufreq_policy *policy)
 {
 	int i;
 	unsigned int freq;
+	struct cpufreq_frequency_table *pxa255_freq_table;
+	pxa_freqs_t *pxa255_freqs;
 
 	/* try to guess pxa27x cpu */
 	if (cpu_is_pxa27x())
 		pxa27x_guess_max_freq();
 
+	init_sdram_rows();
+
 	/* set default policy and cpuinfo */
 	policy->cpuinfo.transition_latency = 1000; /* FIXME: 1 ms, assumed */
 	policy->cur = get_clk_frequency_khz(0);	   /* current freq */
@@ -354,6 +373,8 @@ static __init int pxa_cpufreq_init(struct cpufreq_policy *policy)
 	}
 	pxa255_turbo_freq_table[i].frequency = CPUFREQ_TABLE_END;
 
+	pxa255_turbo_table = !!pxa255_turbo_table;
+
 	/* Generate the pxa27x cpufreq_frequency_table struct */
 	for (i = 0; i < NUM_PXA27x_FREQS; i++) {
 		freq = pxa27x_freqs[i].khz;
@@ -368,8 +389,12 @@ static __init int pxa_cpufreq_init(struct cpufreq_policy *policy)
 	 * Set the policy's minimum and maximum frequencies from the tables
 	 * just constructed.  This sets cpuinfo.mxx_freq, min and max.
 	 */
-	if (cpu_is_pxa25x())
-		cpufreq_frequency_table_cpuinfo(policy, pxa255_run_freq_table);
+	if (cpu_is_pxa25x()) {
+		find_freq_tables(&pxa255_freq_table, &pxa255_freqs);
+		pr_info("PXA255 cpufreq using %s frequency table\n",
+			pxa255_turbo_table ? "turbo" : "run");
+		cpufreq_frequency_table_cpuinfo(policy, pxa255_freq_table);
+	}
 	else if (cpu_is_pxa27x())
 		cpufreq_frequency_table_cpuinfo(policy, pxa27x_freq_table);
 
diff --git a/arch/arm/mach-pxa/devices.c b/arch/arm/mach-pxa/devices.c
index 35736fc08634..e16f8e3d58d3 100644
--- a/arch/arm/mach-pxa/devices.c
+++ b/arch/arm/mach-pxa/devices.c
@@ -4,13 +4,12 @@
 #include <linux/platform_device.h>
 #include <linux/dma-mapping.h>
 
-#include <mach/gpio.h>
+#include <mach/pxa-regs.h>
 #include <mach/udc.h>
 #include <mach/pxafb.h>
 #include <mach/mmc.h>
 #include <mach/irda.h>
 #include <mach/i2c.h>
-#include <mach/mfp-pxa27x.h>
 #include <mach/ohci.h>
 #include <mach/pxa27x_keypad.h>
 #include <mach/pxa2xx_spi.h>
@@ -156,8 +155,8 @@ void __init set_pxa_fb_parent(struct device *parent_dev)
 
 static struct resource pxa_resource_ffuart[] = {
 	{
-		.start	= __PREG(FFUART),
-		.end	= __PREG(FFUART) + 35,
+		.start	= 0x40100000,
+		.end	= 0x40100023,
 		.flags	= IORESOURCE_MEM,
 	}, {
 		.start	= IRQ_FFUART,
@@ -175,8 +174,8 @@ struct platform_device pxa_device_ffuart= {
 
 static struct resource pxa_resource_btuart[] = {
 	{
-		.start	= __PREG(BTUART),
-		.end	= __PREG(BTUART) + 35,
+		.start	= 0x40200000,
+		.end	= 0x40200023,
 		.flags	= IORESOURCE_MEM,
 	}, {
 		.start	= IRQ_BTUART,
@@ -194,8 +193,8 @@ struct platform_device pxa_device_btuart = {
 
 static struct resource pxa_resource_stuart[] = {
 	{
-		.start	= __PREG(STUART),
-		.end	= __PREG(STUART) + 35,
+		.start	= 0x40700000,
+		.end	= 0x40700023,
 		.flags	= IORESOURCE_MEM,
 	}, {
 		.start	= IRQ_STUART,
@@ -213,8 +212,8 @@ struct platform_device pxa_device_stuart = {
 
 static struct resource pxa_resource_hwuart[] = {
 	{
-		.start	= __PREG(HWUART),
-		.end	= __PREG(HWUART) + 47,
+		.start	= 0x41600000,
+		.end	= 0x4160002F,
 		.flags	= IORESOURCE_MEM,
 	}, {
 		.start	= IRQ_HWUART,
@@ -249,18 +248,53 @@ struct platform_device pxa_device_i2c = {
 	.num_resources	= ARRAY_SIZE(pxai2c_resources),
 };
 
-static unsigned long pxa27x_i2c_mfp_cfg[] = {
-	GPIO117_I2C_SCL,
-	GPIO118_I2C_SDA,
-};
-
 void __init pxa_set_i2c_info(struct i2c_pxa_platform_data *info)
 {
-	if (cpu_is_pxa27x())
-		pxa2xx_mfp_config(ARRAY_AND_SIZE(pxa27x_i2c_mfp_cfg));
 	pxa_register_device(&pxa_device_i2c, info);
 }
 
+#ifdef CONFIG_PXA27x
+static struct resource pxa27x_resources_i2c_power[] = {
+	{
+		.start	= 0x40f00180,
+		.end	= 0x40f001a3,
+		.flags	= IORESOURCE_MEM,
+	}, {
+		.start	= IRQ_PWRI2C,
+		.end	= IRQ_PWRI2C,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+struct platform_device pxa27x_device_i2c_power = {
+	.name		= "pxa2xx-i2c",
+	.id		= 1,
+	.resource	= pxa27x_resources_i2c_power,
+	.num_resources	= ARRAY_SIZE(pxa27x_resources_i2c_power),
+};
+#endif
+
+#ifdef CONFIG_PXA3xx
+static struct resource pxa3xx_resources_i2c_power[] = {
+	{
+		.start  = 0x40f500c0,
+		.end    = 0x40f500d3,
+		.flags	= IORESOURCE_MEM,
+	}, {
+		.start	= IRQ_PWRI2C,
+		.end	= IRQ_PWRI2C,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+struct platform_device pxa3xx_device_i2c_power = {
+	.name		= "pxa2xx-i2c",
+	.id		= 1,
+	.resource	= pxa3xx_resources_i2c_power,
+	.num_resources	= ARRAY_SIZE(pxa3xx_resources_i2c_power),
+};
+#endif
+
 static struct resource pxai2s_resources[] = {
 	{
 		.start	= 0x40400000,
@@ -296,11 +330,36 @@ void __init pxa_set_ficp_info(struct pxaficp_platform_data *info)
 	pxa_register_device(&pxa_device_ficp, info);
 }
 
-struct platform_device pxa_device_rtc = {
+static struct resource pxa_rtc_resources[] = {
+	[0] = {
+		.start  = 0x40900000,
+		.end	= 0x40900000 + 0x3b,
+		.flags  = IORESOURCE_MEM,
+	},
+	[1] = {
+		.start  = IRQ_RTC1Hz,
+		.end    = IRQ_RTC1Hz,
+		.flags  = IORESOURCE_IRQ,
+	},
+	[2] = {
+		.start  = IRQ_RTCAlrm,
+		.end    = IRQ_RTCAlrm,
+		.flags  = IORESOURCE_IRQ,
+	},
+};
+
+struct platform_device sa1100_device_rtc = {
 	.name		= "sa1100-rtc",
 	.id		= -1,
 };
 
+struct platform_device pxa_device_rtc = {
+	.name		= "pxa-rtc",
+	.id		= -1,
+	.num_resources  = ARRAY_SIZE(pxa_rtc_resources),
+	.resource       = pxa_rtc_resources,
+};
+
 static struct resource pxa_ac97_resources[] = {
 	[0] = {
 		.start  = 0x40500000,
diff --git a/arch/arm/mach-pxa/devices.h b/arch/arm/mach-pxa/devices.h
index bb04af4b0aa3..ecc24a4dca6d 100644
--- a/arch/arm/mach-pxa/devices.h
+++ b/arch/arm/mach-pxa/devices.h
@@ -11,6 +11,7 @@ extern struct platform_device pxa_device_hwuart;
 extern struct platform_device pxa_device_i2c;
 extern struct platform_device pxa_device_i2s;
 extern struct platform_device pxa_device_ficp;
+extern struct platform_device sa1100_device_rtc;
 extern struct platform_device pxa_device_rtc;
 extern struct platform_device pxa_device_ac97;
 
diff --git a/arch/arm/mach-pxa/dma.c b/arch/arm/mach-pxa/dma.c
index c0be17e0ab82..b1514fb20d3a 100644
--- a/arch/arm/mach-pxa/dma.c
+++ b/arch/arm/mach-pxa/dma.c
@@ -21,7 +21,7 @@
 #include <asm/system.h>
 #include <asm/irq.h>
 #include <mach/hardware.h>
-#include <asm/dma.h>
+#include <mach/dma.h>
 
 #include <mach/pxa-regs.h>
 
diff --git a/arch/arm/mach-pxa/ezx.c b/arch/arm/mach-pxa/ezx.c
index cc3d850cc0b6..3e6aa33a2c7c 100644
--- a/arch/arm/mach-pxa/ezx.c
+++ b/arch/arm/mach-pxa/ezx.c
@@ -21,6 +21,7 @@
 #include <mach/pxafb.h>
 #include <mach/ohci.h>
 #include <mach/i2c.h>
+#include <mach/hardware.h>
 
 #include <mach/mfp-pxa27x.h>
 #include <mach/pxa-regs.h>
@@ -112,6 +113,10 @@ static unsigned long ezx_pin_config[] __initdata = {
 	GPIO91_USB_P3_1,	/* ICL_XRXD */
 	GPIO56_USB_P3_4,	/* ICL_VMOUT */
 	GPIO113_USB_P3_3,	/* /ICL_VMIN */
+
+	/* I2C */
+	GPIO117_I2C_SCL,
+	GPIO118_I2C_SDA,
 };
 
 static void __init ezx_init(void)
diff --git a/arch/arm/mach-pxa/gpio.c b/arch/arm/mach-pxa/gpio.c
index 14930cf8be7b..5fec1e479cb3 100644
--- a/arch/arm/mach-pxa/gpio.c
+++ b/arch/arm/mach-pxa/gpio.c
@@ -25,6 +25,18 @@
 
 #include "generic.h"
 
+#define GPIO0_BASE	((void __iomem *)io_p2v(0x40E00000))
+#define GPIO1_BASE	((void __iomem *)io_p2v(0x40E00004))
+#define GPIO2_BASE	((void __iomem *)io_p2v(0x40E00008))
+#define GPIO3_BASE	((void __iomem *)io_p2v(0x40E00100))
+
+#define GPLR_OFFSET	0x00
+#define GPDR_OFFSET	0x0C
+#define GPSR_OFFSET	0x18
+#define GPCR_OFFSET	0x24
+#define GRER_OFFSET	0x30
+#define GFER_OFFSET	0x3C
+#define GEDR_OFFSET	0x48
 
 struct pxa_gpio_chip {
 	struct gpio_chip chip;
@@ -33,6 +45,18 @@ struct pxa_gpio_chip {
 
 int pxa_last_gpio;
 
+#ifdef CONFIG_CPU_PXA26x
+/* GPIO86/87/88/89 on PXA26x have their direction bits in GPDR2 inverted,
+ * as well as their Alternate Function value being '1' for GPIO in GAFRx.
+ */
+static int __gpio_is_inverted(unsigned gpio)
+{
+	return cpu_is_pxa25x() && gpio > 85;
+}
+#else
+#define __gpio_is_inverted(gpio)	(0)
+#endif
+
 /*
  * Configure pins for GPIO or other functions
  */
@@ -75,7 +99,10 @@ static int pxa_gpio_direction_input(struct gpio_chip *chip, unsigned offset)
 	gpdr = pxa->regbase + GPDR_OFFSET;
 	local_irq_save(flags);
 	value = __raw_readl(gpdr);
-	value &= ~mask;
+	if (__gpio_is_inverted(chip->base + offset))
+		value |= mask;
+	else
+		value &= ~mask;
 	__raw_writel(value, gpdr);
 	local_irq_restore(flags);
 
@@ -97,7 +124,10 @@ static int pxa_gpio_direction_output(struct gpio_chip *chip,
 	gpdr = pxa->regbase + GPDR_OFFSET;
 	local_irq_save(flags);
 	tmp = __raw_readl(gpdr);
-	tmp |= mask;
+	if (__gpio_is_inverted(chip->base + offset))
+		tmp &= ~mask;
+	else
+		tmp |= mask;
 	__raw_writel(tmp, gpdr);
 	local_irq_restore(flags);
 
@@ -173,10 +203,17 @@ static unsigned long GPIO_IRQ_mask[4];
  */
 static int __gpio_is_occupied(unsigned gpio)
 {
-	if (cpu_is_pxa25x() || cpu_is_pxa27x())
-		return GAFR(gpio) & (0x3 << (((gpio) & 0xf) * 2));
-	else
-		return 0;
+	if (cpu_is_pxa27x() || cpu_is_pxa25x()) {
+		int af = (GAFR(gpio) >> ((gpio & 0xf) * 2)) & 0x3;
+		int dir = GPDR(gpio) & GPIO_bit(gpio);
+
+		if (__gpio_is_inverted(gpio))
+			return af != 1 || dir == 0;
+		else
+			return af != 0 || dir != 0;
+	}
+
+	return 0;
 }
 
 static int pxa_gpio_irq_type(unsigned int irq, unsigned int type)
@@ -190,9 +227,8 @@ static int pxa_gpio_irq_type(unsigned int irq, unsigned int type)
 		/* Don't mess with enabled GPIOs using preconfigured edges or
 		 * GPIOs set to alternate function or to output during probe
 		 */
-		if ((GPIO_IRQ_rising_edge[idx] |
-		     GPIO_IRQ_falling_edge[idx] |
-		     GPDR(gpio)) & GPIO_bit(gpio))
+		if ((GPIO_IRQ_rising_edge[idx] & GPIO_bit(gpio)) ||
+		    (GPIO_IRQ_falling_edge[idx] & GPIO_bit(gpio)))
 			return 0;
 
 		if (__gpio_is_occupied(gpio))
@@ -201,7 +237,10 @@ static int pxa_gpio_irq_type(unsigned int irq, unsigned int type)
 		type = IRQ_TYPE_EDGE_RISING | IRQ_TYPE_EDGE_FALLING;
 	}
 
-	GPDR(gpio) &= ~GPIO_bit(gpio);
+	if (__gpio_is_inverted(gpio))
+		GPDR(gpio) |= GPIO_bit(gpio);
+	else
+		GPDR(gpio) &= ~GPIO_bit(gpio);
 
 	if (type & IRQ_TYPE_EDGE_RISING)
 		__set_bit(gpio, GPIO_IRQ_rising_edge);
diff --git a/arch/arm/mach-pxa/h5000.c b/arch/arm/mach-pxa/h5000.c
new file mode 100644
index 000000000000..da6e4422c0f3
--- /dev/null
+++ b/arch/arm/mach-pxa/h5000.c
@@ -0,0 +1,200 @@
+/*
+ * Hardware definitions for HP iPAQ h5xxx Handheld Computers
+ *
+ * Copyright 2000-2003  Hewlett-Packard Company.
+ * Copyright 2002       Jamey Hicks <jamey.hicks@hp.com>
+ * Copyright 2004-2005  Phil Blundell <pb@handhelds.org>
+ * Copyright 2007-2008  Anton Vorontsov <cbouatmailru@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * COMPAQ COMPUTER CORPORATION MAKES NO WARRANTIES, EXPRESSED OR IMPLIED,
+ * AS TO THE USEFULNESS OR CORRECTNESS OF THIS CODE OR ITS
+ * FITNESS FOR ANY PARTICULAR PURPOSE.
+ *
+ * Author: Jamey Hicks.
+ */
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/platform_device.h>
+#include <linux/mtd/mtd.h>
+#include <linux/mtd/partitions.h>
+#include <linux/mtd/physmap.h>
+#include <asm/mach-types.h>
+#include <asm/mach/arch.h>
+#include <asm/mach/map.h>
+#include <mach/h5000.h>
+#include <mach/pxa-regs.h>
+#include <mach/pxa2xx-regs.h>
+#include <mach/mfp-pxa25x.h>
+#include <mach/udc.h>
+#include "generic.h"
+
+/*
+ * Flash
+ */
+
+static struct mtd_partition h5000_flash0_partitions[] = {
+	{
+		.name = "bootldr",
+		.size = 0x00040000,
+		.offset = 0,
+		.mask_flags = MTD_WRITEABLE,
+	},
+	{
+		.name = "root",
+		.size = MTDPART_SIZ_FULL,
+		.offset = MTDPART_OFS_APPEND,
+	},
+};
+
+static struct mtd_partition h5000_flash1_partitions[] = {
+	{
+		.name = "second root",
+		.size = SZ_16M - 0x00040000,
+		.offset = 0,
+	},
+	{
+		.name = "asset",
+		.size = MTDPART_SIZ_FULL,
+		.offset = MTDPART_OFS_APPEND,
+		.mask_flags = MTD_WRITEABLE,
+	},
+};
+
+static struct physmap_flash_data h5000_flash0_data = {
+	.width = 4,
+	.parts = h5000_flash0_partitions,
+	.nr_parts = ARRAY_SIZE(h5000_flash0_partitions),
+};
+
+static struct physmap_flash_data h5000_flash1_data = {
+	.width = 4,
+	.parts = h5000_flash1_partitions,
+	.nr_parts = ARRAY_SIZE(h5000_flash1_partitions),
+};
+
+static struct resource h5000_flash0_resources = {
+	.start = PXA_CS0_PHYS,
+	.end = PXA_CS0_PHYS + SZ_32M - 1,
+	.flags = IORESOURCE_MEM | IORESOURCE_MEM_32BIT,
+};
+
+static struct resource h5000_flash1_resources = {
+	.start = PXA_CS0_PHYS + SZ_32M,
+	.end = PXA_CS0_PHYS + SZ_32M + SZ_16M - 1,
+	.flags = IORESOURCE_MEM | IORESOURCE_MEM_32BIT,
+};
+
+static struct platform_device h5000_flash[] = {
+	{
+		.name = "physmap-flash",
+		.id = 0,
+		.resource = &h5000_flash0_resources,
+		.num_resources = 1,
+		.dev = {
+			.platform_data = &h5000_flash0_data,
+		},
+	},
+	{
+		.name = "physmap-flash",
+		.id = 1,
+		.resource = &h5000_flash1_resources,
+		.num_resources = 1,
+		.dev = {
+			.platform_data = &h5000_flash1_data,
+		},
+	},
+};
+
+/*
+ * USB Device Controller
+ */
+
+static struct pxa2xx_udc_mach_info h5000_udc_mach_info __initdata = {
+	.gpio_pullup = H5000_GPIO_USB_PULLUP,
+};
+
+/*
+ * GPIO setup
+ */
+
+static unsigned long h5000_pin_config[] __initdata = {
+	/* Crystal and Clock Signals */
+	GPIO12_32KHz,
+
+	/* SDRAM and Static Memory I/O Signals */
+	GPIO15_nCS_1,
+	GPIO78_nCS_2,
+	GPIO79_nCS_3,
+	GPIO80_nCS_4,
+
+	/* FFUART */
+	GPIO34_FFUART_RXD,
+	GPIO35_FFUART_CTS,
+	GPIO36_FFUART_DCD,
+	GPIO37_FFUART_DSR,
+	GPIO38_FFUART_RI,
+	GPIO39_FFUART_TXD,
+	GPIO40_FFUART_DTR,
+	GPIO41_FFUART_RTS,
+
+	/* BTUART */
+	GPIO42_BTUART_RXD,
+	GPIO43_BTUART_TXD,
+	GPIO44_BTUART_CTS,
+	GPIO45_BTUART_RTS,
+
+	/* SSP1 */
+	GPIO23_SSP1_SCLK,
+	GPIO25_SSP1_TXD,
+	GPIO26_SSP1_RXD,
+};
+
+/*
+ * Localbus setup:
+ * CS0: Flash;
+ * CS1: MediaQ chip, select 16-bit bus and vlio;
+ * CS5: SAMCOP.
+ */
+
+static void fix_msc(void)
+{
+	MSC0 = 0x129c24f2;
+	MSC1 = 0x7ff424fa;
+	MSC2 = 0x7ff47ff4;
+
+	MDREFR |= 0x02080000;
+}
+
+/*
+ * Platform devices
+ */
+
+static struct platform_device *devices[] __initdata = {
+	&h5000_flash[0],
+	&h5000_flash[1],
+};
+
+static void __init h5000_init(void)
+{
+	fix_msc();
+
+	pxa2xx_mfp_config(ARRAY_AND_SIZE(h5000_pin_config));
+	pxa_set_udc_info(&h5000_udc_mach_info);
+	platform_add_devices(ARRAY_AND_SIZE(devices));
+}
+
+MACHINE_START(H5400, "HP iPAQ H5000")
+	.phys_io = 0x40000000,
+	.io_pg_offst = (io_p2v(0x40000000) >> 18) & 0xfffc,
+	.boot_params = 0xa0000100,
+	.map_io = pxa_map_io,
+	.init_irq = pxa25x_init_irq,
+	.timer = &pxa_timer,
+	.init_machine = h5000_init,
+MACHINE_END
diff --git a/arch/arm/mach-pxa/include/mach/clkdev.h b/arch/arm/mach-pxa/include/mach/clkdev.h
new file mode 100644
index 000000000000..04b37a89801c
--- /dev/null
+++ b/arch/arm/mach-pxa/include/mach/clkdev.h
@@ -0,0 +1,7 @@
+#ifndef __ASM_MACH_CLKDEV_H
+#define __ASM_MACH_CLKDEV_H
+
+#define __clk_get(clk) ({ 1; })
+#define __clk_put(clk) do { } while (0)
+
+#endif
diff --git a/arch/arm/mach-pxa/include/mach/h5000.h b/arch/arm/mach-pxa/include/mach/h5000.h
new file mode 100644
index 000000000000..2a5ae3802787
--- /dev/null
+++ b/arch/arm/mach-pxa/include/mach/h5000.h
@@ -0,0 +1,113 @@
+/*
+ * Hardware definitions for HP iPAQ h5xxx Handheld Computers
+ *
+ * Copyright(20)02 Hewlett-Packard Company.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * COMPAQ COMPUTER CORPORATION MAKES NO WARRANTIES, EXPRESSED OR IMPLIED,
+ * AS TO THE USEFULNESS OR CORRECTNESS OF THIS CODE OR ITS
+ * FITNESS FOR ANY PARTICULAR PURPOSE.
+ *
+ * Author: Jamey Hicks
+ */
+
+#ifndef __ASM_ARCH_H5000_H
+#define __ASM_ARCH_H5000_H
+
+#include <mach/mfp-pxa25x.h>
+
+/*
+ * CPU GPIOs
+ */
+
+#define H5000_GPIO_POWER_BUTTON   (0)
+#define H5000_GPIO_RESET_BUTTON_N (1)
+#define H5000_GPIO_OPT_INT        (2)
+#define H5000_GPIO_BACKUP_POWER   (3)
+#define H5000_GPIO_ACTION_BUTTON  (4)
+#define H5000_GPIO_COM_DCD_SOMETHING  (5) /* what is this really ? */
+/* 6 not connected */
+#define H5000_GPIO_RESET_BUTTON_AGAIN_N (7) /* connected to gpio 1 as well */
+/* 8 not connected */
+#define H5000_GPIO_RSO_N          (9)       /* reset output from max1702 which regulates 3.3 and 2.5 */
+#define H5000_GPIO_ASIC_INT_N   (10)       /* from companion asic */
+#define H5000_GPIO_BT_ENV_0     (11)       /* to LMX9814, set to 1 according to regdump */
+/*(12) not connected */
+#define H5000_GPIO_BT_ENV_1     (13)       /* to LMX9814, set to 1 according to regdump */
+#define H5000_GPIO_BT_WU        (14)       /* from LMX9814, Defined as HOST_WAKEUP in the LMX9820 data sheet */
+/*(15) is CS1# */
+/*(16) not connected */
+/*(17) not connected */
+/*(18) is pcmcia ready */
+/*(19) is dreq1 */
+/*(20) is dreq0 */
+#define H5000_GPIO_OE_RD_NWR	(21)       /* output enable on rd/nwr signal to companion asic */
+/*(22) is not connected */
+#define H5000_GPIO_OPT_SPI_CLK  (23)       /* to extension pack */
+#define H5000_GPIO_OPT_SPI_CS_N (24)       /* to extension pack */
+#define H5000_GPIO_OPT_SPI_DOUT (25)       /* to extension pack */
+#define H5000_GPIO_OPT_SPI_DIN  (26)       /* to extension pack */
+/*(27) not connected */
+#define H5000_GPIO_I2S_BITCLK   (28)       /* connected to AC97 codec */
+#define H5000_GPIO_I2S_DATAOUT  (29)       /* connected to AC97 codec */
+#define H5000_GPIO_I2S_DATAIN   (30)       /* connected to AC97 codec */
+#define H5000_GPIO_I2S_LRCLK    (31)       /* connected to AC97 codec */
+#define H5000_GPIO_I2S_SYSCLK   (32)       /* connected to AC97 codec */
+/*(33) is CS5# */
+#define H5000_GPIO_COM_RXD      (34)       /* connected to cradle/cable connector */
+#define H5000_GPIO_COM_CTS      (35)       /* connected to cradle/cable connector */
+#define H5000_GPIO_COM_DCD      (36)       /* connected to cradle/cable connector */
+#define H5000_GPIO_COM_DSR      (37)       /* connected to cradle/cable connector */
+#define H5000_GPIO_COM_RI       (38)       /* connected to cradle/cable connector */
+#define H5000_GPIO_COM_TXD      (39)       /* connected to cradle/cable connector */
+#define H5000_GPIO_COM_DTR      (40)       /* connected to cradle/cable connector */
+#define H5000_GPIO_COM_RTS      (41)       /* connected to cradle/cable connector */
+
+#define H5000_GPIO_BT_RXD       (42)       /* connected to BT (LMX9814) */
+#define H5000_GPIO_BT_TXD       (43)       /* connected to BT (LMX9814) */
+#define H5000_GPIO_BT_CTS       (44)       /* connected to BT (LMX9814) */
+#define H5000_GPIO_BT_RTS       (45)       /* connected to BT (LMX9814) */
+
+#define H5000_GPIO_IRDA_RXD     (46)
+#define H5000_GPIO_IRDA_TXD     (47)
+
+#define H5000_GPIO_POE_N        (48)       /* used for pcmcia */
+#define H5000_GPIO_PWE_N        (49)       /* used for pcmcia */
+#define H5000_GPIO_PIOR_N       (50)       /* used for pcmcia */
+#define H5000_GPIO_PIOW_N       (51)       /* used for pcmcia */
+#define H5000_GPIO_PCE1_N       (52)       /* used for pcmcia */
+#define H5000_GPIO_PCE2_N       (53)       /* used for pcmcia */
+#define H5000_GPIO_PSKTSEL      (54)       /* used for pcmcia */
+#define H5000_GPIO_PREG_N       (55)       /* used for pcmcia */
+#define H5000_GPIO_PWAIT_N      (56)       /* used for pcmcia */
+#define H5000_GPIO_IOIS16_N     (57)       /* used for pcmcia */
+
+#define H5000_GPIO_IRDA_SD      (58)       /* to hsdl3002 sd */
+/*(59) not connected */
+#define H5000_GPIO_POWER_SD_N   (60)       /* controls power to SD */
+#define H5000_GPIO_POWER_RS232_N	(61)       /* inverted FORCEON to rs232 transceiver */
+#define H5000_GPIO_POWER_ACCEL_N	(62)       /* controls power to accel */
+/*(63) is not connected */
+#define H5000_GPIO_OPT_NVRAM    (64)       /* controls power to expansion pack */
+#define H5000_GPIO_CHG_EN       (65)       /* to sc801 en */
+#define H5000_GPIO_USB_PULLUP   (66)       /* USB d+ pullup via 1.5K resistor */
+#define H5000_GPIO_BT_2V8_N     (67)       /* 2.8V used by bluetooth */
+#define H5000_GPIO_EXT_CHG_RATE (68)       /* enables external charging rate */
+/*(69) is not connected */
+#define H5000_GPIO_CIR_RESET    (70)       /* consumer IR reset */
+#define H5000_GPIO_POWER_LIGHT_SENSOR_N	(71)
+#define H5000_GPIO_BT_M_RESET   (72)
+#define H5000_GPIO_STD_CHG_RATE (73)
+#define H5000_GPIO_SD_WP_N      (74)
+#define H5000_GPIO_MOTOR_ON_N   (75)       /* external pullup on this */
+#define H5000_GPIO_HEADPHONE_DETECT	(76)
+#define H5000_GPIO_USB_CHG_RATE (77)       /* select rate for charging via usb */
+/*(78) is CS2# */
+/*(79) is CS3# */
+/*(80) is CS4# */
+
+#endif /* __ASM_ARCH_H5000_H */
diff --git a/arch/arm/mach-pxa/include/mach/hardware.h b/arch/arm/mach-pxa/include/mach/hardware.h
index a582a6d9b92b..e2d6784aa7ef 100644
--- a/arch/arm/mach-pxa/include/mach/hardware.h
+++ b/arch/arm/mach-pxa/include/mach/hardware.h
@@ -102,6 +102,9 @@
  *  PXA930	B0	0x69056835	0x5E643013
  *  PXA930	B1	0x69056837	0x7E643013
  *  PXA930	B2	0x69056838	0x8E643013
+ *
+ *  PXA935	A0	0x56056931	0x1E653013
+ *  PXA935	B0	0x56056936	0x6E653013
  */
 #ifdef CONFIG_PXA25x
 #define __cpu_is_pxa210(id)				\
@@ -178,12 +181,22 @@
 #define __cpu_is_pxa930(id)				\
 	({						\
 		unsigned int _id = (id) >> 4 & 0xfff;	\
-		_id == 0x683;		\
+		_id == 0x683;				\
 	 })
 #else
 #define __cpu_is_pxa930(id)	(0)
 #endif
 
+#ifdef CONFIG_CPU_PXA935
+#define __cpu_is_pxa935(id)				\
+	({						\
+		unsigned int _id = (id) >> 4 & 0xfff;	\
+		_id == 0x693;				\
+	 })
+#else
+#define __cpu_is_pxa935(id)	(0)
+#endif
+
 #define cpu_is_pxa210()					\
 	({						\
 		__cpu_is_pxa210(read_cpuid_id());	\
@@ -204,8 +217,6 @@
 		__cpu_is_pxa25x(read_cpuid_id());	\
 	})
 
-extern int cpu_is_pxa26x(void);
-
 #define cpu_is_pxa27x()					\
 	({						\
 		__cpu_is_pxa27x(read_cpuid_id());	\
@@ -232,6 +243,12 @@ extern int cpu_is_pxa26x(void);
 		__cpu_is_pxa930(id);			\
 	 })
 
+#define cpu_is_pxa935()					\
+	({						\
+		unsigned int id = read_cpuid(CPUID_ID);	\
+		__cpu_is_pxa935(id);			\
+	 })
+
 /*
  * CPUID Core Generation Bit
  * <= 0x2 for pxa21x/pxa25x/pxa26x/pxa27x
@@ -249,6 +266,12 @@ extern int cpu_is_pxa26x(void);
 		_id == 0x3;				\
 	 })
 
+#define __cpu_is_pxa9xx(id)				\
+	({						\
+		unsigned int _id = (id) >> 4 & 0xfff;	\
+		_id == 0x683 || _id == 0x693;		\
+	 })
+
 #define cpu_is_pxa2xx()					\
 	({						\
 		__cpu_is_pxa2xx(read_cpuid_id());	\
@@ -259,21 +282,10 @@ extern int cpu_is_pxa26x(void);
 		__cpu_is_pxa3xx(read_cpuid_id());	\
 	 })
 
-/*
- * Handy routine to set GPIO alternate functions
- */
-extern int pxa_gpio_mode( int gpio_mode );
-
-/*
- * Return GPIO level, nonzero means high, zero is low
- */
-extern int pxa_gpio_get_value(unsigned gpio);
-
-/*
- * Set output GPIO level
- */
-extern void pxa_gpio_set_value(unsigned gpio, int value);
-
+#define cpu_is_pxa9xx()					\
+	({						\
+		__cpu_is_pxa9xx(read_cpuid_id());	\
+	 })
 /*
  * return current memory and LCD clock frequency in units of 10kHz
  */
diff --git a/arch/arm/mach-pxa/include/mach/io.h b/arch/arm/mach-pxa/include/mach/io.h
index 600fd4f76603..262691fb97d8 100644
--- a/arch/arm/mach-pxa/include/mach/io.h
+++ b/arch/arm/mach-pxa/include/mach/io.h
@@ -6,15 +6,13 @@
 #ifndef __ASM_ARM_ARCH_IO_H
 #define __ASM_ARM_ARCH_IO_H
 
-#include <mach/hardware.h>
-
 #define IO_SPACE_LIMIT 0xffffffff
 
 /*
  * We don't actually have real ISA nor PCI buses, but there is so many
  * drivers out there that might just work if we fake them...
  */
-#define __io(a)			((void __iomem *)(a))
-#define __mem_pci(a)		(a)
+#define __io(a)		__typesafe_io(a)
+#define __mem_pci(a)	(a)
 
 #endif
diff --git a/arch/arm/mach-pxa/include/mach/memory.h b/arch/arm/mach-pxa/include/mach/memory.h
index 59aef89808d6..f626730ee42e 100644
--- a/arch/arm/mach-pxa/include/mach/memory.h
+++ b/arch/arm/mach-pxa/include/mach/memory.h
@@ -18,16 +18,6 @@
 #define PHYS_OFFSET	UL(0xa0000000)
 
 /*
- * Virtual view <-> DMA view memory address translations
- * virt_to_bus: Used to translate the virtual address to an
- *		address suitable to be passed to set_dma_addr
- * bus_to_virt: Used to convert an address for DMA operations
- *		to an address that the kernel can use.
- */
-#define __virt_to_bus(x)	 __virt_to_phys(x)
-#define __bus_to_virt(x)	 __phys_to_virt(x)
-
-/*
  * The nodes are matched with the physical SDRAM banks as follows:
  *
  * 	node 0:  0xa0000000-0xa3ffffff	-->  0xc0000000-0xc3ffffff
@@ -47,6 +37,7 @@ void cmx2xx_pci_adjust_zones(int node, unsigned long *size,
 	cmx2xx_pci_adjust_zones(node, size, holes)
 
 #define ISA_DMA_THRESHOLD	(PHYS_OFFSET + SZ_64M - 1)
+#define MAX_DMA_ADDRESS		(PAGE_OFFSET + SZ_64M)
 #endif
 
 #endif
diff --git a/arch/arm/mach-pxa/include/mach/mfp-pxa25x.h b/arch/arm/mach-pxa/include/mach/mfp-pxa25x.h
index 617cab2cc8d0..a72869b73ee3 100644
--- a/arch/arm/mach-pxa/include/mach/mfp-pxa25x.h
+++ b/arch/arm/mach-pxa/include/mach/mfp-pxa25x.h
@@ -158,4 +158,35 @@
 #define GPIO76_LCD_PCLK		MFP_CFG_OUT(GPIO76, AF2, DRIVE_LOW)
 #define GPIO77_LCD_BIAS		MFP_CFG_OUT(GPIO77, AF2, DRIVE_LOW)
 
+#ifdef CONFIG_CPU_PXA26x
+/* GPIO */
+#define GPIO85_GPIO		MFP_CFG_IN(GPIO85, AF0)
+#define GPIO86_GPIO		MFP_CFG_IN(GPIO86, AF1)
+#define GPIO87_GPIO		MFP_CFG_IN(GPIO87, AF1)
+#define GPIO88_GPIO		MFP_CFG_IN(GPIO88, AF1)
+#define GPIO89_GPIO		MFP_CFG_IN(GPIO89, AF1)
+
+/* SDRAM */
+#define GPIO86_nSDCS2		MFP_CFG_OUT(GPIO86, AF0, DRIVE_HIGH)
+#define GPIO87_nSDCS3		MFP_CFG_OUT(GPIO87, AF0, DRIVE_HIGH)
+#define GPIO88_RDnWR		MFP_CFG_OUT(GPIO88, AF0, DRIVE_HIGH)
+#define GPIO89_nACRESET		MFP_CFG_OUT(GPIO89, AF0, DRIVE_HIGH)
+
+/* USB */
+#define GPIO9_USB_RCV		MFP_CFG_IN(GPIO9, AF1)
+#define GPIO32_USB_VP		MFP_CFG_IN(GPIO32, AF2)
+#define GPIO34_USB_VM		MFP_CFG_IN(GPIO34, AF2)
+#define GPIO39_USB_VPO		MFP_CFG_OUT(GPIO39, AF3, DRIVE_LOW)
+#define GPIO56_USB_VMO		MFP_CFG_OUT(GPIO56, AF1, DRIVE_LOW)
+#define GPIO57_USB_nOE		MFP_CFG_OUT(GPIO57, AF1, DRIVE_HIGH)
+
+/* ASSP */
+#define GPIO28_ASSP_BITCLK_IN	MFP_CFG_IN(GPIO28, AF3)
+#define GPIO28_ASSP_BITCLK_OUT	MFP_CFG_OUT(GPIO28, AF3, DRIVE_LOW)
+#define GPIO29_ASSP_RXD		MFP_CFG_IN(GPIO29, AF3)
+#define GPIO30_ASSP_TXD		MFP_CFG_OUT(GPIO30, AF3, DRIVE_LOW)
+#define GPIO31_ASSP_SFRM_IN	MFP_CFG_IN(GPIO31, AF1)
+#define GPIO31_ASSP_SFRM_OUT	MFP_CFG_OUT(GPIO31, AF3, DRIVE_LOW)
+#endif
+
 #endif /* __ASM_ARCH_MFP_PXA25X_H */
diff --git a/arch/arm/mach-pxa/include/mach/mfp-pxa27x.h b/arch/arm/mach-pxa/include/mach/mfp-pxa27x.h
index 122bdbd53182..da4f85a4f990 100644
--- a/arch/arm/mach-pxa/include/mach/mfp-pxa27x.h
+++ b/arch/arm/mach-pxa/include/mach/mfp-pxa27x.h
@@ -11,6 +11,12 @@
 #include <mach/mfp.h>
 #include <mach/mfp-pxa2xx.h>
 
+/* Note: GPIO3/GPIO4 will be driven by Power I2C when PCFR/PI2C_EN
+ * bit is set, regardless of the GPIO configuration
+ */
+#define GPIO3_GPIO		MFP_CFG_IN(GPIO3, AF0)
+#define GPIO4_GPIO		MFP_CFG_IN(GPIO4, AF0)
+
 /* GPIO */
 #define GPIO85_GPIO		MFP_CFG_IN(GPIO85, AF0)
 #define GPIO86_GPIO		MFP_CFG_IN(GPIO86, AF0)
diff --git a/arch/arm/mach-pxa/include/mach/mioa701.h b/arch/arm/mach-pxa/include/mach/mioa701.h
index 8483cb511831..02868447b0b1 100644
--- a/arch/arm/mach-pxa/include/mach/mioa701.h
+++ b/arch/arm/mach-pxa/include/mach/mioa701.h
@@ -10,12 +10,14 @@
 	 (MFP_PIN(pin) | MFP_##af | MFP_DIR_OUT | MFP_LPM_##state))
 
 /* Global GPIOs */
-#define GPIO9_CHARGE_nEN			9
+#define GPIO9_CHARGE_EN				9
 #define GPIO18_POWEROFF				18
 #define GPIO87_LCD_POWER			87
+#define GPIO96_AC_DETECT			96
+#define GPIO80_MAYBE_CHARGE_VDROP		80	/* Drop of 88mV */
 
 /* USB */
-#define GPIO13_USB_DETECT			13
+#define GPIO13_nUSB_DETECT			13
 #define GPIO22_USB_ENABLE			22
 
 /* SDIO bits */
@@ -24,7 +26,10 @@
 #define GPIO91_SDIO_EN				91
 
 /* Bluetooth */
+#define GPIO14_BT_nACTIVITY			14
 #define GPIO83_BT_ON				83
+#define GPIO77_BT_UNKNOWN1			77
+#define GPIO86_BT_MAYBE_nRESET			86
 
 /* GPS */
 #define GPIO23_GPS_UNKNOWN1			23
diff --git a/arch/arm/mach-pxa/include/mach/pxa-regs.h b/arch/arm/mach-pxa/include/mach/pxa-regs.h
index 15295d960000..31d615aa7723 100644
--- a/arch/arm/mach-pxa/include/mach/pxa-regs.h
+++ b/arch/arm/mach-pxa/include/mach/pxa-regs.h
@@ -13,6 +13,7 @@
 #ifndef __PXA_REGS_H
 #define __PXA_REGS_H
 
+#include <mach/hardware.h>
 
 /*
  * PXA Chip selects
@@ -123,298 +124,6 @@
 #define DCMD_WIDTH4	(3 << 14)	/* 4 byte width (Word) */
 #define DCMD_LENGTH	0x01fff		/* length mask (max = 8K - 1) */
 
-
-/*
- * UARTs
- */
-
-/* Full Function UART (FFUART) */
-#define FFUART		FFRBR
-#define FFRBR		__REG(0x40100000)  /* Receive Buffer Register (read only) */
-#define FFTHR		__REG(0x40100000)  /* Transmit Holding Register (write only) */
-#define FFIER		__REG(0x40100004)  /* Interrupt Enable Register (read/write) */
-#define FFIIR		__REG(0x40100008)  /* Interrupt ID Register (read only) */
-#define FFFCR		__REG(0x40100008)  /* FIFO Control Register (write only) */
-#define FFLCR		__REG(0x4010000C)  /* Line Control Register (read/write) */
-#define FFMCR		__REG(0x40100010)  /* Modem Control Register (read/write) */
-#define FFLSR		__REG(0x40100014)  /* Line Status Register (read only) */
-#define FFMSR		__REG(0x40100018)  /* Modem Status Register (read only) */
-#define FFSPR		__REG(0x4010001C)  /* Scratch Pad Register (read/write) */
-#define FFISR		__REG(0x40100020)  /* Infrared Selection Register (read/write) */
-#define FFDLL		__REG(0x40100000)  /* Divisor Latch Low Register (DLAB = 1) (read/write) */
-#define FFDLH		__REG(0x40100004)  /* Divisor Latch High Register (DLAB = 1) (read/write) */
-
-/* Bluetooth UART (BTUART) */
-#define BTUART		BTRBR
-#define BTRBR		__REG(0x40200000)  /* Receive Buffer Register (read only) */
-#define BTTHR		__REG(0x40200000)  /* Transmit Holding Register (write only) */
-#define BTIER		__REG(0x40200004)  /* Interrupt Enable Register (read/write) */
-#define BTIIR		__REG(0x40200008)  /* Interrupt ID Register (read only) */
-#define BTFCR		__REG(0x40200008)  /* FIFO Control Register (write only) */
-#define BTLCR		__REG(0x4020000C)  /* Line Control Register (read/write) */
-#define BTMCR		__REG(0x40200010)  /* Modem Control Register (read/write) */
-#define BTLSR		__REG(0x40200014)  /* Line Status Register (read only) */
-#define BTMSR		__REG(0x40200018)  /* Modem Status Register (read only) */
-#define BTSPR		__REG(0x4020001C)  /* Scratch Pad Register (read/write) */
-#define BTISR		__REG(0x40200020)  /* Infrared Selection Register (read/write) */
-#define BTDLL		__REG(0x40200000)  /* Divisor Latch Low Register (DLAB = 1) (read/write) */
-#define BTDLH		__REG(0x40200004)  /* Divisor Latch High Register (DLAB = 1) (read/write) */
-
-/* Standard UART (STUART) */
-#define STUART		STRBR
-#define STRBR		__REG(0x40700000)  /* Receive Buffer Register (read only) */
-#define STTHR		__REG(0x40700000)  /* Transmit Holding Register (write only) */
-#define STIER		__REG(0x40700004)  /* Interrupt Enable Register (read/write) */
-#define STIIR		__REG(0x40700008)  /* Interrupt ID Register (read only) */
-#define STFCR		__REG(0x40700008)  /* FIFO Control Register (write only) */
-#define STLCR		__REG(0x4070000C)  /* Line Control Register (read/write) */
-#define STMCR		__REG(0x40700010)  /* Modem Control Register (read/write) */
-#define STLSR		__REG(0x40700014)  /* Line Status Register (read only) */
-#define STMSR		__REG(0x40700018)  /* Reserved */
-#define STSPR		__REG(0x4070001C)  /* Scratch Pad Register (read/write) */
-#define STISR		__REG(0x40700020)  /* Infrared Selection Register (read/write) */
-#define STDLL		__REG(0x40700000)  /* Divisor Latch Low Register (DLAB = 1) (read/write) */
-#define STDLH		__REG(0x40700004)  /* Divisor Latch High Register (DLAB = 1) (read/write) */
-
-/* Hardware UART (HWUART) */
-#define HWUART		HWRBR
-#define HWRBR		__REG(0x41600000)  /* Receive Buffer Register (read only) */
-#define HWTHR		__REG(0x41600000)  /* Transmit Holding Register (write only) */
-#define HWIER		__REG(0x41600004)  /* Interrupt Enable Register (read/write) */
-#define HWIIR		__REG(0x41600008)  /* Interrupt ID Register (read only) */
-#define HWFCR		__REG(0x41600008)  /* FIFO Control Register (write only) */
-#define HWLCR		__REG(0x4160000C)  /* Line Control Register (read/write) */
-#define HWMCR		__REG(0x41600010)  /* Modem Control Register (read/write) */
-#define HWLSR		__REG(0x41600014)  /* Line Status Register (read only) */
-#define HWMSR		__REG(0x41600018)  /* Modem Status Register (read only) */
-#define HWSPR		__REG(0x4160001C)  /* Scratch Pad Register (read/write) */
-#define HWISR		__REG(0x41600020)  /* Infrared Selection Register (read/write) */
-#define HWFOR		__REG(0x41600024)  /* Receive FIFO Occupancy Register (read only) */
-#define HWABR		__REG(0x41600028)  /* Auto-Baud Control Register (read/write) */
-#define HWACR		__REG(0x4160002C)  /* Auto-Baud Count Register (read only) */
-#define HWDLL		__REG(0x41600000)  /* Divisor Latch Low Register (DLAB = 1) (read/write) */
-#define HWDLH		__REG(0x41600004)  /* Divisor Latch High Register (DLAB = 1) (read/write) */
-
-#define IER_DMAE	(1 << 7)	/* DMA Requests Enable */
-#define IER_UUE		(1 << 6)	/* UART Unit Enable */
-#define IER_NRZE	(1 << 5)	/* NRZ coding Enable */
-#define IER_RTIOE	(1 << 4)	/* Receiver Time Out Interrupt Enable */
-#define IER_MIE		(1 << 3)	/* Modem Interrupt Enable */
-#define IER_RLSE	(1 << 2)	/* Receiver Line Status Interrupt Enable */
-#define IER_TIE		(1 << 1)	/* Transmit Data request Interrupt Enable */
-#define IER_RAVIE	(1 << 0)	/* Receiver Data Available Interrupt Enable */
-
-#define IIR_FIFOES1	(1 << 7)	/* FIFO Mode Enable Status */
-#define IIR_FIFOES0	(1 << 6)	/* FIFO Mode Enable Status */
-#define IIR_TOD		(1 << 3)	/* Time Out Detected */
-#define IIR_IID2	(1 << 2)	/* Interrupt Source Encoded */
-#define IIR_IID1	(1 << 1)	/* Interrupt Source Encoded */
-#define IIR_IP		(1 << 0)	/* Interrupt Pending (active low) */
-
-#define FCR_ITL2	(1 << 7)	/* Interrupt Trigger Level */
-#define FCR_ITL1	(1 << 6)	/* Interrupt Trigger Level */
-#define FCR_RESETTF	(1 << 2)	/* Reset Transmitter FIFO */
-#define FCR_RESETRF	(1 << 1)	/* Reset Receiver FIFO */
-#define FCR_TRFIFOE	(1 << 0)	/* Transmit and Receive FIFO Enable */
-#define FCR_ITL_1	(0)
-#define FCR_ITL_8	(FCR_ITL1)
-#define FCR_ITL_16	(FCR_ITL2)
-#define FCR_ITL_32	(FCR_ITL2|FCR_ITL1)
-
-#define LCR_DLAB	(1 << 7)	/* Divisor Latch Access Bit */
-#define LCR_SB		(1 << 6)	/* Set Break */
-#define LCR_STKYP	(1 << 5)	/* Sticky Parity */
-#define LCR_EPS		(1 << 4)	/* Even Parity Select */
-#define LCR_PEN		(1 << 3)	/* Parity Enable */
-#define LCR_STB		(1 << 2)	/* Stop Bit */
-#define LCR_WLS1	(1 << 1)	/* Word Length Select */
-#define LCR_WLS0	(1 << 0)	/* Word Length Select */
-
-#define LSR_FIFOE	(1 << 7)	/* FIFO Error Status */
-#define LSR_TEMT	(1 << 6)	/* Transmitter Empty */
-#define LSR_TDRQ	(1 << 5)	/* Transmit Data Request */
-#define LSR_BI		(1 << 4)	/* Break Interrupt */
-#define LSR_FE		(1 << 3)	/* Framing Error */
-#define LSR_PE		(1 << 2)	/* Parity Error */
-#define LSR_OE		(1 << 1)	/* Overrun Error */
-#define LSR_DR		(1 << 0)	/* Data Ready */
-
-#define MCR_LOOP	(1 << 4)
-#define MCR_OUT2	(1 << 3)	/* force MSR_DCD in loopback mode */
-#define MCR_OUT1	(1 << 2)	/* force MSR_RI in loopback mode */
-#define MCR_RTS		(1 << 1)	/* Request to Send */
-#define MCR_DTR		(1 << 0)	/* Data Terminal Ready */
-
-#define MSR_DCD		(1 << 7)	/* Data Carrier Detect */
-#define MSR_RI		(1 << 6)	/* Ring Indicator */
-#define MSR_DSR		(1 << 5)	/* Data Set Ready */
-#define MSR_CTS		(1 << 4)	/* Clear To Send */
-#define MSR_DDCD	(1 << 3)	/* Delta Data Carrier Detect */
-#define MSR_TERI	(1 << 2)	/* Trailing Edge Ring Indicator */
-#define MSR_DDSR	(1 << 1)	/* Delta Data Set Ready */
-#define MSR_DCTS	(1 << 0)	/* Delta Clear To Send */
-
-/*
- * IrSR (Infrared Selection Register)
- */
-#define STISR_RXPL      (1 << 4)        /* Receive Data Polarity */
-#define STISR_TXPL      (1 << 3)        /* Transmit Data Polarity */
-#define STISR_XMODE     (1 << 2)        /* Transmit Pulse Width Select */
-#define STISR_RCVEIR    (1 << 1)        /* Receiver SIR Enable */
-#define STISR_XMITIR    (1 << 0)        /* Transmitter SIR Enable */
-
-
-/*
- * I2C registers - moved into drivers/i2c/busses/i2c-pxa.c
- */
-
-/*
- * Serial Audio Controller - moved into sound/soc/pxa/pxa2xx-i2s.c
- */
-
-/*
- * AC97 Controller registers
- */
-
-#define POCR		__REG(0x40500000)  /* PCM Out Control Register */
-#define POCR_FEIE	(1 << 3)	/* FIFO Error Interrupt Enable */
-#define POCR_FSRIE	(1 << 1)	/* FIFO Service Request Interrupt Enable */
-
-#define PICR		__REG(0x40500004)  /* PCM In Control Register */
-#define PICR_FEIE	(1 << 3)	/* FIFO Error Interrupt Enable */
-#define PICR_FSRIE	(1 << 1)	/* FIFO Service Request Interrupt Enable */
-
-#define MCCR		__REG(0x40500008)  /* Mic In Control Register */
-#define MCCR_FEIE	(1 << 3)	/* FIFO Error Interrupt Enable */
-#define MCCR_FSRIE	(1 << 1)	/* FIFO Service Request Interrupt Enable */
-
-#define GCR		__REG(0x4050000C)  /* Global Control Register */
-#ifdef CONFIG_PXA3xx
-#define GCR_CLKBPB	(1 << 31)	/* Internal clock enable */
-#endif
-#define GCR_nDMAEN	(1 << 24)	/* non DMA Enable */
-#define GCR_CDONE_IE	(1 << 19)	/* Command Done Interrupt Enable */
-#define GCR_SDONE_IE	(1 << 18)	/* Status Done Interrupt Enable */
-#define GCR_SECRDY_IEN	(1 << 9)	/* Secondary Ready Interrupt Enable */
-#define GCR_PRIRDY_IEN	(1 << 8)	/* Primary Ready Interrupt Enable */
-#define GCR_SECRES_IEN	(1 << 5)	/* Secondary Resume Interrupt Enable */
-#define GCR_PRIRES_IEN	(1 << 4)	/* Primary Resume Interrupt Enable */
-#define GCR_ACLINK_OFF	(1 << 3)	/* AC-link Shut Off */
-#define GCR_WARM_RST	(1 << 2)	/* AC97 Warm Reset */
-#define GCR_COLD_RST	(1 << 1)	/* AC'97 Cold Reset (0 = active) */
-#define GCR_GIE		(1 << 0)	/* Codec GPI Interrupt Enable */
-
-#define POSR		__REG(0x40500010)  /* PCM Out Status Register */
-#define POSR_FIFOE	(1 << 4)	/* FIFO error */
-#define POSR_FSR	(1 << 2)	/* FIFO Service Request */
-
-#define PISR		__REG(0x40500014)  /* PCM In Status Register */
-#define PISR_FIFOE	(1 << 4)	/* FIFO error */
-#define PISR_EOC	(1 << 3)	/* DMA End-of-Chain (exclusive clear) */
-#define PISR_FSR	(1 << 2)	/* FIFO Service Request */
-
-#define MCSR		__REG(0x40500018)  /* Mic In Status Register */
-#define MCSR_FIFOE	(1 << 4)	/* FIFO error */
-#define MCSR_EOC	(1 << 3)	/* DMA End-of-Chain (exclusive clear) */
-#define MCSR_FSR	(1 << 2)	/* FIFO Service Request */
-
-#define GSR		__REG(0x4050001C)  /* Global Status Register */
-#define GSR_CDONE	(1 << 19)	/* Command Done */
-#define GSR_SDONE	(1 << 18)	/* Status Done */
-#define GSR_RDCS	(1 << 15)	/* Read Completion Status */
-#define GSR_BIT3SLT12	(1 << 14)	/* Bit 3 of slot 12 */
-#define GSR_BIT2SLT12	(1 << 13)	/* Bit 2 of slot 12 */
-#define GSR_BIT1SLT12	(1 << 12)	/* Bit 1 of slot 12 */
-#define GSR_SECRES	(1 << 11)	/* Secondary Resume Interrupt */
-#define GSR_PRIRES	(1 << 10)	/* Primary Resume Interrupt */
-#define GSR_SCR		(1 << 9)	/* Secondary Codec Ready */
-#define GSR_PCR		(1 << 8)	/*  Primary Codec Ready */
-#define GSR_MCINT	(1 << 7)	/* Mic In Interrupt */
-#define GSR_POINT	(1 << 6)	/* PCM Out Interrupt */
-#define GSR_PIINT	(1 << 5)	/* PCM In Interrupt */
-#define GSR_ACOFFD	(1 << 3)	/* AC-link Shut Off Done */
-#define GSR_MOINT	(1 << 2)	/* Modem Out Interrupt */
-#define GSR_MIINT	(1 << 1)	/* Modem In Interrupt */
-#define GSR_GSCI	(1 << 0)	/* Codec GPI Status Change Interrupt */
-
-#define CAR		__REG(0x40500020)  /* CODEC Access Register */
-#define CAR_CAIP	(1 << 0)	/* Codec Access In Progress */
-
-#define PCDR		__REG(0x40500040)  /* PCM FIFO Data Register */
-#define MCDR		__REG(0x40500060)  /* Mic-in FIFO Data Register */
-
-#define MOCR		__REG(0x40500100)  /* Modem Out Control Register */
-#define MOCR_FEIE	(1 << 3)	/* FIFO Error */
-#define MOCR_FSRIE	(1 << 1)	/* FIFO Service Request Interrupt Enable */
-
-#define MICR		__REG(0x40500108)  /* Modem In Control Register */
-#define MICR_FEIE	(1 << 3)	/* FIFO Error */
-#define MICR_FSRIE	(1 << 1)	/* FIFO Service Request Interrupt Enable */
-
-#define MOSR		__REG(0x40500110)  /* Modem Out Status Register */
-#define MOSR_FIFOE	(1 << 4)	/* FIFO error */
-#define MOSR_FSR	(1 << 2)	/* FIFO Service Request */
-
-#define MISR		__REG(0x40500118)  /* Modem In Status Register */
-#define MISR_FIFOE	(1 << 4)	/* FIFO error */
-#define MISR_EOC	(1 << 3)	/* DMA End-of-Chain (exclusive clear) */
-#define MISR_FSR	(1 << 2)	/* FIFO Service Request */
-
-#define MODR		__REG(0x40500140)  /* Modem FIFO Data Register */
-
-#define PAC_REG_BASE	__REG(0x40500200)  /* Primary Audio Codec */
-#define SAC_REG_BASE	__REG(0x40500300)  /* Secondary Audio Codec */
-#define PMC_REG_BASE	__REG(0x40500400)  /* Primary Modem Codec */
-#define SMC_REG_BASE	__REG(0x40500500)  /* Secondary Modem Codec */
-
-
-/*
- * Fast Infrared Communication Port
- */
-
-#define FICP		__REG(0x40800000)  /* Start of FICP area */
-#define ICCR0		__REG(0x40800000)  /* ICP Control Register 0 */
-#define ICCR1		__REG(0x40800004)  /* ICP Control Register 1 */
-#define ICCR2		__REG(0x40800008)  /* ICP Control Register 2 */
-#define ICDR		__REG(0x4080000c)  /* ICP Data Register */
-#define ICSR0		__REG(0x40800014)  /* ICP Status Register 0 */
-#define ICSR1		__REG(0x40800018)  /* ICP Status Register 1 */
-
-#define ICCR0_AME	(1 << 7)	/* Address match enable */
-#define ICCR0_TIE	(1 << 6)	/* Transmit FIFO interrupt enable */
-#define ICCR0_RIE	(1 << 5)	/* Recieve FIFO interrupt enable */
-#define ICCR0_RXE	(1 << 4)	/* Receive enable */
-#define ICCR0_TXE	(1 << 3)	/* Transmit enable */
-#define ICCR0_TUS	(1 << 2)	/* Transmit FIFO underrun select */
-#define ICCR0_LBM	(1 << 1)	/* Loopback mode */
-#define ICCR0_ITR	(1 << 0)	/* IrDA transmission */
-
-#define ICCR2_RXP       (1 << 3)	/* Receive Pin Polarity select */
-#define ICCR2_TXP       (1 << 2)	/* Transmit Pin Polarity select */
-#define ICCR2_TRIG	(3 << 0)	/* Receive FIFO Trigger threshold */
-#define ICCR2_TRIG_8    (0 << 0)	/* 	>= 8 bytes */
-#define ICCR2_TRIG_16   (1 << 0)	/*	>= 16 bytes */
-#define ICCR2_TRIG_32   (2 << 0)	/*	>= 32 bytes */
-
-#ifdef CONFIG_PXA27x
-#define ICSR0_EOC	(1 << 6)	/* DMA End of Descriptor Chain */
-#endif
-#define ICSR0_FRE	(1 << 5)	/* Framing error */
-#define ICSR0_RFS	(1 << 4)	/* Receive FIFO service request */
-#define ICSR0_TFS	(1 << 3)	/* Transnit FIFO service request */
-#define ICSR0_RAB	(1 << 2)	/* Receiver abort */
-#define ICSR0_TUR	(1 << 1)	/* Trunsmit FIFO underun */
-#define ICSR0_EIF	(1 << 0)	/* End/Error in FIFO */
-
-#define ICSR1_ROR	(1 << 6)	/* Receiver FIFO underrun  */
-#define ICSR1_CRE	(1 << 5)	/* CRC error */
-#define ICSR1_EOF	(1 << 4)	/* End of frame */
-#define ICSR1_TNF	(1 << 3)	/* Transmit FIFO not full */
-#define ICSR1_RNE	(1 << 2)	/* Receive FIFO not empty */
-#define ICSR1_TBY	(1 << 1)	/* Tramsmiter busy flag */
-#define ICSR1_RSY	(1 << 0)	/* Recevier synchronized flag */
-
-
 /*
  * Real Time Clock
  */
@@ -463,19 +172,6 @@
 
 
 /*
- * Pulse Width Modulator
- */
-
-#define PWM_CTRL0	__REG(0x40B00000)  /* PWM 0 Control Register */
-#define PWM_PWDUTY0	__REG(0x40B00004)  /* PWM 0 Duty Cycle Register */
-#define PWM_PERVAL0	__REG(0x40B00008)  /* PWM 0 Period Control Register */
-
-#define PWM_CTRL1	__REG(0x40C00000)  /* PWM 1Control Register */
-#define PWM_PWDUTY1	__REG(0x40C00004)  /* PWM 1 Duty Cycle Register */
-#define PWM_PERVAL1	__REG(0x40C00008)  /* PWM 1 Period Control Register */
-
-
-/*
  * Interrupt Controller
  */
 
@@ -496,19 +192,6 @@
  * General Purpose I/O
  */
 
-#define GPIO0_BASE	((void __iomem *)io_p2v(0x40E00000))
-#define GPIO1_BASE	((void __iomem *)io_p2v(0x40E00004))
-#define GPIO2_BASE	((void __iomem *)io_p2v(0x40E00008))
-#define GPIO3_BASE	((void __iomem *)io_p2v(0x40E00100))
-
-#define GPLR_OFFSET	0x00
-#define GPDR_OFFSET	0x0C
-#define GPSR_OFFSET	0x18
-#define GPCR_OFFSET	0x24
-#define GRER_OFFSET	0x30
-#define GFER_OFFSET	0x3C
-#define GEDR_OFFSET	0x48
-
 #define GPLR0		__REG(0x40E00000)  /* GPIO Pin-Level Register GPIO<31:0> */
 #define GPLR1		__REG(0x40E00004)  /* GPIO Pin-Level Register GPIO<63:32> */
 #define GPLR2		__REG(0x40E00008)  /* GPIO Pin-Level Register GPIO<80:64> */
@@ -558,10 +241,6 @@
 
 #define GPIO_bit(x)	(1 << ((x) & 0x1f))
 
-#if defined(CONFIG_PXA27x) || defined(CONFIG_PXA3xx)
-
-/* Interrupt Controller */
-
 #define _GPLR(x)	__REG2(0x40E00000, ((x) & 0x60) >> 3)
 #define _GPDR(x)	__REG2(0x40E0000C, ((x) & 0x60) >> 3)
 #define _GPSR(x)	__REG2(0x40E00018, ((x) & 0x60) >> 3)
@@ -580,189 +259,5 @@
 #define GEDR(x)		(*((((x) & 0x7f) < 96) ? &_GEDR(x) : &GEDR3))
 #define GAFR(x)		(*((((x) & 0x7f) < 96) ? &_GAFR(x) : \
 			 ((((x) & 0x7f) < 112) ? &GAFR3_L : &GAFR3_U)))
-#else
-
-#define GPLR(x)		__REG2(0x40E00000, ((x) & 0x60) >> 3)
-#define GPDR(x)		__REG2(0x40E0000C, ((x) & 0x60) >> 3)
-#define GPSR(x)		__REG2(0x40E00018, ((x) & 0x60) >> 3)
-#define GPCR(x)		__REG2(0x40E00024, ((x) & 0x60) >> 3)
-#define GRER(x)		__REG2(0x40E00030, ((x) & 0x60) >> 3)
-#define GFER(x)		__REG2(0x40E0003C, ((x) & 0x60) >> 3)
-#define GEDR(x)		__REG2(0x40E00048, ((x) & 0x60) >> 3)
-#define GAFR(x)		__REG2(0x40E00054, ((x) & 0x70) >> 2)
-
-#endif
-
-/*
- * Power Manager - see pxa2xx-regs.h
- */
-
-/*
- * SSP Serial Port Registers - see arch/arm/mach-pxa/include/mach/regs-ssp.h
- */
-
-/*
- * MultiMediaCard (MMC) controller - see drivers/mmc/host/pxamci.h
- */
-
-/*
- * Core Clock - see arch/arm/mach-pxa/include/mach/pxa2xx-regs.h
- */
-
-#ifdef CONFIG_PXA27x
-
-/* Camera Interface */
-#define CICR0		__REG(0x50000000)
-#define CICR1		__REG(0x50000004)
-#define CICR2		__REG(0x50000008)
-#define CICR3		__REG(0x5000000C)
-#define CICR4		__REG(0x50000010)
-#define CISR		__REG(0x50000014)
-#define CIFR		__REG(0x50000018)
-#define CITOR		__REG(0x5000001C)
-#define CIBR0		__REG(0x50000028)
-#define CIBR1		__REG(0x50000030)
-#define CIBR2		__REG(0x50000038)
-
-#define CICR0_DMAEN	(1 << 31)	/* DMA request enable */
-#define CICR0_PAR_EN	(1 << 30)	/* Parity enable */
-#define CICR0_SL_CAP_EN	(1 << 29)	/* Capture enable for slave mode */
-#define CICR0_ENB	(1 << 28)	/* Camera interface enable */
-#define CICR0_DIS	(1 << 27)	/* Camera interface disable */
-#define CICR0_SIM	(0x7 << 24)	/* Sensor interface mode mask */
-#define CICR0_TOM	(1 << 9)	/* Time-out mask */
-#define CICR0_RDAVM	(1 << 8)	/* Receive-data-available mask */
-#define CICR0_FEM	(1 << 7)	/* FIFO-empty mask */
-#define CICR0_EOLM	(1 << 6)	/* End-of-line mask */
-#define CICR0_PERRM	(1 << 5)	/* Parity-error mask */
-#define CICR0_QDM	(1 << 4)	/* Quick-disable mask */
-#define CICR0_CDM	(1 << 3)	/* Disable-done mask */
-#define CICR0_SOFM	(1 << 2)	/* Start-of-frame mask */
-#define CICR0_EOFM	(1 << 1)	/* End-of-frame mask */
-#define CICR0_FOM	(1 << 0)	/* FIFO-overrun mask */
-
-#define CICR1_TBIT	(1 << 31)	/* Transparency bit */
-#define CICR1_RGBT_CONV	(0x3 << 29)	/* RGBT conversion mask */
-#define CICR1_PPL	(0x7ff << 15)	/* Pixels per line mask */
-#define CICR1_RGB_CONV	(0x7 << 12)	/* RGB conversion mask */
-#define CICR1_RGB_F	(1 << 11)	/* RGB format */
-#define CICR1_YCBCR_F	(1 << 10)	/* YCbCr format */
-#define CICR1_RGB_BPP	(0x7 << 7)	/* RGB bis per pixel mask */
-#define CICR1_RAW_BPP	(0x3 << 5)	/* Raw bis per pixel mask */
-#define CICR1_COLOR_SP	(0x3 << 3)	/* Color space mask */
-#define CICR1_DW	(0x7 << 0)	/* Data width mask */
-
-#define CICR2_BLW	(0xff << 24)	/* Beginning-of-line pixel clock
-					   wait count mask */
-#define CICR2_ELW	(0xff << 16)	/* End-of-line pixel clock
-					   wait count mask */
-#define CICR2_HSW	(0x3f << 10)	/* Horizontal sync pulse width mask */
-#define CICR2_BFPW	(0x3f << 3)	/* Beginning-of-frame pixel clock
-					   wait count mask */
-#define CICR2_FSW	(0x7 << 0)	/* Frame stabilization
-					   wait count mask */
-
-#define CICR3_BFW	(0xff << 24)	/* Beginning-of-frame line clock
-					   wait count mask */
-#define CICR3_EFW	(0xff << 16)	/* End-of-frame line clock
-					   wait count mask */
-#define CICR3_VSW	(0x3f << 10)	/* Vertical sync pulse width mask */
-#define CICR3_BFPW	(0x3f << 3)	/* Beginning-of-frame pixel clock
-					   wait count mask */
-#define CICR3_LPF	(0x7ff << 0)	/* Lines per frame mask */
-
-#define CICR4_MCLK_DLY	(0x3 << 24)	/* MCLK Data Capture Delay mask */
-#define CICR4_PCLK_EN	(1 << 23)	/* Pixel clock enable */
-#define CICR4_PCP	(1 << 22)	/* Pixel clock polarity */
-#define CICR4_HSP	(1 << 21)	/* Horizontal sync polarity */
-#define CICR4_VSP	(1 << 20)	/* Vertical sync polarity */
-#define CICR4_MCLK_EN	(1 << 19)	/* MCLK enable */
-#define CICR4_FR_RATE	(0x7 << 8)	/* Frame rate mask */
-#define CICR4_DIV	(0xff << 0)	/* Clock divisor mask */
-
-#define CISR_FTO	(1 << 15)	/* FIFO time-out */
-#define CISR_RDAV_2	(1 << 14)	/* Channel 2 receive data available */
-#define CISR_RDAV_1	(1 << 13)	/* Channel 1 receive data available */
-#define CISR_RDAV_0	(1 << 12)	/* Channel 0 receive data available */
-#define CISR_FEMPTY_2	(1 << 11)	/* Channel 2 FIFO empty */
-#define CISR_FEMPTY_1	(1 << 10)	/* Channel 1 FIFO empty */
-#define CISR_FEMPTY_0	(1 << 9)	/* Channel 0 FIFO empty */
-#define CISR_EOL	(1 << 8)	/* End of line */
-#define CISR_PAR_ERR	(1 << 7)	/* Parity error */
-#define CISR_CQD	(1 << 6)	/* Camera interface quick disable */
-#define CISR_CDD	(1 << 5)	/* Camera interface disable done */
-#define CISR_SOF	(1 << 4)	/* Start of frame */
-#define CISR_EOF	(1 << 3)	/* End of frame */
-#define CISR_IFO_2	(1 << 2)	/* FIFO overrun for Channel 2 */
-#define CISR_IFO_1	(1 << 1)	/* FIFO overrun for Channel 1 */
-#define CISR_IFO_0	(1 << 0)	/* FIFO overrun for Channel 0 */
-
-#define CIFR_FLVL2	(0x7f << 23)	/* FIFO 2 level mask */
-#define CIFR_FLVL1	(0x7f << 16)	/* FIFO 1 level mask */
-#define CIFR_FLVL0	(0xff << 8)	/* FIFO 0 level mask */
-#define CIFR_THL_0	(0x3 << 4)	/* Threshold Level for Channel 0 FIFO */
-#define CIFR_RESET_F	(1 << 3)	/* Reset input FIFOs */
-#define CIFR_FEN2	(1 << 2)	/* FIFO enable for channel 2 */
-#define CIFR_FEN1	(1 << 1)	/* FIFO enable for channel 1 */
-#define CIFR_FEN0	(1 << 0)	/* FIFO enable for channel 0 */
-
-#define SRAM_SIZE		0x40000 /* 4x64K  */
-
-#define SRAM_MEM_PHYS		0x5C000000
-
-#define IMPMCR		__REG(0x58000000) /* IM Power Management Control Reg */
-#define IMPMSR		__REG(0x58000008) /* IM Power Management Status Reg */
-
-#define IMPMCR_PC3		(0x3 << 22) /* Bank 3 Power Control */
-#define IMPMCR_PC3_RUN_MODE	(0x0 << 22) /*   Run mode */
-#define IMPMCR_PC3_STANDBY_MODE	(0x1 << 22) /*   Standby mode */
-#define IMPMCR_PC3_AUTO_MODE	(0x3 << 22) /*   Automatically controlled */
-
-#define IMPMCR_PC2		(0x3 << 20) /* Bank 2 Power Control */
-#define IMPMCR_PC2_RUN_MODE	(0x0 << 20) /*   Run mode */
-#define IMPMCR_PC2_STANDBY_MODE	(0x1 << 20) /*   Standby mode */
-#define IMPMCR_PC2_AUTO_MODE	(0x3 << 20) /*   Automatically controlled */
-
-#define IMPMCR_PC1		(0x3 << 18) /* Bank 1 Power Control */
-#define IMPMCR_PC1_RUN_MODE	(0x0 << 18) /*   Run mode */
-#define IMPMCR_PC1_STANDBY_MODE	(0x1 << 18) /*   Standby mode */
-#define IMPMCR_PC1_AUTO_MODE	(0x3 << 18) /*   Automatically controlled */
-
-#define IMPMCR_PC0		(0x3 << 16) /* Bank 0 Power Control */
-#define IMPMCR_PC0_RUN_MODE	(0x0 << 16) /*   Run mode */
-#define IMPMCR_PC0_STANDBY_MODE	(0x1 << 16) /*   Standby mode */
-#define IMPMCR_PC0_AUTO_MODE	(0x3 << 16) /*   Automatically controlled */
-
-#define IMPMCR_AW3		(1 << 11) /* Bank 3 Automatic Wake-up enable */
-#define IMPMCR_AW2		(1 << 10) /* Bank 2 Automatic Wake-up enable */
-#define IMPMCR_AW1		(1 << 9)  /* Bank 1 Automatic Wake-up enable */
-#define IMPMCR_AW0		(1 << 8)  /* Bank 0 Automatic Wake-up enable */
-
-#define IMPMCR_DST		(0xFF << 0) /* Delay Standby Time, ms */
-
-#define IMPMSR_PS3		(0x3 << 6) /* Bank 3 Power Status: */
-#define IMPMSR_PS3_RUN_MODE	(0x0 << 6) /*    Run mode */
-#define IMPMSR_PS3_STANDBY_MODE	(0x1 << 6) /*    Standby mode */
-
-#define IMPMSR_PS2		(0x3 << 4) /* Bank 2 Power Status: */
-#define IMPMSR_PS2_RUN_MODE	(0x0 << 4) /*    Run mode */
-#define IMPMSR_PS2_STANDBY_MODE	(0x1 << 4) /*    Standby mode */
-
-#define IMPMSR_PS1		(0x3 << 2) /* Bank 1 Power Status: */
-#define IMPMSR_PS1_RUN_MODE	(0x0 << 2) /*    Run mode */
-#define IMPMSR_PS1_STANDBY_MODE	(0x1 << 2) /*    Standby mode */
-
-#define IMPMSR_PS0		(0x3 << 0) /* Bank 0 Power Status: */
-#define IMPMSR_PS0_RUN_MODE	(0x0 << 0) /*    Run mode */
-#define IMPMSR_PS0_STANDBY_MODE	(0x1 << 0) /*    Standby mode */
-
-#endif
-
-/* PWRMODE register M field values */
-
-#define PWRMODE_IDLE		0x1
-#define PWRMODE_STANDBY		0x2
-#define PWRMODE_SLEEP		0x3
-#define PWRMODE_DEEPSLEEP	0x7
 
 #endif
diff --git a/arch/arm/mach-pxa/include/mach/pxa2xx-gpio.h b/arch/arm/mach-pxa/include/mach/pxa2xx-gpio.h
index 6ef1dd09970b..d83393e25273 100644
--- a/arch/arm/mach-pxa/include/mach/pxa2xx-gpio.h
+++ b/arch/arm/mach-pxa/include/mach/pxa2xx-gpio.h
@@ -365,4 +365,9 @@
 #define GPIO117_I2CSCL_MD	(117 | GPIO_ALT_FN_1_IN)
 #define GPIO118_I2CSDA_MD	(118 | GPIO_ALT_FN_1_IN)
 
+/*
+ * Handy routine to set GPIO alternate functions
+ */
+extern int pxa_gpio_mode( int gpio_mode );
+
 #endif /* __ASM_ARCH_PXA2XX_GPIO_H */
diff --git a/arch/arm/mach-pxa/include/mach/pxa2xx-regs.h b/arch/arm/mach-pxa/include/mach/pxa2xx-regs.h
index 806ecfea44bf..77102d695cc7 100644
--- a/arch/arm/mach-pxa/include/mach/pxa2xx-regs.h
+++ b/arch/arm/mach-pxa/include/mach/pxa2xx-regs.h
@@ -49,6 +49,11 @@
 #define MECR_NOS	(1 << 0)	/* Number Of Sockets: 0 -> 1 sock, 1 -> 2 sock */
 #define MECR_CIT	(1 << 1)	/* Card Is There: 0 -> no card, 1 -> card inserted */
 
+#define MDCNFG_DE0	(1 << 0)	/* SDRAM Bank 0 Enable */
+#define MDCNFG_DE1	(1 << 1)	/* SDRAM Bank 1 Enable */
+#define MDCNFG_DE2	(1 << 16)	/* SDRAM Bank 2 Enable */
+#define MDCNFG_DE3	(1 << 17)	/* SDRAM Bank 3 Enable */
+
 #define MDREFR_K0DB4	(1 << 29)	/* SDCLK0 Divide by 4 Control/Status */
 #define MDREFR_K2FREE	(1 << 25)	/* SDRAM Free-Running Control */
 #define MDREFR_K1FREE	(1 << 24)	/* SDRAM Free-Running Control */
@@ -243,4 +248,11 @@
 #define OSCC_OON	(1 << 1)	/* 32.768kHz OON (write-once only bit) */
 #define OSCC_OOK	(1 << 0)	/* 32.768kHz OOK (read-only bit) */
 
+/* PWRMODE register M field values */
+
+#define PWRMODE_IDLE		0x1
+#define PWRMODE_STANDBY		0x2
+#define PWRMODE_SLEEP		0x3
+#define PWRMODE_DEEPSLEEP	0x7
+
 #endif
diff --git a/arch/arm/mach-pxa/include/mach/regs-ac97.h b/arch/arm/mach-pxa/include/mach/regs-ac97.h
new file mode 100644
index 000000000000..e41b9d202b8c
--- /dev/null
+++ b/arch/arm/mach-pxa/include/mach/regs-ac97.h
@@ -0,0 +1,99 @@
+#ifndef __ASM_ARCH_REGS_AC97_H
+#define __ASM_ARCH_REGS_AC97_H
+
+/*
+ * AC97 Controller registers
+ */
+
+#define POCR		__REG(0x40500000)  /* PCM Out Control Register */
+#define POCR_FEIE	(1 << 3)	/* FIFO Error Interrupt Enable */
+#define POCR_FSRIE	(1 << 1)	/* FIFO Service Request Interrupt Enable */
+
+#define PICR		__REG(0x40500004)  /* PCM In Control Register */
+#define PICR_FEIE	(1 << 3)	/* FIFO Error Interrupt Enable */
+#define PICR_FSRIE	(1 << 1)	/* FIFO Service Request Interrupt Enable */
+
+#define MCCR		__REG(0x40500008)  /* Mic In Control Register */
+#define MCCR_FEIE	(1 << 3)	/* FIFO Error Interrupt Enable */
+#define MCCR_FSRIE	(1 << 1)	/* FIFO Service Request Interrupt Enable */
+
+#define GCR		__REG(0x4050000C)  /* Global Control Register */
+#ifdef CONFIG_PXA3xx
+#define GCR_CLKBPB	(1 << 31)	/* Internal clock enable */
+#endif
+#define GCR_nDMAEN	(1 << 24)	/* non DMA Enable */
+#define GCR_CDONE_IE	(1 << 19)	/* Command Done Interrupt Enable */
+#define GCR_SDONE_IE	(1 << 18)	/* Status Done Interrupt Enable */
+#define GCR_SECRDY_IEN	(1 << 9)	/* Secondary Ready Interrupt Enable */
+#define GCR_PRIRDY_IEN	(1 << 8)	/* Primary Ready Interrupt Enable */
+#define GCR_SECRES_IEN	(1 << 5)	/* Secondary Resume Interrupt Enable */
+#define GCR_PRIRES_IEN	(1 << 4)	/* Primary Resume Interrupt Enable */
+#define GCR_ACLINK_OFF	(1 << 3)	/* AC-link Shut Off */
+#define GCR_WARM_RST	(1 << 2)	/* AC97 Warm Reset */
+#define GCR_COLD_RST	(1 << 1)	/* AC'97 Cold Reset (0 = active) */
+#define GCR_GIE		(1 << 0)	/* Codec GPI Interrupt Enable */
+
+#define POSR		__REG(0x40500010)  /* PCM Out Status Register */
+#define POSR_FIFOE	(1 << 4)	/* FIFO error */
+#define POSR_FSR	(1 << 2)	/* FIFO Service Request */
+
+#define PISR		__REG(0x40500014)  /* PCM In Status Register */
+#define PISR_FIFOE	(1 << 4)	/* FIFO error */
+#define PISR_EOC	(1 << 3)	/* DMA End-of-Chain (exclusive clear) */
+#define PISR_FSR	(1 << 2)	/* FIFO Service Request */
+
+#define MCSR		__REG(0x40500018)  /* Mic In Status Register */
+#define MCSR_FIFOE	(1 << 4)	/* FIFO error */
+#define MCSR_EOC	(1 << 3)	/* DMA End-of-Chain (exclusive clear) */
+#define MCSR_FSR	(1 << 2)	/* FIFO Service Request */
+
+#define GSR		__REG(0x4050001C)  /* Global Status Register */
+#define GSR_CDONE	(1 << 19)	/* Command Done */
+#define GSR_SDONE	(1 << 18)	/* Status Done */
+#define GSR_RDCS	(1 << 15)	/* Read Completion Status */
+#define GSR_BIT3SLT12	(1 << 14)	/* Bit 3 of slot 12 */
+#define GSR_BIT2SLT12	(1 << 13)	/* Bit 2 of slot 12 */
+#define GSR_BIT1SLT12	(1 << 12)	/* Bit 1 of slot 12 */
+#define GSR_SECRES	(1 << 11)	/* Secondary Resume Interrupt */
+#define GSR_PRIRES	(1 << 10)	/* Primary Resume Interrupt */
+#define GSR_SCR		(1 << 9)	/* Secondary Codec Ready */
+#define GSR_PCR		(1 << 8)	/*  Primary Codec Ready */
+#define GSR_MCINT	(1 << 7)	/* Mic In Interrupt */
+#define GSR_POINT	(1 << 6)	/* PCM Out Interrupt */
+#define GSR_PIINT	(1 << 5)	/* PCM In Interrupt */
+#define GSR_ACOFFD	(1 << 3)	/* AC-link Shut Off Done */
+#define GSR_MOINT	(1 << 2)	/* Modem Out Interrupt */
+#define GSR_MIINT	(1 << 1)	/* Modem In Interrupt */
+#define GSR_GSCI	(1 << 0)	/* Codec GPI Status Change Interrupt */
+
+#define CAR		__REG(0x40500020)  /* CODEC Access Register */
+#define CAR_CAIP	(1 << 0)	/* Codec Access In Progress */
+
+#define PCDR		__REG(0x40500040)  /* PCM FIFO Data Register */
+#define MCDR		__REG(0x40500060)  /* Mic-in FIFO Data Register */
+
+#define MOCR		__REG(0x40500100)  /* Modem Out Control Register */
+#define MOCR_FEIE	(1 << 3)	/* FIFO Error */
+#define MOCR_FSRIE	(1 << 1)	/* FIFO Service Request Interrupt Enable */
+
+#define MICR		__REG(0x40500108)  /* Modem In Control Register */
+#define MICR_FEIE	(1 << 3)	/* FIFO Error */
+#define MICR_FSRIE	(1 << 1)	/* FIFO Service Request Interrupt Enable */
+
+#define MOSR		__REG(0x40500110)  /* Modem Out Status Register */
+#define MOSR_FIFOE	(1 << 4)	/* FIFO error */
+#define MOSR_FSR	(1 << 2)	/* FIFO Service Request */
+
+#define MISR		__REG(0x40500118)  /* Modem In Status Register */
+#define MISR_FIFOE	(1 << 4)	/* FIFO error */
+#define MISR_EOC	(1 << 3)	/* DMA End-of-Chain (exclusive clear) */
+#define MISR_FSR	(1 << 2)	/* FIFO Service Request */
+
+#define MODR		__REG(0x40500140)  /* Modem FIFO Data Register */
+
+#define PAC_REG_BASE	__REG(0x40500200)  /* Primary Audio Codec */
+#define SAC_REG_BASE	__REG(0x40500300)  /* Secondary Audio Codec */
+#define PMC_REG_BASE	__REG(0x40500400)  /* Primary Modem Codec */
+#define SMC_REG_BASE	__REG(0x40500500)  /* Secondary Modem Codec */
+
+#endif /* __ASM_ARCH_REGS_AC97_H */
diff --git a/arch/arm/mach-pxa/include/mach/regs-uart.h b/arch/arm/mach-pxa/include/mach/regs-uart.h
new file mode 100644
index 000000000000..55aeb7fb72f6
--- /dev/null
+++ b/arch/arm/mach-pxa/include/mach/regs-uart.h
@@ -0,0 +1,143 @@
+#ifndef __ASM_ARCH_REGS_UART_H
+#define __ASM_ARCH_REGS_UART_H
+
+/*
+ * UARTs
+ */
+
+/* Full Function UART (FFUART) */
+#define FFUART		FFRBR
+#define FFRBR		__REG(0x40100000)  /* Receive Buffer Register (read only) */
+#define FFTHR		__REG(0x40100000)  /* Transmit Holding Register (write only) */
+#define FFIER		__REG(0x40100004)  /* Interrupt Enable Register (read/write) */
+#define FFIIR		__REG(0x40100008)  /* Interrupt ID Register (read only) */
+#define FFFCR		__REG(0x40100008)  /* FIFO Control Register (write only) */
+#define FFLCR		__REG(0x4010000C)  /* Line Control Register (read/write) */
+#define FFMCR		__REG(0x40100010)  /* Modem Control Register (read/write) */
+#define FFLSR		__REG(0x40100014)  /* Line Status Register (read only) */
+#define FFMSR		__REG(0x40100018)  /* Modem Status Register (read only) */
+#define FFSPR		__REG(0x4010001C)  /* Scratch Pad Register (read/write) */
+#define FFISR		__REG(0x40100020)  /* Infrared Selection Register (read/write) */
+#define FFDLL		__REG(0x40100000)  /* Divisor Latch Low Register (DLAB = 1) (read/write) */
+#define FFDLH		__REG(0x40100004)  /* Divisor Latch High Register (DLAB = 1) (read/write) */
+
+/* Bluetooth UART (BTUART) */
+#define BTUART		BTRBR
+#define BTRBR		__REG(0x40200000)  /* Receive Buffer Register (read only) */
+#define BTTHR		__REG(0x40200000)  /* Transmit Holding Register (write only) */
+#define BTIER		__REG(0x40200004)  /* Interrupt Enable Register (read/write) */
+#define BTIIR		__REG(0x40200008)  /* Interrupt ID Register (read only) */
+#define BTFCR		__REG(0x40200008)  /* FIFO Control Register (write only) */
+#define BTLCR		__REG(0x4020000C)  /* Line Control Register (read/write) */
+#define BTMCR		__REG(0x40200010)  /* Modem Control Register (read/write) */
+#define BTLSR		__REG(0x40200014)  /* Line Status Register (read only) */
+#define BTMSR		__REG(0x40200018)  /* Modem Status Register (read only) */
+#define BTSPR		__REG(0x4020001C)  /* Scratch Pad Register (read/write) */
+#define BTISR		__REG(0x40200020)  /* Infrared Selection Register (read/write) */
+#define BTDLL		__REG(0x40200000)  /* Divisor Latch Low Register (DLAB = 1) (read/write) */
+#define BTDLH		__REG(0x40200004)  /* Divisor Latch High Register (DLAB = 1) (read/write) */
+
+/* Standard UART (STUART) */
+#define STUART		STRBR
+#define STRBR		__REG(0x40700000)  /* Receive Buffer Register (read only) */
+#define STTHR		__REG(0x40700000)  /* Transmit Holding Register (write only) */
+#define STIER		__REG(0x40700004)  /* Interrupt Enable Register (read/write) */
+#define STIIR		__REG(0x40700008)  /* Interrupt ID Register (read only) */
+#define STFCR		__REG(0x40700008)  /* FIFO Control Register (write only) */
+#define STLCR		__REG(0x4070000C)  /* Line Control Register (read/write) */
+#define STMCR		__REG(0x40700010)  /* Modem Control Register (read/write) */
+#define STLSR		__REG(0x40700014)  /* Line Status Register (read only) */
+#define STMSR		__REG(0x40700018)  /* Reserved */
+#define STSPR		__REG(0x4070001C)  /* Scratch Pad Register (read/write) */
+#define STISR		__REG(0x40700020)  /* Infrared Selection Register (read/write) */
+#define STDLL		__REG(0x40700000)  /* Divisor Latch Low Register (DLAB = 1) (read/write) */
+#define STDLH		__REG(0x40700004)  /* Divisor Latch High Register (DLAB = 1) (read/write) */
+
+/* Hardware UART (HWUART) */
+#define HWUART		HWRBR
+#define HWRBR		__REG(0x41600000)  /* Receive Buffer Register (read only) */
+#define HWTHR		__REG(0x41600000)  /* Transmit Holding Register (write only) */
+#define HWIER		__REG(0x41600004)  /* Interrupt Enable Register (read/write) */
+#define HWIIR		__REG(0x41600008)  /* Interrupt ID Register (read only) */
+#define HWFCR		__REG(0x41600008)  /* FIFO Control Register (write only) */
+#define HWLCR		__REG(0x4160000C)  /* Line Control Register (read/write) */
+#define HWMCR		__REG(0x41600010)  /* Modem Control Register (read/write) */
+#define HWLSR		__REG(0x41600014)  /* Line Status Register (read only) */
+#define HWMSR		__REG(0x41600018)  /* Modem Status Register (read only) */
+#define HWSPR		__REG(0x4160001C)  /* Scratch Pad Register (read/write) */
+#define HWISR		__REG(0x41600020)  /* Infrared Selection Register (read/write) */
+#define HWFOR		__REG(0x41600024)  /* Receive FIFO Occupancy Register (read only) */
+#define HWABR		__REG(0x41600028)  /* Auto-Baud Control Register (read/write) */
+#define HWACR		__REG(0x4160002C)  /* Auto-Baud Count Register (read only) */
+#define HWDLL		__REG(0x41600000)  /* Divisor Latch Low Register (DLAB = 1) (read/write) */
+#define HWDLH		__REG(0x41600004)  /* Divisor Latch High Register (DLAB = 1) (read/write) */
+
+#define IER_DMAE	(1 << 7)	/* DMA Requests Enable */
+#define IER_UUE		(1 << 6)	/* UART Unit Enable */
+#define IER_NRZE	(1 << 5)	/* NRZ coding Enable */
+#define IER_RTIOE	(1 << 4)	/* Receiver Time Out Interrupt Enable */
+#define IER_MIE		(1 << 3)	/* Modem Interrupt Enable */
+#define IER_RLSE	(1 << 2)	/* Receiver Line Status Interrupt Enable */
+#define IER_TIE		(1 << 1)	/* Transmit Data request Interrupt Enable */
+#define IER_RAVIE	(1 << 0)	/* Receiver Data Available Interrupt Enable */
+
+#define IIR_FIFOES1	(1 << 7)	/* FIFO Mode Enable Status */
+#define IIR_FIFOES0	(1 << 6)	/* FIFO Mode Enable Status */
+#define IIR_TOD		(1 << 3)	/* Time Out Detected */
+#define IIR_IID2	(1 << 2)	/* Interrupt Source Encoded */
+#define IIR_IID1	(1 << 1)	/* Interrupt Source Encoded */
+#define IIR_IP		(1 << 0)	/* Interrupt Pending (active low) */
+
+#define FCR_ITL2	(1 << 7)	/* Interrupt Trigger Level */
+#define FCR_ITL1	(1 << 6)	/* Interrupt Trigger Level */
+#define FCR_RESETTF	(1 << 2)	/* Reset Transmitter FIFO */
+#define FCR_RESETRF	(1 << 1)	/* Reset Receiver FIFO */
+#define FCR_TRFIFOE	(1 << 0)	/* Transmit and Receive FIFO Enable */
+#define FCR_ITL_1	(0)
+#define FCR_ITL_8	(FCR_ITL1)
+#define FCR_ITL_16	(FCR_ITL2)
+#define FCR_ITL_32	(FCR_ITL2|FCR_ITL1)
+
+#define LCR_DLAB	(1 << 7)	/* Divisor Latch Access Bit */
+#define LCR_SB		(1 << 6)	/* Set Break */
+#define LCR_STKYP	(1 << 5)	/* Sticky Parity */
+#define LCR_EPS		(1 << 4)	/* Even Parity Select */
+#define LCR_PEN		(1 << 3)	/* Parity Enable */
+#define LCR_STB		(1 << 2)	/* Stop Bit */
+#define LCR_WLS1	(1 << 1)	/* Word Length Select */
+#define LCR_WLS0	(1 << 0)	/* Word Length Select */
+
+#define LSR_FIFOE	(1 << 7)	/* FIFO Error Status */
+#define LSR_TEMT	(1 << 6)	/* Transmitter Empty */
+#define LSR_TDRQ	(1 << 5)	/* Transmit Data Request */
+#define LSR_BI		(1 << 4)	/* Break Interrupt */
+#define LSR_FE		(1 << 3)	/* Framing Error */
+#define LSR_PE		(1 << 2)	/* Parity Error */
+#define LSR_OE		(1 << 1)	/* Overrun Error */
+#define LSR_DR		(1 << 0)	/* Data Ready */
+
+#define MCR_LOOP	(1 << 4)
+#define MCR_OUT2	(1 << 3)	/* force MSR_DCD in loopback mode */
+#define MCR_OUT1	(1 << 2)	/* force MSR_RI in loopback mode */
+#define MCR_RTS		(1 << 1)	/* Request to Send */
+#define MCR_DTR		(1 << 0)	/* Data Terminal Ready */
+
+#define MSR_DCD		(1 << 7)	/* Data Carrier Detect */
+#define MSR_RI		(1 << 6)	/* Ring Indicator */
+#define MSR_DSR		(1 << 5)	/* Data Set Ready */
+#define MSR_CTS		(1 << 4)	/* Clear To Send */
+#define MSR_DDCD	(1 << 3)	/* Delta Data Carrier Detect */
+#define MSR_TERI	(1 << 2)	/* Trailing Edge Ring Indicator */
+#define MSR_DDSR	(1 << 1)	/* Delta Data Set Ready */
+#define MSR_DCTS	(1 << 0)	/* Delta Clear To Send */
+
+/*
+ * IrSR (Infrared Selection Register)
+ */
+#define STISR_RXPL      (1 << 4)        /* Receive Data Polarity */
+#define STISR_TXPL      (1 << 3)        /* Transmit Data Polarity */
+#define STISR_XMODE     (1 << 2)        /* Transmit Pulse Width Select */
+#define STISR_RCVEIR    (1 << 1)        /* Receiver SIR Enable */
+#define STISR_XMITIR    (1 << 0)        /* Transmitter SIR Enable */
+
+#endif /* __ASM_ARCH_REGS_UART_H */
diff --git a/arch/arm/mach-pxa/include/mach/uncompress.h b/arch/arm/mach-pxa/include/mach/uncompress.h
index 21e3e890af98..a9a4f302b6ef 100644
--- a/arch/arm/mach-pxa/include/mach/uncompress.h
+++ b/arch/arm/mach-pxa/include/mach/uncompress.h
@@ -10,7 +10,7 @@
  */
 
 #include <linux/serial_reg.h>
-#include <mach/pxa-regs.h>
+#include <mach/regs-uart.h>
 #include <asm/mach-types.h>
 
 #define __REG(x)       ((volatile unsigned long *)x)
diff --git a/arch/arm/mach-pxa/littleton.c b/arch/arm/mach-pxa/littleton.c
index b4d00aba0e31..5609f52e36b1 100644
--- a/arch/arm/mach-pxa/littleton.c
+++ b/arch/arm/mach-pxa/littleton.c
@@ -20,6 +20,7 @@
 #include <linux/delay.h>
 #include <linux/platform_device.h>
 #include <linux/clk.h>
+#include <linux/gpio.h>
 #include <linux/spi/spi.h>
 #include <linux/smc91x.h>
 
@@ -36,7 +37,6 @@
 
 #include <mach/pxa-regs.h>
 #include <mach/mfp-pxa300.h>
-#include <mach/gpio.h>
 #include <mach/pxafb.h>
 #include <mach/ssp.h>
 #include <mach/pxa2xx_spi.h>
diff --git a/arch/arm/mach-pxa/magician.c b/arch/arm/mach-pxa/magician.c
index 519138bc5f85..bf59cec27def 100644
--- a/arch/arm/mach-pxa/magician.c
+++ b/arch/arm/mach-pxa/magician.c
@@ -123,6 +123,10 @@ static unsigned long magician_pin_config[] __initdata = {
 	GPIO107_GPIO,	/* DS1WM_IRQ */
 	GPIO108_GPIO,	/* GSM_READY */
 	GPIO115_GPIO,	/* nPEN_IRQ */
+
+	/* I2C */
+	GPIO117_I2C_SCL,
+	GPIO118_I2C_SDA,
 };
 
 /*
diff --git a/arch/arm/mach-pxa/mainstone.c b/arch/arm/mach-pxa/mainstone.c
index f2c7ad8f2b6b..5f224968043c 100644
--- a/arch/arm/mach-pxa/mainstone.c
+++ b/arch/arm/mach-pxa/mainstone.c
@@ -128,6 +128,10 @@ static unsigned long mainstone_pin_config[] = {
 	GPIO108_KP_MKOUT_5,
 	GPIO96_KP_MKOUT_6,
 
+	/* I2C */
+	GPIO117_I2C_SCL,
+	GPIO118_I2C_SDA,
+
 	/* GPIO */
 	GPIO1_GPIO | WAKEUP_ON_EDGE_BOTH,
 };
diff --git a/arch/arm/mach-pxa/mfp-pxa2xx.c b/arch/arm/mach-pxa/mfp-pxa2xx.c
index 2061c00c8ead..33626de8cbf6 100644
--- a/arch/arm/mach-pxa/mfp-pxa2xx.c
+++ b/arch/arm/mach-pxa/mfp-pxa2xx.c
@@ -38,12 +38,13 @@ struct gpio_desc {
 	unsigned	valid		: 1;
 	unsigned	can_wakeup	: 1;
 	unsigned	keypad_gpio	: 1;
+	unsigned	dir_inverted	: 1;
 	unsigned int	mask; /* bit mask in PWER or PKWR */
+	unsigned int	mux_mask; /* bit mask of muxed gpio bits, 0 if no mux */
 	unsigned long	config;
 };
 
 static struct gpio_desc gpio_desc[MFP_PIN_GPIO127 + 1];
-static int gpio_nr;
 
 static unsigned long gpdr_lpm[4];
 
@@ -54,7 +55,7 @@ static int __mfp_config_gpio(unsigned gpio, unsigned long c)
 	int uorl = !!(gpio & 0x10); /* GAFRx_U or GAFRx_L ? */
 	int shft = (gpio & 0xf) << 1;
 	int fn = MFP_AF(c);
-	int dir = c & MFP_DIR_OUT;
+	int is_out = (c & MFP_DIR_OUT) ? 1 : 0;
 
 	if (fn > 3)
 		return -EINVAL;
@@ -68,7 +69,7 @@ static int __mfp_config_gpio(unsigned gpio, unsigned long c)
 	else
 		GAFR_U(bank) = gafr;
 
-	if (dir == MFP_DIR_OUT)
+	if (is_out ^ gpio_desc[gpio].dir_inverted)
 		GPDR(gpio) |= mask;
 	else
 		GPDR(gpio) &= ~mask;
@@ -77,11 +78,11 @@ static int __mfp_config_gpio(unsigned gpio, unsigned long c)
 	switch (c & MFP_LPM_STATE_MASK) {
 	case MFP_LPM_DRIVE_HIGH:
 		PGSR(bank) |= mask;
-		dir = MFP_DIR_OUT;
+		is_out = 1;
 		break;
 	case MFP_LPM_DRIVE_LOW:
 		PGSR(bank) &= ~mask;
-		dir = MFP_DIR_OUT;
+		is_out = 1;
 		break;
 	case MFP_LPM_DEFAULT:
 		break;
@@ -92,7 +93,7 @@ static int __mfp_config_gpio(unsigned gpio, unsigned long c)
 		break;
 	}
 
-	if (dir == MFP_DIR_OUT)
+	if (is_out ^ gpio_desc[gpio].dir_inverted)
 		gpdr_lpm[bank] |= mask;
 	else
 		gpdr_lpm[bank] &= ~mask;
@@ -106,7 +107,7 @@ static int __mfp_config_gpio(unsigned gpio, unsigned long c)
 		return -EINVAL;
 	}
 
-	if ((c & MFP_LPM_CAN_WAKEUP) && (dir == MFP_DIR_OUT)) {
+	if ((c & MFP_LPM_CAN_WAKEUP) && is_out) {
 		pr_warning("%s: output GPIO%d unable to wakeup\n",
 				__func__, gpio);
 		return -EINVAL;
@@ -169,7 +170,7 @@ void pxa2xx_mfp_set_lpm(int mfp, unsigned long lpm)
 int gpio_set_wake(unsigned int gpio, unsigned int on)
 {
 	struct gpio_desc *d;
-	unsigned long c;
+	unsigned long c, mux_taken;
 
 	if (gpio > mfp_to_gpio(MFP_PIN_GPIO127))
 		return -EINVAL;
@@ -183,9 +184,13 @@ int gpio_set_wake(unsigned int gpio, unsigned int on)
 	if (d->keypad_gpio)
 		return -EINVAL;
 
+	mux_taken = (PWER & d->mux_mask) & (~d->mask);
+	if (on && mux_taken)
+		return -EBUSY;
+
 	if (d->can_wakeup && (c & MFP_LPM_CAN_WAKEUP)) {
 		if (on) {
-			PWER |= d->mask;
+			PWER = (PWER & ~d->mux_mask) | d->mask;
 
 			if (c & MFP_LPM_EDGE_RISE)
 				PRER |= d->mask;
@@ -210,7 +215,7 @@ static void __init pxa25x_mfp_init(void)
 {
 	int i;
 
-	for (i = 0; i <= 84; i++)
+	for (i = 0; i <= pxa_last_gpio; i++)
 		gpio_desc[i].valid = 1;
 
 	for (i = 0; i <= 15; i++) {
@@ -218,7 +223,11 @@ static void __init pxa25x_mfp_init(void)
 		gpio_desc[i].mask = GPIO_bit(i);
 	}
 
-	gpio_nr = 85;
+	/* PXA26x has additional 4 GPIOs (86/87/88/89) which has the
+	 * direction bit inverted in GPDR2. See PXA26x DM 4.1.1.
+	 */
+	for (i = 86; i <= pxa_last_gpio; i++)
+		gpio_desc[i].dir_inverted = 1;
 }
 #else
 static inline void pxa25x_mfp_init(void) {}
@@ -251,11 +260,27 @@ int keypad_set_wake(unsigned int on)
 	return 0;
 }
 
+#define PWER_WEMUX2_GPIO38	(1 << 16)
+#define PWER_WEMUX2_GPIO53	(2 << 16)
+#define PWER_WEMUX2_GPIO40	(3 << 16)
+#define PWER_WEMUX2_GPIO36	(4 << 16)
+#define PWER_WEMUX2_MASK	(7 << 16)
+#define PWER_WEMUX3_GPIO31	(1 << 19)
+#define PWER_WEMUX3_GPIO113	(2 << 19)
+#define PWER_WEMUX3_MASK	(3 << 19)
+
+#define INIT_GPIO_DESC_MUXED(mux, gpio)				\
+do {								\
+	gpio_desc[(gpio)].can_wakeup = 1;			\
+	gpio_desc[(gpio)].mask = PWER_ ## mux ## _GPIO ##gpio;	\
+	gpio_desc[(gpio)].mux_mask = PWER_ ## mux ## _MASK;	\
+} while (0)
+
 static void __init pxa27x_mfp_init(void)
 {
 	int i, gpio;
 
-	for (i = 0; i <= 120; i++) {
+	for (i = 0; i <= pxa_last_gpio; i++) {
 		/* skip GPIO2, 5, 6, 7, 8, they are not
 		 * valid pins allow configuration
 		 */
@@ -286,7 +311,12 @@ static void __init pxa27x_mfp_init(void)
 	gpio_desc[35].can_wakeup = 1;
 	gpio_desc[35].mask = PWER_WE35;
 
-	gpio_nr = 121;
+	INIT_GPIO_DESC_MUXED(WEMUX3, 31);
+	INIT_GPIO_DESC_MUXED(WEMUX3, 113);
+	INIT_GPIO_DESC_MUXED(WEMUX2, 38);
+	INIT_GPIO_DESC_MUXED(WEMUX2, 53);
+	INIT_GPIO_DESC_MUXED(WEMUX2, 40);
+	INIT_GPIO_DESC_MUXED(WEMUX2, 36);
 }
 #else
 static inline void pxa27x_mfp_init(void) {}
@@ -300,7 +330,7 @@ static int pxa2xx_mfp_suspend(struct sys_device *d, pm_message_t state)
 {
 	int i;
 
-	for (i = 0; i <= gpio_to_bank(gpio_nr); i++) {
+	for (i = 0; i <= gpio_to_bank(pxa_last_gpio); i++) {
 
 		saved_gafr[0][i] = GAFR_L(i);
 		saved_gafr[1][i] = GAFR_U(i);
@@ -315,7 +345,7 @@ static int pxa2xx_mfp_resume(struct sys_device *d)
 {
 	int i;
 
-	for (i = 0; i <= gpio_to_bank(gpio_nr); i++) {
+	for (i = 0; i <= gpio_to_bank(pxa_last_gpio); i++) {
 		GAFR_L(i) = saved_gafr[0][i];
 		GAFR_U(i) = saved_gafr[1][i];
 		GPDR(i * 32) = saved_gpdr[i];
@@ -348,7 +378,7 @@ static int __init pxa2xx_mfp_init(void)
 		pxa27x_mfp_init();
 
 	/* initialize gafr_run[], pgsr_lpm[] from existing values */
-	for (i = 0; i <= gpio_to_bank(gpio_nr); i++)
+	for (i = 0; i <= gpio_to_bank(pxa_last_gpio); i++)
 		gpdr_lpm[i] = GPDR(i * 32);
 
 	return sysdev_class_register(&pxa2xx_mfp_sysclass);
diff --git a/arch/arm/mach-pxa/mioa701.c b/arch/arm/mach-pxa/mioa701.c
index 782903fe9c6c..2b427e015b6f 100644
--- a/arch/arm/mach-pxa/mioa701.c
+++ b/arch/arm/mach-pxa/mioa701.c
@@ -34,7 +34,7 @@
 #include <linux/irq.h>
 #include <linux/pda_power.h>
 #include <linux/power_supply.h>
-#include <linux/wm97xx.h>
+#include <linux/wm97xx_batt.h>
 #include <linux/mtd/physmap.h>
 
 #include <asm/mach-types.h>
@@ -46,6 +46,9 @@
 #include <mach/mmc.h>
 #include <mach/udc.h>
 #include <mach/pxa27x-udc.h>
+#include <mach/i2c.h>
+#include <mach/camera.h>
+#include <media/soc_camera.h>
 
 #include <mach/mioa701.h>
 
@@ -54,10 +57,11 @@
 
 static unsigned long mioa701_pin_config[] = {
 	/* Mio global */
-	MIO_CFG_OUT(GPIO9_CHARGE_nEN, AF0, DRIVE_LOW),
+	MIO_CFG_OUT(GPIO9_CHARGE_EN, AF0, DRIVE_LOW),
 	MIO_CFG_OUT(GPIO18_POWEROFF, AF0, DRIVE_LOW),
 	MFP_CFG_OUT(GPIO3, AF0, DRIVE_HIGH),
 	MFP_CFG_OUT(GPIO4, AF0, DRIVE_HIGH),
+	MIO_CFG_IN(GPIO80_MAYBE_CHARGE_VDROP, AF0),
 
 	/* Backlight PWM 0 */
 	GPIO16_PWM0_OUT,
@@ -74,7 +78,7 @@ static unsigned long mioa701_pin_config[] = {
 	MIO_CFG_OUT(GPIO91_SDIO_EN, AF0, DRIVE_LOW),
 
 	/* USB */
-	MIO_CFG_IN(GPIO13_USB_DETECT, AF0),
+	MIO_CFG_IN(GPIO13_nUSB_DETECT, AF0),
 	MIO_CFG_OUT(GPIO22_USB_ENABLE, AF0, DRIVE_LOW),
 
 	/* LCD */
@@ -98,12 +102,29 @@ static unsigned long mioa701_pin_config[] = {
 	GPIO75_LCD_LCLK,
 	GPIO76_LCD_PCLK,
 
+	/* QCI */
+	GPIO12_CIF_DD_7,
+	GPIO17_CIF_DD_6,
+	GPIO50_CIF_DD_3,
+	GPIO51_CIF_DD_2,
+	GPIO52_CIF_DD_4,
+	GPIO53_CIF_MCLK,
+	GPIO54_CIF_PCLK,
+	GPIO55_CIF_DD_1,
+	GPIO81_CIF_DD_0,
+	GPIO82_CIF_DD_5,
+	GPIO84_CIF_FV,
+	GPIO85_CIF_LV,
+
 	/* Bluetooth */
+	MIO_CFG_IN(GPIO14_BT_nACTIVITY, AF0),
 	GPIO44_BTUART_CTS,
 	GPIO42_BTUART_RXD,
 	GPIO45_BTUART_RTS,
 	GPIO43_BTUART_TXD,
 	MIO_CFG_OUT(GPIO83_BT_ON, AF0, DRIVE_LOW),
+	MIO_CFG_OUT(GPIO77_BT_UNKNOWN1, AF0, DRIVE_HIGH),
+	MIO_CFG_OUT(GPIO86_BT_MAYBE_nRESET, AF0, DRIVE_HIGH),
 
 	/* GPS */
 	MIO_CFG_OUT(GPIO23_GPS_UNKNOWN1, AF0, DRIVE_LOW),
@@ -151,16 +172,16 @@ static unsigned long mioa701_pin_config[] = {
 	GPIO104_KP_MKOUT_1,
 	GPIO105_KP_MKOUT_2,
 
+	/* I2C */
+	GPIO117_I2C_SCL,
+	GPIO118_I2C_SDA,
+
 	/* Unknown */
-	MFP_CFG_IN(GPIO14, AF0),
 	MFP_CFG_IN(GPIO20, AF0),
 	MFP_CFG_IN(GPIO21, AF0),
 	MFP_CFG_IN(GPIO33, AF0),
 	MFP_CFG_OUT(GPIO49, AF0, DRIVE_HIGH),
 	MFP_CFG_OUT(GPIO57, AF0, DRIVE_HIGH),
-	MFP_CFG_OUT(GPIO77, AF0, DRIVE_HIGH),
-	MFP_CFG_IN(GPIO80, AF0),
-	MFP_CFG_OUT(GPIO86, AF0, DRIVE_HIGH),
 	MFP_CFG_IN(GPIO96, AF0),
 	MFP_CFG_OUT(GPIO116, AF0, DRIVE_HIGH),
 };
@@ -407,7 +428,7 @@ static void udc_power_command(int cmd)
 
 static int is_usb_connected(void)
 {
-	return !!gpio_get_value(GPIO13_USB_DETECT);
+	return !gpio_get_value(GPIO13_nUSB_DETECT);
 }
 
 static struct pxa2xx_udc_mach_info mioa701_udc_info = {
@@ -659,13 +680,19 @@ static char *supplicants[] = {
 	"mioa701_battery"
 };
 
+static int is_ac_connected(void)
+{
+	return gpio_get_value(GPIO96_AC_DETECT);
+}
+
 static void mioa701_set_charge(int flags)
 {
-	gpio_set_value(GPIO9_CHARGE_nEN, !flags);
+	gpio_set_value(GPIO9_CHARGE_EN, (flags == PDA_POWER_CHARGE_USB));
 }
 
 static struct pda_power_pdata power_pdata = {
-	.is_ac_online	= is_usb_connected,
+	.is_ac_online	= is_ac_connected,
+	.is_usb_online	= is_usb_connected,
 	.set_charge = mioa701_set_charge,
 	.supplied_to = supplicants,
 	.num_supplicants = ARRAY_SIZE(supplicants),
@@ -674,8 +701,15 @@ static struct pda_power_pdata power_pdata = {
 static struct resource power_resources[] = {
 	[0] = {
 		.name	= "ac",
-		.start	= gpio_to_irq(GPIO13_USB_DETECT),
-		.end	= gpio_to_irq(GPIO13_USB_DETECT),
+		.start	= gpio_to_irq(GPIO96_AC_DETECT),
+		.end	= gpio_to_irq(GPIO96_AC_DETECT),
+		.flags	= IORESOURCE_IRQ | IORESOURCE_IRQ_HIGHEDGE |
+		IORESOURCE_IRQ_LOWEDGE,
+	},
+	[1] = {
+		.name	= "usb",
+		.start	= gpio_to_irq(GPIO13_nUSB_DETECT),
+		.end	= gpio_to_irq(GPIO13_nUSB_DETECT),
 		.flags	= IORESOURCE_IRQ | IORESOURCE_IRQ_HIGHEDGE |
 		IORESOURCE_IRQ_LOWEDGE,
 	},
@@ -691,120 +725,43 @@ static struct platform_device power_dev = {
 	},
 };
 
-#if defined(CONFIG_PDA_POWER) && defined(CONFIG_TOUCHSCREEN_WM97XX)
-static struct wm97xx *battery_wm;
-
-static enum power_supply_property battery_props[] = {
-	POWER_SUPPLY_PROP_STATUS,
-	POWER_SUPPLY_PROP_VOLTAGE_MAX_DESIGN,
-	POWER_SUPPLY_PROP_VOLTAGE_MIN_DESIGN,
-	POWER_SUPPLY_PROP_VOLTAGE_NOW,
-	POWER_SUPPLY_PROP_CHARGE_FULL_DESIGN,	/* Necessary for apm */
+static struct wm97xx_batt_info mioa701_battery_data = {
+	.batt_aux	= WM97XX_AUX_ID1,
+	.temp_aux	= -1,
+	.charge_gpio	= -1,
+	.min_voltage	= 0xc00,
+	.max_voltage	= 0xfc0,
+	.batt_tech	= POWER_SUPPLY_TECHNOLOGY_LION,
+	.batt_div	= 1,
+	.batt_mult	= 1,
+	.batt_name	= "mioa701_battery",
 };
 
-static int get_battery_voltage(void)
-{
-	int adc = -1;
-
-	if (battery_wm)
-		adc = wm97xx_read_aux_adc(battery_wm, WM97XX_AUX_ID1);
-	return adc;
-}
-
-static int get_battery_status(struct power_supply *b)
-{
-	int status;
-
-	if (is_usb_connected())
-		status = POWER_SUPPLY_STATUS_CHARGING;
-	else
-		status = POWER_SUPPLY_STATUS_DISCHARGING;
-
-	return status;
-}
-
-static int get_property(struct power_supply *b,
-			enum power_supply_property psp,
-			union power_supply_propval *val)
-{
-	int rc = 0;
-
-	switch (psp) {
-	case POWER_SUPPLY_PROP_STATUS:
-		val->intval = get_battery_status(b);
-		break;
-	case POWER_SUPPLY_PROP_VOLTAGE_MAX_DESIGN:
-		val->intval = 0xfd0;
-		break;
-	case POWER_SUPPLY_PROP_VOLTAGE_MIN_DESIGN:
-		val->intval = 0xc00;
-		break;
-	case POWER_SUPPLY_PROP_VOLTAGE_NOW:
-		val->intval = get_battery_voltage();
-		break;
-	case POWER_SUPPLY_PROP_CHARGE_FULL_DESIGN:
-		val->intval = 100;
-		break;
-	default:
-		val->intval = -1;
-		rc = -1;
-	}
-
-	return rc;
+/*
+ * Camera interface
+ */
+struct pxacamera_platform_data mioa701_pxacamera_platform_data = {
+	.flags  = PXA_CAMERA_MASTER | PXA_CAMERA_DATAWIDTH_8 |
+		PXA_CAMERA_PCLK_EN | PXA_CAMERA_MCLK_EN,
+	.mclk_10khz = 5000,
 };
 
-static struct power_supply battery_ps = {
-	.name = "mioa701_battery",
-	.type = POWER_SUPPLY_TYPE_BATTERY,
-	.get_property = get_property,
-	.properties = battery_props,
-	.num_properties = ARRAY_SIZE(battery_props),
+static struct soc_camera_link iclink = {
+	.bus_id	= 0, /* Must match id in pxa27x_device_camera in device.c */
 };
 
-static int battery_probe(struct platform_device *pdev)
-{
-	struct wm97xx *wm = platform_get_drvdata(pdev);
-	int rc;
-
-	battery_wm = wm;
-
-	rc = power_supply_register(NULL, &battery_ps);
-	if (rc)
-		dev_err(&pdev->dev,
-		"Could not register mioa701 battery -> %d\n", rc);
-	return rc;
-}
-
-static int battery_remove(struct platform_device *pdev)
-{
-	battery_wm = NULL;
-	return 0;
-}
-
-static struct platform_driver mioa701_battery_driver = {
-	.driver = {
-		.name = "wm97xx-battery",
+/* Board I2C devices. */
+static struct i2c_board_info __initdata mioa701_i2c_devices[] = {
+	{
+		/* Must initialize before the camera(s) */
+		I2C_BOARD_INFO("mt9m111", 0x5d),
+		.platform_data = &iclink,
 	},
-	.probe = battery_probe,
-	.remove = battery_remove
 };
 
-static int __init mioa701_battery_init(void)
-{
-	int rc;
-
-	rc = platform_driver_register(&mioa701_battery_driver);
-	if (rc)
-		printk(KERN_ERR "Could not register mioa701 battery driver\n");
-	return rc;
-}
-
-#else
-static int __init mioa701_battery_init(void)
-{
-	return 0;
-}
-#endif
+struct i2c_pxa_platform_data i2c_pdata = {
+	.fast_mode = 1,
+};
 
 /*
  * Mio global
@@ -851,17 +808,17 @@ static void mioa701_machine_exit(void);
 static void mioa701_poweroff(void)
 {
 	mioa701_machine_exit();
-	gpio_set_value(GPIO18_POWEROFF, 1);
+	arm_machine_restart('s');
 }
 
 static void mioa701_restart(char c)
 {
 	mioa701_machine_exit();
-	arm_machine_restart(c);
+	arm_machine_restart('s');
 }
 
 struct gpio_ress global_gpios[] = {
-	MIO_GPIO_OUT(GPIO9_CHARGE_nEN, 1, "Charger enable"),
+	MIO_GPIO_OUT(GPIO9_CHARGE_EN, 1, "Charger enable"),
 	MIO_GPIO_OUT(GPIO18_POWEROFF, 0, "Power Off"),
 	MIO_GPIO_OUT(GPIO87_LCD_POWER, 0, "LCD Power")
 };
@@ -879,12 +836,16 @@ static void __init mioa701_machine_init(void)
 	set_pxa_fb_info(&mioa701_pxafb_info);
 	pxa_set_mci_info(&mioa701_mci_info);
 	pxa_set_keypad_info(&mioa701_keypad_info);
+	wm97xx_bat_set_pdata(&mioa701_battery_data);
 	udc_init();
 	pm_power_off = mioa701_poweroff;
 	arm_pm_restart = mioa701_restart;
 	platform_add_devices(devices, ARRAY_SIZE(devices));
 	gsm_init();
-	mioa701_battery_init();
+
+	pxa_set_i2c_info(&i2c_pdata);
+	pxa_set_camera_info(&mioa701_pxacamera_platform_data);
+	i2c_register_board_info(0, ARRAY_AND_SIZE(mioa701_i2c_devices));
 }
 
 static void mioa701_machine_exit(void)
diff --git a/arch/arm/mach-pxa/pcm990-baseboard.c b/arch/arm/mach-pxa/pcm990-baseboard.c
index b36cec5c9eed..3ea01e0eac63 100644
--- a/arch/arm/mach-pxa/pcm990-baseboard.c
+++ b/arch/arm/mach-pxa/pcm990-baseboard.c
@@ -55,6 +55,10 @@ static unsigned long pcm990_pin_config[] __initdata = {
 	GPIO89_USBH1_PEN,
 	/* PWM0 */
 	GPIO16_PWM0_OUT,
+
+	/* I2C */
+	GPIO117_I2C_SCL,
+	GPIO118_I2C_SDA,
 };
 
 /*
diff --git a/arch/arm/mach-pxa/poodle.c b/arch/arm/mach-pxa/poodle.c
index 2e3bd8b1523b..ae88855bf974 100644
--- a/arch/arm/mach-pxa/poodle.c
+++ b/arch/arm/mach-pxa/poodle.c
@@ -20,6 +20,7 @@
 #include <linux/fb.h>
 #include <linux/pm.h>
 #include <linux/delay.h>
+#include <linux/mtd/physmap.h>
 #include <linux/gpio.h>
 #include <linux/spi/spi.h>
 #include <linux/spi/ads7846.h>
@@ -413,9 +414,40 @@ static struct pxafb_mach_info poodle_fb_info = {
 	.lcd_conn	= LCD_COLOR_TFT_16BPP,
 };
 
+static struct mtd_partition sharpsl_rom_parts[] = {
+	{
+		.name	="Boot PROM Filesystem",
+		.offset	= 0x00120000,
+		.size	= MTDPART_SIZ_FULL,
+	},
+};
+
+static struct physmap_flash_data sharpsl_rom_data = {
+	.width		= 2,
+	.nr_parts	= ARRAY_SIZE(sharpsl_rom_parts),
+	.parts		= sharpsl_rom_parts,
+};
+
+static struct resource sharpsl_rom_resources[] = {
+	{
+		.start	= 0x00000000,
+		.end	= 0x007fffff,
+		.flags	= IORESOURCE_MEM,
+	},
+};
+
+static struct platform_device sharpsl_rom_device = {
+	.name	= "physmap-flash",
+	.id	= -1,
+	.resource = sharpsl_rom_resources,
+	.num_resources = ARRAY_SIZE(sharpsl_rom_resources),
+	.dev.platform_data = &sharpsl_rom_data,
+};
+
 static struct platform_device *devices[] __initdata = {
 	&poodle_locomo_device,
 	&poodle_scoop_device,
+	&sharpsl_rom_device,
 };
 
 static void poodle_poweroff(void)
diff --git a/arch/arm/mach-pxa/pwm.c b/arch/arm/mach-pxa/pwm.c
index 74e2ead8cee8..3ca7ffc6904b 100644
--- a/arch/arm/mach-pxa/pwm.c
+++ b/arch/arm/mach-pxa/pwm.c
@@ -173,7 +173,7 @@ static struct pwm_device *pwm_probe(struct platform_device *pdev,
 		return ERR_PTR(-ENOMEM);
 	}
 
-	pwm->clk = clk_get(&pdev->dev, "PWMCLK");
+	pwm->clk = clk_get(&pdev->dev, NULL);
 	if (IS_ERR(pwm->clk)) {
 		ret = PTR_ERR(pwm->clk);
 		goto err_free;
diff --git a/arch/arm/mach-pxa/pxa25x.c b/arch/arm/mach-pxa/pxa25x.c
index 25d17a1dab78..6c57522e2469 100644
--- a/arch/arm/mach-pxa/pxa25x.c
+++ b/arch/arm/mach-pxa/pxa25x.c
@@ -36,12 +36,6 @@
 #include "devices.h"
 #include "clock.h"
 
-int cpu_is_pxa26x(void)
-{
-	return cpu_is_pxa250() && ((BOOT_DEF & 0x8) == 0);
-}
-EXPORT_SYMBOL_GPL(cpu_is_pxa26x);
-
 /*
  * Various clock factors driven by the CCCR register.
  */
@@ -167,36 +161,51 @@ static const struct clkops clk_pxa25x_gpio11_ops = {
  * 95.842MHz -> MMC 19.169MHz, I2C 31.949MHz, FICP 47.923MHz, USB 47.923MHz
  * 147.456MHz -> UART 14.7456MHz, AC97 12.288MHz, I2S 5.672MHz (allegedly)
  */
-static struct clk pxa25x_hwuart_clk =
-	INIT_CKEN("UARTCLK", HWUART, 14745600, 1, &pxa_device_hwuart.dev)
-;
+static DEFINE_CKEN(pxa25x_hwuart, HWUART, 14745600, 1);
+
+static struct clk_lookup pxa25x_hwuart_clkreg =
+	INIT_CLKREG(&clk_pxa25x_hwuart, "pxa2xx-uart.3", NULL);
 
 /*
  * PXA 2xx clock declarations.
  */
-static struct clk pxa25x_clks[] = {
-	INIT_CK("LCDCLK", LCD, &clk_pxa25x_lcd_ops, &pxa_device_fb.dev),
-	INIT_CKEN("UARTCLK", FFUART, 14745600, 1, &pxa_device_ffuart.dev),
-	INIT_CKEN("UARTCLK", BTUART, 14745600, 1, &pxa_device_btuart.dev),
-	INIT_CKEN("UARTCLK", STUART, 14745600, 1, NULL),
-	INIT_CKEN("UDCCLK", USB, 47923000, 5, &pxa25x_device_udc.dev),
-	INIT_CLK("GPIO11_CLK", &clk_pxa25x_gpio11_ops, 3686400, 0, NULL),
-	INIT_CLK("GPIO12_CLK", &clk_pxa25x_gpio12_ops, 32768, 0, NULL),
-	INIT_CKEN("MMCCLK", MMC, 19169000, 0, &pxa_device_mci.dev),
-	INIT_CKEN("I2CCLK", I2C, 31949000, 0, &pxa_device_i2c.dev),
-
-	INIT_CKEN("SSPCLK",  SSP, 3686400, 0, &pxa25x_device_ssp.dev),
-	INIT_CKEN("SSPCLK", NSSP, 3686400, 0, &pxa25x_device_nssp.dev),
-	INIT_CKEN("SSPCLK", ASSP, 3686400, 0, &pxa25x_device_assp.dev),
-	INIT_CKEN("PWMCLK", PWM0, 3686400, 0, &pxa25x_device_pwm0.dev),
-	INIT_CKEN("PWMCLK", PWM1, 3686400, 0, &pxa25x_device_pwm1.dev),
-
-	INIT_CKEN("AC97CLK",     AC97,     24576000, 0, NULL),
-
-	/*
-	INIT_CKEN("I2SCLK",  I2S,  14745600, 0, NULL),
-	*/
-	INIT_CKEN("FICPCLK", FICP, 47923000, 0, NULL),
+static DEFINE_CK(pxa25x_lcd, LCD, &clk_pxa25x_lcd_ops);
+static DEFINE_CKEN(pxa25x_ffuart, FFUART, 14745600, 1);
+static DEFINE_CKEN(pxa25x_btuart, BTUART, 14745600, 1);
+static DEFINE_CKEN(pxa25x_stuart, STUART, 14745600, 1);
+static DEFINE_CKEN(pxa25x_usb, USB, 47923000, 5);
+static DEFINE_CLK(pxa25x_gpio11, &clk_pxa25x_gpio11_ops, 3686400, 0);
+static DEFINE_CLK(pxa25x_gpio12, &clk_pxa25x_gpio12_ops, 32768, 0);
+static DEFINE_CKEN(pxa25x_mmc, MMC, 19169000, 0);
+static DEFINE_CKEN(pxa25x_i2c, I2C, 31949000, 0);
+static DEFINE_CKEN(pxa25x_ssp, SSP, 3686400, 0);
+static DEFINE_CKEN(pxa25x_nssp, NSSP, 3686400, 0);
+static DEFINE_CKEN(pxa25x_assp, ASSP, 3686400, 0);
+static DEFINE_CKEN(pxa25x_pwm0, PWM0, 3686400, 0);
+static DEFINE_CKEN(pxa25x_pwm1, PWM1, 3686400, 0);
+static DEFINE_CKEN(pxa25x_ac97, AC97, 24576000, 0);
+static DEFINE_CKEN(pxa25x_i2s, I2S, 14745600, 0);
+static DEFINE_CKEN(pxa25x_ficp, FICP, 47923000, 0);
+
+static struct clk_lookup pxa25x_clkregs[] = {
+	INIT_CLKREG(&clk_pxa25x_lcd, "pxa2xx-fb", NULL),
+	INIT_CLKREG(&clk_pxa25x_ffuart, "pxa2xx-uart.0", NULL),
+	INIT_CLKREG(&clk_pxa25x_btuart, "pxa2xx-uart.1", NULL),
+	INIT_CLKREG(&clk_pxa25x_stuart, "pxa2xx-uart.2", NULL),
+	INIT_CLKREG(&clk_pxa25x_usb, "pxa25x-udc", NULL),
+	INIT_CLKREG(&clk_pxa25x_mmc, "pxa2xx-mci.0", NULL),
+	INIT_CLKREG(&clk_pxa25x_i2c, "pxa2xx-i2c.0", NULL),
+	INIT_CLKREG(&clk_pxa25x_ssp, "pxa25x-ssp.0", NULL),
+	INIT_CLKREG(&clk_pxa25x_nssp, "pxa25x-nssp.1", NULL),
+	INIT_CLKREG(&clk_pxa25x_assp, "pxa25x-nssp.2", NULL),
+	INIT_CLKREG(&clk_pxa25x_pwm0, "pxa25x-pwm.0", NULL),
+	INIT_CLKREG(&clk_pxa25x_pwm1, "pxa25x-pwm.1", NULL),
+	INIT_CLKREG(&clk_pxa25x_i2s, "pxa2xx-i2s", NULL),
+	INIT_CLKREG(&clk_pxa25x_stuart, "pxa2xx-ir", "UARTCLK"),
+	INIT_CLKREG(&clk_pxa25x_ficp, "pxa2xx-ir", "FICPCLK"),
+	INIT_CLKREG(&clk_pxa25x_ac97, NULL, "AC97CLK"),
+	INIT_CLKREG(&clk_pxa25x_gpio11, NULL, "GPIO11_CLK"),
+	INIT_CLKREG(&clk_pxa25x_gpio12, NULL, "GPIO12_CLK"),
 };
 
 #ifdef CONFIG_PM
@@ -304,13 +313,21 @@ void __init pxa25x_init_irq(void)
 	pxa_init_gpio(85, pxa25x_set_wake);
 }
 
+#ifdef CONFIG_CPU_PXA26x
+void __init pxa26x_init_irq(void)
+{
+	pxa_init_irq(32, pxa25x_set_wake);
+	pxa_init_gpio(90, pxa25x_set_wake);
+}
+#endif
+
 static struct platform_device *pxa25x_devices[] __initdata = {
 	&pxa25x_device_udc,
 	&pxa_device_ffuart,
 	&pxa_device_btuart,
 	&pxa_device_stuart,
 	&pxa_device_i2s,
-	&pxa_device_rtc,
+	&sa1100_device_rtc,
 	&pxa25x_device_ssp,
 	&pxa25x_device_nssp,
 	&pxa25x_device_assp,
@@ -336,7 +353,7 @@ static int __init pxa25x_init(void)
 
 		reset_status = RCSR;
 
-		clks_register(pxa25x_clks, ARRAY_SIZE(pxa25x_clks));
+		clks_register(pxa25x_clkregs, ARRAY_SIZE(pxa25x_clkregs));
 
 		if ((ret = pxa_init_dma(16)))
 			return ret;
@@ -356,8 +373,8 @@ static int __init pxa25x_init(void)
 	}
 
 	/* Only add HWUART for PXA255/26x; PXA210/250 do not have it. */
-	if (cpu_is_pxa255() || cpu_is_pxa26x()) {
-		clks_register(&pxa25x_hwuart_clk, 1);
+	if (cpu_is_pxa255()) {
+		clks_register(&pxa25x_hwuart_clkreg, 1);
 		ret = platform_device_register(&pxa_device_hwuart);
 	}
 
diff --git a/arch/arm/mach-pxa/pxa27x.c b/arch/arm/mach-pxa/pxa27x.c
index 3e4ab2279c99..411bec54fdc4 100644
--- a/arch/arm/mach-pxa/pxa27x.c
+++ b/arch/arm/mach-pxa/pxa27x.c
@@ -144,40 +144,59 @@ static const struct clkops clk_pxa27x_lcd_ops = {
 	.getrate	= clk_pxa27x_lcd_getrate,
 };
 
-static struct clk pxa27x_clks[] = {
-	INIT_CK("LCDCLK", LCD,    &clk_pxa27x_lcd_ops, &pxa_device_fb.dev),
-	INIT_CK("CAMCLK", CAMERA, &clk_pxa27x_lcd_ops, NULL),
-
-	INIT_CKEN("UARTCLK", FFUART, 14857000, 1, &pxa_device_ffuart.dev),
-	INIT_CKEN("UARTCLK", BTUART, 14857000, 1, &pxa_device_btuart.dev),
-	INIT_CKEN("UARTCLK", STUART, 14857000, 1, NULL),
-
-	INIT_CKEN("I2SCLK",  I2S,  14682000, 0, &pxa_device_i2s.dev),
-	INIT_CKEN("I2CCLK",  I2C,  32842000, 0, &pxa_device_i2c.dev),
-	INIT_CKEN("UDCCLK",  USB,  48000000, 5, &pxa27x_device_udc.dev),
-	INIT_CKEN("MMCCLK",  MMC,  19500000, 0, &pxa_device_mci.dev),
-	INIT_CKEN("FICPCLK", FICP, 48000000, 0, &pxa_device_ficp.dev),
-
-	INIT_CKEN("USBCLK", USBHOST, 48000000, 0, &pxa27x_device_ohci.dev),
-	INIT_CKEN("I2CCLK", PWRI2C, 13000000, 0, &pxa27x_device_i2c_power.dev),
-	INIT_CKEN("KBDCLK", KEYPAD, 32768, 0, &pxa27x_device_keypad.dev),
-
-	INIT_CKEN("SSPCLK", SSP1, 13000000, 0, &pxa27x_device_ssp1.dev),
-	INIT_CKEN("SSPCLK", SSP2, 13000000, 0, &pxa27x_device_ssp2.dev),
-	INIT_CKEN("SSPCLK", SSP3, 13000000, 0, &pxa27x_device_ssp3.dev),
-	INIT_CKEN("PWMCLK", PWM0, 13000000, 0, &pxa27x_device_pwm0.dev),
-	INIT_CKEN("PWMCLK", PWM1, 13000000, 0, &pxa27x_device_pwm1.dev),
-
-	INIT_CKEN("AC97CLK",     AC97,     24576000, 0, NULL),
-	INIT_CKEN("AC97CONFCLK", AC97CONF, 24576000, 0, NULL),
-
-	/*
-	INIT_CKEN("MSLCLK",  MSL,  48000000, 0, NULL),
-	INIT_CKEN("USIMCLK", USIM, 48000000, 0, NULL),
-	INIT_CKEN("MSTKCLK", MEMSTK, 19500000, 0, NULL),
-	INIT_CKEN("IMCLK",   IM,   0, 0, NULL),
-	INIT_CKEN("MEMCLK",  MEMC, 0, 0, NULL),
-	*/
+static DEFINE_CK(pxa27x_lcd, LCD, &clk_pxa27x_lcd_ops);
+static DEFINE_CK(pxa27x_camera, CAMERA, &clk_pxa27x_lcd_ops);
+static DEFINE_CKEN(pxa27x_ffuart, FFUART, 14857000, 1);
+static DEFINE_CKEN(pxa27x_btuart, BTUART, 14857000, 1);
+static DEFINE_CKEN(pxa27x_stuart, STUART, 14857000, 1);
+static DEFINE_CKEN(pxa27x_i2s, I2S, 14682000, 0);
+static DEFINE_CKEN(pxa27x_i2c, I2C, 32842000, 0);
+static DEFINE_CKEN(pxa27x_usb, USB, 48000000, 5);
+static DEFINE_CKEN(pxa27x_mmc, MMC, 19500000, 0);
+static DEFINE_CKEN(pxa27x_ficp, FICP, 48000000, 0);
+static DEFINE_CKEN(pxa27x_usbhost, USBHOST, 48000000, 0);
+static DEFINE_CKEN(pxa27x_pwri2c, PWRI2C, 13000000, 0);
+static DEFINE_CKEN(pxa27x_keypad, KEYPAD, 32768, 0);
+static DEFINE_CKEN(pxa27x_ssp1, SSP1, 13000000, 0);
+static DEFINE_CKEN(pxa27x_ssp2, SSP2, 13000000, 0);
+static DEFINE_CKEN(pxa27x_ssp3, SSP3, 13000000, 0);
+static DEFINE_CKEN(pxa27x_pwm0, PWM0, 13000000, 0);
+static DEFINE_CKEN(pxa27x_pwm1, PWM1, 13000000, 0);
+static DEFINE_CKEN(pxa27x_ac97, AC97, 24576000, 0);
+static DEFINE_CKEN(pxa27x_ac97conf, AC97CONF, 24576000, 0);
+static DEFINE_CKEN(pxa27x_msl, MSL, 48000000, 0);
+static DEFINE_CKEN(pxa27x_usim, USIM, 48000000, 0);
+static DEFINE_CKEN(pxa27x_memstk, MEMSTK, 19500000, 0);
+static DEFINE_CKEN(pxa27x_im, IM, 0, 0);
+static DEFINE_CKEN(pxa27x_memc, MEMC, 0, 0);
+
+static struct clk_lookup pxa27x_clkregs[] = {
+	INIT_CLKREG(&clk_pxa27x_lcd, "pxa2xx-fb", NULL),
+	INIT_CLKREG(&clk_pxa27x_camera, "pxa27x-camera.0", NULL),
+	INIT_CLKREG(&clk_pxa27x_ffuart, "pxa2xx-uart.0", NULL),
+	INIT_CLKREG(&clk_pxa27x_btuart, "pxa2xx-uart.1", NULL),
+	INIT_CLKREG(&clk_pxa27x_stuart, "pxa2xx-uart.2", NULL),
+	INIT_CLKREG(&clk_pxa27x_i2s, "pxa2xx-i2s", NULL),
+	INIT_CLKREG(&clk_pxa27x_i2c, "pxa2xx-i2c.0", NULL),
+	INIT_CLKREG(&clk_pxa27x_usb, "pxa27x-udc", NULL),
+	INIT_CLKREG(&clk_pxa27x_mmc, "pxa2xx-mci.0", NULL),
+	INIT_CLKREG(&clk_pxa27x_stuart, "pxa2xx-ir", "UARTCLK"),
+	INIT_CLKREG(&clk_pxa27x_ficp, "pxa2xx-ir", "FICPCLK"),
+	INIT_CLKREG(&clk_pxa27x_usbhost, "pxa27x-ohci", NULL),
+	INIT_CLKREG(&clk_pxa27x_pwri2c, "pxa2xx-i2c.1", NULL),
+	INIT_CLKREG(&clk_pxa27x_keypad, "pxa27x-keypad", NULL),
+	INIT_CLKREG(&clk_pxa27x_ssp1, "pxa27x-ssp.0", NULL),
+	INIT_CLKREG(&clk_pxa27x_ssp2, "pxa27x-ssp.1", NULL),
+	INIT_CLKREG(&clk_pxa27x_ssp3, "pxa27x-ssp.2", NULL),
+	INIT_CLKREG(&clk_pxa27x_pwm0, "pxa27x-pwm.0", NULL),
+	INIT_CLKREG(&clk_pxa27x_pwm1, "pxa27x-pwm.1", NULL),
+	INIT_CLKREG(&clk_pxa27x_ac97, NULL, "AC97CLK"),
+	INIT_CLKREG(&clk_pxa27x_ac97conf, NULL, "AC97CONFCLK"),
+	INIT_CLKREG(&clk_pxa27x_msl, NULL, "MSLCLK"),
+	INIT_CLKREG(&clk_pxa27x_usim, NULL, "USIMCLK"),
+	INIT_CLKREG(&clk_pxa27x_memstk, NULL, "MSTKCLK"),
+	INIT_CLKREG(&clk_pxa27x_im, NULL, "IMCLK"),
+	INIT_CLKREG(&clk_pxa27x_memc, NULL, "MEMCLK"),
 };
 
 #ifdef CONFIG_PM
@@ -313,38 +332,18 @@ static int pxa27x_set_wake(unsigned int irq, unsigned int on)
 void __init pxa27x_init_irq(void)
 {
 	pxa_init_irq(34, pxa27x_set_wake);
-	pxa_init_gpio(128, pxa27x_set_wake);
+	pxa_init_gpio(121, pxa27x_set_wake);
 }
 
 /*
  * device registration specific to PXA27x.
  */
-
-static struct resource i2c_power_resources[] = {
-	{
-		.start	= 0x40f00180,
-		.end	= 0x40f001a3,
-		.flags	= IORESOURCE_MEM,
-	}, {
-		.start	= IRQ_PWRI2C,
-		.end	= IRQ_PWRI2C,
-		.flags	= IORESOURCE_IRQ,
-	},
-};
-
-struct platform_device pxa27x_device_i2c_power = {
-	.name		= "pxa2xx-i2c",
-	.id		= 1,
-	.resource	= i2c_power_resources,
-	.num_resources	= ARRAY_SIZE(i2c_power_resources),
-};
-
 void __init pxa27x_set_i2c_power_info(struct i2c_pxa_platform_data *info)
 {
 	local_irq_disable();
 	PCFR |= PCFR_PI2CEN;
 	local_irq_enable();
-	pxa27x_device_i2c_power.dev.platform_data = info;
+	pxa_register_device(&pxa27x_device_i2c_power, info);
 }
 
 static struct platform_device *devices[] __initdata = {
@@ -353,8 +352,8 @@ static struct platform_device *devices[] __initdata = {
 	&pxa_device_btuart,
 	&pxa_device_stuart,
 	&pxa_device_i2s,
+	&sa1100_device_rtc,
 	&pxa_device_rtc,
-	&pxa27x_device_i2c_power,
 	&pxa27x_device_ssp1,
 	&pxa27x_device_ssp2,
 	&pxa27x_device_ssp3,
@@ -380,7 +379,7 @@ static int __init pxa27x_init(void)
 
 		reset_status = RCSR;
 
-		clks_register(pxa27x_clks, ARRAY_SIZE(pxa27x_clks));
+		clks_register(pxa27x_clkregs, ARRAY_SIZE(pxa27x_clkregs));
 
 		if ((ret = pxa_init_dma(32)))
 			return ret;
diff --git a/arch/arm/mach-pxa/pxa300.c b/arch/arm/mach-pxa/pxa300.c
index 9adc7fc4618a..f735e58e6669 100644
--- a/arch/arm/mach-pxa/pxa300.c
+++ b/arch/arm/mach-pxa/pxa300.c
@@ -85,14 +85,16 @@ static struct pxa3xx_mfp_addr_map pxa310_mfp_addr_map[] __initdata = {
 	MFP_ADDR_END,
 };
 
-static struct clk common_clks[] = {
-	PXA3xx_CKEN("NANDCLK", NAND, 156000000, 0, &pxa3xx_device_nand.dev),
+static DEFINE_PXA3_CKEN(common_nand, NAND, 156000000, 0);
+
+static struct clk_lookup common_clkregs[] = {
+	INIT_CLKREG(&clk_common_nand, "pxa3xx-nand", "NANDCLK"),
 };
 
-static struct clk pxa310_clks[] = {
-#ifdef CONFIG_CPU_PXA310
-	PXA3xx_CKEN("MMCCLK", MMC3, 19500000, 0, &pxa3xx_device_mci3.dev),
-#endif
+static DEFINE_PXA3_CKEN(pxa310_mmc3, MMC3, 19500000, 0);
+
+static struct clk_lookup pxa310_clkregs[] = {
+	INIT_CLKREG(&clk_pxa310_mmc3, "pxa2xx-mci.2", "MMCCLK"),
 };
 
 static int __init pxa300_init(void)
@@ -100,12 +102,12 @@ static int __init pxa300_init(void)
 	if (cpu_is_pxa300() || cpu_is_pxa310()) {
 		pxa3xx_init_mfp();
 		pxa3xx_mfp_init_addr(pxa300_mfp_addr_map);
-		clks_register(ARRAY_AND_SIZE(common_clks));
+		clks_register(ARRAY_AND_SIZE(common_clkregs));
 	}
 
 	if (cpu_is_pxa310()) {
 		pxa3xx_mfp_init_addr(pxa310_mfp_addr_map);
-		clks_register(ARRAY_AND_SIZE(pxa310_clks));
+		clks_register(ARRAY_AND_SIZE(pxa310_clkregs));
 	}
 
 	return 0;
diff --git a/arch/arm/mach-pxa/pxa320.c b/arch/arm/mach-pxa/pxa320.c
index 016eb18f01a3..effe408c186f 100644
--- a/arch/arm/mach-pxa/pxa320.c
+++ b/arch/arm/mach-pxa/pxa320.c
@@ -80,8 +80,10 @@ static struct pxa3xx_mfp_addr_map pxa320_mfp_addr_map[] __initdata = {
 	MFP_ADDR_END,
 };
 
-static struct clk pxa320_clks[] = {
-	PXA3xx_CKEN("NANDCLK", NAND, 104000000, 0, &pxa3xx_device_nand.dev),
+static DEFINE_PXA3_CKEN(pxa320_nand, NAND, 104000000, 0);
+
+static struct clk_lookup pxa320_clkregs[] = {
+	INIT_CLKREG(&clk_pxa320_nand, "pxa3xx-nand", "NANDCLK"),
 };
 
 static int __init pxa320_init(void)
@@ -89,7 +91,7 @@ static int __init pxa320_init(void)
 	if (cpu_is_pxa320()) {
 		pxa3xx_init_mfp();
 		pxa3xx_mfp_init_addr(pxa320_mfp_addr_map);
-		clks_register(ARRAY_AND_SIZE(pxa320_clks));
+		clks_register(ARRAY_AND_SIZE(pxa320_clkregs));
 	}
 
 	return 0;
diff --git a/arch/arm/mach-pxa/pxa3xx.c b/arch/arm/mach-pxa/pxa3xx.c
index b3cd5d0b0f35..490893824e78 100644
--- a/arch/arm/mach-pxa/pxa3xx.c
+++ b/arch/arm/mach-pxa/pxa3xx.c
@@ -29,6 +29,7 @@
 #include <mach/pm.h>
 #include <mach/dma.h>
 #include <mach/ssp.h>
+#include <mach/i2c.h>
 
 #include "generic.h"
 #include "devices.h"
@@ -216,43 +217,58 @@ static const struct clkops clk_dummy_ops = {
 	.disable	= clk_dummy_disable,
 };
 
-static struct clk pxa3xx_clks[] = {
-	{
-		.name           = "CLK_POUT",
-		.ops            = &clk_pout_ops,
-		.rate           = 13000000,
-		.delay          = 70,
-	},
-
-	/* Power I2C clock is always on */
-	{
-		.name		= "I2CCLK",
-		.ops		= &clk_dummy_ops,
-		.dev		= &pxa3xx_device_i2c_power.dev,
-	},
-
-	PXA3xx_CK("LCDCLK",  LCD,    &clk_pxa3xx_hsio_ops, &pxa_device_fb.dev),
-	PXA3xx_CK("CAMCLK",  CAMERA, &clk_pxa3xx_hsio_ops, NULL),
-	PXA3xx_CK("AC97CLK", AC97,   &clk_pxa3xx_ac97_ops, NULL),
-
-	PXA3xx_CKEN("UARTCLK", FFUART, 14857000, 1, &pxa_device_ffuart.dev),
-	PXA3xx_CKEN("UARTCLK", BTUART, 14857000, 1, &pxa_device_btuart.dev),
-	PXA3xx_CKEN("UARTCLK", STUART, 14857000, 1, NULL),
-
-	PXA3xx_CKEN("I2CCLK", I2C,  32842000, 0, &pxa_device_i2c.dev),
-	PXA3xx_CKEN("UDCCLK", UDC,  48000000, 5, &pxa27x_device_udc.dev),
-	PXA3xx_CKEN("USBCLK", USBH, 48000000, 0, &pxa27x_device_ohci.dev),
-	PXA3xx_CKEN("KBDCLK", KEYPAD,  32768, 0, &pxa27x_device_keypad.dev),
+static struct clk clk_pxa3xx_pout = {
+	.ops		= &clk_pout_ops,
+	.rate		= 13000000,
+	.delay		= 70,
+};
 
-	PXA3xx_CKEN("SSPCLK", SSP1, 13000000, 0, &pxa27x_device_ssp1.dev),
-	PXA3xx_CKEN("SSPCLK", SSP2, 13000000, 0, &pxa27x_device_ssp2.dev),
-	PXA3xx_CKEN("SSPCLK", SSP3, 13000000, 0, &pxa27x_device_ssp3.dev),
-	PXA3xx_CKEN("SSPCLK", SSP4, 13000000, 0, &pxa3xx_device_ssp4.dev),
-	PXA3xx_CKEN("PWMCLK", PWM0, 13000000, 0, &pxa27x_device_pwm0.dev),
-	PXA3xx_CKEN("PWMCLK", PWM1, 13000000, 0, &pxa27x_device_pwm1.dev),
+static struct clk clk_dummy = {
+	.ops		= &clk_dummy_ops,
+};
 
-	PXA3xx_CKEN("MMCCLK", MMC1, 19500000, 0, &pxa_device_mci.dev),
-	PXA3xx_CKEN("MMCCLK", MMC2, 19500000, 0, &pxa3xx_device_mci2.dev),
+static DEFINE_PXA3_CK(pxa3xx_lcd, LCD, &clk_pxa3xx_hsio_ops);
+static DEFINE_PXA3_CK(pxa3xx_camera, CAMERA, &clk_pxa3xx_hsio_ops);
+static DEFINE_PXA3_CK(pxa3xx_ac97, AC97, &clk_pxa3xx_ac97_ops);
+static DEFINE_PXA3_CKEN(pxa3xx_ffuart, FFUART, 14857000, 1);
+static DEFINE_PXA3_CKEN(pxa3xx_btuart, BTUART, 14857000, 1);
+static DEFINE_PXA3_CKEN(pxa3xx_stuart, STUART, 14857000, 1);
+static DEFINE_PXA3_CKEN(pxa3xx_i2c, I2C, 32842000, 0);
+static DEFINE_PXA3_CKEN(pxa3xx_udc, UDC, 48000000, 5);
+static DEFINE_PXA3_CKEN(pxa3xx_usbh, USBH, 48000000, 0);
+static DEFINE_PXA3_CKEN(pxa3xx_keypad, KEYPAD, 32768, 0);
+static DEFINE_PXA3_CKEN(pxa3xx_ssp1, SSP1, 13000000, 0);
+static DEFINE_PXA3_CKEN(pxa3xx_ssp2, SSP2, 13000000, 0);
+static DEFINE_PXA3_CKEN(pxa3xx_ssp3, SSP3, 13000000, 0);
+static DEFINE_PXA3_CKEN(pxa3xx_ssp4, SSP4, 13000000, 0);
+static DEFINE_PXA3_CKEN(pxa3xx_pwm0, PWM0, 13000000, 0);
+static DEFINE_PXA3_CKEN(pxa3xx_pwm1, PWM1, 13000000, 0);
+static DEFINE_PXA3_CKEN(pxa3xx_mmc1, MMC1, 19500000, 0);
+static DEFINE_PXA3_CKEN(pxa3xx_mmc2, MMC2, 19500000, 0);
+
+static struct clk_lookup pxa3xx_clkregs[] = {
+	INIT_CLKREG(&clk_pxa3xx_pout, NULL, "CLK_POUT"),
+	/* Power I2C clock is always on */
+	INIT_CLKREG(&clk_dummy, "pxa2xx-i2c.1", NULL),
+	INIT_CLKREG(&clk_pxa3xx_lcd, "pxa2xx-fb", NULL),
+	INIT_CLKREG(&clk_pxa3xx_camera, NULL, "CAMCLK"),
+	INIT_CLKREG(&clk_pxa3xx_ac97, NULL, "AC97CLK"),
+	INIT_CLKREG(&clk_pxa3xx_ffuart, "pxa2xx-uart.0", NULL),
+	INIT_CLKREG(&clk_pxa3xx_btuart, "pxa2xx-uart.1", NULL),
+	INIT_CLKREG(&clk_pxa3xx_stuart, "pxa2xx-uart.2", NULL),
+	INIT_CLKREG(&clk_pxa3xx_stuart, "pxa2xx-ir", "UARTCLK"),
+	INIT_CLKREG(&clk_pxa3xx_i2c, "pxa2xx-i2c.0", NULL),
+	INIT_CLKREG(&clk_pxa3xx_udc, "pxa27x-udc", NULL),
+	INIT_CLKREG(&clk_pxa3xx_usbh, "pxa27x-ohci", NULL),
+	INIT_CLKREG(&clk_pxa3xx_keypad, "pxa27x-keypad", NULL),
+	INIT_CLKREG(&clk_pxa3xx_ssp1, "pxa27x-ssp.0", NULL),
+	INIT_CLKREG(&clk_pxa3xx_ssp2, "pxa27x-ssp.1", NULL),
+	INIT_CLKREG(&clk_pxa3xx_ssp3, "pxa27x-ssp.2", NULL),
+	INIT_CLKREG(&clk_pxa3xx_ssp4, "pxa27x-ssp.3", NULL),
+	INIT_CLKREG(&clk_pxa3xx_pwm0, "pxa27x-pwm.0", NULL),
+	INIT_CLKREG(&clk_pxa3xx_pwm1, "pxa27x-pwm.1", NULL),
+	INIT_CLKREG(&clk_pxa3xx_mmc1, "pxa2xx-mci.0", NULL),
+	INIT_CLKREG(&clk_pxa3xx_mmc2, "pxa2xx-mci.1", NULL),
 };
 
 #ifdef CONFIG_PM
@@ -529,28 +545,9 @@ void __init pxa3xx_init_irq(void)
  * device registration specific to PXA3xx.
  */
 
-static struct resource i2c_power_resources[] = {
-	{
-		.start  = 0x40f500c0,
-		.end    = 0x40f500d3,
-		.flags	= IORESOURCE_MEM,
-	}, {
-		.start	= IRQ_PWRI2C,
-		.end	= IRQ_PWRI2C,
-		.flags	= IORESOURCE_IRQ,
-	},
-};
-
-struct platform_device pxa3xx_device_i2c_power = {
-	.name		= "pxa2xx-i2c",
-	.id		= 1,
-	.resource	= i2c_power_resources,
-	.num_resources	= ARRAY_SIZE(i2c_power_resources),
-};
-
 void __init pxa3xx_set_i2c_power_info(struct i2c_pxa_platform_data *info)
 {
-	pxa3xx_device_i2c_power.dev.platform_data = info;
+	pxa_register_device(&pxa3xx_device_i2c_power, info);
 }
 
 static struct platform_device *devices[] __initdata = {
@@ -559,6 +556,7 @@ static struct platform_device *devices[] __initdata = {
 	&pxa_device_btuart,
 	&pxa_device_stuart,
 	&pxa_device_i2s,
+	&sa1100_device_rtc,
 	&pxa_device_rtc,
 	&pxa27x_device_ssp1,
 	&pxa27x_device_ssp2,
@@ -566,7 +564,6 @@ static struct platform_device *devices[] __initdata = {
 	&pxa3xx_device_ssp4,
 	&pxa27x_device_pwm0,
 	&pxa27x_device_pwm1,
-	&pxa3xx_device_i2c_power,
 };
 
 static struct sys_device pxa3xx_sysdev[] = {
@@ -595,7 +592,7 @@ static int __init pxa3xx_init(void)
 		 */
 		ASCR &= ~(ASCR_RDH | ASCR_D1S | ASCR_D2S | ASCR_D3S);
 
-		clks_register(pxa3xx_clks, ARRAY_SIZE(pxa3xx_clks));
+		clks_register(pxa3xx_clkregs, ARRAY_SIZE(pxa3xx_clkregs));
 
 		if ((ret = pxa_init_dma(32)))
 			return ret;
diff --git a/arch/arm/mach-pxa/smemc.c b/arch/arm/mach-pxa/smemc.c
index ad346addc028..d6f6904132a6 100644
--- a/arch/arm/mach-pxa/smemc.c
+++ b/arch/arm/mach-pxa/smemc.c
@@ -8,6 +8,8 @@
 #include <linux/io.h>
 #include <linux/sysdev.h>
 
+#include <mach/hardware.h>
+
 #define SMEMC_PHYS_BASE	(0x4A000000)
 #define SMEMC_PHYS_SIZE	(0x90)
 
diff --git a/arch/arm/mach-pxa/spitz.c b/arch/arm/mach-pxa/spitz.c
index 3be76ee2bdbf..7299d87a1cb3 100644
--- a/arch/arm/mach-pxa/spitz.c
+++ b/arch/arm/mach-pxa/spitz.c
@@ -22,6 +22,7 @@
 #include <linux/gpio.h>
 #include <linux/leds.h>
 #include <linux/mmc/host.h>
+#include <linux/mtd/physmap.h>
 #include <linux/pm.h>
 #include <linux/backlight.h>
 #include <linux/io.h>
@@ -122,6 +123,10 @@ static unsigned long spitz_pin_config[] __initdata = {
 	GPIO105_GPIO,	/* SPITZ_GPIO_CF_IRQ */
 	GPIO106_GPIO,	/* SPITZ_GPIO_CF2_IRQ */
 
+	/* I2C */
+	GPIO117_I2C_SCL,
+	GPIO118_I2C_SDA,
+
 	GPIO1_GPIO | WAKEUP_ON_EDGE_RISE,
 };
 
@@ -609,10 +614,41 @@ static struct pxafb_mach_info spitz_pxafb_info = {
 };
 
 
+static struct mtd_partition sharpsl_rom_parts[] = {
+	{
+		.name	="Boot PROM Filesystem",
+		.offset	= 0x00140000,
+		.size	= MTDPART_SIZ_FULL,
+	},
+};
+
+static struct physmap_flash_data sharpsl_rom_data = {
+	.width		= 2,
+	.nr_parts	= ARRAY_SIZE(sharpsl_rom_parts),
+	.parts		= sharpsl_rom_parts,
+};
+
+static struct resource sharpsl_rom_resources[] = {
+	{
+		.start	= 0x00000000,
+		.end	= 0x007fffff,
+		.flags	= IORESOURCE_MEM,
+	},
+};
+
+static struct platform_device sharpsl_rom_device = {
+	.name	= "physmap-flash",
+	.id	= -1,
+	.resource = sharpsl_rom_resources,
+	.num_resources = ARRAY_SIZE(sharpsl_rom_resources),
+	.dev.platform_data = &sharpsl_rom_data,
+};
+
 static struct platform_device *devices[] __initdata = {
 	&spitzscoop_device,
 	&spitzkbd_device,
 	&spitzled_device,
+	&sharpsl_rom_device,
 };
 
 static void spitz_poweroff(void)
diff --git a/arch/arm/mach-pxa/ssp.c b/arch/arm/mach-pxa/ssp.c
index 2c31ec725688..6f42004db3ed 100644
--- a/arch/arm/mach-pxa/ssp.c
+++ b/arch/arm/mach-pxa/ssp.c
@@ -356,7 +356,7 @@ static int __devinit ssp_probe(struct platform_device *pdev, int type)
 	}
 	ssp->pdev = pdev;
 
-	ssp->clk = clk_get(&pdev->dev, "SSPCLK");
+	ssp->clk = clk_get(&pdev->dev, NULL);
 	if (IS_ERR(ssp->clk)) {
 		ret = PTR_ERR(ssp->clk);
 		goto err_free;
diff --git a/arch/arm/mach-pxa/time.c b/arch/arm/mach-pxa/time.c
index f8a9a62959e5..ef4ddf9d5040 100644
--- a/arch/arm/mach-pxa/time.c
+++ b/arch/arm/mach-pxa/time.c
@@ -22,6 +22,7 @@
 #include <asm/div64.h>
 #include <asm/mach/irq.h>
 #include <asm/mach/time.h>
+#include <mach/hardware.h>
 #include <mach/pxa-regs.h>
 #include <asm/mach-types.h>
 
diff --git a/arch/arm/mach-pxa/tosa.c b/arch/arm/mach-pxa/tosa.c
index 224897a67d15..3332e5d0356c 100644
--- a/arch/arm/mach-pxa/tosa.c
+++ b/arch/arm/mach-pxa/tosa.c
@@ -25,6 +25,7 @@
 #include <linux/mfd/tmio.h>
 #include <linux/mtd/nand.h>
 #include <linux/mtd/partitions.h>
+#include <linux/mtd/physmap.h>
 #include <linux/pm.h>
 #include <linux/gpio_keys.h>
 #include <linux/input.h>
@@ -733,6 +734,45 @@ static void tosa_tc6393xb_teardown(struct platform_device *dev)
 	gpio_free(TOSA_GPIO_CARD_VCC_ON);
 }
 
+#ifdef CONFIG_MFD_TC6393XB
+static struct fb_videomode tosa_tc6393xb_lcd_mode[] = {
+	{
+		.xres = 480,
+		.yres = 640,
+		.pixclock = 0x002cdf00,/* PLL divisor */
+		.left_margin = 0x004c,
+		.right_margin = 0x005b,
+		.upper_margin = 0x0001,
+		.lower_margin = 0x000d,
+		.hsync_len = 0x0002,
+		.vsync_len = 0x0001,
+		.sync = FB_SYNC_HOR_HIGH_ACT | FB_SYNC_VERT_HIGH_ACT,
+		.vmode = FB_VMODE_NONINTERLACED,
+	},{
+		.xres = 240,
+		.yres = 320,
+		.pixclock = 0x00e7f203,/* PLL divisor */
+		.left_margin = 0x0024,
+		.right_margin = 0x002f,
+		.upper_margin = 0x0001,
+		.lower_margin = 0x000d,
+		.hsync_len = 0x0002,
+		.vsync_len = 0x0001,
+		.sync = FB_SYNC_HOR_HIGH_ACT | FB_SYNC_VERT_HIGH_ACT,
+		.vmode = FB_VMODE_NONINTERLACED,
+	}
+};
+
+static struct tmio_fb_data tosa_tc6393xb_fb_config = {
+	.lcd_set_power	= tc6393xb_lcd_set_power,
+	.lcd_mode	= tc6393xb_lcd_mode,
+	.num_modes	= ARRAY_SIZE(tosa_tc6393xb_lcd_mode),
+	.modes		= &tosa_tc6393xb_lcd_mode[0],
+	.height		= 82,
+	.width		= 60,
+};
+#endif
+
 static struct tc6393xb_platform_data tosa_tc6393xb_data = {
 	.scr_pll2cr	= 0x0cc1,
 	.scr_gper	= 0x3300,
@@ -748,6 +788,9 @@ static struct tc6393xb_platform_data tosa_tc6393xb_data = {
 	.resume		= tosa_tc6393xb_resume,
 
 	.nand_data	= &tosa_tc6393xb_nand_config,
+#ifdef CONFIG_MFD_TC6393XB
+	.fb_data	= &tosa_tc6393xb_fb_config,
+#endif
 
 	.resume_restore = 1,
 };
@@ -789,6 +832,36 @@ static struct spi_board_info spi_board_info[] __initdata = {
 	},
 };
 
+static struct mtd_partition sharpsl_rom_parts[] = {
+	{
+		.name	="Boot PROM Filesystem",
+		.offset	= 0x00160000,
+		.size	= MTDPART_SIZ_FULL,
+	},
+};
+
+static struct physmap_flash_data sharpsl_rom_data = {
+	.width		= 2,
+	.nr_parts	= ARRAY_SIZE(sharpsl_rom_parts),
+	.parts		= sharpsl_rom_parts,
+};
+
+static struct resource sharpsl_rom_resources[] = {
+	{
+		.start	= 0x00000000,
+		.end	= 0x007fffff,
+		.flags	= IORESOURCE_MEM,
+	},
+};
+
+static struct platform_device sharpsl_rom_device = {
+	.name	= "physmap-flash",
+	.id	= -1,
+	.resource = sharpsl_rom_resources,
+	.num_resources = ARRAY_SIZE(sharpsl_rom_resources),
+	.dev.platform_data = &sharpsl_rom_data,
+};
+
 static struct platform_device *devices[] __initdata = {
 	&tosascoop_device,
 	&tosascoop_jc_device,
@@ -798,6 +871,7 @@ static struct platform_device *devices[] __initdata = {
 	&tosa_gpio_keys_device,
 	&tosaled_device,
 	&tosa_bt_device,
+	&sharpsl_rom_device,
 };
 
 static void tosa_poweroff(void)
diff --git a/arch/arm/mach-pxa/zylonite.c b/arch/arm/mach-pxa/zylonite.c
index 813804433466..218d2001f1df 100644
--- a/arch/arm/mach-pxa/zylonite.c
+++ b/arch/arm/mach-pxa/zylonite.c
@@ -18,6 +18,7 @@
 #include <linux/interrupt.h>
 #include <linux/init.h>
 #include <linux/platform_device.h>
+#include <linux/gpio.h>
 #include <linux/pwm_backlight.h>
 #include <linux/smc91x.h>
 
@@ -25,7 +26,6 @@
 #include <asm/mach/arch.h>
 #include <mach/hardware.h>
 #include <mach/audio.h>
-#include <mach/gpio.h>
 #include <mach/pxafb.h>
 #include <mach/zylonite.h>
 #include <mach/mmc.h>
diff --git a/arch/arm/mach-pxa/zylonite_pxa320.c b/arch/arm/mach-pxa/zylonite_pxa320.c
index 0f244744daae..28e4e623780b 100644
--- a/arch/arm/mach-pxa/zylonite_pxa320.c
+++ b/arch/arm/mach-pxa/zylonite_pxa320.c
@@ -16,8 +16,8 @@
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/init.h>
+#include <linux/gpio.h>
 
-#include <mach/gpio.h>
 #include <mach/mfp-pxa320.h>
 #include <mach/zylonite.h>
 
diff --git a/arch/arm/mach-realview/Kconfig b/arch/arm/mach-realview/Kconfig
index 5ccde7cf39e8..ad911854eb4c 100644
--- a/arch/arm/mach-realview/Kconfig
+++ b/arch/arm/mach-realview/Kconfig
@@ -7,9 +7,17 @@ config MACH_REALVIEW_EB
 	help
 	  Include support for the ARM(R) RealView Emulation Baseboard platform.
 
+config REALVIEW_EB_A9MP
+	bool "Support Multicore Cortex-A9"
+	depends on MACH_REALVIEW_EB
+	select CPU_V7
+	help
+	  Enable support for the Cortex-A9MPCore tile on the Realview platform.
+
 config REALVIEW_EB_ARM11MP
 	bool "Support ARM11MPCore tile"
 	depends on MACH_REALVIEW_EB
+	select CPU_V6
 	help
 	  Enable support for the ARM11MPCore tile on the Realview platform.
 
@@ -25,6 +33,7 @@ config REALVIEW_EB_ARM11MP_REVB
 
 config MACH_REALVIEW_PB11MP
 	bool "Support RealView/PB11MPCore platform"
+	select CPU_V6
 	select ARM_GIC
 	help
 	  Include support for the ARM(R) RealView MPCore Platform Baseboard.
@@ -33,8 +42,29 @@ config MACH_REALVIEW_PB11MP
 
 config MACH_REALVIEW_PB1176
 	bool "Support RealView/PB1176 platform"
+	select CPU_V6
 	select ARM_GIC
 	help
 	  Include support for the ARM(R) RealView ARM1176 Platform Baseboard.
 
+config MACH_REALVIEW_PBA8
+	bool "Support RealView/PB-A8 platform"
+	select CPU_V7
+	select ARM_GIC
+	help
+	  Include support for the ARM(R) RealView Cortex-A8 Platform Baseboard.
+	  PB-A8 is a platform with an on-board Cortex-A8 and has support for
+	  PCI-E and Compact Flash.
+
+config REALVIEW_HIGH_PHYS_OFFSET
+	bool "High physical base address for the RealView platform"
+	depends on !MACH_REALVIEW_PB1176
+	default y
+	help
+	  RealView boards other than PB1176 have the RAM available at
+	  0x70000000, 256MB of which being mirrored at 0x00000000. If
+	  the board supports 512MB of RAM, this option allows the
+	  memory to be accessed contiguously at the high physical
+	  offset.
+
 endmenu
diff --git a/arch/arm/mach-realview/Makefile b/arch/arm/mach-realview/Makefile
index d2ae077431dd..7bea8ffc4b59 100644
--- a/arch/arm/mach-realview/Makefile
+++ b/arch/arm/mach-realview/Makefile
@@ -6,5 +6,6 @@ obj-y					:= core.o clock.o
 obj-$(CONFIG_MACH_REALVIEW_EB)		+= realview_eb.o
 obj-$(CONFIG_MACH_REALVIEW_PB11MP)	+= realview_pb11mp.o
 obj-$(CONFIG_MACH_REALVIEW_PB1176)	+= realview_pb1176.o
+obj-$(CONFIG_MACH_REALVIEW_PBA8)	+= realview_pba8.o
 obj-$(CONFIG_SMP)			+= platsmp.o headsmp.o localtimer.o
 obj-$(CONFIG_HOTPLUG_CPU)		+= hotplug.o
diff --git a/arch/arm/mach-realview/Makefile.boot b/arch/arm/mach-realview/Makefile.boot
index c7e75acfe6c9..d97e003d3df4 100644
--- a/arch/arm/mach-realview/Makefile.boot
+++ b/arch/arm/mach-realview/Makefile.boot
@@ -1,4 +1,9 @@
+ifeq ($(CONFIG_REALVIEW_HIGH_PHYS_OFFSET),y)
+   zreladdr-y	:= 0x70008000
+params_phys-y	:= 0x70000100
+initrd_phys-y	:= 0x70800000
+else
    zreladdr-y	:= 0x00008000
 params_phys-y	:= 0x00000100
 initrd_phys-y	:= 0x00800000
-
+endif
diff --git a/arch/arm/mach-realview/clock.c b/arch/arm/mach-realview/clock.c
index 3347c4236a60..a7043115de72 100644
--- a/arch/arm/mach-realview/clock.c
+++ b/arch/arm/mach-realview/clock.c
@@ -10,9 +10,11 @@
  */
 #include <linux/module.h>
 #include <linux/kernel.h>
+#include <linux/device.h>
 #include <linux/list.h>
 #include <linux/errno.h>
 #include <linux/err.h>
+#include <linux/string.h>
 #include <linux/clk.h>
 #include <linux/mutex.h>
 
@@ -20,32 +22,6 @@
 
 #include "clock.h"
 
-static LIST_HEAD(clocks);
-static DEFINE_MUTEX(clocks_mutex);
-
-struct clk *clk_get(struct device *dev, const char *id)
-{
-	struct clk *p, *clk = ERR_PTR(-ENOENT);
-
-	mutex_lock(&clocks_mutex);
-	list_for_each_entry(p, &clocks, node) {
-		if (strcmp(id, p->name) == 0 && try_module_get(p->owner)) {
-			clk = p;
-			break;
-		}
-	}
-	mutex_unlock(&clocks_mutex);
-
-	return clk;
-}
-EXPORT_SYMBOL(clk_get);
-
-void clk_put(struct clk *clk)
-{
-	module_put(clk->owner);
-}
-EXPORT_SYMBOL(clk_put);
-
 int clk_enable(struct clk *clk)
 {
 	return 0;
@@ -65,7 +41,9 @@ EXPORT_SYMBOL(clk_get_rate);
 
 long clk_round_rate(struct clk *clk, unsigned long rate)
 {
-	return rate;
+	struct icst307_vco vco;
+	vco = icst307_khz_to_vco(clk->params, rate / 1000);
+	return icst307_khz(clk->params, vco) * 1000;
 }
 EXPORT_SYMBOL(clk_round_rate);
 
@@ -78,57 +56,9 @@ int clk_set_rate(struct clk *clk, unsigned long rate)
 
 		vco = icst307_khz_to_vco(clk->params, rate / 1000);
 		clk->rate = icst307_khz(clk->params, vco) * 1000;
-
-		printk("Clock %s: setting VCO reg params: S=%d R=%d V=%d\n",
-			clk->name, vco.s, vco.r, vco.v);
-
 		clk->setvco(clk, vco);
 		ret = 0;
 	}
 	return ret;
 }
 EXPORT_SYMBOL(clk_set_rate);
-
-/*
- * These are fixed clocks.
- */
-static struct clk kmi_clk = {
-	.name	= "KMIREFCLK",
-	.rate	= 24000000,
-};
-
-static struct clk uart_clk = {
-	.name	= "UARTCLK",
-	.rate	= 24000000,
-};
-
-static struct clk mmci_clk = {
-	.name	= "MCLK",
-	.rate	= 24000000,
-};
-
-int clk_register(struct clk *clk)
-{
-	mutex_lock(&clocks_mutex);
-	list_add(&clk->node, &clocks);
-	mutex_unlock(&clocks_mutex);
-	return 0;
-}
-EXPORT_SYMBOL(clk_register);
-
-void clk_unregister(struct clk *clk)
-{
-	mutex_lock(&clocks_mutex);
-	list_del(&clk->node);
-	mutex_unlock(&clocks_mutex);
-}
-EXPORT_SYMBOL(clk_unregister);
-
-static int __init clk_init(void)
-{
-	clk_register(&kmi_clk);
-	clk_register(&uart_clk);
-	clk_register(&mmci_clk);
-	return 0;
-}
-arch_initcall(clk_init);
diff --git a/arch/arm/mach-realview/clock.h b/arch/arm/mach-realview/clock.h
index dadba695e181..ebbb0f06b600 100644
--- a/arch/arm/mach-realview/clock.h
+++ b/arch/arm/mach-realview/clock.h
@@ -12,14 +12,8 @@ struct module;
 struct icst307_params;
 
 struct clk {
-	struct list_head	node;
 	unsigned long		rate;
-	struct module		*owner;
-	const char		*name;
 	const struct icst307_params *params;
 	void			*data;
 	void			(*setvco)(struct clk *, struct icst307_vco vco);
 };
-
-int clk_register(struct clk *clk);
-void clk_unregister(struct clk *clk);
diff --git a/arch/arm/mach-realview/core.c b/arch/arm/mach-realview/core.c
index 2f04d54711e7..5f1d55963ced 100644
--- a/arch/arm/mach-realview/core.c
+++ b/arch/arm/mach-realview/core.c
@@ -28,11 +28,14 @@
 #include <linux/clocksource.h>
 #include <linux/clockchips.h>
 #include <linux/io.h>
+#include <linux/smc911x.h>
 
+#include <asm/clkdev.h>
 #include <asm/system.h>
 #include <mach/hardware.h>
 #include <asm/irq.h>
 #include <asm/leds.h>
+#include <asm/mach-types.h>
 #include <asm/hardware/arm_timer.h>
 #include <asm/hardware/icst307.h>
 
@@ -49,7 +52,7 @@
 
 #define REALVIEW_REFCOUNTER	(__io_address(REALVIEW_SYS_BASE) + REALVIEW_SYS_24MHz_OFFSET)
 
-/* used by entry-macro.S */
+/* used by entry-macro.S and platsmp.c */
 void __iomem *gic_cpu_base_addr;
 
 /*
@@ -124,6 +127,29 @@ int realview_flash_register(struct resource *res, u32 num)
 	return platform_device_register(&realview_flash_device);
 }
 
+static struct smc911x_platdata realview_smc911x_platdata = {
+	.flags		= SMC911X_USE_32BIT,
+	.irq_flags	= IRQF_SHARED,
+	.irq_polarity	= 1,
+};
+
+static struct platform_device realview_eth_device = {
+	.name		= "smc911x",
+	.id		= 0,
+	.num_resources	= 2,
+};
+
+int realview_eth_register(const char *name, struct resource *res)
+{
+	if (name)
+		realview_eth_device.name = name;
+	realview_eth_device.resource = res;
+	if (strcmp(realview_eth_device.name, "smc911x") == 0)
+		realview_eth_device.dev.platform_data = &realview_smc911x_platdata;
+
+	return platform_device_register(&realview_eth_device);
+}
+
 static struct resource realview_i2c_resource = {
 	.start		= REALVIEW_I2C_BASE,
 	.end		= REALVIEW_I2C_BASE + SZ_4K - 1,
@@ -177,9 +203,14 @@ static const struct icst307_params realview_oscvco_params = {
 static void realview_oscvco_set(struct clk *clk, struct icst307_vco vco)
 {
 	void __iomem *sys_lock = __io_address(REALVIEW_SYS_BASE) + REALVIEW_SYS_LOCK_OFFSET;
-	void __iomem *sys_osc = __io_address(REALVIEW_SYS_BASE) + REALVIEW_SYS_OSC4_OFFSET;
+	void __iomem *sys_osc;
 	u32 val;
 
+	if (machine_is_realview_pb1176())
+		sys_osc = __io_address(REALVIEW_SYS_BASE) + REALVIEW_SYS_OSC0_OFFSET;
+	else
+		sys_osc = __io_address(REALVIEW_SYS_BASE) + REALVIEW_SYS_OSC4_OFFSET;
+
 	val = readl(sys_osc) & ~0x7ffff;
 	val |= vco.v | (vco.r << 9) | (vco.s << 16);
 
@@ -188,13 +219,60 @@ static void realview_oscvco_set(struct clk *clk, struct icst307_vco vco)
 	writel(0, sys_lock);
 }
 
-struct clk realview_clcd_clk = {
-	.name	= "CLCDCLK",
+static struct clk oscvco_clk = {
 	.params	= &realview_oscvco_params,
 	.setvco = realview_oscvco_set,
 };
 
 /*
+ * These are fixed clocks.
+ */
+static struct clk ref24_clk = {
+	.rate	= 24000000,
+};
+
+static struct clk_lookup lookups[] = {
+	{	/* UART0 */
+		.dev_id		= "dev:f1",
+		.clk		= &ref24_clk,
+	}, {	/* UART1 */
+		.dev_id		= "dev:f2",
+		.clk		= &ref24_clk,
+	}, {	/* UART2 */
+		.dev_id		= "dev:f3",
+		.clk		= &ref24_clk,
+	}, {	/* UART3 */
+		.dev_id		= "fpga:09",
+		.clk		= &ref24_clk,
+	}, {	/* KMI0 */
+		.dev_id		= "fpga:06",
+		.clk		= &ref24_clk,
+	}, {	/* KMI1 */
+		.dev_id		= "fpga:07",
+		.clk		= &ref24_clk,
+	}, {	/* MMC0 */
+		.dev_id		= "fpga:05",
+		.clk		= &ref24_clk,
+	}, {	/* EB:CLCD */
+		.dev_id		= "dev:20",
+		.clk		= &oscvco_clk,
+	}, {	/* PB:CLCD */
+		.dev_id		= "issp:20",
+		.clk		= &oscvco_clk,
+	}
+};
+
+static int __init clk_init(void)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(lookups); i++)
+		clkdev_add(&lookups[i]);
+	return 0;
+}
+arch_initcall(clk_init);
+
+/*
  * CLCD support.
  */
 #define SYS_CLCD_NLCDIOON	(1 << 2)
@@ -226,7 +304,30 @@ static struct clcd_panel vga = {
 	.width		= -1,
 	.height		= -1,
 	.tim2		= TIM2_BCD | TIM2_IPC,
-	.cntl		= CNTL_LCDTFT | CNTL_LCDVCOMP(1),
+	.cntl		= CNTL_LCDTFT | CNTL_BGR | CNTL_LCDVCOMP(1),
+	.bpp		= 16,
+};
+
+static struct clcd_panel xvga = {
+	.mode		= {
+		.name		= "XVGA",
+		.refresh	= 60,
+		.xres		= 1024,
+		.yres		= 768,
+		.pixclock	= 15748,
+		.left_margin	= 152,
+		.right_margin	= 48,
+		.upper_margin	= 23,
+		.lower_margin	= 3,
+		.hsync_len	= 104,
+		.vsync_len	= 4,
+		.sync		= 0,
+		.vmode		= FB_VMODE_NONINTERLACED,
+	},
+	.width		= -1,
+	.height		= -1,
+	.tim2		= TIM2_BCD | TIM2_IPC,
+	.cntl		= CNTL_LCDTFT | CNTL_BGR | CNTL_LCDVCOMP(1),
 	.bpp		= 16,
 };
 
@@ -249,7 +350,7 @@ static struct clcd_panel sanyo_3_8_in = {
 	.width		= -1,
 	.height		= -1,
 	.tim2		= TIM2_BCD,
-	.cntl		= CNTL_LCDTFT | CNTL_LCDVCOMP(1),
+	.cntl		= CNTL_LCDTFT | CNTL_BGR | CNTL_LCDVCOMP(1),
 	.bpp		= 16,
 };
 
@@ -272,7 +373,7 @@ static struct clcd_panel sanyo_2_5_in = {
 	.width		= -1,
 	.height		= -1,
 	.tim2		= TIM2_IVS | TIM2_IHS | TIM2_IPC,
-	.cntl		= CNTL_LCDTFT | CNTL_LCDVCOMP(1),
+	.cntl		= CNTL_LCDTFT | CNTL_BGR | CNTL_LCDVCOMP(1),
 	.bpp		= 16,
 };
 
@@ -295,7 +396,7 @@ static struct clcd_panel epson_2_2_in = {
 	.width		= -1,
 	.height		= -1,
 	.tim2		= TIM2_BCD | TIM2_IPC,
-	.cntl		= CNTL_LCDTFT | CNTL_LCDVCOMP(1),
+	.cntl		= CNTL_LCDTFT | CNTL_BGR | CNTL_LCDVCOMP(1),
 	.bpp		= 16,
 };
 
@@ -308,9 +409,15 @@ static struct clcd_panel epson_2_2_in = {
 static struct clcd_panel *realview_clcd_panel(void)
 {
 	void __iomem *sys_clcd = __io_address(REALVIEW_SYS_BASE) + REALVIEW_SYS_CLCD_OFFSET;
-	struct clcd_panel *panel = &vga;
+	struct clcd_panel *vga_panel;
+	struct clcd_panel *panel;
 	u32 val;
 
+	if (machine_is_realview_eb())
+		vga_panel = &vga;
+	else
+		vga_panel = &xvga;
+
 	val = readl(sys_clcd) & SYS_CLCD_ID_MASK;
 	if (val == SYS_CLCD_ID_SANYO_3_8)
 		panel = &sanyo_3_8_in;
@@ -319,11 +426,11 @@ static struct clcd_panel *realview_clcd_panel(void)
 	else if (val == SYS_CLCD_ID_EPSON_2_2)
 		panel = &epson_2_2_in;
 	else if (val == SYS_CLCD_ID_VGA)
-		panel = &vga;
+		panel = vga_panel;
 	else {
 		printk(KERN_ERR "CLCD: unknown LCD panel ID 0x%08x, using VGA\n",
 			val);
-		panel = &vga;
+		panel = vga_panel;
 	}
 
 	return panel;
@@ -358,12 +465,18 @@ static void realview_clcd_enable(struct clcd_fb *fb)
 	writel(val, sys_clcd);
 }
 
-static unsigned long framesize = SZ_1M;
-
 static int realview_clcd_setup(struct clcd_fb *fb)
 {
+	unsigned long framesize;
 	dma_addr_t dma;
 
+	if (machine_is_realview_eb())
+		/* VGA, 16bpp */
+		framesize = 640 * 480 * 2;
+	else
+		/* XVGA, 16bpp */
+		framesize = 1024 * 768 * 2;
+
 	fb->panel		= realview_clcd_panel();
 
 	fb->fb.screen_base = dma_alloc_writecombine(&fb->dev->dev, framesize,
@@ -588,7 +701,7 @@ void __init realview_timer_init(unsigned int timer_irq)
 	 * The dummy clock device has to be registered before the main device
 	 * so that the latter will broadcast the clock events
 	 */
-	local_timer_setup(smp_processor_id());
+	local_timer_setup();
 #endif
 
 	/* 
diff --git a/arch/arm/mach-realview/core.h b/arch/arm/mach-realview/core.h
index 3cea92c70d8f..44269b162d49 100644
--- a/arch/arm/mach-realview/core.h
+++ b/arch/arm/mach-realview/core.h
@@ -31,7 +31,7 @@
 static struct amba_device name##_device = {			\
 	.dev		= {					\
 		.coherent_dma_mask = ~0,			\
-		.bus_id	= busid,				\
+		.init_name = busid,				\
 		.platform_data = plat,				\
 	},							\
 	.res		= {					\
@@ -48,12 +48,10 @@ extern struct platform_device realview_flash_device;
 extern struct platform_device realview_i2c_device;
 extern struct mmc_platform_data realview_mmc0_plat_data;
 extern struct mmc_platform_data realview_mmc1_plat_data;
-extern struct clk realview_clcd_clk;
 extern struct clcd_board clcd_plat_data;
 extern void __iomem *gic_cpu_base_addr;
 #ifdef CONFIG_LOCAL_TIMERS
-extern void __iomem *twd_base_addr;
-extern unsigned int twd_size;
+extern void __iomem *twd_base;
 #endif
 extern void __iomem *timer0_va_base;
 extern void __iomem *timer1_va_base;
@@ -63,5 +61,6 @@ extern void __iomem *timer3_va_base;
 extern void realview_leds_event(led_event_t ledevt);
 extern void realview_timer_init(unsigned int timer_irq);
 extern int realview_flash_register(struct resource *res, u32 num);
+extern int realview_eth_register(const char *name, struct resource *res);
 
 #endif
diff --git a/arch/arm/mach-realview/hotplug.c b/arch/arm/mach-realview/hotplug.c
index 09748cbcd10e..be048e3e8799 100644
--- a/arch/arm/mach-realview/hotplug.c
+++ b/arch/arm/mach-realview/hotplug.c
@@ -13,6 +13,8 @@
 #include <linux/smp.h>
 #include <linux/completion.h>
 
+#include <asm/cacheflush.h>
+
 extern volatile int pen_release;
 
 static DECLARE_COMPLETION(cpu_killed);
@@ -21,7 +23,8 @@ static inline void cpu_enter_lowpower(void)
 {
 	unsigned int v;
 
-	asm volatile(	"mcr	p15, 0, %1, c7, c14, 0\n"
+	flush_cache_all();
+	asm volatile(
 	"	mcr	p15, 0, %1, c7, c5, 0\n"
 	"	mcr	p15, 0, %1, c7, c10, 4\n"
 	/*
diff --git a/arch/arm/mach-realview/include/mach/board-eb.h b/arch/arm/mach-realview/include/mach/board-eb.h
index 8d699fd324d0..268d7701fa9b 100644
--- a/arch/arm/mach-realview/include/mach/board-eb.h
+++ b/arch/arm/mach-realview/include/mach/board-eb.h
@@ -49,16 +49,14 @@
 #ifdef CONFIG_REALVIEW_EB_ARM11MP_REVB
 #define REALVIEW_EB11MP_SCU_BASE	0x10100000	/* SCU registers */
 #define REALVIEW_EB11MP_GIC_CPU_BASE	0x10100100	/* Generic interrupt controller CPU interface */
-#define REALVIEW_EB11MP_TWD_BASE	0x10100700
-#define REALVIEW_EB11MP_TWD_SIZE	0x00000100
+#define REALVIEW_EB11MP_TWD_BASE	0x10100600
 #define REALVIEW_EB11MP_GIC_DIST_BASE	0x10101000	/* Generic interrupt controller distributor */
 #define REALVIEW_EB11MP_L220_BASE	0x10102000	/* L220 registers */
 #define REALVIEW_EB11MP_SYS_PLD_CTRL1	0xD8		/* Register offset for MPCore sysctl */
 #else
 #define REALVIEW_EB11MP_SCU_BASE	0x1F000000	/* SCU registers */
 #define REALVIEW_EB11MP_GIC_CPU_BASE	0x1F000100	/* Generic interrupt controller CPU interface */
-#define REALVIEW_EB11MP_TWD_BASE	0x1F000700
-#define REALVIEW_EB11MP_TWD_SIZE	0x00000100
+#define REALVIEW_EB11MP_TWD_BASE	0x1F000600
 #define REALVIEW_EB11MP_GIC_DIST_BASE	0x1F001000	/* Generic interrupt controller distributor */
 #define REALVIEW_EB11MP_L220_BASE	0x1F002000	/* L220 registers */
 #define REALVIEW_EB11MP_SYS_PLD_CTRL1	0x74		/* Register offset for MPCore sysctl */
@@ -163,7 +161,7 @@
 #define NR_IRQS			NR_IRQS_EB
 #endif
 
-#if defined(CONFIG_REALVIEW_EB_ARM11MP) \
+#if defined(CONFIG_REALVIEW_EB_ARM11MP) || defined(CONFIG_REALVIEW_EB_A9MP) \
 	&& (!defined(MAX_GIC_NR) || (MAX_GIC_NR < NR_GIC_EB11MP))
 #undef MAX_GIC_NR
 #define MAX_GIC_NR		NR_GIC_EB11MP
@@ -177,6 +175,7 @@
 #define REALVIEW_EB_PROC_ARM9		0x02000000
 #define REALVIEW_EB_PROC_ARM11		0x04000000
 #define REALVIEW_EB_PROC_ARM11MP	0x06000000
+#define REALVIEW_EB_PROC_A9MP		0x0C000000
 
 #define check_eb_proc(proc_type)						\
 	((readl(__io_address(REALVIEW_SYS_PROCID)) & REALVIEW_EB_PROC_MASK)	\
@@ -188,4 +187,13 @@
 #define core_tile_eb11mp()	0
 #endif
 
+#ifdef CONFIG_REALVIEW_EB_A9MP
+#define core_tile_a9mp()	check_eb_proc(REALVIEW_EB_PROC_A9MP)
+#else
+#define core_tile_a9mp()	0
+#endif
+
+#define machine_is_realview_eb_mp() \
+	(machine_is_realview_eb() && (core_tile_eb11mp() || core_tile_a9mp()))
+
 #endif	/* __ASM_ARCH_BOARD_EB_H */
diff --git a/arch/arm/mach-realview/include/mach/board-pb11mp.h b/arch/arm/mach-realview/include/mach/board-pb11mp.h
index ecd80e58631e..53ea0e7a1267 100644
--- a/arch/arm/mach-realview/include/mach/board-pb11mp.h
+++ b/arch/arm/mach-realview/include/mach/board-pb11mp.h
@@ -77,8 +77,7 @@
  */
 #define REALVIEW_TC11MP_SCU_BASE		0x1F000000	/* IRQ, Test chip */
 #define REALVIEW_TC11MP_GIC_CPU_BASE		0x1F000100	/* Test chip interrupt controller CPU interface */
-#define REALVIEW_TC11MP_TWD_BASE		0x1F000700
-#define REALVIEW_TC11MP_TWD_SIZE		0x00000100
+#define REALVIEW_TC11MP_TWD_BASE		0x1F000600
 #define REALVIEW_TC11MP_GIC_DIST_BASE		0x1F001000	/* Test chip interrupt controller distributor */
 #define REALVIEW_TC11MP_L220_BASE		0x1F002000	/* L220 registers */
 
diff --git a/arch/arm/mach-realview/include/mach/board-pba8.h b/arch/arm/mach-realview/include/mach/board-pba8.h
new file mode 100644
index 000000000000..c8bed8f58bab
--- /dev/null
+++ b/arch/arm/mach-realview/include/mach/board-pba8.h
@@ -0,0 +1,152 @@
+/*
+ * include/asm-arm/arch-realview/board-pba8.h
+ *
+ * Copyright (C) 2008 ARM Limited
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+ * MA 02110-1301, USA.
+ */
+
+#ifndef __ASM_ARCH_BOARD_PBA8_H
+#define __ASM_ARCH_BOARD_PBA8_H
+
+#include <mach/platform.h>
+
+/*
+ * Peripheral addresses
+ */
+#define REALVIEW_PBA8_UART0_BASE		0x10009000	/* UART 0 */
+#define REALVIEW_PBA8_UART1_BASE		0x1000A000	/* UART 1 */
+#define REALVIEW_PBA8_UART2_BASE		0x1000B000	/* UART 2 */
+#define REALVIEW_PBA8_UART3_BASE		0x1000C000	/* UART 3 */
+#define REALVIEW_PBA8_SSP_BASE			0x1000D000	/* Synchronous Serial Port */
+#define REALVIEW_PBA8_WATCHDOG0_BASE		0x1000F000	/* Watchdog 0 */
+#define REALVIEW_PBA8_WATCHDOG_BASE		0x10010000	/* watchdog interface */
+#define REALVIEW_PBA8_TIMER0_1_BASE		0x10011000	/* Timer 0 and 1 */
+#define REALVIEW_PBA8_TIMER2_3_BASE		0x10012000	/* Timer 2 and 3 */
+#define REALVIEW_PBA8_GPIO0_BASE		0x10013000	/* GPIO port 0 */
+#define REALVIEW_PBA8_RTC_BASE			0x10017000	/* Real Time Clock */
+#define REALVIEW_PBA8_TIMER4_5_BASE		0x10018000	/* Timer 4/5 */
+#define REALVIEW_PBA8_TIMER6_7_BASE		0x10019000	/* Timer 6/7 */
+#define REALVIEW_PBA8_SCTL_BASE			0x1001A000	/* System Controller */
+#define REALVIEW_PBA8_CLCD_BASE			0x10020000	/* CLCD */
+#define REALVIEW_PBA8_ONB_SRAM_BASE		0x10060000	/* On-board SRAM */
+#define REALVIEW_PBA8_DMC_BASE			0x100E0000	/* DMC configuration */
+#define REALVIEW_PBA8_SMC_BASE			0x100E1000	/* SMC configuration */
+#define REALVIEW_PBA8_CAN_BASE			0x100E2000	/* CAN bus */
+#define REALVIEW_PBA8_CF_BASE			0x18000000	/* Compact flash */
+#define REALVIEW_PBA8_CF_MEM_BASE		0x18003000	/* SMC for Compact flash */
+#define REALVIEW_PBA8_GIC_CPU_BASE		0x1E000000	/* Generic interrupt controller CPU interface */
+#define REALVIEW_PBA8_FLASH0_BASE		0x40000000
+#define REALVIEW_PBA8_FLASH0_SIZE		SZ_64M
+#define REALVIEW_PBA8_FLASH1_BASE		0x44000000
+#define REALVIEW_PBA8_FLASH1_SIZE		SZ_64M
+#define REALVIEW_PBA8_ETH_BASE			0x4E000000	/* Ethernet */
+#define REALVIEW_PBA8_USB_BASE			0x4F000000	/* USB */
+#define REALVIEW_PBA8_GIC_DIST_BASE		0x1E001000	/* Generic interrupt controller distributor */
+#define REALVIEW_PBA8_LT_BASE			0xC0000000	/* Logic Tile expansion */
+#define REALVIEW_PBA8_SDRAM6_BASE		0x70000000	/* SDRAM bank 6 256MB */
+#define REALVIEW_PBA8_SDRAM7_BASE		0x80000000	/* SDRAM bank 7 256MB */
+
+#define REALVIEW_PBA8_SYS_PLD_CTRL1		0x74
+
+/*
+ * PBA8 PCI regions
+ */
+#define REALVIEW_PBA8_PCI_BASE			0x90040000	/* PCI-X Unit base */
+#define REALVIEW_PBA8_PCI_IO_BASE		0x90050000	/* IO Region on AHB */
+#define REALVIEW_PBA8_PCI_MEM_BASE		0xA0000000	/* MEM Region on AHB */
+
+#define REALVIEW_PBA8_PCI_BASE_SIZE		0x10000		/* 16 Kb */
+#define REALVIEW_PBA8_PCI_IO_SIZE		0x1000		/* 4 Kb */
+#define REALVIEW_PBA8_PCI_MEM_SIZE		0x20000000	/* 512 MB */
+
+/*
+ * Irqs
+ */
+#define IRQ_PBA8_GIC_START			32
+
+/* L220
+#define IRQ_PBA8_L220_EVENT	(IRQ_PBA8_GIC_START + 29)
+#define IRQ_PBA8_L220_SLAVE	(IRQ_PBA8_GIC_START + 30)
+#define IRQ_PBA8_L220_DECODE	(IRQ_PBA8_GIC_START + 31)
+*/
+
+/*
+ * PB-A8 on-board gic irq sources
+ */
+#define IRQ_PBA8_WATCHDOG	(IRQ_PBA8_GIC_START + 0)	/* Watchdog timer */
+#define IRQ_PBA8_SOFT		(IRQ_PBA8_GIC_START + 1)	/* Software interrupt */
+#define IRQ_PBA8_COMMRx		(IRQ_PBA8_GIC_START + 2)	/* Debug Comm Rx interrupt */
+#define IRQ_PBA8_COMMTx		(IRQ_PBA8_GIC_START + 3)	/* Debug Comm Tx interrupt */
+#define IRQ_PBA8_TIMER0_1	(IRQ_PBA8_GIC_START + 4)	/* Timer 0/1 (default timer) */
+#define IRQ_PBA8_TIMER2_3	(IRQ_PBA8_GIC_START + 5)	/* Timer 2/3 */
+#define IRQ_PBA8_GPIO0		(IRQ_PBA8_GIC_START + 6)	/* GPIO 0 */
+#define IRQ_PBA8_GPIO1		(IRQ_PBA8_GIC_START + 7)	/* GPIO 1 */
+#define IRQ_PBA8_GPIO2		(IRQ_PBA8_GIC_START + 8)	/* GPIO 2 */
+								/* 9 reserved */
+#define IRQ_PBA8_RTC		(IRQ_PBA8_GIC_START + 10)	/* Real Time Clock */
+#define IRQ_PBA8_SSP		(IRQ_PBA8_GIC_START + 11)	/* Synchronous Serial Port */
+#define IRQ_PBA8_UART0		(IRQ_PBA8_GIC_START + 12)	/* UART 0 on development chip */
+#define IRQ_PBA8_UART1		(IRQ_PBA8_GIC_START + 13)	/* UART 1 on development chip */
+#define IRQ_PBA8_UART2		(IRQ_PBA8_GIC_START + 14)	/* UART 2 on development chip */
+#define IRQ_PBA8_UART3		(IRQ_PBA8_GIC_START + 15)	/* UART 3 on development chip */
+#define IRQ_PBA8_SCI		(IRQ_PBA8_GIC_START + 16)	/* Smart Card Interface */
+#define IRQ_PBA8_MMCI0A		(IRQ_PBA8_GIC_START + 17)	/* Multimedia Card 0A */
+#define IRQ_PBA8_MMCI0B		(IRQ_PBA8_GIC_START + 18)	/* Multimedia Card 0B */
+#define IRQ_PBA8_AACI		(IRQ_PBA8_GIC_START + 19)	/* Audio Codec */
+#define IRQ_PBA8_KMI0		(IRQ_PBA8_GIC_START + 20)	/* Keyboard/Mouse port 0 */
+#define IRQ_PBA8_KMI1		(IRQ_PBA8_GIC_START + 21)	/* Keyboard/Mouse port 1 */
+#define IRQ_PBA8_CHARLCD	(IRQ_PBA8_GIC_START + 22)	/* Character LCD */
+#define IRQ_PBA8_CLCD		(IRQ_PBA8_GIC_START + 23)	/* CLCD controller */
+#define IRQ_PBA8_DMAC		(IRQ_PBA8_GIC_START + 24)	/* DMA controller */
+#define IRQ_PBA8_PWRFAIL	(IRQ_PBA8_GIC_START + 25)	/* Power failure */
+#define IRQ_PBA8_PISMO		(IRQ_PBA8_GIC_START + 26)	/* PISMO interface */
+#define IRQ_PBA8_DoC		(IRQ_PBA8_GIC_START + 27)	/* Disk on Chip memory controller */
+#define IRQ_PBA8_ETH		(IRQ_PBA8_GIC_START + 28)	/* Ethernet controller */
+#define IRQ_PBA8_USB		(IRQ_PBA8_GIC_START + 29)	/* USB controller */
+#define IRQ_PBA8_TSPEN		(IRQ_PBA8_GIC_START + 30)	/* Touchscreen pen */
+#define IRQ_PBA8_TSKPAD		(IRQ_PBA8_GIC_START + 31)	/* Touchscreen keypad */
+
+/* ... */
+#define IRQ_PBA8_PCI0		(IRQ_PBA8_GIC_START + 50)
+#define IRQ_PBA8_PCI1		(IRQ_PBA8_GIC_START + 51)
+#define IRQ_PBA8_PCI2		(IRQ_PBA8_GIC_START + 52)
+#define IRQ_PBA8_PCI3		(IRQ_PBA8_GIC_START + 53)
+
+#define IRQ_PBA8_SMC		-1
+#define IRQ_PBA8_SCTL		-1
+
+#define NR_GIC_PBA8		1
+
+/*
+ * Only define NR_IRQS if less than NR_IRQS_PBA8
+ */
+#define NR_IRQS_PBA8		(IRQ_PBA8_GIC_START + 64)
+
+#if defined(CONFIG_MACH_REALVIEW_PBA8)
+
+#if !defined(NR_IRQS) || (NR_IRQS < NR_IRQS_PBA8)
+#undef NR_IRQS
+#define NR_IRQS			NR_IRQS_PBA8
+#endif
+
+#if !defined(MAX_GIC_NR) || (MAX_GIC_NR < NR_GIC_PBA8)
+#undef MAX_GIC_NR
+#define MAX_GIC_NR		NR_GIC_PBA8
+#endif
+
+#endif	/* CONFIG_MACH_REALVIEW_PBA8 */
+
+#endif	/* __ASM_ARCH_BOARD_PBA8_H */
diff --git a/arch/arm/mach-realview/include/mach/clkdev.h b/arch/arm/mach-realview/include/mach/clkdev.h
new file mode 100644
index 000000000000..04b37a89801c
--- /dev/null
+++ b/arch/arm/mach-realview/include/mach/clkdev.h
@@ -0,0 +1,7 @@
+#ifndef __ASM_MACH_CLKDEV_H
+#define __ASM_MACH_CLKDEV_H
+
+#define __clk_get(clk) ({ 1; })
+#define __clk_put(clk) do { } while (0)
+
+#endif
diff --git a/arch/arm/mach-realview/include/mach/debug-macro.S b/arch/arm/mach-realview/include/mach/debug-macro.S
index 7196bcadff0c..92dbcb9e1792 100644
--- a/arch/arm/mach-realview/include/mach/debug-macro.S
+++ b/arch/arm/mach-realview/include/mach/debug-macro.S
@@ -8,15 +8,36 @@
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
- *
-*/
+ */
+
+#if defined(CONFIG_MACH_REALVIEW_EB) || \
+    defined(CONFIG_MACH_REALVIEW_PB11MP) || \
+    defined(CONFIG_MACH_REALVIEW_PBA8)
+#ifndef DEBUG_LL_UART_OFFSET
+#define DEBUG_LL_UART_OFFSET	0x00009000
+#elif DEBUG_LL_UART_OFFSET != 0x00009000
+#warning "DEBUG_LL_UART_OFFSET already defined to a different value"
+#endif
+#endif
+
+#ifdef CONFIG_MACH_REALVIEW_PB1176
+#ifndef DEBUG_LL_UART_OFFSET
+#define DEBUG_LL_UART_OFFSET	0x0010c000
+#elif DEBUG_LL_UART_OFFSET != 0x0010c000
+#warning "DEBUG_LL_UART_OFFSET already defined to a different value"
+#endif
+#endif
+
+#ifndef DEBUG_LL_UART_OFFSET
+#error "Unknown RealView platform"
+#endif
 
 		.macro	addruart,rx
 		mrc	p15, 0, \rx, c1, c0
 		tst	\rx, #1			@ MMU enabled?
 		moveq	\rx,      #0x10000000
-		movne	\rx,      #0xf0000000	@ virtual base
-		orr	\rx, \rx, #0x00009000
+		movne	\rx,      #0xfb000000	@ virtual base
+		orr	\rx, \rx, #DEBUG_LL_UART_OFFSET
 		.endm
 
 #include <asm/hardware/debug-pl01x.S>
diff --git a/arch/arm/mach-realview/include/mach/dma.h b/arch/arm/mach-realview/include/mach/dma.h
deleted file mode 100644
index f1a5a1a10952..000000000000
--- a/arch/arm/mach-realview/include/mach/dma.h
+++ /dev/null
@@ -1,20 +0,0 @@
-/*
- *  arch/arm/mach-realview/include/mach/dma.h
- *
- *  Copyright (C) 2003 ARM Limited.
- *  Copyright (C) 1997,1998 Russell King
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
- */
diff --git a/arch/arm/mach-realview/include/mach/hardware.h b/arch/arm/mach-realview/include/mach/hardware.h
index 79a93b3dfca9..b42c14f89acb 100644
--- a/arch/arm/mach-realview/include/mach/hardware.h
+++ b/arch/arm/mach-realview/include/mach/hardware.h
@@ -25,7 +25,14 @@
 #include <asm/sizes.h>
 
 /* macro to get at IO space when running virtually */
-#define IO_ADDRESS(x)		(((x) & 0x0fffffff) + 0xf0000000)
+/*
+ * Statically mapped addresses:
+ *
+ * 10xx xxxx -> fbxx xxxx
+ * 1exx xxxx -> fdxx xxxx
+ * 1fxx xxxx -> fexx xxxx
+ */
+#define IO_ADDRESS(x)		(((x) & 0x03ffffff) + 0xfb000000)
 #define __io_address(n)		__io(IO_ADDRESS(n))
 
 #endif
diff --git a/arch/arm/mach-realview/include/mach/io.h b/arch/arm/mach-realview/include/mach/io.h
index aa069424d310..f05bcdf605d8 100644
--- a/arch/arm/mach-realview/include/mach/io.h
+++ b/arch/arm/mach-realview/include/mach/io.h
@@ -22,12 +22,7 @@
 
 #define IO_SPACE_LIMIT 0xffffffff
 
-static inline void __iomem *__io(unsigned long addr)
-{
-	return (void __iomem *)addr;
-}
-
-#define __io(a)			__io(a)
-#define __mem_pci(a)		(a)
+#define __io(a)		__typesafe_io(a)
+#define __mem_pci(a)	(a)
 
 #endif
diff --git a/arch/arm/mach-realview/include/mach/irqs.h b/arch/arm/mach-realview/include/mach/irqs.h
index 02a918529db3..fe5cb987aa21 100644
--- a/arch/arm/mach-realview/include/mach/irqs.h
+++ b/arch/arm/mach-realview/include/mach/irqs.h
@@ -25,6 +25,7 @@
 #include <mach/board-eb.h>
 #include <mach/board-pb11mp.h>
 #include <mach/board-pb1176.h>
+#include <mach/board-pba8.h>
 
 #define IRQ_LOCALTIMER		29
 #define IRQ_LOCALWDOG		30
diff --git a/arch/arm/mach-realview/include/mach/memory.h b/arch/arm/mach-realview/include/mach/memory.h
index 0e673483a141..293c30025e7e 100644
--- a/arch/arm/mach-realview/include/mach/memory.h
+++ b/arch/arm/mach-realview/include/mach/memory.h
@@ -23,16 +23,10 @@
 /*
  * Physical DRAM offset.
  */
+#ifdef CONFIG_REALVIEW_HIGH_PHYS_OFFSET
+#define PHYS_OFFSET		UL(0x70000000)
+#else
 #define PHYS_OFFSET		UL(0x00000000)
-
-/*
- * Virtual view <-> DMA view memory address translations
- * virt_to_bus: Used to translate the virtual address to an
- *              address suitable to be passed to set_dma_addr
- * bus_to_virt: Used to convert an address for DMA operations
- *              to an address that the kernel can use.
- */
-#define __virt_to_bus(x)	((x) - PAGE_OFFSET)
-#define __bus_to_virt(x)	((x) + PAGE_OFFSET)
+#endif
 
 #endif
diff --git a/arch/arm/mach-realview/include/mach/uncompress.h b/arch/arm/mach-realview/include/mach/uncompress.h
index 79f50f218e77..415d634d52ab 100644
--- a/arch/arm/mach-realview/include/mach/uncompress.h
+++ b/arch/arm/mach-realview/include/mach/uncompress.h
@@ -23,6 +23,7 @@
 #include <mach/board-eb.h>
 #include <mach/board-pb11mp.h>
 #include <mach/board-pb1176.h>
+#include <mach/board-pba8.h>
 
 #define AMBA_UART_DR(base)	(*(volatile unsigned char *)((base) + 0x00))
 #define AMBA_UART_LCRH(base)	(*(volatile unsigned char *)((base) + 0x2c))
@@ -40,6 +41,8 @@ static inline unsigned long get_uart_base(void)
 		return REALVIEW_PB11MP_UART0_BASE;
 	else if (machine_is_realview_pb1176())
 		return REALVIEW_PB1176_UART0_BASE;
+	else if (machine_is_realview_pba8())
+		return REALVIEW_PBA8_UART0_BASE;
 	else
 		return 0;
 }
diff --git a/arch/arm/mach-realview/include/mach/vmalloc.h b/arch/arm/mach-realview/include/mach/vmalloc.h
index 48cbcc873db2..fe0de1b507ac 100644
--- a/arch/arm/mach-realview/include/mach/vmalloc.h
+++ b/arch/arm/mach-realview/include/mach/vmalloc.h
@@ -18,4 +18,4 @@
  * along with this program; if not, write to the Free Software
  * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
  */
-#define VMALLOC_END		(PAGE_OFFSET + 0x18000000)
+#define VMALLOC_END		0xf8000000
diff --git a/arch/arm/mach-realview/localtimer.c b/arch/arm/mach-realview/localtimer.c
index 44d178cd5733..9019ef2e5611 100644
--- a/arch/arm/mach-realview/localtimer.c
+++ b/arch/arm/mach-realview/localtimer.c
@@ -38,18 +38,14 @@ void local_timer_interrupt(void)
 
 #ifdef CONFIG_LOCAL_TIMERS
 
-#define TWD_BASE(cpu)	(twd_base_addr + (cpu) * twd_size)
-
 /* set up by the platform code */
-void __iomem *twd_base_addr;
-unsigned int twd_size;
+void __iomem *twd_base;
 
 static unsigned long mpcore_timer_rate;
 
 static void local_timer_set_mode(enum clock_event_mode mode,
 				 struct clock_event_device *clk)
 {
-	void __iomem *base = TWD_BASE(smp_processor_id());
 	unsigned long ctrl;
 
 	switch(mode) {
@@ -68,17 +64,16 @@ static void local_timer_set_mode(enum clock_event_mode mode,
 		ctrl = 0;
 	}
 
-	__raw_writel(ctrl, base + TWD_TIMER_CONTROL);
+	__raw_writel(ctrl, twd_base + TWD_TIMER_CONTROL);
 }
 
 static int local_timer_set_next_event(unsigned long evt,
 				      struct clock_event_device *unused)
 {
-	void __iomem *base = TWD_BASE(smp_processor_id());
-	unsigned long ctrl = __raw_readl(base + TWD_TIMER_CONTROL);
+	unsigned long ctrl = __raw_readl(twd_base + TWD_TIMER_CONTROL);
 
-	__raw_writel(evt, base + TWD_TIMER_COUNTER);
-	__raw_writel(ctrl | TWD_TIMER_CONTROL_ENABLE, base + TWD_TIMER_CONTROL);
+	__raw_writel(evt, twd_base + TWD_TIMER_COUNTER);
+	__raw_writel(ctrl | TWD_TIMER_CONTROL_ENABLE, twd_base + TWD_TIMER_CONTROL);
 
 	return 0;
 }
@@ -91,19 +86,16 @@ static int local_timer_set_next_event(unsigned long evt,
  */
 int local_timer_ack(void)
 {
-	void __iomem *base = TWD_BASE(smp_processor_id());
-
-	if (__raw_readl(base + TWD_TIMER_INTSTAT)) {
-		__raw_writel(1, base + TWD_TIMER_INTSTAT);
+	if (__raw_readl(twd_base + TWD_TIMER_INTSTAT)) {
+		__raw_writel(1, twd_base + TWD_TIMER_INTSTAT);
 		return 1;
 	}
 
 	return 0;
 }
 
-static void __cpuinit twd_calibrate_rate(unsigned int cpu)
+static void __cpuinit twd_calibrate_rate(void)
 {
-	void __iomem *base = TWD_BASE(cpu);
 	unsigned long load, count;
 	u64 waitjiffies;
 
@@ -124,15 +116,15 @@ static void __cpuinit twd_calibrate_rate(unsigned int cpu)
 		waitjiffies += 5;
 
 				 /* enable, no interrupt or reload */
-		__raw_writel(0x1, base + TWD_TIMER_CONTROL);
+		__raw_writel(0x1, twd_base + TWD_TIMER_CONTROL);
 
 				 /* maximum value */
-		__raw_writel(0xFFFFFFFFU, base + TWD_TIMER_COUNTER);
+		__raw_writel(0xFFFFFFFFU, twd_base + TWD_TIMER_COUNTER);
 
 		while (get_jiffies_64() < waitjiffies)
 			udelay(10);
 
-		count = __raw_readl(base + TWD_TIMER_COUNTER);
+		count = __raw_readl(twd_base + TWD_TIMER_COUNTER);
 
 		mpcore_timer_rate = (0xFFFFFFFFU - count) * (HZ / 5);
 
@@ -142,18 +134,19 @@ static void __cpuinit twd_calibrate_rate(unsigned int cpu)
 
 	load = mpcore_timer_rate / HZ;
 
-	__raw_writel(load, base + TWD_TIMER_LOAD);
+	__raw_writel(load, twd_base + TWD_TIMER_LOAD);
 }
 
 /*
  * Setup the local clock events for a CPU.
  */
-void __cpuinit local_timer_setup(unsigned int cpu)
+void __cpuinit local_timer_setup(void)
 {
+	unsigned int cpu = smp_processor_id();
 	struct clock_event_device *clk = &per_cpu(local_clockevent, cpu);
 	unsigned long flags;
 
-	twd_calibrate_rate(cpu);
+	twd_calibrate_rate();
 
 	clk->name		= "local_timer";
 	clk->features		= CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT;
@@ -178,9 +171,9 @@ void __cpuinit local_timer_setup(unsigned int cpu)
 /*
  * take a local timer down
  */
-void __cpuexit local_timer_stop(unsigned int cpu)
+void __cpuexit local_timer_stop(void)
 {
-	__raw_writel(0, TWD_BASE(cpu) + TWD_TIMER_CONTROL);
+	__raw_writel(0, twd_base + TWD_TIMER_CONTROL);
 }
 
 #else	/* CONFIG_LOCAL_TIMERS */
@@ -190,8 +183,9 @@ static void dummy_timer_set_mode(enum clock_event_mode mode,
 {
 }
 
-void __cpuinit local_timer_setup(unsigned int cpu)
+void __cpuinit local_timer_setup(void)
 {
+	unsigned int cpu = smp_processor_id();
 	struct clock_event_device *clk = &per_cpu(local_clockevent, cpu);
 
 	clk->name		= "dummy_timer";
diff --git a/arch/arm/mach-realview/platsmp.c b/arch/arm/mach-realview/platsmp.c
index e102aeb0f76e..8fce85f33033 100644
--- a/arch/arm/mach-realview/platsmp.c
+++ b/arch/arm/mach-realview/platsmp.c
@@ -23,6 +23,8 @@
 #include <mach/board-pb11mp.h>
 #include <mach/scu.h>
 
+#include "core.h"
+
 extern void realview_secondary_startup(void);
 
 /*
@@ -31,15 +33,20 @@ extern void realview_secondary_startup(void);
  */
 volatile int __cpuinitdata pen_release = -1;
 
+static void __iomem *scu_base_addr(void)
+{
+	if (machine_is_realview_eb_mp())
+		return __io_address(REALVIEW_EB11MP_SCU_BASE);
+	else if (machine_is_realview_pb11mp())
+		return __io_address(REALVIEW_TC11MP_SCU_BASE);
+	else
+		return (void __iomem *)0;
+}
+
 static unsigned int __init get_core_count(void)
 {
 	unsigned int ncores;
-	void __iomem *scu_base = 0;
-
-	if (machine_is_realview_eb() && core_tile_eb11mp())
-		scu_base = __io_address(REALVIEW_EB11MP_SCU_BASE);
-	else if (machine_is_realview_pb11mp())
-		scu_base = __io_address(REALVIEW_TC11MP_SCU_BASE);
+	void __iomem *scu_base = scu_base_addr();
 
 	if (scu_base) {
 		ncores = __raw_readl(scu_base + SCU_CONFIG);
@@ -56,14 +63,7 @@ static unsigned int __init get_core_count(void)
 static void scu_enable(void)
 {
 	u32 scu_ctrl;
-	void __iomem *scu_base;
-
-	if (machine_is_realview_eb() && core_tile_eb11mp())
-		scu_base = __io_address(REALVIEW_EB11MP_SCU_BASE);
-	else if (machine_is_realview_pb11mp())
-		scu_base = __io_address(REALVIEW_TC11MP_SCU_BASE);
-	else
-		BUG();
+	void __iomem *scu_base = scu_base_addr();
 
 	scu_ctrl = __raw_readl(scu_base + SCU_CTRL);
 	scu_ctrl |= 1;
@@ -88,10 +88,7 @@ void __cpuinit platform_secondary_init(unsigned int cpu)
 	 * core (e.g. timer irq), then they will not have been enabled
 	 * for us: do so
 	 */
-	if (machine_is_realview_eb() && core_tile_eb11mp())
-		gic_cpu_init(0, __io_address(REALVIEW_EB11MP_GIC_CPU_BASE));
-	else if (machine_is_realview_pb11mp())
-		gic_cpu_init(0, __io_address(REALVIEW_TC11MP_GIC_CPU_BASE));
+	gic_cpu_init(0, gic_cpu_base_addr);
 
 	/*
 	 * let the primary processor know we're out of the
@@ -232,9 +229,7 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
 	 * dummy (!CONFIG_LOCAL_TIMERS), it was already registers in
 	 * realview_timer_init
 	 */
-	if ((machine_is_realview_eb() && core_tile_eb11mp()) ||
-	    machine_is_realview_pb11mp())
-		local_timer_setup(cpu);
+	local_timer_setup();
 #endif
 
 	/*
diff --git a/arch/arm/mach-realview/realview_eb.c b/arch/arm/mach-realview/realview_eb.c
index eb829eb1ebe2..bed39ed97613 100644
--- a/arch/arm/mach-realview/realview_eb.c
+++ b/arch/arm/mach-realview/realview_eb.c
@@ -108,7 +108,7 @@ static struct map_desc realview_eb11mp_io_desc[] __initdata = {
 static void __init realview_eb_map_io(void)
 {
 	iotable_init(realview_eb_io_desc, ARRAY_SIZE(realview_eb_io_desc));
-	if (core_tile_eb11mp())
+	if (core_tile_eb11mp() || core_tile_a9mp())
 		iotable_init(realview_eb11mp_io_desc, ARRAY_SIZE(realview_eb11mp_io_desc));
 }
 
@@ -242,12 +242,6 @@ static struct resource realview_eb_eth_resources[] = {
 	},
 };
 
-static struct platform_device realview_eb_eth_device = {
-	.id		= 0,
-	.num_resources	= ARRAY_SIZE(realview_eb_eth_resources),
-	.resource	= realview_eb_eth_resources,
-};
-
 /*
  * Detect and register the correct Ethernet device. RealView/EB rev D
  * platforms use the newer SMSC LAN9118 Ethernet chip
@@ -255,26 +249,24 @@ static struct platform_device realview_eb_eth_device = {
 static int eth_device_register(void)
 {
 	void __iomem *eth_addr = ioremap(REALVIEW_EB_ETH_BASE, SZ_4K);
+	const char *name = NULL;
 	u32 idrev;
 
 	if (!eth_addr)
 		return -ENOMEM;
 
 	idrev = readl(eth_addr + 0x50);
-	if ((idrev & 0xFFFF0000) == 0x01180000)
-		/* SMSC LAN9118 chip present */
-		realview_eb_eth_device.name = "smc911x";
-	else
-		/* SMSC 91C111 chip present */
-		realview_eb_eth_device.name = "smc91x";
+	if ((idrev & 0xFFFF0000) != 0x01180000)
+		/* SMSC LAN9118 not present, use LAN91C111 instead */
+		name = "smc91x";
 
 	iounmap(eth_addr);
-	return platform_device_register(&realview_eb_eth_device);
+	return realview_eth_register(name, realview_eb_eth_resources);
 }
 
 static void __init gic_init_irq(void)
 {
-	if (core_tile_eb11mp()) {
+	if (core_tile_eb11mp() || core_tile_a9mp()) {
 		unsigned int pldctrl;
 
 		/* new irq mode */
@@ -342,10 +334,9 @@ static void __init realview_eb_timer_init(void)
 	timer2_va_base = __io_address(REALVIEW_EB_TIMER2_3_BASE);
 	timer3_va_base = __io_address(REALVIEW_EB_TIMER2_3_BASE) + 0x20;
 
-	if (core_tile_eb11mp()) {
+	if (core_tile_eb11mp() || core_tile_a9mp()) {
 #ifdef CONFIG_LOCAL_TIMERS
-		twd_base_addr = __io_address(REALVIEW_EB11MP_TWD_BASE);
-		twd_size = REALVIEW_EB11MP_TWD_SIZE;
+		twd_base = __io_address(REALVIEW_EB11MP_TWD_BASE);
 #endif
 		timer_irq = IRQ_EB11MP_TIMER0_1;
 	} else
@@ -362,7 +353,7 @@ static void __init realview_eb_init(void)
 {
 	int i;
 
-	if (core_tile_eb11mp()) {
+	if (core_tile_eb11mp() || core_tile_a9mp()) {
 		realview_eb11mp_fixup();
 
 #ifdef CONFIG_CACHE_L2X0
@@ -372,8 +363,6 @@ static void __init realview_eb_init(void)
 #endif
 	}
 
-	clk_register(&realview_clcd_clk);
-
 	realview_flash_register(&realview_eb_flash_resource, 1);
 	platform_device_register(&realview_i2c_device);
 	eth_device_register();
@@ -392,7 +381,7 @@ MACHINE_START(REALVIEW_EB, "ARM-RealView EB")
 	/* Maintainer: ARM Ltd/Deep Blue Solutions Ltd */
 	.phys_io	= REALVIEW_EB_UART0_BASE,
 	.io_pg_offst	= (IO_ADDRESS(REALVIEW_EB_UART0_BASE) >> 18) & 0xfffc,
-	.boot_params	= 0x00000100,
+	.boot_params	= PHYS_OFFSET + 0x00000100,
 	.map_io		= realview_eb_map_io,
 	.init_irq	= gic_init_irq,
 	.timer		= &realview_eb_timer,
diff --git a/arch/arm/mach-realview/realview_pb1176.c b/arch/arm/mach-realview/realview_pb1176.c
index cccdb3eb90fe..8f0683c22140 100644
--- a/arch/arm/mach-realview/realview_pb1176.c
+++ b/arch/arm/mach-realview/realview_pb1176.c
@@ -222,13 +222,6 @@ static struct resource realview_pb1176_smsc911x_resources[] = {
 	},
 };
 
-static struct platform_device realview_pb1176_smsc911x_device = {
-	.name		= "smc911x",
-	.id		= 0,
-	.num_resources	= ARRAY_SIZE(realview_pb1176_smsc911x_resources),
-	.resource	= realview_pb1176_smsc911x_resources,
-};
-
 static void __init gic_init_irq(void)
 {
 	/* ARM1176 DevChip GIC, primary */
@@ -265,10 +258,8 @@ static void __init realview_pb1176_init(void)
 	l2x0_init(__io_address(REALVIEW_PB1176_L220_BASE), 0x00730000, 0xfe000fff);
 #endif
 
-	clk_register(&realview_clcd_clk);
-
 	realview_flash_register(&realview_pb1176_flash_resource, 1);
-	platform_device_register(&realview_pb1176_smsc911x_device);
+	realview_eth_register(NULL, realview_pb1176_smsc911x_resources);
 
 	for (i = 0; i < ARRAY_SIZE(amba_devs); i++) {
 		struct amba_device *d = amba_devs[i];
@@ -284,7 +275,7 @@ MACHINE_START(REALVIEW_PB1176, "ARM-RealView PB1176")
 	/* Maintainer: ARM Ltd/Deep Blue Solutions Ltd */
 	.phys_io	= REALVIEW_PB1176_UART0_BASE,
 	.io_pg_offst	= (IO_ADDRESS(REALVIEW_PB1176_UART0_BASE) >> 18) & 0xfffc,
-	.boot_params	= 0x00000100,
+	.boot_params	= PHYS_OFFSET + 0x00000100,
 	.map_io		= realview_pb1176_map_io,
 	.init_irq	= gic_init_irq,
 	.timer		= &realview_pb1176_timer,
diff --git a/arch/arm/mach-realview/realview_pb11mp.c b/arch/arm/mach-realview/realview_pb11mp.c
index 8b863148ec18..3ebdb2dadd6f 100644
--- a/arch/arm/mach-realview/realview_pb11mp.c
+++ b/arch/arm/mach-realview/realview_pb11mp.c
@@ -230,13 +230,6 @@ static struct resource realview_pb11mp_smsc911x_resources[] = {
 	},
 };
 
-static struct platform_device realview_pb11mp_smsc911x_device = {
-	.name		= "smc911x",
-	.id		= 0,
-	.num_resources	= ARRAY_SIZE(realview_pb11mp_smsc911x_resources),
-	.resource	= realview_pb11mp_smsc911x_resources,
-};
-
 struct resource realview_pb11mp_cf_resources[] = {
 	[0] = {
 		.start		= REALVIEW_PB11MP_CF_BASE,
@@ -292,8 +285,7 @@ static void __init realview_pb11mp_timer_init(void)
 	timer3_va_base = __io_address(REALVIEW_PB11MP_TIMER2_3_BASE) + 0x20;
 
 #ifdef CONFIG_LOCAL_TIMERS
-	twd_base_addr = __io_address(REALVIEW_TC11MP_TWD_BASE);
-	twd_size = REALVIEW_TC11MP_TWD_SIZE;
+	twd_base = __io_address(REALVIEW_TC11MP_TWD_BASE);
 #endif
 	realview_timer_init(IRQ_TC11MP_TIMER0_1);
 }
@@ -312,11 +304,9 @@ static void __init realview_pb11mp_init(void)
 	l2x0_init(__io_address(REALVIEW_TC11MP_L220_BASE), 0x00790000, 0xfe000fff);
 #endif
 
-	clk_register(&realview_clcd_clk);
-
 	realview_flash_register(realview_pb11mp_flash_resource,
 				ARRAY_SIZE(realview_pb11mp_flash_resource));
-	platform_device_register(&realview_pb11mp_smsc911x_device);
+	realview_eth_register(NULL, realview_pb11mp_smsc911x_resources);
 	platform_device_register(&realview_i2c_device);
 	platform_device_register(&realview_pb11mp_cf_device);
 
@@ -334,7 +324,7 @@ MACHINE_START(REALVIEW_PB11MP, "ARM-RealView PB11MPCore")
 	/* Maintainer: ARM Ltd/Deep Blue Solutions Ltd */
 	.phys_io	= REALVIEW_PB11MP_UART0_BASE,
 	.io_pg_offst	= (IO_ADDRESS(REALVIEW_PB11MP_UART0_BASE) >> 18) & 0xfffc,
-	.boot_params	= 0x00000100,
+	.boot_params	= PHYS_OFFSET + 0x00000100,
 	.map_io		= realview_pb11mp_map_io,
 	.init_irq	= gic_init_irq,
 	.timer		= &realview_pb11mp_timer,
diff --git a/arch/arm/mach-realview/realview_pba8.c b/arch/arm/mach-realview/realview_pba8.c
new file mode 100644
index 000000000000..34c94435d2d8
--- /dev/null
+++ b/arch/arm/mach-realview/realview_pba8.c
@@ -0,0 +1,300 @@
+/*
+ *  linux/arch/arm/mach-realview/realview_pba8.c
+ *
+ *  Copyright (C) 2008 ARM Limited
+ *  Copyright (C) 2000 Deep Blue Solutions Ltd
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ */
+
+#include <linux/init.h>
+#include <linux/platform_device.h>
+#include <linux/sysdev.h>
+#include <linux/amba/bus.h>
+#include <linux/io.h>
+
+#include <asm/irq.h>
+#include <asm/leds.h>
+#include <asm/mach-types.h>
+#include <asm/hardware/gic.h>
+#include <asm/hardware/icst307.h>
+
+#include <asm/mach/arch.h>
+#include <asm/mach/map.h>
+#include <asm/mach/mmc.h>
+#include <asm/mach/time.h>
+
+#include <mach/hardware.h>
+#include <mach/board-pba8.h>
+#include <mach/irqs.h>
+
+#include "core.h"
+#include "clock.h"
+
+static struct map_desc realview_pba8_io_desc[] __initdata = {
+	{
+		.virtual	= IO_ADDRESS(REALVIEW_SYS_BASE),
+		.pfn		= __phys_to_pfn(REALVIEW_SYS_BASE),
+		.length		= SZ_4K,
+		.type		= MT_DEVICE,
+	}, {
+		.virtual	= IO_ADDRESS(REALVIEW_PBA8_GIC_CPU_BASE),
+		.pfn		= __phys_to_pfn(REALVIEW_PBA8_GIC_CPU_BASE),
+		.length		= SZ_4K,
+		.type		= MT_DEVICE,
+	}, {
+		.virtual	= IO_ADDRESS(REALVIEW_PBA8_GIC_DIST_BASE),
+		.pfn		= __phys_to_pfn(REALVIEW_PBA8_GIC_DIST_BASE),
+		.length		= SZ_4K,
+		.type		= MT_DEVICE,
+	}, {
+		.virtual	= IO_ADDRESS(REALVIEW_SCTL_BASE),
+		.pfn		= __phys_to_pfn(REALVIEW_SCTL_BASE),
+		.length		= SZ_4K,
+		.type		= MT_DEVICE,
+	}, {
+		.virtual	= IO_ADDRESS(REALVIEW_PBA8_TIMER0_1_BASE),
+		.pfn		= __phys_to_pfn(REALVIEW_PBA8_TIMER0_1_BASE),
+		.length		= SZ_4K,
+		.type		= MT_DEVICE,
+	}, {
+		.virtual	= IO_ADDRESS(REALVIEW_PBA8_TIMER2_3_BASE),
+		.pfn		= __phys_to_pfn(REALVIEW_PBA8_TIMER2_3_BASE),
+		.length		= SZ_4K,
+		.type		= MT_DEVICE,
+	},
+#ifdef CONFIG_PCI
+	{
+		.virtual	= PCIX_UNIT_BASE,
+		.pfn		= __phys_to_pfn(REALVIEW_PBA8_PCI_BASE),
+		.length		= REALVIEW_PBA8_PCI_BASE_SIZE,
+		.type		= MT_DEVICE
+	},
+#endif
+#ifdef CONFIG_DEBUG_LL
+	{
+		.virtual	= IO_ADDRESS(REALVIEW_PBA8_UART0_BASE),
+		.pfn		= __phys_to_pfn(REALVIEW_PBA8_UART0_BASE),
+		.length		= SZ_4K,
+		.type		= MT_DEVICE,
+	},
+#endif
+};
+
+static void __init realview_pba8_map_io(void)
+{
+	iotable_init(realview_pba8_io_desc, ARRAY_SIZE(realview_pba8_io_desc));
+}
+
+/*
+ * RealView PBA8Core AMBA devices
+ */
+
+#define GPIO2_IRQ		{ IRQ_PBA8_GPIO2, NO_IRQ }
+#define GPIO2_DMA		{ 0, 0 }
+#define GPIO3_IRQ		{ IRQ_PBA8_GPIO3, NO_IRQ }
+#define GPIO3_DMA		{ 0, 0 }
+#define AACI_IRQ		{ IRQ_PBA8_AACI, NO_IRQ }
+#define AACI_DMA		{ 0x80, 0x81 }
+#define MMCI0_IRQ		{ IRQ_PBA8_MMCI0A, IRQ_PBA8_MMCI0B }
+#define MMCI0_DMA		{ 0x84, 0 }
+#define KMI0_IRQ		{ IRQ_PBA8_KMI0, NO_IRQ }
+#define KMI0_DMA		{ 0, 0 }
+#define KMI1_IRQ		{ IRQ_PBA8_KMI1, NO_IRQ }
+#define KMI1_DMA		{ 0, 0 }
+#define PBA8_SMC_IRQ		{ NO_IRQ, NO_IRQ }
+#define PBA8_SMC_DMA		{ 0, 0 }
+#define MPMC_IRQ		{ NO_IRQ, NO_IRQ }
+#define MPMC_DMA		{ 0, 0 }
+#define PBA8_CLCD_IRQ		{ IRQ_PBA8_CLCD, NO_IRQ }
+#define PBA8_CLCD_DMA		{ 0, 0 }
+#define DMAC_IRQ		{ IRQ_PBA8_DMAC, NO_IRQ }
+#define DMAC_DMA		{ 0, 0 }
+#define SCTL_IRQ		{ NO_IRQ, NO_IRQ }
+#define SCTL_DMA		{ 0, 0 }
+#define PBA8_WATCHDOG_IRQ	{ IRQ_PBA8_WATCHDOG, NO_IRQ }
+#define PBA8_WATCHDOG_DMA	{ 0, 0 }
+#define PBA8_GPIO0_IRQ		{ IRQ_PBA8_GPIO0, NO_IRQ }
+#define PBA8_GPIO0_DMA		{ 0, 0 }
+#define GPIO1_IRQ		{ IRQ_PBA8_GPIO1, NO_IRQ }
+#define GPIO1_DMA		{ 0, 0 }
+#define PBA8_RTC_IRQ		{ IRQ_PBA8_RTC, NO_IRQ }
+#define PBA8_RTC_DMA		{ 0, 0 }
+#define SCI_IRQ			{ IRQ_PBA8_SCI, NO_IRQ }
+#define SCI_DMA			{ 7, 6 }
+#define PBA8_UART0_IRQ		{ IRQ_PBA8_UART0, NO_IRQ }
+#define PBA8_UART0_DMA		{ 15, 14 }
+#define PBA8_UART1_IRQ		{ IRQ_PBA8_UART1, NO_IRQ }
+#define PBA8_UART1_DMA		{ 13, 12 }
+#define PBA8_UART2_IRQ		{ IRQ_PBA8_UART2, NO_IRQ }
+#define PBA8_UART2_DMA		{ 11, 10 }
+#define PBA8_UART3_IRQ		{ IRQ_PBA8_UART3, NO_IRQ }
+#define PBA8_UART3_DMA		{ 0x86, 0x87 }
+#define PBA8_SSP_IRQ		{ IRQ_PBA8_SSP, NO_IRQ }
+#define PBA8_SSP_DMA		{ 9, 8 }
+
+/* FPGA Primecells */
+AMBA_DEVICE(aaci,	"fpga:04",	AACI,		NULL);
+AMBA_DEVICE(mmc0,	"fpga:05",	MMCI0,		&realview_mmc0_plat_data);
+AMBA_DEVICE(kmi0,	"fpga:06",	KMI0,		NULL);
+AMBA_DEVICE(kmi1,	"fpga:07",	KMI1,		NULL);
+AMBA_DEVICE(uart3,	"fpga:09",	PBA8_UART3,	NULL);
+
+/* DevChip Primecells */
+AMBA_DEVICE(smc,	"dev:00",	PBA8_SMC,	NULL);
+AMBA_DEVICE(sctl,	"dev:e0",	SCTL,		NULL);
+AMBA_DEVICE(wdog,	"dev:e1",	PBA8_WATCHDOG, NULL);
+AMBA_DEVICE(gpio0,	"dev:e4",	PBA8_GPIO0,	NULL);
+AMBA_DEVICE(gpio1,	"dev:e5",	GPIO1,		NULL);
+AMBA_DEVICE(gpio2,	"dev:e6",	GPIO2,		NULL);
+AMBA_DEVICE(rtc,	"dev:e8",	PBA8_RTC,	NULL);
+AMBA_DEVICE(sci0,	"dev:f0",	SCI,		NULL);
+AMBA_DEVICE(uart0,	"dev:f1",	PBA8_UART0,	NULL);
+AMBA_DEVICE(uart1,	"dev:f2",	PBA8_UART1,	NULL);
+AMBA_DEVICE(uart2,	"dev:f3",	PBA8_UART2,	NULL);
+AMBA_DEVICE(ssp0,	"dev:f4",	PBA8_SSP,	NULL);
+
+/* Primecells on the NEC ISSP chip */
+AMBA_DEVICE(clcd,	"issp:20",	PBA8_CLCD,	&clcd_plat_data);
+AMBA_DEVICE(dmac,	"issp:30",	DMAC,		NULL);
+
+static struct amba_device *amba_devs[] __initdata = {
+	&dmac_device,
+	&uart0_device,
+	&uart1_device,
+	&uart2_device,
+	&uart3_device,
+	&smc_device,
+	&clcd_device,
+	&sctl_device,
+	&wdog_device,
+	&gpio0_device,
+	&gpio1_device,
+	&gpio2_device,
+	&rtc_device,
+	&sci0_device,
+	&ssp0_device,
+	&aaci_device,
+	&mmc0_device,
+	&kmi0_device,
+	&kmi1_device,
+};
+
+/*
+ * RealView PB-A8 platform devices
+ */
+static struct resource realview_pba8_flash_resource[] = {
+	[0] = {
+		.start		= REALVIEW_PBA8_FLASH0_BASE,
+		.end		= REALVIEW_PBA8_FLASH0_BASE + REALVIEW_PBA8_FLASH0_SIZE - 1,
+		.flags		= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start		= REALVIEW_PBA8_FLASH1_BASE,
+		.end		= REALVIEW_PBA8_FLASH1_BASE + REALVIEW_PBA8_FLASH1_SIZE - 1,
+		.flags		= IORESOURCE_MEM,
+	},
+};
+
+static struct resource realview_pba8_smsc911x_resources[] = {
+	[0] = {
+		.start		= REALVIEW_PBA8_ETH_BASE,
+		.end		= REALVIEW_PBA8_ETH_BASE + SZ_64K - 1,
+		.flags		= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start		= IRQ_PBA8_ETH,
+		.end		= IRQ_PBA8_ETH,
+		.flags		= IORESOURCE_IRQ,
+	},
+};
+
+struct resource realview_pba8_cf_resources[] = {
+	[0] = {
+		.start		= REALVIEW_PBA8_CF_BASE,
+		.end		= REALVIEW_PBA8_CF_BASE + SZ_4K - 1,
+		.flags		= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start		= REALVIEW_PBA8_CF_MEM_BASE,
+		.end		= REALVIEW_PBA8_CF_MEM_BASE + SZ_4K - 1,
+		.flags		= IORESOURCE_MEM,
+	},
+	[2] = {
+		.start		= -1,		/* FIXME: Find correct irq */
+		.end		= -1,
+		.flags		= IORESOURCE_IRQ,
+	},
+};
+
+struct platform_device realview_pba8_cf_device = {
+	.name		= "compactflash",
+	.id		= 0,
+	.num_resources	= ARRAY_SIZE(realview_pba8_cf_resources),
+	.resource	= realview_pba8_cf_resources,
+};
+
+static void __init gic_init_irq(void)
+{
+	/* ARM PB-A8 on-board GIC */
+	gic_cpu_base_addr = __io_address(REALVIEW_PBA8_GIC_CPU_BASE);
+	gic_dist_init(0, __io_address(REALVIEW_PBA8_GIC_DIST_BASE), IRQ_PBA8_GIC_START);
+	gic_cpu_init(0, __io_address(REALVIEW_PBA8_GIC_CPU_BASE));
+}
+
+static void __init realview_pba8_timer_init(void)
+{
+	timer0_va_base = __io_address(REALVIEW_PBA8_TIMER0_1_BASE);
+	timer1_va_base = __io_address(REALVIEW_PBA8_TIMER0_1_BASE) + 0x20;
+	timer2_va_base = __io_address(REALVIEW_PBA8_TIMER2_3_BASE);
+	timer3_va_base = __io_address(REALVIEW_PBA8_TIMER2_3_BASE) + 0x20;
+
+	realview_timer_init(IRQ_PBA8_TIMER0_1);
+}
+
+static struct sys_timer realview_pba8_timer = {
+	.init		= realview_pba8_timer_init,
+};
+
+static void __init realview_pba8_init(void)
+{
+	int i;
+
+	realview_flash_register(realview_pba8_flash_resource,
+				ARRAY_SIZE(realview_pba8_flash_resource));
+	realview_eth_register(NULL, realview_pba8_smsc911x_resources);
+	platform_device_register(&realview_i2c_device);
+	platform_device_register(&realview_pba8_cf_device);
+
+	for (i = 0; i < ARRAY_SIZE(amba_devs); i++) {
+		struct amba_device *d = amba_devs[i];
+		amba_device_register(d, &iomem_resource);
+	}
+
+#ifdef CONFIG_LEDS
+	leds_event = realview_leds_event;
+#endif
+}
+
+MACHINE_START(REALVIEW_PBA8, "ARM-RealView PB-A8")
+	/* Maintainer: ARM Ltd/Deep Blue Solutions Ltd */
+	.phys_io	= REALVIEW_PBA8_UART0_BASE,
+	.io_pg_offst	= (IO_ADDRESS(REALVIEW_PBA8_UART0_BASE) >> 18) & 0xfffc,
+	.boot_params	= PHYS_OFFSET + 0x00000100,
+	.map_io		= realview_pba8_map_io,
+	.init_irq	= gic_init_irq,
+	.timer		= &realview_pba8_timer,
+	.init_machine	= realview_pba8_init,
+MACHINE_END
diff --git a/arch/arm/mach-rpc/include/mach/io.h b/arch/arm/mach-rpc/include/mach/io.h
index 9f0553b7ec28..20da7f486e51 100644
--- a/arch/arm/mach-rpc/include/mach/io.h
+++ b/arch/arm/mach-rpc/include/mach/io.h
@@ -18,49 +18,6 @@
 #define IO_SPACE_LIMIT 0xffffffff
 
 /*
- * GCC is totally crap at loading/storing data.  We try to persuade it
- * to do the right thing by using these whereever possible instead of
- * the above.
- */
-#define __arch_base_getb(b,o)			\
- ({						\
-	unsigned int __v, __r = (b);		\
-	__asm__ __volatile__(			\
-		"ldrb	%0, [%1, %2]"		\
-		: "=r" (__v)			\
-		: "r" (__r), "Ir" (o));		\
-	__v;					\
- })
-
-#define __arch_base_getl(b,o)			\
- ({						\
-	unsigned int __v, __r = (b);		\
-	__asm__ __volatile__(			\
-		"ldr	%0, [%1, %2]"		\
-		: "=r" (__v)			\
-		: "r" (__r), "Ir" (o));		\
-	__v;					\
- })
-
-#define __arch_base_putb(v,b,o)			\
- ({						\
-	unsigned int __r = (b);			\
-	__asm__ __volatile__(			\
-		"strb	%0, [%1, %2]"		\
-		:				\
-		: "r" (v), "r" (__r), "Ir" (o));\
- })
-
-#define __arch_base_putl(v,b,o)			\
- ({						\
-	unsigned int __r = (b);			\
-	__asm__ __volatile__(			\
-		"str	%0, [%1, %2]"		\
-		:				\
-		: "r" (v), "r" (__r), "Ir" (o));\
- })
-
-/*
  * We use two different types of addressing - PC style addresses, and ARM
  * addresses.  PC style accesses the PC hardware with the normal PC IO
  * addresses, eg 0x3f8 for serial#1.  ARM addresses are 0x80000000+
@@ -232,15 +189,13 @@ DECLARE_IO(int,l,"")
 	result;									\
 })
 
-#define __ioaddrc(port)		__ioaddr(port)
-
 #define inb(p)	 	(__builtin_constant_p((p)) ? __inbc(p)    : __inb(p))
 #define inw(p)	 	(__builtin_constant_p((p)) ? __inwc(p)    : __inw(p))
 #define inl(p)	 	(__builtin_constant_p((p)) ? __inlc(p)    : __inl(p))
 #define outb(v,p)	(__builtin_constant_p((p)) ? __outbc(v,p) : __outb(v,p))
 #define outw(v,p)	(__builtin_constant_p((p)) ? __outwc(v,p) : __outw(v,p))
 #define outl(v,p)	(__builtin_constant_p((p)) ? __outlc(v,p) : __outl(v,p))
-#define __ioaddr(p)	(__builtin_constant_p((p)) ? __ioaddr(p)  : __ioaddrc(p))
+
 /* the following macro is deprecated */
 #define ioaddr(port)	((unsigned long)__ioaddr((port)))
 
diff --git a/arch/arm/mach-rpc/include/mach/irqs.h b/arch/arm/mach-rpc/include/mach/irqs.h
index 4ce6ca97f669..3d2037496e38 100644
--- a/arch/arm/mach-rpc/include/mach/irqs.h
+++ b/arch/arm/mach-rpc/include/mach/irqs.h
@@ -44,3 +44,4 @@
 
 #define IRQ_TIMER		IRQ_TIMER0
 
+#define NR_IRQS			128
diff --git a/arch/arm/mach-rpc/include/mach/dma.h b/arch/arm/mach-rpc/include/mach/isa-dma.h
index 360b56f8f29f..bad720548587 100644
--- a/arch/arm/mach-rpc/include/mach/dma.h
+++ b/arch/arm/mach-rpc/include/mach/isa-dma.h
@@ -1,5 +1,5 @@
 /*
- *  arch/arm/mach-rpc/include/mach/dma.h
+ *  arch/arm/mach-rpc/include/mach/isa-dma.h
  *
  *  Copyright (C) 1997 Russell King
  *
@@ -10,12 +10,6 @@
 #ifndef __ASM_ARCH_DMA_H
 #define __ASM_ARCH_DMA_H
 
-/*
- * This is the maximum DMA address that can be DMAd to.
- * There should not be more than (0xd0000000 - 0xc0000000)
- * bytes of RAM.
- */
-#define MAX_DMA_ADDRESS		0xd0000000
 #define MAX_DMA_CHANNELS	8
 
 #define DMA_0			0
diff --git a/arch/arm/mach-rpc/include/mach/memory.h b/arch/arm/mach-rpc/include/mach/memory.h
index 9bf7e43e2863..78191bf25192 100644
--- a/arch/arm/mach-rpc/include/mach/memory.h
+++ b/arch/arm/mach-rpc/include/mach/memory.h
@@ -24,13 +24,6 @@
 #define PHYS_OFFSET	UL(0x10000000)
 
 /*
- * These are exactly the same on the RiscPC as the
- * physical memory view.
- */
-#define __virt_to_bus(x) __virt_to_phys(x)
-#define __bus_to_virt(x) __phys_to_virt(x)
-
-/*
  * Cache flushing area - ROM
  */
 #define FLUSH_BASE_PHYS		0x00000000
diff --git a/arch/arm/mach-s3c2400/include/mach/memory.h b/arch/arm/mach-s3c2400/include/mach/memory.h
index 8f4878e4f591..cf5901ffd385 100644
--- a/arch/arm/mach-s3c2400/include/mach/memory.h
+++ b/arch/arm/mach-s3c2400/include/mach/memory.h
@@ -17,7 +17,4 @@
 
 #define PHYS_OFFSET	UL(0x0C000000)
 
-#define __virt_to_bus(x) __virt_to_phys(x)
-#define __bus_to_virt(x) __phys_to_virt(x)
-
 #endif
diff --git a/arch/arm/mach-s3c2410/Kconfig b/arch/arm/mach-s3c2410/Kconfig
index 99fdc736698c..7315569fbfd7 100644
--- a/arch/arm/mach-s3c2410/Kconfig
+++ b/arch/arm/mach-s3c2410/Kconfig
@@ -7,6 +7,7 @@
 config CPU_S3C2410
 	bool
 	depends on ARCH_S3C2410
+	select CPU_ARM920T
 	select S3C2410_CLOCK
 	select S3C2410_GPIO
 	select CPU_LLSERIAL_S3C2410
diff --git a/arch/arm/mach-s3c2410/dma.c b/arch/arm/mach-s3c2410/dma.c
index 7d914a470b6c..552b4c778fdc 100644
--- a/arch/arm/mach-s3c2410/dma.c
+++ b/arch/arm/mach-s3c2410/dma.c
@@ -17,7 +17,6 @@
 #include <linux/sysdev.h>
 #include <linux/serial_core.h>
 
-#include <asm/dma.h>
 #include <mach/dma.h>
 
 #include <plat/cpu.h>
@@ -25,12 +24,12 @@
 
 #include <plat/regs-serial.h>
 #include <mach/regs-gpio.h>
-#include <asm/plat-s3c/regs-ac97.h>
+#include <plat/regs-ac97.h>
 #include <mach/regs-mem.h>
 #include <mach/regs-lcd.h>
 #include <mach/regs-sdi.h>
 #include <asm/plat-s3c24xx/regs-iis.h>
-#include <asm/plat-s3c24xx/regs-spi.h>
+#include <plat/regs-spi.h>
 
 static struct s3c24xx_dma_map __initdata s3c2410_dma_mappings[] = {
 	[DMACH_XD0] = {
diff --git a/arch/arm/mach-s3c2410/include/mach/dma.h b/arch/arm/mach-s3c2410/include/mach/dma.h
index 891b53cd69b8..13358ce2128c 100644
--- a/arch/arm/mach-s3c2410/include/mach/dma.h
+++ b/arch/arm/mach-s3c2410/include/mach/dma.h
@@ -16,11 +16,6 @@
 #include <linux/sysdev.h>
 #include <mach/hardware.h>
 
-/*
- * This is the maximum DMA address(physical address) that can be DMAd to.
- *
- */
-#define MAX_DMA_ADDRESS		0x40000000
 #define MAX_DMA_TRANSFER_SIZE   0x100000 /* Data Unit is half word  */
 
 /* We use `virtual` dma channels to hide the fact we have only a limited
@@ -254,7 +249,7 @@ typedef unsigned long dma_device_t;
  * request a dma channel exclusivley
 */
 
-extern int s3c2410_dma_request(dmach_t channel,
+extern int s3c2410_dma_request(unsigned int channel,
 			       struct s3c2410_dma_client *, void *dev);
 
 
@@ -263,14 +258,14 @@ extern int s3c2410_dma_request(dmach_t channel,
  * change the state of the dma channel
 */
 
-extern int s3c2410_dma_ctrl(dmach_t channel, enum s3c2410_chan_op op);
+extern int s3c2410_dma_ctrl(unsigned int channel, enum s3c2410_chan_op op);
 
 /* s3c2410_dma_setflags
  *
  * set the channel's flags to a given state
 */
 
-extern int s3c2410_dma_setflags(dmach_t channel,
+extern int s3c2410_dma_setflags(unsigned int channel,
 				unsigned int flags);
 
 /* s3c2410_dma_free
@@ -278,7 +273,7 @@ extern int s3c2410_dma_setflags(dmach_t channel,
  * free the dma channel (will also abort any outstanding operations)
 */
 
-extern int s3c2410_dma_free(dmach_t channel, struct s3c2410_dma_client *);
+extern int s3c2410_dma_free(unsigned int channel, struct s3c2410_dma_client *);
 
 /* s3c2410_dma_enqueue
  *
@@ -287,7 +282,7 @@ extern int s3c2410_dma_free(dmach_t channel, struct s3c2410_dma_client *);
  * drained before the buffer is given to the DMA system.
 */
 
-extern int s3c2410_dma_enqueue(dmach_t channel, void *id,
+extern int s3c2410_dma_enqueue(unsigned int channel, void *id,
 			       dma_addr_t data, int size);
 
 /* s3c2410_dma_config
@@ -295,7 +290,7 @@ extern int s3c2410_dma_enqueue(dmach_t channel, void *id,
  * configure the dma channel
 */
 
-extern int s3c2410_dma_config(dmach_t channel, int xferunit, int dcon);
+extern int s3c2410_dma_config(unsigned int channel, int xferunit, int dcon);
 
 /* s3c2410_dma_devconfig
  *
@@ -310,11 +305,11 @@ extern int s3c2410_dma_devconfig(int channel, enum s3c2410_dmasrc source,
  * get the position that the dma transfer is currently at
 */
 
-extern int s3c2410_dma_getposition(dmach_t channel,
+extern int s3c2410_dma_getposition(unsigned int channel,
 				   dma_addr_t *src, dma_addr_t *dest);
 
-extern int s3c2410_dma_set_opfn(dmach_t, s3c2410_dma_opfn_t rtn);
-extern int s3c2410_dma_set_buffdone_fn(dmach_t, s3c2410_dma_cbfn_t rtn);
+extern int s3c2410_dma_set_opfn(unsigned int, s3c2410_dma_opfn_t rtn);
+extern int s3c2410_dma_set_buffdone_fn(unsigned int, s3c2410_dma_cbfn_t rtn);
 
 /* DMA Register definitions */
 
diff --git a/arch/arm/mach-s3c2410/include/mach/memory.h b/arch/arm/mach-s3c2410/include/mach/memory.h
index 93782628a786..6f1e5871ae4b 100644
--- a/arch/arm/mach-s3c2410/include/mach/memory.h
+++ b/arch/arm/mach-s3c2410/include/mach/memory.h
@@ -13,7 +13,4 @@
 
 #define PHYS_OFFSET	UL(0x30000000)
 
-#define __virt_to_bus(x) __virt_to_phys(x)
-#define __bus_to_virt(x) __phys_to_virt(x)
-
 #endif
diff --git a/arch/arm/mach-s3c2410/include/mach/system-reset.h b/arch/arm/mach-s3c2410/include/mach/system-reset.h
index 43535a0e7186..7613d0a384ba 100644
--- a/arch/arm/mach-s3c2410/include/mach/system-reset.h
+++ b/arch/arm/mach-s3c2410/include/mach/system-reset.h
@@ -13,7 +13,7 @@
 #include <mach/hardware.h>
 #include <linux/io.h>
 
-#include <asm/plat-s3c/regs-watchdog.h>
+#include <plat/regs-watchdog.h>
 #include <mach/regs-clock.h>
 
 #include <linux/clk.h>
diff --git a/arch/arm/mach-s3c2410/mach-bast.c b/arch/arm/mach-s3c2410/mach-bast.c
index 8db9c700e3c2..c04c24444e0d 100644
--- a/arch/arm/mach-s3c2410/mach-bast.c
+++ b/arch/arm/mach-s3c2410/mach-bast.c
@@ -44,8 +44,8 @@
 #include <mach/regs-mem.h>
 #include <mach/regs-lcd.h>
 
-#include <asm/plat-s3c/nand.h>
-#include <asm/plat-s3c/iic.h>
+#include <plat/nand.h>
+#include <plat/iic.h>
 #include <mach/fb.h>
 
 #include <linux/mtd/mtd.h>
diff --git a/arch/arm/mach-s3c2410/mach-h1940.c b/arch/arm/mach-s3c2410/mach-h1940.c
index 98716d0108e9..32d550fcff4d 100644
--- a/arch/arm/mach-s3c2410/mach-h1940.c
+++ b/arch/arm/mach-s3c2410/mach-h1940.c
@@ -38,7 +38,7 @@
 #include <mach/h1940.h>
 #include <mach/h1940-latch.h>
 #include <mach/fb.h>
-#include <asm/plat-s3c24xx/udc.h>
+#include <plat/udc.h>
 
 #include <plat/clock.h>
 #include <plat/devs.h>
diff --git a/arch/arm/mach-s3c2410/mach-n30.c b/arch/arm/mach-s3c2410/mach-n30.c
index 82505517846c..7a7c45d28fe7 100644
--- a/arch/arm/mach-s3c2410/mach-n30.c
+++ b/arch/arm/mach-s3c2410/mach-n30.c
@@ -40,14 +40,14 @@
 #include <asm/mach/irq.h>
 #include <asm/mach/map.h>
 
-#include <asm/plat-s3c/iic.h>
+#include <plat/iic.h>
 #include <plat/regs-serial.h>
 
 #include <plat/clock.h>
 #include <plat/cpu.h>
 #include <plat/devs.h>
 #include <plat/s3c2410.h>
-#include <asm/plat-s3c24xx/udc.h>
+#include <plat/udc.h>
 
 static struct map_desc n30_iodesc[] __initdata = {
 	/* nothing here yet */
diff --git a/arch/arm/mach-s3c2410/mach-qt2410.c b/arch/arm/mach-s3c2410/mach-qt2410.c
index 661807e14e8a..ef868472f6a4 100644
--- a/arch/arm/mach-s3c2410/mach-qt2410.c
+++ b/arch/arm/mach-s3c2410/mach-qt2410.c
@@ -50,8 +50,8 @@
 #include <mach/leds-gpio.h>
 #include <plat/regs-serial.h>
 #include <mach/fb.h>
-#include <asm/plat-s3c/nand.h>
-#include <asm/plat-s3c24xx/udc.h>
+#include <plat/nand.h>
+#include <plat/udc.h>
 #include <mach/spi.h>
 #include <mach/spi-gpio.h>
 
diff --git a/arch/arm/mach-s3c2412/Kconfig b/arch/arm/mach-s3c2412/Kconfig
index c59a9d2ee9a6..ca99564ae4b5 100644
--- a/arch/arm/mach-s3c2412/Kconfig
+++ b/arch/arm/mach-s3c2412/Kconfig
@@ -7,6 +7,7 @@
 config CPU_S3C2412
 	bool
 	depends on ARCH_S3C2410
+	select CPU_ARM926T
 	select CPU_LLSERIAL_S3C2440
 	select S3C2412_PM if PM
 	select S3C2412_DMA if S3C2410_DMA
diff --git a/arch/arm/mach-s3c2412/dma.c b/arch/arm/mach-s3c2412/dma.c
index ba0591e71f32..919856c9433f 100644
--- a/arch/arm/mach-s3c2412/dma.c
+++ b/arch/arm/mach-s3c2412/dma.c
@@ -18,7 +18,6 @@
 #include <linux/serial_core.h>
 #include <linux/io.h>
 
-#include <asm/dma.h>
 #include <mach/dma.h>
 
 #include <plat/dma.h>
@@ -26,13 +25,13 @@
 
 #include <plat/regs-serial.h>
 #include <mach/regs-gpio.h>
-#include <asm/plat-s3c/regs-ac97.h>
+#include <plat/regs-ac97.h>
 #include <mach/regs-mem.h>
 #include <mach/regs-lcd.h>
 #include <mach/regs-sdi.h>
 #include <asm/plat-s3c24xx/regs-s3c2412-iis.h>
 #include <asm/plat-s3c24xx/regs-iis.h>
-#include <asm/plat-s3c24xx/regs-spi.h>
+#include <plat/regs-spi.h>
 
 #define MAP(x) { (x)| DMA_CH_VALID, (x)| DMA_CH_VALID, (x)| DMA_CH_VALID, (x)| DMA_CH_VALID }
 
diff --git a/arch/arm/mach-s3c2412/mach-jive.c b/arch/arm/mach-s3c2412/mach-jive.c
index b08f18c8c47a..25ff1ec9f8ad 100644
--- a/arch/arm/mach-s3c2412/mach-jive.c
+++ b/arch/arm/mach-s3c2412/mach-jive.c
@@ -31,8 +31,8 @@
 #include <asm/mach/irq.h>
 
 #include <plat/regs-serial.h>
-#include <asm/plat-s3c/nand.h>
-#include <asm/plat-s3c/iic.h>
+#include <plat/nand.h>
+#include <plat/iic.h>
 
 #include <mach/regs-power.h>
 #include <mach/regs-gpio.h>
@@ -52,7 +52,7 @@
 #include <plat/devs.h>
 #include <plat/cpu.h>
 #include <plat/pm.h>
-#include <asm/plat-s3c24xx/udc.h>
+#include <plat/udc.h>
 
 static struct map_desc jive_iodesc[] __initdata = {
 };
diff --git a/arch/arm/mach-s3c2412/mach-smdk2413.c b/arch/arm/mach-s3c2412/mach-smdk2413.c
index c719b5a740a9..8fd17b8d5679 100644
--- a/arch/arm/mach-s3c2412/mach-smdk2413.c
+++ b/arch/arm/mach-s3c2412/mach-smdk2413.c
@@ -37,7 +37,7 @@
 #include <mach/regs-lcd.h>
 
 #include <mach/idle.h>
-#include <asm/plat-s3c24xx/udc.h>
+#include <plat/udc.h>
 #include <mach/fb.h>
 
 #include <plat/s3c2410.h>
diff --git a/arch/arm/mach-s3c2412/mach-vstms.c b/arch/arm/mach-s3c2412/mach-vstms.c
index 4cfa19ad9be0..da32a6cb17ae 100644
--- a/arch/arm/mach-s3c2412/mach-vstms.c
+++ b/arch/arm/mach-s3c2412/mach-vstms.c
@@ -39,7 +39,7 @@
 #include <mach/idle.h>
 #include <mach/fb.h>
 
-#include <asm/plat-s3c/nand.h>
+#include <plat/nand.h>
 
 #include <plat/s3c2410.h>
 #include <plat/s3c2412.h>
diff --git a/arch/arm/mach-s3c2412/s3c2412.c b/arch/arm/mach-s3c2412/s3c2412.c
index 313759c3da69..a086818e117e 100644
--- a/arch/arm/mach-s3c2412/s3c2412.c
+++ b/arch/arm/mach-s3c2412/s3c2412.c
@@ -39,7 +39,7 @@
 #include <mach/regs-gpio.h>
 #include <mach/regs-gpioj.h>
 #include <mach/regs-dsc.h>
-#include <asm/plat-s3c24xx/regs-spi.h>
+#include <plat/regs-spi.h>
 #include <mach/regs-s3c2412.h>
 
 #include <plat/s3c2412.h>
diff --git a/arch/arm/mach-s3c2440/Kconfig b/arch/arm/mach-s3c2440/Kconfig
index 25de042ab996..0429d255b0d8 100644
--- a/arch/arm/mach-s3c2440/Kconfig
+++ b/arch/arm/mach-s3c2440/Kconfig
@@ -7,6 +7,7 @@
 config CPU_S3C2440
 	bool
 	depends on ARCH_S3C2410
+	select CPU_ARM920T
 	select S3C2410_CLOCK
 	select S3C2410_PM if PM
 	select S3C2410_GPIO
diff --git a/arch/arm/mach-s3c2440/dma.c b/arch/arm/mach-s3c2440/dma.c
index 32303f6a8321..5b5ee0b8f4e0 100644
--- a/arch/arm/mach-s3c2440/dma.c
+++ b/arch/arm/mach-s3c2440/dma.c
@@ -17,7 +17,6 @@
 #include <linux/sysdev.h>
 #include <linux/serial_core.h>
 
-#include <asm/dma.h>
 #include <mach/dma.h>
 
 #include <plat/dma.h>
@@ -25,12 +24,12 @@
 
 #include <plat/regs-serial.h>
 #include <mach/regs-gpio.h>
-#include <asm/plat-s3c/regs-ac97.h>
+#include <plat/regs-ac97.h>
 #include <mach/regs-mem.h>
 #include <mach/regs-lcd.h>
 #include <mach/regs-sdi.h>
 #include <asm/plat-s3c24xx/regs-iis.h>
-#include <asm/plat-s3c24xx/regs-spi.h>
+#include <plat/regs-spi.h>
 
 static struct s3c24xx_dma_map __initdata s3c2440_dma_mappings[] = {
 	[DMACH_XD0] = {
diff --git a/arch/arm/mach-s3c2440/mach-anubis.c b/arch/arm/mach-s3c2440/mach-anubis.c
index e2beca470484..334379bdfc6e 100644
--- a/arch/arm/mach-s3c2440/mach-anubis.c
+++ b/arch/arm/mach-s3c2440/mach-anubis.c
@@ -39,7 +39,7 @@
 #include <mach/regs-gpio.h>
 #include <mach/regs-mem.h>
 #include <mach/regs-lcd.h>
-#include <asm/plat-s3c/nand.h>
+#include <plat/nand.h>
 
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/nand.h>
diff --git a/arch/arm/mach-s3c2440/mach-at2440evb.c b/arch/arm/mach-s3c2440/mach-at2440evb.c
index 66876c6f2f1c..07b42a0207d1 100644
--- a/arch/arm/mach-s3c2440/mach-at2440evb.c
+++ b/arch/arm/mach-s3c2440/mach-at2440evb.c
@@ -35,7 +35,7 @@
 #include <mach/regs-gpio.h>
 #include <mach/regs-mem.h>
 #include <mach/regs-lcd.h>
-#include <asm/plat-s3c/nand.h>
+#include <plat/nand.h>
 
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/nand.h>
diff --git a/arch/arm/mach-s3c2440/mach-osiris.c b/arch/arm/mach-s3c2440/mach-osiris.c
index 2361d606abc5..884a3c7ae75f 100644
--- a/arch/arm/mach-s3c2440/mach-osiris.c
+++ b/arch/arm/mach-s3c2440/mach-osiris.c
@@ -37,7 +37,7 @@
 #include <mach/regs-gpio.h>
 #include <mach/regs-mem.h>
 #include <mach/regs-lcd.h>
-#include <asm/plat-s3c/nand.h>
+#include <plat/nand.h>
 
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/nand.h>
diff --git a/arch/arm/mach-s3c2440/mach-rx3715.c b/arch/arm/mach-s3c2440/mach-rx3715.c
index 4d14c7cff892..fbd081de592f 100644
--- a/arch/arm/mach-s3c2440/mach-rx3715.c
+++ b/arch/arm/mach-s3c2440/mach-rx3715.c
@@ -42,7 +42,7 @@
 #include <mach/regs-lcd.h>
 
 #include <mach/h1940.h>
-#include <asm/plat-s3c/nand.h>
+#include <plat/nand.h>
 #include <mach/fb.h>
 
 #include <plat/clock.h>
diff --git a/arch/arm/mach-s3c2442/Kconfig b/arch/arm/mach-s3c2442/Kconfig
index 26d131a77074..b289d198020e 100644
--- a/arch/arm/mach-s3c2442/Kconfig
+++ b/arch/arm/mach-s3c2442/Kconfig
@@ -7,6 +7,7 @@
 config CPU_S3C2442
 	bool
 	depends on ARCH_S3C2410
+	select CPU_ARM920T
 	select S3C2410_CLOCK
 	select S3C2410_GPIO
 	select S3C2410_PM if PM
diff --git a/arch/arm/mach-s3c2443/dma.c b/arch/arm/mach-s3c2443/dma.c
index f73ccb25ff94..2a58a4d5aa5a 100644
--- a/arch/arm/mach-s3c2443/dma.c
+++ b/arch/arm/mach-s3c2443/dma.c
@@ -18,7 +18,6 @@
 #include <linux/serial_core.h>
 #include <linux/io.h>
 
-#include <asm/dma.h>
 #include <mach/dma.h>
 
 #include <plat/dma.h>
@@ -26,12 +25,12 @@
 
 #include <plat/regs-serial.h>
 #include <mach/regs-gpio.h>
-#include <asm/plat-s3c/regs-ac97.h>
+#include <plat/regs-ac97.h>
 #include <mach/regs-mem.h>
 #include <mach/regs-lcd.h>
 #include <mach/regs-sdi.h>
 #include <asm/plat-s3c24xx/regs-iis.h>
-#include <asm/plat-s3c24xx/regs-spi.h>
+#include <plat/regs-spi.h>
 
 #define MAP(x) { \
 		[0]	= (x) | DMA_CH_VALID,	\
diff --git a/arch/arm/mach-sa1100/clock.c b/arch/arm/mach-sa1100/clock.c
index 43c30f84abf2..dab3c6347a8f 100644
--- a/arch/arm/mach-sa1100/clock.c
+++ b/arch/arm/mach-sa1100/clock.c
@@ -3,6 +3,7 @@
  */
 #include <linux/module.h>
 #include <linux/kernel.h>
+#include <linux/device.h>
 #include <linux/list.h>
 #include <linux/errno.h>
 #include <linux/err.h>
@@ -14,36 +15,39 @@
 #include <mach/hardware.h>
 
 /*
- * Very simple clock implementation - we only have one clock to
- * deal with at the moment, so we only match using the "name".
+ * Very simple clock implementation - we only have one clock to deal with.
  */
 struct clk {
-	struct list_head	node;
-	unsigned long		rate;
-	const char		*name;
 	unsigned int		enabled;
-	void			(*enable)(void);
-	void			(*disable)(void);
 };
 
-static LIST_HEAD(clocks);
-static DEFINE_MUTEX(clocks_mutex);
+static void clk_gpio27_enable(void)
+{
+	/*
+	 * First, set up the 3.6864MHz clock on GPIO 27 for the SA-1111:
+	 * (SA-1110 Developer's Manual, section 9.1.2.1)
+	 */
+	GAFR |= GPIO_32_768kHz;
+	GPDR |= GPIO_32_768kHz;
+	TUCR = TUCR_3_6864MHz;
+}
+
+static void clk_gpio27_disable(void)
+{
+	TUCR = 0;
+	GPDR &= ~GPIO_32_768kHz;
+	GAFR &= ~GPIO_32_768kHz;
+}
+
+static struct clk clk_gpio27;
+
 static DEFINE_SPINLOCK(clocks_lock);
 
 struct clk *clk_get(struct device *dev, const char *id)
 {
-	struct clk *p, *clk = ERR_PTR(-ENOENT);
-
-	mutex_lock(&clocks_mutex);
-	list_for_each_entry(p, &clocks, node) {
-		if (strcmp(id, p->name) == 0) {
-			clk = p;
-			break;
-		}
-	}
-	mutex_unlock(&clocks_mutex);
+	const char *devname = dev_name(dev);
 
-	return clk;
+	return strcmp(devname, "sa1111.0") ? ERR_PTR(-ENOENT) : &clk_gpio27;
 }
 EXPORT_SYMBOL(clk_get);
 
@@ -58,7 +62,7 @@ int clk_enable(struct clk *clk)
 
 	spin_lock_irqsave(&clocks_lock, flags);
 	if (clk->enabled++ == 0)
-		clk->enable();
+		clk_gpio27_enable();
 	spin_unlock_irqrestore(&clocks_lock, flags);
 	return 0;
 }
@@ -72,63 +76,13 @@ void clk_disable(struct clk *clk)
 
 	spin_lock_irqsave(&clocks_lock, flags);
 	if (--clk->enabled == 0)
-		clk->disable();
+		clk_gpio27_disable();
 	spin_unlock_irqrestore(&clocks_lock, flags);
 }
 EXPORT_SYMBOL(clk_disable);
 
 unsigned long clk_get_rate(struct clk *clk)
 {
-	return clk->rate;
+	return 3686400;
 }
 EXPORT_SYMBOL(clk_get_rate);
-
-
-static void clk_gpio27_enable(void)
-{
-	/*
-	 * First, set up the 3.6864MHz clock on GPIO 27 for the SA-1111:
-	 * (SA-1110 Developer's Manual, section 9.1.2.1)
-	 */
-	GAFR |= GPIO_32_768kHz;
-	GPDR |= GPIO_32_768kHz;
-	TUCR = TUCR_3_6864MHz;
-}
-
-static void clk_gpio27_disable(void)
-{
-	TUCR = 0;
-	GPDR &= ~GPIO_32_768kHz;
-	GAFR &= ~GPIO_32_768kHz;
-}
-
-static struct clk clk_gpio27 = {
-	.name		= "SA1111_CLK",
-	.rate		= 3686400,
-	.enable		= clk_gpio27_enable,
-	.disable	= clk_gpio27_disable,
-};
-
-int clk_register(struct clk *clk)
-{
-	mutex_lock(&clocks_mutex);
-	list_add(&clk->node, &clocks);
-	mutex_unlock(&clocks_mutex);
-	return 0;
-}
-EXPORT_SYMBOL(clk_register);
-
-void clk_unregister(struct clk *clk)
-{
-	mutex_lock(&clocks_mutex);
-	list_del(&clk->node);
-	mutex_unlock(&clocks_mutex);
-}
-EXPORT_SYMBOL(clk_unregister);
-
-static int __init clk_init(void)
-{
-	clk_register(&clk_gpio27);
-	return 0;
-}
-arch_initcall(clk_init);
diff --git a/arch/arm/mach-sa1100/collie.c b/arch/arm/mach-sa1100/collie.c
index fe289997cfaf..2052eb88c961 100644
--- a/arch/arm/mach-sa1100/collie.c
+++ b/arch/arm/mach-sa1100/collie.c
@@ -68,23 +68,22 @@ struct platform_device colliescoop_device = {
 };
 
 static struct scoop_pcmcia_dev collie_pcmcia_scoop[] = {
-{
-       .dev        = &colliescoop_device.dev,
-       .irq        = COLLIE_IRQ_GPIO_CF_IRQ,
-       .cd_irq     = COLLIE_IRQ_GPIO_CF_CD,
-       .cd_irq_str = "PCMCIA0 CD",
-},
+	{
+	.dev		= &colliescoop_device.dev,
+	.irq		= COLLIE_IRQ_GPIO_CF_IRQ,
+	.cd_irq		= COLLIE_IRQ_GPIO_CF_CD,
+	.cd_irq_str	= "PCMCIA0 CD",
+	},
 };
 
 static struct scoop_pcmcia_config collie_pcmcia_config = {
-	.devs         = &collie_pcmcia_scoop[0],
-	.num_devs     = 1,
+	.devs		= &collie_pcmcia_scoop[0],
+	.num_devs	= 1,
 };
 
-
 static struct mcp_plat_data collie_mcp_data = {
-	.mccr0          = MCCR0_ADM | MCCR0_ExtClk,
-	.sclk_rate      = 9216000,
+	.mccr0		= MCCR0_ADM | MCCR0_ExtClk,
+	.sclk_rate	= 9216000,
 };
 
 #ifdef CONFIG_SHARP_LOCOMO
@@ -95,14 +94,14 @@ struct platform_device collie_locomo_device;
 
 static void collie_uart_set_mctrl(struct uart_port *port, u_int mctrl)
 {
- 	if (mctrl & TIOCM_RTS)
+	if (mctrl & TIOCM_RTS)
 		locomo_gpio_write(&collie_locomo_device.dev, LOCOMO_GPIO_RTS, 0);
- 	else
+	else
 		locomo_gpio_write(&collie_locomo_device.dev, LOCOMO_GPIO_RTS, 1);
 
- 	if (mctrl & TIOCM_DTR)
+	if (mctrl & TIOCM_DTR)
 		locomo_gpio_write(&collie_locomo_device.dev, LOCOMO_GPIO_DTR, 0);
- 	else
+	else
 		locomo_gpio_write(&collie_locomo_device.dev, LOCOMO_GPIO_DTR, 1);
 }
 
diff --git a/arch/arm/mach-sa1100/collie_pm.c b/arch/arm/mach-sa1100/collie_pm.c
index b1161fc80602..b39307f26b52 100644
--- a/arch/arm/mach-sa1100/collie_pm.c
+++ b/arch/arm/mach-sa1100/collie_pm.c
@@ -26,7 +26,7 @@
 #include <asm/irq.h>
 #include <mach/hardware.h>
 #include <asm/hardware/scoop.h>
-#include <asm/dma.h>
+#include <mach/dma.h>
 #include <mach/collie.h>
 #include <asm/mach/sharpsl_param.h>
 #include <asm/hardware/sharpsl_pm.h>
@@ -263,24 +263,24 @@ static int __init collie_pm_ucb_add(struct ucb1x00_dev *pdev)
 }
 
 static struct ucb1x00_driver collie_pm_ucb_driver = {
-	.add            = collie_pm_ucb_add,
+	.add	= collie_pm_ucb_add,
 };
 
 static struct platform_device *collie_pm_device;
 
 static int __init collie_pm_init(void)
 {
-        int ret;
+	int ret;
 
-        collie_pm_device = platform_device_alloc("sharpsl-pm", -1);
-        if (!collie_pm_device)
-                return -ENOMEM;
+	collie_pm_device = platform_device_alloc("sharpsl-pm", -1);
+	if (!collie_pm_device)
+		return -ENOMEM;
 
-        collie_pm_device->dev.platform_data = &collie_pm_machinfo;
-        ret = platform_device_add(collie_pm_device);
+	collie_pm_device->dev.platform_data = &collie_pm_machinfo;
+	ret = platform_device_add(collie_pm_device);
 
-        if (ret)
-                platform_device_put(collie_pm_device);
+	if (ret)
+		platform_device_put(collie_pm_device);
 
 	if (!ret)
 		ret = ucb1x00_register_driver(&collie_pm_ucb_driver);
@@ -291,7 +291,7 @@ static int __init collie_pm_init(void)
 static void __exit collie_pm_exit(void)
 {
 	ucb1x00_unregister_driver(&collie_pm_ucb_driver);
-        platform_device_unregister(collie_pm_device);
+	platform_device_unregister(collie_pm_device);
 }
 
 module_init(collie_pm_init);
diff --git a/arch/arm/mach-sa1100/cpu-sa1100.c b/arch/arm/mach-sa1100/cpu-sa1100.c
index 244d5956312c..ef817876a5d6 100644
--- a/arch/arm/mach-sa1100/cpu-sa1100.c
+++ b/arch/arm/mach-sa1100/cpu-sa1100.c
@@ -3,17 +3,17 @@
  *
  * Copyright (C) 2000 2001, The Delft University of Technology
  *
- * Authors: 
+ * Authors:
  * - Johan Pouwelse (J.A.Pouwelse@its.tudelft.nl): initial version
  * - Erik Mouw (J.A.K.Mouw@its.tudelft.nl):
  *   - major rewrite for linux-2.3.99
- *   - rewritten for the more generic power management scheme in 
+ *   - rewritten for the more generic power management scheme in
  *     linux-2.4.5-rmk1
  *
  * This software has been developed while working on the LART
  * computing board (http://www.lartmaker.nl/), which is
  * sponsored by the Mobile Multi-media Communications
- * (http://www.mmc.tudelft.nl/) and Ubiquitous Communications 
+ * (http://www.mmc.tudelft.nl/) and Ubiquitous Communications
  * (http://www.ubicom.tudelft.nl/) projects.
  *
  * The authors can be reached at:
@@ -36,7 +36,7 @@
  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  * GNU General Public License for more details.
- * 
+ *
  * You should have received a copy of the GNU General Public License
  * along with this program; if not, write to the Free Software
  * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
@@ -44,7 +44,7 @@
  *
  * Theory of operations
  * ====================
- * 
+ *
  * Clock scaling can be used to lower the power consumption of the CPU
  * core. This will give you a somewhat longer running time.
  *
@@ -58,11 +58,11 @@
  *   MDCNFG    0xA0000000    DRAM config
  *   MDCAS0    0xA0000004    Access waveform
  *   MDCAS1    0xA0000008    Access waveform
- *   MDCAS2    0xA000000C    Access waveform 
+ *   MDCAS2    0xA000000C    Access waveform
  *
  * Care must be taken to change the DRAM parameters the correct way,
  * because otherwise the DRAM becomes unusable and the kernel will
- * crash. 
+ * crash.
  *
  * The simple solution to avoid a kernel crash is to put the actual
  * clock change in ROM and jump to that code from the kernel. The main
@@ -75,7 +75,7 @@
  * as long as all re-configuration steps yield a valid DRAM
  * configuration. The advantages are clear: it will run on all SA-1100
  * platforms, and the code is very simple.
- * 
+ *
  * If you really want to understand what is going on in
  * sa1100_update_dram_timings(), you'll have to read sections 8.2,
  * 9.5.7.3, and 10.2 from the "Intel StrongARM SA-1100 Microprocessor
@@ -97,7 +97,7 @@
 typedef struct {
 	int speed;
 	u32 mdcnfg;
-	u32 mdcas0; 
+	u32 mdcas0;
 	u32 mdcas1;
 	u32 mdcas2;
 } sa1100_dram_regs_t;
@@ -147,7 +147,7 @@ static void sa1100_update_dram_timings(int current_speed, int new_speed)
 	/* No risk, no fun: run with interrupts on! */
 	if (new_speed > current_speed) {
 		/* We're going FASTER, so first relax the memory
-		 * timings before changing the core frequency 
+		 * timings before changing the core frequency
 		 */
 		
 		/* Half the memory access clock */
diff --git a/arch/arm/mach-sa1100/cpu-sa1110.c b/arch/arm/mach-sa1100/cpu-sa1110.c
index 3e4fb214eada..63b32b68b296 100644
--- a/arch/arm/mach-sa1100/cpu-sa1110.c
+++ b/arch/arm/mach-sa1100/cpu-sa1110.c
@@ -81,14 +81,14 @@ static struct sdram_params sdram_tbl[] __initdata = {
 		.twr		= 9,
 		.refresh	= 64000,
 		.cas_latency	= 3,
-	}, {    /* Samsung K4S281632B-1H */
-	        .name           = "K4S281632B-1H",
-		.rows           = 12,
-		.tck            = 10,
-		.trp            = 20,
-		.twr            = 10,
-		.refresh        = 64000,
-		.cas_latency    = 3,
+	}, {	/* Samsung K4S281632B-1H */
+		.name           = "K4S281632B-1H",
+		.rows		= 12,
+		.tck		= 10,
+		.trp		= 20,
+		.twr		= 10,
+		.refresh	= 64000,
+		.cas_latency	= 3,
 	}, {	/* Samsung KM416S4030CT */
 		.name		= "KM416S4030CT",
 		.rows		= 13,
@@ -220,7 +220,7 @@ sdram_update_refresh(u_int cpu_khz, struct sdram_params *sdram)
 }
 
 /*
- * Ok, set the CPU frequency.  
+ * Ok, set the CPU frequency.
  */
 static int sa1110_target(struct cpufreq_policy *policy,
 			 unsigned int target_freq,
diff --git a/arch/arm/mach-sa1100/dma.c b/arch/arm/mach-sa1100/dma.c
index f990a3e85846..95f9c5a6d6d5 100644
--- a/arch/arm/mach-sa1100/dma.c
+++ b/arch/arm/mach-sa1100/dma.c
@@ -19,7 +19,7 @@
 #include <asm/system.h>
 #include <asm/irq.h>
 #include <mach/hardware.h>
-#include <asm/dma.h>
+#include <mach/dma.h>
 
 
 #undef DEBUG
@@ -113,10 +113,10 @@ int sa1100_request_dma (dma_device_t device, const char *device_id,
 		}
 	}
 	if (!err) {
-	       if (dma)
-		       dma->device = device;
-	       else
-		       err = -ENOSR;
+		if (dma)
+			dma->device = device;
+		else
+			err = -ENOSR;
 	}
 	spin_unlock(&dma_list_lock);
 	if (err)
diff --git a/arch/arm/mach-sa1100/include/mach/h3600.h b/arch/arm/mach-sa1100/include/mach/h3600.h
index 3ca0ecf095e6..9cc47fddb335 100644
--- a/arch/arm/mach-sa1100/include/mach/h3600.h
+++ b/arch/arm/mach-sa1100/include/mach/h3600.h
@@ -32,14 +32,14 @@ typedef int __bitwise pm_request_t;
 #define machine_is_h3xxx() (machine_is_h3100() || machine_is_h3600() || machine_is_h3800())
 
 /* Physical memory regions corresponding to chip selects */
-#define H3600_EGPIO_PHYS     (SA1100_CS5_PHYS + 0x01000000)
-#define H3600_BANK_2_PHYS    SA1100_CS2_PHYS
-#define H3600_BANK_4_PHYS    SA1100_CS4_PHYS
+#define H3600_EGPIO_PHYS	(SA1100_CS5_PHYS + 0x01000000)
+#define H3600_BANK_2_PHYS	SA1100_CS2_PHYS
+#define H3600_BANK_4_PHYS	SA1100_CS4_PHYS
 
 /* Virtual memory regions corresponding to chip selects 2 & 4 (used on sleeves) */
-#define H3600_EGPIO_VIRT     0xf0000000
-#define H3600_BANK_2_VIRT    0xf1000000
-#define H3600_BANK_4_VIRT    0xf3800000
+#define H3600_EGPIO_VIRT	0xf0000000
+#define H3600_BANK_2_VIRT	0xf1000000
+#define H3600_BANK_4_VIRT	0xf3800000
 
 /*
    Machine-independent GPIO definitions
diff --git a/arch/arm/mach-sa1100/include/mach/io.h b/arch/arm/mach-sa1100/include/mach/io.h
index 0c070a6149bc..d8b43f3dcd2d 100644
--- a/arch/arm/mach-sa1100/include/mach/io.h
+++ b/arch/arm/mach-sa1100/include/mach/io.h
@@ -16,11 +16,7 @@
  * We don't actually have real ISA nor PCI buses, but there is so many 
  * drivers out there that might just work if we fake them...
  */
-static inline void __iomem *__io(unsigned long addr)
-{
-	return (void __iomem *)addr;
-}
-#define __io(a)			__io(a)
-#define __mem_pci(a)		(a)
+#define __io(a)		__typesafe_io(a)
+#define __mem_pci(a)	(a)
 
 #endif
diff --git a/arch/arm/mach-sa1100/include/mach/memory.h b/arch/arm/mach-sa1100/include/mach/memory.h
index 1c127b68581d..e9f8eed900f5 100644
--- a/arch/arm/mach-sa1100/include/mach/memory.h
+++ b/arch/arm/mach-sa1100/include/mach/memory.h
@@ -23,23 +23,12 @@ void sa1111_adjust_zones(int node, unsigned long *size, unsigned long *holes);
 	sa1111_adjust_zones(node, size, holes)
 
 #define ISA_DMA_THRESHOLD	(PHYS_OFFSET + SZ_1M - 1)
+#define MAX_DMA_ADDRESS		(PAGE_OFFSET + SZ_1M)
 
 #endif
 #endif
 
 /*
- * Virtual view <-> DMA view memory address translations
- * virt_to_bus: Used to translate the virtual address to an
- *		address suitable to be passed to set_dma_addr
- * bus_to_virt: Used to convert an address for DMA operations
- *		to an address that the kernel can use.
- *
- * On the SA1100, bus addresses are equivalent to physical addresses.
- */
-#define __virt_to_bus(x)	 __virt_to_phys(x)
-#define __bus_to_virt(x)	 __phys_to_virt(x)
-
-/*
  * Because of the wide memory address space between physical RAM banks on the
  * SA1100, it's much convenient to use Linux's SparseMEM support to implement
  * our memory map representation.  Assuming all memory nodes have equal access
diff --git a/arch/arm/mach-sa1100/pleb.c b/arch/arm/mach-sa1100/pleb.c
index e45d3a1890bc..e1458bc1868e 100644
--- a/arch/arm/mach-sa1100/pleb.c
+++ b/arch/arm/mach-sa1100/pleb.c
@@ -122,12 +122,12 @@ static void __init pleb_map_io(void)
 	sa1100_map_io();
 
 	sa1100_register_uart(0, 3);
-        sa1100_register_uart(1, 1);
+	sa1100_register_uart(1, 1);
 
-        GAFR |= (GPIO_UART_TXD | GPIO_UART_RXD);
-        GPDR |= GPIO_UART_TXD;
-        GPDR &= ~GPIO_UART_RXD;
-        PPAR |= PPAR_UPR;
+	GAFR |= (GPIO_UART_TXD | GPIO_UART_RXD);
+	GPDR |= GPIO_UART_TXD;
+	GPDR &= ~GPIO_UART_RXD;
+	PPAR |= PPAR_UPR;
 
 	/*
 	 * Fix expansion memory timing for network card
diff --git a/arch/arm/mach-sa1100/shannon.c b/arch/arm/mach-sa1100/shannon.c
index 9ccdd09cf69f..ddd917d1083d 100644
--- a/arch/arm/mach-sa1100/shannon.c
+++ b/arch/arm/mach-sa1100/shannon.c
@@ -33,7 +33,7 @@ static struct mtd_partition shannon_partitions[] = {
 		.offset		= MTDPART_OFS_APPEND,
 		.size		= 0xe0000
 	},
-	{ 
+	{
 		.name		= "initrd",
 		.offset		= MTDPART_OFS_APPEND,	
 		.size		= MTDPART_SIZ_FULL
diff --git a/arch/arm/mach-sa1100/sleep.S b/arch/arm/mach-sa1100/sleep.S
index 171441f96710..80f31bad707c 100644
--- a/arch/arm/mach-sa1100/sleep.S
+++ b/arch/arm/mach-sa1100/sleep.S
@@ -100,36 +100,36 @@ ENTRY(sa1100_cpu_suspend)
 	ldr	r1, =MSC1
 	ldr	r2, =MSC2
 
-        ldr     r3, [r0]
-        bic     r3, r3, #FMsk(MSC_RT)
-        bic     r3, r3, #FMsk(MSC_RT)<<16
+	ldr	r3, [r0]
+	bic	r3, r3, #FMsk(MSC_RT)
+	bic	r3, r3, #FMsk(MSC_RT)<<16
 
-        ldr     r4, [r1]
-        bic     r4, r4, #FMsk(MSC_RT)
-        bic     r4, r4, #FMsk(MSC_RT)<<16
+	ldr	r4, [r1]
+	bic	r4, r4, #FMsk(MSC_RT)
+	bic	r4, r4, #FMsk(MSC_RT)<<16
 
-        ldr     r5, [r2]
-        bic     r5, r5, #FMsk(MSC_RT)
-        bic     r5, r5, #FMsk(MSC_RT)<<16
+	ldr	r5, [r2]
+	bic	r5, r5, #FMsk(MSC_RT)
+	bic	r5, r5, #FMsk(MSC_RT)<<16
 
-        ldr     r6, =MDREFR
+	ldr	r6, =MDREFR
 
-        ldr     r7, [r6]
-        bic     r7, r7, #0x0000FF00
-        bic     r7, r7, #0x000000F0
-        orr     r8, r7, #MDREFR_SLFRSH
+	ldr	r7, [r6]
+bic	r7, r7, #0x0000FF00
+bic	r7, r7, #0x000000F0
+orr	r8, r7, #MDREFR_SLFRSH
 
-        ldr     r9, =MDCNFG
-        ldr     r10, [r9]
-        bic     r10, r10, #(MDCNFG_DE0+MDCNFG_DE1)
-        bic     r10, r10, #(MDCNFG_DE2+MDCNFG_DE3)
+	ldr	r9, =MDCNFG
+	ldr	r10, [r9]
+	bic	r10, r10, #(MDCNFG_DE0+MDCNFG_DE1)
+	bic	r10, r10, #(MDCNFG_DE2+MDCNFG_DE3)
 
-        bic     r11, r8, #MDREFR_SLFRSH
-        bic     r11, r11, #MDREFR_E1PIN
+	bic	r11, r8, #MDREFR_SLFRSH
+	bic	r11, r11, #MDREFR_E1PIN
 
-        ldr     r12, =PMCR
+	ldr	r12, =PMCR
 
-        mov     r13, #PMCR_SF
+	mov	r13, #PMCR_SF
 
 	b	sa1110_sdram_controller_fix
 
@@ -188,10 +188,10 @@ ENTRY(sa1100_cpu_resume)
 	mcr	p15, 0, r1, c8, c7, 0   	@ flush I+D TLBs
 	mcr	p15, 0, r1, c7, c7, 0		@ flush I&D cache
 	mcr	p15, 0, r1, c9, c0, 0		@ invalidate RB
-	mcr     p15, 0, r1, c9, c0, 5		@ allow user space to use RB
+	mcr	p15, 0, r1, c9, c0, 5		@ allow user space to use RB
 
-	mcr 	p15, 0, r4, c3, c0, 0		@ domain ID
-	mcr 	p15, 0, r5, c2, c0, 0		@ translation table base addr
+	mcr	p15, 0, r4, c3, c0, 0		@ domain ID
+	mcr	p15, 0, r5, c2, c0, 0		@ translation table base addr
 	mcr	p15, 0, r6, c13, c0, 0		@ PID
 	b	resume_turn_on_mmu		@ cache align execution
 
@@ -209,7 +209,7 @@ sleep_save_sp:
 
 	.text
 resume_after_mmu:
-	mcr     p15, 0, r1, c15, c1, 2		@ enable clock switching
+	mcr	p15, 0, r1, c15, c1, 2		@ enable clock switching
 	ldmfd	sp!, {r4 - r12, pc}		@ return to caller
 
 
diff --git a/arch/arm/mach-sa1100/time.c b/arch/arm/mach-sa1100/time.c
index 24c0a4bae850..8c5e727f3b75 100644
--- a/arch/arm/mach-sa1100/time.c
+++ b/arch/arm/mach-sa1100/time.c
@@ -2,8 +2,8 @@
  * linux/arch/arm/mach-sa1100/time.c
  *
  * Copyright (C) 1998 Deborah Wallach.
- * Twiddles  (C) 1999 	Hugo Fiennes <hugo@empeg.com>
- * 
+ * Twiddles  (C) 1999 Hugo Fiennes <hugo@empeg.com>
+ *
  * 2000/03/29 (C) Nicolas Pitre <nico@cam.org>
  *	Rewritten: big cleanup, much simpler, better HZ accuracy.
  *
diff --git a/arch/arm/mach-shark/core.c b/arch/arm/mach-shark/core.c
index a9400d984451..a23fd3d0163a 100644
--- a/arch/arm/mach-shark/core.c
+++ b/arch/arm/mach-shark/core.c
@@ -16,6 +16,8 @@
 #include <asm/leds.h>
 #include <asm/param.h>
 
+#include <mach/hardware.h>
+
 #include <asm/mach/map.h>
 #include <asm/mach/arch.h>
 #include <asm/mach/time.h>
diff --git a/arch/arm/mach-shark/include/mach/hardware.h b/arch/arm/mach-shark/include/mach/hardware.h
index cb0ee2943c1a..01bf76099ce5 100644
--- a/arch/arm/mach-shark/include/mach/hardware.h
+++ b/arch/arm/mach-shark/include/mach/hardware.h
@@ -28,8 +28,6 @@
 #define ROMCARD_SIZE		0x08000000
 #define ROMCARD_START		0x10000000
 
-#define PCIO_BASE		0xe0000000
-
 
 /* defines for the Framebuffer */
 #define FB_START		0x06000000
diff --git a/arch/arm/mach-shark/include/mach/io.h b/arch/arm/mach-shark/include/mach/io.h
index 92475922c068..c5cee829fc87 100644
--- a/arch/arm/mach-shark/include/mach/io.h
+++ b/arch/arm/mach-shark/include/mach/io.h
@@ -11,46 +11,10 @@
 #ifndef __ASM_ARM_ARCH_IO_H
 #define __ASM_ARM_ARCH_IO_H
 
-#include <mach/hardware.h>
+#define PCIO_BASE	0xe0000000
+#define IO_SPACE_LIMIT	0xffffffff
 
-#define IO_SPACE_LIMIT 0xffffffff
-
-/*
- * We use two different types of addressing - PC style addresses, and ARM
- * addresses.  PC style accesses the PC hardware with the normal PC IO
- * addresses, eg 0x3f8 for serial#1.  ARM addresses are 0x80000000+
- * and are translated to the start of IO.
- */
-#define __PORT_PCIO(x)	(!((x) & 0x80000000))
-
-#define __io(a)                 ((void __iomem *)(PCIO_BASE + (a)))
-
-
-static inline unsigned int __ioaddr (unsigned int port)			\
-{										\
-	if (__PORT_PCIO(port))							\
-		return (unsigned int)(PCIO_BASE + (port));			\
-	else									\
-		return (unsigned int)(IO_BASE + (port));			\
-}
-
-#define __mem_pci(addr) (addr)
-
-/*
- * Translated address IO functions
- *
- * IO address has already been translated to a virtual address
- */
-#define outb_t(v,p)								\
-	(*(volatile unsigned char *)(p) = (v))
-
-#define inb_t(p)								\
-	(*(volatile unsigned char *)(p))
-
-#define outl_t(v,p)								\
-	(*(volatile unsigned long *)(p) = (v))
-
-#define inl_t(p)								\
-	(*(volatile unsigned long *)(p))
+#define __io(a)		((void __iomem *)(PCIO_BASE + (a)))
+#define __mem_pci(addr)	(addr)
 
 #endif
diff --git a/arch/arm/mach-shark/include/mach/dma.h b/arch/arm/mach-shark/include/mach/isa-dma.h
index c0a29bd2a74f..864298ff3927 100644
--- a/arch/arm/mach-shark/include/mach/dma.h
+++ b/arch/arm/mach-shark/include/mach/isa-dma.h
@@ -1,5 +1,5 @@
 /*
- * arch/arm/mach-shark/include/mach/dma.h
+ * arch/arm/mach-shark/include/mach/isa-dma.h
  *
  * by Alexander Schulz
  */
@@ -10,7 +10,6 @@
  * The rest is not DMAable. See dev /  .properties
  * in OpenFirmware.
  */
-#define MAX_DMA_ADDRESS		0xC0400000
 #define MAX_DMA_CHANNELS	8
 #define DMA_ISA_CASCADE         4
 
diff --git a/arch/arm/mach-shark/include/mach/memory.h b/arch/arm/mach-shark/include/mach/memory.h
index b7874ad9f9f6..c5ab038925d6 100644
--- a/arch/arm/mach-shark/include/mach/memory.h
+++ b/arch/arm/mach-shark/include/mach/memory.h
@@ -33,12 +33,10 @@ static inline void __arch_adjust_zones(int node, unsigned long *zone_size, unsig
 	__arch_adjust_zones(node, size, holes)
 
 #define ISA_DMA_THRESHOLD	(PHYS_OFFSET + SZ_4M - 1)
+#define MAX_DMA_ADDRESS		(PAGE_OFFSET + SZ_4M)
 
 #endif
 
-#define __virt_to_bus(x)	__virt_to_phys(x)
-#define __bus_to_virt(x)	__phys_to_virt(x)
-
 /*
  * Cache flushing area
  */
diff --git a/arch/arm/mach-versatile/Kconfig b/arch/arm/mach-versatile/Kconfig
index 95096afd5271..c781f30c8368 100644
--- a/arch/arm/mach-versatile/Kconfig
+++ b/arch/arm/mach-versatile/Kconfig
@@ -3,12 +3,14 @@ menu "Versatile platform type"
 
 config ARCH_VERSATILE_PB
 	bool "Support Versatile/PB platform"
+	select CPU_ARM926T
 	default y
 	help
 	  Include support for the ARM(R) Versatile/PB platform.
 
 config MACH_VERSATILE_AB
 	bool "Support Versatile/AB platform"
+	select CPU_ARM926T
 	help
 	  Include support for the ARM(R) Versatile/AP platform.
 
diff --git a/arch/arm/mach-versatile/clock.c b/arch/arm/mach-versatile/clock.c
index 58937f1fb38c..c50a44ea7ee6 100644
--- a/arch/arm/mach-versatile/clock.c
+++ b/arch/arm/mach-versatile/clock.c
@@ -10,6 +10,7 @@
  */
 #include <linux/module.h>
 #include <linux/kernel.h>
+#include <linux/device.h>
 #include <linux/list.h>
 #include <linux/errno.h>
 #include <linux/err.h>
@@ -17,36 +18,11 @@
 #include <linux/clk.h>
 #include <linux/mutex.h>
 
+#include <asm/clkdev.h>
 #include <asm/hardware/icst307.h>
 
 #include "clock.h"
 
-static LIST_HEAD(clocks);
-static DEFINE_MUTEX(clocks_mutex);
-
-struct clk *clk_get(struct device *dev, const char *id)
-{
-	struct clk *p, *clk = ERR_PTR(-ENOENT);
-
-	mutex_lock(&clocks_mutex);
-	list_for_each_entry(p, &clocks, node) {
-		if (strcmp(id, p->name) == 0 && try_module_get(p->owner)) {
-			clk = p;
-			break;
-		}
-	}
-	mutex_unlock(&clocks_mutex);
-
-	return clk;
-}
-EXPORT_SYMBOL(clk_get);
-
-void clk_put(struct clk *clk)
-{
-	module_put(clk->owner);
-}
-EXPORT_SYMBOL(clk_put);
-
 int clk_enable(struct clk *clk)
 {
 	return 0;
@@ -66,7 +42,9 @@ EXPORT_SYMBOL(clk_get_rate);
 
 long clk_round_rate(struct clk *clk, unsigned long rate)
 {
-	return rate;
+	struct icst307_vco vco;
+	vco = icst307_khz_to_vco(clk->params, rate / 1000);
+	return icst307_khz(clk->params, vco) * 1000;
 }
 EXPORT_SYMBOL(clk_round_rate);
 
@@ -79,57 +57,9 @@ int clk_set_rate(struct clk *clk, unsigned long rate)
 
 		vco = icst307_khz_to_vco(clk->params, rate / 1000);
 		clk->rate = icst307_khz(clk->params, vco) * 1000;
-
-		printk("Clock %s: setting VCO reg params: S=%d R=%d V=%d\n",
-			clk->name, vco.s, vco.r, vco.v);
-
 		clk->setvco(clk, vco);
 		ret = 0;
 	}
 	return ret;
 }
 EXPORT_SYMBOL(clk_set_rate);
-
-/*
- * These are fixed clocks.
- */
-static struct clk kmi_clk = {
-	.name	= "KMIREFCLK",
-	.rate	= 24000000,
-};
-
-static struct clk uart_clk = {
-	.name	= "UARTCLK",
-	.rate	= 24000000,
-};
-
-static struct clk mmci_clk = {
-	.name	= "MCLK",
-	.rate	= 24000000,
-};
-
-int clk_register(struct clk *clk)
-{
-	mutex_lock(&clocks_mutex);
-	list_add(&clk->node, &clocks);
-	mutex_unlock(&clocks_mutex);
-	return 0;
-}
-EXPORT_SYMBOL(clk_register);
-
-void clk_unregister(struct clk *clk)
-{
-	mutex_lock(&clocks_mutex);
-	list_del(&clk->node);
-	mutex_unlock(&clocks_mutex);
-}
-EXPORT_SYMBOL(clk_unregister);
-
-static int __init clk_init(void)
-{
-	clk_register(&kmi_clk);
-	clk_register(&uart_clk);
-	clk_register(&mmci_clk);
-	return 0;
-}
-arch_initcall(clk_init);
diff --git a/arch/arm/mach-versatile/clock.h b/arch/arm/mach-versatile/clock.h
index 8b0b61dd17e4..03468fdc3e58 100644
--- a/arch/arm/mach-versatile/clock.h
+++ b/arch/arm/mach-versatile/clock.h
@@ -12,14 +12,9 @@ struct module;
 struct icst307_params;
 
 struct clk {
-	struct list_head	node;
 	unsigned long		rate;
-	struct module		*owner;
-	const char		*name;
 	const struct icst307_params *params;
+	u32			oscoff;
 	void			*data;
 	void			(*setvco)(struct clk *, struct icst307_vco vco);
 };
-
-int clk_register(struct clk *clk);
-void clk_unregister(struct clk *clk);
diff --git a/arch/arm/mach-versatile/core.c b/arch/arm/mach-versatile/core.c
index 565e0ba0d67e..df25aa138509 100644
--- a/arch/arm/mach-versatile/core.c
+++ b/arch/arm/mach-versatile/core.c
@@ -31,6 +31,7 @@
 #include <linux/cnt32_to_63.h>
 #include <linux/io.h>
 
+#include <asm/clkdev.h>
 #include <asm/system.h>
 #include <mach/hardware.h>
 #include <asm/irq.h>
@@ -373,22 +374,60 @@ static const struct icst307_params versatile_oscvco_params = {
 
 static void versatile_oscvco_set(struct clk *clk, struct icst307_vco vco)
 {
-	void __iomem *sys_lock = __io_address(VERSATILE_SYS_BASE) + VERSATILE_SYS_LOCK_OFFSET;
-	void __iomem *sys_osc = __io_address(VERSATILE_SYS_BASE) + VERSATILE_SYS_OSCCLCD_OFFSET;
+	void __iomem *sys = __io_address(VERSATILE_SYS_BASE);
+	void __iomem *sys_lock = sys + VERSATILE_SYS_LOCK_OFFSET;
 	u32 val;
 
-	val = readl(sys_osc) & ~0x7ffff;
+	val = readl(sys + clk->oscoff) & ~0x7ffff;
 	val |= vco.v | (vco.r << 9) | (vco.s << 16);
 
 	writel(0xa05f, sys_lock);
-	writel(val, sys_osc);
+	writel(val, sys + clk->oscoff);
 	writel(0, sys_lock);
 }
 
-static struct clk versatile_clcd_clk = {
-	.name	= "CLCDCLK",
+static struct clk osc4_clk = {
 	.params	= &versatile_oscvco_params,
-	.setvco = versatile_oscvco_set,
+	.oscoff	= VERSATILE_SYS_OSCCLCD_OFFSET,
+	.setvco	= versatile_oscvco_set,
+};
+
+/*
+ * These are fixed clocks.
+ */
+static struct clk ref24_clk = {
+	.rate	= 24000000,
+};
+
+static struct clk_lookup lookups[] __initdata = {
+	{	/* UART0 */
+		.dev_id		= "dev:f1",
+		.clk		= &ref24_clk,
+	}, {	/* UART1 */
+		.dev_id		= "dev:f2",
+		.clk		= &ref24_clk,
+	}, {	/* UART2 */
+		.dev_id		= "dev:f3",
+		.clk		= &ref24_clk,
+	}, {	/* UART3 */
+		.dev_id		= "fpga:09",
+		.clk		= &ref24_clk,
+	}, {	/* KMI0 */
+		.dev_id		= "fpga:06",
+		.clk		= &ref24_clk,
+	}, {	/* KMI1 */
+		.dev_id		= "fpga:07",
+		.clk		= &ref24_clk,
+	}, {	/* MMC0 */
+		.dev_id		= "fpga:05",
+		.clk		= &ref24_clk,
+	}, {	/* MMC1 */
+		.dev_id		= "fpga:0b",
+		.clk		= &ref24_clk,
+	}, {	/* CLCD */
+		.dev_id		= "dev:20",
+		.clk		= &osc4_clk,
+	}
 };
 
 /*
@@ -786,7 +825,8 @@ void __init versatile_init(void)
 {
 	int i;
 
-	clk_register(&versatile_clcd_clk);
+	for (i = 0; i < ARRAY_SIZE(lookups); i++)
+		clkdev_add(&lookups[i]);
 
 	platform_device_register(&versatile_flash_device);
 	platform_device_register(&versatile_i2c_device);
diff --git a/arch/arm/mach-versatile/core.h b/arch/arm/mach-versatile/core.h
index afcaa858eb1f..9d39886a8351 100644
--- a/arch/arm/mach-versatile/core.h
+++ b/arch/arm/mach-versatile/core.h
@@ -34,7 +34,7 @@ extern unsigned int mmc_status(struct device *dev);
 static struct amba_device name##_device = {			\
 	.dev		= {					\
 		.coherent_dma_mask = ~0,			\
-		.bus_id	= busid,				\
+		.init_name = busid,				\
 		.platform_data = plat,				\
 	},							\
 	.res		= {					\
diff --git a/arch/arm/mach-versatile/include/mach/clkdev.h b/arch/arm/mach-versatile/include/mach/clkdev.h
new file mode 100644
index 000000000000..04b37a89801c
--- /dev/null
+++ b/arch/arm/mach-versatile/include/mach/clkdev.h
@@ -0,0 +1,7 @@
+#ifndef __ASM_MACH_CLKDEV_H
+#define __ASM_MACH_CLKDEV_H
+
+#define __clk_get(clk) ({ 1; })
+#define __clk_put(clk) do { } while (0)
+
+#endif
diff --git a/arch/arm/mach-versatile/include/mach/dma.h b/arch/arm/mach-versatile/include/mach/dma.h
deleted file mode 100644
index 0aabf12c8834..000000000000
--- a/arch/arm/mach-versatile/include/mach/dma.h
+++ /dev/null
@@ -1,20 +0,0 @@
-/*
- *  arch/arm/mach-versatile/include/mach/dma.h
- *
- *  Copyright (C) 2003 ARM Limited.
- *  Copyright (C) 1997,1998 Russell King
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
- */
diff --git a/arch/arm/mach-versatile/include/mach/io.h b/arch/arm/mach-versatile/include/mach/io.h
index c0b9dd1d0257..f067c14c7182 100644
--- a/arch/arm/mach-versatile/include/mach/io.h
+++ b/arch/arm/mach-versatile/include/mach/io.h
@@ -22,11 +22,7 @@
 
 #define IO_SPACE_LIMIT 0xffffffff
 
-static inline void __iomem *__io(unsigned long addr)
-{
-	return (void __iomem *)addr;
-}
-#define __io(a)	__io(a)
-#define __mem_pci(a)		(a)
+#define __io(a)		__typesafe_io(a)
+#define __mem_pci(a)	(a)
 
 #endif
diff --git a/arch/arm/mach-versatile/include/mach/irqs.h b/arch/arm/mach-versatile/include/mach/irqs.h
index 216a1312e62e..9bfdb30e1f3f 100644
--- a/arch/arm/mach-versatile/include/mach/irqs.h
+++ b/arch/arm/mach-versatile/include/mach/irqs.h
@@ -60,39 +60,6 @@
 #define IRQ_VICSOURCE31		(IRQ_VIC_START + INT_VICSOURCE31)
 #define IRQ_VIC_END		(IRQ_VIC_START + 31)
 
-#define IRQMASK_WDOGINT		INTMASK_WDOGINT
-#define IRQMASK_SOFTINT		INTMASK_SOFTINT
-#define IRQMASK_COMMRx 		INTMASK_COMMRx
-#define IRQMASK_COMMTx 		INTMASK_COMMTx
-#define IRQMASK_TIMERINT0_1	INTMASK_TIMERINT0_1
-#define IRQMASK_TIMERINT2_3	INTMASK_TIMERINT2_3
-#define IRQMASK_GPIOINT0	INTMASK_GPIOINT0
-#define IRQMASK_GPIOINT1	INTMASK_GPIOINT1
-#define IRQMASK_GPIOINT2	INTMASK_GPIOINT2
-#define IRQMASK_GPIOINT3	INTMASK_GPIOINT3
-#define IRQMASK_RTCINT 		INTMASK_RTCINT
-#define IRQMASK_SSPINT 		INTMASK_SSPINT
-#define IRQMASK_UARTINT0	INTMASK_UARTINT0
-#define IRQMASK_UARTINT1	INTMASK_UARTINT1
-#define IRQMASK_UARTINT2	INTMASK_UARTINT2
-#define IRQMASK_SCIINT 		INTMASK_SCIINT
-#define IRQMASK_CLCDINT		INTMASK_CLCDINT
-#define IRQMASK_DMAINT 		INTMASK_DMAINT
-#define IRQMASK_PWRFAILINT	INTMASK_PWRFAILINT
-#define IRQMASK_MBXINT 		INTMASK_MBXINT
-#define IRQMASK_GNDINT 		INTMASK_GNDINT
-#define IRQMASK_VICSOURCE21	INTMASK_VICSOURCE21
-#define IRQMASK_VICSOURCE22	INTMASK_VICSOURCE22
-#define IRQMASK_VICSOURCE23	INTMASK_VICSOURCE23
-#define IRQMASK_VICSOURCE24	INTMASK_VICSOURCE24
-#define IRQMASK_VICSOURCE25	INTMASK_VICSOURCE25
-#define IRQMASK_VICSOURCE26	INTMASK_VICSOURCE26
-#define IRQMASK_VICSOURCE27	INTMASK_VICSOURCE27
-#define IRQMASK_VICSOURCE28	INTMASK_VICSOURCE28
-#define IRQMASK_VICSOURCE29	INTMASK_VICSOURCE29
-#define IRQMASK_VICSOURCE30	INTMASK_VICSOURCE30
-#define IRQMASK_VICSOURCE31	INTMASK_VICSOURCE31
-
 /* 
  *  FIQ interrupts definitions are the same as the INT definitions.
  */
@@ -130,39 +97,6 @@
 #define FIQ_VICSOURCE31		INT_VICSOURCE31
 
 
-#define FIQMASK_WDOGINT		INTMASK_WDOGINT
-#define FIQMASK_SOFTINT		INTMASK_SOFTINT
-#define FIQMASK_COMMRx 		INTMASK_COMMRx
-#define FIQMASK_COMMTx 		INTMASK_COMMTx
-#define FIQMASK_TIMERINT0_1	INTMASK_TIMERINT0_1
-#define FIQMASK_TIMERINT2_3	INTMASK_TIMERINT2_3
-#define FIQMASK_GPIOINT0	INTMASK_GPIOINT0
-#define FIQMASK_GPIOINT1	INTMASK_GPIOINT1
-#define FIQMASK_GPIOINT2	INTMASK_GPIOINT2
-#define FIQMASK_GPIOINT3	INTMASK_GPIOINT3
-#define FIQMASK_RTCINT 		INTMASK_RTCINT
-#define FIQMASK_SSPINT 		INTMASK_SSPINT
-#define FIQMASK_UARTINT0	INTMASK_UARTINT0
-#define FIQMASK_UARTINT1	INTMASK_UARTINT1
-#define FIQMASK_UARTINT2	INTMASK_UARTINT2
-#define FIQMASK_SCIINT 		INTMASK_SCIINT
-#define FIQMASK_CLCDINT		INTMASK_CLCDINT
-#define FIQMASK_DMAINT 		INTMASK_DMAINT
-#define FIQMASK_PWRFAILINT	INTMASK_PWRFAILINT
-#define FIQMASK_MBXINT 		INTMASK_MBXINT
-#define FIQMASK_GNDINT 		INTMASK_GNDINT
-#define FIQMASK_VICSOURCE21	INTMASK_VICSOURCE21
-#define FIQMASK_VICSOURCE22	INTMASK_VICSOURCE22
-#define FIQMASK_VICSOURCE23	INTMASK_VICSOURCE23
-#define FIQMASK_VICSOURCE24	INTMASK_VICSOURCE24
-#define FIQMASK_VICSOURCE25	INTMASK_VICSOURCE25
-#define FIQMASK_VICSOURCE26	INTMASK_VICSOURCE26
-#define FIQMASK_VICSOURCE27	INTMASK_VICSOURCE27
-#define FIQMASK_VICSOURCE28	INTMASK_VICSOURCE28
-#define FIQMASK_VICSOURCE29	INTMASK_VICSOURCE29
-#define FIQMASK_VICSOURCE30	INTMASK_VICSOURCE30
-#define FIQMASK_VICSOURCE31	INTMASK_VICSOURCE31
-
 /*
  * Secondary interrupt controller
  */
@@ -188,24 +122,4 @@
 #define IRQ_SIC_PCI3		(IRQ_SIC_START + SIC_INT_PCI3)
 #define IRQ_SIC_END		63
 
-#define SIC_IRQMASK_MMCI0B	SIC_INTMASK_MMCI0B
-#define SIC_IRQMASK_MMCI1B	SIC_INTMASK_MMCI1B
-#define SIC_IRQMASK_KMI0	SIC_INTMASK_KMI0
-#define SIC_IRQMASK_KMI1	SIC_INTMASK_KMI1
-#define SIC_IRQMASK_SCI3	SIC_INTMASK_SCI3
-#define SIC_IRQMASK_UART3	SIC_INTMASK_UART3
-#define SIC_IRQMASK_CLCD	SIC_INTMASK_CLCD
-#define SIC_IRQMASK_TOUCH	SIC_INTMASK_TOUCH
-#define SIC_IRQMASK_KEYPAD	SIC_INTMASK_KEYPAD
-#define SIC_IRQMASK_DoC		SIC_INTMASK_DoC
-#define SIC_IRQMASK_MMCI0A	SIC_INTMASK_MMCI0A
-#define SIC_IRQMASK_MMCI1A	SIC_INTMASK_MMCI1A
-#define SIC_IRQMASK_AACI	SIC_INTMASK_AACI
-#define SIC_IRQMASK_ETH		SIC_INTMASK_ETH
-#define SIC_IRQMASK_USB		SIC_INTMASK_USB
-#define SIC_IRQMASK_PCI0	SIC_INTMASK_PCI0
-#define SIC_IRQMASK_PCI1	SIC_INTMASK_PCI1
-#define SIC_IRQMASK_PCI2	SIC_INTMASK_PCI2
-#define SIC_IRQMASK_PCI3	SIC_INTMASK_PCI3
-
 #define NR_IRQS			64
diff --git a/arch/arm/mach-versatile/include/mach/memory.h b/arch/arm/mach-versatile/include/mach/memory.h
index b6315c0602ac..79aeab86b903 100644
--- a/arch/arm/mach-versatile/include/mach/memory.h
+++ b/arch/arm/mach-versatile/include/mach/memory.h
@@ -25,14 +25,4 @@
  */
 #define PHYS_OFFSET	UL(0x00000000)
 
-/*
- * Virtual view <-> DMA view memory address translations
- * virt_to_bus: Used to translate the virtual address to an
- *              address suitable to be passed to set_dma_addr
- * bus_to_virt: Used to convert an address for DMA operations
- *              to an address that the kernel can use.
- */
-#define __virt_to_bus(x)	((x) - PAGE_OFFSET)
-#define __bus_to_virt(x)	((x) + PAGE_OFFSET)
-
 #endif
diff --git a/arch/arm/mach-versatile/include/mach/platform.h b/arch/arm/mach-versatile/include/mach/platform.h
index f91ba930ca8a..83207395191a 100644
--- a/arch/arm/mach-versatile/include/mach/platform.h
+++ b/arch/arm/mach-versatile/include/mach/platform.h
@@ -347,44 +347,6 @@
 #define INT_VICSOURCE30                 30	/* PCI 3 */
 #define INT_VICSOURCE31                 31	/* SIC source */
 
-/* 
- *  Interrupt bit positions
- * 
- */
-#define INTMASK_WDOGINT                 (1 << INT_WDOGINT)
-#define INTMASK_SOFTINT                 (1 << INT_SOFTINT)
-#define INTMASK_COMMRx                  (1 << INT_COMMRx)
-#define INTMASK_COMMTx                  (1 << INT_COMMTx)
-#define INTMASK_TIMERINT0_1             (1 << INT_TIMERINT0_1)
-#define INTMASK_TIMERINT2_3             (1 << INT_TIMERINT2_3)
-#define INTMASK_GPIOINT0                (1 << INT_GPIOINT0)
-#define INTMASK_GPIOINT1                (1 << INT_GPIOINT1)
-#define INTMASK_GPIOINT2                (1 << INT_GPIOINT2)
-#define INTMASK_GPIOINT3                (1 << INT_GPIOINT3)
-#define INTMASK_RTCINT                  (1 << INT_RTCINT)
-#define INTMASK_SSPINT                  (1 << INT_SSPINT)
-#define INTMASK_UARTINT0                (1 << INT_UARTINT0)
-#define INTMASK_UARTINT1                (1 << INT_UARTINT1)
-#define INTMASK_UARTINT2                (1 << INT_UARTINT2)
-#define INTMASK_SCIINT                  (1 << INT_SCIINT)
-#define INTMASK_CLCDINT                 (1 << INT_CLCDINT)
-#define INTMASK_DMAINT                  (1 << INT_DMAINT)
-#define INTMASK_PWRFAILINT              (1 << INT_PWRFAILINT)
-#define INTMASK_MBXINT                  (1 << INT_MBXINT)
-#define INTMASK_GNDINT                  (1 << INT_GNDINT)
-#define INTMASK_VICSOURCE21             (1 << INT_VICSOURCE21)
-#define INTMASK_VICSOURCE22             (1 << INT_VICSOURCE22)
-#define INTMASK_VICSOURCE23             (1 << INT_VICSOURCE23)
-#define INTMASK_VICSOURCE24             (1 << INT_VICSOURCE24)
-#define INTMASK_VICSOURCE25             (1 << INT_VICSOURCE25)
-#define INTMASK_VICSOURCE26             (1 << INT_VICSOURCE26)
-#define INTMASK_VICSOURCE27             (1 << INT_VICSOURCE27)
-#define INTMASK_VICSOURCE28             (1 << INT_VICSOURCE28)
-#define INTMASK_VICSOURCE29             (1 << INT_VICSOURCE29)
-#define INTMASK_VICSOURCE30             (1 << INT_VICSOURCE30)
-#define INTMASK_VICSOURCE31             (1 << INT_VICSOURCE31)
-
-
 #define VERSATILE_SC_VALID_INT               0x003FFFFF
 
 #define MAXIRQNUM                       31
@@ -417,26 +379,6 @@
 #define SIC_INT_PCI3                    30
 
 
-#define SIC_INTMASK_MMCI0B              (1 << SIC_INT_MMCI0B)
-#define SIC_INTMASK_MMCI1B              (1 << SIC_INT_MMCI1B)
-#define SIC_INTMASK_KMI0                (1 << SIC_INT_KMI0)
-#define SIC_INTMASK_KMI1                (1 << SIC_INT_KMI1)
-#define SIC_INTMASK_SCI3                (1 << SIC_INT_SCI3)
-#define SIC_INTMASK_UART3               (1 << SIC_INT_UART3)
-#define SIC_INTMASK_CLCD                (1 << SIC_INT_CLCD)
-#define SIC_INTMASK_TOUCH               (1 << SIC_INT_TOUCH)
-#define SIC_INTMASK_KEYPAD              (1 << SIC_INT_KEYPAD)
-#define SIC_INTMASK_DoC                 (1 << SIC_INT_DoC)
-#define SIC_INTMASK_MMCI0A              (1 << SIC_INT_MMCI0A)
-#define SIC_INTMASK_MMCI1A              (1 << SIC_INT_MMCI1A)
-#define SIC_INTMASK_AACI                (1 << SIC_INT_AACI)
-#define SIC_INTMASK_ETH                 (1 << SIC_INT_ETH)
-#define SIC_INTMASK_USB                 (1 << SIC_INT_USB)
-#define SIC_INTMASK_PCI0                (1 << SIC_INT_PCI0)
-#define SIC_INTMASK_PCI1                (1 << SIC_INT_PCI1)
-#define SIC_INTMASK_PCI2                (1 << SIC_INT_PCI2)
-#define SIC_INTMASK_PCI3                (1 << SIC_INT_PCI3)
-
 /* 
  *  Clean base - dummy
  * 
diff --git a/arch/arm/mach-w90x900/Kconfig b/arch/arm/mach-w90x900/Kconfig
new file mode 100644
index 000000000000..8e4178fe5ec2
--- /dev/null
+++ b/arch/arm/mach-w90x900/Kconfig
@@ -0,0 +1,19 @@
+if ARCH_W90X900
+
+config CPU_W90P910
+	bool
+	help
+	  Support for W90P910 of Nuvoton W90X900 CPUs.
+
+menu "W90P910 Machines"
+
+config MACH_W90P910EVB
+	bool "Nuvoton W90P910 Evaluation Board"
+	default y
+	select CPU_W90P910
+	help
+	   Say Y here if you are using the Nuvoton W90P910EVB
+
+endmenu
+
+endif
diff --git a/arch/arm/mach-w90x900/Makefile b/arch/arm/mach-w90x900/Makefile
new file mode 100644
index 000000000000..0c0c1d63f1c7
--- /dev/null
+++ b/arch/arm/mach-w90x900/Makefile
@@ -0,0 +1,15 @@
+#
+# Makefile for the linux kernel.
+#
+
+# Object file lists.
+
+obj-y				:= irq.o time.o
+
+# W90X900 CPU support files
+
+obj-$(CONFIG_CPU_W90P910)	+= w90p910.o
+
+# machine support
+
+obj-$(CONFIG_MACH_W90P910EVB)	+= mach-w90p910evb.o
diff --git a/arch/arm/mach-w90x900/Makefile.boot b/arch/arm/mach-w90x900/Makefile.boot
new file mode 100644
index 000000000000..a057b546b6e5
--- /dev/null
+++ b/arch/arm/mach-w90x900/Makefile.boot
@@ -0,0 +1,3 @@
+zreladdr-y	:= 0x00008000
+params_phys-y	:= 0x00000100
+
diff --git a/arch/arm/mach-w90x900/cpu.h b/arch/arm/mach-w90x900/cpu.h
new file mode 100644
index 000000000000..40ff40845df0
--- /dev/null
+++ b/arch/arm/mach-w90x900/cpu.h
@@ -0,0 +1,77 @@
+/*
+ * arch/arm/mach-w90x900/cpu.h
+ *
+ * Based on linux/include/asm-arm/plat-s3c24xx/cpu.h by Ben Dooks
+ *
+ * Copyright (c) 2008 Nuvoton technology corporation
+ * All rights reserved.
+ *
+ * Header file for W90X900 CPU support
+ *
+ * Wan ZongShun <mcuos.com@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#define IODESC_ENT(y)                                  \
+{                                                      \
+       .virtual = (unsigned long)W90X900_VA_##y,       \
+       .pfn     = __phys_to_pfn(W90X900_PA_##y),       \
+       .length  = W90X900_SZ_##y,                      \
+       .type    = MT_DEVICE,                           \
+}
+
+/*Cpu identifier register*/
+
+#define W90X900PDID	W90X900_VA_GCR
+#define W90P910_CPUID	0x02900910
+#define W90P920_CPUID	0x02900920
+#define W90P950_CPUID	0x02900950
+#define W90N960_CPUID	0x02900960
+
+struct w90x900_uartcfg;
+struct map_desc;
+struct sys_timer;
+
+/* core initialisation functions */
+
+extern void w90x900_init_irq(void);
+extern void w90p910_init_io(struct map_desc *mach_desc, int size);
+extern void w90p910_init_uarts(struct w90x900_uartcfg *cfg, int no);
+extern void w90p910_init_clocks(int xtal);
+extern void w90p910_map_io(struct map_desc *mach_desc, int size);
+extern struct sys_timer w90x900_timer;
+
+#define W90X900_RES(name)				\
+struct resource w90x900_##name##_resource[] = {		\
+	[0] = {						\
+		.start = name##_PA,			\
+		.end   = name##_PA + 0x0ff,		\
+		.flags = IORESOURCE_MEM,		\
+	},						\
+	[1] = {						\
+		.start = IRQ_##name,			\
+		.end   = IRQ_##name,			\
+		.flags = IORESOURCE_IRQ,		\
+	}						\
+}
+
+#define W90X900_DEVICE(devname, regname, devid, platdevname)		\
+struct platform_device w90x900_##devname = {				\
+	.name		= platdevname,					\
+	.id		= devid,					\
+	.num_resources 	= ARRAY_SIZE(w90x900_##regname##_resource),	\
+	.resource 	= w90x900_##regname##_resource,			\
+}
+
+#define W90X900_UARTCFG(port, flag, uc, ulc, ufc)	\
+{							\
+		.hwport	= port,				\
+		.flags	= flag,				\
+		.ucon	= uc,				\
+		.ulcon	= ulc,				\
+		.ufcon	= ufc,				\
+}
diff --git a/arch/arm/mach-w90x900/include/mach/entry-macro.S b/arch/arm/mach-w90x900/include/mach/entry-macro.S
new file mode 100644
index 000000000000..d39aca5be9ee
--- /dev/null
+++ b/arch/arm/mach-w90x900/include/mach/entry-macro.S
@@ -0,0 +1,34 @@
+/*
+ * arch/arm/mach-w90x900/include/mach/entry-macro.S
+ *
+ * Low-level IRQ helper macros for W90P910-based platforms
+ *
+ * This file is licensed under  the terms of the GNU General Public
+ * License version 2. This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
+ *
+ */
+
+#include <mach/hardware.h>
+#include <mach/regs-irq.h>
+
+	.macro  get_irqnr_preamble, base, tmp
+	.endm
+
+	.macro  arch_ret_to_user, tmp1, tmp2
+	.endm
+
+	.macro	get_irqnr_and_base, irqnr, irqstat, base, tmp
+
+		mov	\base, #AIC_BA
+
+		ldr	\irqnr, [ \base, #AIC_IPER]
+		ldr	\irqnr, [ \base, #AIC_ISNR]
+		cmp	\irqnr, #0
+
+	.endm
+
+	/* currently don't need an disable_fiq macro */
+
+	.macro	disable_fiq
+	.endm
diff --git a/arch/arm/mach-w90x900/include/mach/hardware.h b/arch/arm/mach-w90x900/include/mach/hardware.h
new file mode 100644
index 000000000000..fe3c6265a466
--- /dev/null
+++ b/arch/arm/mach-w90x900/include/mach/hardware.h
@@ -0,0 +1,24 @@
+/*
+ * arch/arm/mach-w90x900/include/mach/hardware.h
+ *
+ * Copyright (c) 2008 Nuvoton technology corporation
+ * All rights reserved.
+ *
+ * Wan ZongShun <mcuos.com@gmail.com>
+ *
+ * Based on arch/arm/mach-s3c2410/include/mach/hardware.h
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ */
+
+#ifndef __ASM_ARCH_HARDWARE_H
+#define __ASM_ARCH_HARDWARE_H
+
+#include <asm/sizes.h>
+#include <mach/map.h>
+
+#endif /* __ASM_ARCH_HARDWARE_H */
diff --git a/arch/arm/mach-w90x900/include/mach/io.h b/arch/arm/mach-w90x900/include/mach/io.h
new file mode 100644
index 000000000000..d96ab99df05b
--- /dev/null
+++ b/arch/arm/mach-w90x900/include/mach/io.h
@@ -0,0 +1,30 @@
+/*
+ * arch/arm/mach-w90x900/include/mach/io.h
+ *
+ * Copyright (c) 2008 Nuvoton technology corporation
+ * All rights reserved.
+ *
+ * Wan ZongShun <mcuos.com@gmail.com>
+ *
+ * Based on arch/arm/mach-s3c2410/include/mach/io.h
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ */
+
+#ifndef __ASM_ARM_ARCH_IO_H
+#define __ASM_ARM_ARCH_IO_H
+
+#define IO_SPACE_LIMIT	0xffffffff
+
+/*
+ * 1:1 mapping for ioremapped regions.
+ */
+
+#define __mem_pci(a)	(a)
+#define __io(a)		__typesafe_io(a)
+
+#endif
diff --git a/arch/arm/mach-w90x900/include/mach/irqs.h b/arch/arm/mach-w90x900/include/mach/irqs.h
new file mode 100644
index 000000000000..1c583f9cbcde
--- /dev/null
+++ b/arch/arm/mach-w90x900/include/mach/irqs.h
@@ -0,0 +1,45 @@
+/*
+ * arch/arm/mach-w90x900/include/mach/irqs.h
+ *
+ * Copyright (c) 2008 Nuvoton technology corporation
+ * All rights reserved.
+ *
+ * Wan ZongShun <mcuos.com@gmail.com>
+ *
+ * Based on arch/arm/mach-s3c2410/include/mach/irqs.h
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ */
+
+#ifndef __ASM_ARCH_IRQS_H
+#define __ASM_ARCH_IRQS_H
+
+/*
+ * we keep the first set of CPU IRQs out of the range of
+ * the ISA space, so that the PC104 has them to itself
+ * and we don't end up having to do horrible things to the
+ * standard ISA drivers....
+ *
+ */
+
+#define W90X900_IRQ(x)	(x)
+
+/* Main cpu interrupts */
+
+#define IRQ_WDT		W90X900_IRQ(1)
+#define IRQ_UART0	W90X900_IRQ(7)
+#define IRQ_UART1	W90X900_IRQ(8)
+#define IRQ_UART2	W90X900_IRQ(9)
+#define IRQ_UART3	W90X900_IRQ(10)
+#define IRQ_UART4	W90X900_IRQ(11)
+#define IRQ_TIMER0	W90X900_IRQ(12)
+#define IRQ_TIMER1	W90X900_IRQ(13)
+#define IRQ_T_INT_GROUP	W90X900_IRQ(14)
+#define IRQ_ADC		W90X900_IRQ(31)
+#define NR_IRQS		(IRQ_ADC+1)
+
+#endif /* __ASM_ARCH_IRQ_H */
diff --git a/arch/arm/mach-w90x900/include/mach/map.h b/arch/arm/mach-w90x900/include/mach/map.h
new file mode 100644
index 000000000000..79320ebe614b
--- /dev/null
+++ b/arch/arm/mach-w90x900/include/mach/map.h
@@ -0,0 +1,76 @@
+/*
+ * arch/arm/mach-w90x900/include/mach/map.h
+ *
+ * Copyright (c) 2008 Nuvoton technology corporation
+ * All rights reserved.
+ *
+ * Wan ZongShun <mcuos.com@gmail.com>
+ *
+ * Based on arch/arm/mach-s3c2410/include/mach/map.h
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ */
+
+#ifndef __ASM_ARCH_MAP_H
+#define __ASM_ARCH_MAP_H
+
+#ifndef __ASSEMBLY__
+#define W90X900_ADDR(x)		((void __iomem *)(0xF0000000 + (x)))
+#else
+#define W90X900_ADDR(x)		(0xF0000000 + (x))
+#endif
+
+#define AHB_IO_BASE		0xB0000000
+#define APB_IO_BASE		0xB8000000
+#define CLOCKPW_BASE		(APB_IO_BASE+0x200)
+#define AIC_IO_BASE		(APB_IO_BASE+0x2000)
+#define TIMER_IO_BASE		(APB_IO_BASE+0x1000)
+
+/*
+ * interrupt controller is the first thing we put in, to make
+ * the assembly code for the irq detection easier
+ */
+
+#define W90X900_VA_IRQ		W90X900_ADDR(0x00000000)
+#define W90X900_PA_IRQ		(0xB8002000)
+#define W90X900_SZ_IRQ		SZ_4K
+
+#define W90X900_VA_GCR		W90X900_ADDR(0x08002000)
+#define W90X900_PA_GCR		(0xB0000000)
+#define W90X900_SZ_GCR		SZ_4K
+
+/* Clock and Power management */
+
+#define W90X900_VA_CLKPWR	(W90X900_VA_GCR+0x200)
+#define W90X900_PA_CLKPWR	(0xB0000200)
+#define W90X900_SZ_CLKPWR	SZ_4K
+
+/* EBI management */
+
+#define W90X900_VA_EBI		W90X900_ADDR(0x00001000)
+#define W90X900_PA_EBI		(0xB0001000)
+#define W90X900_SZ_EBI		SZ_4K
+
+/* UARTs */
+
+#define W90X900_VA_UART		W90X900_ADDR(0x08000000)
+#define W90X900_PA_UART		(0xB8000000)
+#define W90X900_SZ_UART		SZ_4K
+
+/* Timers */
+
+#define W90X900_VA_TIMER	W90X900_ADDR(0x08001000)
+#define W90X900_PA_TIMER	(0xB8001000)
+#define W90X900_SZ_TIMER	SZ_4K
+
+/* GPIO ports */
+
+#define W90X900_VA_GPIO		W90X900_ADDR(0x08003000)
+#define W90X900_PA_GPIO		(0xB8003000)
+#define W90X900_SZ_GPIO		SZ_4K
+
+#endif /* __ASM_ARCH_MAP_H */
diff --git a/arch/arm/mach-w90x900/include/mach/memory.h b/arch/arm/mach-w90x900/include/mach/memory.h
new file mode 100644
index 000000000000..971b80702c27
--- /dev/null
+++ b/arch/arm/mach-w90x900/include/mach/memory.h
@@ -0,0 +1,23 @@
+/*
+ * arch/arm/mach-w90x900/include/mach/memory.h
+ *
+ * Copyright (c) 2008 Nuvoton technology corporation
+ * All rights reserved.
+ *
+ * Wan ZongShun <mcuos.com@gmail.com>
+ *
+ * Based on arch/arm/mach-s3c2410/include/mach/memory.h
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ */
+
+#ifndef __ASM_ARCH_MEMORY_H
+#define __ASM_ARCH_MEMORY_H
+
+#define PHYS_OFFSET	UL(0x00000000)
+
+#endif
diff --git a/arch/arm/mach-w90x900/include/mach/regs-irq.h b/arch/arm/mach-w90x900/include/mach/regs-irq.h
new file mode 100644
index 000000000000..8a3185fbc9cf
--- /dev/null
+++ b/arch/arm/mach-w90x900/include/mach/regs-irq.h
@@ -0,0 +1,51 @@
+/*
+ * arch/arm/mach-w90x900/include/mach/regs-irq.h
+ *
+ * Copyright (c) 2008 Nuvoton technology corporation
+ * All rights reserved.
+ *
+ * Wan ZongShun <mcuos.com@gmail.com>
+ *
+ * Based on arch/arm/mach-s3c2410/include/mach/regs-irq.h
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ */
+
+#ifndef ___ASM_ARCH_REGS_IRQ_H
+#define ___ASM_ARCH_REGS_IRQ_H
+
+/* Advance Interrupt Controller (AIC) Registers */
+
+#define AIC_BA    		W90X900_VA_IRQ
+
+#define REG_AIC_IRQSC		(AIC_BA+0x80)
+#define REG_AIC_GEN		(AIC_BA+0x84)
+#define REG_AIC_GASR		(AIC_BA+0x88)
+#define REG_AIC_GSCR		(AIC_BA+0x8C)
+#define REG_AIC_IRSR		(AIC_BA+0x100)
+#define REG_AIC_IASR		(AIC_BA+0x104)
+#define REG_AIC_ISR		(AIC_BA+0x108)
+#define REG_AIC_IPER		(AIC_BA+0x10C)
+#define REG_AIC_ISNR		(AIC_BA+0x110)
+#define REG_AIC_IMR		(AIC_BA+0x114)
+#define REG_AIC_OISR		(AIC_BA+0x118)
+#define REG_AIC_MECR		(AIC_BA+0x120)
+#define REG_AIC_MDCR		(AIC_BA+0x124)
+#define REG_AIC_SSCR		(AIC_BA+0x128)
+#define REG_AIC_SCCR		(AIC_BA+0x12C)
+#define REG_AIC_EOSCR		(AIC_BA+0x130)
+#define AIC_IPER		(0x10C)
+#define AIC_ISNR		(0x110)
+
+/*16-18 bits of REG_AIC_GEN define irq(2-4) group*/
+
+#define TIMER2_IRQ		(1 << 16)
+#define TIMER3_IRQ		(1 << 17)
+#define TIMER4_IRQ		(1 << 18)
+#define TIME_GROUP_IRQ		(TIMER2_IRQ|TIMER3_IRQ|TIMER4_IRQ)
+
+#endif /* ___ASM_ARCH_REGS_IRQ_H */
diff --git a/arch/arm/mach-w90x900/include/mach/regs-serial.h b/arch/arm/mach-w90x900/include/mach/regs-serial.h
new file mode 100644
index 000000000000..f08fa0d75e11
--- /dev/null
+++ b/arch/arm/mach-w90x900/include/mach/regs-serial.h
@@ -0,0 +1,59 @@
+/*
+ * arch/arm/mach-w90x900/include/mach/regs-serial.h
+ *
+ * Copyright (c) 2008 Nuvoton technology corporation
+ * All rights reserved.
+ *
+ * Wan ZongShun <mcuos.com@gmail.com>
+ *
+ * Based on arch/arm/mach-s3c2410/include/mach/regs-serial.h
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ */
+
+#ifndef __ASM_ARM_REGS_SERIAL_H
+#define __ASM_ARM_REGS_SERIAL_H
+
+#define UART0_BA	W90X900_VA_UART
+#define UART1_BA	(W90X900_VA_UART+0x100)
+#define UART2_BA	(W90X900_VA_UART+0x200)
+#define UART3_BA	(W90X900_VA_UART+0x300)
+#define UART4_BA	(W90X900_VA_UART+0x400)
+
+#define UART0_PA	W90X900_PA_UART
+#define UART1_PA	(W90X900_PA_UART+0x100)
+#define UART2_PA	(W90X900_PA_UART+0x200)
+#define UART3_PA	(W90X900_PA_UART+0x300)
+#define UART4_PA	(W90X900_PA_UART+0x400)
+
+#ifndef __ASSEMBLY__
+
+struct w90x900_uart_clksrc {
+	const char	*name;
+	unsigned int	divisor;
+	unsigned int	min_baud;
+	unsigned int	max_baud;
+};
+
+struct w90x900_uartcfg {
+	unsigned char	hwport;
+	unsigned char	unused;
+	unsigned short	flags;
+	unsigned long	uart_flags;
+
+	unsigned long	ucon;
+	unsigned long	ulcon;
+	unsigned long	ufcon;
+
+	struct w90x900_uart_clksrc *clocks;
+	unsigned int	clocks_size;
+};
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* __ASM_ARM_REGS_SERIAL_H */
+
diff --git a/arch/arm/mach-w90x900/include/mach/regs-timer.h b/arch/arm/mach-w90x900/include/mach/regs-timer.h
new file mode 100644
index 000000000000..8f390620c0e4
--- /dev/null
+++ b/arch/arm/mach-w90x900/include/mach/regs-timer.h
@@ -0,0 +1,42 @@
+/*
+ * arch/arm/mach-w90x900/include/mach/regs-timer.h
+ *
+ * Copyright (c) 2008 Nuvoton technology corporation
+ * All rights reserved.
+ *
+ * Wan ZongShun <mcuos.com@gmail.com>
+ *
+ * Based on arch/arm/mach-s3c2410/include/mach/regs-timer.h
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ */
+
+#ifndef __ASM_ARCH_REGS_TIMER_H
+#define __ASM_ARCH_REGS_TIMER_H
+
+/* Timer Registers */
+
+#define TMR_BA			W90X900_VA_TIMER
+#define REG_TCSR0		(TMR_BA+0x00)
+#define REG_TCSR1		(TMR_BA+0x04)
+#define REG_TICR0		(TMR_BA+0x08)
+#define REG_TICR1		(TMR_BA+0x0C)
+#define REG_TDR0		(TMR_BA+0x10)
+#define REG_TDR1		(TMR_BA+0x14)
+#define REG_TISR		(TMR_BA+0x18)
+#define REG_WTCR		(TMR_BA+0x1C)
+#define REG_TCSR2		(TMR_BA+0x20)
+#define REG_TCSR3		(TMR_BA+0x24)
+#define REG_TICR2		(TMR_BA+0x28)
+#define REG_TICR3		(TMR_BA+0x2C)
+#define REG_TDR2		(TMR_BA+0x30)
+#define REG_TDR3		(TMR_BA+0x34)
+#define REG_TCSR4		(TMR_BA+0x40)
+#define REG_TICR4		(TMR_BA+0x48)
+#define REG_TDR4		(TMR_BA+0x50)
+
+#endif /*  __ASM_ARCH_REGS_TIMER_H */
diff --git a/arch/arm/mach-w90x900/include/mach/system.h b/arch/arm/mach-w90x900/include/mach/system.h
new file mode 100644
index 000000000000..93753f922618
--- /dev/null
+++ b/arch/arm/mach-w90x900/include/mach/system.h
@@ -0,0 +1,28 @@
+/*
+ * arch/arm/mach-w90x900/include/mach/system.h
+ *
+ * Copyright (c) 2008 Nuvoton technology corporation
+ * All rights reserved.
+ *
+ * Wan ZongShun <mcuos.com@gmail.com>
+ *
+ * Based on arch/arm/mach-s3c2410/include/mach/system.h
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ */
+
+#include <asm/proc-fns.h>
+
+static void arch_idle(void)
+{
+}
+
+static void arch_reset(char mode)
+{
+	cpu_reset(0);
+}
+
diff --git a/arch/arm/mach-w90x900/include/mach/timex.h b/arch/arm/mach-w90x900/include/mach/timex.h
new file mode 100644
index 000000000000..164dce0b64db
--- /dev/null
+++ b/arch/arm/mach-w90x900/include/mach/timex.h
@@ -0,0 +1,25 @@
+/*
+ * arch/arm/mach-w90x900/include/mach/timex.h
+ *
+ * Copyright (c) 2008 Nuvoton technology corporation
+ * All rights reserved.
+ *
+ * Wan ZongShun <mcuos.com@gmail.com>
+ *
+ * Based on arch/arm/mach-s3c2410/include/mach/timex.h
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ */
+
+#ifndef __ASM_ARCH_TIMEX_H
+#define __ASM_ARCH_TIMEX_H
+
+/* CLOCK_TICK_RATE Now, I don't use it. */
+
+#define CLOCK_TICK_RATE 15000000
+
+#endif /* __ASM_ARCH_TIMEX_H */
diff --git a/arch/arm/mach-w90x900/include/mach/uncompress.h b/arch/arm/mach-w90x900/include/mach/uncompress.h
new file mode 100644
index 000000000000..050d9fe5ae1b
--- /dev/null
+++ b/arch/arm/mach-w90x900/include/mach/uncompress.h
@@ -0,0 +1,40 @@
+/*
+ * arch/arm/mach-w90x900/include/mach/uncompress.h
+ *
+ * Copyright (c) 2008 Nuvoton technology corporation
+ * All rights reserved.
+ *
+ * Wan ZongShun <mcuos.com@gmail.com>
+ *
+ * Based on arch/arm/mach-s3c2410/include/mach/uncompress.h
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ */
+
+#ifndef __ASM_ARCH_UNCOMPRESS_H
+#define __ASM_ARCH_UNCOMPRESS_H
+
+/* Defines for UART registers */
+
+#include <mach/regs-serial.h>
+#include <mach/map.h>
+
+#define arch_decomp_wdog()
+
+static void putc(int ch)
+{
+}
+
+static inline void flush(void)
+{
+}
+
+static void arch_decomp_setup(void)
+{
+}
+
+#endif/* __ASM_W90X900_UNCOMPRESS_H */
diff --git a/arch/arm/mach-w90x900/include/mach/vmalloc.h b/arch/arm/mach-w90x900/include/mach/vmalloc.h
new file mode 100644
index 000000000000..2f9dfb928533
--- /dev/null
+++ b/arch/arm/mach-w90x900/include/mach/vmalloc.h
@@ -0,0 +1,23 @@
+/*
+ * arch/arm/mach-w90x900/include/mach/vmalloc.h
+ *
+ * Copyright (c) 2008 Nuvoton technology corporation
+ * All rights reserved.
+ *
+ * Wan ZongShun <mcuos.com@gmail.com>
+ *
+ * Based on arch/arm/mach-s3c2410/include/mach/vmalloc.h
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ */
+
+#ifndef __ASM_ARCH_VMALLOC_H
+#define __ASM_ARCH_VMALLOC_H
+
+#define VMALLOC_END	  (0xE0000000)
+
+#endif /* __ASM_ARCH_VMALLOC_H */
diff --git a/arch/arm/mach-w90x900/irq.c b/arch/arm/mach-w90x900/irq.c
new file mode 100644
index 000000000000..0b4fc194729c
--- /dev/null
+++ b/arch/arm/mach-w90x900/irq.c
@@ -0,0 +1,76 @@
+/*
+ * linux/arch/arm/mach-w90x900/irq.c
+ *
+ * based on linux/arch/arm/plat-s3c24xx/irq.c by Ben Dooks
+ *
+ * Copyright (c) 2008 Nuvoton technology corporation
+ * All rights reserved.
+ *
+ * Wan ZongShun <mcuos.com@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ */
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/interrupt.h>
+#include <linux/ioport.h>
+#include <linux/ptrace.h>
+#include <linux/sysdev.h>
+#include <linux/io.h>
+
+#include <asm/irq.h>
+#include <asm/mach/irq.h>
+
+#include <mach/hardware.h>
+#include <mach/regs-irq.h>
+
+static void w90x900_irq_mask(unsigned int irq)
+{
+	__raw_writel(1 << irq, REG_AIC_MDCR);
+}
+
+/*
+ * By the w90p910 spec,any irq,only write 1
+ * to REG_AIC_EOSCR for ACK
+ */
+
+static void w90x900_irq_ack(unsigned int irq)
+{
+	__raw_writel(0x01, REG_AIC_EOSCR);
+}
+
+static void w90x900_irq_unmask(unsigned int irq)
+{
+	unsigned long mask;
+
+	if (irq == IRQ_T_INT_GROUP) {
+		mask = __raw_readl(REG_AIC_GEN);
+		__raw_writel(TIME_GROUP_IRQ | mask, REG_AIC_GEN);
+		__raw_writel(1 << IRQ_T_INT_GROUP, REG_AIC_MECR);
+	}
+	__raw_writel(1 << irq, REG_AIC_MECR);
+}
+
+static struct irq_chip w90x900_irq_chip = {
+	.ack	   = w90x900_irq_ack,
+	.mask	   = w90x900_irq_mask,
+	.unmask	   = w90x900_irq_unmask,
+};
+
+void __init w90x900_init_irq(void)
+{
+	int irqno;
+
+	__raw_writel(0xFFFFFFFE, REG_AIC_MDCR);
+
+	for (irqno = IRQ_WDT; irqno <= IRQ_ADC; irqno++) {
+		set_irq_chip(irqno, &w90x900_irq_chip);
+		set_irq_handler(irqno, handle_level_irq);
+		set_irq_flags(irqno, IRQF_VALID);
+	}
+}
diff --git a/arch/arm/mach-w90x900/mach-w90p910evb.c b/arch/arm/mach-w90x900/mach-w90p910evb.c
new file mode 100644
index 000000000000..9307a2475438
--- /dev/null
+++ b/arch/arm/mach-w90x900/mach-w90p910evb.c
@@ -0,0 +1,72 @@
+/*
+ * linux/arch/arm/mach-w90x900/mach-w90p910evb.c
+ *
+ * Based on mach-s3c2410/mach-smdk2410.c by Jonas Dietsche
+ *
+ * Copyright (C) 2008 Nuvoton technology corporation
+ * All rights reserved.
+ *
+ * Wan ZongShun <mcuos.com@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation; either version 2 of
+ * the License, or (at your option) any later version.
+ *
+ */
+
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/interrupt.h>
+#include <linux/list.h>
+#include <linux/timer.h>
+#include <linux/init.h>
+#include <linux/platform_device.h>
+
+#include <asm/mach/arch.h>
+#include <asm/mach/map.h>
+#include <asm/mach/irq.h>
+#include <asm/mach-types.h>
+
+#include <mach/regs-serial.h>
+
+#include "cpu.h"
+
+static struct map_desc w90p910_iodesc[] __initdata = {
+};
+
+static struct w90x900_uartcfg w90p910_uartcfgs[] = {
+	W90X900_UARTCFG(0, 0, 0, 0, 0),
+	W90X900_UARTCFG(1, 0, 0, 0, 0),
+	W90X900_UARTCFG(2, 0, 0, 0, 0),
+	W90X900_UARTCFG(3, 0, 0, 0, 0),
+	W90X900_UARTCFG(4, 0, 0, 0, 0),
+};
+
+/*Here should be your evb resourse,such as LCD*/
+
+static struct platform_device *w90p910evb_dev[] __initdata = {
+};
+
+static void __init w90p910evb_map_io(void)
+{
+	w90p910_map_io(w90p910_iodesc, ARRAY_SIZE(w90p910_iodesc));
+	w90p910_init_clocks(0);
+	w90p910_init_uarts(w90p910_uartcfgs, ARRAY_SIZE(w90p910_uartcfgs));
+}
+
+static void __init w90p910evb_init(void)
+{
+	platform_add_devices(w90p910evb_dev, ARRAY_SIZE(w90p910evb_dev));
+}
+
+MACHINE_START(W90P910EVB, "W90P910EVB")
+	/* Maintainer: Wan ZongShun */
+	.phys_io	= W90X900_PA_UART,
+	.io_pg_offst	= (((u32)W90X900_VA_UART) >> 18) & 0xfffc,
+	.boot_params	= 0,
+	.map_io		= w90p910evb_map_io,
+	.init_irq	= w90x900_init_irq,
+	.init_machine	= w90p910evb_init,
+	.timer		= &w90x900_timer,
+MACHINE_END
diff --git a/arch/arm/mach-w90x900/time.c b/arch/arm/mach-w90x900/time.c
new file mode 100644
index 000000000000..3a69e381f316
--- /dev/null
+++ b/arch/arm/mach-w90x900/time.c
@@ -0,0 +1,80 @@
+/*
+ * linux/arch/arm/mach-w90x900/time.c
+ *
+ * Based on linux/arch/arm/plat-s3c24xx/time.c by Ben Dooks
+ *
+ * Copyright (c) 2008 Nuvoton technology corporation
+ * All rights reserved.
+ *
+ * Wan ZongShun <mcuos.com@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ */
+
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/err.h>
+#include <linux/clk.h>
+#include <linux/io.h>
+#include <linux/leds.h>
+
+#include <asm/mach-types.h>
+#include <asm/mach/irq.h>
+#include <asm/mach/time.h>
+
+#include <mach/system.h>
+#include <mach/map.h>
+#include <mach/regs-timer.h>
+
+static unsigned long w90x900_gettimeoffset(void)
+{
+	return 0;
+}
+
+/*IRQ handler for the timer*/
+
+static irqreturn_t
+w90x900_timer_interrupt(int irq, void *dev_id)
+{
+	timer_tick();
+	__raw_writel(0x01, REG_TISR); /* clear TIF0 */
+	return IRQ_HANDLED;
+}
+
+static struct irqaction w90x900_timer_irq = {
+	.name		= "w90x900 Timer Tick",
+	.flags		= IRQF_DISABLED | IRQF_TIMER | IRQF_IRQPOLL,
+	.handler	= w90x900_timer_interrupt,
+};
+
+/*Set up timer reg.*/
+
+static void w90x900_timer_setup(void)
+{
+	__raw_writel(0, REG_TCSR0);
+	__raw_writel(0, REG_TCSR1);
+	__raw_writel(0, REG_TCSR2);
+	__raw_writel(0, REG_TCSR3);
+	__raw_writel(0, REG_TCSR4);
+	__raw_writel(0x1F, REG_TISR);
+	__raw_writel(15000000/(100 * 100), REG_TICR0);
+	__raw_writel(0x68000063, REG_TCSR0);
+}
+
+static void __init w90x900_timer_init(void)
+{
+	w90x900_timer_setup();
+	setup_irq(IRQ_TIMER0, &w90x900_timer_irq);
+}
+
+struct sys_timer w90x900_timer = {
+	.init		= w90x900_timer_init,
+	.offset		= w90x900_gettimeoffset,
+	.resume		= w90x900_timer_setup
+};
diff --git a/arch/arm/mach-w90x900/w90p910.c b/arch/arm/mach-w90x900/w90p910.c
new file mode 100644
index 000000000000..aa783bc94310
--- /dev/null
+++ b/arch/arm/mach-w90x900/w90p910.c
@@ -0,0 +1,134 @@
+/*
+ * linux/arch/arm/mach-w90x900/w90p910.c
+ *
+ * Based on linux/arch/arm/plat-s3c24xx/s3c244x.c by Ben Dooks
+ *
+ * Copyright (c) 2008 Nuvoton technology corporation
+ * All rights reserved.
+ *
+ * Wan ZongShun <mcuos.com@gmail.com>
+ *
+ * W90P910 cpu support
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ */
+
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/interrupt.h>
+#include <linux/list.h>
+#include <linux/timer.h>
+#include <linux/init.h>
+#include <linux/platform_device.h>
+#include <linux/io.h>
+
+#include <asm/mach/arch.h>
+#include <asm/mach/map.h>
+#include <asm/mach/irq.h>
+#include <asm/irq.h>
+
+#include <mach/hardware.h>
+#include <mach/regs-serial.h>
+
+#include "cpu.h"
+
+/*W90P910 has five uarts*/
+
+#define MAX_UART_COUNT 5
+static int uart_count;
+static struct platform_device *uart_devs[MAX_UART_COUNT-1];
+
+/* Initial IO mappings */
+
+static struct map_desc w90p910_iodesc[] __initdata = {
+	IODESC_ENT(IRQ),
+	IODESC_ENT(GCR),
+	IODESC_ENT(UART),
+	IODESC_ENT(TIMER),
+	IODESC_ENT(EBI),
+	/*IODESC_ENT(LCD),*/
+};
+
+/*Init the dev resource*/
+
+static W90X900_RES(UART0);
+static W90X900_RES(UART1);
+static W90X900_RES(UART2);
+static W90X900_RES(UART3);
+static W90X900_RES(UART4);
+static W90X900_DEVICE(uart0, UART0, 0, "w90x900-uart");
+static W90X900_DEVICE(uart1, UART1, 1, "w90x900-uart");
+static W90X900_DEVICE(uart2, UART2, 2, "w90x900-uart");
+static W90X900_DEVICE(uart3, UART3, 3, "w90x900-uart");
+static W90X900_DEVICE(uart4, UART4, 4, "w90x900-uart");
+
+static struct platform_device *uart_devices[] __initdata = {
+	&w90x900_uart0,
+	&w90x900_uart1,
+	&w90x900_uart2,
+	&w90x900_uart3,
+	&w90x900_uart4
+};
+
+/*Init W90P910 uart device*/
+
+void __init w90p910_init_uarts(struct w90x900_uartcfg *cfg, int no)
+{
+	struct platform_device *platdev;
+	int uart, uartdev;
+
+	/*By min() to judge count of uart be used indeed*/
+
+	uartdev = ARRAY_SIZE(uart_devices);
+	no = min(uartdev, no);
+
+	for (uart = 0; uart < no; uart++, cfg++) {
+		if (cfg->hwport != uart)
+			printk(KERN_ERR "w90x900_uartcfg[%d] error\n", uart);
+		platdev = uart_devices[cfg->hwport];
+		uart_devs[uart] = platdev;
+		platdev->dev.platform_data = cfg;
+	}
+	uart_count = uart;
+}
+
+/*Init W90P910 evb io*/
+
+void __init w90p910_map_io(struct map_desc *mach_desc, int mach_size)
+{
+	unsigned long idcode = 0x0;
+
+	iotable_init(w90p910_iodesc, ARRAY_SIZE(w90p910_iodesc));
+
+	idcode = __raw_readl(W90X900PDID);
+	if (idcode != W90P910_CPUID)
+		printk(KERN_ERR "CPU type 0x%08lx is not W90P910\n", idcode);
+}
+
+/*Init W90P910 clock*/
+
+void __init w90p910_init_clocks(int xtal)
+{
+}
+
+static int __init w90p910_init_cpu(void)
+{
+	return 0;
+}
+
+static int __init w90x900_arch_init(void)
+{
+	int ret;
+
+	ret = w90p910_init_cpu();
+	if (ret != 0)
+		return ret;
+
+	return platform_add_devices(uart_devs, uart_count);
+
+}
+arch_initcall(w90x900_arch_init);
diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig
index ab5f7a21350b..d490f3773c01 100644
--- a/arch/arm/mm/Kconfig
+++ b/arch/arm/mm/Kconfig
@@ -10,8 +10,7 @@ config CPU_32
 
 # ARM610
 config CPU_ARM610
-	bool "Support ARM610 processor"
-	depends on ARCH_RPC
+	bool "Support ARM610 processor" if ARCH_RPC
 	select CPU_32v3
 	select CPU_CACHE_V3
 	select CPU_CACHE_VIVT
@@ -43,8 +42,7 @@ config CPU_ARM7TDMI
 
 # ARM710
 config CPU_ARM710
-	bool "Support ARM710 processor" if !ARCH_CLPS7500 && ARCH_RPC
-	default y if ARCH_CLPS7500
+	bool "Support ARM710 processor" if ARCH_RPC
 	select CPU_32v3
 	select CPU_CACHE_V3
 	select CPU_CACHE_VIVT
@@ -63,8 +61,7 @@ config CPU_ARM710
 
 # ARM720T
 config CPU_ARM720T
-	bool "Support ARM720T processor" if !ARCH_CLPS711X && !ARCH_L7200 && !ARCH_CDB89712 && ARCH_INTEGRATOR
-	default y if ARCH_CLPS711X || ARCH_L7200 || ARCH_CDB89712 || ARCH_H720X
+	bool "Support ARM720T processor" if ARCH_INTEGRATOR
 	select CPU_32v4T
 	select CPU_ABRT_LV4T
 	select CPU_PABRT_NOIFAR
@@ -114,9 +111,7 @@ config CPU_ARM9TDMI
 
 # ARM920T
 config CPU_ARM920T
-	bool "Support ARM920T processor"
-	depends on ARCH_EP93XX || ARCH_INTEGRATOR || CPU_S3C2410 || CPU_S3C2440 || CPU_S3C2442 || ARCH_IMX || ARCH_AAEC2000 || ARCH_AT91RM9200
-	default y if CPU_S3C2410 || CPU_S3C2440 || CPU_S3C2442 || ARCH_AT91RM9200
+	bool "Support ARM920T processor" if ARCH_INTEGRATOR
 	select CPU_32v4T
 	select CPU_ABRT_EV4T
 	select CPU_PABRT_NOIFAR
@@ -138,8 +133,6 @@ config CPU_ARM920T
 # ARM922T
 config CPU_ARM922T
 	bool "Support ARM922T processor" if ARCH_INTEGRATOR
-	depends on ARCH_LH7A40X || ARCH_INTEGRATOR || ARCH_KS8695
-	default y if ARCH_LH7A40X || ARCH_KS8695
 	select CPU_32v4T
 	select CPU_ABRT_EV4T
 	select CPU_PABRT_NOIFAR
@@ -159,8 +152,6 @@ config CPU_ARM922T
 # ARM925T
 config CPU_ARM925T
  	bool "Support ARM925T processor" if ARCH_OMAP1
- 	depends on ARCH_OMAP15XX
- 	default y if ARCH_OMAP15XX
 	select CPU_32v4T
 	select CPU_ABRT_EV4T
 	select CPU_PABRT_NOIFAR
@@ -179,22 +170,7 @@ config CPU_ARM925T
 
 # ARM926T
 config CPU_ARM926T
-	bool "Support ARM926T processor"
-	depends on ARCH_INTEGRATOR || ARCH_VERSATILE_PB || \
-		MACH_VERSATILE_AB || ARCH_OMAP730 || \
-		ARCH_OMAP16XX || MACH_REALVIEW_EB || \
-		ARCH_PNX4008 || ARCH_NETX || CPU_S3C2412 || \
-		ARCH_AT91SAM9260 || ARCH_AT91SAM9261 || \
-		ARCH_AT91SAM9263 || ARCH_AT91SAM9RL || \
-		ARCH_AT91SAM9G20 || ARCH_AT91CAP9 || \
-		ARCH_NS9XXX || ARCH_DAVINCI || ARCH_MX2
-	default y if ARCH_VERSATILE_PB || MACH_VERSATILE_AB || \
-		ARCH_OMAP730 || ARCH_OMAP16XX || \
-		ARCH_PNX4008 || ARCH_NETX || CPU_S3C2412 || \
-		ARCH_AT91SAM9260 || ARCH_AT91SAM9261 || \
-		ARCH_AT91SAM9263 || ARCH_AT91SAM9RL || \
-		ARCH_AT91SAM9G20 || ARCH_AT91CAP9 || \
-		ARCH_NS9XXX || ARCH_DAVINCI || ARCH_MX2
+	bool "Support ARM926T processor" if ARCH_INTEGRATOR || MACH_REALVIEW_EB
 	select CPU_32v5
 	select CPU_ABRT_EV5TJ
 	select CPU_PABRT_NOIFAR
@@ -247,8 +223,7 @@ config CPU_ARM946E
 
 # ARM1020 - needs validating
 config CPU_ARM1020
-	bool "Support ARM1020T (rev 0) processor"
-	depends on ARCH_INTEGRATOR
+	bool "Support ARM1020T (rev 0) processor" if ARCH_INTEGRATOR
 	select CPU_32v5
 	select CPU_ABRT_EV4T
 	select CPU_PABRT_NOIFAR
@@ -266,8 +241,7 @@ config CPU_ARM1020
 
 # ARM1020E - needs validating
 config CPU_ARM1020E
-	bool "Support ARM1020E processor"
-	depends on ARCH_INTEGRATOR
+	bool "Support ARM1020E processor" if ARCH_INTEGRATOR
 	select CPU_32v5
 	select CPU_ABRT_EV4T
 	select CPU_PABRT_NOIFAR
@@ -280,8 +254,7 @@ config CPU_ARM1020E
 
 # ARM1022E
 config CPU_ARM1022
-	bool "Support ARM1022E processor"
-	depends on ARCH_INTEGRATOR
+	bool "Support ARM1022E processor" if ARCH_INTEGRATOR
 	select CPU_32v5
 	select CPU_ABRT_EV4T
 	select CPU_PABRT_NOIFAR
@@ -299,8 +272,7 @@ config CPU_ARM1022
 
 # ARM1026EJ-S
 config CPU_ARM1026
-	bool "Support ARM1026EJ-S processor"
-	depends on ARCH_INTEGRATOR
+	bool "Support ARM1026EJ-S processor" if ARCH_INTEGRATOR
 	select CPU_32v5
 	select CPU_ABRT_EV5T # But need Jazelle, but EV5TJ ignores bit 10
 	select CPU_PABRT_NOIFAR
@@ -317,8 +289,7 @@ config CPU_ARM1026
 
 # SA110
 config CPU_SA110
-	bool "Support StrongARM(R) SA-110 processor" if !ARCH_EBSA110 && !FOOTBRIDGE && !ARCH_TBOX && !ARCH_SHARK && !ARCH_NEXUSPCI && ARCH_RPC
-	default y if ARCH_EBSA110 || FOOTBRIDGE || ARCH_TBOX || ARCH_SHARK || ARCH_NEXUSPCI
+	bool "Support StrongARM(R) SA-110 processor" if ARCH_RPC
 	select CPU_32v3 if ARCH_RPC
 	select CPU_32v4 if !ARCH_RPC
 	select CPU_ABRT_EV4
@@ -340,8 +311,6 @@ config CPU_SA110
 # SA1100
 config CPU_SA1100
 	bool
-	depends on ARCH_SA1100
-	default y
 	select CPU_32v4
 	select CPU_ABRT_EV4
 	select CPU_PABRT_NOIFAR
@@ -353,8 +322,6 @@ config CPU_SA1100
 # XScale
 config CPU_XSCALE
 	bool
-	depends on ARCH_IOP32X || ARCH_IOP33X || PXA25x || PXA27x || ARCH_IXP4XX || ARCH_IXP2000
-	default y
 	select CPU_32v5
 	select CPU_ABRT_EV5T
 	select CPU_PABRT_NOIFAR
@@ -365,8 +332,6 @@ config CPU_XSCALE
 # XScale Core Version 3
 config CPU_XSC3
 	bool
-	depends on ARCH_IXP23XX || ARCH_IOP13XX || PXA3xx
-	default y
 	select CPU_32v5
 	select CPU_ABRT_EV5T
 	select CPU_PABRT_NOIFAR
@@ -378,8 +343,6 @@ config CPU_XSC3
 # Feroceon
 config CPU_FEROCEON
 	bool
-	depends on ARCH_ORION5X || ARCH_LOKI || ARCH_KIRKWOOD || ARCH_MV78XX0
-	default y
 	select CPU_32v5
 	select CPU_ABRT_EV5T
 	select CPU_PABRT_NOIFAR
@@ -399,10 +362,7 @@ config CPU_FEROCEON_OLD_ID
 
 # ARMv6
 config CPU_V6
-	bool "Support ARM V6 processor"
-	depends on ARCH_INTEGRATOR || MACH_REALVIEW_EB || ARCH_OMAP2 || ARCH_MX3 || ARCH_MSM || MACH_REALVIEW_PB11MP || MACH_REALVIEW_PB1176
-	default y if ARCH_MX3
-	default y if ARCH_MSM
+	bool "Support ARM V6 processor" if ARCH_INTEGRATOR || MACH_REALVIEW_EB
 	select CPU_32v6
 	select CPU_ABRT_EV6
 	select CPU_PABRT_NOIFAR
@@ -427,8 +387,7 @@ config CPU_32v6K
 
 # ARMv7
 config CPU_V7
-	bool "Support ARM V7 processor"
-	depends on ARCH_INTEGRATOR || MACH_REALVIEW_EB || ARCH_OMAP3
+	bool "Support ARM V7 processor" if ARCH_INTEGRATOR || MACH_REALVIEW_EB
 	select CPU_32v6K
 	select CPU_32v7
 	select CPU_ABRT_EV7
@@ -745,7 +704,7 @@ config CACHE_FEROCEON_L2_WRITETHROUGH
 
 config CACHE_L2X0
 	bool "Enable the L2x0 outer cache controller"
-	depends on REALVIEW_EB_ARM11MP || MACH_REALVIEW_PB11MP || MACH_REALVIEW_PB1176
+	depends on REALVIEW_EB_ARM11MP || MACH_REALVIEW_PB11MP || MACH_REALVIEW_PB1176 || REALVIEW_EB_A9MP
 	default y
 	select OUTER_CACHE
 	help
diff --git a/arch/arm/mm/alignment.c b/arch/arm/mm/alignment.c
index 133e65d166b3..3a398befed41 100644
--- a/arch/arm/mm/alignment.c
+++ b/arch/arm/mm/alignment.c
@@ -17,6 +17,7 @@
 #include <linux/string.h>
 #include <linux/proc_fs.h>
 #include <linux/init.h>
+#include <linux/sched.h>
 #include <linux/uaccess.h>
 
 #include <asm/unaligned.h>
@@ -70,6 +71,10 @@ static unsigned long ai_dword;
 static unsigned long ai_multi;
 static int ai_usermode;
 
+#define UM_WARN		(1 << 0)
+#define UM_FIXUP	(1 << 1)
+#define UM_SIGNAL	(1 << 2)
+
 #ifdef CONFIG_PROC_FS
 static const char *usermode_action[] = {
 	"ignored",
@@ -754,7 +759,7 @@ do_alignment(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
  user:
 	ai_user += 1;
 
-	if (ai_usermode & 1)
+	if (ai_usermode & UM_WARN)
 		printk("Alignment trap: %s (%d) PC=0x%08lx Instr=0x%0*lx "
 		       "Address=0x%08lx FSR 0x%03x\n", current->comm,
 			task_pid_nr(current), instrptr,
@@ -762,10 +767,10 @@ do_alignment(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 		        thumb_mode(regs) ? tinstr : instr,
 		        addr, fsr);
 
-	if (ai_usermode & 2)
+	if (ai_usermode & UM_FIXUP)
 		goto fixup;
 
-	if (ai_usermode & 4)
+	if (ai_usermode & UM_SIGNAL)
 		force_sig(SIGBUS, current);
 	else
 		set_cr(cr_no_alignment);
@@ -796,6 +801,22 @@ static int __init alignment_init(void)
 	res->write_proc = proc_alignment_write;
 #endif
 
+	/*
+	 * ARMv6 and later CPUs can perform unaligned accesses for
+	 * most single load and store instructions up to word size.
+	 * LDM, STM, LDRD and STRD still need to be handled.
+	 *
+	 * Ignoring the alignment fault is not an option on these
+	 * CPUs since we spin re-faulting the instruction without
+	 * making any progress.
+	 */
+	if (cpu_architecture() >= CPU_ARCH_ARMv6 && (cr_alignment & CR_U)) {
+		cr_alignment &= ~CR_A;
+		cr_no_alignment &= ~CR_A;
+		set_cr(cr_alignment);
+		ai_usermode = UM_FIXUP;
+	}
+
 	hook_fault_code(1, do_alignment, SIGILL, "alignment exception");
 	hook_fault_code(3, do_alignment, SIGILL, "alignment exception");
 
diff --git a/arch/arm/mm/cache-v3.S b/arch/arm/mm/cache-v3.S
index 3b3639eb7ca5..8a4abebc478a 100644
--- a/arch/arm/mm/cache-v3.S
+++ b/arch/arm/mm/cache-v3.S
@@ -9,7 +9,6 @@
  */
 #include <linux/linkage.h>
 #include <linux/init.h>
-#include <mach/hardware.h>
 #include <asm/page.h>
 #include "proc-macros.S"
 
diff --git a/arch/arm/mm/cache-v4.S b/arch/arm/mm/cache-v4.S
index 5786adf10040..3668611cb400 100644
--- a/arch/arm/mm/cache-v4.S
+++ b/arch/arm/mm/cache-v4.S
@@ -9,7 +9,6 @@
  */
 #include <linux/linkage.h>
 #include <linux/init.h>
-#include <mach/hardware.h>
 #include <asm/page.h>
 #include "proc-macros.S"
 
diff --git a/arch/arm/mm/cache-v4wt.S b/arch/arm/mm/cache-v4wt.S
index 51a9b0b273b6..c54fa2cc40e6 100644
--- a/arch/arm/mm/cache-v4wt.S
+++ b/arch/arm/mm/cache-v4wt.S
@@ -13,7 +13,6 @@
  */
 #include <linux/linkage.h>
 #include <linux/init.h>
-#include <mach/hardware.h>
 #include <asm/page.h>
 #include "proc-macros.S"
 
diff --git a/arch/arm/mm/cache-v7.S b/arch/arm/mm/cache-v7.S
index d19c2bec2b1f..be93ff02a98d 100644
--- a/arch/arm/mm/cache-v7.S
+++ b/arch/arm/mm/cache-v7.S
@@ -26,6 +26,7 @@
  *	- mm    - mm_struct describing address space
  */
 ENTRY(v7_flush_dcache_all)
+	dmb					@ ensure ordering with previous memory accesses
 	mrc	p15, 1, r0, c0, c0, 1		@ read clidr
 	ands	r3, r0, #0x7000000		@ extract loc from clidr
 	mov	r3, r3, lsr #23			@ left align loc bit field
@@ -64,6 +65,7 @@ skip:
 finished:
 	mov	r10, #0				@ swith back to cache level 0
 	mcr	p15, 2, r10, c0, c0, 0		@ select current cache level in cssr
+	dsb
 	isb
 	mov	pc, lr
 ENDPROC(v7_flush_dcache_all)
diff --git a/arch/arm/mm/copypage-feroceon.S b/arch/arm/mm/copypage-feroceon.S
deleted file mode 100644
index 7eb0d320d240..000000000000
--- a/arch/arm/mm/copypage-feroceon.S
+++ /dev/null
@@ -1,95 +0,0 @@
-/*
- *  linux/arch/arm/lib/copypage-feroceon.S
- *
- *  Copyright (C) 2008 Marvell Semiconductors
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This handles copy_user_page and clear_user_page on Feroceon
- * more optimally than the generic implementations.
- */
-#include <linux/linkage.h>
-#include <linux/init.h>
-#include <asm/asm-offsets.h>
-
-	.text
-	.align	5
-
-ENTRY(feroceon_copy_user_page)
-	stmfd	sp!, {r4-r9, lr}
-	mov	ip, #PAGE_SZ
-1:	mov	lr, r1
-	ldmia	r1!, {r2 - r9}
-	pld	[lr, #32]
-	pld	[lr, #64]
-	pld	[lr, #96]
-	pld	[lr, #128]
-	pld	[lr, #160]
-	pld	[lr, #192]
-	pld	[lr, #224]
-	stmia	r0, {r2 - r9}
-	ldmia	r1!, {r2 - r9}
-	mcr	p15, 0, r0, c7, c14, 1		@ clean and invalidate D line
-	add	r0, r0, #32
-	stmia	r0, {r2 - r9}
-	ldmia	r1!, {r2 - r9}
-	mcr	p15, 0, r0, c7, c14, 1		@ clean and invalidate D line
-	add	r0, r0, #32
-	stmia	r0, {r2 - r9}
-	ldmia	r1!, {r2 - r9}
-	mcr	p15, 0, r0, c7, c14, 1		@ clean and invalidate D line
-	add	r0, r0, #32
-	stmia	r0, {r2 - r9}
-	ldmia	r1!, {r2 - r9}
-	mcr	p15, 0, r0, c7, c14, 1		@ clean and invalidate D line
-	add	r0, r0, #32
-	stmia	r0, {r2 - r9}
-	ldmia	r1!, {r2 - r9}
-	mcr	p15, 0, r0, c7, c14, 1		@ clean and invalidate D line
-	add	r0, r0, #32
-	stmia	r0, {r2 - r9}
-	ldmia	r1!, {r2 - r9}
-	mcr	p15, 0, r0, c7, c14, 1		@ clean and invalidate D line
-	add	r0, r0, #32
-	stmia	r0, {r2 - r9}
-	ldmia	r1!, {r2 - r9}
-	mcr	p15, 0, r0, c7, c14, 1		@ clean and invalidate D line
-	add	r0, r0, #32
-	stmia	r0, {r2 - r9}
-	subs	ip, ip, #(32 * 8)
-	mcr	p15, 0, r0, c7, c14, 1		@ clean and invalidate D line
-	add	r0, r0, #32
-	bne	1b
-	mcr	p15, 0, ip, c7, c10, 4		@ drain WB
-	ldmfd	sp!, {r4-r9, pc}
-
-	.align	5
-
-ENTRY(feroceon_clear_user_page)
-	stmfd	sp!, {r4-r7, lr}
-	mov	r1, #PAGE_SZ/32
-	mov	r2, #0
-	mov	r3, #0
-	mov	r4, #0
-	mov	r5, #0
-	mov	r6, #0
-	mov	r7, #0
-	mov	ip, #0
-	mov	lr, #0
-1:	stmia	r0, {r2-r7, ip, lr}
-	subs	r1, r1, #1
-	mcr	p15, 0, r0, c7, c14, 1		@ clean and invalidate D line
-	add	r0, r0, #32
-	bne	1b
-	mcr	p15, 0, r1, c7, c10, 4		@ drain WB
-	ldmfd	sp!, {r4-r7, pc}
-
-	__INITDATA
-
-	.type	feroceon_user_fns, #object
-ENTRY(feroceon_user_fns)
-	.long	feroceon_clear_user_page
-	.long	feroceon_copy_user_page
-	.size	feroceon_user_fns, . - feroceon_user_fns
diff --git a/arch/arm/mm/copypage-feroceon.c b/arch/arm/mm/copypage-feroceon.c
new file mode 100644
index 000000000000..c3ba6a94da0c
--- /dev/null
+++ b/arch/arm/mm/copypage-feroceon.c
@@ -0,0 +1,111 @@
+/*
+ *  linux/arch/arm/mm/copypage-feroceon.S
+ *
+ *  Copyright (C) 2008 Marvell Semiconductors
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This handles copy_user_highpage and clear_user_page on Feroceon
+ * more optimally than the generic implementations.
+ */
+#include <linux/init.h>
+#include <linux/highmem.h>
+
+static void __attribute__((naked))
+feroceon_copy_user_page(void *kto, const void *kfrom)
+{
+	asm("\
+	stmfd	sp!, {r4-r9, lr}		\n\
+	mov	ip, %0				\n\
+1:	mov	lr, r1				\n\
+	ldmia	r1!, {r2 - r9}			\n\
+	pld	[lr, #32]			\n\
+	pld	[lr, #64]			\n\
+	pld	[lr, #96]			\n\
+	pld	[lr, #128]			\n\
+	pld	[lr, #160]			\n\
+	pld	[lr, #192]			\n\
+	pld	[lr, #224]			\n\
+	stmia	r0, {r2 - r9}			\n\
+	ldmia	r1!, {r2 - r9}			\n\
+	mcr	p15, 0, r0, c7, c14, 1		@ clean and invalidate D line\n\
+	add	r0, r0, #32			\n\
+	stmia	r0, {r2 - r9}			\n\
+	ldmia	r1!, {r2 - r9}			\n\
+	mcr	p15, 0, r0, c7, c14, 1		@ clean and invalidate D line\n\
+	add	r0, r0, #32			\n\
+	stmia	r0, {r2 - r9}			\n\
+	ldmia	r1!, {r2 - r9}			\n\
+	mcr	p15, 0, r0, c7, c14, 1		@ clean and invalidate D line\n\
+	add	r0, r0, #32			\n\
+	stmia	r0, {r2 - r9}			\n\
+	ldmia	r1!, {r2 - r9}			\n\
+	mcr	p15, 0, r0, c7, c14, 1		@ clean and invalidate D line\n\
+	add	r0, r0, #32			\n\
+	stmia	r0, {r2 - r9}			\n\
+	ldmia	r1!, {r2 - r9}			\n\
+	mcr	p15, 0, r0, c7, c14, 1		@ clean and invalidate D line\n\
+	add	r0, r0, #32			\n\
+	stmia	r0, {r2 - r9}			\n\
+	ldmia	r1!, {r2 - r9}			\n\
+	mcr	p15, 0, r0, c7, c14, 1		@ clean and invalidate D line\n\
+	add	r0, r0, #32			\n\
+	stmia	r0, {r2 - r9}			\n\
+	ldmia	r1!, {r2 - r9}			\n\
+	mcr	p15, 0, r0, c7, c14, 1		@ clean and invalidate D line\n\
+	add	r0, r0, #32			\n\
+	stmia	r0, {r2 - r9}			\n\
+	subs	ip, ip, #(32 * 8)		\n\
+	mcr	p15, 0, r0, c7, c14, 1		@ clean and invalidate D line\n\
+	add	r0, r0, #32			\n\
+	bne	1b				\n\
+	mcr	p15, 0, ip, c7, c10, 4		@ drain WB\n\
+	ldmfd	sp!, {r4-r9, pc}"
+	:
+	: "I" (PAGE_SIZE));
+}
+
+void feroceon_copy_user_highpage(struct page *to, struct page *from,
+	unsigned long vaddr)
+{
+	void *kto, *kfrom;
+
+	kto = kmap_atomic(to, KM_USER0);
+	kfrom = kmap_atomic(from, KM_USER1);
+	feroceon_copy_user_page(kto, kfrom);
+	kunmap_atomic(kfrom, KM_USER1);
+	kunmap_atomic(kto, KM_USER0);
+}
+
+void feroceon_clear_user_highpage(struct page *page, unsigned long vaddr)
+{
+	void *ptr, *kaddr = kmap_atomic(page, KM_USER0);
+	asm volatile ("\
+	mov	r1, %2				\n\
+	mov	r2, #0				\n\
+	mov	r3, #0				\n\
+	mov	r4, #0				\n\
+	mov	r5, #0				\n\
+	mov	r6, #0				\n\
+	mov	r7, #0				\n\
+	mov	ip, #0				\n\
+	mov	lr, #0				\n\
+1:	stmia	%0, {r2-r7, ip, lr}		\n\
+	subs	r1, r1, #1			\n\
+	mcr	p15, 0, %0, c7, c14, 1		@ clean and invalidate D line\n\
+	add	%0, %0, #32			\n\
+	bne	1b				\n\
+	mcr	p15, 0, r1, c7, c10, 4		@ drain WB"
+	: "=r" (ptr)
+	: "0" (kaddr), "I" (PAGE_SIZE / 32)
+	: "r1", "r2", "r3", "r4", "r5", "r6", "r7", "ip", "lr");
+	kunmap_atomic(kaddr, KM_USER0);
+}
+
+struct cpu_user_fns feroceon_user_fns __initdata = {
+	.cpu_clear_user_highpage = feroceon_clear_user_highpage,
+	.cpu_copy_user_highpage	= feroceon_copy_user_highpage,
+};
+
diff --git a/arch/arm/mm/copypage-v3.S b/arch/arm/mm/copypage-v3.S
deleted file mode 100644
index 2ee394b11bcb..000000000000
--- a/arch/arm/mm/copypage-v3.S
+++ /dev/null
@@ -1,67 +0,0 @@
-/*
- *  linux/arch/arm/lib/copypage.S
- *
- *  Copyright (C) 1995-1999 Russell King
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- *  ASM optimised string functions
- */
-#include <linux/linkage.h>
-#include <linux/init.h>
-#include <asm/assembler.h>
-#include <asm/asm-offsets.h>
-
-		.text
-		.align	5
-/*
- * ARMv3 optimised copy_user_page
- *
- * FIXME: do we need to handle cache stuff...
- */
-ENTRY(v3_copy_user_page)
-	stmfd	sp!, {r4, lr}			@	2
-	mov	r2, #PAGE_SZ/64			@	1
-	ldmia	r1!, {r3, r4, ip, lr}		@	4+1
-1:	stmia	r0!, {r3, r4, ip, lr}		@	4
-	ldmia	r1!, {r3, r4, ip, lr}		@	4+1
-	stmia	r0!, {r3, r4, ip, lr}		@	4
-	ldmia	r1!, {r3, r4, ip, lr}		@	4+1
-	stmia	r0!, {r3, r4, ip, lr}		@	4
-	ldmia	r1!, {r3, r4, ip, lr}		@	4
-	subs	r2, r2, #1			@	1
-	stmia	r0!, {r3, r4, ip, lr}		@	4
-	ldmneia	r1!, {r3, r4, ip, lr}		@	4
-	bne	1b				@	1
-	ldmfd	sp!, {r4, pc}			@	3
-
-	.align	5
-/*
- * ARMv3 optimised clear_user_page
- *
- * FIXME: do we need to handle cache stuff...
- */
-ENTRY(v3_clear_user_page)
-	str	lr, [sp, #-4]!
-	mov	r1, #PAGE_SZ/64			@ 1
-	mov	r2, #0				@ 1
-	mov	r3, #0				@ 1
-	mov	ip, #0				@ 1
-	mov	lr, #0				@ 1
-1:	stmia	r0!, {r2, r3, ip, lr}		@ 4
-	stmia	r0!, {r2, r3, ip, lr}		@ 4
-	stmia	r0!, {r2, r3, ip, lr}		@ 4
-	stmia	r0!, {r2, r3, ip, lr}		@ 4
-	subs	r1, r1, #1			@ 1
-	bne	1b				@ 1
-	ldr	pc, [sp], #4
-
-	__INITDATA
-
-	.type	v3_user_fns, #object
-ENTRY(v3_user_fns)
-	.long	v3_clear_user_page
-	.long	v3_copy_user_page
-	.size	v3_user_fns, . - v3_user_fns
diff --git a/arch/arm/mm/copypage-v3.c b/arch/arm/mm/copypage-v3.c
new file mode 100644
index 000000000000..70ed96c8af8e
--- /dev/null
+++ b/arch/arm/mm/copypage-v3.c
@@ -0,0 +1,81 @@
+/*
+ *  linux/arch/arm/mm/copypage-v3.c
+ *
+ *  Copyright (C) 1995-1999 Russell King
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <linux/init.h>
+#include <linux/highmem.h>
+
+/*
+ * ARMv3 optimised copy_user_highpage
+ *
+ * FIXME: do we need to handle cache stuff...
+ */
+static void __attribute__((naked))
+v3_copy_user_page(void *kto, const void *kfrom)
+{
+	asm("\n\
+	stmfd	sp!, {r4, lr}			@	2\n\
+	mov	r2, %2				@	1\n\
+	ldmia	%0!, {r3, r4, ip, lr}		@	4+1\n\
+1:	stmia	%1!, {r3, r4, ip, lr}		@	4\n\
+	ldmia	%0!, {r3, r4, ip, lr}		@	4+1\n\
+	stmia	%1!, {r3, r4, ip, lr}		@	4\n\
+	ldmia	%0!, {r3, r4, ip, lr}		@	4+1\n\
+	stmia	%1!, {r3, r4, ip, lr}		@	4\n\
+	ldmia	%0!, {r3, r4, ip, lr}		@	4\n\
+	subs	r2, r2, #1			@	1\n\
+	stmia	%1!, {r3, r4, ip, lr}		@	4\n\
+	ldmneia	%0!, {r3, r4, ip, lr}		@	4\n\
+	bne	1b				@	1\n\
+	ldmfd	sp!, {r4, pc}			@	3"
+	:
+	: "r" (kfrom), "r" (kto), "I" (PAGE_SIZE / 64));
+}
+
+void v3_copy_user_highpage(struct page *to, struct page *from,
+	unsigned long vaddr)
+{
+	void *kto, *kfrom;
+
+	kto = kmap_atomic(to, KM_USER0);
+	kfrom = kmap_atomic(from, KM_USER1);
+	v3_copy_user_page(kto, kfrom);
+	kunmap_atomic(kfrom, KM_USER1);
+	kunmap_atomic(kto, KM_USER0);
+}
+
+/*
+ * ARMv3 optimised clear_user_page
+ *
+ * FIXME: do we need to handle cache stuff...
+ */
+void v3_clear_user_highpage(struct page *page, unsigned long vaddr)
+{
+	void *ptr, *kaddr = kmap_atomic(page, KM_USER0);
+	asm volatile("\n\
+	mov	r1, %2				@ 1\n\
+	mov	r2, #0				@ 1\n\
+	mov	r3, #0				@ 1\n\
+	mov	ip, #0				@ 1\n\
+	mov	lr, #0				@ 1\n\
+1:	stmia	%0!, {r2, r3, ip, lr}		@ 4\n\
+	stmia	%0!, {r2, r3, ip, lr}		@ 4\n\
+	stmia	%0!, {r2, r3, ip, lr}		@ 4\n\
+	stmia	%0!, {r2, r3, ip, lr}		@ 4\n\
+	subs	r1, r1, #1			@ 1\n\
+	bne	1b				@ 1"
+	: "=r" (ptr)
+	: "0" (kaddr), "I" (PAGE_SIZE / 64)
+	: "r1", "r2", "r3", "ip", "lr");
+	kunmap_atomic(kaddr, KM_USER0);
+}
+
+struct cpu_user_fns v3_user_fns __initdata = {
+	.cpu_clear_user_highpage = v3_clear_user_highpage,
+	.cpu_copy_user_highpage	= v3_copy_user_highpage,
+};
diff --git a/arch/arm/mm/copypage-v4mc.c b/arch/arm/mm/copypage-v4mc.c
index 8d33e2549344..bdb5fd983b15 100644
--- a/arch/arm/mm/copypage-v4mc.c
+++ b/arch/arm/mm/copypage-v4mc.c
@@ -15,8 +15,8 @@
  */
 #include <linux/init.h>
 #include <linux/mm.h>
+#include <linux/highmem.h>
 
-#include <asm/page.h>
 #include <asm/pgtable.h>
 #include <asm/tlbflush.h>
 #include <asm/cacheflush.h>
@@ -33,7 +33,7 @@
 static DEFINE_SPINLOCK(minicache_lock);
 
 /*
- * ARMv4 mini-dcache optimised copy_user_page
+ * ARMv4 mini-dcache optimised copy_user_highpage
  *
  * We flush the destination cache lines just before we write the data into the
  * corresponding address.  Since the Dcache is read-allocate, this removes the
@@ -42,7 +42,7 @@ static DEFINE_SPINLOCK(minicache_lock);
  *
  * Note: We rely on all ARMv4 processors implementing the "invalidate D line"
  * instruction.  If your processor does not supply this, you have to write your
- * own copy_user_page that does the right thing.
+ * own copy_user_highpage that does the right thing.
  */
 static void __attribute__((naked))
 mc_copy_user_page(void *from, void *to)
@@ -68,50 +68,53 @@ mc_copy_user_page(void *from, void *to)
 	: "r" (from), "r" (to), "I" (PAGE_SIZE / 64));
 }
 
-void v4_mc_copy_user_page(void *kto, const void *kfrom, unsigned long vaddr)
+void v4_mc_copy_user_highpage(struct page *from, struct page *to,
+	unsigned long vaddr)
 {
-	struct page *page = virt_to_page(kfrom);
+	void *kto = kmap_atomic(to, KM_USER1);
 
-	if (test_and_clear_bit(PG_dcache_dirty, &page->flags))
-		__flush_dcache_page(page_mapping(page), page);
+	if (test_and_clear_bit(PG_dcache_dirty, &from->flags))
+		__flush_dcache_page(page_mapping(from), from);
 
 	spin_lock(&minicache_lock);
 
-	set_pte_ext(TOP_PTE(0xffff8000), pfn_pte(__pa(kfrom) >> PAGE_SHIFT, minicache_pgprot), 0);
+	set_pte_ext(TOP_PTE(0xffff8000), pfn_pte(page_to_pfn(from), minicache_pgprot), 0);
 	flush_tlb_kernel_page(0xffff8000);
 
 	mc_copy_user_page((void *)0xffff8000, kto);
 
 	spin_unlock(&minicache_lock);
+
+	kunmap_atomic(kto, KM_USER1);
 }
 
 /*
  * ARMv4 optimised clear_user_page
  */
-void __attribute__((naked))
-v4_mc_clear_user_page(void *kaddr, unsigned long vaddr)
+void v4_mc_clear_user_highpage(struct page *page, unsigned long vaddr)
 {
-	asm volatile(
-	"str	lr, [sp, #-4]!\n\
-	mov	r1, %0				@ 1\n\
+	void *ptr, *kaddr = kmap_atomic(page, KM_USER0);
+	asm volatile("\
+	mov	r1, %2				@ 1\n\
 	mov	r2, #0				@ 1\n\
 	mov	r3, #0				@ 1\n\
 	mov	ip, #0				@ 1\n\
 	mov	lr, #0				@ 1\n\
-1:	mcr	p15, 0, r0, c7, c6, 1		@ 1   invalidate D line\n\
-	stmia	r0!, {r2, r3, ip, lr}		@ 4\n\
-	stmia	r0!, {r2, r3, ip, lr}		@ 4\n\
-	mcr	p15, 0, r0, c7, c6, 1		@ 1   invalidate D line\n\
-	stmia	r0!, {r2, r3, ip, lr}		@ 4\n\
-	stmia	r0!, {r2, r3, ip, lr}		@ 4\n\
+1:	mcr	p15, 0, %0, c7, c6, 1		@ 1   invalidate D line\n\
+	stmia	%0!, {r2, r3, ip, lr}		@ 4\n\
+	stmia	%0!, {r2, r3, ip, lr}		@ 4\n\
+	mcr	p15, 0, %0, c7, c6, 1		@ 1   invalidate D line\n\
+	stmia	%0!, {r2, r3, ip, lr}		@ 4\n\
+	stmia	%0!, {r2, r3, ip, lr}		@ 4\n\
 	subs	r1, r1, #1			@ 1\n\
-	bne	1b				@ 1\n\
-	ldr	pc, [sp], #4"
-	:
-	: "I" (PAGE_SIZE / 64));
+	bne	1b				@ 1"
+	: "=r" (ptr)
+	: "0" (kaddr), "I" (PAGE_SIZE / 64)
+	: "r1", "r2", "r3", "ip", "lr");
+	kunmap_atomic(kaddr, KM_USER0);
 }
 
 struct cpu_user_fns v4_mc_user_fns __initdata = {
-	.cpu_clear_user_page	= v4_mc_clear_user_page, 
-	.cpu_copy_user_page	= v4_mc_copy_user_page,
+	.cpu_clear_user_highpage = v4_mc_clear_user_highpage,
+	.cpu_copy_user_highpage	= v4_mc_copy_user_highpage,
 };
diff --git a/arch/arm/mm/copypage-v4wb.S b/arch/arm/mm/copypage-v4wb.S
deleted file mode 100644
index 83117354b1cd..000000000000
--- a/arch/arm/mm/copypage-v4wb.S
+++ /dev/null
@@ -1,79 +0,0 @@
-/*
- *  linux/arch/arm/lib/copypage.S
- *
- *  Copyright (C) 1995-1999 Russell King
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- *  ASM optimised string functions
- */
-#include <linux/linkage.h>
-#include <linux/init.h>
-#include <asm/asm-offsets.h>
-
-	.text
-	.align	5
-/*
- * ARMv4 optimised copy_user_page
- *
- * We flush the destination cache lines just before we write the data into the
- * corresponding address.  Since the Dcache is read-allocate, this removes the
- * Dcache aliasing issue.  The writes will be forwarded to the write buffer,
- * and merged as appropriate.
- *
- * Note: We rely on all ARMv4 processors implementing the "invalidate D line"
- * instruction.  If your processor does not supply this, you have to write your
- * own copy_user_page that does the right thing.
- */
-ENTRY(v4wb_copy_user_page)
-	stmfd	sp!, {r4, lr}			@ 2
-	mov	r2, #PAGE_SZ/64			@ 1
-	ldmia	r1!, {r3, r4, ip, lr}		@ 4
-1:	mcr	p15, 0, r0, c7, c6, 1		@ 1   invalidate D line
-	stmia	r0!, {r3, r4, ip, lr}		@ 4
-	ldmia	r1!, {r3, r4, ip, lr}		@ 4+1
-	stmia	r0!, {r3, r4, ip, lr}		@ 4
-	ldmia	r1!, {r3, r4, ip, lr}		@ 4
-	mcr	p15, 0, r0, c7, c6, 1		@ 1   invalidate D line
-	stmia	r0!, {r3, r4, ip, lr}		@ 4
-	ldmia	r1!, {r3, r4, ip, lr}		@ 4
-	subs	r2, r2, #1			@ 1
-	stmia	r0!, {r3, r4, ip, lr}		@ 4
-	ldmneia	r1!, {r3, r4, ip, lr}		@ 4
-	bne	1b				@ 1
-	mcr	p15, 0, r1, c7, c10, 4		@ 1   drain WB
-	ldmfd	 sp!, {r4, pc}			@ 3
-
-	.align	5
-/*
- * ARMv4 optimised clear_user_page
- *
- * Same story as above.
- */
-ENTRY(v4wb_clear_user_page)
-	str	lr, [sp, #-4]!
-	mov	r1, #PAGE_SZ/64			@ 1
-	mov	r2, #0				@ 1
-	mov	r3, #0				@ 1
-	mov	ip, #0				@ 1
-	mov	lr, #0				@ 1
-1:	mcr	p15, 0, r0, c7, c6, 1		@ 1   invalidate D line
-	stmia	r0!, {r2, r3, ip, lr}		@ 4
-	stmia	r0!, {r2, r3, ip, lr}		@ 4
-	mcr	p15, 0, r0, c7, c6, 1		@ 1   invalidate D line
-	stmia	r0!, {r2, r3, ip, lr}		@ 4
-	stmia	r0!, {r2, r3, ip, lr}		@ 4
-	subs	r1, r1, #1			@ 1
-	bne	1b				@ 1
-	mcr	p15, 0, r1, c7, c10, 4		@ 1   drain WB
-	ldr	pc, [sp], #4
-
-	__INITDATA
-
-	.type	v4wb_user_fns, #object
-ENTRY(v4wb_user_fns)
-	.long	v4wb_clear_user_page
-	.long	v4wb_copy_user_page
-	.size	v4wb_user_fns, . - v4wb_user_fns
diff --git a/arch/arm/mm/copypage-v4wb.c b/arch/arm/mm/copypage-v4wb.c
new file mode 100644
index 000000000000..3ec93dab7656
--- /dev/null
+++ b/arch/arm/mm/copypage-v4wb.c
@@ -0,0 +1,94 @@
+/*
+ *  linux/arch/arm/mm/copypage-v4wb.c
+ *
+ *  Copyright (C) 1995-1999 Russell King
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <linux/init.h>
+#include <linux/highmem.h>
+
+/*
+ * ARMv4 optimised copy_user_highpage
+ *
+ * We flush the destination cache lines just before we write the data into the
+ * corresponding address.  Since the Dcache is read-allocate, this removes the
+ * Dcache aliasing issue.  The writes will be forwarded to the write buffer,
+ * and merged as appropriate.
+ *
+ * Note: We rely on all ARMv4 processors implementing the "invalidate D line"
+ * instruction.  If your processor does not supply this, you have to write your
+ * own copy_user_highpage that does the right thing.
+ */
+static void __attribute__((naked))
+v4wb_copy_user_page(void *kto, const void *kfrom)
+{
+	asm("\
+	stmfd	sp!, {r4, lr}			@ 2\n\
+	mov	r2, %0				@ 1\n\
+	ldmia	r1!, {r3, r4, ip, lr}		@ 4\n\
+1:	mcr	p15, 0, r0, c7, c6, 1		@ 1   invalidate D line\n\
+	stmia	r0!, {r3, r4, ip, lr}		@ 4\n\
+	ldmia	r1!, {r3, r4, ip, lr}		@ 4+1\n\
+	stmia	r0!, {r3, r4, ip, lr}		@ 4\n\
+	ldmia	r1!, {r3, r4, ip, lr}		@ 4\n\
+	mcr	p15, 0, r0, c7, c6, 1		@ 1   invalidate D line\n\
+	stmia	r0!, {r3, r4, ip, lr}		@ 4\n\
+	ldmia	r1!, {r3, r4, ip, lr}		@ 4\n\
+	subs	r2, r2, #1			@ 1\n\
+	stmia	r0!, {r3, r4, ip, lr}		@ 4\n\
+	ldmneia	r1!, {r3, r4, ip, lr}		@ 4\n\
+	bne	1b				@ 1\n\
+	mcr	p15, 0, r1, c7, c10, 4		@ 1   drain WB\n\
+	ldmfd	 sp!, {r4, pc}			@ 3"
+	:
+	: "I" (PAGE_SIZE / 64));
+}
+
+void v4wb_copy_user_highpage(struct page *to, struct page *from,
+	unsigned long vaddr)
+{
+	void *kto, *kfrom;
+
+	kto = kmap_atomic(to, KM_USER0);
+	kfrom = kmap_atomic(from, KM_USER1);
+	v4wb_copy_user_page(kto, kfrom);
+	kunmap_atomic(kfrom, KM_USER1);
+	kunmap_atomic(kto, KM_USER0);
+}
+
+/*
+ * ARMv4 optimised clear_user_page
+ *
+ * Same story as above.
+ */
+void v4wb_clear_user_highpage(struct page *page, unsigned long vaddr)
+{
+	void *ptr, *kaddr = kmap_atomic(page, KM_USER0);
+	asm volatile("\
+	mov	r1, %2				@ 1\n\
+	mov	r2, #0				@ 1\n\
+	mov	r3, #0				@ 1\n\
+	mov	ip, #0				@ 1\n\
+	mov	lr, #0				@ 1\n\
+1:	mcr	p15, 0, %0, c7, c6, 1		@ 1   invalidate D line\n\
+	stmia	%0!, {r2, r3, ip, lr}		@ 4\n\
+	stmia	%0!, {r2, r3, ip, lr}		@ 4\n\
+	mcr	p15, 0, %0, c7, c6, 1		@ 1   invalidate D line\n\
+	stmia	%0!, {r2, r3, ip, lr}		@ 4\n\
+	stmia	%0!, {r2, r3, ip, lr}		@ 4\n\
+	subs	r1, r1, #1			@ 1\n\
+	bne	1b				@ 1\n\
+	mcr	p15, 0, r1, c7, c10, 4		@ 1   drain WB"
+	: "=r" (ptr)
+	: "0" (kaddr), "I" (PAGE_SIZE / 64)
+	: "r1", "r2", "r3", "ip", "lr");
+	kunmap_atomic(kaddr, KM_USER0);
+}
+
+struct cpu_user_fns v4wb_user_fns __initdata = {
+	.cpu_clear_user_highpage = v4wb_clear_user_highpage,
+	.cpu_copy_user_highpage	= v4wb_copy_user_highpage,
+};
diff --git a/arch/arm/mm/copypage-v4wt.S b/arch/arm/mm/copypage-v4wt.S
deleted file mode 100644
index e1f2af28d549..000000000000
--- a/arch/arm/mm/copypage-v4wt.S
+++ /dev/null
@@ -1,73 +0,0 @@
-/*
- *  linux/arch/arm/lib/copypage-v4.S
- *
- *  Copyright (C) 1995-1999 Russell King
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- *  ASM optimised string functions
- *
- *  This is for CPUs with a writethrough cache and 'flush ID cache' is
- *  the only supported cache operation.
- */
-#include <linux/linkage.h>
-#include <linux/init.h>
-#include <asm/asm-offsets.h>
-
-	.text
-	.align	5
-/*
- * ARMv4 optimised copy_user_page
- *
- * Since we have writethrough caches, we don't have to worry about
- * dirty data in the cache.  However, we do have to ensure that
- * subsequent reads are up to date.
- */
-ENTRY(v4wt_copy_user_page)
-	stmfd	sp!, {r4, lr}			@ 2
-	mov	r2, #PAGE_SZ/64			@ 1
-	ldmia	r1!, {r3, r4, ip, lr}		@ 4
-1:	stmia	r0!, {r3, r4, ip, lr}		@ 4
-	ldmia	r1!, {r3, r4, ip, lr}		@ 4+1
-	stmia	r0!, {r3, r4, ip, lr}		@ 4
-	ldmia	r1!, {r3, r4, ip, lr}		@ 4
-	stmia	r0!, {r3, r4, ip, lr}		@ 4
-	ldmia	r1!, {r3, r4, ip, lr}		@ 4
-	subs	r2, r2, #1			@ 1
-	stmia	r0!, {r3, r4, ip, lr}		@ 4
-	ldmneia	r1!, {r3, r4, ip, lr}		@ 4
-	bne	1b				@ 1
-	mcr	p15, 0, r2, c7, c7, 0		@ flush ID cache
-	ldmfd	sp!, {r4, pc}			@ 3
-
-	.align	5
-/*
- * ARMv4 optimised clear_user_page
- *
- * Same story as above.
- */
-ENTRY(v4wt_clear_user_page)
-	str	lr, [sp, #-4]!
-	mov	r1, #PAGE_SZ/64			@ 1
-	mov	r2, #0				@ 1
-	mov	r3, #0				@ 1
-	mov	ip, #0				@ 1
-	mov	lr, #0				@ 1
-1:	stmia	r0!, {r2, r3, ip, lr}		@ 4
-	stmia	r0!, {r2, r3, ip, lr}		@ 4
-	stmia	r0!, {r2, r3, ip, lr}		@ 4
-	stmia	r0!, {r2, r3, ip, lr}		@ 4
-	subs	r1, r1, #1			@ 1
-	bne	1b				@ 1
-	mcr	p15, 0, r2, c7, c7, 0		@ flush ID cache
-	ldr	pc, [sp], #4
-
-	__INITDATA
-
-	.type	v4wt_user_fns, #object
-ENTRY(v4wt_user_fns)
-	.long	v4wt_clear_user_page
-	.long	v4wt_copy_user_page
-	.size	v4wt_user_fns, . - v4wt_user_fns
diff --git a/arch/arm/mm/copypage-v4wt.c b/arch/arm/mm/copypage-v4wt.c
new file mode 100644
index 000000000000..0f1188efae45
--- /dev/null
+++ b/arch/arm/mm/copypage-v4wt.c
@@ -0,0 +1,88 @@
+/*
+ *  linux/arch/arm/mm/copypage-v4wt.S
+ *
+ *  Copyright (C) 1995-1999 Russell King
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ *  This is for CPUs with a writethrough cache and 'flush ID cache' is
+ *  the only supported cache operation.
+ */
+#include <linux/init.h>
+#include <linux/highmem.h>
+
+/*
+ * ARMv4 optimised copy_user_highpage
+ *
+ * Since we have writethrough caches, we don't have to worry about
+ * dirty data in the cache.  However, we do have to ensure that
+ * subsequent reads are up to date.
+ */
+static void __attribute__((naked))
+v4wt_copy_user_page(void *kto, const void *kfrom)
+{
+	asm("\
+	stmfd	sp!, {r4, lr}			@ 2\n\
+	mov	r2, %0				@ 1\n\
+	ldmia	r1!, {r3, r4, ip, lr}		@ 4\n\
+1:	stmia	r0!, {r3, r4, ip, lr}		@ 4\n\
+	ldmia	r1!, {r3, r4, ip, lr}		@ 4+1\n\
+	stmia	r0!, {r3, r4, ip, lr}		@ 4\n\
+	ldmia	r1!, {r3, r4, ip, lr}		@ 4\n\
+	stmia	r0!, {r3, r4, ip, lr}		@ 4\n\
+	ldmia	r1!, {r3, r4, ip, lr}		@ 4\n\
+	subs	r2, r2, #1			@ 1\n\
+	stmia	r0!, {r3, r4, ip, lr}		@ 4\n\
+	ldmneia	r1!, {r3, r4, ip, lr}		@ 4\n\
+	bne	1b				@ 1\n\
+	mcr	p15, 0, r2, c7, c7, 0		@ flush ID cache\n\
+	ldmfd	sp!, {r4, pc}			@ 3"
+	:
+	: "I" (PAGE_SIZE / 64));
+}
+
+void v4wt_copy_user_highpage(struct page *to, struct page *from,
+	unsigned long vaddr)
+{
+	void *kto, *kfrom;
+
+	kto = kmap_atomic(to, KM_USER0);
+	kfrom = kmap_atomic(from, KM_USER1);
+	v4wt_copy_user_page(kto, kfrom);
+	kunmap_atomic(kfrom, KM_USER1);
+	kunmap_atomic(kto, KM_USER0);
+}
+
+/*
+ * ARMv4 optimised clear_user_page
+ *
+ * Same story as above.
+ */
+void v4wt_clear_user_highpage(struct page *page, unsigned long vaddr)
+{
+	void *ptr, *kaddr = kmap_atomic(page, KM_USER0);
+	asm volatile("\
+	mov	r1, %2				@ 1\n\
+	mov	r2, #0				@ 1\n\
+	mov	r3, #0				@ 1\n\
+	mov	ip, #0				@ 1\n\
+	mov	lr, #0				@ 1\n\
+1:	stmia	%0!, {r2, r3, ip, lr}		@ 4\n\
+	stmia	%0!, {r2, r3, ip, lr}		@ 4\n\
+	stmia	%0!, {r2, r3, ip, lr}		@ 4\n\
+	stmia	%0!, {r2, r3, ip, lr}		@ 4\n\
+	subs	r1, r1, #1			@ 1\n\
+	bne	1b				@ 1\n\
+	mcr	p15, 0, r2, c7, c7, 0		@ flush ID cache"
+	: "=r" (ptr)
+	: "0" (kaddr), "I" (PAGE_SIZE / 64)
+	: "r1", "r2", "r3", "ip", "lr");
+	kunmap_atomic(kaddr, KM_USER0);
+}
+
+struct cpu_user_fns v4wt_user_fns __initdata = {
+	.cpu_clear_user_highpage = v4wt_clear_user_highpage,
+	.cpu_copy_user_highpage	= v4wt_copy_user_highpage,
+};
diff --git a/arch/arm/mm/copypage-v6.c b/arch/arm/mm/copypage-v6.c
index 0e21c0767580..4127a7bddfe5 100644
--- a/arch/arm/mm/copypage-v6.c
+++ b/arch/arm/mm/copypage-v6.c
@@ -10,8 +10,8 @@
 #include <linux/init.h>
 #include <linux/spinlock.h>
 #include <linux/mm.h>
+#include <linux/highmem.h>
 
-#include <asm/page.h>
 #include <asm/pgtable.h>
 #include <asm/shmparam.h>
 #include <asm/tlbflush.h>
@@ -33,41 +33,56 @@ static DEFINE_SPINLOCK(v6_lock);
  * Copy the user page.  No aliasing to deal with so we can just
  * attack the kernel's existing mapping of these pages.
  */
-static void v6_copy_user_page_nonaliasing(void *kto, const void *kfrom, unsigned long vaddr)
+static void v6_copy_user_highpage_nonaliasing(struct page *to,
+	struct page *from, unsigned long vaddr)
 {
+	void *kto, *kfrom;
+
+	kfrom = kmap_atomic(from, KM_USER0);
+	kto = kmap_atomic(to, KM_USER1);
 	copy_page(kto, kfrom);
+	kunmap_atomic(kto, KM_USER1);
+	kunmap_atomic(kfrom, KM_USER0);
 }
 
 /*
  * Clear the user page.  No aliasing to deal with so we can just
  * attack the kernel's existing mapping of this page.
  */
-static void v6_clear_user_page_nonaliasing(void *kaddr, unsigned long vaddr)
+static void v6_clear_user_highpage_nonaliasing(struct page *page, unsigned long vaddr)
 {
+	void *kaddr = kmap_atomic(page, KM_USER0);
 	clear_page(kaddr);
+	kunmap_atomic(kaddr, KM_USER0);
 }
 
 /*
- * Copy the page, taking account of the cache colour.
+ * Discard data in the kernel mapping for the new page.
+ * FIXME: needs this MCRR to be supported.
  */
-static void v6_copy_user_page_aliasing(void *kto, const void *kfrom, unsigned long vaddr)
+static void discard_old_kernel_data(void *kto)
 {
-	unsigned int offset = CACHE_COLOUR(vaddr);
-	unsigned long from, to;
-	struct page *page = virt_to_page(kfrom);
-
-	if (test_and_clear_bit(PG_dcache_dirty, &page->flags))
-		__flush_dcache_page(page_mapping(page), page);
-
-	/*
-	 * Discard data in the kernel mapping for the new page.
-	 * FIXME: needs this MCRR to be supported.
-	 */
 	__asm__("mcrr	p15, 0, %1, %0, c6	@ 0xec401f06"
 	   :
 	   : "r" (kto),
 	     "r" ((unsigned long)kto + PAGE_SIZE - L1_CACHE_BYTES)
 	   : "cc");
+}
+
+/*
+ * Copy the page, taking account of the cache colour.
+ */
+static void v6_copy_user_highpage_aliasing(struct page *to,
+	struct page *from, unsigned long vaddr)
+{
+	unsigned int offset = CACHE_COLOUR(vaddr);
+	unsigned long kfrom, kto;
+
+	if (test_and_clear_bit(PG_dcache_dirty, &from->flags))
+		__flush_dcache_page(page_mapping(from), from);
+
+	/* FIXME: not highmem safe */
+	discard_old_kernel_data(page_address(to));
 
 	/*
 	 * Now copy the page using the same cache colour as the
@@ -75,16 +90,16 @@ static void v6_copy_user_page_aliasing(void *kto, const void *kfrom, unsigned lo
 	 */
 	spin_lock(&v6_lock);
 
-	set_pte_ext(TOP_PTE(from_address) + offset, pfn_pte(__pa(kfrom) >> PAGE_SHIFT, PAGE_KERNEL), 0);
-	set_pte_ext(TOP_PTE(to_address) + offset, pfn_pte(__pa(kto) >> PAGE_SHIFT, PAGE_KERNEL), 0);
+	set_pte_ext(TOP_PTE(from_address) + offset, pfn_pte(page_to_pfn(from), PAGE_KERNEL), 0);
+	set_pte_ext(TOP_PTE(to_address) + offset, pfn_pte(page_to_pfn(to), PAGE_KERNEL), 0);
 
-	from = from_address + (offset << PAGE_SHIFT);
-	to   = to_address + (offset << PAGE_SHIFT);
+	kfrom = from_address + (offset << PAGE_SHIFT);
+	kto   = to_address + (offset << PAGE_SHIFT);
 
-	flush_tlb_kernel_page(from);
-	flush_tlb_kernel_page(to);
+	flush_tlb_kernel_page(kfrom);
+	flush_tlb_kernel_page(kto);
 
-	copy_page((void *)to, (void *)from);
+	copy_page((void *)kto, (void *)kfrom);
 
 	spin_unlock(&v6_lock);
 }
@@ -94,20 +109,13 @@ static void v6_copy_user_page_aliasing(void *kto, const void *kfrom, unsigned lo
  * so remap the kernel page into the same cache colour as the user
  * page.
  */
-static void v6_clear_user_page_aliasing(void *kaddr, unsigned long vaddr)
+static void v6_clear_user_highpage_aliasing(struct page *page, unsigned long vaddr)
 {
 	unsigned int offset = CACHE_COLOUR(vaddr);
 	unsigned long to = to_address + (offset << PAGE_SHIFT);
 
-	/*
-	 * Discard data in the kernel mapping for the new page
-	 * FIXME: needs this MCRR to be supported.
-	 */
-	__asm__("mcrr	p15, 0, %1, %0, c6	@ 0xec401f06"
-	   :
-	   : "r" (kaddr),
-	     "r" ((unsigned long)kaddr + PAGE_SIZE - L1_CACHE_BYTES)
-	   : "cc");
+	/* FIXME: not highmem safe */
+	discard_old_kernel_data(page_address(page));
 
 	/*
 	 * Now clear the page using the same cache colour as
@@ -115,7 +123,7 @@ static void v6_clear_user_page_aliasing(void *kaddr, unsigned long vaddr)
 	 */
 	spin_lock(&v6_lock);
 
-	set_pte_ext(TOP_PTE(to_address) + offset, pfn_pte(__pa(kaddr) >> PAGE_SHIFT, PAGE_KERNEL), 0);
+	set_pte_ext(TOP_PTE(to_address) + offset, pfn_pte(page_to_pfn(page), PAGE_KERNEL), 0);
 	flush_tlb_kernel_page(to);
 	clear_page((void *)to);
 
@@ -123,15 +131,15 @@ static void v6_clear_user_page_aliasing(void *kaddr, unsigned long vaddr)
 }
 
 struct cpu_user_fns v6_user_fns __initdata = {
-	.cpu_clear_user_page	= v6_clear_user_page_nonaliasing,
-	.cpu_copy_user_page	= v6_copy_user_page_nonaliasing,
+	.cpu_clear_user_highpage = v6_clear_user_highpage_nonaliasing,
+	.cpu_copy_user_highpage	= v6_copy_user_highpage_nonaliasing,
 };
 
 static int __init v6_userpage_init(void)
 {
 	if (cache_is_vipt_aliasing()) {
-		cpu_user.cpu_clear_user_page = v6_clear_user_page_aliasing;
-		cpu_user.cpu_copy_user_page = v6_copy_user_page_aliasing;
+		cpu_user.cpu_clear_user_highpage = v6_clear_user_highpage_aliasing;
+		cpu_user.cpu_copy_user_highpage = v6_copy_user_highpage_aliasing;
 	}
 
 	return 0;
diff --git a/arch/arm/mm/copypage-xsc3.S b/arch/arm/mm/copypage-xsc3.S
deleted file mode 100644
index 9a2cb4332b4c..000000000000
--- a/arch/arm/mm/copypage-xsc3.S
+++ /dev/null
@@ -1,97 +0,0 @@
-/*
- *  linux/arch/arm/lib/copypage-xsc3.S
- *
- *  Copyright (C) 2004 Intel Corp.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * Adapted for 3rd gen XScale core, no more mini-dcache
- * Author: Matt Gilbert (matthew.m.gilbert@intel.com)
- */
-
-#include <linux/linkage.h>
-#include <linux/init.h>
-#include <asm/asm-offsets.h>
-
-/*
- * General note:
- *  We don't really want write-allocate cache behaviour for these functions
- *  since that will just eat through 8K of the cache.
- */
-
-	.text
-	.align	5
-/*
- * XSC3 optimised copy_user_page
- *  r0 = destination
- *  r1 = source
- *  r2 = virtual user address of ultimate destination page
- *
- * The source page may have some clean entries in the cache already, but we
- * can safely ignore them - break_cow() will flush them out of the cache
- * if we eventually end up using our copied page.
- *
- */
-ENTRY(xsc3_mc_copy_user_page)
-	stmfd	sp!, {r4, r5, lr}
-	mov	lr, #PAGE_SZ/64-1
-
-	pld	[r1, #0]
-	pld	[r1, #32]
-1:	pld	[r1, #64]
-	pld	[r1, #96]
-
-2:	ldrd	r2, [r1], #8
-	mov	ip, r0
-	ldrd	r4, [r1], #8
-	mcr	p15, 0, ip, c7, c6, 1		@ invalidate
-	strd	r2, [r0], #8
-	ldrd	r2, [r1], #8
-	strd	r4, [r0], #8
-	ldrd	r4, [r1], #8
-	strd	r2, [r0], #8
-	strd	r4, [r0], #8
-	ldrd	r2, [r1], #8
-	mov	ip, r0
-	ldrd	r4, [r1], #8
-	mcr	p15, 0, ip, c7, c6, 1		@ invalidate
-	strd	r2, [r0], #8
-	ldrd	r2, [r1], #8
-	subs	lr, lr, #1
-	strd	r4, [r0], #8
-	ldrd	r4, [r1], #8
-	strd	r2, [r0], #8
-	strd	r4, [r0], #8
-	bgt	1b
-	beq	2b
-
-	ldmfd	sp!, {r4, r5, pc}
-
-	.align	5
-/*
- * XScale optimised clear_user_page
- *  r0 = destination
- *  r1 = virtual user address of ultimate destination page
- */
-ENTRY(xsc3_mc_clear_user_page)
-	mov	r1, #PAGE_SZ/32
-	mov	r2, #0
-	mov	r3, #0
-1:	mcr	p15, 0, r0, c7, c6, 1		@ invalidate line
-	strd	r2, [r0], #8
-	strd	r2, [r0], #8
-	strd	r2, [r0], #8
-	strd	r2, [r0], #8
-	subs	r1, r1, #1
-	bne	1b
-	mov	pc, lr
-
-	__INITDATA
-
-	.type	xsc3_mc_user_fns, #object
-ENTRY(xsc3_mc_user_fns)
-	.long	xsc3_mc_clear_user_page
-	.long	xsc3_mc_copy_user_page
-	.size	xsc3_mc_user_fns, . - xsc3_mc_user_fns
diff --git a/arch/arm/mm/copypage-xsc3.c b/arch/arm/mm/copypage-xsc3.c
new file mode 100644
index 000000000000..39a994542cad
--- /dev/null
+++ b/arch/arm/mm/copypage-xsc3.c
@@ -0,0 +1,113 @@
+/*
+ *  linux/arch/arm/mm/copypage-xsc3.S
+ *
+ *  Copyright (C) 2004 Intel Corp.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Adapted for 3rd gen XScale core, no more mini-dcache
+ * Author: Matt Gilbert (matthew.m.gilbert@intel.com)
+ */
+#include <linux/init.h>
+#include <linux/highmem.h>
+
+/*
+ * General note:
+ *  We don't really want write-allocate cache behaviour for these functions
+ *  since that will just eat through 8K of the cache.
+ */
+
+/*
+ * XSC3 optimised copy_user_highpage
+ *  r0 = destination
+ *  r1 = source
+ *
+ * The source page may have some clean entries in the cache already, but we
+ * can safely ignore them - break_cow() will flush them out of the cache
+ * if we eventually end up using our copied page.
+ *
+ */
+static void __attribute__((naked))
+xsc3_mc_copy_user_page(void *kto, const void *kfrom)
+{
+	asm("\
+	stmfd	sp!, {r4, r5, lr}		\n\
+	mov	lr, %0				\n\
+						\n\
+	pld	[r1, #0]			\n\
+	pld	[r1, #32]			\n\
+1:	pld	[r1, #64]			\n\
+	pld	[r1, #96]			\n\
+						\n\
+2:	ldrd	r2, [r1], #8			\n\
+	mov	ip, r0				\n\
+	ldrd	r4, [r1], #8			\n\
+	mcr	p15, 0, ip, c7, c6, 1		@ invalidate\n\
+	strd	r2, [r0], #8			\n\
+	ldrd	r2, [r1], #8			\n\
+	strd	r4, [r0], #8			\n\
+	ldrd	r4, [r1], #8			\n\
+	strd	r2, [r0], #8			\n\
+	strd	r4, [r0], #8			\n\
+	ldrd	r2, [r1], #8			\n\
+	mov	ip, r0				\n\
+	ldrd	r4, [r1], #8			\n\
+	mcr	p15, 0, ip, c7, c6, 1		@ invalidate\n\
+	strd	r2, [r0], #8			\n\
+	ldrd	r2, [r1], #8			\n\
+	subs	lr, lr, #1			\n\
+	strd	r4, [r0], #8			\n\
+	ldrd	r4, [r1], #8			\n\
+	strd	r2, [r0], #8			\n\
+	strd	r4, [r0], #8			\n\
+	bgt	1b				\n\
+	beq	2b				\n\
+						\n\
+	ldmfd	sp!, {r4, r5, pc}"
+	:
+	: "I" (PAGE_SIZE / 64 - 1));
+}
+
+void xsc3_mc_copy_user_highpage(struct page *to, struct page *from,
+	unsigned long vaddr)
+{
+	void *kto, *kfrom;
+
+	kto = kmap_atomic(to, KM_USER0);
+	kfrom = kmap_atomic(from, KM_USER1);
+	xsc3_mc_copy_user_page(kto, kfrom);
+	kunmap_atomic(kfrom, KM_USER1);
+	kunmap_atomic(kto, KM_USER0);
+}
+
+/*
+ * XScale optimised clear_user_page
+ *  r0 = destination
+ *  r1 = virtual user address of ultimate destination page
+ */
+void xsc3_mc_clear_user_highpage(struct page *page, unsigned long vaddr)
+{
+	void *ptr, *kaddr = kmap_atomic(page, KM_USER0);
+	asm volatile ("\
+	mov	r1, %2				\n\
+	mov	r2, #0				\n\
+	mov	r3, #0				\n\
+1:	mcr	p15, 0, %0, c7, c6, 1		@ invalidate line\n\
+	strd	r2, [%0], #8			\n\
+	strd	r2, [%0], #8			\n\
+	strd	r2, [%0], #8			\n\
+	strd	r2, [%0], #8			\n\
+	subs	r1, r1, #1			\n\
+	bne	1b"
+	: "=r" (ptr)
+	: "0" (kaddr), "I" (PAGE_SIZE / 32)
+	: "r1", "r2", "r3");
+	kunmap_atomic(kaddr, KM_USER0);
+}
+
+struct cpu_user_fns xsc3_mc_user_fns __initdata = {
+	.cpu_clear_user_highpage = xsc3_mc_clear_user_highpage,
+	.cpu_copy_user_highpage	= xsc3_mc_copy_user_highpage,
+};
diff --git a/arch/arm/mm/copypage-xscale.c b/arch/arm/mm/copypage-xscale.c
index bad49331bbf9..d18f2397ee2d 100644
--- a/arch/arm/mm/copypage-xscale.c
+++ b/arch/arm/mm/copypage-xscale.c
@@ -15,8 +15,8 @@
  */
 #include <linux/init.h>
 #include <linux/mm.h>
+#include <linux/highmem.h>
 
-#include <asm/page.h>
 #include <asm/pgtable.h>
 #include <asm/tlbflush.h>
 #include <asm/cacheflush.h>
@@ -35,7 +35,7 @@
 static DEFINE_SPINLOCK(minicache_lock);
 
 /*
- * XScale mini-dcache optimised copy_user_page
+ * XScale mini-dcache optimised copy_user_highpage
  *
  * We flush the destination cache lines just before we write the data into the
  * corresponding address.  Since the Dcache is read-allocate, this removes the
@@ -90,48 +90,53 @@ mc_copy_user_page(void *from, void *to)
 	: "r" (from), "r" (to), "I" (PAGE_SIZE / 64 - 1));
 }
 
-void xscale_mc_copy_user_page(void *kto, const void *kfrom, unsigned long vaddr)
+void xscale_mc_copy_user_highpage(struct page *to, struct page *from,
+	unsigned long vaddr)
 {
-	struct page *page = virt_to_page(kfrom);
+	void *kto = kmap_atomic(to, KM_USER1);
 
-	if (test_and_clear_bit(PG_dcache_dirty, &page->flags))
-		__flush_dcache_page(page_mapping(page), page);
+	if (test_and_clear_bit(PG_dcache_dirty, &from->flags))
+		__flush_dcache_page(page_mapping(from), from);
 
 	spin_lock(&minicache_lock);
 
-	set_pte_ext(TOP_PTE(COPYPAGE_MINICACHE), pfn_pte(__pa(kfrom) >> PAGE_SHIFT, minicache_pgprot), 0);
+	set_pte_ext(TOP_PTE(COPYPAGE_MINICACHE), pfn_pte(page_to_pfn(from), minicache_pgprot), 0);
 	flush_tlb_kernel_page(COPYPAGE_MINICACHE);
 
 	mc_copy_user_page((void *)COPYPAGE_MINICACHE, kto);
 
 	spin_unlock(&minicache_lock);
+
+	kunmap_atomic(kto, KM_USER1);
 }
 
 /*
  * XScale optimised clear_user_page
  */
-void __attribute__((naked))
-xscale_mc_clear_user_page(void *kaddr, unsigned long vaddr)
+void
+xscale_mc_clear_user_highpage(struct page *page, unsigned long vaddr)
 {
+	void *ptr, *kaddr = kmap_atomic(page, KM_USER0);
 	asm volatile(
-	"mov	r1, %0				\n\
+	"mov	r1, %2				\n\
 	mov	r2, #0				\n\
 	mov	r3, #0				\n\
-1:	mov	ip, r0				\n\
-	strd	r2, [r0], #8			\n\
-	strd	r2, [r0], #8			\n\
-	strd	r2, [r0], #8			\n\
-	strd	r2, [r0], #8			\n\
+1:	mov	ip, %0				\n\
+	strd	r2, [%0], #8			\n\
+	strd	r2, [%0], #8			\n\
+	strd	r2, [%0], #8			\n\
+	strd	r2, [%0], #8			\n\
 	mcr	p15, 0, ip, c7, c10, 1		@ clean D line\n\
 	subs	r1, r1, #1			\n\
 	mcr	p15, 0, ip, c7, c6, 1		@ invalidate D line\n\
-	bne	1b				\n\
-	mov	pc, lr"
-	:
-	: "I" (PAGE_SIZE / 32));
+	bne	1b"
+	: "=r" (ptr)
+	: "0" (kaddr), "I" (PAGE_SIZE / 32)
+	: "r1", "r2", "r3", "ip");
+	kunmap_atomic(kaddr, KM_USER0);
 }
 
 struct cpu_user_fns xscale_mc_user_fns __initdata = {
-	.cpu_clear_user_page	= xscale_mc_clear_user_page, 
-	.cpu_copy_user_page	= xscale_mc_copy_user_page,
+	.cpu_clear_user_highpage = xscale_mc_clear_user_highpage,
+	.cpu_copy_user_highpage	= xscale_mc_copy_user_highpage,
 };
diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c
index 2df8d9facf57..ffd8b228a139 100644
--- a/arch/arm/mm/fault.c
+++ b/arch/arm/mm/fault.c
@@ -14,6 +14,7 @@
 #include <linux/init.h>
 #include <linux/kprobes.h>
 #include <linux/uaccess.h>
+#include <linux/page-flags.h>
 
 #include <asm/system.h>
 #include <asm/pgtable.h>
@@ -83,13 +84,14 @@ void show_pte(struct mm_struct *mm, unsigned long addr)
 			break;
 		}
 
-#ifndef CONFIG_HIGHMEM
 		/* We must not map this if we have highmem enabled */
+		if (PageHighMem(pfn_to_page(pmd_val(*pmd) >> PAGE_SHIFT)))
+			break;
+
 		pte = pte_offset_map(pmd, addr);
 		printk(", *pte=%08lx", pte_val(*pte));
 		printk(", *ppte=%08lx", pte_val(pte[-PTRS_PER_PTE]));
 		pte_unmap(pte);
-#endif
 	} while(0);
 
 	printk("\n");
diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c
index 82c4b4217989..34df4d9d03a6 100644
--- a/arch/arm/mm/init.c
+++ b/arch/arm/mm/init.c
@@ -17,6 +17,7 @@
 #include <linux/initrd.h>
 
 #include <asm/mach-types.h>
+#include <asm/sections.h>
 #include <asm/setup.h>
 #include <asm/sizes.h>
 #include <asm/tlb.h>
@@ -64,10 +65,11 @@ static int __init parse_tag_initrd2(const struct tag *tag)
 __tagtable(ATAG_INITRD2, parse_tag_initrd2);
 
 /*
- * This is used to pass memory configuration data from paging_init
- * to mem_init, and by show_mem() to skip holes in the memory map.
+ * This keeps memory configuration data used by a couple memory
+ * initialization functions, as well as show_mem() for the skipping
+ * of holes in the memory map.  It is populated by arm_add_memory().
  */
-static struct meminfo meminfo = { 0, };
+struct meminfo meminfo;
 
 void show_mem(void)
 {
@@ -128,7 +130,7 @@ find_bootmap_pfn(int node, struct meminfo *mi, unsigned int bootmap_pages)
 {
 	unsigned int start_pfn, i, bootmap_pfn;
 
-	start_pfn   = PAGE_ALIGN(__pa(&_end)) >> PAGE_SHIFT;
+	start_pfn   = PAGE_ALIGN(__pa(_end)) >> PAGE_SHIFT;
 	bootmap_pfn = 0;
 
 	for_each_nodebank(i, mi, node) {
@@ -331,13 +333,12 @@ static void __init bootmem_free_node(int node, struct meminfo *mi)
 	free_area_init_node(node, zone_size, start_pfn, zhole_size);
 }
 
-void __init bootmem_init(struct meminfo *mi)
+void __init bootmem_init(void)
 {
+	struct meminfo *mi = &meminfo;
 	unsigned long memend_pfn = 0;
 	int node, initrd_node;
 
-	memcpy(&meminfo, mi, sizeof(meminfo));
-
 	/*
 	 * Locate which node contains the ramdisk image, if any.
 	 */
@@ -394,20 +395,22 @@ void __init bootmem_init(struct meminfo *mi)
 	max_pfn = max_low_pfn = memend_pfn - PHYS_PFN_OFFSET;
 }
 
-static inline void free_area(unsigned long addr, unsigned long end, char *s)
+static inline int free_area(unsigned long pfn, unsigned long end, char *s)
 {
-	unsigned int size = (end - addr) >> 10;
+	unsigned int pages = 0, size = (end - pfn) << (PAGE_SHIFT - 10);
 
-	for (; addr < end; addr += PAGE_SIZE) {
-		struct page *page = virt_to_page(addr);
+	for (; pfn < end; pfn++) {
+		struct page *page = pfn_to_page(pfn);
 		ClearPageReserved(page);
 		init_page_count(page);
-		free_page(addr);
-		totalram_pages++;
+		__free_page(page);
+		pages++;
 	}
 
 	if (size && s)
 		printk(KERN_INFO "Freeing %s memory: %dK\n", s, size);
+
+	return pages;
 }
 
 static inline void
@@ -478,13 +481,9 @@ static void __init free_unused_memmap_node(int node, struct meminfo *mi)
  */
 void __init mem_init(void)
 {
-	unsigned int codepages, datapages, initpages;
+	unsigned int codesize, datasize, initsize;
 	int i, node;
 
-	codepages = &_etext - &_text;
-	datapages = &_end - &__data_start;
-	initpages = &__init_end - &__init_begin;
-
 #ifndef CONFIG_DISCONTIGMEM
 	max_mapnr   = virt_to_page(high_memory) - mem_map;
 #endif
@@ -501,7 +500,8 @@ void __init mem_init(void)
 
 #ifdef CONFIG_SA1111
 	/* now that our DMA memory is actually so designated, we can free it */
-	free_area(PAGE_OFFSET, (unsigned long)swapper_pg_dir, NULL);
+	totalram_pages += free_area(PHYS_PFN_OFFSET,
+				    __phys_to_pfn(__pa(swapper_pg_dir)), NULL);
 #endif
 
 	/*
@@ -509,18 +509,21 @@ void __init mem_init(void)
 	 * real number of pages we have in this system
 	 */
 	printk(KERN_INFO "Memory:");
-
 	num_physpages = 0;
 	for (i = 0; i < meminfo.nr_banks; i++) {
 		num_physpages += bank_pfn_size(&meminfo.bank[i]);
 		printk(" %ldMB", bank_phys_size(&meminfo.bank[i]) >> 20);
 	}
-
 	printk(" = %luMB total\n", num_physpages >> (20 - PAGE_SHIFT));
+
+	codesize = _etext - _text;
+	datasize = _end - _data;
+	initsize = __init_end - __init_begin;
+
 	printk(KERN_NOTICE "Memory: %luKB available (%dK code, "
 		"%dK data, %dK init)\n",
 		(unsigned long) nr_free_pages() << (PAGE_SHIFT-10),
-		codepages >> 10, datapages >> 10, initpages >> 10);
+		codesize >> 10, datasize >> 10, initsize >> 10);
 
 	if (PAGE_SIZE >= 16384 && num_physpages <= 128) {
 		extern int sysctl_overcommit_memory;
@@ -535,11 +538,10 @@ void __init mem_init(void)
 
 void free_initmem(void)
 {
-	if (!machine_is_integrator() && !machine_is_cintegrator()) {
-		free_area((unsigned long)(&__init_begin),
-			  (unsigned long)(&__init_end),
-			  "init");
-	}
+	if (!machine_is_integrator() && !machine_is_cintegrator())
+		totalram_pages += free_area(__phys_to_pfn(__pa(__init_begin)),
+					    __phys_to_pfn(__pa(__init_end)),
+					    "init");
 }
 
 #ifdef CONFIG_BLK_DEV_INITRD
@@ -549,7 +551,9 @@ static int keep_initrd;
 void free_initrd_mem(unsigned long start, unsigned long end)
 {
 	if (!keep_initrd)
-		free_area(start, end, "initrd");
+		totalram_pages += free_area(__phys_to_pfn(__pa(start)),
+					    __phys_to_pfn(__pa(end)),
+					    "initrd");
 }
 
 static int __init keepinitrd_setup(char *__unused)
diff --git a/arch/arm/mm/mm.h b/arch/arm/mm/mm.h
index 5d9f53907b4e..95bbe112965e 100644
--- a/arch/arm/mm/mm.h
+++ b/arch/arm/mm/mm.h
@@ -32,7 +32,5 @@ struct meminfo;
 struct pglist_data;
 
 void __init create_mapping(struct map_desc *md);
-void __init bootmem_init(struct meminfo *mi);
+void __init bootmem_init(void);
 void reserve_node_zero(struct pglist_data *pgdat);
-
-extern void _text, _stext, _etext, __data_start, _end, __init_begin, __init_end;
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index 7f36c825718d..2ab5f962a053 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -17,6 +17,7 @@
 
 #include <asm/cputype.h>
 #include <asm/mach-types.h>
+#include <asm/sections.h>
 #include <asm/setup.h>
 #include <asm/sizes.h>
 #include <asm/tlb.h>
@@ -646,61 +647,79 @@ static void __init early_vmalloc(char **arg)
 			"vmalloc area too small, limiting to %luMB\n",
 			vmalloc_reserve >> 20);
 	}
+
+	if (vmalloc_reserve > VMALLOC_END - (PAGE_OFFSET + SZ_32M)) {
+		vmalloc_reserve = VMALLOC_END - (PAGE_OFFSET + SZ_32M);
+		printk(KERN_WARNING
+			"vmalloc area is too big, limiting to %luMB\n",
+			vmalloc_reserve >> 20);
+	}
 }
 __early_param("vmalloc=", early_vmalloc);
 
 #define VMALLOC_MIN	(void *)(VMALLOC_END - vmalloc_reserve)
 
-static int __init check_membank_valid(struct membank *mb)
+static void __init sanity_check_meminfo(void)
 {
-	/*
-	 * Check whether this memory region has non-zero size or
-	 * invalid node number.
-	 */
-	if (mb->size == 0 || mb->node >= MAX_NUMNODES)
-		return 0;
-
-	/*
-	 * Check whether this memory region would entirely overlap
-	 * the vmalloc area.
-	 */
-	if (phys_to_virt(mb->start) >= VMALLOC_MIN) {
-		printk(KERN_NOTICE "Ignoring RAM at %.8lx-%.8lx "
-			"(vmalloc region overlap).\n",
-			mb->start, mb->start + mb->size - 1);
-		return 0;
-	}
-
-	/*
-	 * Check whether this memory region would partially overlap
-	 * the vmalloc area.
-	 */
-	if (phys_to_virt(mb->start + mb->size) < phys_to_virt(mb->start) ||
-	    phys_to_virt(mb->start + mb->size) > VMALLOC_MIN) {
-		unsigned long newsize = VMALLOC_MIN - phys_to_virt(mb->start);
-
-		printk(KERN_NOTICE "Truncating RAM at %.8lx-%.8lx "
-			"to -%.8lx (vmalloc region overlap).\n",
-			mb->start, mb->start + mb->size - 1,
-			mb->start + newsize - 1);
-		mb->size = newsize;
-	}
+	int i, j;
 
-	return 1;
-}
+	for (i = 0, j = 0; i < meminfo.nr_banks; i++) {
+		struct membank *bank = &meminfo.bank[j];
+		*bank = meminfo.bank[i];
 
-static void __init sanity_check_meminfo(struct meminfo *mi)
-{
-	int i, j;
+#ifdef CONFIG_HIGHMEM
+		/*
+		 * Split those memory banks which are partially overlapping
+		 * the vmalloc area greatly simplifying things later.
+		 */
+		if (__va(bank->start) < VMALLOC_MIN &&
+		    bank->size > VMALLOC_MIN - __va(bank->start)) {
+			if (meminfo.nr_banks >= NR_BANKS) {
+				printk(KERN_CRIT "NR_BANKS too low, "
+						 "ignoring high memory\n");
+			} else {
+				memmove(bank + 1, bank,
+					(meminfo.nr_banks - i) * sizeof(*bank));
+				meminfo.nr_banks++;
+				i++;
+				bank[1].size -= VMALLOC_MIN - __va(bank->start);
+				bank[1].start = __pa(VMALLOC_MIN - 1) + 1;
+				j++;
+			}
+			bank->size = VMALLOC_MIN - __va(bank->start);
+		}
+#else
+		/*
+		 * Check whether this memory bank would entirely overlap
+		 * the vmalloc area.
+		 */
+		if (__va(bank->start) >= VMALLOC_MIN) {
+			printk(KERN_NOTICE "Ignoring RAM at %.8lx-%.8lx "
+			       "(vmalloc region overlap).\n",
+			       bank->start, bank->start + bank->size - 1);
+			continue;
+		}
 
-	for (i = 0, j = 0; i < mi->nr_banks; i++) {
-		if (check_membank_valid(&mi->bank[i]))
-			mi->bank[j++] = mi->bank[i];
+		/*
+		 * Check whether this memory bank would partially overlap
+		 * the vmalloc area.
+		 */
+		if (__va(bank->start + bank->size) > VMALLOC_MIN ||
+		    __va(bank->start + bank->size) < __va(bank->start)) {
+			unsigned long newsize = VMALLOC_MIN - __va(bank->start);
+			printk(KERN_NOTICE "Truncating RAM at %.8lx-%.8lx "
+			       "to -%.8lx (vmalloc region overlap).\n",
+			       bank->start, bank->start + bank->size - 1,
+			       bank->start + newsize - 1);
+			bank->size = newsize;
+		}
+#endif
+		j++;
 	}
-	mi->nr_banks = j;
+	meminfo.nr_banks = j;
 }
 
-static inline void prepare_page_table(struct meminfo *mi)
+static inline void prepare_page_table(void)
 {
 	unsigned long addr;
 
@@ -712,7 +731,7 @@ static inline void prepare_page_table(struct meminfo *mi)
 
 #ifdef CONFIG_XIP_KERNEL
 	/* The XIP kernel is mapped in the module area -- skip over it */
-	addr = ((unsigned long)&_etext + PGDIR_SIZE - 1) & PGDIR_MASK;
+	addr = ((unsigned long)_etext + PGDIR_SIZE - 1) & PGDIR_MASK;
 #endif
 	for ( ; addr < PAGE_OFFSET; addr += PGDIR_SIZE)
 		pmd_clear(pmd_off_k(addr));
@@ -721,7 +740,7 @@ static inline void prepare_page_table(struct meminfo *mi)
 	 * Clear out all the kernel space mappings, except for the first
 	 * memory bank, up to the end of the vmalloc region.
 	 */
-	for (addr = __phys_to_virt(mi->bank[0].start + mi->bank[0].size);
+	for (addr = __phys_to_virt(bank_phys_end(&meminfo.bank[0]));
 	     addr < VMALLOC_END; addr += PGDIR_SIZE)
 		pmd_clear(pmd_off_k(addr));
 }
@@ -738,10 +757,10 @@ void __init reserve_node_zero(pg_data_t *pgdat)
 	 * Note that this can only be in node 0.
 	 */
 #ifdef CONFIG_XIP_KERNEL
-	reserve_bootmem_node(pgdat, __pa(&__data_start), &_end - &__data_start,
+	reserve_bootmem_node(pgdat, __pa(_data), _end - _data,
 			BOOTMEM_DEFAULT);
 #else
-	reserve_bootmem_node(pgdat, __pa(&_stext), &_end - &_stext,
+	reserve_bootmem_node(pgdat, __pa(_stext), _end - _stext,
 			BOOTMEM_DEFAULT);
 #endif
 
@@ -820,7 +839,7 @@ static void __init devicemaps_init(struct machine_desc *mdesc)
 #ifdef CONFIG_XIP_KERNEL
 	map.pfn = __phys_to_pfn(CONFIG_XIP_PHYS_ADDR & SECTION_MASK);
 	map.virtual = MODULES_VADDR;
-	map.length = ((unsigned long)&_etext - map.virtual + ~SECTION_MASK) & SECTION_MASK;
+	map.length = ((unsigned long)_etext - map.virtual + ~SECTION_MASK) & SECTION_MASK;
 	map.type = MT_ROM;
 	create_mapping(&map);
 #endif
@@ -880,14 +899,14 @@ static void __init devicemaps_init(struct machine_desc *mdesc)
  * paging_init() sets up the page tables, initialises the zone memory
  * maps, and sets up the zero page, bad page and bad page tables.
  */
-void __init paging_init(struct meminfo *mi, struct machine_desc *mdesc)
+void __init paging_init(struct machine_desc *mdesc)
 {
 	void *zero_page;
 
 	build_mem_type_table();
-	sanity_check_meminfo(mi);
-	prepare_page_table(mi);
-	bootmem_init(mi);
+	sanity_check_meminfo();
+	prepare_page_table();
+	bootmem_init();
 	devicemaps_init(mdesc);
 
 	top_pmd = pmd_off_k(0xffff0000);
@@ -896,7 +915,7 @@ void __init paging_init(struct meminfo *mi, struct machine_desc *mdesc)
 	 * allocate the zero page.  Note that we count on this going ok.
 	 */
 	zero_page = alloc_bootmem_low_pages(PAGE_SIZE);
-	memzero(zero_page, PAGE_SIZE);
+	memset(zero_page, 0, PAGE_SIZE);
 	empty_zero_page = virt_to_page(zero_page);
 	flush_dcache_page(empty_zero_page);
 }
diff --git a/arch/arm/mm/nommu.c b/arch/arm/mm/nommu.c
index 07b62b238979..ad7bacc693b2 100644
--- a/arch/arm/mm/nommu.c
+++ b/arch/arm/mm/nommu.c
@@ -10,6 +10,7 @@
 #include <linux/io.h>
 
 #include <asm/cacheflush.h>
+#include <asm/sections.h>
 #include <asm/page.h>
 #include <asm/mach/arch.h>
 
@@ -25,10 +26,10 @@ void __init reserve_node_zero(pg_data_t *pgdat)
 	 * Note that this can only be in node 0.
 	 */
 #ifdef CONFIG_XIP_KERNEL
-	reserve_bootmem_node(pgdat, __pa(&__data_start), &_end - &__data_start,
+	reserve_bootmem_node(pgdat, __pa(_data), _end - _data,
 			BOOTMEM_DEFAULT);
 #else
-	reserve_bootmem_node(pgdat, __pa(&_stext), &_end - &_stext,
+	reserve_bootmem_node(pgdat, __pa(_stext), _end - _stext,
 			BOOTMEM_DEFAULT);
 #endif
 
@@ -41,27 +42,13 @@ void __init reserve_node_zero(pg_data_t *pgdat)
 			BOOTMEM_DEFAULT);
 }
 
-static void __init sanity_check_meminfo(struct meminfo *mi)
-{
-	int i, j;
-
-	for (i = 0, j = 0; i < mi->nr_banks; i++) {
-		struct membank *mb = &mi->bank[i];
-
-		if (mb->size != 0 && mb->node < MAX_NUMNODES)
-			mi->bank[j++] = mi->bank[i];
-	}
-	mi->nr_banks = j;
-}
-
 /*
  * paging_init() sets up the page tables, initialises the zone memory
  * maps, and sets up the zero page, bad page and bad page tables.
  */
-void __init paging_init(struct meminfo *mi, struct machine_desc *mdesc)
+void __init paging_init(struct machine_desc *mdesc)
 {
-	sanity_check_meminfo(mi);
-	bootmem_init(mi);
+	bootmem_init();
 }
 
 /*
diff --git a/arch/arm/mm/pgd.c b/arch/arm/mm/pgd.c
index e0f19ab91163..2690146161ba 100644
--- a/arch/arm/mm/pgd.c
+++ b/arch/arm/mm/pgd.c
@@ -31,7 +31,7 @@ pgd_t *get_pgd_slow(struct mm_struct *mm)
 	if (!new_pgd)
 		goto no_pgd;
 
-	memzero(new_pgd, FIRST_KERNEL_PGD_NR * sizeof(pgd_t));
+	memset(new_pgd, 0, FIRST_KERNEL_PGD_NR * sizeof(pgd_t));
 
 	/*
 	 * Copy over the kernel and IO PGD entries
diff --git a/arch/arm/mm/proc-syms.c b/arch/arm/mm/proc-syms.c
index 2b5ba396e3a6..4ad3bf291ad3 100644
--- a/arch/arm/mm/proc-syms.c
+++ b/arch/arm/mm/proc-syms.c
@@ -33,8 +33,8 @@ EXPORT_SYMBOL(cpu_cache);
 
 #ifdef CONFIG_MMU
 #ifndef MULTI_USER
-EXPORT_SYMBOL(__cpu_clear_user_page);
-EXPORT_SYMBOL(__cpu_copy_user_page);
+EXPORT_SYMBOL(__cpu_clear_user_highpage);
+EXPORT_SYMBOL(__cpu_copy_user_highpage);
 #else
 EXPORT_SYMBOL(cpu_user);
 #endif
diff --git a/arch/arm/mm/proc-v6.S b/arch/arm/mm/proc-v6.S
index 294943b85973..f0cc599facb7 100644
--- a/arch/arm/mm/proc-v6.S
+++ b/arch/arm/mm/proc-v6.S
@@ -71,6 +71,8 @@ ENTRY(cpu_v6_reset)
  *	IRQs are already disabled.
  */
 ENTRY(cpu_v6_do_idle)
+	mov	r1, #0
+	mcr	p15, 0, r1, c7, c10, 4		@ DWB - WFI may enter a low-power mode
 	mcr	p15, 0, r1, c7, c0, 4		@ wait for interrupt
 	mov	pc, lr
 
diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S
index 4d3c0a73e7fb..d1ebec42521d 100644
--- a/arch/arm/mm/proc-v7.S
+++ b/arch/arm/mm/proc-v7.S
@@ -20,9 +20,17 @@
 
 #define TTB_C		(1 << 0)
 #define TTB_S		(1 << 1)
+#define TTB_RGN_NC	(0 << 3)
+#define TTB_RGN_OC_WBWA	(1 << 3)
 #define TTB_RGN_OC_WT	(2 << 3)
 #define TTB_RGN_OC_WB	(3 << 3)
 
+#ifndef CONFIG_SMP
+#define TTB_FLAGS	TTB_C|TTB_RGN_OC_WB		@ mark PTWs cacheable, outer WB
+#else
+#define TTB_FLAGS	TTB_C|TTB_S|TTB_RGN_OC_WBWA	@ mark PTWs cacheable and shared, outer WBWA
+#endif
+
 ENTRY(cpu_v7_proc_init)
 	mov	pc, lr
 ENDPROC(cpu_v7_proc_init)
@@ -55,6 +63,7 @@ ENDPROC(cpu_v7_reset)
  *	IRQs are already disabled.
  */
 ENTRY(cpu_v7_do_idle)
+	dsb					@ WFI may enter a low-power mode
 	wfi
 	mov	pc, lr
 ENDPROC(cpu_v7_do_idle)
@@ -85,7 +94,7 @@ ENTRY(cpu_v7_switch_mm)
 #ifdef CONFIG_MMU
 	mov	r2, #0
 	ldr	r1, [r1, #MM_CONTEXT_ID]	@ get mm->context.id
-	orr	r0, r0, #TTB_RGN_OC_WB		@ mark PTWs outer cacheable, WB
+	orr	r0, r0, #TTB_FLAGS
 	mcr	p15, 0, r2, c13, c0, 1		@ set reserved context ID
 	isb
 1:	mcr	p15, 0, r0, c2, c0, 0		@ set TTB 0
@@ -162,6 +171,11 @@ cpu_v7_name:
  *	- cache type register is implemented
  */
 __v7_setup:
+#ifdef CONFIG_SMP
+	mrc	p15, 0, r0, c1, c0, 1		@ Enable SMP/nAMP mode
+	orr	r0, r0, #(0x1 << 6)
+	mcr	p15, 0, r0, c1, c0, 1
+#endif
 	adr	r12, __v7_setup_stack		@ the local stack
 	stmia	r12, {r0-r5, r7, r9, r11, lr}
 	bl	v7_flush_dcache_all
@@ -174,8 +188,7 @@ __v7_setup:
 #ifdef CONFIG_MMU
 	mcr	p15, 0, r10, c8, c7, 0		@ invalidate I + D TLBs
 	mcr	p15, 0, r10, c2, c0, 2		@ TTB control register
-	orr	r4, r4, #TTB_RGN_OC_WB		@ mark PTWs outer cacheable, WB
-	mcr	p15, 0, r4, c2, c0, 0		@ load TTB0
+	orr	r4, r4, #TTB_FLAGS
 	mcr	p15, 0, r4, c2, c0, 1		@ load TTB1
 	mov	r10, #0x1f			@ domains 0, 1 = manager
 	mcr	p15, 0, r10, c3, c0, 0		@ load domain access register
diff --git a/arch/arm/mm/proc-xsc3.S b/arch/arm/mm/proc-xsc3.S
index 8f6cf56c11c0..33515c214b92 100644
--- a/arch/arm/mm/proc-xsc3.S
+++ b/arch/arm/mm/proc-xsc3.S
@@ -481,3 +481,28 @@ __xsc3_proc_info:
 	.long	xsc3_mc_user_fns
 	.long	xsc3_cache_fns
 	.size	__xsc3_proc_info, . - __xsc3_proc_info
+
+/* Note: PXA935 changed its implementor ID from Intel to Marvell */
+
+	.type	__xsc3_pxa935_proc_info,#object
+__xsc3_pxa935_proc_info:
+	.long	0x56056000
+	.long	0xffffe000
+	.long	PMD_TYPE_SECT | \
+		PMD_SECT_BUFFERABLE | \
+		PMD_SECT_CACHEABLE | \
+		PMD_SECT_AP_WRITE | \
+		PMD_SECT_AP_READ
+	.long	PMD_TYPE_SECT | \
+		PMD_SECT_AP_WRITE | \
+		PMD_SECT_AP_READ
+	b	__xsc3_setup
+	.long	cpu_arch_name
+	.long	cpu_elf_name
+	.long	HWCAP_SWP|HWCAP_HALF|HWCAP_THUMB|HWCAP_FAST_MULT|HWCAP_EDSP
+	.long	cpu_xsc3_name
+	.long	xsc3_processor_functions
+	.long	v4wbi_tlb_fns
+	.long	xsc3_mc_user_fns
+	.long	xsc3_cache_fns
+	.size	__xsc3_pxa935_proc_info, . - __xsc3_pxa935_proc_info
diff --git a/arch/arm/plat-mxc/Kconfig b/arch/arm/plat-mxc/Kconfig
index b2a7e3fad117..a1612958a59e 100644
--- a/arch/arm/plat-mxc/Kconfig
+++ b/arch/arm/plat-mxc/Kconfig
@@ -8,11 +8,13 @@ choice
 
 config ARCH_MX2
 	bool "MX2-based"
+	select CPU_ARM926T
 	help
 	  This enables support for systems based on the Freescale i.MX2 family
 
 config ARCH_MX3
 	bool "MX3-based"
+	select CPU_V6
 	help
 	  This enables support for systems based on the Freescale i.MX3 family
 
diff --git a/arch/arm/plat-mxc/dma-mx1-mx2.c b/arch/arm/plat-mxc/dma-mx1-mx2.c
index b296f19fd89a..214274344442 100644
--- a/arch/arm/plat-mxc/dma-mx1-mx2.c
+++ b/arch/arm/plat-mxc/dma-mx1-mx2.c
@@ -34,7 +34,7 @@
 #include <asm/system.h>
 #include <asm/irq.h>
 #include <mach/hardware.h>
-#include <asm/dma.h>
+#include <mach/dma.h>
 #include <mach/dma-mx1-mx2.h>
 
 #define DMA_DCR     0x00		/* Control Register */
diff --git a/arch/arm/plat-mxc/include/mach/dma-mx1-mx2.h b/arch/arm/plat-mxc/include/mach/dma-mx1-mx2.h
index e85fd946116c..6cc6f0c8cb25 100644
--- a/arch/arm/plat-mxc/include/mach/dma-mx1-mx2.h
+++ b/arch/arm/plat-mxc/include/mach/dma-mx1-mx2.h
@@ -22,7 +22,7 @@
  * MA 02110-1301, USA.
  */
 
-#include <asm/dma.h>
+#include <mach/dma.h>
 
 #ifndef __ASM_ARCH_MXC_DMA_H
 #define __ASM_ARCH_MXC_DMA_H
diff --git a/arch/arm/plat-mxc/include/mach/dma.h b/arch/arm/plat-mxc/include/mach/dma.h
deleted file mode 100644
index c822d569a05e..000000000000
--- a/arch/arm/plat-mxc/include/mach/dma.h
+++ /dev/null
@@ -1,14 +0,0 @@
-/*
- * Copyright 2004-2007 Freescale Semiconductor, Inc. All Rights Reserved.
- */
-
-/*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#ifndef __ASM_ARCH_MXC_DMA_H__
-#define __ASM_ARCH_MXC_DMA_H__
-
-#endif
diff --git a/arch/arm/plat-mxc/include/mach/io.h b/arch/arm/plat-mxc/include/mach/io.h
index 5d4cb1196441..c0cb267e7403 100644
--- a/arch/arm/plat-mxc/include/mach/io.h
+++ b/arch/arm/plat-mxc/include/mach/io.h
@@ -35,8 +35,8 @@ __mx3_ioremap(unsigned long phys_addr, size_t size, unsigned int mtype)
 #endif
 
 /* io address mapping macro */
-#define __io(a)			((void __iomem *)(a))
+#define __io(a)		__typesafe_io(a)
 
-#define __mem_pci(a)		(a)
+#define __mem_pci(a)	(a)
 
 #endif
diff --git a/arch/arm/plat-mxc/include/mach/memory.h b/arch/arm/plat-mxc/include/mach/memory.h
index d7a8d3ebed57..203688e6164e 100644
--- a/arch/arm/plat-mxc/include/mach/memory.h
+++ b/arch/arm/plat-mxc/include/mach/memory.h
@@ -13,17 +13,4 @@
 
 #include <mach/hardware.h>
 
-/*
- * Virtual view <-> DMA view memory address translations
- * This macro is used to translate the virtual address to an address
- * suitable to be passed to set_dma_addr()
- */
-#define __virt_to_bus(a)	__virt_to_phys(a)
-
-/*
- * Used to convert an address for DMA operations to an address that the
- * kernel can use.
- */
-#define __bus_to_virt(a)	__phys_to_virt(a)
-
 #endif /* __ASM_ARCH_MXC_MEMORY_H__ */
diff --git a/arch/arm/plat-mxc/include/mach/usb.h b/arch/arm/plat-mxc/include/mach/usb.h
new file mode 100644
index 000000000000..2dacb3086f1c
--- /dev/null
+++ b/arch/arm/plat-mxc/include/mach/usb.h
@@ -0,0 +1,23 @@
+/*
+ *	Copyright (C) 2008 Darius Augulis <augulis.darius@gmail.com>
+ *
+ *	This program is free software; you can redistribute it and/or modify
+ *	it under the terms of the GNU General Public License as published by
+ *	the Free Software Foundation; either version 2 of the License, or
+ *	(at your option) any later version.
+ *
+ *	This program is distributed in the hope that it will be useful,
+ *	but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *	MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *	GNU General Public License for more details.
+ */
+
+#ifndef __ASM_ARCH_MXC_USB
+#define __ASM_ARCH_MXC_USB
+
+struct imxusb_platform_data {
+	int (*init)(struct device *);
+	int (*exit)(struct device *);
+};
+
+#endif /* __ASM_ARCH_MXC_USB */
diff --git a/arch/arm/plat-omap/Kconfig b/arch/arm/plat-omap/Kconfig
index a94f0c44ebc8..46d3b0b9ce69 100644
--- a/arch/arm/plat-omap/Kconfig
+++ b/arch/arm/plat-omap/Kconfig
@@ -14,9 +14,11 @@ config ARCH_OMAP1
 
 config ARCH_OMAP2
 	bool "TI OMAP2"
+	select CPU_V6
 
 config ARCH_OMAP3
 	bool "TI OMAP3"
+	select CPU_V7
 
 endchoice
 
diff --git a/arch/arm/plat-omap/dma.c b/arch/arm/plat-omap/dma.c
index 50f8b4ad9a09..7686b9fa53f2 100644
--- a/arch/arm/plat-omap/dma.c
+++ b/arch/arm/plat-omap/dma.c
@@ -29,7 +29,7 @@
 
 #include <asm/system.h>
 #include <mach/hardware.h>
-#include <asm/dma.h>
+#include <mach/dma.h>
 
 #include <mach/tc.h>
 
diff --git a/arch/arm/plat-omap/include/mach/io.h b/arch/arm/plat-omap/include/mach/io.h
index adc83b7b8205..d92bf7964481 100644
--- a/arch/arm/plat-omap/include/mach/io.h
+++ b/arch/arm/plat-omap/include/mach/io.h
@@ -42,8 +42,8 @@
  * We don't actually have real ISA nor PCI buses, but there is so many
  * drivers out there that might just work if we fake them...
  */
-#define __io(a)			((void __iomem *)(PCIO_BASE + (a)))
-#define __mem_pci(a)		(a)
+#define __io(a)		__typesafe_io(a)
+#define __mem_pci(a)	(a)
 
 /*
  * ----------------------------------------------------------------------------
@@ -51,8 +51,6 @@
  * ----------------------------------------------------------------------------
  */
 
-#define PCIO_BASE	0
-
 #if defined(CONFIG_ARCH_OMAP1)
 
 #define IO_PHYS			0xFFFB0000
diff --git a/arch/arm/plat-omap/include/mach/memory.h b/arch/arm/plat-omap/include/mach/memory.h
index d40cac60b959..d6b5ca6c7da2 100644
--- a/arch/arm/plat-omap/include/mach/memory.h
+++ b/arch/arm/plat-omap/include/mach/memory.h
@@ -43,18 +43,7 @@
 #endif
 
 /*
- * Conversion between SDRAM and fake PCI bus, used by USB
- * NOTE: Physical address must be converted to Local Bus address
- *	 on OMAP-1510 only
- */
-
-/*
  * Bus address is physical address, except for OMAP-1510 Local Bus.
- */
-#define __virt_to_bus(x)	__virt_to_phys(x)
-#define __bus_to_virt(x)	__phys_to_virt(x)
-
-/*
  * OMAP-1510 bus address is translated into a Local Bus address if the
  * OMAP bus type is lbus. We do the address translation based on the
  * device overriding the defaults used in the dma-mapping API.
@@ -70,20 +59,20 @@
 
 #define virt_to_lbus(x)		((x) - PAGE_OFFSET + OMAP1510_LB_OFFSET)
 #define lbus_to_virt(x)		((x) - OMAP1510_LB_OFFSET + PAGE_OFFSET)
-#define is_lbus_device(dev)	(cpu_is_omap15xx() && dev && (strncmp(dev->bus_id, "ohci", 4) == 0))
+#define is_lbus_device(dev)	(cpu_is_omap15xx() && dev && (strncmp(dev_name(dev), "ohci", 4) == 0))
 
 #define __arch_page_to_dma(dev, page)	({is_lbus_device(dev) ? \
 					(dma_addr_t)virt_to_lbus(page_address(page)) : \
-					(dma_addr_t)__virt_to_bus(page_address(page));})
+					(dma_addr_t)__virt_to_phys(page_address(page));})
 
 #define __arch_dma_to_virt(dev, addr)	({ (void *) (is_lbus_device(dev) ? \
 						lbus_to_virt(addr) : \
-						__bus_to_virt(addr)); })
+						__phys_to_virt(addr)); })
 
 #define __arch_virt_to_dma(dev, addr)	({ unsigned long __addr = (unsigned long)(addr); \
 					   (dma_addr_t) (is_lbus_device(dev) ? \
 						virt_to_lbus(__addr) : \
-						__virt_to_bus(__addr)); })
+						__virt_to_phys(__addr)); })
 
 #endif	/* CONFIG_ARCH_OMAP15XX */
 
diff --git a/arch/arm/plat-omap/include/mach/omapfb.h b/arch/arm/plat-omap/include/mach/omapfb.h
index ec67fb428607..7b74d1255e0b 100644
--- a/arch/arm/plat-omap/include/mach/omapfb.h
+++ b/arch/arm/plat-omap/include/mach/omapfb.h
@@ -353,8 +353,8 @@ struct omapfb_device {
 	u32			pseudo_palette[17];
 
 	struct lcd_panel	*panel;			/* LCD panel */
-	struct lcd_ctrl         *ctrl;			/* LCD controller */
-	struct lcd_ctrl		*int_ctrl;		/* internal LCD ctrl */
+	const struct lcd_ctrl	*ctrl;			/* LCD controller */
+	const struct lcd_ctrl	*int_ctrl;		/* internal LCD ctrl */
 	struct lcd_ctrl_extif	*ext_if;		/* LCD ctrl external
 							   interface */
 	struct device		*dev;
diff --git a/arch/arm/plat-omap/sram.c b/arch/arm/plat-omap/sram.c
index 9f9a921829c0..dcd9d16da2e9 100644
--- a/arch/arm/plat-omap/sram.c
+++ b/arch/arm/plat-omap/sram.c
@@ -255,7 +255,7 @@ void omap_sram_reprogram_clock(u32 dpllctl, u32 ckctl)
 	if (!_omap_sram_reprogram_clock)
 		omap_sram_error();
 
-	return _omap_sram_reprogram_clock(dpllctl, ckctl);
+	_omap_sram_reprogram_clock(dpllctl, ckctl);
 }
 
 int __init omap1_sram_init(void)
@@ -282,8 +282,8 @@ void omap2_sram_ddr_init(u32 *slow_dll_ctrl, u32 fast_dll_ctrl,
 	if (!_omap2_sram_ddr_init)
 		omap_sram_error();
 
-	return _omap2_sram_ddr_init(slow_dll_ctrl, fast_dll_ctrl,
-				    base_cs, force_unlock);
+	_omap2_sram_ddr_init(slow_dll_ctrl, fast_dll_ctrl,
+			     base_cs, force_unlock);
 }
 
 static void (*_omap2_sram_reprogram_sdrc)(u32 perf_level, u32 dll_val,
@@ -294,7 +294,7 @@ void omap2_sram_reprogram_sdrc(u32 perf_level, u32 dll_val, u32 mem_type)
 	if (!_omap2_sram_reprogram_sdrc)
 		omap_sram_error();
 
-	return _omap2_sram_reprogram_sdrc(perf_level, dll_val, mem_type);
+	_omap2_sram_reprogram_sdrc(perf_level, dll_val, mem_type);
 }
 
 static u32 (*_omap2_set_prcm)(u32 dpll_ctrl_val, u32 sdrc_rfr_val, int bypass);
diff --git a/arch/arm/plat-omap/usb.c b/arch/arm/plat-omap/usb.c
index 67ca1e216df7..add0485703b5 100644
--- a/arch/arm/plat-omap/usb.c
+++ b/arch/arm/plat-omap/usb.c
@@ -77,38 +77,6 @@
 
 /*-------------------------------------------------------------------------*/
 
-#if	defined(CONFIG_ARCH_OMAP_OTG) || defined(CONFIG_USB_MUSB_OTG)
-
-static struct otg_transceiver *xceiv;
-
-/**
- * otg_get_transceiver - find the (single) OTG transceiver driver
- *
- * Returns the transceiver driver, after getting a refcount to it; or
- * null if there is no such transceiver.  The caller is responsible for
- * releasing that count.
- */
-struct otg_transceiver *otg_get_transceiver(void)
-{
-	if (xceiv)
-		get_device(xceiv->dev);
-	return xceiv;
-}
-EXPORT_SYMBOL(otg_get_transceiver);
-
-int otg_set_transceiver(struct otg_transceiver *x)
-{
-	if (xceiv && x)
-		return -EBUSY;
-	xceiv = x;
-	return 0;
-}
-EXPORT_SYMBOL(otg_set_transceiver);
-
-#endif
-
-/*-------------------------------------------------------------------------*/
-
 #if defined(CONFIG_ARCH_OMAP_OTG) || defined(CONFIG_ARCH_OMAP15XX)
 
 static void omap2_usb_devconf_clear(u8 port, u32 mask)
diff --git a/arch/arm/plat-orion/pcie.c b/arch/arm/plat-orion/pcie.c
index 883902fead89..d41d41d78ad9 100644
--- a/arch/arm/plat-orion/pcie.c
+++ b/arch/arm/plat-orion/pcie.c
@@ -35,7 +35,7 @@
 #define  PCIE_CONF_REG(r)		((((r) & 0xf00) << 16) | ((r) & 0xfc))
 #define  PCIE_CONF_BUS(b)		(((b) & 0xff) << 16)
 #define  PCIE_CONF_DEV(d)		(((d) & 0x1f) << 11)
-#define  PCIE_CONF_FUNC(f)		(((f) & 0x3) << 8)
+#define  PCIE_CONF_FUNC(f)		(((f) & 0x7) << 8)
 #define PCIE_CONF_DATA_OFF	0x18fc
 #define PCIE_MASK_OFF		0x1910
 #define PCIE_CTRL_OFF		0x1a00
diff --git a/include/asm-arm/plat-s3c/iic.h b/arch/arm/plat-s3c/include/plat/iic.h
index 5106acaa1d0e..5106acaa1d0e 100644
--- a/include/asm-arm/plat-s3c/iic.h
+++ b/arch/arm/plat-s3c/include/plat/iic.h
diff --git a/include/asm-arm/plat-s3c/nand.h b/arch/arm/plat-s3c/include/plat/nand.h
index f4dcd14af059..f4dcd14af059 100644
--- a/include/asm-arm/plat-s3c/nand.h
+++ b/arch/arm/plat-s3c/include/plat/nand.h
diff --git a/include/asm-arm/plat-s3c/regs-ac97.h b/arch/arm/plat-s3c/include/plat/regs-ac97.h
index c3878f7acb83..c3878f7acb83 100644
--- a/include/asm-arm/plat-s3c/regs-ac97.h
+++ b/arch/arm/plat-s3c/include/plat/regs-ac97.h
diff --git a/include/asm-arm/plat-s3c/regs-iic.h b/arch/arm/plat-s3c/include/plat/regs-iic.h
index 2f7c17de8ac8..2f7c17de8ac8 100644
--- a/include/asm-arm/plat-s3c/regs-iic.h
+++ b/arch/arm/plat-s3c/include/plat/regs-iic.h
diff --git a/include/asm-arm/plat-s3c/regs-nand.h b/arch/arm/plat-s3c/include/plat/regs-nand.h
index b2caa4bca270..b2caa4bca270 100644
--- a/include/asm-arm/plat-s3c/regs-nand.h
+++ b/arch/arm/plat-s3c/include/plat/regs-nand.h
diff --git a/include/asm-arm/plat-s3c/regs-rtc.h b/arch/arm/plat-s3c/include/plat/regs-rtc.h
index d5837cf8e402..d5837cf8e402 100644
--- a/include/asm-arm/plat-s3c/regs-rtc.h
+++ b/arch/arm/plat-s3c/include/plat/regs-rtc.h
diff --git a/include/asm-arm/plat-s3c/regs-watchdog.h b/arch/arm/plat-s3c/include/plat/regs-watchdog.h
index 4938492470f7..4938492470f7 100644
--- a/include/asm-arm/plat-s3c/regs-watchdog.h
+++ b/arch/arm/plat-s3c/include/plat/regs-watchdog.h
diff --git a/arch/arm/plat-s3c/include/plat/uncompress.h b/arch/arm/plat-s3c/include/plat/uncompress.h
index 4df006b9cc10..8a8a927292e0 100644
--- a/arch/arm/plat-s3c/include/plat/uncompress.h
+++ b/arch/arm/plat-s3c/include/plat/uncompress.h
@@ -28,7 +28,7 @@ static void arch_detect_cpu(void);
 /* defines for UART registers */
 
 #include <plat/regs-serial.h>
-#include <asm/plat-s3c/regs-watchdog.h>
+#include <plat/regs-watchdog.h>
 
 /* working in physical space... */
 #undef S3C2410_WDOGREG
diff --git a/arch/arm/plat-s3c24xx/common-smdk.c b/arch/arm/plat-s3c24xx/common-smdk.c
index 3098736c65d9..3d4837021ac7 100644
--- a/arch/arm/plat-s3c24xx/common-smdk.c
+++ b/arch/arm/plat-s3c24xx/common-smdk.c
@@ -38,7 +38,7 @@
 #include <mach/regs-gpio.h>
 #include <mach/leds-gpio.h>
 
-#include <asm/plat-s3c/nand.h>
+#include <plat/nand.h>
 
 #include <plat/common-smdk.h>
 #include <plat/devs.h>
diff --git a/arch/arm/plat-s3c24xx/devs.c b/arch/arm/plat-s3c24xx/devs.c
index e93f8bf6d338..adf535aaf43a 100644
--- a/arch/arm/plat-s3c24xx/devs.c
+++ b/arch/arm/plat-s3c24xx/devs.c
@@ -29,11 +29,11 @@
 #include <asm/irq.h>
 
 #include <plat/regs-serial.h>
-#include <asm/plat-s3c24xx/udc.h>
+#include <plat/udc.h>
 
 #include <plat/devs.h>
 #include <plat/cpu.h>
-#include <asm/plat-s3c24xx/regs-spi.h>
+#include <plat/regs-spi.h>
 
 /* Serial port registrations */
 
diff --git a/arch/arm/plat-s3c24xx/dma.c b/arch/arm/plat-s3c24xx/dma.c
index 1baf941d1930..63bb22b973e3 100644
--- a/arch/arm/plat-s3c24xx/dma.c
+++ b/arch/arm/plat-s3c24xx/dma.c
@@ -31,9 +31,8 @@
 #include <asm/system.h>
 #include <asm/irq.h>
 #include <mach/hardware.h>
-#include <asm/dma.h>
+#include <mach/dma.h>
 
-#include <asm/mach/dma.h>
 #include <mach/map.h>
 
 #include <plat/dma.h>
@@ -804,7 +803,7 @@ EXPORT_SYMBOL(s3c2410_dma_request);
  * allowed to go through.
 */
 
-int s3c2410_dma_free(dmach_t channel, struct s3c2410_dma_client *client)
+int s3c2410_dma_free(unsigned int channel, struct s3c2410_dma_client *client)
 {
 	struct s3c2410_dma_chan *chan = lookup_dma_channel(channel);
 	unsigned long flags;
@@ -995,7 +994,7 @@ static int s3c2410_dma_started(struct s3c2410_dma_chan *chan)
 }
 
 int
-s3c2410_dma_ctrl(dmach_t channel, enum s3c2410_chan_op op)
+s3c2410_dma_ctrl(unsigned int channel, enum s3c2410_chan_op op)
 {
 	struct s3c2410_dma_chan *chan = lookup_dma_channel(channel);
 
@@ -1043,7 +1042,7 @@ EXPORT_SYMBOL(s3c2410_dma_ctrl);
  * dcon:         base value of the DCONx register
 */
 
-int s3c2410_dma_config(dmach_t channel,
+int s3c2410_dma_config(unsigned int channel,
 		       int xferunit,
 		       int dcon)
 {
@@ -1092,7 +1091,7 @@ int s3c2410_dma_config(dmach_t channel,
 
 EXPORT_SYMBOL(s3c2410_dma_config);
 
-int s3c2410_dma_setflags(dmach_t channel, unsigned int flags)
+int s3c2410_dma_setflags(unsigned int channel, unsigned int flags)
 {
 	struct s3c2410_dma_chan *chan = lookup_dma_channel(channel);
 
@@ -1113,7 +1112,7 @@ EXPORT_SYMBOL(s3c2410_dma_setflags);
  * irq?
 */
 
-int s3c2410_dma_set_opfn(dmach_t channel, s3c2410_dma_opfn_t rtn)
+int s3c2410_dma_set_opfn(unsigned int channel, s3c2410_dma_opfn_t rtn)
 {
 	struct s3c2410_dma_chan *chan = lookup_dma_channel(channel);
 
@@ -1129,7 +1128,7 @@ int s3c2410_dma_set_opfn(dmach_t channel, s3c2410_dma_opfn_t rtn)
 
 EXPORT_SYMBOL(s3c2410_dma_set_opfn);
 
-int s3c2410_dma_set_buffdone_fn(dmach_t channel, s3c2410_dma_cbfn_t rtn)
+int s3c2410_dma_set_buffdone_fn(unsigned int channel, s3c2410_dma_cbfn_t rtn)
 {
 	struct s3c2410_dma_chan *chan = lookup_dma_channel(channel);
 
@@ -1219,7 +1218,7 @@ EXPORT_SYMBOL(s3c2410_dma_devconfig);
  * returns the current transfer points for the dma source and destination
 */
 
-int s3c2410_dma_getposition(dmach_t channel, dma_addr_t *src, dma_addr_t *dst)
+int s3c2410_dma_getposition(unsigned int channel, dma_addr_t *src, dma_addr_t *dst)
 {
  	struct s3c2410_dma_chan *chan = lookup_dma_channel(channel);
 
diff --git a/include/asm-arm/plat-s3c24xx/mci.h b/arch/arm/plat-s3c24xx/include/plat/mci.h
index 2d0852ac3b27..2d0852ac3b27 100644
--- a/include/asm-arm/plat-s3c24xx/mci.h
+++ b/arch/arm/plat-s3c24xx/include/plat/mci.h
diff --git a/include/asm-arm/plat-s3c24xx/regs-spi.h b/arch/arm/plat-s3c24xx/include/plat/regs-spi.h
index 2b35479ee35c..2b35479ee35c 100644
--- a/include/asm-arm/plat-s3c24xx/regs-spi.h
+++ b/arch/arm/plat-s3c24xx/include/plat/regs-spi.h
diff --git a/include/asm-arm/plat-s3c24xx/regs-udc.h b/arch/arm/plat-s3c24xx/include/plat/regs-udc.h
index f0dd4a41b37b..f0dd4a41b37b 100644
--- a/include/asm-arm/plat-s3c24xx/regs-udc.h
+++ b/arch/arm/plat-s3c24xx/include/plat/regs-udc.h
diff --git a/include/asm-arm/plat-s3c24xx/udc.h b/arch/arm/plat-s3c24xx/include/plat/udc.h
index 546bb4008f49..546bb4008f49 100644
--- a/include/asm-arm/plat-s3c24xx/udc.h
+++ b/arch/arm/plat-s3c24xx/include/plat/udc.h
diff --git a/arch/arm/tools/mach-types b/arch/arm/tools/mach-types
index 43aa2020f85c..fd23c0e9e698 100644
--- a/arch/arm/tools/mach-types
+++ b/arch/arm/tools/mach-types
@@ -12,7 +12,7 @@
 #
 #   http://www.arm.linux.org.uk/developer/machines/?action=new
 #
-# Last update: Thu Sep 25 10:10:50 2008
+# Last update: Sun Nov 30 16:39:36 2008
 #
 # machine_is_xxx	CONFIG_xxxx		MACH_TYPE_xxx		number
 #
@@ -1380,7 +1380,7 @@ holon			MACH_HOLON		HOLON			1377
 olip8			MACH_OLIP8		OLIP8			1378
 ghi270hg		MACH_GHI270HG		GHI270HG		1379
 davinci_dm6467_evm	MACH_DAVINCI_DM6467_EVM	DAVINCI_DM6467_EVM	1380
-davinci_dm355_evm	MACH_DAVINCI_DM350_EVM	DAVINCI_DM350_EVM	1381
+davinci_dm355_evm	MACH_DAVINCI_DM355_EVM	DAVINCI_DM355_EVM	1381
 blackriver		MACH_BLACKRIVER		BLACKRIVER		1383
 sandgate_wp		MACH_SANDGATEWP		SANDGATEWP		1384
 cdotbwsg		MACH_CDOTBWSG		CDOTBWSG		1385
@@ -1771,7 +1771,7 @@ axs_ultrax		MACH_AXS_ULTRAX		AXS_ULTRAX		1779
 at572d940deb		MACH_AT572D940DEB	AT572D940DEB		1780
 davinci_da8xx_evm	MACH_DAVINCI_DA8XX_EVM	DAVINCI_DA8XX_EVM	1781
 ep9302			MACH_EP9302		EP9302			1782
-at572d940hfeb		MACH_AT572D940HFEB	AT572D940HFEB		1783
+at572d940hfek		MACH_AT572D940HFEB	AT572D940HFEB		1783
 cybook3			MACH_CYBOOK3		CYBOOK3			1784
 wdg002			MACH_WDG002		WDG002			1785
 sg560adsl		MACH_SG560ADSL		SG560ADSL		1786
@@ -1899,3 +1899,98 @@ rut100			MACH_RUT100		RUT100			1908
 asusp535		MACH_ASUSP535		ASUSP535		1909
 htcraphael		MACH_HTCRAPHAEL		HTCRAPHAEL		1910
 sygdg1			MACH_SYGDG1		SYGDG1			1911
+sygdg2			MACH_SYGDG2		SYGDG2			1912
+seoul			MACH_SEOUL		SEOUL			1913
+salerno			MACH_SALERNO		SALERNO			1914
+ucn_s3c64xx		MACH_UCN_S3C64XX	UCN_S3C64XX		1915
+msm7201a		MACH_MSM7201A		MSM7201A		1916
+lpr1			MACH_LPR1		LPR1			1917
+armadillo500fx		MACH_ARMADILLO500FX	ARMADILLO500FX		1918
+g3evm			MACH_G3EVM		G3EVM			1919
+z3_dm355		MACH_Z3_DM355		Z3_DM355		1920
+w90p910evb		MACH_W90P910EVB		W90P910EVB		1921
+w90p920evb		MACH_W90P920EVB		W90P920EVB		1922
+w90p950evb		MACH_W90P950EVB		W90P950EVB		1923
+w90n960evb		MACH_W90N960EVB		W90N960EVB		1924
+camhd			MACH_CAMHD		CAMHD			1925
+mvc100			MACH_MVC100		MVC100			1926
+electrum_200		MACH_ELECTRUM_200	ELECTRUM_200		1927
+htcjade			MACH_HTCJADE		HTCJADE			1928
+memphis			MACH_MEMPHIS		MEMPHIS			1929
+imx27sbc		MACH_IMX27SBC		IMX27SBC		1930
+lextar			MACH_LEXTAR		LEXTAR			1931
+mv88f6281gtw_ge		MACH_MV88F6281GTW_GE	MV88F6281GTW_GE		1932
+ncp			MACH_NCP		NCP			1933
+z32an_series		MACH_Z32AN		Z32AN			1934
+tmq_capd		MACH_TMQ_CAPD		TMQ_CAPD		1935
+omap3_wl		MACH_OMAP3_WL		OMAP3_WL		1936
+chumby			MACH_CHUMBY		CHUMBY			1937
+atsarm9			MACH_ATSARM9		ATSARM9			1938
+davinci_dm365_evm	MACH_DAVINCI_DM365_EVM	DAVINCI_DM365_EVM	1939
+bahamas			MACH_BAHAMAS		BAHAMAS			1940
+das			MACH_DAS		DAS			1941
+minidas			MACH_MINIDAS		MINIDAS			1942
+vk1000			MACH_VK1000		VK1000			1943
+centro			MACH_CENTRO		CENTRO			1944
+ctera_2bay		MACH_CTERA_2BAY		CTERA_2BAY		1945
+edgeconnect		MACH_EDGECONNECT	EDGECONNECT		1946
+nd27000			MACH_ND27000		ND27000			1947
+cobra			MACH_GEMALTO_COBRA	GEMALTO_COBRA		1948
+ingelabs_comet		MACH_INGELABS_COMET	INGELABS_COMET		1949
+pollux_wiz		MACH_POLLUX_WIZ		POLLUX_WIZ		1950
+blackstone		MACH_BLACKSTONE		BLACKSTONE		1951
+topaz			MACH_TOPAZ		TOPAZ			1952
+aixle			MACH_AIXLE		AIXLE			1953
+mw998			MACH_MW998		MW998			1954
+nokia_rx51		MACH_NOKIA_RX51		NOKIA_RX51		1955
+vsc5605ev		MACH_VSC5605EV		VSC5605EV		1956
+nt98700dk		MACH_NT98700DK		NT98700DK		1957
+icontact		MACH_ICONTACT		ICONTACT		1958
+swarco_frcpu		MACH_SWARCO_FRCPU	SWARCO_FRCPU		1959
+swarco_scpu		MACH_SWARCO_SCPU	SWARCO_SCPU		1960
+bbox_p16		MACH_BBOX_P16		BBOX_P16		1961
+bstd			MACH_BSTD		BSTD			1962
+sbc2440ii		MACH_SBC2440II		SBC2440II		1963
+pcm034			MACH_PCM034		PCM034			1964
+neso			MACH_NESO		NESO			1965
+wlnx_9g20		MACH_WLNX_9G20		WLNX_9G20		1966
+omap_zoom2		MACH_OMAP_ZOOM2		OMAP_ZOOM2		1967
+totemnova		MACH_TOTEMNOVA		TOTEMNOVA		1968
+c5000			MACH_C5000		C5000			1969
+unipo_at91sam9263	MACH_UNIPO_AT91SAM9263	UNIPO_AT91SAM9263	1970
+ethernut5		MACH_ETHERNUT5		ETHERNUT5		1971
+arm11			MACH_ARM11		ARM11			1972
+cpuat9260		MACH_CPUAT9260		CPUAT9260		1973
+cpupxa255		MACH_CPUPXA255		CPUPXA255		1974
+cpuimx27		MACH_CPUIMX27		CPUIMX27		1975
+cheflux			MACH_CHEFLUX		CHEFLUX			1976
+eb_cpux9k2		MACH_EB_CPUX9K2		EB_CPUX9K2		1977
+opcotec			MACH_OPCOTEC		OPCOTEC			1978
+yt			MACH_YT			YT			1979
+motoq			MACH_MOTOQ		MOTOQ			1980
+bsb1			MACH_BSB1		BSB1			1981
+acs5k			MACH_ACS5K		ACS5K			1982
+milan			MACH_MILAN		MILAN			1983
+quartzv2		MACH_QUARTZV2		QUARTZV2		1984
+rsvp			MACH_RSVP		RSVP			1985
+rmp200			MACH_RMP200		RMP200			1986
+snapper_9260		MACH_SNAPPER_9260	SNAPPER_9260		1987
+dsm320			MACH_DSM320		DSM320			1988
+adsgcm			MACH_ADSGCM		ADSGCM			1989
+ase2_400		MACH_ASE2_400		ASE2_400		1990
+pizza			MACH_PIZZA		PIZZA			1991
+spot_ngpl		MACH_SPOT_NGPL		SPOT_NGPL		1992
+armata			MACH_ARMATA		ARMATA			1993
+exeda			MACH_EXEDA		EXEDA			1994
+mx31sf005		MACH_MX31SF005		MX31SF005		1995
+f5d8231_4_v2		MACH_F5D8231_4_V2	F5D8231_4_V2		1996
+q2440			MACH_Q2440		Q2440			1997
+qq2440			MACH_QQ2440		QQ2440			1998
+mini2440		MACH_MINI2440		MINI2440		1999
+colibri300		MACH_COLIBRI300		COLIBRI300		2000
+jades			MACH_JADES		JADES			2001
+spark			MACH_SPARK		SPARK			2002
+benzina			MACH_BENZINA		BENZINA			2003
+blaze			MACH_BLAZE		BLAZE			2004
+linkstation_ls_hgl	MACH_LINKSTATION_LS_HGL	LINKSTATION_LS_HGL	2005
+htcvenus		MACH_HTCVENUS		HTCVENUS		2006
diff --git a/arch/arm/vfp/vfphw.S b/arch/arm/vfp/vfphw.S
index a62dcf7098ba..3c73aafe3e01 100644
--- a/arch/arm/vfp/vfphw.S
+++ b/arch/arm/vfp/vfphw.S
@@ -101,9 +101,12 @@ ENTRY(vfp_support_entry)
 	VFPFSTMIA r4, r5		@ save the working registers
 	VFPFMRX	r5, FPSCR		@ current status
 	tst	r1, #FPEXC_EX		@ is there additional state to save?
-	VFPFMRX	r6, FPINST, NE		@ FPINST (only if FPEXC.EX is set)
-	tstne	r1, #FPEXC_FP2V		@ is there an FPINST2 to read?
-	VFPFMRX	r8, FPINST2, NE		@ FPINST2 if needed (and present)
+	beq	1f
+	VFPFMRX	r6, FPINST		@ FPINST (only if FPEXC.EX is set)
+	tst	r1, #FPEXC_FP2V		@ is there an FPINST2 to read?
+	beq	1f
+	VFPFMRX	r8, FPINST2		@ FPINST2 if needed (and present)
+1:
 	stmia	r4, {r1, r5, r6, r8}	@ save FPEXC, FPSCR, FPINST, FPINST2
 					@ and point r4 at the word at the
 					@ start of the register dump
@@ -117,9 +120,12 @@ no_old_VFP_process:
 					@ FPEXC is in a safe state
 	ldmia	r10, {r1, r5, r6, r8}	@ load FPEXC, FPSCR, FPINST, FPINST2
 	tst	r1, #FPEXC_EX		@ is there additional state to restore?
-	VFPFMXR	FPINST, r6, NE		@ restore FPINST (only if FPEXC.EX is set)
-	tstne	r1, #FPEXC_FP2V		@ is there an FPINST2 to write?
-	VFPFMXR	FPINST2, r8, NE		@ FPINST2 if needed (and present)
+	beq	1f
+	VFPFMXR	FPINST, r6		@ restore FPINST (only if FPEXC.EX is set)
+	tst	r1, #FPEXC_FP2V		@ is there an FPINST2 to write?
+	beq	1f
+	VFPFMXR	FPINST2, r8		@ FPINST2 if needed (and present)
+1:
 	VFPFMXR	FPSCR, r5		@ restore status
 
 check_for_exception:
@@ -175,9 +181,12 @@ ENTRY(vfp_save_state)
 	VFPFSTMIA r0, r2		@ save the working registers
 	VFPFMRX	r2, FPSCR		@ current status
 	tst	r1, #FPEXC_EX		@ is there additional state to save?
-	VFPFMRX	r3, FPINST, NE		@ FPINST (only if FPEXC.EX is set)
-	tstne	r1, #FPEXC_FP2V		@ is there an FPINST2 to read?
-	VFPFMRX	r12, FPINST2, NE	@ FPINST2 if needed (and present)
+	beq	1f
+	VFPFMRX	r3, FPINST		@ FPINST (only if FPEXC.EX is set)
+	tst	r1, #FPEXC_FP2V		@ is there an FPINST2 to read?
+	beq	1f
+	VFPFMRX	r12, FPINST2		@ FPINST2 if needed (and present)
+1:
 	stmia	r0, {r1, r2, r3, r12}	@ save FPEXC, FPSCR, FPINST, FPINST2
 	mov	pc, lr
 ENDPROC(vfp_save_state)
diff --git a/arch/arm/vfp/vfpmodule.c b/arch/arm/vfp/vfpmodule.c
index c0d2c9bb952b..67ca340a7c85 100644
--- a/arch/arm/vfp/vfpmodule.c
+++ b/arch/arm/vfp/vfpmodule.c
@@ -371,6 +371,15 @@ static int __init vfp_init(void)
 		 * in place; report VFP support to userspace.
 		 */
 		elf_hwcap |= HWCAP_VFP;
+#ifdef CONFIG_NEON
+		/*
+		 * Check for the presence of the Advanced SIMD
+		 * load/store instructions, integer and single
+		 * precision floating point operations.
+		 */
+		if ((fmrx(MVFR1) & 0x000fff00) == 0x00011100)
+			elf_hwcap |= HWCAP_NEON;
+#endif
 	}
 	return 0;
 }
diff --git a/arch/avr32/mach-at32ap/at32ap700x.c b/arch/avr32/mach-at32ap/at32ap700x.c
index 0c6e02f80a31..066252eebf61 100644
--- a/arch/avr32/mach-at32ap/at32ap700x.c
+++ b/arch/avr32/mach-at32ap/at32ap700x.c
@@ -967,28 +967,28 @@ static inline void configure_usart0_pins(void)
 {
 	u32 pin_mask = (1 << 8) | (1 << 9); /* RXD & TXD */
 
-	select_peripheral(PIOA, pin_mask, PERIPH_B, 0);
+	select_peripheral(PIOA, pin_mask, PERIPH_B, AT32_GPIOF_PULLUP);
 }
 
 static inline void configure_usart1_pins(void)
 {
 	u32 pin_mask = (1 << 17) | (1 << 18); /* RXD & TXD */
 
-	select_peripheral(PIOA, pin_mask, PERIPH_A, 0);
+	select_peripheral(PIOA, pin_mask, PERIPH_A, AT32_GPIOF_PULLUP);
 }
 
 static inline void configure_usart2_pins(void)
 {
 	u32 pin_mask = (1 << 26) | (1 << 27); /* RXD & TXD */
 
-	select_peripheral(PIOB, pin_mask, PERIPH_B, 0);
+	select_peripheral(PIOB, pin_mask, PERIPH_B, AT32_GPIOF_PULLUP);
 }
 
 static inline void configure_usart3_pins(void)
 {
 	u32 pin_mask = (1 << 18) | (1 << 17); /* RXD & TXD */
 
-	select_peripheral(PIOB, pin_mask, PERIPH_B, 0);
+	select_peripheral(PIOB, pin_mask, PERIPH_B, AT32_GPIOF_PULLUP);
 }
 
 static struct platform_device *__initdata at32_usarts[4];
diff --git a/arch/avr32/mach-at32ap/clock.c b/arch/avr32/mach-at32ap/clock.c
index 138a00a2a2d0..442f08c5e641 100644
--- a/arch/avr32/mach-at32ap/clock.c
+++ b/arch/avr32/mach-at32ap/clock.c
@@ -198,7 +198,7 @@ dump_clock(struct clk *parent, struct clkinf *r)
 	unsigned	i;
 
 	/* skip clocks coupled to devices that aren't registered */
-	if (parent->dev && !parent->dev->bus_id[0] && !parent->users)
+	if (parent->dev && !dev_name(parent->dev) && !parent->users)
 		return;
 
 	/* <nest spaces> name <pad to end> */
@@ -214,7 +214,7 @@ dump_clock(struct clk *parent, struct clkinf *r)
 		parent->users ? "on" : "off",	/* NOTE: not-paranoid!! */
 		clk_get_rate(parent));
 	if (parent->dev)
-		seq_printf(r->s, ", for %s", parent->dev->bus_id);
+		seq_printf(r->s, ", for %s", dev_name(parent->dev));
 	seq_printf(r->s, "\n");
 
 	/* cost of this scan is small, but not linear... */
diff --git a/arch/blackfin/boot/Makefile b/arch/blackfin/boot/Makefile
index 522f3c124060..e028d13481a9 100644
--- a/arch/blackfin/boot/Makefile
+++ b/arch/blackfin/boot/Makefile
@@ -25,7 +25,7 @@ $(obj)/vmlinux.gz: $(obj)/vmlinux.bin FORCE
 
 $(obj)/vmImage: $(obj)/vmlinux.gz
 	$(call if_changed,uimage)
-	@echo 'Kernel: $@ is ready'
+	@$(kecho) 'Kernel: $@ is ready'
 
 install:
 	sh $(srctree)/$(src)/install.sh $(KERNELRELEASE) $(BOOTIMAGE) System.map "$(INSTALL_PATH)"
diff --git a/arch/cris/arch-v32/drivers/iop_fw_load.c b/arch/cris/arch-v32/drivers/iop_fw_load.c
index 3b3857ec1f15..2f8ea0f7a63c 100644
--- a/arch/cris/arch-v32/drivers/iop_fw_load.c
+++ b/arch/cris/arch-v32/drivers/iop_fw_load.c
@@ -24,12 +24,12 @@
 #error "Please contact <greg@kroah.com> for details on how to fix it properly."
 
 static struct device iop_spu_device[2] = {
-	{ .bus_id =     "iop-spu0", },
-	{ .bus_id =     "iop-spu1", },
+	{ .init_name =     "iop-spu0", },
+	{ .init_name =     "iop-spu1", },
 };
 
 static struct device iop_mpu_device = {
-	.bus_id =       "iop-mpu",
+	.init_name =       "iop-mpu",
 };
 
 static int wait_mpu_idle(void)
diff --git a/arch/cris/include/arch-v10/arch/byteorder.h b/arch/cris/include/arch-v10/arch/byteorder.h
index 255b646b7fa8..ffbd6673a098 100644
--- a/arch/cris/include/arch-v10/arch/byteorder.h
+++ b/arch/cris/include/arch-v10/arch/byteorder.h
@@ -9,18 +9,20 @@
  * them together into ntohl etc.
  */
 
-static inline __attribute_const__ __u32 ___arch__swab32(__u32 x)
+static inline __attribute_const__ __u32 __arch_swab32(__u32 x)
 {
 	__asm__ ("swapwb %0" : "=r" (x) : "0" (x));
-  
+
 	return(x);
 }
+#define __arch_swab32 __arch_swab32
 
-static inline __attribute_const__ __u16 ___arch__swab16(__u16 x)
+static inline __attribute_const__ __u16 __arch_swab16(__u16 x)
 {
 	__asm__ ("swapb %0" : "=r" (x) : "0" (x));
-	
+
 	return(x);
 }
+#define __arch_swab16 __arch_swab16
 
 #endif
diff --git a/arch/cris/include/arch-v32/arch/byteorder.h b/arch/cris/include/arch-v32/arch/byteorder.h
index 6ef8fb4a35f2..fb76087fa2d9 100644
--- a/arch/cris/include/arch-v32/arch/byteorder.h
+++ b/arch/cris/include/arch-v32/arch/byteorder.h
@@ -4,17 +4,19 @@
 #include <asm/types.h>
 
 static inline __const__ __u32
-___arch__swab32(__u32 x)
+__arch_swab32(__u32 x)
 {
 	__asm__ __volatile__ ("swapwb %0" : "=r" (x) : "0" (x));
 	return (x);
 }
+#define __arch_swab32 __arch_swab32
 
 static inline __const__ __u16
-___arch__swab16(__u16 x)
+__arch_swab16(__u16 x)
 {
 	__asm__ __volatile__ ("swapb %0" : "=r" (x) : "0" (x));
 	return (x);
 }
+#define __arch_swab16 __arch_swab16
 
 #endif /* _ASM_CRIS_ARCH_BYTEORDER_H */
diff --git a/arch/cris/include/asm/byteorder.h b/arch/cris/include/asm/byteorder.h
index cc8e418cfd14..420c03021343 100644
--- a/arch/cris/include/asm/byteorder.h
+++ b/arch/cris/include/asm/byteorder.h
@@ -1,26 +1,14 @@
 #ifndef _CRIS_BYTEORDER_H
 #define _CRIS_BYTEORDER_H
 
-#ifdef __GNUC__
+#define __LITTLE_ENDIAN
+#define __SWAB_64_THRU_32__
 
 #ifdef __KERNEL__
-#include <arch/byteorder.h>
-
-/* defines are necessary because the other files detect the presence
- * of a defined __arch_swab32, not an inline
- */
-#define __arch__swab32(x) ___arch__swab32(x)
-#define __arch__swab16(x) ___arch__swab16(x)
-#endif /* __KERNEL__ */
-
-#if !defined(__STRICT_ANSI__) || defined(__KERNEL__)
-#  define __BYTEORDER_HAS_U64__
-#  define __SWAB_64_THRU_32__
+# include <arch/byteorder.h>
 #endif
 
-#endif /* __GNUC__ */
-
-#include <linux/byteorder/little_endian.h>
+#include <linux/byteorder.h>
 
 #endif
 
diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig
index 6bd91ed7cd03..7fa8f615ba6e 100644
--- a/arch/ia64/Kconfig
+++ b/arch/ia64/Kconfig
@@ -99,7 +99,7 @@ config GENERIC_IOMAP
 	bool
 	default y
 
-config SCHED_NO_NO_OMIT_FRAME_POINTER
+config SCHED_OMIT_FRAME_POINTER
 	bool
 	default y
 
diff --git a/arch/ia64/kernel/pci-dma.c b/arch/ia64/kernel/pci-dma.c
index 2a92f637431d..d0ada067a4af 100644
--- a/arch/ia64/kernel/pci-dma.c
+++ b/arch/ia64/kernel/pci-dma.c
@@ -39,7 +39,7 @@ int iommu_detected __read_mostly;
    be probably a smaller DMA mask, but this is bug-to-bug compatible
    to i386. */
 struct device fallback_dev = {
-	.bus_id = "fallback device",
+	.init_name = "fallback device",
 	.coherent_dma_mask = DMA_32BIT_MASK,
 	.dma_mask = &fallback_dev.coherent_dma_mask,
 };
diff --git a/arch/ia64/sn/kernel/tiocx.c b/arch/ia64/sn/kernel/tiocx.c
index a88eba3314d7..3f864238566d 100644
--- a/arch/ia64/sn/kernel/tiocx.c
+++ b/arch/ia64/sn/kernel/tiocx.c
@@ -206,8 +206,7 @@ cx_device_register(nasid_t nasid, int part_num, int mfg_num,
 	cx_dev->dev.parent = NULL;
 	cx_dev->dev.bus = &tiocx_bus_type;
 	cx_dev->dev.release = tiocx_bus_release;
-	snprintf(cx_dev->dev.bus_id, BUS_ID_SIZE, "%d",
-		 cx_dev->cx_id.nasid);
+	dev_set_name(&cx_dev->dev, "%d", cx_dev->cx_id.nasid);
 	device_register(&cx_dev->dev);
 	get_device(&cx_dev->dev);
 
diff --git a/arch/m32r/Kconfig b/arch/m32r/Kconfig
index dbaed4a63815..29047d5c259a 100644
--- a/arch/m32r/Kconfig
+++ b/arch/m32r/Kconfig
@@ -273,7 +273,7 @@ config GENERIC_CALIBRATE_DELAY
 	bool
 	default y
 
-config SCHED_NO_NO_OMIT_FRAME_POINTER
+config SCHED_OMIT_FRAME_POINTER
         bool
         default y
 
diff --git a/arch/m68k/fpsp040/setox.S b/arch/m68k/fpsp040/setox.S
index 145af5447581..f1acf7e36d6b 100644
--- a/arch/m68k/fpsp040/setox.S
+++ b/arch/m68k/fpsp040/setox.S
@@ -36,9 +36,9 @@
 |	depending on their values, the program may run faster or slower --
 |	but no worse than 10% slower even in the extreme cases.
 |
-|	The program setoxm1 takes approximately ???/??? cycles for input
+|	The program setoxm1 takes approximately ??? / ??? cycles for input
 |	argument X, 0.25 <= |X| < 70log2. For |X| < 0.25, it takes
-|	approximately ???/??? cycles. For the less common arguments,
+|	approximately ??? / ??? cycles. For the less common arguments,
 |	depending on their values, the program may run faster or slower --
 |	but no worse than 10% slower even in the extreme cases.
 |
diff --git a/arch/m68k/mac/baboon.c b/arch/m68k/mac/baboon.c
index c7b25b0aacff..245d16d078ad 100644
--- a/arch/m68k/mac/baboon.c
+++ b/arch/m68k/mac/baboon.c
@@ -18,11 +18,14 @@
 #include <asm/macints.h>
 #include <asm/mac_baboon.h>
 
-/* #define DEBUG_BABOON */
 /* #define DEBUG_IRQS */
 
+extern void mac_enable_irq(unsigned int);
+extern void mac_disable_irq(unsigned int);
+
 int baboon_present;
 static volatile struct baboon *baboon;
+static unsigned char baboon_disabled;
 
 #if 0
 extern int macide_ack_intr(struct ata_channel *);
@@ -88,34 +91,51 @@ static irqreturn_t baboon_irq(int irq, void *dev_id)
 
 void __init baboon_register_interrupts(void)
 {
-	request_irq(IRQ_NUBUS_C, baboon_irq, IRQ_FLG_LOCK|IRQ_FLG_FAST,
-		    "baboon", (void *) baboon);
+	baboon_disabled = 0;
+	request_irq(IRQ_NUBUS_C, baboon_irq, 0, "baboon", (void *)baboon);
 }
 
-void baboon_irq_enable(int irq) {
+/*
+ * The means for masking individual baboon interrupts remains a mystery, so
+ * enable the umbrella interrupt only when no baboon interrupt is disabled.
+ */
+
+void baboon_irq_enable(int irq)
+{
+	int irq_idx = IRQ_IDX(irq);
+
 #ifdef DEBUG_IRQUSE
 	printk("baboon_irq_enable(%d)\n", irq);
 #endif
-	/* FIXME: figure out how to mask and unmask baboon interrupt sources */
-	enable_irq(IRQ_NUBUS_C);
+
+	baboon_disabled &= ~(1 << irq_idx);
+	if (!baboon_disabled)
+		mac_enable_irq(IRQ_NUBUS_C);
 }
 
-void baboon_irq_disable(int irq) {
+void baboon_irq_disable(int irq)
+{
+	int irq_idx = IRQ_IDX(irq);
+
 #ifdef DEBUG_IRQUSE
 	printk("baboon_irq_disable(%d)\n", irq);
 #endif
-	disable_irq(IRQ_NUBUS_C);
+
+	baboon_disabled |= 1 << irq_idx;
+	if (baboon_disabled)
+		mac_disable_irq(IRQ_NUBUS_C);
 }
 
-void baboon_irq_clear(int irq) {
-	int irq_idx	= IRQ_IDX(irq);
+void baboon_irq_clear(int irq)
+{
+	int irq_idx = IRQ_IDX(irq);
 
 	baboon->mb_ifr &= ~(1 << irq_idx);
 }
 
 int baboon_irq_pending(int irq)
 {
-	int irq_idx	= IRQ_IDX(irq);
+	int irq_idx = IRQ_IDX(irq);
 
 	return baboon->mb_ifr & (1 << irq_idx);
 }
diff --git a/arch/m68k/mac/config.c b/arch/m68k/mac/config.c
index c45e18449f32..8819b97be324 100644
--- a/arch/m68k/mac/config.c
+++ b/arch/m68k/mac/config.c
@@ -162,10 +162,7 @@ void __init config_mac(void)
 	mach_init_IRQ = mac_init_IRQ;
 	mach_get_model = mac_get_model;
 	mach_gettimeoffset = mac_gettimeoffset;
-#warning move to adb/via init
-#if 0
 	mach_hwclk = mac_hwclk;
-#endif
 	mach_set_clock_mmss = mac_set_clock_mmss;
 	mach_reset = mac_reset;
 	mach_halt = mac_poweroff;
diff --git a/arch/m68k/mac/debug.c b/arch/m68k/mac/debug.c
index 2165740786a5..65dd77a742a3 100644
--- a/arch/m68k/mac/debug.c
+++ b/arch/m68k/mac/debug.c
@@ -24,7 +24,6 @@
 #define BOOTINFO_COMPAT_1_0
 #include <asm/setup.h>
 #include <asm/bootinfo.h>
-#include <asm/machw.h>
 #include <asm/macints.h>
 
 extern unsigned long mac_videobase;
diff --git a/arch/m68k/mac/macints.c b/arch/m68k/mac/macints.c
index ecddac4a02b9..82e560c076ce 100644
--- a/arch/m68k/mac/macints.c
+++ b/arch/m68k/mac/macints.c
@@ -127,7 +127,6 @@
 #include <asm/irq.h>
 #include <asm/traps.h>
 #include <asm/bootinfo.h>
-#include <asm/machw.h>
 #include <asm/macintosh.h>
 #include <asm/mac_via.h>
 #include <asm/mac_psc.h>
@@ -215,8 +214,8 @@ irqreturn_t mac_debug_handler(int, void *);
 
 /* #define DEBUG_MACINTS */
 
-static void mac_enable_irq(unsigned int irq);
-static void mac_disable_irq(unsigned int irq);
+void mac_enable_irq(unsigned int irq);
+void mac_disable_irq(unsigned int irq);
 
 static struct irq_controller mac_irq_controller = {
 	.name		= "mac",
@@ -275,7 +274,7 @@ void __init mac_init_IRQ(void)
  * These routines are just dispatchers to the VIA/OSS/PSC routines.
  */
 
-static void mac_enable_irq(unsigned int irq)
+void mac_enable_irq(unsigned int irq)
 {
 	int irq_src = IRQ_SRC(irq);
 
@@ -308,7 +307,7 @@ static void mac_enable_irq(unsigned int irq)
 	}
 }
 
-static void mac_disable_irq(unsigned int irq)
+void mac_disable_irq(unsigned int irq)
 {
 	int irq_src = IRQ_SRC(irq);
 
diff --git a/arch/m68k/mac/misc.c b/arch/m68k/mac/misc.c
index 56d1f5676ade..a44c7086ab39 100644
--- a/arch/m68k/mac/misc.c
+++ b/arch/m68k/mac/misc.c
@@ -93,7 +93,7 @@ static void cuda_write_pram(int offset, __u8 data)
 #define cuda_write_pram NULL
 #endif
 
-#ifdef CONFIG_ADB_PMU68K
+#if 0 /* def CONFIG_ADB_PMU68K */
 static long pmu_read_time(void)
 {
 	struct adb_request req;
@@ -148,7 +148,7 @@ static void pmu_write_pram(int offset, __u8 data)
 #define pmu_write_pram NULL
 #endif
 
-#ifdef CONFIG_ADB_MACIISI
+#if 0 /* def CONFIG_ADB_MACIISI */
 extern int maciisi_request(struct adb_request *req,
 			void (*done)(struct adb_request *), int nbytes, ...);
 
@@ -717,13 +717,18 @@ int mac_hwclk(int op, struct rtc_time *t)
 		unmktime(now, 0,
 			 &t->tm_year, &t->tm_mon, &t->tm_mday,
 			 &t->tm_hour, &t->tm_min, &t->tm_sec);
+#if 0
 		printk("mac_hwclk: read %04d-%02d-%-2d %02d:%02d:%02d\n",
-			t->tm_year + 1900, t->tm_mon + 1, t->tm_mday, t->tm_hour, t->tm_min, t->tm_sec);
+			t->tm_year + 1900, t->tm_mon + 1, t->tm_mday,
+			t->tm_hour, t->tm_min, t->tm_sec);
+#endif
 	} else { /* write */
+#if 0
 		printk("mac_hwclk: tried to write %04d-%02d-%-2d %02d:%02d:%02d\n",
-			t->tm_year + 1900, t->tm_mon + 1, t->tm_mday, t->tm_hour, t->tm_min, t->tm_sec);
+			t->tm_year + 1900, t->tm_mon + 1, t->tm_mday,
+			t->tm_hour, t->tm_min, t->tm_sec);
+#endif
 
-#if 0	/* it trashes my rtc */
 		now = mktime(t->tm_year + 1900, t->tm_mon + 1, t->tm_mday,
 			     t->tm_hour, t->tm_min, t->tm_sec);
 
@@ -742,7 +747,6 @@ int mac_hwclk(int op, struct rtc_time *t)
 		case MAC_ADB_IISI:
 			maciisi_write_time(now);
 		}
-#endif
 	}
 	return 0;
 }
diff --git a/arch/m68k/mac/oss.c b/arch/m68k/mac/oss.c
index 43d83e054b8e..8426501119ca 100644
--- a/arch/m68k/mac/oss.c
+++ b/arch/m68k/mac/oss.c
@@ -21,7 +21,6 @@
 #include <linux/init.h>
 
 #include <asm/bootinfo.h>
-#include <asm/machw.h>
 #include <asm/macintosh.h>
 #include <asm/macints.h>
 #include <asm/mac_via.h>
diff --git a/arch/m68k/mac/via.c b/arch/m68k/mac/via.c
index 1bdb03c73c0f..f01d418e64fe 100644
--- a/arch/m68k/mac/via.c
+++ b/arch/m68k/mac/via.c
@@ -32,15 +32,10 @@
 #include <asm/bootinfo.h>
 #include <asm/macintosh.h>
 #include <asm/macints.h>
-#include <asm/machw.h>
 #include <asm/mac_via.h>
 #include <asm/mac_psc.h>
 
 volatile __u8 *via1, *via2;
-#if 0
-/* See note in mac_via.h about how this is possibly not useful */
-volatile long *via_memory_bogon=(long *)&via_memory_bogon;
-#endif
 int rbv_present;
 int via_alt_mapping;
 EXPORT_SYMBOL(via_alt_mapping);
@@ -66,7 +61,7 @@ static int gIER,gIFR,gBufA,gBufB;
 #define MAC_CLOCK_LOW		(MAC_CLOCK_TICK&0xFF)
 #define MAC_CLOCK_HIGH		(MAC_CLOCK_TICK>>8)
 
-/* To disable a NuBus slot on Quadras we make the slot IRQ lines outputs, set
+/* To disable a NuBus slot on Quadras we make that slot IRQ line an output set
  * high. On RBV we just use the slot interrupt enable register. On Macs with
  * genuine VIA chips we must use nubus_disabled to keep track of disabled slot
  * interrupts. When any slot IRQ is disabled we mask the (edge triggered) CA1
@@ -180,7 +175,7 @@ void __init via_init(void)
 	via1[vT1CH] = 0;
 	via1[vT2CL] = 0;
 	via1[vT2CH] = 0;
-	via1[vACR] &= 0x3F;
+	via1[vACR] &= ~0xC0; /* setup T1 timer with no PB7 output */
 	via1[vACR] &= ~0x03; /* disable port A & B latches */
 
 	/*
@@ -203,40 +198,41 @@ void __init via_init(void)
 
 	/* Everything below this point is VIA2/RBV only... */
 
-	if (oss_present) return;
+	if (oss_present)
+		return;
 
-#if 1
 	/* Some machines support an alternate IRQ mapping that spreads  */
 	/* Ethernet and Sound out to their own autolevel IRQs and moves */
 	/* VIA1 to level 6. A/UX uses this mapping and we do too.  Note */
 	/* that the IIfx emulates this alternate mapping using the OSS. */
 
-	switch(macintosh_config->ident) {
-		case MAC_MODEL_P475:
-		case MAC_MODEL_P475F:
-		case MAC_MODEL_P575:
-		case MAC_MODEL_Q605:
-		case MAC_MODEL_Q605_ACC:
-		case MAC_MODEL_C610:
-		case MAC_MODEL_Q610:
-		case MAC_MODEL_Q630:
-		case MAC_MODEL_C650:
-		case MAC_MODEL_Q650:
-		case MAC_MODEL_Q700:
-		case MAC_MODEL_Q800:
-		case MAC_MODEL_Q900:
-		case MAC_MODEL_Q950:
+	via_alt_mapping = 0;
+	if (macintosh_config->via_type == MAC_VIA_QUADRA)
+		switch (macintosh_config->ident) {
+		case MAC_MODEL_C660:
+		case MAC_MODEL_Q840:
+			/* not applicable */
+			break;
+		case MAC_MODEL_P588:
+		case MAC_MODEL_TV:
+		case MAC_MODEL_PB140:
+		case MAC_MODEL_PB145:
+		case MAC_MODEL_PB160:
+		case MAC_MODEL_PB165:
+		case MAC_MODEL_PB165C:
+		case MAC_MODEL_PB170:
+		case MAC_MODEL_PB180:
+		case MAC_MODEL_PB180C:
+		case MAC_MODEL_PB190:
+		case MAC_MODEL_PB520:
+			/* not yet tested */
+			break;
+		default:
 			via_alt_mapping = 1;
 			via1[vDirB] |= 0x40;
 			via1[vBufB] &= ~0x40;
 			break;
-		default:
-			via_alt_mapping = 0;
-			break;
-	}
-#else
-	via_alt_mapping = 0;
-#endif
+		}
 
 	/*
 	 * Now initialize VIA2. For RBV we just kill all interrupts;
@@ -252,14 +248,17 @@ void __init via_init(void)
 		via2[vT1CH] = 0;
 		via2[vT2CL] = 0;
 		via2[vT2CH] = 0;
-		via2[vACR] &= 0x3F;
+		via2[vACR] &= ~0xC0; /* setup T1 timer with no PB7 output */
 		via2[vACR] &= ~0x03; /* disable port A & B latches */
 	}
 
 	/*
-	 * Set vPCR for SCSI interrupts (but not on RBV)
+	 * Set vPCR for control line interrupts (but not on RBV)
 	 */
 	if (!rbv_present) {
+		/* For all VIA types, CA1 (SLOTS IRQ) and CB1 (ASC IRQ)
+		 * are made negative edge triggered here.
+		 */
 		if (macintosh_config->scsi_type == MAC_SCSI_OLD) {
 			/* CB2 (IRQ) indep. input, positive edge */
 			/* CA2 (DRQ) indep. input, positive edge */
@@ -466,21 +465,6 @@ irqreturn_t via1_irq(int irq, void *dev_id)
 		++irq_num;
 		irq_bit <<= 1;
 	} while (events >= irq_bit);
-
-#if 0 /* freakin' pmu is doing weird stuff */
-	if (!oss_present) {
-		/* This (still) seems to be necessary to get IDE
-		   working.  However, if you enable VBL interrupts,
-		   you're screwed... */
-		/* FIXME: should we check the SLOTIRQ bit before
-                   pulling this stunt? */
-		/* No, it won't be set. that's why we're doing this. */
-		via_irq_disable(IRQ_MAC_NUBUS);
-		via_irq_clear(IRQ_MAC_NUBUS);
-		m68k_handle_int(IRQ_MAC_NUBUS);
-		via_irq_enable(IRQ_MAC_NUBUS);
-	}
-#endif
 	return IRQ_HANDLED;
 }
 
diff --git a/arch/m68knommu/platform/coldfire/entry.S b/arch/m68knommu/platform/coldfire/entry.S
index 1e3c0dcbd7ac..3b471c0da24a 100644
--- a/arch/m68knommu/platform/coldfire/entry.S
+++ b/arch/m68knommu/platform/coldfire/entry.S
@@ -215,19 +215,8 @@ ENTRY(fasthandler)
 	RESTORE_LOCAL
 
 ENTRY(ret_from_interrupt)
-	moveb	%sp@(PT_SR),%d0
-	andl	#0x7,%d0
-	jeq	1f
-
-	RESTORE_ALL
-
-1:
-	/* check if we need to do software interrupts */
-	movel	irq_stat+CPUSTAT_SOFTIRQ_PENDING,%d0
-	jeq	ret_from_exception
-
-	pea	ret_from_exception
-	jmp	do_softirq
+	/* the fasthandler is confusing me, haven't seen any user */
+	jmp	ret_from_exception
 
 /*
  * Beware - when entering resume, prev (the current task) is
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index f4af967a6b30..a5255e7c79e0 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -653,7 +653,7 @@ config GENERIC_CMOS_UPDATE
 	bool
 	default y
 
-config SCHED_NO_NO_OMIT_FRAME_POINTER
+config SCHED_OMIT_FRAME_POINTER
 	bool
 	default y
 
diff --git a/arch/mips/configs/fulong_defconfig b/arch/mips/configs/fulong_defconfig
index 620980081a30..b6698a232ae9 100644
--- a/arch/mips/configs/fulong_defconfig
+++ b/arch/mips/configs/fulong_defconfig
@@ -1,63 +1,78 @@
 #
 # Automatically generated make config: don't edit
-# Linux kernel version: 2.6.22-rc4
-# Mon Jun 11 00:23:51 2007
+# Linux kernel version: 2.6.28-rc6
+# Fri Nov 28 17:53:48 2008
 #
 CONFIG_MIPS=y
 
 #
 # Machine selection
 #
-CONFIG_LEMOTE_FULONG=y
 # CONFIG_MACH_ALCHEMY is not set
 # CONFIG_BASLER_EXCITE is not set
+# CONFIG_BCM47XX is not set
 # CONFIG_MIPS_COBALT is not set
 # CONFIG_MACH_DECSTATION is not set
 # CONFIG_MACH_JAZZ is not set
+# CONFIG_LASAT is not set
+CONFIG_LEMOTE_FULONG=y
 # CONFIG_MIPS_MALTA is not set
-# CONFIG_WR_PPMC is not set
 # CONFIG_MIPS_SIM is not set
+# CONFIG_MACH_EMMA is not set
+# CONFIG_MACH_VR41XX is not set
+# CONFIG_NXP_STB220 is not set
+# CONFIG_NXP_STB225 is not set
 # CONFIG_PNX8550_JBS is not set
 # CONFIG_PNX8550_STB810 is not set
-# CONFIG_MACH_VR41XX is not set
+# CONFIG_PMC_MSP is not set
 # CONFIG_PMC_YOSEMITE is not set
-# CONFIG_MARKEINS is not set
 # CONFIG_SGI_IP22 is not set
 # CONFIG_SGI_IP27 is not set
+# CONFIG_SGI_IP28 is not set
 # CONFIG_SGI_IP32 is not set
-# CONFIG_SIBYTE_BIGSUR is not set
-# CONFIG_SIBYTE_SWARM is not set
-# CONFIG_SIBYTE_SENTOSA is not set
-# CONFIG_SIBYTE_RHONE is not set
-# CONFIG_SIBYTE_CARMEL is not set
-# CONFIG_SIBYTE_LITTLESUR is not set
 # CONFIG_SIBYTE_CRHINE is not set
+# CONFIG_SIBYTE_CARMEL is not set
 # CONFIG_SIBYTE_CRHONE is not set
+# CONFIG_SIBYTE_RHONE is not set
+# CONFIG_SIBYTE_SWARM is not set
+# CONFIG_SIBYTE_LITTLESUR is not set
+# CONFIG_SIBYTE_SENTOSA is not set
+# CONFIG_SIBYTE_BIGSUR is not set
 # CONFIG_SNI_RM is not set
-# CONFIG_TOSHIBA_JMR3927 is not set
-# CONFIG_TOSHIBA_RBTX4927 is not set
-# CONFIG_TOSHIBA_RBTX4938 is not set
+# CONFIG_MACH_TX39XX is not set
+# CONFIG_MACH_TX49XX is not set
+# CONFIG_MIKROTIK_RB532 is not set
+# CONFIG_WR_PPMC is not set
 CONFIG_RWSEM_GENERIC_SPINLOCK=y
 # CONFIG_ARCH_HAS_ILOG2_U32 is not set
 # CONFIG_ARCH_HAS_ILOG2_U64 is not set
+CONFIG_ARCH_SUPPORTS_OPROFILE=y
 CONFIG_GENERIC_FIND_NEXT_BIT=y
 CONFIG_GENERIC_HWEIGHT=y
 CONFIG_GENERIC_CALIBRATE_DELAY=y
+CONFIG_GENERIC_CLOCKEVENTS=y
 CONFIG_GENERIC_TIME=y
+CONFIG_GENERIC_CMOS_UPDATE=y
 CONFIG_SCHED_NO_NO_OMIT_FRAME_POINTER=y
 CONFIG_GENERIC_HARDIRQS_NO__DO_IRQ=y
+CONFIG_CEVT_R4K=y
+CONFIG_CSRC_R4K=y
 CONFIG_DMA_NONCOHERENT=y
 CONFIG_DMA_NEED_PCI_MAP_STATE=y
 CONFIG_EARLY_PRINTK=y
 CONFIG_SYS_HAS_EARLY_PRINTK=y
+# CONFIG_HOTPLUG_CPU is not set
 CONFIG_I8259=y
 # CONFIG_NO_IOPORT is not set
+CONFIG_GENERIC_ISA_DMA=y
+CONFIG_GENERIC_ISA_DMA_SUPPORT_BROKEN=y
 # CONFIG_CPU_BIG_ENDIAN is not set
 CONFIG_CPU_LITTLE_ENDIAN=y
 CONFIG_SYS_SUPPORTS_LITTLE_ENDIAN=y
 CONFIG_IRQ_CPU=y
 CONFIG_BOOT_ELF32=y
 CONFIG_MIPS_L1_CACHE_SHIFT=5
+CONFIG_HAVE_STD_PC_SERIAL_PORT=y
 
 #
 # CPU selection
@@ -75,6 +90,7 @@ CONFIG_CPU_LOONGSON2=y
 # CONFIG_CPU_TX49XX is not set
 # CONFIG_CPU_R5000 is not set
 # CONFIG_CPU_R5432 is not set
+# CONFIG_CPU_R5500 is not set
 # CONFIG_CPU_R6000 is not set
 # CONFIG_CPU_NEVADA is not set
 # CONFIG_CPU_R8000 is not set
@@ -101,7 +117,6 @@ CONFIG_BOARD_SCACHE=y
 CONFIG_MIPS_MT_DISABLED=y
 # CONFIG_MIPS_MT_SMP is not set
 # CONFIG_MIPS_MT_SMTC is not set
-# CONFIG_MIPS_VPE_LOADER is not set
 CONFIG_CPU_HAS_WB=y
 CONFIG_CPU_HAS_SYNC=y
 CONFIG_GENERIC_HARDIRQS=y
@@ -109,6 +124,7 @@ CONFIG_GENERIC_IRQ_PROBE=y
 CONFIG_CPU_SUPPORTS_HIGHMEM=y
 CONFIG_SYS_SUPPORTS_HIGHMEM=y
 CONFIG_ARCH_FLATMEM_ENABLE=y
+CONFIG_ARCH_POPULATES_NODE_MAP=y
 CONFIG_ARCH_SPARSEMEM_ENABLE=y
 CONFIG_SELECT_MEMORY_MODEL=y
 CONFIG_FLATMEM_MANUAL=y
@@ -117,9 +133,17 @@ CONFIG_FLATMEM_MANUAL=y
 CONFIG_FLATMEM=y
 CONFIG_FLAT_NODE_MEM_MAP=y
 CONFIG_SPARSEMEM_STATIC=y
+CONFIG_PAGEFLAGS_EXTENDED=y
 CONFIG_SPLIT_PTLOCK_CPUS=4
 CONFIG_RESOURCES_64BIT=y
+CONFIG_PHYS_ADDR_T_64BIT=y
 CONFIG_ZONE_DMA_FLAG=0
+CONFIG_VIRT_TO_BUS=y
+CONFIG_UNEVICTABLE_LRU=y
+CONFIG_TICK_ONESHOT=y
+CONFIG_NO_HZ=y
+CONFIG_HIGH_RES_TIMERS=y
+CONFIG_GENERIC_CLOCKEVENTS_BUILD=y
 # CONFIG_HZ_48 is not set
 # CONFIG_HZ_100 is not set
 # CONFIG_HZ_128 is not set
@@ -133,37 +157,40 @@ CONFIG_HZ=250
 CONFIG_PREEMPT_VOLUNTARY=y
 # CONFIG_PREEMPT is not set
 # CONFIG_KEXEC is not set
+CONFIG_SECCOMP=y
 CONFIG_LOCKDEP_SUPPORT=y
 CONFIG_STACKTRACE_SUPPORT=y
 CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config"
 
 #
-# Code maturity level options
+# General setup
 #
 CONFIG_EXPERIMENTAL=y
 CONFIG_BROKEN_ON_SMP=y
 CONFIG_INIT_ENV_ARG_LIMIT=32
-
-#
-# General setup
-#
 CONFIG_LOCALVERSION="lm32"
 # CONFIG_LOCALVERSION_AUTO is not set
 CONFIG_SWAP=y
 CONFIG_SYSVIPC=y
-# CONFIG_IPC_NS is not set
 CONFIG_SYSVIPC_SYSCTL=y
 CONFIG_POSIX_MQUEUE=y
 CONFIG_BSD_PROCESS_ACCT=y
 # CONFIG_BSD_PROCESS_ACCT_V3 is not set
 # CONFIG_TASKSTATS is not set
-# CONFIG_UTS_NS is not set
 # CONFIG_AUDIT is not set
 CONFIG_IKCONFIG=y
 CONFIG_IKCONFIG_PROC=y
 CONFIG_LOG_BUF_SHIFT=14
+# CONFIG_CGROUPS is not set
+# CONFIG_GROUP_SCHED is not set
 CONFIG_SYSFS_DEPRECATED=y
+CONFIG_SYSFS_DEPRECATED_V2=y
 # CONFIG_RELAY is not set
+CONFIG_NAMESPACES=y
+# CONFIG_UTS_NS is not set
+# CONFIG_IPC_NS is not set
+CONFIG_USER_NS=y
+CONFIG_PID_NS=y
 # CONFIG_BLK_DEV_INITRD is not set
 # CONFIG_CC_OPTIMIZE_FOR_SIZE is not set
 CONFIG_SYSCTL=y
@@ -175,6 +202,8 @@ CONFIG_HOTPLUG=y
 CONFIG_PRINTK=y
 CONFIG_BUG=y
 CONFIG_ELF_CORE=y
+# CONFIG_PCSPKR_PLATFORM is not set
+# CONFIG_COMPAT_BRK is not set
 CONFIG_BASE_FULL=y
 CONFIG_FUTEX=y
 CONFIG_ANON_INODES=y
@@ -183,29 +212,33 @@ CONFIG_SIGNALFD=y
 CONFIG_TIMERFD=y
 CONFIG_EVENTFD=y
 CONFIG_SHMEM=y
+CONFIG_AIO=y
 CONFIG_VM_EVENT_COUNTERS=y
+CONFIG_PCI_QUIRKS=y
 CONFIG_SLAB=y
 # CONFIG_SLUB is not set
 # CONFIG_SLOB is not set
+CONFIG_PROFILING=y
+# CONFIG_MARKERS is not set
+CONFIG_OPROFILE=m
+CONFIG_HAVE_OPROFILE=y
+# CONFIG_HAVE_GENERIC_DMA_COHERENT is not set
+CONFIG_SLABINFO=y
 CONFIG_RT_MUTEXES=y
 # CONFIG_TINY_SHMEM is not set
 CONFIG_BASE_SMALL=0
-
-#
-# Loadable module support
-#
 CONFIG_MODULES=y
+# CONFIG_MODULE_FORCE_LOAD is not set
 CONFIG_MODULE_UNLOAD=y
 CONFIG_MODULE_FORCE_UNLOAD=y
 # CONFIG_MODVERSIONS is not set
 # CONFIG_MODULE_SRCVERSION_ALL is not set
 CONFIG_KMOD=y
-
-#
-# Block layer
-#
 CONFIG_BLOCK=y
 # CONFIG_BLK_DEV_IO_TRACE is not set
+CONFIG_BLK_DEV_BSG=y
+# CONFIG_BLK_DEV_INTEGRITY is not set
+CONFIG_BLOCK_COMPAT=y
 
 #
 # IO Schedulers
@@ -219,19 +252,19 @@ CONFIG_IOSCHED_CFQ=y
 CONFIG_DEFAULT_CFQ=y
 # CONFIG_DEFAULT_NOOP is not set
 CONFIG_DEFAULT_IOSCHED="cfq"
+CONFIG_CLASSIC_RCU=y
+CONFIG_FREEZER=y
 
 #
 # Bus options (PCI, PCMCIA, EISA, ISA, TC)
 #
 CONFIG_HW_HAS_PCI=y
 CONFIG_PCI=y
+CONFIG_PCI_DOMAINS=y
 # CONFIG_ARCH_SUPPORTS_MSI is not set
+CONFIG_PCI_LEGACY=y
 CONFIG_ISA=y
 CONFIG_MMU=y
-
-#
-# PCCARD (PCMCIA/CardBus) support
-#
 # CONFIG_PCCARD is not set
 # CONFIG_HOTPLUG_PCI is not set
 
@@ -239,8 +272,9 @@ CONFIG_MMU=y
 # Executable file formats
 #
 CONFIG_BINFMT_ELF=y
+# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
+# CONFIG_HAVE_AOUT is not set
 CONFIG_BINFMT_MISC=y
-# CONFIG_BUILD_ELF64 is not set
 CONFIG_MIPS32_COMPAT=y
 CONFIG_COMPAT=y
 CONFIG_SYSVIPC_COMPAT=y
@@ -251,14 +285,12 @@ CONFIG_BINFMT_ELF32=y
 #
 # Power management options
 #
+CONFIG_ARCH_SUSPEND_POSSIBLE=y
 CONFIG_PM=y
-# CONFIG_PM_LEGACY is not set
 # CONFIG_PM_DEBUG is not set
-# CONFIG_PM_SYSFS_DEPRECATED is not set
-
-#
-# Networking
-#
+CONFIG_PM_SLEEP=y
+CONFIG_SUSPEND=y
+CONFIG_SUSPEND_FREEZER=y
 CONFIG_NET=y
 
 #
@@ -271,6 +303,7 @@ CONFIG_XFRM=y
 # CONFIG_XFRM_USER is not set
 # CONFIG_XFRM_SUB_POLICY is not set
 # CONFIG_XFRM_MIGRATE is not set
+# CONFIG_XFRM_STATISTICS is not set
 # CONFIG_NET_KEY is not set
 CONFIG_INET=y
 CONFIG_IP_MULTICAST=y
@@ -294,18 +327,17 @@ CONFIG_INET_TUNNEL=m
 # CONFIG_INET_XFRM_MODE_TRANSPORT is not set
 # CONFIG_INET_XFRM_MODE_TUNNEL is not set
 CONFIG_INET_XFRM_MODE_BEET=y
+# CONFIG_INET_LRO is not set
 # CONFIG_INET_DIAG is not set
 # CONFIG_TCP_CONG_ADVANCED is not set
 CONFIG_TCP_CONG_CUBIC=y
 CONFIG_DEFAULT_TCP_CONG="cubic"
 # CONFIG_TCP_MD5SIG is not set
-# CONFIG_IP_VS is not set
 # CONFIG_IPV6 is not set
-# CONFIG_INET6_XFRM_TUNNEL is not set
-# CONFIG_INET6_TUNNEL is not set
 # CONFIG_NETWORK_SECMARK is not set
 CONFIG_NETFILTER=y
 # CONFIG_NETFILTER_DEBUG is not set
+CONFIG_NETFILTER_ADVANCED=y
 
 #
 # Core Netfilter Configuration
@@ -313,53 +345,59 @@ CONFIG_NETFILTER=y
 CONFIG_NETFILTER_NETLINK=m
 CONFIG_NETFILTER_NETLINK_QUEUE=m
 CONFIG_NETFILTER_NETLINK_LOG=m
-# CONFIG_NF_CONNTRACK_ENABLED is not set
 # CONFIG_NF_CONNTRACK is not set
 CONFIG_NETFILTER_XTABLES=m
 CONFIG_NETFILTER_XT_TARGET_CLASSIFY=m
 # CONFIG_NETFILTER_XT_TARGET_DSCP is not set
 CONFIG_NETFILTER_XT_TARGET_MARK=m
-CONFIG_NETFILTER_XT_TARGET_NFQUEUE=m
 # CONFIG_NETFILTER_XT_TARGET_NFLOG is not set
+CONFIG_NETFILTER_XT_TARGET_NFQUEUE=m
+CONFIG_NETFILTER_XT_TARGET_RATEEST=m
+CONFIG_NETFILTER_XT_TARGET_TRACE=m
 # CONFIG_NETFILTER_XT_TARGET_TCPMSS is not set
+CONFIG_NETFILTER_XT_TARGET_TCPOPTSTRIP=m
 CONFIG_NETFILTER_XT_MATCH_COMMENT=m
 CONFIG_NETFILTER_XT_MATCH_DCCP=m
 # CONFIG_NETFILTER_XT_MATCH_DSCP is not set
 CONFIG_NETFILTER_XT_MATCH_ESP=m
+# CONFIG_NETFILTER_XT_MATCH_HASHLIMIT is not set
+CONFIG_NETFILTER_XT_MATCH_IPRANGE=m
 CONFIG_NETFILTER_XT_MATCH_LENGTH=m
 CONFIG_NETFILTER_XT_MATCH_LIMIT=m
 CONFIG_NETFILTER_XT_MATCH_MAC=m
 CONFIG_NETFILTER_XT_MATCH_MARK=m
-# CONFIG_NETFILTER_XT_MATCH_POLICY is not set
 CONFIG_NETFILTER_XT_MATCH_MULTIPORT=m
+CONFIG_NETFILTER_XT_MATCH_OWNER=m
+# CONFIG_NETFILTER_XT_MATCH_POLICY is not set
 CONFIG_NETFILTER_XT_MATCH_PKTTYPE=m
 CONFIG_NETFILTER_XT_MATCH_QUOTA=m
+CONFIG_NETFILTER_XT_MATCH_RATEEST=m
 CONFIG_NETFILTER_XT_MATCH_REALM=m
+CONFIG_NETFILTER_XT_MATCH_RECENT=m
+# CONFIG_NETFILTER_XT_MATCH_RECENT_PROC_COMPAT is not set
 CONFIG_NETFILTER_XT_MATCH_SCTP=m
 CONFIG_NETFILTER_XT_MATCH_STATISTIC=m
 CONFIG_NETFILTER_XT_MATCH_STRING=m
 CONFIG_NETFILTER_XT_MATCH_TCPMSS=m
-# CONFIG_NETFILTER_XT_MATCH_HASHLIMIT is not set
+CONFIG_NETFILTER_XT_MATCH_TIME=m
+CONFIG_NETFILTER_XT_MATCH_U32=m
+# CONFIG_IP_VS is not set
 
 #
 # IP: Netfilter Configuration
 #
+# CONFIG_NF_DEFRAG_IPV4 is not set
 CONFIG_IP_NF_QUEUE=m
 CONFIG_IP_NF_IPTABLES=m
-CONFIG_IP_NF_MATCH_IPRANGE=m
-CONFIG_IP_NF_MATCH_TOS=m
-CONFIG_IP_NF_MATCH_RECENT=m
-CONFIG_IP_NF_MATCH_ECN=m
+CONFIG_IP_NF_MATCH_ADDRTYPE=m
 CONFIG_IP_NF_MATCH_AH=m
+CONFIG_IP_NF_MATCH_ECN=m
 CONFIG_IP_NF_MATCH_TTL=m
-CONFIG_IP_NF_MATCH_OWNER=m
-CONFIG_IP_NF_MATCH_ADDRTYPE=m
 CONFIG_IP_NF_FILTER=m
 CONFIG_IP_NF_TARGET_REJECT=m
 CONFIG_IP_NF_TARGET_LOG=m
 CONFIG_IP_NF_TARGET_ULOG=m
 CONFIG_IP_NF_MANGLE=m
-CONFIG_IP_NF_TARGET_TOS=m
 CONFIG_IP_NF_TARGET_ECN=m
 CONFIG_IP_NF_TARGET_TTL=m
 CONFIG_IP_NF_RAW=m
@@ -371,6 +409,7 @@ CONFIG_IP_NF_ARP_MANGLE=m
 # CONFIG_TIPC is not set
 # CONFIG_ATM is not set
 # CONFIG_BRIDGE is not set
+# CONFIG_NET_DSA is not set
 # CONFIG_VLAN_8021Q is not set
 # CONFIG_DECNET is not set
 # CONFIG_LLC2 is not set
@@ -380,10 +419,6 @@ CONFIG_IP_NF_ARP_MANGLE=m
 # CONFIG_LAPB is not set
 # CONFIG_ECONET is not set
 # CONFIG_WAN_ROUTER is not set
-
-#
-# QoS and/or fair queueing
-#
 # CONFIG_NET_SCHED is not set
 CONFIG_NET_CLS_ROUTE=y
 
@@ -392,23 +427,25 @@ CONFIG_NET_CLS_ROUTE=y
 #
 # CONFIG_NET_PKTGEN is not set
 # CONFIG_HAMRADIO is not set
+# CONFIG_CAN is not set
 # CONFIG_IRDA is not set
 # CONFIG_BT is not set
 # CONFIG_AF_RXRPC is not set
-
-#
-# Wireless
-#
+CONFIG_PHONET=m
+CONFIG_WIRELESS=y
 # CONFIG_CFG80211 is not set
+CONFIG_WIRELESS_OLD_REGULATORY=y
 CONFIG_WIRELESS_EXT=y
+CONFIG_WIRELESS_EXT_SYSFS=y
 # CONFIG_MAC80211 is not set
 CONFIG_IEEE80211=m
 # CONFIG_IEEE80211_DEBUG is not set
 CONFIG_IEEE80211_CRYPT_WEP=m
 # CONFIG_IEEE80211_CRYPT_CCMP is not set
 # CONFIG_IEEE80211_CRYPT_TKIP is not set
-# CONFIG_IEEE80211_SOFTMAC is not set
 # CONFIG_RFKILL is not set
+CONFIG_NET_9P=m
+# CONFIG_NET_9P_DEBUG is not set
 
 #
 # Device Drivers
@@ -417,14 +454,13 @@ CONFIG_IEEE80211_CRYPT_WEP=m
 #
 # Generic Driver Options
 #
+CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_STANDALONE=y
 CONFIG_PREVENT_FIRMWARE_BUILD=y
 CONFIG_FW_LOADER=m
+CONFIG_FIRMWARE_IN_KERNEL=y
+CONFIG_EXTRA_FIRMWARE=""
 # CONFIG_SYS_HYPERVISOR is not set
-
-#
-# Connector - unified userspace <-> kernelspace linker
-#
 # CONFIG_CONNECTOR is not set
 CONFIG_MTD=m
 # CONFIG_MTD_DEBUG is not set
@@ -443,6 +479,7 @@ CONFIG_MTD_BLOCK=m
 # CONFIG_INFTL is not set
 # CONFIG_RFD_FTL is not set
 # CONFIG_SSFDC is not set
+# CONFIG_MTD_OOPS is not set
 
 #
 # RAM/ROM/Flash chip drivers
@@ -482,6 +519,7 @@ CONFIG_MTD_PHYSMAP=m
 CONFIG_MTD_PHYSMAP_START=0x1fc00000
 CONFIG_MTD_PHYSMAP_LEN=0x80000
 CONFIG_MTD_PHYSMAP_BANKWIDTH=1
+# CONFIG_MTD_INTEL_VR_NOR is not set
 # CONFIG_MTD_PLATRAM is not set
 
 #
@@ -506,21 +544,9 @@ CONFIG_MTD_PHYSMAP_BANKWIDTH=1
 # UBI - Unsorted block images
 #
 # CONFIG_MTD_UBI is not set
-
-#
-# Parallel port support
-#
 # CONFIG_PARPORT is not set
-
-#
-# Plug and Play support
-#
 # CONFIG_PNP is not set
-# CONFIG_PNPACPI is not set
-
-#
-# Block devices
-#
+CONFIG_BLK_DEV=y
 # CONFIG_BLK_CPQ_DA is not set
 # CONFIG_BLK_CPQ_CISS_DA is not set
 # CONFIG_BLK_DEV_DAC960 is not set
@@ -534,32 +560,28 @@ CONFIG_BLK_DEV_CRYPTOLOOP=m
 CONFIG_BLK_DEV_RAM=m
 CONFIG_BLK_DEV_RAM_COUNT=16
 CONFIG_BLK_DEV_RAM_SIZE=4096
-CONFIG_BLK_DEV_RAM_BLOCKSIZE=1024
+# CONFIG_BLK_DEV_XIP is not set
 CONFIG_CDROM_PKTCDVD=m
 CONFIG_CDROM_PKTCDVD_BUFFERS=8
 # CONFIG_CDROM_PKTCDVD_WCACHE is not set
 CONFIG_ATA_OVER_ETH=m
-
-#
-# Misc devices
-#
-# CONFIG_PHANTOM is not set
-# CONFIG_SGI_IOC4 is not set
-# CONFIG_TIFM_CORE is not set
-# CONFIG_BLINK is not set
+# CONFIG_BLK_DEV_HD is not set
+# CONFIG_MISC_DEVICES is not set
+CONFIG_HAVE_IDE=y
 CONFIG_IDE=y
-CONFIG_IDE_MAX_HWIFS=4
-CONFIG_BLK_DEV_IDE=y
 
 #
-# Please see Documentation/ide.txt for help/info on IDE drives
+# Please see Documentation/ide/ide.txt for help/info on IDE drives
 #
+CONFIG_IDE_TIMINGS=y
+CONFIG_IDE_ATAPI=y
 # CONFIG_BLK_DEV_IDE_SATA is not set
-CONFIG_BLK_DEV_IDEDISK=y
-CONFIG_IDEDISK_MULTI_MODE=y
+CONFIG_IDE_GD=y
+CONFIG_IDE_GD_ATA=y
+# CONFIG_IDE_GD_ATAPI is not set
 CONFIG_BLK_DEV_IDECD=y
+CONFIG_BLK_DEV_IDECD_VERBOSE_ERRORS=y
 # CONFIG_BLK_DEV_IDETAPE is not set
-# CONFIG_BLK_DEV_IDEFLOPPY is not set
 CONFIG_BLK_DEV_IDESCSI=y
 CONFIG_IDE_TASK_IOCTL=y
 CONFIG_IDE_PROC_FS=y
@@ -568,24 +590,25 @@ CONFIG_IDE_PROC_FS=y
 # IDE chipset support/bugfixes
 #
 CONFIG_IDE_GENERIC=y
+# CONFIG_BLK_DEV_PLATFORM is not set
+CONFIG_BLK_DEV_IDEDMA_SFF=y
+
+#
+# PCI IDE chipsets support
+#
 CONFIG_BLK_DEV_IDEPCI=y
-CONFIG_IDEPCI_SHARE_IRQ=y
 CONFIG_IDEPCI_PCIBUS_ORDER=y
 # CONFIG_BLK_DEV_OFFBOARD is not set
 CONFIG_BLK_DEV_GENERIC=y
 # CONFIG_BLK_DEV_OPTI621 is not set
 CONFIG_BLK_DEV_IDEDMA_PCI=y
-# CONFIG_BLK_DEV_IDEDMA_FORCED is not set
-# CONFIG_IDEDMA_ONLYDISK is not set
 # CONFIG_BLK_DEV_AEC62XX is not set
 # CONFIG_BLK_DEV_ALI15X3 is not set
 # CONFIG_BLK_DEV_AMD74XX is not set
 # CONFIG_BLK_DEV_CMD64X is not set
 # CONFIG_BLK_DEV_TRIFLEX is not set
-# CONFIG_BLK_DEV_CY82C693 is not set
 # CONFIG_BLK_DEV_CS5520 is not set
 # CONFIG_BLK_DEV_CS5530 is not set
-# CONFIG_BLK_DEV_HPT34X is not set
 # CONFIG_BLK_DEV_HPT366 is not set
 # CONFIG_BLK_DEV_JMICRON is not set
 # CONFIG_BLK_DEV_SC1200 is not set
@@ -601,17 +624,28 @@ CONFIG_BLK_DEV_IDEDMA_PCI=y
 # CONFIG_BLK_DEV_TRM290 is not set
 CONFIG_BLK_DEV_VIA82CXXX=y
 # CONFIG_BLK_DEV_TC86C001 is not set
-# CONFIG_IDE_ARM is not set
-# CONFIG_IDE_CHIPSETS is not set
+
+#
+# Other IDE chipsets support
+#
+
+#
+# Note: most of these also require special kernel boot parameters
+#
+# CONFIG_BLK_DEV_4DRIVES is not set
+# CONFIG_BLK_DEV_ALI14XX is not set
+# CONFIG_BLK_DEV_DTC2278 is not set
+# CONFIG_BLK_DEV_HT6560B is not set
+# CONFIG_BLK_DEV_QD65XX is not set
+# CONFIG_BLK_DEV_UMC8672 is not set
 CONFIG_BLK_DEV_IDEDMA=y
-# CONFIG_IDEDMA_IVB is not set
-# CONFIG_BLK_DEV_HD is not set
 
 #
 # SCSI device support
 #
 # CONFIG_RAID_ATTRS is not set
 CONFIG_SCSI=y
+CONFIG_SCSI_DMA=y
 # CONFIG_SCSI_TGT is not set
 # CONFIG_SCSI_NETLINK is not set
 CONFIG_SCSI_PROC_FS=y
@@ -644,88 +678,30 @@ CONFIG_SCSI_WAIT_SCAN=m
 # CONFIG_SCSI_ISCSI_ATTRS is not set
 # CONFIG_SCSI_SAS_ATTRS is not set
 # CONFIG_SCSI_SAS_LIBSAS is not set
-
-#
-# SCSI low-level drivers
-#
-# CONFIG_ISCSI_TCP is not set
-# CONFIG_BLK_DEV_3W_XXXX_RAID is not set
-# CONFIG_SCSI_3W_9XXX is not set
-# CONFIG_SCSI_ACARD is not set
-# CONFIG_SCSI_AACRAID is not set
-# CONFIG_SCSI_AIC7XXX is not set
-# CONFIG_SCSI_AIC7XXX_OLD is not set
-# CONFIG_SCSI_AIC79XX is not set
-# CONFIG_SCSI_AIC94XX is not set
-# CONFIG_SCSI_IN2000 is not set
-# CONFIG_SCSI_ARCMSR is not set
-# CONFIG_MEGARAID_NEWGEN is not set
-# CONFIG_MEGARAID_LEGACY is not set
-# CONFIG_MEGARAID_SAS is not set
-# CONFIG_SCSI_HPTIOP is not set
-# CONFIG_SCSI_DMX3191D is not set
-# CONFIG_SCSI_DTC3280 is not set
-# CONFIG_SCSI_FUTURE_DOMAIN is not set
-# CONFIG_SCSI_GENERIC_NCR5380 is not set
-# CONFIG_SCSI_GENERIC_NCR5380_MMIO is not set
-# CONFIG_SCSI_IPS is not set
-# CONFIG_SCSI_INITIO is not set
-# CONFIG_SCSI_INIA100 is not set
-# CONFIG_SCSI_NCR53C406A is not set
-# CONFIG_SCSI_STEX is not set
-# CONFIG_SCSI_SYM53C8XX_2 is not set
-# CONFIG_SCSI_PAS16 is not set
-# CONFIG_SCSI_PSI240I is not set
-# CONFIG_SCSI_QLOGIC_FAS is not set
-# CONFIG_SCSI_QLOGIC_1280 is not set
-# CONFIG_SCSI_QLA_FC is not set
-# CONFIG_SCSI_QLA_ISCSI is not set
-# CONFIG_SCSI_LPFC is not set
-# CONFIG_SCSI_SYM53C416 is not set
-# CONFIG_SCSI_DC395x is not set
-# CONFIG_SCSI_DC390T is not set
-# CONFIG_SCSI_T128 is not set
-# CONFIG_SCSI_DEBUG is not set
-# CONFIG_SCSI_SRP is not set
+# CONFIG_SCSI_SRP_ATTRS is not set
+# CONFIG_SCSI_LOWLEVEL is not set
+# CONFIG_SCSI_DH is not set
 # CONFIG_ATA is not set
-
-#
-# Old CD-ROM drivers (not SCSI, not IDE)
-#
-# CONFIG_CD_NO_IDESCSI is not set
-
-#
-# Multi-device support (RAID and LVM)
-#
 # CONFIG_MD is not set
-
-#
-# Fusion MPT device support
-#
 # CONFIG_FUSION is not set
-# CONFIG_FUSION_SPI is not set
-# CONFIG_FUSION_FC is not set
-# CONFIG_FUSION_SAS is not set
 
 #
 # IEEE 1394 (FireWire) support
 #
-# CONFIG_FIREWIRE is not set
-# CONFIG_IEEE1394 is not set
 
 #
-# I2O device support
+# Enable only one of the two stacks, unless you know what you are doing
 #
+# CONFIG_FIREWIRE is not set
+# CONFIG_IEEE1394 is not set
 # CONFIG_I2O is not set
-
-#
-# Network device support
-#
 CONFIG_NETDEVICES=y
 # CONFIG_DUMMY is not set
 # CONFIG_BONDING is not set
+CONFIG_MACVLAN=m
 # CONFIG_EQUALIZER is not set
 # CONFIG_TUN is not set
+CONFIG_VETH=m
 # CONFIG_ARCNET is not set
 CONFIG_PHYLIB=m
 
@@ -740,29 +716,32 @@ CONFIG_CICADA_PHY=m
 # CONFIG_VITESSE_PHY is not set
 # CONFIG_SMSC_PHY is not set
 # CONFIG_BROADCOM_PHY is not set
-# CONFIG_FIXED_PHY is not set
-
-#
-# Ethernet (10 or 100Mbit)
-#
+# CONFIG_ICPLUS_PHY is not set
+# CONFIG_REALTEK_PHY is not set
+# CONFIG_MDIO_BITBANG is not set
 CONFIG_NET_ETHERNET=y
 CONFIG_MII=y
+# CONFIG_AX88796 is not set
 # CONFIG_HAPPYMEAL is not set
 # CONFIG_SUNGEM is not set
 # CONFIG_CASSINI is not set
 # CONFIG_NET_VENDOR_3COM is not set
 # CONFIG_NET_VENDOR_SMC is not set
+# CONFIG_SMC91X is not set
 # CONFIG_DM9000 is not set
 # CONFIG_NET_VENDOR_RACAL is not set
-
-#
-# Tulip family network device support
-#
 # CONFIG_NET_TULIP is not set
 # CONFIG_AT1700 is not set
 # CONFIG_DEPCA is not set
 # CONFIG_HP100 is not set
 # CONFIG_NET_ISA is not set
+# CONFIG_IBM_NEW_EMAC_ZMII is not set
+# CONFIG_IBM_NEW_EMAC_RGMII is not set
+# CONFIG_IBM_NEW_EMAC_TAH is not set
+# CONFIG_IBM_NEW_EMAC_EMAC4 is not set
+# CONFIG_IBM_NEW_EMAC_NO_FLOW_CTRL is not set
+# CONFIG_IBM_NEW_EMAC_MAL_CLR_ICINTSTAT is not set
+# CONFIG_IBM_NEW_EMAC_MAL_COMMON_ERR is not set
 CONFIG_NET_PCI=y
 # CONFIG_PCNET32 is not set
 # CONFIG_AMD8111_ETH is not set
@@ -773,7 +752,6 @@ CONFIG_NET_PCI=y
 # CONFIG_FORCEDETH is not set
 # CONFIG_CS89x0 is not set
 # CONFIG_TC35815 is not set
-# CONFIG_DGRS is not set
 # CONFIG_EEPRO100 is not set
 # CONFIG_E100 is not set
 # CONFIG_FEALNX is not set
@@ -785,15 +763,21 @@ CONFIG_8139TOO=y
 # CONFIG_8139TOO_TUNE_TWISTER is not set
 # CONFIG_8139TOO_8129 is not set
 # CONFIG_8139_OLD_RX_RESET is not set
+# CONFIG_R6040 is not set
 # CONFIG_SIS900 is not set
 # CONFIG_EPIC100 is not set
 # CONFIG_SUNDANCE is not set
+# CONFIG_TLAN is not set
 # CONFIG_VIA_RHINE is not set
 # CONFIG_SC92031 is not set
+# CONFIG_ATL2 is not set
 CONFIG_NETDEV_1000=y
 # CONFIG_ACENIC is not set
 # CONFIG_DL2K is not set
 # CONFIG_E1000 is not set
+# CONFIG_E1000E is not set
+# CONFIG_IP1000 is not set
+# CONFIG_IGB is not set
 # CONFIG_NS83820 is not set
 # CONFIG_HAMACHI is not set
 # CONFIG_YELLOWFIN is not set
@@ -801,20 +785,29 @@ CONFIG_NETDEV_1000=y
 # CONFIG_SIS190 is not set
 # CONFIG_SKGE is not set
 # CONFIG_SKY2 is not set
-# CONFIG_SK98LIN is not set
 # CONFIG_VIA_VELOCITY is not set
 # CONFIG_TIGON3 is not set
 # CONFIG_BNX2 is not set
 # CONFIG_QLA3XXX is not set
 # CONFIG_ATL1 is not set
+# CONFIG_ATL1E is not set
+# CONFIG_JME is not set
 CONFIG_NETDEV_10000=y
 # CONFIG_CHELSIO_T1 is not set
 # CONFIG_CHELSIO_T3 is not set
+# CONFIG_ENIC is not set
+# CONFIG_IXGBE is not set
 # CONFIG_IXGB is not set
 # CONFIG_S2IO is not set
 # CONFIG_MYRI10GE is not set
 # CONFIG_NETXEN_NIC is not set
+# CONFIG_NIU is not set
+# CONFIG_MLX4_EN is not set
 # CONFIG_MLX4_CORE is not set
+# CONFIG_TEHUTI is not set
+# CONFIG_BNX2X is not set
+# CONFIG_QLGE is not set
+# CONFIG_SFC is not set
 # CONFIG_TR is not set
 
 #
@@ -822,6 +815,7 @@ CONFIG_NETDEV_10000=y
 #
 # CONFIG_WLAN_PRE80211 is not set
 # CONFIG_WLAN_80211 is not set
+# CONFIG_IWLWIFI_LEDS is not set
 
 #
 # USB Network Adapters
@@ -830,7 +824,6 @@ CONFIG_NETDEV_10000=y
 # CONFIG_USB_KAWETH is not set
 # CONFIG_USB_PEGASUS is not set
 # CONFIG_USB_RTL8150 is not set
-# CONFIG_USB_USBNET_MII is not set
 # CONFIG_USB_USBNET is not set
 # CONFIG_WAN is not set
 # CONFIG_FDDI is not set
@@ -844,25 +837,17 @@ CONFIG_PPP_DEFLATE=m
 CONFIG_PPP_BSDCOMP=m
 CONFIG_PPP_MPPE=m
 CONFIG_PPPOE=m
+CONFIG_PPPOL2TP=m
 CONFIG_SLIP=m
 CONFIG_SLIP_COMPRESSED=y
 CONFIG_SLHC=m
 CONFIG_SLIP_SMART=y
 CONFIG_SLIP_MODE_SLIP6=y
 CONFIG_NET_FC=y
-# CONFIG_SHAPER is not set
 # CONFIG_NETCONSOLE is not set
 # CONFIG_NETPOLL is not set
 # CONFIG_NET_POLL_CONTROLLER is not set
-
-#
-# ISDN subsystem
-#
 # CONFIG_ISDN is not set
-
-#
-# Telephony Support
-#
 # CONFIG_PHONE is not set
 
 #
@@ -870,6 +855,7 @@ CONFIG_NET_FC=y
 #
 CONFIG_INPUT=y
 CONFIG_INPUT_FF_MEMLESS=y
+# CONFIG_INPUT_POLLDEV is not set
 
 #
 # Userland interfaces
@@ -879,7 +865,6 @@ CONFIG_INPUT_MOUSEDEV_PSAUX=y
 CONFIG_INPUT_MOUSEDEV_SCREEN_X=1024
 CONFIG_INPUT_MOUSEDEV_SCREEN_Y=768
 # CONFIG_INPUT_JOYDEV is not set
-# CONFIG_INPUT_TSDEV is not set
 # CONFIG_INPUT_EVDEV is not set
 # CONFIG_INPUT_EVBUG is not set
 
@@ -900,9 +885,11 @@ CONFIG_MOUSE_PS2_LOGIPS2PP=y
 CONFIG_MOUSE_PS2_SYNAPTICS=y
 CONFIG_MOUSE_PS2_LIFEBOOK=y
 CONFIG_MOUSE_PS2_TRACKPOINT=y
+# CONFIG_MOUSE_PS2_ELANTECH is not set
 # CONFIG_MOUSE_PS2_TOUCHKIT is not set
 CONFIG_MOUSE_SERIAL=y
 # CONFIG_MOUSE_APPLETOUCH is not set
+# CONFIG_MOUSE_BCM5974 is not set
 # CONFIG_MOUSE_INPORT is not set
 # CONFIG_MOUSE_LOGIBM is not set
 # CONFIG_MOUSE_PC110PAD is not set
@@ -927,10 +914,13 @@ CONFIG_SERIO_LIBPS2=y
 # Character devices
 #
 CONFIG_VT=y
+CONFIG_CONSOLE_TRANSLATIONS=y
 CONFIG_VT_CONSOLE=y
 CONFIG_HW_CONSOLE=y
 # CONFIG_VT_HW_CONSOLE_BINDING is not set
+CONFIG_DEVKMEM=y
 # CONFIG_SERIAL_NONSTANDARD is not set
+# CONFIG_NOZOMI is not set
 
 #
 # Serial drivers
@@ -951,105 +941,152 @@ CONFIG_SERIAL_CORE_CONSOLE=y
 CONFIG_UNIX98_PTYS=y
 CONFIG_LEGACY_PTYS=y
 CONFIG_LEGACY_PTY_COUNT=256
-
-#
-# IPMI
-#
 # CONFIG_IPMI_HANDLER is not set
-# CONFIG_WATCHDOG is not set
 CONFIG_HW_RANDOM=y
-CONFIG_RTC=y
 # CONFIG_DTLK is not set
 # CONFIG_R3964 is not set
 # CONFIG_APPLICOM is not set
-# CONFIG_DRM is not set
 # CONFIG_RAW_DRIVER is not set
-
-#
-# TPM devices
-#
 # CONFIG_TCG_TPM is not set
 CONFIG_DEVPORT=y
 CONFIG_I2C=m
 CONFIG_I2C_BOARDINFO=y
 CONFIG_I2C_CHARDEV=m
+CONFIG_I2C_HELPER_AUTO=y
 
 #
-# I2C Algorithms
+# I2C Hardware Bus support
 #
-# CONFIG_I2C_ALGOBIT is not set
-# CONFIG_I2C_ALGOPCF is not set
-# CONFIG_I2C_ALGOPCA is not set
 
 #
-# I2C Hardware Bus support
+# PC SMBus host controller drivers
 #
 # CONFIG_I2C_ALI1535 is not set
 # CONFIG_I2C_ALI1563 is not set
 # CONFIG_I2C_ALI15X3 is not set
 # CONFIG_I2C_AMD756 is not set
 # CONFIG_I2C_AMD8111 is not set
-# CONFIG_I2C_ELEKTOR is not set
 # CONFIG_I2C_I801 is not set
-# CONFIG_I2C_I810 is not set
+# CONFIG_I2C_ISCH is not set
 # CONFIG_I2C_PIIX4 is not set
 # CONFIG_I2C_NFORCE2 is not set
-# CONFIG_I2C_OCORES is not set
-# CONFIG_I2C_PARPORT_LIGHT is not set
-# CONFIG_I2C_PROSAVAGE is not set
-# CONFIG_I2C_SAVAGE4 is not set
-# CONFIG_I2C_SIMTEC is not set
 # CONFIG_I2C_SIS5595 is not set
 # CONFIG_I2C_SIS630 is not set
 # CONFIG_I2C_SIS96X is not set
-# CONFIG_I2C_STUB is not set
-# CONFIG_I2C_TINY_USB is not set
 # CONFIG_I2C_VIA is not set
 CONFIG_I2C_VIAPRO=m
+
+#
+# I2C system bus drivers (mostly embedded / system-on-chip)
+#
+# CONFIG_I2C_OCORES is not set
+# CONFIG_I2C_SIMTEC is not set
+
+#
+# External I2C/SMBus adapter drivers
+#
+# CONFIG_I2C_PARPORT_LIGHT is not set
+# CONFIG_I2C_TAOS_EVM is not set
+# CONFIG_I2C_TINY_USB is not set
+
+#
+# Graphics adapter I2C/DDC channel drivers
+#
 # CONFIG_I2C_VOODOO3 is not set
+
+#
+# Other I2C/SMBus bus drivers
+#
+# CONFIG_I2C_ELEKTOR is not set
 # CONFIG_I2C_PCA_ISA is not set
+# CONFIG_I2C_PCA_PLATFORM is not set
+# CONFIG_I2C_STUB is not set
 
 #
 # Miscellaneous I2C Chip support
 #
-# CONFIG_SENSORS_DS1337 is not set
-# CONFIG_SENSORS_DS1374 is not set
+# CONFIG_DS1682 is not set
+# CONFIG_AT24 is not set
 # CONFIG_SENSORS_EEPROM is not set
 # CONFIG_SENSORS_PCF8574 is not set
+# CONFIG_PCF8575 is not set
 # CONFIG_SENSORS_PCA9539 is not set
 # CONFIG_SENSORS_PCF8591 is not set
 # CONFIG_SENSORS_MAX6875 is not set
+# CONFIG_SENSORS_TSL2550 is not set
 # CONFIG_I2C_DEBUG_CORE is not set
 # CONFIG_I2C_DEBUG_ALGO is not set
 # CONFIG_I2C_DEBUG_BUS is not set
 # CONFIG_I2C_DEBUG_CHIP is not set
-
-#
-# SPI support
-#
 # CONFIG_SPI is not set
-# CONFIG_SPI_MASTER is not set
+# CONFIG_W1 is not set
+# CONFIG_POWER_SUPPLY is not set
+# CONFIG_HWMON is not set
+# CONFIG_THERMAL is not set
+# CONFIG_THERMAL_HWMON is not set
+# CONFIG_WATCHDOG is not set
+CONFIG_SSB_POSSIBLE=y
 
 #
-# Dallas's 1-wire bus
+# Sonics Silicon Backplane
 #
-# CONFIG_W1 is not set
-# CONFIG_HWMON is not set
+# CONFIG_SSB is not set
 
 #
 # Multifunction device drivers
 #
+# CONFIG_MFD_CORE is not set
 # CONFIG_MFD_SM501 is not set
+# CONFIG_HTC_PASIC3 is not set
+# CONFIG_MFD_TMIO is not set
+# CONFIG_MFD_WM8400 is not set
+# CONFIG_MFD_WM8350_I2C is not set
+# CONFIG_REGULATOR is not set
 
 #
 # Multimedia devices
 #
+
+#
+# Multimedia core support
+#
 CONFIG_VIDEO_DEV=m
-CONFIG_VIDEO_V4L1=y
+CONFIG_VIDEO_V4L2_COMMON=m
+CONFIG_VIDEO_ALLOW_V4L1=y
 CONFIG_VIDEO_V4L1_COMPAT=y
-CONFIG_VIDEO_V4L2=y
+# CONFIG_DVB_CORE is not set
+CONFIG_VIDEO_MEDIA=m
+
+#
+# Multimedia drivers
+#
+CONFIG_MEDIA_ATTACH=y
+CONFIG_MEDIA_TUNER=m
+CONFIG_MEDIA_TUNER_CUSTOMIZE=y
+CONFIG_MEDIA_TUNER_SIMPLE=m
+CONFIG_MEDIA_TUNER_TDA8290=m
+CONFIG_MEDIA_TUNER_TDA827X=m
+CONFIG_MEDIA_TUNER_TDA18271=m
+CONFIG_MEDIA_TUNER_TDA9887=m
+CONFIG_MEDIA_TUNER_TEA5761=m
+CONFIG_MEDIA_TUNER_TEA5767=m
+CONFIG_MEDIA_TUNER_MT20XX=m
+CONFIG_MEDIA_TUNER_MT2060=m
+CONFIG_MEDIA_TUNER_MT2266=m
+CONFIG_MEDIA_TUNER_MT2131=m
+CONFIG_MEDIA_TUNER_QT1010=m
+CONFIG_MEDIA_TUNER_XC2028=m
+CONFIG_MEDIA_TUNER_XC5000=m
+CONFIG_MEDIA_TUNER_MXL5005S=m
+CONFIG_MEDIA_TUNER_MXL5007T=m
+CONFIG_VIDEO_V4L2=m
+CONFIG_VIDEO_V4L1=m
+CONFIG_VIDEOBUF_GEN=m
+CONFIG_VIDEOBUF_VMALLOC=m
+CONFIG_VIDEOBUF_DMA_CONTIG=m
 CONFIG_VIDEO_CAPTURE_DRIVERS=y
 # CONFIG_VIDEO_ADV_DEBUG is not set
+# CONFIG_VIDEO_FIXED_MINOR_RANGES is not set
 CONFIG_VIDEO_HELPER_CHIPS_AUTO=y
 # CONFIG_VIDEO_VIVI is not set
 # CONFIG_VIDEO_BT848 is not set
@@ -1058,17 +1095,46 @@ CONFIG_VIDEO_HELPER_CHIPS_AUTO=y
 # CONFIG_VIDEO_CPIA2 is not set
 # CONFIG_VIDEO_SAA5246A is not set
 # CONFIG_VIDEO_SAA5249 is not set
-# CONFIG_TUNER_3036 is not set
 # CONFIG_VIDEO_STRADIS is not set
 # CONFIG_VIDEO_SAA7134 is not set
 # CONFIG_VIDEO_MXB is not set
-# CONFIG_VIDEO_DPC is not set
 # CONFIG_VIDEO_HEXIUM_ORION is not set
 # CONFIG_VIDEO_HEXIUM_GEMINI is not set
 # CONFIG_VIDEO_CX88 is not set
 # CONFIG_VIDEO_IVTV is not set
 # CONFIG_VIDEO_CAFE_CCIC is not set
+CONFIG_SOC_CAMERA=m
+CONFIG_SOC_CAMERA_MT9M001=m
+CONFIG_SOC_CAMERA_MT9M111=m
+CONFIG_SOC_CAMERA_MT9V022=m
+CONFIG_SOC_CAMERA_PLATFORM=m
+CONFIG_VIDEO_SH_MOBILE_CEU=m
 CONFIG_V4L_USB_DRIVERS=y
+CONFIG_USB_VIDEO_CLASS=m
+CONFIG_USB_VIDEO_CLASS_INPUT_EVDEV=y
+CONFIG_USB_GSPCA=m
+CONFIG_USB_M5602=m
+CONFIG_USB_GSPCA_CONEX=m
+CONFIG_USB_GSPCA_ETOMS=m
+CONFIG_USB_GSPCA_FINEPIX=m
+CONFIG_USB_GSPCA_MARS=m
+CONFIG_USB_GSPCA_OV519=m
+CONFIG_USB_GSPCA_PAC207=m
+CONFIG_USB_GSPCA_PAC7311=m
+CONFIG_USB_GSPCA_SONIXB=m
+CONFIG_USB_GSPCA_SONIXJ=m
+CONFIG_USB_GSPCA_SPCA500=m
+CONFIG_USB_GSPCA_SPCA501=m
+CONFIG_USB_GSPCA_SPCA505=m
+CONFIG_USB_GSPCA_SPCA506=m
+CONFIG_USB_GSPCA_SPCA508=m
+CONFIG_USB_GSPCA_SPCA561=m
+CONFIG_USB_GSPCA_STK014=m
+CONFIG_USB_GSPCA_SUNPLUS=m
+CONFIG_USB_GSPCA_T613=m
+CONFIG_USB_GSPCA_TV8532=m
+CONFIG_USB_GSPCA_VC032X=m
+CONFIG_USB_GSPCA_ZC3XX=m
 # CONFIG_VIDEO_PVRUSB2 is not set
 # CONFIG_VIDEO_EM28XX is not set
 # CONFIG_VIDEO_USBVISION is not set
@@ -1079,7 +1145,6 @@ CONFIG_USB_KONICAWC=m
 CONFIG_USB_QUICKCAM_MESSENGER=m
 CONFIG_USB_ET61X251=m
 # CONFIG_VIDEO_OVCAMCHIP is not set
-# CONFIG_USB_W9968CF is not set
 CONFIG_USB_OV511=m
 CONFIG_USB_SE401=m
 CONFIG_USB_SN9C102=m
@@ -1088,6 +1153,8 @@ CONFIG_USB_ZC0301=m
 CONFIG_USB_PWC=m
 # CONFIG_USB_PWC_DEBUG is not set
 # CONFIG_USB_ZR364XX is not set
+CONFIG_USB_STKWEBCAM=m
+CONFIG_USB_S2255=m
 CONFIG_RADIO_ADAPTERS=y
 # CONFIG_RADIO_CADET is not set
 # CONFIG_RADIO_RTRACK is not set
@@ -1104,33 +1171,30 @@ CONFIG_RADIO_ADAPTERS=y
 # CONFIG_RADIO_TYPHOON is not set
 # CONFIG_RADIO_ZOLTRIX is not set
 # CONFIG_USB_DSBR is not set
-# CONFIG_DVB_CORE is not set
+CONFIG_USB_SI470X=m
+CONFIG_USB_MR800=m
 CONFIG_DAB=y
 # CONFIG_USB_DABUSB is not set
 
 #
 # Graphics support
 #
-CONFIG_BACKLIGHT_LCD_SUPPORT=y
-CONFIG_BACKLIGHT_CLASS_DEVICE=y
-CONFIG_LCD_CLASS_DEVICE=m
-
-#
-# Display device support
-#
-# CONFIG_DISPLAY_SUPPORT is not set
+# CONFIG_DRM is not set
 # CONFIG_VGASTATE is not set
+CONFIG_VIDEO_OUTPUT_CONTROL=m
 CONFIG_FB=y
 # CONFIG_FIRMWARE_EDID is not set
 # CONFIG_FB_DDC is not set
+# CONFIG_FB_BOOT_VESA_SUPPORT is not set
 CONFIG_FB_CFB_FILLRECT=y
 CONFIG_FB_CFB_COPYAREA=y
 CONFIG_FB_CFB_IMAGEBLIT=y
+# CONFIG_FB_CFB_REV_PIXELS_IN_BYTE is not set
 # CONFIG_FB_SYS_FILLRECT is not set
 # CONFIG_FB_SYS_COPYAREA is not set
 # CONFIG_FB_SYS_IMAGEBLIT is not set
+# CONFIG_FB_FOREIGN_ENDIAN is not set
 # CONFIG_FB_SYS_FOPS is not set
-CONFIG_FB_DEFERRED_IO=y
 # CONFIG_FB_SVGALIB is not set
 # CONFIG_FB_MACMODES is not set
 CONFIG_FB_BACKLIGHT=y
@@ -1158,16 +1222,30 @@ CONFIG_FB_RADEON_BACKLIGHT=y
 # CONFIG_FB_S3 is not set
 # CONFIG_FB_SAVAGE is not set
 # CONFIG_FB_SIS is not set
+# CONFIG_FB_VIA is not set
 # CONFIG_FB_NEOMAGIC is not set
 # CONFIG_FB_KYRO is not set
 # CONFIG_FB_3DFX is not set
 # CONFIG_FB_VOODOO1 is not set
-# CONFIG_FB_SMIVGX is not set
 # CONFIG_FB_VT8623 is not set
 # CONFIG_FB_TRIDENT is not set
 # CONFIG_FB_ARK is not set
 # CONFIG_FB_PM3 is not set
+# CONFIG_FB_CARMINE is not set
 # CONFIG_FB_VIRTUAL is not set
+# CONFIG_FB_METRONOME is not set
+# CONFIG_FB_MB862XX is not set
+CONFIG_BACKLIGHT_LCD_SUPPORT=y
+CONFIG_LCD_CLASS_DEVICE=m
+# CONFIG_LCD_ILI9320 is not set
+# CONFIG_LCD_PLATFORM is not set
+CONFIG_BACKLIGHT_CLASS_DEVICE=y
+# CONFIG_BACKLIGHT_CORGI is not set
+
+#
+# Display device support
+#
+# CONFIG_DISPLAY_SUPPORT is not set
 
 #
 # Console display driver support
@@ -1176,20 +1254,14 @@ CONFIG_FB_RADEON_BACKLIGHT=y
 # CONFIG_MDA_CONSOLE is not set
 CONFIG_DUMMY_CONSOLE=y
 CONFIG_FRAMEBUFFER_CONSOLE=y
+# CONFIG_FRAMEBUFFER_CONSOLE_DETECT_PRIMARY is not set
 # CONFIG_FRAMEBUFFER_CONSOLE_ROTATION is not set
 # CONFIG_FONTS is not set
 CONFIG_FONT_8x8=y
 CONFIG_FONT_8x16=y
 # CONFIG_LOGO is not set
-
-#
-# Sound
-#
 CONFIG_SOUND=y
-
-#
-# Advanced Linux Sound Architecture
-#
+CONFIG_SOUND_OSS_CORE=y
 CONFIG_SND=m
 CONFIG_SND_TIMER=m
 CONFIG_SND_PCM=m
@@ -1201,28 +1273,22 @@ CONFIG_SND_MIXER_OSS=m
 CONFIG_SND_PCM_OSS=m
 CONFIG_SND_PCM_OSS_PLUGINS=y
 CONFIG_SND_SEQUENCER_OSS=y
-CONFIG_SND_RTCTIMER=m
-CONFIG_SND_SEQ_RTCTIMER_DEFAULT=y
 # CONFIG_SND_DYNAMIC_MINORS is not set
 CONFIG_SND_SUPPORT_OLD_API=y
 CONFIG_SND_VERBOSE_PROCFS=y
 # CONFIG_SND_VERBOSE_PRINTK is not set
 # CONFIG_SND_DEBUG is not set
-
-#
-# Generic devices
-#
+CONFIG_SND_VMASTER=y
 CONFIG_SND_MPU401_UART=m
 CONFIG_SND_AC97_CODEC=m
+CONFIG_SND_DRIVERS=y
 # CONFIG_SND_DUMMY is not set
 # CONFIG_SND_VIRMIDI is not set
 # CONFIG_SND_MTPAV is not set
 # CONFIG_SND_SERIAL_U16550 is not set
 # CONFIG_SND_MPU401 is not set
-
-#
-# PCI devices
-#
+# CONFIG_SND_AC97_POWER_SAVE is not set
+CONFIG_SND_PCI=y
 # CONFIG_SND_AD1889 is not set
 # CONFIG_SND_ALS300 is not set
 # CONFIG_SND_ALI5451 is not set
@@ -1231,10 +1297,12 @@ CONFIG_SND_AC97_CODEC=m
 # CONFIG_SND_AU8810 is not set
 # CONFIG_SND_AU8820 is not set
 # CONFIG_SND_AU8830 is not set
+# CONFIG_SND_AW2 is not set
 # CONFIG_SND_AZT3328 is not set
 # CONFIG_SND_BT87X is not set
 # CONFIG_SND_CA0106 is not set
 # CONFIG_SND_CMIPCI is not set
+# CONFIG_SND_OXYGEN is not set
 # CONFIG_SND_CS4281 is not set
 # CONFIG_SND_CS46XX is not set
 # CONFIG_SND_DARLA20 is not set
@@ -1259,6 +1327,7 @@ CONFIG_SND_AC97_CODEC=m
 # CONFIG_SND_HDA_INTEL is not set
 # CONFIG_SND_HDSP is not set
 # CONFIG_SND_HDSPM is not set
+# CONFIG_SND_HIFIER is not set
 # CONFIG_SND_ICE1712 is not set
 # CONFIG_SND_ICE1724 is not set
 # CONFIG_SND_INTEL8X0 is not set
@@ -1276,43 +1345,26 @@ CONFIG_SND_AC97_CODEC=m
 # CONFIG_SND_TRIDENT is not set
 CONFIG_SND_VIA82XX=m
 # CONFIG_SND_VIA82XX_MODEM is not set
+# CONFIG_SND_VIRTUOSO is not set
 # CONFIG_SND_VX222 is not set
 # CONFIG_SND_YMFPCI is not set
-# CONFIG_SND_AC97_POWER_SAVE is not set
-
-#
-# ALSA MIPS devices
-#
-
-#
-# USB devices
-#
+CONFIG_SND_MIPS=y
+CONFIG_SND_USB=y
 # CONFIG_SND_USB_AUDIO is not set
 # CONFIG_SND_USB_CAIAQ is not set
-
-#
-# System on Chip audio support
-#
 # CONFIG_SND_SOC is not set
-
-#
-# Open Sound System
-#
 # CONFIG_SOUND_PRIME is not set
 CONFIG_AC97_BUS=m
-
-#
-# HID Devices
-#
+CONFIG_HID_SUPPORT=y
 CONFIG_HID=y
 # CONFIG_HID_DEBUG is not set
+CONFIG_HIDRAW=y
 
 #
 # USB Input Devices
 #
 CONFIG_USB_HID=m
-# CONFIG_USB_HIDINPUT_POWERBOOK is not set
-# CONFIG_HID_FF is not set
+CONFIG_HID_PID=y
 CONFIG_USB_HIDDEV=y
 
 #
@@ -1322,13 +1374,39 @@ CONFIG_USB_HIDDEV=y
 # CONFIG_USB_MOUSE is not set
 
 #
-# USB support
-#
+# Special HID drivers
+#
+CONFIG_HID_COMPAT=y
+CONFIG_HID_A4TECH=m
+CONFIG_HID_APPLE=m
+CONFIG_HID_BELKIN=m
+CONFIG_HID_BRIGHT=m
+CONFIG_HID_CHERRY=m
+CONFIG_HID_CHICONY=m
+CONFIG_HID_CYPRESS=m
+CONFIG_HID_DELL=m
+CONFIG_HID_EZKEY=m
+CONFIG_HID_GYRATION=m
+CONFIG_HID_LOGITECH=m
+CONFIG_LOGITECH_FF=y
+CONFIG_LOGIRUMBLEPAD2_FF=y
+CONFIG_HID_MICROSOFT=m
+CONFIG_HID_MONTEREY=m
+CONFIG_HID_PANTHERLORD=m
+# CONFIG_PANTHERLORD_FF is not set
+CONFIG_HID_PETALYNX=m
+CONFIG_HID_SAMSUNG=m
+CONFIG_HID_SONY=m
+CONFIG_HID_SUNPLUS=m
+# CONFIG_THRUSTMASTER_FF is not set
+CONFIG_ZEROPLUS_FF=m
+CONFIG_USB_SUPPORT=y
 CONFIG_USB_ARCH_HAS_HCD=y
 CONFIG_USB_ARCH_HAS_OHCI=y
 CONFIG_USB_ARCH_HAS_EHCI=y
 CONFIG_USB=y
 # CONFIG_USB_DEBUG is not set
+CONFIG_USB_ANNOUNCE_NEW_DEVICES=y
 
 #
 # Miscellaneous USB options
@@ -1338,35 +1416,46 @@ CONFIG_USB_DEVICEFS=y
 # CONFIG_USB_DYNAMIC_MINORS is not set
 # CONFIG_USB_SUSPEND is not set
 # CONFIG_USB_OTG is not set
+CONFIG_USB_OTG_WHITELIST=y
+# CONFIG_USB_OTG_BLACKLIST_HUB is not set
+# CONFIG_USB_MON is not set
+# CONFIG_USB_WUSB is not set
+CONFIG_USB_WUSB_CBAF=m
+# CONFIG_USB_WUSB_CBAF_DEBUG is not set
 
 #
 # USB Host Controller Drivers
 #
+CONFIG_USB_C67X00_HCD=m
 CONFIG_USB_EHCI_HCD=y
-CONFIG_USB_EHCI_SPLIT_ISO=y
 CONFIG_USB_EHCI_ROOT_HUB_TT=y
 CONFIG_USB_EHCI_TT_NEWSCHED=y
-# CONFIG_USB_EHCI_BIG_ENDIAN_MMIO is not set
 # CONFIG_USB_ISP116X_HCD is not set
+CONFIG_USB_ISP1760_HCD=m
 CONFIG_USB_OHCI_HCD=y
 # CONFIG_USB_OHCI_BIG_ENDIAN_DESC is not set
 # CONFIG_USB_OHCI_BIG_ENDIAN_MMIO is not set
 CONFIG_USB_OHCI_LITTLE_ENDIAN=y
 CONFIG_USB_UHCI_HCD=m
 # CONFIG_USB_SL811_HCD is not set
+CONFIG_USB_R8A66597_HCD=m
+# CONFIG_USB_WHCI_HCD is not set
+# CONFIG_USB_HWA_HCD is not set
 
 #
 # USB Device Class drivers
 #
 CONFIG_USB_ACM=y
 CONFIG_USB_PRINTER=y
+CONFIG_USB_WDM=m
+CONFIG_USB_TMC=m
 
 #
-# NOTE: USB_STORAGE enables SCSI, and 'SCSI disk support'
+# NOTE: USB_STORAGE depends on SCSI but BLK_DEV_SD may also be needed;
 #
 
 #
-# may also be needed; see USB_STORAGE Help for more information
+# see USB_STORAGE Help for more information
 #
 CONFIG_USB_STORAGE=y
 # CONFIG_USB_STORAGE_DEBUG is not set
@@ -1379,7 +1468,9 @@ CONFIG_USB_STORAGE=y
 # CONFIG_USB_STORAGE_SDDR55 is not set
 # CONFIG_USB_STORAGE_JUMPSHOT is not set
 # CONFIG_USB_STORAGE_ALAUDA is not set
+CONFIG_USB_STORAGE_ONETOUCH=y
 # CONFIG_USB_STORAGE_KARMA is not set
+CONFIG_USB_STORAGE_CYPRESS_ATACB=y
 CONFIG_USB_LIBUSUAL=y
 
 #
@@ -1387,15 +1478,10 @@ CONFIG_USB_LIBUSUAL=y
 #
 # CONFIG_USB_MDC800 is not set
 # CONFIG_USB_MICROTEK is not set
-# CONFIG_USB_MON is not set
 
 #
 # USB port drivers
 #
-
-#
-# USB Serial Converter support
-#
 # CONFIG_USB_SERIAL is not set
 
 #
@@ -1404,7 +1490,7 @@ CONFIG_USB_LIBUSUAL=y
 # CONFIG_USB_EMI62 is not set
 # CONFIG_USB_EMI26 is not set
 # CONFIG_USB_ADUTUX is not set
-# CONFIG_USB_AUERSWALD is not set
+CONFIG_USB_SEVSEG=m
 # CONFIG_USB_RIO500 is not set
 # CONFIG_USB_LEGOTOWER is not set
 # CONFIG_USB_LCD is not set
@@ -1421,56 +1507,75 @@ CONFIG_USB_LIBUSUAL=y
 # CONFIG_USB_TRANCEVIBRATOR is not set
 # CONFIG_USB_IOWARRIOR is not set
 # CONFIG_USB_TEST is not set
-
-#
-# USB DSL modem support
-#
-
-#
-# USB Gadget Support
-#
+CONFIG_USB_ISIGHTFW=m
+CONFIG_USB_VST=m
 # CONFIG_USB_GADGET is not set
+# CONFIG_UWB is not set
 # CONFIG_MMC is not set
-
-#
-# LED devices
-#
+# CONFIG_MEMSTICK is not set
 # CONFIG_NEW_LEDS is not set
-
-#
-# LED drivers
-#
-
-#
-# LED Triggers
-#
-
-#
-# InfiniBand support
-#
+# CONFIG_ACCESSIBILITY is not set
 # CONFIG_INFINIBAND is not set
+CONFIG_RTC_LIB=y
+CONFIG_RTC_CLASS=m
 
 #
-# EDAC - error detection and reporting (RAS) (EXPERIMENTAL)
+# RTC interfaces
 #
+CONFIG_RTC_INTF_SYSFS=y
+CONFIG_RTC_INTF_PROC=y
+CONFIG_RTC_INTF_DEV=y
+CONFIG_RTC_INTF_DEV_UIE_EMUL=y
+# CONFIG_RTC_DRV_TEST is not set
 
 #
-# Real Time Clock
+# I2C RTC drivers
 #
-# CONFIG_RTC_CLASS is not set
+# CONFIG_RTC_DRV_DS1307 is not set
+# CONFIG_RTC_DRV_DS1374 is not set
+# CONFIG_RTC_DRV_DS1672 is not set
+# CONFIG_RTC_DRV_MAX6900 is not set
+# CONFIG_RTC_DRV_RS5C372 is not set
+# CONFIG_RTC_DRV_ISL1208 is not set
+# CONFIG_RTC_DRV_X1205 is not set
+# CONFIG_RTC_DRV_PCF8563 is not set
+# CONFIG_RTC_DRV_PCF8583 is not set
+# CONFIG_RTC_DRV_M41T80 is not set
+# CONFIG_RTC_DRV_S35390A is not set
+# CONFIG_RTC_DRV_FM3130 is not set
+# CONFIG_RTC_DRV_RX8581 is not set
 
 #
-# DMA Engine support
+# SPI RTC drivers
 #
-# CONFIG_DMA_ENGINE is not set
 
 #
-# DMA Clients
+# Platform RTC drivers
 #
+CONFIG_RTC_DRV_CMOS=m
+# CONFIG_RTC_DRV_DS1286 is not set
+# CONFIG_RTC_DRV_DS1511 is not set
+# CONFIG_RTC_DRV_DS1553 is not set
+# CONFIG_RTC_DRV_DS1742 is not set
+# CONFIG_RTC_DRV_STK17TA8 is not set
+# CONFIG_RTC_DRV_M48T86 is not set
+# CONFIG_RTC_DRV_M48T35 is not set
+# CONFIG_RTC_DRV_M48T59 is not set
+# CONFIG_RTC_DRV_BQ4802 is not set
+# CONFIG_RTC_DRV_V3020 is not set
 
 #
-# DMA Devices
+# on-CPU RTC drivers
 #
+# CONFIG_DMADEVICES is not set
+CONFIG_UIO=m
+CONFIG_UIO_CIF=m
+# CONFIG_UIO_PDRV is not set
+# CONFIG_UIO_PDRV_GENIRQ is not set
+# CONFIG_UIO_SMX is not set
+# CONFIG_UIO_SERCOS3 is not set
+# CONFIG_STAGING is not set
+CONFIG_STAGING_EXCLUDE_BUILD=y
 
 #
 # File systems
@@ -1478,27 +1583,31 @@ CONFIG_USB_LIBUSUAL=y
 CONFIG_EXT2_FS=y
 # CONFIG_EXT2_FS_XATTR is not set
 CONFIG_EXT2_FS_XIP=y
-CONFIG_FS_XIP=y
 CONFIG_EXT3_FS=y
 # CONFIG_EXT3_FS_XATTR is not set
-# CONFIG_EXT4DEV_FS is not set
+CONFIG_EXT4_FS=m
+CONFIG_EXT4DEV_COMPAT=y
+CONFIG_EXT4_FS_XATTR=y
+CONFIG_EXT4_FS_POSIX_ACL=y
+CONFIG_EXT4_FS_SECURITY=y
+CONFIG_FS_XIP=y
 CONFIG_JBD=y
-# CONFIG_JBD_DEBUG is not set
+CONFIG_JBD2=m
+CONFIG_FS_MBCACHE=m
 CONFIG_REISERFS_FS=m
 # CONFIG_REISERFS_CHECK is not set
 # CONFIG_REISERFS_PROC_INFO is not set
 # CONFIG_REISERFS_FS_XATTR is not set
 # CONFIG_JFS_FS is not set
 CONFIG_FS_POSIX_ACL=y
+CONFIG_FILE_LOCKING=y
 # CONFIG_XFS_FS is not set
 # CONFIG_GFS2_FS is not set
 # CONFIG_OCFS2_FS is not set
-# CONFIG_MINIX_FS is not set
-# CONFIG_ROMFS_FS is not set
+CONFIG_DNOTIFY=y
 CONFIG_INOTIFY=y
 CONFIG_INOTIFY_USER=y
 # CONFIG_QUOTA is not set
-CONFIG_DNOTIFY=y
 CONFIG_AUTOFS_FS=y
 CONFIG_AUTOFS4_FS=y
 CONFIG_FUSE_FS=y
@@ -1530,11 +1639,11 @@ CONFIG_NTFS_RW=y
 CONFIG_PROC_FS=y
 CONFIG_PROC_KCORE=y
 CONFIG_PROC_SYSCTL=y
+CONFIG_PROC_PAGE_MONITOR=y
 CONFIG_SYSFS=y
 CONFIG_TMPFS=y
 # CONFIG_TMPFS_POSIX_ACL is not set
 # CONFIG_HUGETLB_PAGE is not set
-CONFIG_RAMFS=y
 # CONFIG_CONFIGFS_FS is not set
 
 #
@@ -1550,25 +1659,23 @@ CONFIG_RAMFS=y
 # CONFIG_JFFS2_FS is not set
 # CONFIG_CRAMFS is not set
 # CONFIG_VXFS_FS is not set
+# CONFIG_MINIX_FS is not set
+CONFIG_OMFS_FS=m
 # CONFIG_HPFS_FS is not set
 # CONFIG_QNX4FS_FS is not set
+# CONFIG_ROMFS_FS is not set
 # CONFIG_SYSV_FS is not set
 # CONFIG_UFS_FS is not set
-
-#
-# Network File Systems
-#
+CONFIG_NETWORK_FILESYSTEMS=y
 CONFIG_NFS_FS=m
 CONFIG_NFS_V3=y
 CONFIG_NFS_V3_ACL=y
 CONFIG_NFS_V4=y
-CONFIG_NFS_DIRECTIO=y
 CONFIG_NFSD=m
 CONFIG_NFSD_V2_ACL=y
 CONFIG_NFSD_V3=y
 CONFIG_NFSD_V3_ACL=y
 CONFIG_NFSD_V4=y
-CONFIG_NFSD_TCP=y
 CONFIG_LOCKD=m
 CONFIG_LOCKD_V4=y
 CONFIG_EXPORTFS=m
@@ -1576,7 +1683,7 @@ CONFIG_NFS_ACL_SUPPORT=m
 CONFIG_NFS_COMMON=y
 CONFIG_SUNRPC=m
 CONFIG_SUNRPC_GSS=m
-# CONFIG_SUNRPC_BIND34 is not set
+# CONFIG_SUNRPC_REGISTER_V4 is not set
 CONFIG_RPCSEC_GSS_KRB5=m
 # CONFIG_RPCSEC_GSS_SPKM3 is not set
 CONFIG_SMB_FS=m
@@ -1616,10 +1723,6 @@ CONFIG_MSDOS_PARTITION=y
 # CONFIG_KARMA_PARTITION is not set
 # CONFIG_EFI_PARTITION is not set
 # CONFIG_SYSV68_PARTITION is not set
-
-#
-# Native Language Support
-#
 CONFIG_NLS=y
 CONFIG_NLS_DEFAULT="utf8"
 # CONFIG_NLS_CODEPAGE_437 is not set
@@ -1660,30 +1763,31 @@ CONFIG_NLS_ISO8859_1=y
 # CONFIG_NLS_KOI8_R is not set
 # CONFIG_NLS_KOI8_U is not set
 CONFIG_NLS_UTF8=y
-
-#
-# Distributed Lock Manager
-#
 # CONFIG_DLM is not set
 
 #
-# Profiling support
-#
-CONFIG_PROFILING=y
-CONFIG_OPROFILE=m
-
-#
 # Kernel hacking
 #
 CONFIG_TRACE_IRQFLAGS_SUPPORT=y
 # CONFIG_PRINTK_TIME is not set
+CONFIG_ENABLE_WARN_DEPRECATED=y
 # CONFIG_ENABLE_MUST_CHECK is not set
+CONFIG_FRAME_WARN=2048
 # CONFIG_MAGIC_SYSRQ is not set
 # CONFIG_UNUSED_SYMBOLS is not set
 # CONFIG_DEBUG_FS is not set
 # CONFIG_HEADERS_CHECK is not set
 # CONFIG_DEBUG_KERNEL is not set
-CONFIG_CROSSCOMPILE=y
+# CONFIG_DEBUG_MEMORY_INIT is not set
+# CONFIG_RCU_CPU_STALL_DETECTOR is not set
+CONFIG_SYSCTL_SYSCALL_CHECK=y
+
+#
+# Tracers
+#
+CONFIG_DYNAMIC_PRINTK_DEBUG=y
+# CONFIG_SAMPLES is not set
+CONFIG_HAVE_ARCH_KGDB=y
 CONFIG_CMDLINE=""
 
 #
@@ -1691,64 +1795,113 @@ CONFIG_CMDLINE=""
 #
 # CONFIG_KEYS is not set
 # CONFIG_SECURITY is not set
+# CONFIG_SECURITYFS is not set
+CONFIG_SECURITY_FILE_CAPABILITIES=y
+CONFIG_CRYPTO=y
 
 #
-# Cryptographic options
+# Crypto core or helper
 #
-CONFIG_CRYPTO=y
+CONFIG_CRYPTO_FIPS=y
 CONFIG_CRYPTO_ALGAPI=y
-CONFIG_CRYPTO_BLKCIPHER=m
+CONFIG_CRYPTO_AEAD=y
+CONFIG_CRYPTO_BLKCIPHER=y
 CONFIG_CRYPTO_HASH=y
+CONFIG_CRYPTO_RNG=y
 CONFIG_CRYPTO_MANAGER=y
+CONFIG_CRYPTO_GF128MUL=m
+# CONFIG_CRYPTO_NULL is not set
+# CONFIG_CRYPTO_CRYPTD is not set
+CONFIG_CRYPTO_AUTHENC=m
+# CONFIG_CRYPTO_TEST is not set
+
+#
+# Authenticated Encryption with Associated Data
+#
+CONFIG_CRYPTO_CCM=m
+CONFIG_CRYPTO_GCM=m
+CONFIG_CRYPTO_SEQIV=m
+
+#
+# Block modes
+#
+CONFIG_CRYPTO_CBC=m
+CONFIG_CRYPTO_CTR=m
+CONFIG_CRYPTO_CTS=m
+CONFIG_CRYPTO_ECB=m
+# CONFIG_CRYPTO_LRW is not set
+CONFIG_CRYPTO_PCBC=m
+CONFIG_CRYPTO_XTS=m
+
+#
+# Hash modes
+#
 CONFIG_CRYPTO_HMAC=y
 # CONFIG_CRYPTO_XCBC is not set
-# CONFIG_CRYPTO_NULL is not set
+
+#
+# Digest
+#
+# CONFIG_CRYPTO_CRC32C is not set
 # CONFIG_CRYPTO_MD4 is not set
 CONFIG_CRYPTO_MD5=m
+# CONFIG_CRYPTO_MICHAEL_MIC is not set
+CONFIG_CRYPTO_RMD128=m
+CONFIG_CRYPTO_RMD160=m
+CONFIG_CRYPTO_RMD256=m
+CONFIG_CRYPTO_RMD320=m
 CONFIG_CRYPTO_SHA1=m
 # CONFIG_CRYPTO_SHA256 is not set
 # CONFIG_CRYPTO_SHA512 is not set
-# CONFIG_CRYPTO_WP512 is not set
 # CONFIG_CRYPTO_TGR192 is not set
-# CONFIG_CRYPTO_GF128MUL is not set
-CONFIG_CRYPTO_ECB=m
-CONFIG_CRYPTO_CBC=m
-CONFIG_CRYPTO_PCBC=m
-# CONFIG_CRYPTO_LRW is not set
-# CONFIG_CRYPTO_CRYPTD is not set
-CONFIG_CRYPTO_DES=m
-# CONFIG_CRYPTO_FCRYPT is not set
+# CONFIG_CRYPTO_WP512 is not set
+
+#
+# Ciphers
+#
+CONFIG_CRYPTO_AES=m
+# CONFIG_CRYPTO_ANUBIS is not set
+CONFIG_CRYPTO_ARC4=m
 # CONFIG_CRYPTO_BLOWFISH is not set
-# CONFIG_CRYPTO_TWOFISH is not set
-# CONFIG_CRYPTO_SERPENT is not set
-# CONFIG_CRYPTO_AES is not set
+# CONFIG_CRYPTO_CAMELLIA is not set
 # CONFIG_CRYPTO_CAST5 is not set
 # CONFIG_CRYPTO_CAST6 is not set
-# CONFIG_CRYPTO_TEA is not set
-CONFIG_CRYPTO_ARC4=m
+CONFIG_CRYPTO_DES=m
+# CONFIG_CRYPTO_FCRYPT is not set
 # CONFIG_CRYPTO_KHAZAD is not set
-# CONFIG_CRYPTO_ANUBIS is not set
+CONFIG_CRYPTO_SALSA20=m
+CONFIG_CRYPTO_SEED=m
+# CONFIG_CRYPTO_SERPENT is not set
+# CONFIG_CRYPTO_TEA is not set
+# CONFIG_CRYPTO_TWOFISH is not set
+
+#
+# Compression
+#
 CONFIG_CRYPTO_DEFLATE=m
-# CONFIG_CRYPTO_MICHAEL_MIC is not set
-# CONFIG_CRYPTO_CRC32C is not set
-# CONFIG_CRYPTO_CAMELLIA is not set
-# CONFIG_CRYPTO_TEST is not set
+CONFIG_CRYPTO_LZO=m
 
 #
-# Hardware crypto devices
+# Random Number Generation
 #
+CONFIG_CRYPTO_ANSI_CPRNG=m
+# CONFIG_CRYPTO_HW is not set
 
 #
 # Library routines
 #
 CONFIG_BITREVERSE=y
 CONFIG_CRC_CCITT=y
-# CONFIG_CRC16 is not set
-# CONFIG_CRC_ITU_T is not set
+CONFIG_CRC16=m
+# CONFIG_CRC_T10DIF is not set
+CONFIG_CRC_ITU_T=m
 CONFIG_CRC32=y
+CONFIG_CRC7=m
 # CONFIG_LIBCRC32C is not set
 CONFIG_ZLIB_INFLATE=m
 CONFIG_ZLIB_DEFLATE=m
+CONFIG_LZO_COMPRESS=m
+CONFIG_LZO_DECOMPRESS=m
 CONFIG_TEXTSEARCH=y
 CONFIG_TEXTSEARCH_KMP=m
 CONFIG_TEXTSEARCH_BM=m
diff --git a/arch/mips/configs/ip22_defconfig b/arch/mips/configs/ip22_defconfig
index f719bf5e01aa..115822876417 100644
--- a/arch/mips/configs/ip22_defconfig
+++ b/arch/mips/configs/ip22_defconfig
@@ -1,30 +1,34 @@
 #
 # Automatically generated make config: don't edit
-# Linux kernel version: 2.6.23-rc2
-# Tue Aug  7 12:39:49 2007
+# Linux kernel version: 2.6.28-rc6
+# Fri Nov 28 15:41:33 2008
 #
 CONFIG_MIPS=y
 
 #
 # Machine selection
 #
-CONFIG_ZONE_DMA=y
 # CONFIG_MACH_ALCHEMY is not set
 # CONFIG_BASLER_EXCITE is not set
+# CONFIG_BCM47XX is not set
 # CONFIG_MIPS_COBALT is not set
 # CONFIG_MACH_DECSTATION is not set
 # CONFIG_MACH_JAZZ is not set
+# CONFIG_LASAT is not set
 # CONFIG_LEMOTE_FULONG is not set
 # CONFIG_MIPS_MALTA is not set
 # CONFIG_MIPS_SIM is not set
-# CONFIG_MARKEINS is not set
+# CONFIG_MACH_EMMA is not set
 # CONFIG_MACH_VR41XX is not set
+# CONFIG_NXP_STB220 is not set
+# CONFIG_NXP_STB225 is not set
 # CONFIG_PNX8550_JBS is not set
 # CONFIG_PNX8550_STB810 is not set
 # CONFIG_PMC_MSP is not set
 # CONFIG_PMC_YOSEMITE is not set
 CONFIG_SGI_IP22=y
 # CONFIG_SGI_IP27 is not set
+# CONFIG_SGI_IP28 is not set
 # CONFIG_SGI_IP32 is not set
 # CONFIG_SIBYTE_CRHINE is not set
 # CONFIG_SIBYTE_CARMEL is not set
@@ -35,34 +39,49 @@ CONFIG_SGI_IP22=y
 # CONFIG_SIBYTE_SENTOSA is not set
 # CONFIG_SIBYTE_BIGSUR is not set
 # CONFIG_SNI_RM is not set
-# CONFIG_TOSHIBA_JMR3927 is not set
-# CONFIG_TOSHIBA_RBTX4927 is not set
-# CONFIG_TOSHIBA_RBTX4938 is not set
+# CONFIG_MACH_TX39XX is not set
+# CONFIG_MACH_TX49XX is not set
+# CONFIG_MIKROTIK_RB532 is not set
 # CONFIG_WR_PPMC is not set
 CONFIG_RWSEM_GENERIC_SPINLOCK=y
 # CONFIG_ARCH_HAS_ILOG2_U32 is not set
 # CONFIG_ARCH_HAS_ILOG2_U64 is not set
+CONFIG_ARCH_SUPPORTS_OPROFILE=y
 CONFIG_GENERIC_FIND_NEXT_BIT=y
 CONFIG_GENERIC_HWEIGHT=y
 CONFIG_GENERIC_CALIBRATE_DELAY=y
+CONFIG_GENERIC_CLOCKEVENTS=y
 CONFIG_GENERIC_TIME=y
+CONFIG_GENERIC_CMOS_UPDATE=y
 CONFIG_SCHED_NO_NO_OMIT_FRAME_POINTER=y
 # CONFIG_GENERIC_HARDIRQS_NO__DO_IRQ is not set
 CONFIG_ARC=y
+CONFIG_CEVT_R4K=y
+CONFIG_CSRC_R4K=y
 CONFIG_DMA_NONCOHERENT=y
 CONFIG_DMA_NEED_PCI_MAP_STATE=y
 CONFIG_EARLY_PRINTK=y
 CONFIG_SYS_HAS_EARLY_PRINTK=y
+# CONFIG_HOTPLUG_CPU is not set
+CONFIG_I8259=y
 # CONFIG_NO_IOPORT is not set
+CONFIG_GENERIC_ISA_DMA=y
 CONFIG_GENERIC_ISA_DMA_SUPPORT_BROKEN=y
 CONFIG_CPU_BIG_ENDIAN=y
 # CONFIG_CPU_LITTLE_ENDIAN is not set
 CONFIG_SYS_SUPPORTS_BIG_ENDIAN=y
 CONFIG_IRQ_CPU=y
 CONFIG_SWAP_IO_SPACE=y
+CONFIG_SGI_HAS_INDYDOG=y
+CONFIG_SGI_HAS_HAL2=y
+CONFIG_SGI_HAS_SEEQ=y
+CONFIG_SGI_HAS_WD93=y
+CONFIG_SGI_HAS_ZILOG=y
+CONFIG_SGI_HAS_I8042=y
+CONFIG_DEFAULT_SGI_PARTITION=y
 CONFIG_ARC32=y
 CONFIG_BOOT_ELF32=y
-CONFIG_MIPS_L1_CACHE_SHIFT=5
+CONFIG_MIPS_L1_CACHE_SHIFT=7
 CONFIG_ARC_CONSOLE=y
 CONFIG_ARC_PROMLIB=y
 
@@ -82,6 +101,7 @@ CONFIG_ARC_PROMLIB=y
 # CONFIG_CPU_TX49XX is not set
 CONFIG_CPU_R5000=y
 # CONFIG_CPU_R5432 is not set
+# CONFIG_CPU_R5500 is not set
 # CONFIG_CPU_R6000 is not set
 # CONFIG_CPU_NEVADA is not set
 # CONFIG_CPU_R8000 is not set
@@ -115,18 +135,24 @@ CONFIG_CPU_HAS_SYNC=y
 CONFIG_GENERIC_HARDIRQS=y
 CONFIG_GENERIC_IRQ_PROBE=y
 CONFIG_ARCH_FLATMEM_ENABLE=y
+CONFIG_ARCH_POPULATES_NODE_MAP=y
 CONFIG_SELECT_MEMORY_MODEL=y
 CONFIG_FLATMEM_MANUAL=y
 # CONFIG_DISCONTIGMEM_MANUAL is not set
 # CONFIG_SPARSEMEM_MANUAL is not set
 CONFIG_FLATMEM=y
 CONFIG_FLAT_NODE_MEM_MAP=y
-# CONFIG_SPARSEMEM_STATIC is not set
+CONFIG_PAGEFLAGS_EXTENDED=y
 CONFIG_SPLIT_PTLOCK_CPUS=4
 # CONFIG_RESOURCES_64BIT is not set
-CONFIG_ZONE_DMA_FLAG=1
-CONFIG_BOUNCE=y
+# CONFIG_PHYS_ADDR_T_64BIT is not set
+CONFIG_ZONE_DMA_FLAG=0
 CONFIG_VIRT_TO_BUS=y
+CONFIG_UNEVICTABLE_LRU=y
+CONFIG_TICK_ONESHOT=y
+CONFIG_NO_HZ=y
+CONFIG_HIGH_RES_TIMERS=y
+CONFIG_GENERIC_CLOCKEVENTS_BUILD=y
 # CONFIG_HZ_48 is not set
 # CONFIG_HZ_100 is not set
 # CONFIG_HZ_128 is not set
@@ -159,13 +185,20 @@ CONFIG_SYSVIPC_SYSCTL=y
 # CONFIG_POSIX_MQUEUE is not set
 # CONFIG_BSD_PROCESS_ACCT is not set
 # CONFIG_TASKSTATS is not set
-# CONFIG_USER_NS is not set
 # CONFIG_AUDIT is not set
 CONFIG_IKCONFIG=y
 CONFIG_IKCONFIG_PROC=y
 CONFIG_LOG_BUF_SHIFT=14
+# CONFIG_CGROUPS is not set
+# CONFIG_GROUP_SCHED is not set
 CONFIG_SYSFS_DEPRECATED=y
+CONFIG_SYSFS_DEPRECATED_V2=y
 CONFIG_RELAY=y
+CONFIG_NAMESPACES=y
+CONFIG_UTS_NS=y
+CONFIG_IPC_NS=y
+CONFIG_USER_NS=y
+CONFIG_PID_NS=y
 # CONFIG_BLK_DEV_INITRD is not set
 # CONFIG_CC_OPTIMIZE_FOR_SIZE is not set
 CONFIG_SYSCTL=y
@@ -177,6 +210,8 @@ CONFIG_KALLSYMS=y
 CONFIG_PRINTK=y
 CONFIG_BUG=y
 CONFIG_ELF_CORE=y
+# CONFIG_PCSPKR_PLATFORM is not set
+# CONFIG_COMPAT_BRK is not set
 CONFIG_BASE_FULL=y
 CONFIG_FUTEX=y
 CONFIG_ANON_INODES=y
@@ -185,14 +220,21 @@ CONFIG_SIGNALFD=y
 CONFIG_TIMERFD=y
 CONFIG_EVENTFD=y
 CONFIG_SHMEM=y
+CONFIG_AIO=y
 CONFIG_VM_EVENT_COUNTERS=y
 CONFIG_SLAB=y
 # CONFIG_SLUB is not set
 # CONFIG_SLOB is not set
+# CONFIG_PROFILING is not set
+# CONFIG_MARKERS is not set
+CONFIG_HAVE_OPROFILE=y
+# CONFIG_HAVE_GENERIC_DMA_COHERENT is not set
+CONFIG_SLABINFO=y
 CONFIG_RT_MUTEXES=y
 # CONFIG_TINY_SHMEM is not set
 CONFIG_BASE_SMALL=0
 CONFIG_MODULES=y
+# CONFIG_MODULE_FORCE_LOAD is not set
 CONFIG_MODULE_UNLOAD=y
 # CONFIG_MODULE_FORCE_UNLOAD is not set
 CONFIG_MODVERSIONS=y
@@ -203,6 +245,7 @@ CONFIG_BLOCK=y
 # CONFIG_BLK_DEV_IO_TRACE is not set
 # CONFIG_LSF is not set
 # CONFIG_BLK_DEV_BSG is not set
+# CONFIG_BLK_DEV_INTEGRITY is not set
 
 #
 # IO Schedulers
@@ -216,6 +259,8 @@ CONFIG_DEFAULT_AS=y
 # CONFIG_DEFAULT_CFQ is not set
 # CONFIG_DEFAULT_NOOP is not set
 CONFIG_DEFAULT_IOSCHED="anticipatory"
+CONFIG_CLASSIC_RCU=y
+# CONFIG_FREEZER is not set
 
 #
 # Bus options (PCI, PCMCIA, EISA, ISA, TC)
@@ -224,29 +269,24 @@ CONFIG_HW_HAS_EISA=y
 # CONFIG_ARCH_SUPPORTS_MSI is not set
 # CONFIG_EISA is not set
 CONFIG_MMU=y
-
-#
-# PCCARD (PCMCIA/CardBus) support
-#
+CONFIG_I8253=y
 
 #
 # Executable file formats
 #
 CONFIG_BINFMT_ELF=y
+# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
+# CONFIG_HAVE_AOUT is not set
 CONFIG_BINFMT_MISC=m
 CONFIG_TRAD_SIGNALS=y
 
 #
 # Power management options
 #
+CONFIG_ARCH_SUSPEND_POSSIBLE=y
 CONFIG_PM=y
-# CONFIG_PM_LEGACY is not set
 # CONFIG_PM_DEBUG is not set
 # CONFIG_SUSPEND is not set
-
-#
-# Networking
-#
 CONFIG_NET=y
 
 #
@@ -259,6 +299,8 @@ CONFIG_XFRM=y
 CONFIG_XFRM_USER=m
 # CONFIG_XFRM_SUB_POLICY is not set
 CONFIG_XFRM_MIGRATE=y
+# CONFIG_XFRM_STATISTICS is not set
+CONFIG_XFRM_IPCOMP=m
 CONFIG_NET_KEY=y
 CONFIG_NET_KEY_MIGRATE=y
 CONFIG_INET=y
@@ -282,42 +324,13 @@ CONFIG_INET_TUNNEL=m
 CONFIG_INET_XFRM_MODE_TRANSPORT=m
 CONFIG_INET_XFRM_MODE_TUNNEL=m
 CONFIG_INET_XFRM_MODE_BEET=m
+# CONFIG_INET_LRO is not set
 CONFIG_INET_DIAG=y
 CONFIG_INET_TCP_DIAG=y
 # CONFIG_TCP_CONG_ADVANCED is not set
 CONFIG_TCP_CONG_CUBIC=y
 CONFIG_DEFAULT_TCP_CONG="cubic"
 CONFIG_TCP_MD5SIG=y
-CONFIG_IP_VS=m
-# CONFIG_IP_VS_DEBUG is not set
-CONFIG_IP_VS_TAB_BITS=12
-
-#
-# IPVS transport protocol load balancing support
-#
-CONFIG_IP_VS_PROTO_TCP=y
-CONFIG_IP_VS_PROTO_UDP=y
-CONFIG_IP_VS_PROTO_ESP=y
-CONFIG_IP_VS_PROTO_AH=y
-
-#
-# IPVS scheduler
-#
-CONFIG_IP_VS_RR=m
-CONFIG_IP_VS_WRR=m
-CONFIG_IP_VS_LC=m
-CONFIG_IP_VS_WLC=m
-CONFIG_IP_VS_LBLC=m
-CONFIG_IP_VS_LBLCR=m
-CONFIG_IP_VS_DH=m
-CONFIG_IP_VS_SH=m
-CONFIG_IP_VS_SED=m
-CONFIG_IP_VS_NQ=m
-
-#
-# IPVS application helper
-#
-CONFIG_IP_VS_FTP=m
 CONFIG_IPV6=m
 CONFIG_IPV6_PRIVACY=y
 CONFIG_IPV6_ROUTER_PREF=y
@@ -334,12 +347,16 @@ CONFIG_INET6_XFRM_MODE_TUNNEL=m
 CONFIG_INET6_XFRM_MODE_BEET=m
 CONFIG_INET6_XFRM_MODE_ROUTEOPTIMIZATION=m
 CONFIG_IPV6_SIT=m
+CONFIG_IPV6_NDISC_NODETYPE=y
 CONFIG_IPV6_TUNNEL=m
 CONFIG_IPV6_MULTIPLE_TABLES=y
 CONFIG_IPV6_SUBTREES=y
+CONFIG_IPV6_MROUTE=y
+CONFIG_IPV6_PIMSM_V2=y
 CONFIG_NETWORK_SECMARK=y
 CONFIG_NETFILTER=y
 # CONFIG_NETFILTER_DEBUG is not set
+CONFIG_NETFILTER_ADVANCED=y
 
 #
 # Core Netfilter Configuration
@@ -347,12 +364,12 @@ CONFIG_NETFILTER=y
 CONFIG_NETFILTER_NETLINK=m
 CONFIG_NETFILTER_NETLINK_QUEUE=m
 CONFIG_NETFILTER_NETLINK_LOG=m
-CONFIG_NF_CONNTRACK_ENABLED=m
 CONFIG_NF_CONNTRACK=m
 CONFIG_NF_CT_ACCT=y
 CONFIG_NF_CONNTRACK_MARK=y
 CONFIG_NF_CONNTRACK_SECMARK=y
 CONFIG_NF_CONNTRACK_EVENTS=y
+CONFIG_NF_CT_PROTO_DCCP=m
 CONFIG_NF_CT_PROTO_GRE=m
 CONFIG_NF_CT_PROTO_SCTP=m
 CONFIG_NF_CT_PROTO_UDPLITE=m
@@ -366,18 +383,22 @@ CONFIG_NF_CONNTRACK_SANE=m
 CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
 CONFIG_NF_CT_NETLINK=m
+CONFIG_NETFILTER_TPROXY=m
 CONFIG_NETFILTER_XTABLES=m
 CONFIG_NETFILTER_XT_TARGET_CLASSIFY=m
 CONFIG_NETFILTER_XT_TARGET_CONNMARK=m
+CONFIG_NETFILTER_XT_TARGET_CONNSECMARK=m
 CONFIG_NETFILTER_XT_TARGET_DSCP=m
 CONFIG_NETFILTER_XT_TARGET_MARK=m
-CONFIG_NETFILTER_XT_TARGET_NFQUEUE=m
 CONFIG_NETFILTER_XT_TARGET_NFLOG=m
+CONFIG_NETFILTER_XT_TARGET_NFQUEUE=m
 CONFIG_NETFILTER_XT_TARGET_NOTRACK=m
+CONFIG_NETFILTER_XT_TARGET_RATEEST=m
+CONFIG_NETFILTER_XT_TARGET_TPROXY=m
 CONFIG_NETFILTER_XT_TARGET_TRACE=m
 CONFIG_NETFILTER_XT_TARGET_SECMARK=m
-CONFIG_NETFILTER_XT_TARGET_CONNSECMARK=m
 CONFIG_NETFILTER_XT_TARGET_TCPMSS=m
+CONFIG_NETFILTER_XT_TARGET_TCPOPTSTRIP=m
 CONFIG_NETFILTER_XT_MATCH_COMMENT=m
 CONFIG_NETFILTER_XT_MATCH_CONNBYTES=m
 CONFIG_NETFILTER_XT_MATCH_CONNLIMIT=m
@@ -386,39 +407,75 @@ CONFIG_NETFILTER_XT_MATCH_CONNTRACK=m
 CONFIG_NETFILTER_XT_MATCH_DCCP=m
 CONFIG_NETFILTER_XT_MATCH_DSCP=m
 CONFIG_NETFILTER_XT_MATCH_ESP=m
+CONFIG_NETFILTER_XT_MATCH_HASHLIMIT=m
 CONFIG_NETFILTER_XT_MATCH_HELPER=m
+CONFIG_NETFILTER_XT_MATCH_IPRANGE=m
 CONFIG_NETFILTER_XT_MATCH_LENGTH=m
 CONFIG_NETFILTER_XT_MATCH_LIMIT=m
 CONFIG_NETFILTER_XT_MATCH_MAC=m
 CONFIG_NETFILTER_XT_MATCH_MARK=m
-CONFIG_NETFILTER_XT_MATCH_POLICY=m
 CONFIG_NETFILTER_XT_MATCH_MULTIPORT=m
+CONFIG_NETFILTER_XT_MATCH_OWNER=m
+CONFIG_NETFILTER_XT_MATCH_POLICY=m
 CONFIG_NETFILTER_XT_MATCH_PKTTYPE=m
 CONFIG_NETFILTER_XT_MATCH_QUOTA=m
+CONFIG_NETFILTER_XT_MATCH_RATEEST=m
 CONFIG_NETFILTER_XT_MATCH_REALM=m
+CONFIG_NETFILTER_XT_MATCH_RECENT=m
+CONFIG_NETFILTER_XT_MATCH_RECENT_PROC_COMPAT=y
 CONFIG_NETFILTER_XT_MATCH_SCTP=m
+CONFIG_NETFILTER_XT_MATCH_SOCKET=m
 CONFIG_NETFILTER_XT_MATCH_STATE=m
 CONFIG_NETFILTER_XT_MATCH_STATISTIC=m
 CONFIG_NETFILTER_XT_MATCH_STRING=m
 CONFIG_NETFILTER_XT_MATCH_TCPMSS=m
+CONFIG_NETFILTER_XT_MATCH_TIME=m
 CONFIG_NETFILTER_XT_MATCH_U32=m
-CONFIG_NETFILTER_XT_MATCH_HASHLIMIT=m
+CONFIG_IP_VS=m
+CONFIG_IP_VS_IPV6=y
+# CONFIG_IP_VS_DEBUG is not set
+CONFIG_IP_VS_TAB_BITS=12
+
+#
+# IPVS transport protocol load balancing support
+#
+CONFIG_IP_VS_PROTO_TCP=y
+CONFIG_IP_VS_PROTO_UDP=y
+CONFIG_IP_VS_PROTO_AH_ESP=y
+CONFIG_IP_VS_PROTO_ESP=y
+CONFIG_IP_VS_PROTO_AH=y
+
+#
+# IPVS scheduler
+#
+CONFIG_IP_VS_RR=m
+CONFIG_IP_VS_WRR=m
+CONFIG_IP_VS_LC=m
+CONFIG_IP_VS_WLC=m
+CONFIG_IP_VS_LBLC=m
+CONFIG_IP_VS_LBLCR=m
+CONFIG_IP_VS_DH=m
+CONFIG_IP_VS_SH=m
+CONFIG_IP_VS_SED=m
+CONFIG_IP_VS_NQ=m
+
+#
+# IPVS application helper
+#
+CONFIG_IP_VS_FTP=m
 
 #
 # IP: Netfilter Configuration
 #
+CONFIG_NF_DEFRAG_IPV4=m
 CONFIG_NF_CONNTRACK_IPV4=m
 CONFIG_NF_CONNTRACK_PROC_COMPAT=y
 CONFIG_IP_NF_QUEUE=m
 CONFIG_IP_NF_IPTABLES=m
-CONFIG_IP_NF_MATCH_IPRANGE=m
-CONFIG_IP_NF_MATCH_TOS=m
-CONFIG_IP_NF_MATCH_RECENT=m
-CONFIG_IP_NF_MATCH_ECN=m
+CONFIG_IP_NF_MATCH_ADDRTYPE=m
 CONFIG_IP_NF_MATCH_AH=m
+CONFIG_IP_NF_MATCH_ECN=m
 CONFIG_IP_NF_MATCH_TTL=m
-CONFIG_IP_NF_MATCH_OWNER=m
-CONFIG_IP_NF_MATCH_ADDRTYPE=m
 CONFIG_IP_NF_FILTER=m
 CONFIG_IP_NF_TARGET_REJECT=m
 CONFIG_IP_NF_TARGET_LOG=m
@@ -426,11 +483,13 @@ CONFIG_IP_NF_TARGET_ULOG=m
 CONFIG_NF_NAT=m
 CONFIG_NF_NAT_NEEDED=y
 CONFIG_IP_NF_TARGET_MASQUERADE=m
-CONFIG_IP_NF_TARGET_REDIRECT=m
 CONFIG_IP_NF_TARGET_NETMAP=m
-CONFIG_IP_NF_TARGET_SAME=m
+CONFIG_IP_NF_TARGET_REDIRECT=m
 CONFIG_NF_NAT_SNMP_BASIC=m
+CONFIG_NF_NAT_PROTO_DCCP=m
 CONFIG_NF_NAT_PROTO_GRE=m
+CONFIG_NF_NAT_PROTO_UDPLITE=m
+CONFIG_NF_NAT_PROTO_SCTP=m
 CONFIG_NF_NAT_FTP=m
 CONFIG_NF_NAT_IRC=m
 CONFIG_NF_NAT_TFTP=m
@@ -439,32 +498,30 @@ CONFIG_NF_NAT_PPTP=m
 CONFIG_NF_NAT_H323=m
 CONFIG_NF_NAT_SIP=m
 CONFIG_IP_NF_MANGLE=m
-CONFIG_IP_NF_TARGET_TOS=m
+CONFIG_IP_NF_TARGET_CLUSTERIP=m
 CONFIG_IP_NF_TARGET_ECN=m
 CONFIG_IP_NF_TARGET_TTL=m
-CONFIG_IP_NF_TARGET_CLUSTERIP=m
 CONFIG_IP_NF_RAW=m
 CONFIG_IP_NF_ARPTABLES=m
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
 
 #
-# IPv6: Netfilter Configuration (EXPERIMENTAL)
+# IPv6: Netfilter Configuration
 #
 CONFIG_NF_CONNTRACK_IPV6=m
 CONFIG_IP6_NF_QUEUE=m
 CONFIG_IP6_NF_IPTABLES=m
-CONFIG_IP6_NF_MATCH_RT=m
-CONFIG_IP6_NF_MATCH_OPTS=m
+CONFIG_IP6_NF_MATCH_AH=m
+CONFIG_IP6_NF_MATCH_EUI64=m
 CONFIG_IP6_NF_MATCH_FRAG=m
+CONFIG_IP6_NF_MATCH_OPTS=m
 CONFIG_IP6_NF_MATCH_HL=m
-CONFIG_IP6_NF_MATCH_OWNER=m
 CONFIG_IP6_NF_MATCH_IPV6HEADER=m
-CONFIG_IP6_NF_MATCH_AH=m
 CONFIG_IP6_NF_MATCH_MH=m
-CONFIG_IP6_NF_MATCH_EUI64=m
-CONFIG_IP6_NF_FILTER=m
+CONFIG_IP6_NF_MATCH_RT=m
 CONFIG_IP6_NF_TARGET_LOG=m
+CONFIG_IP6_NF_FILTER=m
 CONFIG_IP6_NF_TARGET_REJECT=m
 CONFIG_IP6_NF_MANGLE=m
 CONFIG_IP6_NF_TARGET_HL=m
@@ -479,6 +536,7 @@ CONFIG_SCTP_HMAC_MD5=y
 # CONFIG_TIPC is not set
 # CONFIG_ATM is not set
 # CONFIG_BRIDGE is not set
+# CONFIG_NET_DSA is not set
 # CONFIG_VLAN_8021Q is not set
 # CONFIG_DECNET is not set
 # CONFIG_LLC2 is not set
@@ -488,12 +546,7 @@ CONFIG_SCTP_HMAC_MD5=y
 # CONFIG_LAPB is not set
 # CONFIG_ECONET is not set
 # CONFIG_WAN_ROUTER is not set
-
-#
-# QoS and/or fair queueing
-#
 CONFIG_NET_SCHED=y
-CONFIG_NET_SCH_FIFO=y
 
 #
 # Queueing/Scheduling
@@ -502,7 +555,7 @@ CONFIG_NET_SCH_CBQ=m
 CONFIG_NET_SCH_HTB=m
 CONFIG_NET_SCH_HFSC=m
 CONFIG_NET_SCH_PRIO=m
-CONFIG_NET_SCH_RR=m
+# CONFIG_NET_SCH_MULTIQ is not set
 CONFIG_NET_SCH_RED=m
 CONFIG_NET_SCH_SFQ=m
 CONFIG_NET_SCH_TEQL=m
@@ -526,6 +579,7 @@ CONFIG_NET_CLS_U32=m
 # CONFIG_CLS_U32_MARK is not set
 CONFIG_NET_CLS_RSVP=m
 CONFIG_NET_CLS_RSVP6=m
+CONFIG_NET_CLS_FLOW=m
 # CONFIG_NET_EMATCH is not set
 CONFIG_NET_CLS_ACT=y
 CONFIG_NET_ACT_POLICE=y
@@ -533,35 +587,28 @@ CONFIG_NET_ACT_GACT=m
 CONFIG_GACT_PROB=y
 CONFIG_NET_ACT_MIRRED=m
 CONFIG_NET_ACT_IPT=m
+CONFIG_NET_ACT_NAT=m
 CONFIG_NET_ACT_PEDIT=m
 CONFIG_NET_ACT_SIMP=m
-CONFIG_NET_CLS_POLICE=y
+CONFIG_NET_ACT_SKBEDIT=m
 # CONFIG_NET_CLS_IND is not set
+CONFIG_NET_SCH_FIFO=y
 
 #
 # Network testing
 #
 # CONFIG_NET_PKTGEN is not set
 # CONFIG_HAMRADIO is not set
+# CONFIG_CAN is not set
 # CONFIG_IRDA is not set
 # CONFIG_BT is not set
 # CONFIG_AF_RXRPC is not set
+CONFIG_PHONET=m
 CONFIG_FIB_RULES=y
-
-#
-# Wireless
-#
-CONFIG_CFG80211=m
+# CONFIG_WIRELESS is not set
 CONFIG_WIRELESS_EXT=y
-CONFIG_MAC80211=m
-# CONFIG_MAC80211_DEBUG is not set
 CONFIG_IEEE80211=m
-# CONFIG_IEEE80211_DEBUG is not set
 CONFIG_IEEE80211_CRYPT_WEP=m
-CONFIG_IEEE80211_CRYPT_CCMP=m
-CONFIG_IEEE80211_CRYPT_TKIP=m
-CONFIG_IEEE80211_SOFTMAC=m
-# CONFIG_IEEE80211_SOFTMAC_DEBUG is not set
 CONFIG_RFKILL=m
 CONFIG_RFKILL_INPUT=m
 # CONFIG_NET_9P is not set
@@ -588,7 +635,9 @@ CONFIG_CDROM_PKTCDVD=m
 CONFIG_CDROM_PKTCDVD_BUFFERS=8
 # CONFIG_CDROM_PKTCDVD_WCACHE is not set
 CONFIG_ATA_OVER_ETH=m
+# CONFIG_BLK_DEV_HD is not set
 # CONFIG_MISC_DEVICES is not set
+CONFIG_HAVE_IDE=y
 # CONFIG_IDE is not set
 
 #
@@ -628,20 +677,22 @@ CONFIG_SCSI_SPI_ATTRS=m
 # CONFIG_SCSI_FC_ATTRS is not set
 CONFIG_SCSI_ISCSI_ATTRS=m
 # CONFIG_SCSI_SAS_LIBSAS is not set
+# CONFIG_SCSI_SRP_ATTRS is not set
 CONFIG_SCSI_LOWLEVEL=y
 CONFIG_ISCSI_TCP=m
 CONFIG_SGIWD93_SCSI=y
 # CONFIG_SCSI_DEBUG is not set
+# CONFIG_SCSI_DH is not set
 # CONFIG_ATA is not set
 # CONFIG_MD is not set
 CONFIG_NETDEVICES=y
-# CONFIG_NETDEVICES_MULTIQUEUE is not set
 # CONFIG_IFB is not set
 CONFIG_DUMMY=m
 CONFIG_BONDING=m
 CONFIG_MACVLAN=m
 CONFIG_EQUALIZER=m
 CONFIG_TUN=m
+CONFIG_VETH=m
 CONFIG_PHYLIB=m
 
 #
@@ -656,11 +707,21 @@ CONFIG_CICADA_PHY=m
 # CONFIG_SMSC_PHY is not set
 # CONFIG_BROADCOM_PHY is not set
 # CONFIG_ICPLUS_PHY is not set
-# CONFIG_FIXED_PHY is not set
+CONFIG_REALTEK_PHY=m
+CONFIG_MDIO_BITBANG=m
 CONFIG_NET_ETHERNET=y
-# CONFIG_MII is not set
+CONFIG_MII=m
 # CONFIG_AX88796 is not set
+CONFIG_SMC91X=m
 # CONFIG_DM9000 is not set
+# CONFIG_IBM_NEW_EMAC_ZMII is not set
+# CONFIG_IBM_NEW_EMAC_RGMII is not set
+# CONFIG_IBM_NEW_EMAC_TAH is not set
+# CONFIG_IBM_NEW_EMAC_EMAC4 is not set
+# CONFIG_IBM_NEW_EMAC_NO_FLOW_CTRL is not set
+# CONFIG_IBM_NEW_EMAC_MAL_CLR_ICINTSTAT is not set
+# CONFIG_IBM_NEW_EMAC_MAL_COMMON_ERR is not set
+# CONFIG_B44 is not set
 CONFIG_SGISEEQ=y
 # CONFIG_NETDEV_1000 is not set
 # CONFIG_NETDEV_10000 is not set
@@ -672,12 +733,12 @@ CONFIG_WLAN_PRE80211=y
 CONFIG_STRIP=m
 CONFIG_WLAN_80211=y
 # CONFIG_LIBERTAS is not set
+# CONFIG_IWLWIFI_LEDS is not set
 CONFIG_HOSTAP=m
 # CONFIG_HOSTAP_FIRMWARE is not set
 # CONFIG_WAN is not set
 # CONFIG_PPP is not set
 # CONFIG_SLIP is not set
-# CONFIG_SHAPER is not set
 # CONFIG_NETCONSOLE is not set
 # CONFIG_NETPOLL is not set
 # CONFIG_NET_POLL_CONTROLLER is not set
@@ -699,7 +760,6 @@ CONFIG_INPUT_MOUSEDEV_PSAUX=y
 CONFIG_INPUT_MOUSEDEV_SCREEN_X=1024
 CONFIG_INPUT_MOUSEDEV_SCREEN_Y=768
 # CONFIG_INPUT_JOYDEV is not set
-# CONFIG_INPUT_TSDEV is not set
 # CONFIG_INPUT_EVDEV is not set
 # CONFIG_INPUT_EVBUG is not set
 
@@ -720,6 +780,7 @@ CONFIG_MOUSE_PS2_LOGIPS2PP=y
 # CONFIG_MOUSE_PS2_SYNAPTICS is not set
 # CONFIG_MOUSE_PS2_LIFEBOOK is not set
 CONFIG_MOUSE_PS2_TRACKPOINT=y
+# CONFIG_MOUSE_PS2_ELANTECH is not set
 # CONFIG_MOUSE_PS2_TOUCHKIT is not set
 CONFIG_MOUSE_SERIAL=m
 # CONFIG_MOUSE_VSXXXAA is not set
@@ -742,9 +803,11 @@ CONFIG_SERIO_RAW=m
 # Character devices
 #
 CONFIG_VT=y
+CONFIG_CONSOLE_TRANSLATIONS=y
 CONFIG_VT_CONSOLE=y
 CONFIG_HW_CONSOLE=y
 CONFIG_VT_HW_CONSOLE_BINDING=y
+CONFIG_DEVKMEM=y
 # CONFIG_SERIAL_NONSTANDARD is not set
 
 #
@@ -761,6 +824,17 @@ CONFIG_UNIX98_PTYS=y
 CONFIG_LEGACY_PTYS=y
 CONFIG_LEGACY_PTY_COUNT=256
 # CONFIG_IPMI_HANDLER is not set
+# CONFIG_HW_RANDOM is not set
+# CONFIG_R3964 is not set
+CONFIG_RAW_DRIVER=m
+CONFIG_MAX_RAW_DEVS=256
+# CONFIG_TCG_TPM is not set
+# CONFIG_I2C is not set
+# CONFIG_SPI is not set
+# CONFIG_W1 is not set
+# CONFIG_POWER_SUPPLY is not set
+# CONFIG_HWMON is not set
+CONFIG_THERMAL=m
 CONFIG_WATCHDOG=y
 # CONFIG_WATCHDOG_NOWAYOUT is not set
 
@@ -769,47 +843,50 @@ CONFIG_WATCHDOG=y
 #
 # CONFIG_SOFT_WATCHDOG is not set
 CONFIG_INDYDOG=m
-# CONFIG_HW_RANDOM is not set
-# CONFIG_RTC is not set
-# CONFIG_R3964 is not set
-CONFIG_RAW_DRIVER=m
-CONFIG_MAX_RAW_DEVS=256
-# CONFIG_TCG_TPM is not set
-# CONFIG_I2C is not set
+CONFIG_SSB_POSSIBLE=y
 
 #
-# SPI support
+# Sonics Silicon Backplane
 #
-# CONFIG_SPI is not set
-# CONFIG_SPI_MASTER is not set
-# CONFIG_W1 is not set
-# CONFIG_POWER_SUPPLY is not set
-# CONFIG_HWMON is not set
+# CONFIG_SSB is not set
 
 #
 # Multifunction device drivers
 #
+# CONFIG_MFD_CORE is not set
 # CONFIG_MFD_SM501 is not set
+# CONFIG_HTC_PASIC3 is not set
+# CONFIG_MFD_TMIO is not set
+# CONFIG_REGULATOR is not set
 
 #
 # Multimedia devices
 #
+
+#
+# Multimedia core support
+#
 # CONFIG_VIDEO_DEV is not set
 # CONFIG_DVB_CORE is not set
+# CONFIG_VIDEO_MEDIA is not set
+
+#
+# Multimedia drivers
+#
 # CONFIG_DAB is not set
 
 #
 # Graphics support
 #
+# CONFIG_VGASTATE is not set
+# CONFIG_VIDEO_OUTPUT_CONTROL is not set
+# CONFIG_FB is not set
 # CONFIG_BACKLIGHT_LCD_SUPPORT is not set
 
 #
 # Display device support
 #
 # CONFIG_DISPLAY_SUPPORT is not set
-# CONFIG_VGASTATE is not set
-# CONFIG_VIDEO_OUTPUT_CONTROL is not set
-# CONFIG_FB is not set
 
 #
 # Console display driver support
@@ -823,48 +900,77 @@ CONFIG_LOGO=y
 # CONFIG_LOGO_LINUX_VGA16 is not set
 # CONFIG_LOGO_LINUX_CLUT224 is not set
 CONFIG_LOGO_SGI_CLUT224=y
-
-#
-# Sound
-#
 # CONFIG_SOUND is not set
 CONFIG_HID_SUPPORT=y
 CONFIG_HID=y
 # CONFIG_HID_DEBUG is not set
+CONFIG_HIDRAW=y
+CONFIG_HID_PID=y
+
+#
+# Special HID drivers
+#
+CONFIG_HID_COMPAT=y
 CONFIG_USB_SUPPORT=y
 # CONFIG_USB_ARCH_HAS_HCD is not set
 # CONFIG_USB_ARCH_HAS_OHCI is not set
 # CONFIG_USB_ARCH_HAS_EHCI is not set
+# CONFIG_USB_OTG_WHITELIST is not set
+# CONFIG_USB_OTG_BLACKLIST_HUB is not set
 
 #
-# NOTE: USB_STORAGE enables SCSI, and 'SCSI disk support'
+# Enable Host or Gadget support to see Inventra options
 #
 
 #
-# USB Gadget Support
+# NOTE: USB_STORAGE depends on SCSI but BLK_DEV_SD may also be needed;
 #
 # CONFIG_USB_GADGET is not set
 # CONFIG_MMC is not set
+# CONFIG_MEMSTICK is not set
 # CONFIG_NEW_LEDS is not set
-# CONFIG_RTC_CLASS is not set
+# CONFIG_ACCESSIBILITY is not set
+CONFIG_RTC_LIB=y
+CONFIG_RTC_CLASS=y
+CONFIG_RTC_HCTOSYS=y
+CONFIG_RTC_HCTOSYS_DEVICE="rtc0"
+# CONFIG_RTC_DEBUG is not set
 
 #
-# DMA Engine support
+# RTC interfaces
 #
-# CONFIG_DMA_ENGINE is not set
+CONFIG_RTC_INTF_SYSFS=y
+CONFIG_RTC_INTF_PROC=y
+CONFIG_RTC_INTF_DEV=y
+CONFIG_RTC_INTF_DEV_UIE_EMUL=y
+# CONFIG_RTC_DRV_TEST is not set
 
 #
-# DMA Clients
+# SPI RTC drivers
 #
 
 #
-# DMA Devices
+# Platform RTC drivers
 #
+# CONFIG_RTC_DRV_CMOS is not set
+CONFIG_RTC_DRV_DS1286=y
+# CONFIG_RTC_DRV_DS1511 is not set
+# CONFIG_RTC_DRV_DS1553 is not set
+# CONFIG_RTC_DRV_DS1742 is not set
+# CONFIG_RTC_DRV_STK17TA8 is not set
+# CONFIG_RTC_DRV_M48T86 is not set
+# CONFIG_RTC_DRV_M48T35 is not set
+# CONFIG_RTC_DRV_M48T59 is not set
+# CONFIG_RTC_DRV_BQ4802 is not set
+# CONFIG_RTC_DRV_V3020 is not set
 
 #
-# Userspace I/O
+# on-CPU RTC drivers
 #
+# CONFIG_DMADEVICES is not set
 # CONFIG_UIO is not set
+# CONFIG_STAGING is not set
+CONFIG_STAGING_EXCLUDE_BUILD=y
 
 #
 # File systems
@@ -876,29 +982,33 @@ CONFIG_EXT3_FS=y
 CONFIG_EXT3_FS_XATTR=y
 CONFIG_EXT3_FS_POSIX_ACL=y
 CONFIG_EXT3_FS_SECURITY=y
-# CONFIG_EXT4DEV_FS is not set
+CONFIG_EXT4_FS=m
+CONFIG_EXT4DEV_COMPAT=y
+CONFIG_EXT4_FS_XATTR=y
+CONFIG_EXT4_FS_POSIX_ACL=y
+CONFIG_EXT4_FS_SECURITY=y
 CONFIG_JBD=y
-# CONFIG_JBD_DEBUG is not set
+CONFIG_JBD2=m
 CONFIG_FS_MBCACHE=y
 # CONFIG_REISERFS_FS is not set
 # CONFIG_JFS_FS is not set
 CONFIG_FS_POSIX_ACL=y
+CONFIG_FILE_LOCKING=y
 CONFIG_XFS_FS=m
 CONFIG_XFS_QUOTA=y
-CONFIG_XFS_SECURITY=y
 # CONFIG_XFS_POSIX_ACL is not set
 # CONFIG_XFS_RT is not set
-# CONFIG_GFS2_FS is not set
+# CONFIG_XFS_DEBUG is not set
 # CONFIG_OCFS2_FS is not set
-CONFIG_MINIX_FS=m
-# CONFIG_ROMFS_FS is not set
+CONFIG_DNOTIFY=y
 CONFIG_INOTIFY=y
 CONFIG_INOTIFY_USER=y
 CONFIG_QUOTA=y
+CONFIG_QUOTA_NETLINK_INTERFACE=y
+# CONFIG_PRINT_QUOTA_WARNING is not set
 # CONFIG_QFMT_V1 is not set
 CONFIG_QFMT_V2=m
 CONFIG_QUOTACTL=y
-CONFIG_DNOTIFY=y
 CONFIG_AUTOFS_FS=m
 CONFIG_AUTOFS4_FS=m
 CONFIG_FUSE_FS=m
@@ -929,11 +1039,11 @@ CONFIG_FAT_DEFAULT_IOCHARSET="iso8859-1"
 CONFIG_PROC_FS=y
 CONFIG_PROC_KCORE=y
 CONFIG_PROC_SYSCTL=y
+CONFIG_PROC_PAGE_MONITOR=y
 CONFIG_SYSFS=y
 CONFIG_TMPFS=y
 CONFIG_TMPFS_POSIX_ACL=y
 # CONFIG_HUGETLB_PAGE is not set
-CONFIG_RAMFS=y
 CONFIG_CONFIGFS_FS=m
 
 #
@@ -949,27 +1059,25 @@ CONFIG_CONFIGFS_FS=m
 CONFIG_EFS_FS=m
 # CONFIG_CRAMFS is not set
 # CONFIG_VXFS_FS is not set
+CONFIG_MINIX_FS=m
+CONFIG_OMFS_FS=m
 # CONFIG_HPFS_FS is not set
 # CONFIG_QNX4FS_FS is not set
+# CONFIG_ROMFS_FS is not set
 # CONFIG_SYSV_FS is not set
 CONFIG_UFS_FS=m
 # CONFIG_UFS_FS_WRITE is not set
 # CONFIG_UFS_DEBUG is not set
-
-#
-# Network File Systems
-#
+CONFIG_NETWORK_FILESYSTEMS=y
 CONFIG_NFS_FS=m
 CONFIG_NFS_V3=y
 CONFIG_NFS_V3_ACL=y
 # CONFIG_NFS_V4 is not set
-# CONFIG_NFS_DIRECTIO is not set
 CONFIG_NFSD=m
 CONFIG_NFSD_V2_ACL=y
 CONFIG_NFSD_V3=y
 CONFIG_NFSD_V3_ACL=y
 # CONFIG_NFSD_V4 is not set
-CONFIG_NFSD_TCP=y
 CONFIG_LOCKD=m
 CONFIG_LOCKD_V4=y
 CONFIG_EXPORTFS=m
@@ -977,7 +1085,7 @@ CONFIG_NFS_ACL_SUPPORT=m
 CONFIG_NFS_COMMON=y
 CONFIG_SUNRPC=m
 CONFIG_SUNRPC_GSS=m
-# CONFIG_SUNRPC_BIND34 is not set
+# CONFIG_SUNRPC_REGISTER_V4 is not set
 CONFIG_RPCSEC_GSS_KRB5=m
 # CONFIG_RPCSEC_GSS_SPKM3 is not set
 CONFIG_SMB_FS=m
@@ -986,12 +1094,12 @@ CONFIG_SMB_NLS_REMOTE="cp437"
 CONFIG_CIFS=m
 # CONFIG_CIFS_STATS is not set
 # CONFIG_CIFS_WEAK_PW_HASH is not set
+CONFIG_CIFS_UPCALL=y
 # CONFIG_CIFS_XATTR is not set
 # CONFIG_CIFS_DEBUG2 is not set
 # CONFIG_CIFS_EXPERIMENTAL is not set
 # CONFIG_NCP_FS is not set
 CONFIG_CODA_FS=m
-# CONFIG_CODA_FS_OLD_API is not set
 # CONFIG_AFS_FS is not set
 
 #
@@ -1015,10 +1123,6 @@ CONFIG_SGI_PARTITION=y
 # CONFIG_KARMA_PARTITION is not set
 # CONFIG_EFI_PARTITION is not set
 # CONFIG_SYSV68_PARTITION is not set
-
-#
-# Native Language Support
-#
 CONFIG_NLS=m
 CONFIG_NLS_DEFAULT="iso8859-1"
 CONFIG_NLS_CODEPAGE_437=m
@@ -1059,30 +1163,32 @@ CONFIG_NLS_ISO8859_15=m
 CONFIG_NLS_KOI8_R=m
 CONFIG_NLS_KOI8_U=m
 CONFIG_NLS_UTF8=m
-
-#
-# Distributed Lock Manager
-#
 CONFIG_DLM=m
 # CONFIG_DLM_DEBUG is not set
 
 #
-# Profiling support
-#
-# CONFIG_PROFILING is not set
-
-#
 # Kernel hacking
 #
 CONFIG_TRACE_IRQFLAGS_SUPPORT=y
 # CONFIG_PRINTK_TIME is not set
+CONFIG_ENABLE_WARN_DEPRECATED=y
 CONFIG_ENABLE_MUST_CHECK=y
+CONFIG_FRAME_WARN=1024
 # CONFIG_MAGIC_SYSRQ is not set
 # CONFIG_UNUSED_SYMBOLS is not set
 # CONFIG_DEBUG_FS is not set
 # CONFIG_HEADERS_CHECK is not set
 # CONFIG_DEBUG_KERNEL is not set
-CONFIG_CROSSCOMPILE=y
+CONFIG_DEBUG_MEMORY_INIT=y
+# CONFIG_RCU_CPU_STALL_DETECTOR is not set
+# CONFIG_SYSCTL_SYSCALL_CHECK is not set
+
+#
+# Tracers
+#
+CONFIG_DYNAMIC_PRINTK_DEBUG=y
+# CONFIG_SAMPLES is not set
+CONFIG_HAVE_ARCH_KGDB=y
 CONFIG_CMDLINE=""
 
 #
@@ -1091,46 +1197,97 @@ CONFIG_CMDLINE=""
 CONFIG_KEYS=y
 CONFIG_KEYS_DEBUG_PROC_KEYS=y
 # CONFIG_SECURITY is not set
+# CONFIG_SECURITYFS is not set
+CONFIG_SECURITY_FILE_CAPABILITIES=y
 CONFIG_CRYPTO=y
+
+#
+# Crypto core or helper
+#
+CONFIG_CRYPTO_FIPS=y
 CONFIG_CRYPTO_ALGAPI=y
-CONFIG_CRYPTO_ABLKCIPHER=m
-CONFIG_CRYPTO_BLKCIPHER=m
+CONFIG_CRYPTO_AEAD=y
+CONFIG_CRYPTO_BLKCIPHER=y
 CONFIG_CRYPTO_HASH=y
+CONFIG_CRYPTO_RNG=y
 CONFIG_CRYPTO_MANAGER=y
+CONFIG_CRYPTO_GF128MUL=m
+CONFIG_CRYPTO_NULL=m
+CONFIG_CRYPTO_CRYPTD=m
+CONFIG_CRYPTO_AUTHENC=m
+# CONFIG_CRYPTO_TEST is not set
+
+#
+# Authenticated Encryption with Associated Data
+#
+CONFIG_CRYPTO_CCM=m
+CONFIG_CRYPTO_GCM=m
+CONFIG_CRYPTO_SEQIV=m
+
+#
+# Block modes
+#
+CONFIG_CRYPTO_CBC=m
+CONFIG_CRYPTO_CTR=m
+CONFIG_CRYPTO_CTS=m
+CONFIG_CRYPTO_ECB=m
+CONFIG_CRYPTO_LRW=m
+CONFIG_CRYPTO_PCBC=m
+CONFIG_CRYPTO_XTS=m
+
+#
+# Hash modes
+#
 CONFIG_CRYPTO_HMAC=y
 CONFIG_CRYPTO_XCBC=m
-CONFIG_CRYPTO_NULL=m
+
+#
+# Digest
+#
+CONFIG_CRYPTO_CRC32C=m
 CONFIG_CRYPTO_MD4=m
 CONFIG_CRYPTO_MD5=y
+CONFIG_CRYPTO_MICHAEL_MIC=m
+CONFIG_CRYPTO_RMD128=m
+CONFIG_CRYPTO_RMD160=m
+CONFIG_CRYPTO_RMD256=m
+CONFIG_CRYPTO_RMD320=m
 CONFIG_CRYPTO_SHA1=m
 CONFIG_CRYPTO_SHA256=m
 CONFIG_CRYPTO_SHA512=m
-CONFIG_CRYPTO_WP512=m
 CONFIG_CRYPTO_TGR192=m
-CONFIG_CRYPTO_GF128MUL=m
-CONFIG_CRYPTO_ECB=m
-CONFIG_CRYPTO_CBC=m
-CONFIG_CRYPTO_PCBC=m
-CONFIG_CRYPTO_LRW=m
-CONFIG_CRYPTO_CRYPTD=m
-CONFIG_CRYPTO_DES=m
-CONFIG_CRYPTO_FCRYPT=m
-CONFIG_CRYPTO_BLOWFISH=m
-CONFIG_CRYPTO_TWOFISH=m
-CONFIG_CRYPTO_TWOFISH_COMMON=m
-CONFIG_CRYPTO_SERPENT=m
+CONFIG_CRYPTO_WP512=m
+
+#
+# Ciphers
+#
 CONFIG_CRYPTO_AES=m
+CONFIG_CRYPTO_ANUBIS=m
+CONFIG_CRYPTO_ARC4=m
+CONFIG_CRYPTO_BLOWFISH=m
+CONFIG_CRYPTO_CAMELLIA=m
 CONFIG_CRYPTO_CAST5=m
 CONFIG_CRYPTO_CAST6=m
-CONFIG_CRYPTO_TEA=m
-CONFIG_CRYPTO_ARC4=m
+CONFIG_CRYPTO_DES=m
+CONFIG_CRYPTO_FCRYPT=m
 CONFIG_CRYPTO_KHAZAD=m
-CONFIG_CRYPTO_ANUBIS=m
+CONFIG_CRYPTO_SALSA20=m
+CONFIG_CRYPTO_SEED=m
+CONFIG_CRYPTO_SERPENT=m
+CONFIG_CRYPTO_TEA=m
+CONFIG_CRYPTO_TWOFISH=m
+CONFIG_CRYPTO_TWOFISH_COMMON=m
+
+#
+# Compression
+#
 CONFIG_CRYPTO_DEFLATE=m
-CONFIG_CRYPTO_MICHAEL_MIC=m
-CONFIG_CRYPTO_CRC32C=m
-CONFIG_CRYPTO_CAMELLIA=m
-# CONFIG_CRYPTO_TEST is not set
+CONFIG_CRYPTO_LZO=m
+
+#
+# Random Number Generation
+#
+CONFIG_CRYPTO_ANSI_CPRNG=m
 # CONFIG_CRYPTO_HW is not set
 
 #
@@ -1139,12 +1296,15 @@ CONFIG_CRYPTO_CAMELLIA=m
 CONFIG_BITREVERSE=m
 # CONFIG_CRC_CCITT is not set
 CONFIG_CRC16=m
-# CONFIG_CRC_ITU_T is not set
+CONFIG_CRC_T10DIF=m
+CONFIG_CRC_ITU_T=m
 CONFIG_CRC32=m
 # CONFIG_CRC7 is not set
 CONFIG_LIBCRC32C=m
 CONFIG_ZLIB_INFLATE=m
 CONFIG_ZLIB_DEFLATE=m
+CONFIG_LZO_COMPRESS=m
+CONFIG_LZO_DECOMPRESS=m
 CONFIG_TEXTSEARCH=y
 CONFIG_TEXTSEARCH_KMP=m
 CONFIG_TEXTSEARCH_BM=m
diff --git a/arch/mips/configs/malta_defconfig b/arch/mips/configs/malta_defconfig
index 74daa0cf87e6..1ecdd3b65dc7 100644
--- a/arch/mips/configs/malta_defconfig
+++ b/arch/mips/configs/malta_defconfig
@@ -1,7 +1,7 @@
 #
 # Automatically generated make config: don't edit
-# Linux kernel version: 2.6.23-rc2
-# Tue Aug  7 12:59:29 2007
+# Linux kernel version: 2.6.28-rc6
+# Mon Dec  1 08:08:19 2008
 #
 CONFIG_MIPS=y
 
@@ -11,20 +11,25 @@ CONFIG_MIPS=y
 CONFIG_ZONE_DMA=y
 # CONFIG_MACH_ALCHEMY is not set
 # CONFIG_BASLER_EXCITE is not set
+# CONFIG_BCM47XX is not set
 # CONFIG_MIPS_COBALT is not set
 # CONFIG_MACH_DECSTATION is not set
 # CONFIG_MACH_JAZZ is not set
+# CONFIG_LASAT is not set
 # CONFIG_LEMOTE_FULONG is not set
 CONFIG_MIPS_MALTA=y
 # CONFIG_MIPS_SIM is not set
-# CONFIG_MARKEINS is not set
+# CONFIG_MACH_EMMA is not set
 # CONFIG_MACH_VR41XX is not set
+# CONFIG_NXP_STB220 is not set
+# CONFIG_NXP_STB225 is not set
 # CONFIG_PNX8550_JBS is not set
 # CONFIG_PNX8550_STB810 is not set
 # CONFIG_PMC_MSP is not set
 # CONFIG_PMC_YOSEMITE is not set
 # CONFIG_SGI_IP22 is not set
 # CONFIG_SGI_IP27 is not set
+# CONFIG_SGI_IP28 is not set
 # CONFIG_SGI_IP32 is not set
 # CONFIG_SIBYTE_CRHINE is not set
 # CONFIG_SIBYTE_CARMEL is not set
@@ -35,13 +40,14 @@ CONFIG_MIPS_MALTA=y
 # CONFIG_SIBYTE_SENTOSA is not set
 # CONFIG_SIBYTE_BIGSUR is not set
 # CONFIG_SNI_RM is not set
-# CONFIG_TOSHIBA_JMR3927 is not set
-# CONFIG_TOSHIBA_RBTX4927 is not set
-# CONFIG_TOSHIBA_RBTX4938 is not set
+# CONFIG_MACH_TX39XX is not set
+# CONFIG_MACH_TX49XX is not set
+# CONFIG_MIKROTIK_RB532 is not set
 # CONFIG_WR_PPMC is not set
 CONFIG_RWSEM_GENERIC_SPINLOCK=y
 # CONFIG_ARCH_HAS_ILOG2_U32 is not set
 # CONFIG_ARCH_HAS_ILOG2_U64 is not set
+CONFIG_ARCH_SUPPORTS_OPROFILE=y
 CONFIG_GENERIC_FIND_NEXT_BIT=y
 CONFIG_GENERIC_HWEIGHT=y
 CONFIG_GENERIC_CALIBRATE_DELAY=y
@@ -51,21 +57,26 @@ CONFIG_GENERIC_CMOS_UPDATE=y
 CONFIG_SCHED_NO_NO_OMIT_FRAME_POINTER=y
 # CONFIG_GENERIC_HARDIRQS_NO__DO_IRQ is not set
 CONFIG_ARCH_MAY_HAVE_PC_FDC=y
+CONFIG_BOOT_RAW=y
 CONFIG_CEVT_R4K=y
+CONFIG_CSRC_R4K=y
 CONFIG_DMA_NONCOHERENT=y
 CONFIG_DMA_NEED_PCI_MAP_STATE=y
 CONFIG_EARLY_PRINTK=y
 CONFIG_SYS_HAS_EARLY_PRINTK=y
-CONFIG_GENERIC_ISA_DMA=y
+# CONFIG_HOTPLUG_CPU is not set
 CONFIG_I8259=y
 CONFIG_MIPS_BONITO64=y
 CONFIG_MIPS_MSC=y
 # CONFIG_NO_IOPORT is not set
+CONFIG_GENERIC_ISA_DMA=y
 # CONFIG_CPU_BIG_ENDIAN is not set
 CONFIG_CPU_LITTLE_ENDIAN=y
 CONFIG_SYS_SUPPORTS_BIG_ENDIAN=y
 CONFIG_SYS_SUPPORTS_LITTLE_ENDIAN=y
 CONFIG_IRQ_CPU=y
+CONFIG_IRQ_GIC=y
+CONFIG_MIPS_BOARDS_GEN=y
 CONFIG_PCI_GT64XXX_PCI0=y
 CONFIG_SWAP_IO_SPACE=y
 CONFIG_BOOT_ELF32=y
@@ -74,10 +85,6 @@ CONFIG_MIPS_L1_CACHE_SHIFT=5
 #
 # CPU selection
 #
-CONFIG_TICK_ONESHOT=y
-CONFIG_NO_HZ=y
-CONFIG_HIGH_RES_TIMERS=y
-CONFIG_GENERIC_CLOCKEVENTS_BUILD=y
 # CONFIG_CPU_LOONGSON2 is not set
 # CONFIG_CPU_MIPS32_R1 is not set
 CONFIG_CPU_MIPS32_R2=y
@@ -91,6 +98,7 @@ CONFIG_CPU_MIPS32_R2=y
 # CONFIG_CPU_TX49XX is not set
 # CONFIG_CPU_R5000 is not set
 # CONFIG_CPU_R5432 is not set
+# CONFIG_CPU_R5500 is not set
 # CONFIG_CPU_R6000 is not set
 # CONFIG_CPU_NEVADA is not set
 # CONFIG_CPU_R8000 is not set
@@ -108,6 +116,7 @@ CONFIG_CPU_MIPSR2=y
 CONFIG_SYS_SUPPORTS_32BIT_KERNEL=y
 CONFIG_SYS_SUPPORTS_64BIT_KERNEL=y
 CONFIG_CPU_SUPPORTS_32BIT_KERNEL=y
+CONFIG_HARDWARE_WATCHPOINTS=y
 
 #
 # Kernel type
@@ -125,6 +134,8 @@ CONFIG_CPU_HAS_PREFETCH=y
 CONFIG_MIPS_MT_SMP=y
 # CONFIG_MIPS_MT_SMTC is not set
 CONFIG_MIPS_MT=y
+# CONFIG_SCHED_SMT is not set
+CONFIG_SYS_SUPPORTS_SCHED_SMT=y
 CONFIG_SYS_SUPPORTS_MULTITHREADING=y
 CONFIG_MIPS_MT_FPAFF=y
 # CONFIG_MIPS_VPE_LOADER is not set
@@ -132,7 +143,6 @@ CONFIG_CPU_HAS_LLSC=y
 # CONFIG_CPU_HAS_SMARTMIPS is not set
 CONFIG_CPU_MIPSR2_IRQ_VI=y
 CONFIG_CPU_MIPSR2_IRQ_EI=y
-CONFIG_CPU_MIPSR2_SRS=y
 CONFIG_CPU_HAS_SYNC=y
 CONFIG_GENERIC_HARDIRQS=y
 CONFIG_GENERIC_IRQ_PROBE=y
@@ -140,22 +150,30 @@ CONFIG_IRQ_PER_CPU=y
 CONFIG_CPU_SUPPORTS_HIGHMEM=y
 CONFIG_SYS_SUPPORTS_SMARTMIPS=y
 CONFIG_ARCH_FLATMEM_ENABLE=y
+CONFIG_ARCH_POPULATES_NODE_MAP=y
 CONFIG_SELECT_MEMORY_MODEL=y
 CONFIG_FLATMEM_MANUAL=y
 # CONFIG_DISCONTIGMEM_MANUAL is not set
 # CONFIG_SPARSEMEM_MANUAL is not set
 CONFIG_FLATMEM=y
 CONFIG_FLAT_NODE_MEM_MAP=y
-# CONFIG_SPARSEMEM_STATIC is not set
+CONFIG_PAGEFLAGS_EXTENDED=y
 CONFIG_SPLIT_PTLOCK_CPUS=4
 # CONFIG_RESOURCES_64BIT is not set
+# CONFIG_PHYS_ADDR_T_64BIT is not set
 CONFIG_ZONE_DMA_FLAG=1
 CONFIG_BOUNCE=y
 CONFIG_VIRT_TO_BUS=y
+CONFIG_UNEVICTABLE_LRU=y
 CONFIG_SMP=y
+CONFIG_SMP_UP=y
 CONFIG_SYS_SUPPORTS_SMP=y
 CONFIG_NR_CPUS_DEFAULT_2=y
 CONFIG_NR_CPUS=2
+CONFIG_TICK_ONESHOT=y
+CONFIG_NO_HZ=y
+CONFIG_HIGH_RES_TIMERS=y
+CONFIG_GENERIC_CLOCKEVENTS_BUILD=y
 # CONFIG_HZ_48 is not set
 CONFIG_HZ_100=y
 # CONFIG_HZ_128 is not set
@@ -168,7 +186,6 @@ CONFIG_HZ=100
 CONFIG_PREEMPT_NONE=y
 # CONFIG_PREEMPT_VOLUNTARY is not set
 # CONFIG_PREEMPT is not set
-CONFIG_PREEMPT_BKL=y
 # CONFIG_KEXEC is not set
 CONFIG_SECCOMP=y
 CONFIG_LOCKDEP_SUPPORT=y
@@ -189,13 +206,19 @@ CONFIG_SYSVIPC_SYSCTL=y
 # CONFIG_POSIX_MQUEUE is not set
 # CONFIG_BSD_PROCESS_ACCT is not set
 # CONFIG_TASKSTATS is not set
-# CONFIG_USER_NS is not set
 # CONFIG_AUDIT is not set
 # CONFIG_IKCONFIG is not set
 CONFIG_LOG_BUF_SHIFT=15
-# CONFIG_CPUSETS is not set
+# CONFIG_CGROUPS is not set
+# CONFIG_GROUP_SCHED is not set
 CONFIG_SYSFS_DEPRECATED=y
+CONFIG_SYSFS_DEPRECATED_V2=y
 CONFIG_RELAY=y
+CONFIG_NAMESPACES=y
+CONFIG_UTS_NS=y
+CONFIG_IPC_NS=y
+# CONFIG_USER_NS is not set
+CONFIG_PID_NS=y
 # CONFIG_BLK_DEV_INITRD is not set
 # CONFIG_CC_OPTIMIZE_FOR_SIZE is not set
 CONFIG_SYSCTL=y
@@ -207,6 +230,8 @@ CONFIG_HOTPLUG=y
 CONFIG_PRINTK=y
 CONFIG_BUG=y
 CONFIG_ELF_CORE=y
+CONFIG_PCSPKR_PLATFORM=y
+# CONFIG_COMPAT_BRK is not set
 CONFIG_BASE_FULL=y
 CONFIG_FUTEX=y
 CONFIG_ANON_INODES=y
@@ -215,14 +240,23 @@ CONFIG_SIGNALFD=y
 CONFIG_TIMERFD=y
 CONFIG_EVENTFD=y
 CONFIG_SHMEM=y
+CONFIG_AIO=y
 CONFIG_VM_EVENT_COUNTERS=y
+CONFIG_PCI_QUIRKS=y
 CONFIG_SLAB=y
 # CONFIG_SLUB is not set
 # CONFIG_SLOB is not set
+# CONFIG_PROFILING is not set
+# CONFIG_MARKERS is not set
+CONFIG_HAVE_OPROFILE=y
+CONFIG_USE_GENERIC_SMP_HELPERS=y
+# CONFIG_HAVE_GENERIC_DMA_COHERENT is not set
+CONFIG_SLABINFO=y
 CONFIG_RT_MUTEXES=y
 # CONFIG_TINY_SHMEM is not set
 CONFIG_BASE_SMALL=0
 CONFIG_MODULES=y
+# CONFIG_MODULE_FORCE_LOAD is not set
 CONFIG_MODULE_UNLOAD=y
 # CONFIG_MODULE_FORCE_UNLOAD is not set
 CONFIG_MODVERSIONS=y
@@ -234,6 +268,7 @@ CONFIG_BLOCK=y
 # CONFIG_BLK_DEV_IO_TRACE is not set
 # CONFIG_LSF is not set
 # CONFIG_BLK_DEV_BSG is not set
+# CONFIG_BLK_DEV_INTEGRITY is not set
 
 #
 # IO Schedulers
@@ -247,19 +282,19 @@ CONFIG_DEFAULT_AS=y
 # CONFIG_DEFAULT_CFQ is not set
 # CONFIG_DEFAULT_NOOP is not set
 CONFIG_DEFAULT_IOSCHED="anticipatory"
+CONFIG_CLASSIC_RCU=y
+# CONFIG_FREEZER is not set
 
 #
 # Bus options (PCI, PCMCIA, EISA, ISA, TC)
 #
 CONFIG_HW_HAS_PCI=y
 CONFIG_PCI=y
+CONFIG_PCI_DOMAINS=y
 # CONFIG_ARCH_SUPPORTS_MSI is not set
+CONFIG_PCI_LEGACY=y
 CONFIG_MMU=y
 CONFIG_I8253=y
-
-#
-# PCCARD (PCMCIA/CardBus) support
-#
 # CONFIG_PCCARD is not set
 # CONFIG_HOTPLUG_PCI is not set
 
@@ -267,6 +302,8 @@ CONFIG_I8253=y
 # Executable file formats
 #
 CONFIG_BINFMT_ELF=y
+# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
+# CONFIG_HAVE_AOUT is not set
 # CONFIG_BINFMT_MISC is not set
 CONFIG_TRAD_SIGNALS=y
 
@@ -274,12 +311,7 @@ CONFIG_TRAD_SIGNALS=y
 # Power management options
 #
 CONFIG_PM=y
-# CONFIG_PM_LEGACY is not set
 # CONFIG_PM_DEBUG is not set
-
-#
-# Networking
-#
 CONFIG_NET=y
 
 #
@@ -292,6 +324,8 @@ CONFIG_XFRM=y
 CONFIG_XFRM_USER=m
 # CONFIG_XFRM_SUB_POLICY is not set
 CONFIG_XFRM_MIGRATE=y
+# CONFIG_XFRM_STATISTICS is not set
+CONFIG_XFRM_IPCOMP=m
 CONFIG_NET_KEY=y
 CONFIG_NET_KEY_MIGRATE=y
 CONFIG_INET=y
@@ -323,42 +357,13 @@ CONFIG_INET_TUNNEL=m
 CONFIG_INET_XFRM_MODE_TRANSPORT=m
 CONFIG_INET_XFRM_MODE_TUNNEL=m
 CONFIG_INET_XFRM_MODE_BEET=y
+CONFIG_INET_LRO=m
 CONFIG_INET_DIAG=y
 CONFIG_INET_TCP_DIAG=y
 # CONFIG_TCP_CONG_ADVANCED is not set
 CONFIG_TCP_CONG_CUBIC=y
 CONFIG_DEFAULT_TCP_CONG="cubic"
 CONFIG_TCP_MD5SIG=y
-CONFIG_IP_VS=m
-# CONFIG_IP_VS_DEBUG is not set
-CONFIG_IP_VS_TAB_BITS=12
-
-#
-# IPVS transport protocol load balancing support
-#
-CONFIG_IP_VS_PROTO_TCP=y
-CONFIG_IP_VS_PROTO_UDP=y
-CONFIG_IP_VS_PROTO_ESP=y
-CONFIG_IP_VS_PROTO_AH=y
-
-#
-# IPVS scheduler
-#
-CONFIG_IP_VS_RR=m
-CONFIG_IP_VS_WRR=m
-CONFIG_IP_VS_LC=m
-CONFIG_IP_VS_WLC=m
-CONFIG_IP_VS_LBLC=m
-CONFIG_IP_VS_LBLCR=m
-CONFIG_IP_VS_DH=m
-CONFIG_IP_VS_SH=m
-CONFIG_IP_VS_SED=m
-CONFIG_IP_VS_NQ=m
-
-#
-# IPVS application helper
-#
-CONFIG_IP_VS_FTP=m
 CONFIG_IPV6=m
 CONFIG_IPV6_PRIVACY=y
 CONFIG_IPV6_ROUTER_PREF=y
@@ -375,11 +380,15 @@ CONFIG_INET6_XFRM_MODE_TUNNEL=m
 CONFIG_INET6_XFRM_MODE_BEET=m
 # CONFIG_INET6_XFRM_MODE_ROUTEOPTIMIZATION is not set
 CONFIG_IPV6_SIT=m
+CONFIG_IPV6_NDISC_NODETYPE=y
 CONFIG_IPV6_TUNNEL=m
 # CONFIG_IPV6_MULTIPLE_TABLES is not set
+CONFIG_IPV6_MROUTE=y
+CONFIG_IPV6_PIMSM_V2=y
 CONFIG_NETWORK_SECMARK=y
 CONFIG_NETFILTER=y
 # CONFIG_NETFILTER_DEBUG is not set
+CONFIG_NETFILTER_ADVANCED=y
 CONFIG_BRIDGE_NETFILTER=y
 
 #
@@ -388,12 +397,12 @@ CONFIG_BRIDGE_NETFILTER=y
 CONFIG_NETFILTER_NETLINK=m
 CONFIG_NETFILTER_NETLINK_QUEUE=m
 CONFIG_NETFILTER_NETLINK_LOG=m
-CONFIG_NF_CONNTRACK_ENABLED=m
 CONFIG_NF_CONNTRACK=m
 CONFIG_NF_CT_ACCT=y
 CONFIG_NF_CONNTRACK_MARK=y
 CONFIG_NF_CONNTRACK_SECMARK=y
 CONFIG_NF_CONNTRACK_EVENTS=y
+CONFIG_NF_CT_PROTO_DCCP=m
 CONFIG_NF_CT_PROTO_GRE=m
 CONFIG_NF_CT_PROTO_SCTP=m
 CONFIG_NF_CT_PROTO_UDPLITE=m
@@ -407,18 +416,22 @@ CONFIG_NF_CONNTRACK_SANE=m
 CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
 CONFIG_NF_CT_NETLINK=m
+CONFIG_NETFILTER_TPROXY=m
 CONFIG_NETFILTER_XTABLES=m
 CONFIG_NETFILTER_XT_TARGET_CLASSIFY=m
 CONFIG_NETFILTER_XT_TARGET_CONNMARK=m
+# CONFIG_NETFILTER_XT_TARGET_CONNSECMARK is not set
 # CONFIG_NETFILTER_XT_TARGET_DSCP is not set
 CONFIG_NETFILTER_XT_TARGET_MARK=m
-CONFIG_NETFILTER_XT_TARGET_NFQUEUE=m
 CONFIG_NETFILTER_XT_TARGET_NFLOG=m
+CONFIG_NETFILTER_XT_TARGET_NFQUEUE=m
 CONFIG_NETFILTER_XT_TARGET_NOTRACK=m
+CONFIG_NETFILTER_XT_TARGET_RATEEST=m
+CONFIG_NETFILTER_XT_TARGET_TPROXY=m
 CONFIG_NETFILTER_XT_TARGET_TRACE=m
 CONFIG_NETFILTER_XT_TARGET_SECMARK=m
-# CONFIG_NETFILTER_XT_TARGET_CONNSECMARK is not set
 CONFIG_NETFILTER_XT_TARGET_TCPMSS=m
+CONFIG_NETFILTER_XT_TARGET_TCPOPTSTRIP=m
 CONFIG_NETFILTER_XT_MATCH_COMMENT=m
 CONFIG_NETFILTER_XT_MATCH_CONNBYTES=m
 CONFIG_NETFILTER_XT_MATCH_CONNLIMIT=m
@@ -427,40 +440,76 @@ CONFIG_NETFILTER_XT_MATCH_CONNTRACK=m
 CONFIG_NETFILTER_XT_MATCH_DCCP=m
 # CONFIG_NETFILTER_XT_MATCH_DSCP is not set
 CONFIG_NETFILTER_XT_MATCH_ESP=m
+CONFIG_NETFILTER_XT_MATCH_HASHLIMIT=m
 CONFIG_NETFILTER_XT_MATCH_HELPER=m
+CONFIG_NETFILTER_XT_MATCH_IPRANGE=m
 CONFIG_NETFILTER_XT_MATCH_LENGTH=m
 CONFIG_NETFILTER_XT_MATCH_LIMIT=m
 CONFIG_NETFILTER_XT_MATCH_MAC=m
 CONFIG_NETFILTER_XT_MATCH_MARK=m
-CONFIG_NETFILTER_XT_MATCH_POLICY=m
 CONFIG_NETFILTER_XT_MATCH_MULTIPORT=m
+CONFIG_NETFILTER_XT_MATCH_OWNER=m
+CONFIG_NETFILTER_XT_MATCH_POLICY=m
 # CONFIG_NETFILTER_XT_MATCH_PHYSDEV is not set
 CONFIG_NETFILTER_XT_MATCH_PKTTYPE=m
 CONFIG_NETFILTER_XT_MATCH_QUOTA=m
+CONFIG_NETFILTER_XT_MATCH_RATEEST=m
 CONFIG_NETFILTER_XT_MATCH_REALM=m
+CONFIG_NETFILTER_XT_MATCH_RECENT=m
+# CONFIG_NETFILTER_XT_MATCH_RECENT_PROC_COMPAT is not set
 CONFIG_NETFILTER_XT_MATCH_SCTP=m
+CONFIG_NETFILTER_XT_MATCH_SOCKET=m
 CONFIG_NETFILTER_XT_MATCH_STATE=m
 CONFIG_NETFILTER_XT_MATCH_STATISTIC=m
 CONFIG_NETFILTER_XT_MATCH_STRING=m
 CONFIG_NETFILTER_XT_MATCH_TCPMSS=m
+CONFIG_NETFILTER_XT_MATCH_TIME=m
 CONFIG_NETFILTER_XT_MATCH_U32=m
-CONFIG_NETFILTER_XT_MATCH_HASHLIMIT=m
+CONFIG_IP_VS=m
+CONFIG_IP_VS_IPV6=y
+# CONFIG_IP_VS_DEBUG is not set
+CONFIG_IP_VS_TAB_BITS=12
+
+#
+# IPVS transport protocol load balancing support
+#
+CONFIG_IP_VS_PROTO_TCP=y
+CONFIG_IP_VS_PROTO_UDP=y
+CONFIG_IP_VS_PROTO_AH_ESP=y
+CONFIG_IP_VS_PROTO_ESP=y
+CONFIG_IP_VS_PROTO_AH=y
+
+#
+# IPVS scheduler
+#
+CONFIG_IP_VS_RR=m
+CONFIG_IP_VS_WRR=m
+CONFIG_IP_VS_LC=m
+CONFIG_IP_VS_WLC=m
+CONFIG_IP_VS_LBLC=m
+CONFIG_IP_VS_LBLCR=m
+CONFIG_IP_VS_DH=m
+CONFIG_IP_VS_SH=m
+CONFIG_IP_VS_SED=m
+CONFIG_IP_VS_NQ=m
+
+#
+# IPVS application helper
+#
+CONFIG_IP_VS_FTP=m
 
 #
 # IP: Netfilter Configuration
 #
+CONFIG_NF_DEFRAG_IPV4=m
 CONFIG_NF_CONNTRACK_IPV4=m
 CONFIG_NF_CONNTRACK_PROC_COMPAT=y
 CONFIG_IP_NF_QUEUE=m
 CONFIG_IP_NF_IPTABLES=m
-CONFIG_IP_NF_MATCH_IPRANGE=m
-CONFIG_IP_NF_MATCH_TOS=m
-CONFIG_IP_NF_MATCH_RECENT=m
-CONFIG_IP_NF_MATCH_ECN=m
+CONFIG_IP_NF_MATCH_ADDRTYPE=m
 CONFIG_IP_NF_MATCH_AH=m
+CONFIG_IP_NF_MATCH_ECN=m
 CONFIG_IP_NF_MATCH_TTL=m
-CONFIG_IP_NF_MATCH_OWNER=m
-CONFIG_IP_NF_MATCH_ADDRTYPE=m
 CONFIG_IP_NF_FILTER=m
 CONFIG_IP_NF_TARGET_REJECT=m
 CONFIG_IP_NF_TARGET_LOG=m
@@ -468,11 +517,13 @@ CONFIG_IP_NF_TARGET_ULOG=m
 CONFIG_NF_NAT=m
 CONFIG_NF_NAT_NEEDED=y
 CONFIG_IP_NF_TARGET_MASQUERADE=m
-CONFIG_IP_NF_TARGET_REDIRECT=m
 CONFIG_IP_NF_TARGET_NETMAP=m
-CONFIG_IP_NF_TARGET_SAME=m
+CONFIG_IP_NF_TARGET_REDIRECT=m
 CONFIG_NF_NAT_SNMP_BASIC=m
+CONFIG_NF_NAT_PROTO_DCCP=m
 CONFIG_NF_NAT_PROTO_GRE=m
+CONFIG_NF_NAT_PROTO_UDPLITE=m
+CONFIG_NF_NAT_PROTO_SCTP=m
 CONFIG_NF_NAT_FTP=m
 CONFIG_NF_NAT_IRC=m
 CONFIG_NF_NAT_TFTP=m
@@ -481,40 +532,34 @@ CONFIG_NF_NAT_PPTP=m
 CONFIG_NF_NAT_H323=m
 CONFIG_NF_NAT_SIP=m
 CONFIG_IP_NF_MANGLE=m
-CONFIG_IP_NF_TARGET_TOS=m
+CONFIG_IP_NF_TARGET_CLUSTERIP=m
 CONFIG_IP_NF_TARGET_ECN=m
 CONFIG_IP_NF_TARGET_TTL=m
-CONFIG_IP_NF_TARGET_CLUSTERIP=m
 CONFIG_IP_NF_RAW=m
 CONFIG_IP_NF_ARPTABLES=m
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
 
 #
-# IPv6: Netfilter Configuration (EXPERIMENTAL)
+# IPv6: Netfilter Configuration
 #
 CONFIG_NF_CONNTRACK_IPV6=m
 CONFIG_IP6_NF_QUEUE=m
 CONFIG_IP6_NF_IPTABLES=m
-CONFIG_IP6_NF_MATCH_RT=m
-CONFIG_IP6_NF_MATCH_OPTS=m
+CONFIG_IP6_NF_MATCH_AH=m
+CONFIG_IP6_NF_MATCH_EUI64=m
 CONFIG_IP6_NF_MATCH_FRAG=m
+CONFIG_IP6_NF_MATCH_OPTS=m
 CONFIG_IP6_NF_MATCH_HL=m
-CONFIG_IP6_NF_MATCH_OWNER=m
 CONFIG_IP6_NF_MATCH_IPV6HEADER=m
-CONFIG_IP6_NF_MATCH_AH=m
 CONFIG_IP6_NF_MATCH_MH=m
-CONFIG_IP6_NF_MATCH_EUI64=m
-CONFIG_IP6_NF_FILTER=m
+CONFIG_IP6_NF_MATCH_RT=m
 CONFIG_IP6_NF_TARGET_LOG=m
+CONFIG_IP6_NF_FILTER=m
 CONFIG_IP6_NF_TARGET_REJECT=m
 CONFIG_IP6_NF_MANGLE=m
 CONFIG_IP6_NF_TARGET_HL=m
 CONFIG_IP6_NF_RAW=m
-
-#
-# Bridge: Netfilter Configuration
-#
 CONFIG_BRIDGE_NF_EBTABLES=m
 CONFIG_BRIDGE_EBT_BROUTE=m
 CONFIG_BRIDGE_EBT_T_FILTER=m
@@ -523,6 +568,7 @@ CONFIG_BRIDGE_EBT_802_3=m
 CONFIG_BRIDGE_EBT_AMONG=m
 CONFIG_BRIDGE_EBT_ARP=m
 CONFIG_BRIDGE_EBT_IP=m
+CONFIG_BRIDGE_EBT_IP6=m
 CONFIG_BRIDGE_EBT_LIMIT=m
 CONFIG_BRIDGE_EBT_MARK=m
 CONFIG_BRIDGE_EBT_PKTTYPE=m
@@ -535,6 +581,7 @@ CONFIG_BRIDGE_EBT_REDIRECT=m
 CONFIG_BRIDGE_EBT_SNAT=m
 CONFIG_BRIDGE_EBT_LOG=m
 CONFIG_BRIDGE_EBT_ULOG=m
+CONFIG_BRIDGE_EBT_NFLOG=m
 # CONFIG_IP_DCCP is not set
 CONFIG_IP_SCTP=m
 # CONFIG_SCTP_DBG_MSG is not set
@@ -544,8 +591,12 @@ CONFIG_IP_SCTP=m
 CONFIG_SCTP_HMAC_MD5=y
 # CONFIG_TIPC is not set
 # CONFIG_ATM is not set
+CONFIG_STP=m
+CONFIG_GARP=m
 CONFIG_BRIDGE=m
+# CONFIG_NET_DSA is not set
 CONFIG_VLAN_8021Q=m
+CONFIG_VLAN_8021Q_GVRP=y
 # CONFIG_DECNET is not set
 CONFIG_LLC=m
 # CONFIG_LLC2 is not set
@@ -559,12 +610,7 @@ CONFIG_IPDDP_DECAP=y
 # CONFIG_LAPB is not set
 # CONFIG_ECONET is not set
 # CONFIG_WAN_ROUTER is not set
-
-#
-# QoS and/or fair queueing
-#
 CONFIG_NET_SCHED=y
-CONFIG_NET_SCH_FIFO=y
 
 #
 # Queueing/Scheduling
@@ -573,7 +619,7 @@ CONFIG_NET_SCH_CBQ=m
 CONFIG_NET_SCH_HTB=m
 CONFIG_NET_SCH_HFSC=m
 CONFIG_NET_SCH_PRIO=m
-CONFIG_NET_SCH_RR=m
+# CONFIG_NET_SCH_MULTIQ is not set
 CONFIG_NET_SCH_RED=m
 CONFIG_NET_SCH_SFQ=m
 CONFIG_NET_SCH_TEQL=m
@@ -597,6 +643,7 @@ CONFIG_NET_CLS_U32=m
 # CONFIG_CLS_U32_MARK is not set
 CONFIG_NET_CLS_RSVP=m
 CONFIG_NET_CLS_RSVP6=m
+CONFIG_NET_CLS_FLOW=m
 # CONFIG_NET_EMATCH is not set
 CONFIG_NET_CLS_ACT=y
 CONFIG_NET_ACT_POLICE=y
@@ -604,37 +651,51 @@ CONFIG_NET_ACT_GACT=m
 CONFIG_GACT_PROB=y
 CONFIG_NET_ACT_MIRRED=m
 CONFIG_NET_ACT_IPT=m
+CONFIG_NET_ACT_NAT=m
 CONFIG_NET_ACT_PEDIT=m
 CONFIG_NET_ACT_SIMP=m
-CONFIG_NET_CLS_POLICE=y
+CONFIG_NET_ACT_SKBEDIT=m
 CONFIG_NET_CLS_IND=y
+CONFIG_NET_SCH_FIFO=y
 
 #
 # Network testing
 #
 # CONFIG_NET_PKTGEN is not set
 # CONFIG_HAMRADIO is not set
+# CONFIG_CAN is not set
 # CONFIG_IRDA is not set
 # CONFIG_BT is not set
 # CONFIG_AF_RXRPC is not set
+CONFIG_PHONET=m
 CONFIG_FIB_RULES=y
-
-#
-# Wireless
-#
+CONFIG_WIRELESS=y
 CONFIG_CFG80211=m
+CONFIG_NL80211=y
+CONFIG_WIRELESS_OLD_REGULATORY=y
 CONFIG_WIRELESS_EXT=y
+CONFIG_WIRELESS_EXT_SYSFS=y
 CONFIG_MAC80211=m
-# CONFIG_MAC80211_DEBUG is not set
+
+#
+# Rate control algorithm selection
+#
+CONFIG_MAC80211_RC_PID=y
+CONFIG_MAC80211_RC_MINSTREL=y
+CONFIG_MAC80211_RC_DEFAULT_PID=y
+# CONFIG_MAC80211_RC_DEFAULT_MINSTREL is not set
+CONFIG_MAC80211_RC_DEFAULT="pid"
+CONFIG_MAC80211_MESH=y
+CONFIG_MAC80211_LEDS=y
+# CONFIG_MAC80211_DEBUG_MENU is not set
 CONFIG_IEEE80211=m
 # CONFIG_IEEE80211_DEBUG is not set
 CONFIG_IEEE80211_CRYPT_WEP=m
 CONFIG_IEEE80211_CRYPT_CCMP=m
 CONFIG_IEEE80211_CRYPT_TKIP=m
-CONFIG_IEEE80211_SOFTMAC=m
-# CONFIG_IEEE80211_SOFTMAC_DEBUG is not set
 CONFIG_RFKILL=m
 CONFIG_RFKILL_INPUT=m
+CONFIG_RFKILL_LEDS=y
 # CONFIG_NET_9P is not set
 
 #
@@ -644,9 +705,12 @@ CONFIG_RFKILL_INPUT=m
 #
 # Generic Driver Options
 #
+CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_STANDALONE=y
 CONFIG_PREVENT_FIRMWARE_BUILD=y
 CONFIG_FW_LOADER=y
+CONFIG_FIRMWARE_IN_KERNEL=y
+CONFIG_EXTRA_FIRMWARE=""
 # CONFIG_SYS_HYPERVISOR is not set
 CONFIG_CONNECTOR=m
 CONFIG_MTD=y
@@ -655,6 +719,7 @@ CONFIG_MTD=y
 CONFIG_MTD_PARTITIONS=y
 # CONFIG_MTD_REDBOOT_PARTS is not set
 # CONFIG_MTD_CMDLINE_PARTS is not set
+# CONFIG_MTD_AR7_PARTS is not set
 
 #
 # User Modules And Translation Layers
@@ -667,6 +732,7 @@ CONFIG_MTD_BLOCK=y
 # CONFIG_INFTL is not set
 # CONFIG_RFD_FTL is not set
 # CONFIG_SSFDC is not set
+CONFIG_MTD_OOPS=m
 
 #
 # RAM/ROM/Flash chip drivers
@@ -701,6 +767,7 @@ CONFIG_MTD_PHYSMAP=y
 CONFIG_MTD_PHYSMAP_START=0x0
 CONFIG_MTD_PHYSMAP_LEN=0x0
 CONFIG_MTD_PHYSMAP_BANKWIDTH=0
+# CONFIG_MTD_INTEL_VR_NOR is not set
 # CONFIG_MTD_PLATRAM is not set
 
 #
@@ -748,25 +815,26 @@ CONFIG_BLK_DEV_NBD=m
 CONFIG_BLK_DEV_RAM=y
 CONFIG_BLK_DEV_RAM_COUNT=16
 CONFIG_BLK_DEV_RAM_SIZE=4096
-CONFIG_BLK_DEV_RAM_BLOCKSIZE=1024
+# CONFIG_BLK_DEV_XIP is not set
 CONFIG_CDROM_PKTCDVD=m
 CONFIG_CDROM_PKTCDVD_BUFFERS=8
 # CONFIG_CDROM_PKTCDVD_WCACHE is not set
 CONFIG_ATA_OVER_ETH=m
+# CONFIG_BLK_DEV_HD is not set
 # CONFIG_MISC_DEVICES is not set
+CONFIG_HAVE_IDE=y
 CONFIG_IDE=y
-CONFIG_IDE_MAX_HWIFS=4
-CONFIG_BLK_DEV_IDE=y
 
 #
-# Please see Documentation/ide.txt for help/info on IDE drives
+# Please see Documentation/ide/ide.txt for help/info on IDE drives
 #
 # CONFIG_BLK_DEV_IDE_SATA is not set
-CONFIG_BLK_DEV_IDEDISK=y
-# CONFIG_IDEDISK_MULTI_MODE is not set
+CONFIG_IDE_GD=y
+CONFIG_IDE_GD_ATA=y
+# CONFIG_IDE_GD_ATAPI is not set
 CONFIG_BLK_DEV_IDECD=y
+CONFIG_BLK_DEV_IDECD_VERBOSE_ERRORS=y
 # CONFIG_BLK_DEV_IDETAPE is not set
-# CONFIG_BLK_DEV_IDEFLOPPY is not set
 # CONFIG_BLK_DEV_IDESCSI is not set
 # CONFIG_IDE_TASK_IOCTL is not set
 CONFIG_IDE_PROC_FS=y
@@ -775,24 +843,25 @@ CONFIG_IDE_PROC_FS=y
 # IDE chipset support/bugfixes
 #
 CONFIG_IDE_GENERIC=y
+# CONFIG_BLK_DEV_PLATFORM is not set
+CONFIG_BLK_DEV_IDEDMA_SFF=y
+
+#
+# PCI IDE chipsets support
+#
 CONFIG_BLK_DEV_IDEPCI=y
-# CONFIG_IDEPCI_SHARE_IRQ is not set
 CONFIG_IDEPCI_PCIBUS_ORDER=y
 # CONFIG_BLK_DEV_OFFBOARD is not set
 CONFIG_BLK_DEV_GENERIC=y
 # CONFIG_BLK_DEV_OPTI621 is not set
 CONFIG_BLK_DEV_IDEDMA_PCI=y
-# CONFIG_BLK_DEV_IDEDMA_FORCED is not set
-# CONFIG_IDEDMA_ONLYDISK is not set
 # CONFIG_BLK_DEV_AEC62XX is not set
 # CONFIG_BLK_DEV_ALI15X3 is not set
 # CONFIG_BLK_DEV_AMD74XX is not set
 # CONFIG_BLK_DEV_CMD64X is not set
 # CONFIG_BLK_DEV_TRIFLEX is not set
-# CONFIG_BLK_DEV_CY82C693 is not set
 # CONFIG_BLK_DEV_CS5520 is not set
 # CONFIG_BLK_DEV_CS5530 is not set
-# CONFIG_BLK_DEV_HPT34X is not set
 # CONFIG_BLK_DEV_HPT366 is not set
 # CONFIG_BLK_DEV_JMICRON is not set
 # CONFIG_BLK_DEV_SC1200 is not set
@@ -808,10 +877,7 @@ CONFIG_BLK_DEV_IT8213=m
 # CONFIG_BLK_DEV_TRM290 is not set
 # CONFIG_BLK_DEV_VIA82CXXX is not set
 CONFIG_BLK_DEV_TC86C001=m
-# CONFIG_IDE_ARM is not set
 CONFIG_BLK_DEV_IDEDMA=y
-# CONFIG_IDEDMA_IVB is not set
-# CONFIG_BLK_DEV_HD is not set
 
 #
 # SCSI device support
@@ -848,8 +914,10 @@ CONFIG_SCSI_WAIT_SCAN=m
 #
 CONFIG_SCSI_SPI_ATTRS=m
 CONFIG_SCSI_FC_ATTRS=m
+# CONFIG_SCSI_FC_TGT_ATTRS is not set
 CONFIG_SCSI_ISCSI_ATTRS=m
 # CONFIG_SCSI_SAS_LIBSAS is not set
+# CONFIG_SCSI_SRP_ATTRS is not set
 CONFIG_SCSI_LOWLEVEL=y
 CONFIG_ISCSI_TCP=m
 CONFIG_BLK_DEV_3W_XXXX_RAID=m
@@ -866,6 +934,7 @@ CONFIG_AIC7XXX_REG_PRETTY_PRINT=y
 # CONFIG_SCSI_AIC79XX is not set
 # CONFIG_SCSI_AIC94XX is not set
 # CONFIG_SCSI_DPT_I2O is not set
+# CONFIG_SCSI_ADVANSYS is not set
 # CONFIG_SCSI_ARCMSR is not set
 # CONFIG_MEGARAID_NEWGEN is not set
 # CONFIG_MEGARAID_LEGACY is not set
@@ -876,6 +945,7 @@ CONFIG_AIC7XXX_REG_PRETTY_PRINT=y
 # CONFIG_SCSI_IPS is not set
 # CONFIG_SCSI_INITIO is not set
 # CONFIG_SCSI_INIA100 is not set
+# CONFIG_SCSI_MVSAS is not set
 # CONFIG_SCSI_STEX is not set
 # CONFIG_SCSI_SYM53C8XX_2 is not set
 # CONFIG_SCSI_QLOGIC_1280 is not set
@@ -887,6 +957,7 @@ CONFIG_AIC7XXX_REG_PRETTY_PRINT=y
 # CONFIG_SCSI_NSP32 is not set
 # CONFIG_SCSI_DEBUG is not set
 # CONFIG_SCSI_SRP is not set
+# CONFIG_SCSI_DH is not set
 # CONFIG_ATA is not set
 CONFIG_MD=y
 CONFIG_BLK_DEV_MD=m
@@ -905,32 +976,28 @@ CONFIG_DM_SNAPSHOT=m
 CONFIG_DM_MIRROR=m
 CONFIG_DM_ZERO=m
 CONFIG_DM_MULTIPATH=m
-CONFIG_DM_MULTIPATH_EMC=m
-CONFIG_DM_MULTIPATH_RDAC=m
 # CONFIG_DM_DELAY is not set
+# CONFIG_DM_UEVENT is not set
+# CONFIG_FUSION is not set
 
 #
-# Fusion MPT device support
+# IEEE 1394 (FireWire) support
 #
-# CONFIG_FUSION is not set
-# CONFIG_FUSION_SPI is not set
-# CONFIG_FUSION_FC is not set
-# CONFIG_FUSION_SAS is not set
 
 #
-# IEEE 1394 (FireWire) support
+# Enable only one of the two stacks, unless you know what you are doing
 #
 # CONFIG_FIREWIRE is not set
 # CONFIG_IEEE1394 is not set
 # CONFIG_I2O is not set
 CONFIG_NETDEVICES=y
-CONFIG_NETDEVICES_MULTIQUEUE=y
 CONFIG_IFB=m
 CONFIG_DUMMY=m
 CONFIG_BONDING=m
 CONFIG_MACVLAN=m
 CONFIG_EQUALIZER=m
 CONFIG_TUN=m
+CONFIG_VETH=m
 # CONFIG_ARCNET is not set
 CONFIG_PHYLIB=m
 
@@ -946,26 +1013,34 @@ CONFIG_VITESSE_PHY=m
 CONFIG_SMSC_PHY=m
 CONFIG_BROADCOM_PHY=m
 CONFIG_ICPLUS_PHY=m
-# CONFIG_FIXED_PHY is not set
+CONFIG_REALTEK_PHY=m
+CONFIG_MDIO_BITBANG=m
 CONFIG_NET_ETHERNET=y
 CONFIG_MII=y
 CONFIG_AX88796=m
+# CONFIG_AX88796_93CX6 is not set
 # CONFIG_HAPPYMEAL is not set
 # CONFIG_SUNGEM is not set
 # CONFIG_CASSINI is not set
 # CONFIG_NET_VENDOR_3COM is not set
+# CONFIG_SMC91X is not set
 # CONFIG_DM9000 is not set
 # CONFIG_NET_TULIP is not set
 # CONFIG_HP100 is not set
+# CONFIG_IBM_NEW_EMAC_ZMII is not set
+# CONFIG_IBM_NEW_EMAC_RGMII is not set
+# CONFIG_IBM_NEW_EMAC_TAH is not set
+# CONFIG_IBM_NEW_EMAC_EMAC4 is not set
+# CONFIG_IBM_NEW_EMAC_NO_FLOW_CTRL is not set
+# CONFIG_IBM_NEW_EMAC_MAL_CLR_ICINTSTAT is not set
+# CONFIG_IBM_NEW_EMAC_MAL_COMMON_ERR is not set
 CONFIG_NET_PCI=y
 CONFIG_PCNET32=y
-# CONFIG_PCNET32_NAPI is not set
 # CONFIG_AMD8111_ETH is not set
 # CONFIG_ADAPTEC_STARFIRE is not set
 # CONFIG_B44 is not set
 # CONFIG_FORCEDETH is not set
 CONFIG_TC35815=m
-# CONFIG_DGRS is not set
 # CONFIG_EEPRO100 is not set
 # CONFIG_E100 is not set
 # CONFIG_FEALNX is not set
@@ -973,16 +1048,21 @@ CONFIG_TC35815=m
 # CONFIG_NE2K_PCI is not set
 # CONFIG_8139CP is not set
 # CONFIG_8139TOO is not set
+# CONFIG_R6040 is not set
 # CONFIG_SIS900 is not set
 # CONFIG_EPIC100 is not set
 # CONFIG_SUNDANCE is not set
 # CONFIG_TLAN is not set
 # CONFIG_VIA_RHINE is not set
 # CONFIG_SC92031 is not set
+# CONFIG_ATL2 is not set
 CONFIG_NETDEV_1000=y
 # CONFIG_ACENIC is not set
 # CONFIG_DL2K is not set
 # CONFIG_E1000 is not set
+# CONFIG_E1000E is not set
+# CONFIG_IP1000 is not set
+# CONFIG_IGB is not set
 # CONFIG_NS83820 is not set
 # CONFIG_HAMACHI is not set
 # CONFIG_YELLOWFIN is not set
@@ -995,14 +1075,24 @@ CONFIG_NETDEV_1000=y
 # CONFIG_BNX2 is not set
 # CONFIG_QLA3XXX is not set
 # CONFIG_ATL1 is not set
+# CONFIG_ATL1E is not set
+# CONFIG_JME is not set
 CONFIG_NETDEV_10000=y
 # CONFIG_CHELSIO_T1 is not set
 CONFIG_CHELSIO_T3=m
+# CONFIG_ENIC is not set
+# CONFIG_IXGBE is not set
 # CONFIG_IXGB is not set
 # CONFIG_S2IO is not set
 # CONFIG_MYRI10GE is not set
 CONFIG_NETXEN_NIC=m
+# CONFIG_NIU is not set
+# CONFIG_MLX4_EN is not set
 # CONFIG_MLX4_CORE is not set
+# CONFIG_TEHUTI is not set
+# CONFIG_BNX2X is not set
+# CONFIG_QLGE is not set
+# CONFIG_SFC is not set
 # CONFIG_TR is not set
 
 #
@@ -1022,6 +1112,7 @@ CONFIG_IPW2200_QOS=y
 # CONFIG_IPW2200_DEBUG is not set
 CONFIG_LIBERTAS=m
 # CONFIG_LIBERTAS_DEBUG is not set
+# CONFIG_LIBERTAS_THINFIRM is not set
 CONFIG_HERMES=m
 CONFIG_PLX_HERMES=m
 CONFIG_TMD_HERMES=m
@@ -1030,25 +1121,30 @@ CONFIG_PCI_HERMES=m
 CONFIG_ATMEL=m
 CONFIG_PCI_ATMEL=m
 CONFIG_PRISM54=m
+# CONFIG_RTL8180 is not set
+# CONFIG_ADM8211 is not set
+# CONFIG_MAC80211_HWSIM is not set
+# CONFIG_P54_COMMON is not set
+# CONFIG_ATH5K is not set
+# CONFIG_ATH9K is not set
+# CONFIG_IWLCORE is not set
+# CONFIG_IWLWIFI_LEDS is not set
+# CONFIG_IWLAGN is not set
+# CONFIG_IWL3945 is not set
 CONFIG_HOSTAP=m
 CONFIG_HOSTAP_FIRMWARE=y
 CONFIG_HOSTAP_FIRMWARE_NVRAM=y
 CONFIG_HOSTAP_PLX=m
 CONFIG_HOSTAP_PCI=m
-CONFIG_BCM43XX=m
-CONFIG_BCM43XX_DEBUG=y
-CONFIG_BCM43XX_DMA=y
-CONFIG_BCM43XX_PIO=y
-CONFIG_BCM43XX_DMA_AND_PIO_MODE=y
-# CONFIG_BCM43XX_DMA_MODE is not set
-# CONFIG_BCM43XX_PIO_MODE is not set
+# CONFIG_B43 is not set
+# CONFIG_B43LEGACY is not set
+# CONFIG_RT2X00 is not set
 # CONFIG_WAN is not set
 # CONFIG_FDDI is not set
 # CONFIG_HIPPI is not set
 # CONFIG_PPP is not set
 # CONFIG_SLIP is not set
 # CONFIG_NET_FC is not set
-# CONFIG_SHAPER is not set
 # CONFIG_NETCONSOLE is not set
 # CONFIG_NETPOLL is not set
 # CONFIG_NET_POLL_CONTROLLER is not set
@@ -1070,7 +1166,6 @@ CONFIG_INPUT_MOUSEDEV_PSAUX=y
 CONFIG_INPUT_MOUSEDEV_SCREEN_X=1024
 CONFIG_INPUT_MOUSEDEV_SCREEN_Y=768
 # CONFIG_INPUT_JOYDEV is not set
-# CONFIG_INPUT_TSDEV is not set
 # CONFIG_INPUT_EVDEV is not set
 # CONFIG_INPUT_EVBUG is not set
 
@@ -1099,10 +1194,13 @@ CONFIG_SERIO_SERPORT=y
 # Character devices
 #
 CONFIG_VT=y
+CONFIG_CONSOLE_TRANSLATIONS=y
 CONFIG_VT_CONSOLE=y
 CONFIG_HW_CONSOLE=y
 CONFIG_VT_HW_CONSOLE_BINDING=y
+CONFIG_DEVKMEM=y
 # CONFIG_SERIAL_NONSTANDARD is not set
+# CONFIG_NOZOMI is not set
 
 #
 # Serial drivers
@@ -1124,101 +1222,165 @@ CONFIG_UNIX98_PTYS=y
 CONFIG_LEGACY_PTYS=y
 CONFIG_LEGACY_PTY_COUNT=256
 # CONFIG_IPMI_HANDLER is not set
-# CONFIG_WATCHDOG is not set
 CONFIG_HW_RANDOM=m
-CONFIG_RTC=y
 # CONFIG_R3964 is not set
 # CONFIG_APPLICOM is not set
-# CONFIG_DRM is not set
 # CONFIG_RAW_DRIVER is not set
 # CONFIG_TCG_TPM is not set
 CONFIG_DEVPORT=y
 # CONFIG_I2C is not set
-
-#
-# SPI support
-#
 # CONFIG_SPI is not set
-# CONFIG_SPI_MASTER is not set
 # CONFIG_W1 is not set
 # CONFIG_POWER_SUPPLY is not set
 # CONFIG_HWMON is not set
+# CONFIG_THERMAL is not set
+# CONFIG_THERMAL_HWMON is not set
+# CONFIG_WATCHDOG is not set
+CONFIG_SSB_POSSIBLE=y
+
+#
+# Sonics Silicon Backplane
+#
+# CONFIG_SSB is not set
 
 #
 # Multifunction device drivers
 #
+# CONFIG_MFD_CORE is not set
 # CONFIG_MFD_SM501 is not set
+# CONFIG_HTC_PASIC3 is not set
+# CONFIG_MFD_TMIO is not set
+# CONFIG_REGULATOR is not set
 
 #
 # Multimedia devices
 #
+
+#
+# Multimedia core support
+#
 # CONFIG_VIDEO_DEV is not set
 # CONFIG_DVB_CORE is not set
+# CONFIG_VIDEO_MEDIA is not set
+
+#
+# Multimedia drivers
+#
 # CONFIG_DAB is not set
 
 #
 # Graphics support
 #
+# CONFIG_DRM is not set
+# CONFIG_VGASTATE is not set
+# CONFIG_VIDEO_OUTPUT_CONTROL is not set
+# CONFIG_FB is not set
 # CONFIG_BACKLIGHT_LCD_SUPPORT is not set
 
 #
 # Display device support
 #
 # CONFIG_DISPLAY_SUPPORT is not set
-# CONFIG_VGASTATE is not set
-# CONFIG_VIDEO_OUTPUT_CONTROL is not set
-# CONFIG_FB is not set
 
 #
 # Console display driver support
 #
 # CONFIG_VGA_CONSOLE is not set
 CONFIG_DUMMY_CONSOLE=y
-
-#
-# Sound
-#
 # CONFIG_SOUND is not set
 CONFIG_HID_SUPPORT=y
 CONFIG_HID=m
 # CONFIG_HID_DEBUG is not set
+# CONFIG_HIDRAW is not set
+# CONFIG_HID_PID is not set
+
+#
+# Special HID drivers
+#
+CONFIG_HID_COMPAT=y
 CONFIG_USB_SUPPORT=y
 CONFIG_USB_ARCH_HAS_HCD=y
 CONFIG_USB_ARCH_HAS_OHCI=y
 CONFIG_USB_ARCH_HAS_EHCI=y
 # CONFIG_USB is not set
+# CONFIG_USB_OTG_WHITELIST is not set
+# CONFIG_USB_OTG_BLACKLIST_HUB is not set
 
 #
-# NOTE: USB_STORAGE enables SCSI, and 'SCSI disk support'
+# Enable Host or Gadget support to see Inventra options
 #
 
 #
-# USB Gadget Support
+# NOTE: USB_STORAGE depends on SCSI but BLK_DEV_SD may also be needed;
 #
 # CONFIG_USB_GADGET is not set
+# CONFIG_UWB is not set
 # CONFIG_MMC is not set
-# CONFIG_NEW_LEDS is not set
+# CONFIG_MEMSTICK is not set
+CONFIG_NEW_LEDS=y
+CONFIG_LEDS_CLASS=m
+
+#
+# LED drivers
+#
+
+#
+# LED Triggers
+#
+CONFIG_LEDS_TRIGGERS=y
+CONFIG_LEDS_TRIGGER_TIMER=m
+CONFIG_LEDS_TRIGGER_IDE_DISK=y
+CONFIG_LEDS_TRIGGER_HEARTBEAT=m
+CONFIG_LEDS_TRIGGER_BACKLIGHT=m
+CONFIG_LEDS_TRIGGER_DEFAULT_ON=m
+# CONFIG_ACCESSIBILITY is not set
 # CONFIG_INFINIBAND is not set
-# CONFIG_RTC_CLASS is not set
+CONFIG_RTC_LIB=y
+CONFIG_RTC_CLASS=y
+CONFIG_RTC_HCTOSYS=y
+CONFIG_RTC_HCTOSYS_DEVICE="rtc0"
+# CONFIG_RTC_DEBUG is not set
 
 #
-# DMA Engine support
+# RTC interfaces
 #
-# CONFIG_DMA_ENGINE is not set
+CONFIG_RTC_INTF_SYSFS=y
+CONFIG_RTC_INTF_PROC=y
+CONFIG_RTC_INTF_DEV=y
+# CONFIG_RTC_INTF_DEV_UIE_EMUL is not set
+# CONFIG_RTC_DRV_TEST is not set
 
 #
-# DMA Clients
+# SPI RTC drivers
 #
 
 #
-# DMA Devices
+# Platform RTC drivers
 #
+CONFIG_RTC_DRV_CMOS=y
+# CONFIG_RTC_DRV_DS1286 is not set
+# CONFIG_RTC_DRV_DS1511 is not set
+# CONFIG_RTC_DRV_DS1553 is not set
+# CONFIG_RTC_DRV_DS1742 is not set
+# CONFIG_RTC_DRV_STK17TA8 is not set
+# CONFIG_RTC_DRV_M48T86 is not set
+# CONFIG_RTC_DRV_M48T35 is not set
+# CONFIG_RTC_DRV_M48T59 is not set
+# CONFIG_RTC_DRV_BQ4802 is not set
+# CONFIG_RTC_DRV_V3020 is not set
 
 #
-# Userspace I/O
+# on-CPU RTC drivers
 #
+# CONFIG_DMADEVICES is not set
 CONFIG_UIO=m
 CONFIG_UIO_CIF=m
+# CONFIG_UIO_PDRV is not set
+# CONFIG_UIO_PDRV_GENIRQ is not set
+# CONFIG_UIO_SMX is not set
+# CONFIG_UIO_SERCOS3 is not set
+# CONFIG_STAGING is not set
+CONFIG_STAGING_EXCLUDE_BUILD=y
 
 #
 # File systems
@@ -1230,9 +1392,8 @@ CONFIG_EXT3_FS=y
 CONFIG_EXT3_FS_XATTR=y
 # CONFIG_EXT3_FS_POSIX_ACL is not set
 # CONFIG_EXT3_FS_SECURITY is not set
-# CONFIG_EXT4DEV_FS is not set
+# CONFIG_EXT4_FS is not set
 CONFIG_JBD=y
-# CONFIG_JBD_DEBUG is not set
 CONFIG_FS_MBCACHE=y
 CONFIG_REISERFS_FS=m
 # CONFIG_REISERFS_CHECK is not set
@@ -1246,22 +1407,22 @@ CONFIG_JFS_SECURITY=y
 # CONFIG_JFS_DEBUG is not set
 # CONFIG_JFS_STATISTICS is not set
 CONFIG_FS_POSIX_ACL=y
+CONFIG_FILE_LOCKING=y
 CONFIG_XFS_FS=m
 CONFIG_XFS_QUOTA=y
-CONFIG_XFS_SECURITY=y
 CONFIG_XFS_POSIX_ACL=y
 # CONFIG_XFS_RT is not set
-# CONFIG_GFS2_FS is not set
+# CONFIG_XFS_DEBUG is not set
 # CONFIG_OCFS2_FS is not set
-CONFIG_MINIX_FS=m
-CONFIG_ROMFS_FS=m
+CONFIG_DNOTIFY=y
 CONFIG_INOTIFY=y
 CONFIG_INOTIFY_USER=y
 CONFIG_QUOTA=y
+# CONFIG_QUOTA_NETLINK_INTERFACE is not set
+CONFIG_PRINT_QUOTA_WARNING=y
 # CONFIG_QFMT_V1 is not set
 CONFIG_QFMT_V2=y
 CONFIG_QUOTACTL=y
-CONFIG_DNOTIFY=y
 CONFIG_AUTOFS_FS=y
 # CONFIG_AUTOFS4_FS is not set
 CONFIG_FUSE_FS=m
@@ -1291,11 +1452,11 @@ CONFIG_FAT_DEFAULT_IOCHARSET="iso8859-1"
 CONFIG_PROC_FS=y
 CONFIG_PROC_KCORE=y
 CONFIG_PROC_SYSCTL=y
+CONFIG_PROC_PAGE_MONITOR=y
 CONFIG_SYSFS=y
 CONFIG_TMPFS=y
 # CONFIG_TMPFS_POSIX_ACL is not set
 # CONFIG_HUGETLB_PAGE is not set
-CONFIG_RAMFS=y
 # CONFIG_CONFIGFS_FS is not set
 
 #
@@ -1312,46 +1473,48 @@ CONFIG_EFS_FS=m
 CONFIG_JFFS2_FS=m
 CONFIG_JFFS2_FS_DEBUG=0
 CONFIG_JFFS2_FS_WRITEBUFFER=y
+# CONFIG_JFFS2_FS_WBUF_VERIFY is not set
 # CONFIG_JFFS2_SUMMARY is not set
 CONFIG_JFFS2_FS_XATTR=y
 CONFIG_JFFS2_FS_POSIX_ACL=y
 CONFIG_JFFS2_FS_SECURITY=y
 CONFIG_JFFS2_COMPRESSION_OPTIONS=y
 CONFIG_JFFS2_ZLIB=y
+# CONFIG_JFFS2_LZO is not set
 CONFIG_JFFS2_RTIME=y
 CONFIG_JFFS2_RUBIN=y
 # CONFIG_JFFS2_CMODE_NONE is not set
 CONFIG_JFFS2_CMODE_PRIORITY=y
 # CONFIG_JFFS2_CMODE_SIZE is not set
+# CONFIG_JFFS2_CMODE_FAVOURLZO is not set
+# CONFIG_UBIFS_FS is not set
 CONFIG_CRAMFS=m
 CONFIG_VXFS_FS=m
+CONFIG_MINIX_FS=m
+# CONFIG_OMFS_FS is not set
 # CONFIG_HPFS_FS is not set
 # CONFIG_QNX4FS_FS is not set
+CONFIG_ROMFS_FS=m
 CONFIG_SYSV_FS=m
 CONFIG_UFS_FS=m
 # CONFIG_UFS_FS_WRITE is not set
 # CONFIG_UFS_DEBUG is not set
-
-#
-# Network File Systems
-#
+CONFIG_NETWORK_FILESYSTEMS=y
 CONFIG_NFS_FS=y
 CONFIG_NFS_V3=y
 # CONFIG_NFS_V3_ACL is not set
 # CONFIG_NFS_V4 is not set
-# CONFIG_NFS_DIRECTIO is not set
+CONFIG_ROOT_NFS=y
 CONFIG_NFSD=y
 CONFIG_NFSD_V3=y
 # CONFIG_NFSD_V3_ACL is not set
 # CONFIG_NFSD_V4 is not set
-# CONFIG_NFSD_TCP is not set
-CONFIG_ROOT_NFS=y
 CONFIG_LOCKD=y
 CONFIG_LOCKD_V4=y
 CONFIG_EXPORTFS=y
 CONFIG_NFS_COMMON=y
 CONFIG_SUNRPC=y
-# CONFIG_SUNRPC_BIND34 is not set
+# CONFIG_SUNRPC_REGISTER_V4 is not set
 # CONFIG_RPCSEC_GSS_KRB5 is not set
 # CONFIG_RPCSEC_GSS_SPKM3 is not set
 # CONFIG_SMB_FS is not set
@@ -1365,10 +1528,6 @@ CONFIG_SUNRPC=y
 #
 # CONFIG_PARTITION_ADVANCED is not set
 CONFIG_MSDOS_PARTITION=y
-
-#
-# Native Language Support
-#
 CONFIG_NLS=m
 CONFIG_NLS_DEFAULT="iso8859-1"
 CONFIG_NLS_CODEPAGE_437=m
@@ -1409,29 +1568,30 @@ CONFIG_NLS_ISO8859_15=m
 CONFIG_NLS_KOI8_R=m
 CONFIG_NLS_KOI8_U=m
 CONFIG_NLS_UTF8=m
-
-#
-# Distributed Lock Manager
-#
 # CONFIG_DLM is not set
 
 #
-# Profiling support
-#
-# CONFIG_PROFILING is not set
-
-#
 # Kernel hacking
 #
 CONFIG_TRACE_IRQFLAGS_SUPPORT=y
 # CONFIG_PRINTK_TIME is not set
+CONFIG_ENABLE_WARN_DEPRECATED=y
 CONFIG_ENABLE_MUST_CHECK=y
+CONFIG_FRAME_WARN=1024
 # CONFIG_MAGIC_SYSRQ is not set
 # CONFIG_UNUSED_SYMBOLS is not set
 # CONFIG_DEBUG_FS is not set
 # CONFIG_HEADERS_CHECK is not set
 # CONFIG_DEBUG_KERNEL is not set
-CONFIG_CROSSCOMPILE=y
+# CONFIG_DEBUG_MEMORY_INIT is not set
+# CONFIG_RCU_CPU_STALL_DETECTOR is not set
+
+#
+# Tracers
+#
+# CONFIG_DYNAMIC_PRINTK_DEBUG is not set
+# CONFIG_SAMPLES is not set
+CONFIG_HAVE_ARCH_KGDB=y
 CONFIG_CMDLINE=""
 
 #
@@ -1439,51 +1599,103 @@ CONFIG_CMDLINE=""
 #
 # CONFIG_KEYS is not set
 # CONFIG_SECURITY is not set
+# CONFIG_SECURITYFS is not set
+# CONFIG_SECURITY_FILE_CAPABILITIES is not set
 CONFIG_XOR_BLOCKS=m
 CONFIG_ASYNC_CORE=m
 CONFIG_ASYNC_MEMCPY=m
 CONFIG_ASYNC_XOR=m
 CONFIG_CRYPTO=y
+
+#
+# Crypto core or helper
+#
+# CONFIG_CRYPTO_FIPS is not set
 CONFIG_CRYPTO_ALGAPI=y
-CONFIG_CRYPTO_ABLKCIPHER=m
-CONFIG_CRYPTO_BLKCIPHER=m
+CONFIG_CRYPTO_AEAD=y
+CONFIG_CRYPTO_BLKCIPHER=y
 CONFIG_CRYPTO_HASH=y
+CONFIG_CRYPTO_RNG=y
 CONFIG_CRYPTO_MANAGER=y
+CONFIG_CRYPTO_GF128MUL=m
+CONFIG_CRYPTO_NULL=m
+CONFIG_CRYPTO_CRYPTD=m
+CONFIG_CRYPTO_AUTHENC=m
+# CONFIG_CRYPTO_TEST is not set
+
+#
+# Authenticated Encryption with Associated Data
+#
+# CONFIG_CRYPTO_CCM is not set
+# CONFIG_CRYPTO_GCM is not set
+# CONFIG_CRYPTO_SEQIV is not set
+
+#
+# Block modes
+#
+CONFIG_CRYPTO_CBC=m
+# CONFIG_CRYPTO_CTR is not set
+# CONFIG_CRYPTO_CTS is not set
+CONFIG_CRYPTO_ECB=m
+CONFIG_CRYPTO_LRW=m
+CONFIG_CRYPTO_PCBC=m
+# CONFIG_CRYPTO_XTS is not set
+
+#
+# Hash modes
+#
 CONFIG_CRYPTO_HMAC=y
 CONFIG_CRYPTO_XCBC=m
-CONFIG_CRYPTO_NULL=m
+
+#
+# Digest
+#
+CONFIG_CRYPTO_CRC32C=m
 CONFIG_CRYPTO_MD4=m
 CONFIG_CRYPTO_MD5=y
+CONFIG_CRYPTO_MICHAEL_MIC=m
+# CONFIG_CRYPTO_RMD128 is not set
+# CONFIG_CRYPTO_RMD160 is not set
+# CONFIG_CRYPTO_RMD256 is not set
+# CONFIG_CRYPTO_RMD320 is not set
 CONFIG_CRYPTO_SHA1=m
 CONFIG_CRYPTO_SHA256=m
 CONFIG_CRYPTO_SHA512=m
-CONFIG_CRYPTO_WP512=m
 CONFIG_CRYPTO_TGR192=m
-CONFIG_CRYPTO_GF128MUL=m
-CONFIG_CRYPTO_ECB=m
-CONFIG_CRYPTO_CBC=m
-CONFIG_CRYPTO_PCBC=m
-CONFIG_CRYPTO_LRW=m
-CONFIG_CRYPTO_CRYPTD=m
-CONFIG_CRYPTO_DES=m
-CONFIG_CRYPTO_FCRYPT=m
-CONFIG_CRYPTO_BLOWFISH=m
-CONFIG_CRYPTO_TWOFISH=m
-CONFIG_CRYPTO_TWOFISH_COMMON=m
-CONFIG_CRYPTO_SERPENT=m
+CONFIG_CRYPTO_WP512=m
+
+#
+# Ciphers
+#
 CONFIG_CRYPTO_AES=m
+CONFIG_CRYPTO_ANUBIS=m
+CONFIG_CRYPTO_ARC4=m
+CONFIG_CRYPTO_BLOWFISH=m
+CONFIG_CRYPTO_CAMELLIA=m
 CONFIG_CRYPTO_CAST5=m
 CONFIG_CRYPTO_CAST6=m
-CONFIG_CRYPTO_TEA=m
-CONFIG_CRYPTO_ARC4=m
+CONFIG_CRYPTO_DES=m
+CONFIG_CRYPTO_FCRYPT=m
 CONFIG_CRYPTO_KHAZAD=m
-CONFIG_CRYPTO_ANUBIS=m
+# CONFIG_CRYPTO_SALSA20 is not set
+# CONFIG_CRYPTO_SEED is not set
+CONFIG_CRYPTO_SERPENT=m
+CONFIG_CRYPTO_TEA=m
+CONFIG_CRYPTO_TWOFISH=m
+CONFIG_CRYPTO_TWOFISH_COMMON=m
+
+#
+# Compression
+#
 CONFIG_CRYPTO_DEFLATE=m
-CONFIG_CRYPTO_MICHAEL_MIC=m
-CONFIG_CRYPTO_CRC32C=m
-CONFIG_CRYPTO_CAMELLIA=m
-# CONFIG_CRYPTO_TEST is not set
+# CONFIG_CRYPTO_LZO is not set
+
+#
+# Random Number Generation
+#
+# CONFIG_CRYPTO_ANSI_CPRNG is not set
 CONFIG_CRYPTO_HW=y
+# CONFIG_CRYPTO_DEV_HIFN_795X is not set
 
 #
 # Library routines
@@ -1491,7 +1703,8 @@ CONFIG_CRYPTO_HW=y
 CONFIG_BITREVERSE=y
 # CONFIG_CRC_CCITT is not set
 CONFIG_CRC16=m
-# CONFIG_CRC_ITU_T is not set
+# CONFIG_CRC_T10DIF is not set
+CONFIG_CRC_ITU_T=m
 CONFIG_CRC32=y
 # CONFIG_CRC7 is not set
 CONFIG_LIBCRC32C=m
diff --git a/arch/mips/kernel/scall32-o32.S b/arch/mips/kernel/scall32-o32.S
index 759f68066b5d..d0916a55cd77 100644
--- a/arch/mips/kernel/scall32-o32.S
+++ b/arch/mips/kernel/scall32-o32.S
@@ -262,14 +262,11 @@ bad_alignment:
 	LEAF(sys_syscall)
 	subu	t0, a0, __NR_O32_Linux	# check syscall number
 	sltiu	v0, t0, __NR_O32_Linux_syscalls + 1
+	beqz	t0, einval		# do not recurse
 	sll	t1, t0, 3
 	beqz	v0, einval
-
 	lw	t2, sys_call_table(t1)		# syscall routine
 
-	li	v1, 4000 - __NR_O32_Linux	# index of sys_syscall
-	beq	t0, v1, einval			# do not recurse
-
 	/* Some syscalls like execve get their arguments from struct pt_regs
 	   and claim zero arguments in the syscall table. Thus we have to
 	   assume the worst case and shuffle around all potential arguments.
@@ -627,7 +624,7 @@ einval:	li	v0, -ENOSYS
 	sys	sys_pselect6		6
 	sys	sys_ppoll		5
 	sys	sys_unshare		1
-	sys	sys_splice		4
+	sys	sys_splice		6
 	sys	sys_sync_file_range	7	/* 4305 */
 	sys	sys_tee			4
 	sys	sys_vmsplice		4
diff --git a/arch/mips/kernel/scall64-n32.S b/arch/mips/kernel/scall64-n32.S
index e266b3aa6560..30f3b6317a83 100644
--- a/arch/mips/kernel/scall64-n32.S
+++ b/arch/mips/kernel/scall64-n32.S
@@ -390,7 +390,7 @@ EXPORT(sysn32_call_table)
 	PTR	sys_splice
 	PTR	sys_sync_file_range
 	PTR	sys_tee
-	PTR	sys_vmsplice			/* 6270 */
+	PTR	compat_sys_vmsplice		/* 6270 */
 	PTR	sys_move_pages
 	PTR	compat_sys_set_robust_list
 	PTR	compat_sys_get_robust_list
diff --git a/arch/mips/kernel/scall64-o32.S b/arch/mips/kernel/scall64-o32.S
index 6c7ef8313ebd..fefef4af8595 100644
--- a/arch/mips/kernel/scall64-o32.S
+++ b/arch/mips/kernel/scall64-o32.S
@@ -174,14 +174,12 @@ not_o32_scall:
 	END(handle_sys)
 
 LEAF(sys32_syscall)
-	sltu	v0, a0, __NR_O32_Linux + __NR_O32_Linux_syscalls + 1
+	subu	t0, a0, __NR_O32_Linux	# check syscall number
+	sltiu	v0, t0, __NR_O32_Linux_syscalls + 1
+	beqz	t0, einval		# do not recurse
+	dsll	t1, t0, 3
 	beqz	v0, einval
-
-	dsll	v0, a0, 3
-	ld	t2, (sys_call_table - (__NR_O32_Linux * 8))(v0)
-
-	li	v1, 4000		# indirect syscall number
-	beq	a0, v1, einval		# do not recurse
+	ld	t2, sys_call_table(t1)		# syscall routine
 
 	move	a0, a1			# shift argument registers
 	move	a1, a2
@@ -198,7 +196,7 @@ LEAF(sys32_syscall)
 	jr	t2
 	/* Unreached */
 
-einval:	li	v0, -EINVAL
+einval:	li	v0, -ENOSYS
 	jr	ra
 	END(sys32_syscall)
 
@@ -512,7 +510,7 @@ sys_call_table:
 	PTR	sys_splice
 	PTR	sys32_sync_file_range		/* 4305 */
 	PTR	sys_tee
-	PTR	sys_vmsplice
+	PTR	compat_sys_vmsplice
 	PTR	compat_sys_move_pages
 	PTR	compat_sys_set_robust_list
 	PTR	compat_sys_get_robust_list	/* 4310 */
diff --git a/arch/mips/kernel/vpe.c b/arch/mips/kernel/vpe.c
index 972b2d2b8401..c4a1ba91cd39 100644
--- a/arch/mips/kernel/vpe.c
+++ b/arch/mips/kernel/vpe.c
@@ -1134,7 +1134,7 @@ static int vpe_release(struct inode *inode, struct file *filp)
 
 	/* It's good to be able to run the SP and if it chokes have a look at
 	   the /dev/rt?. But if we reset the pointer to the shared struct we
-	   loose what has happened. So perhaps if garbage is sent to the vpe
+	   lose what has happened. So perhaps if garbage is sent to the vpe
 	   device, use it as a trigger for the reset. Hopefully a nice
 	   executable will be along shortly. */
 	if (ret < 0)
@@ -1454,7 +1454,7 @@ static int __init vpe_module_init(void)
 	device_initialize(&vpe_device);
 	vpe_device.class	= &vpe_class,
 	vpe_device.parent	= NULL,
-	strlcpy(vpe_device.bus_id, "vpe1", BUS_ID_SIZE);
+	dev_set_name(&vpe_device, "vpe1");
 	vpe_device.devt = MKDEV(major, minor);
 	err = device_add(&vpe_device);
 	if (err) {
diff --git a/arch/mips/mti-malta/Makefile b/arch/mips/mti-malta/Makefile
index cef2db8d2225..32e847808df1 100644
--- a/arch/mips/mti-malta/Makefile
+++ b/arch/mips/mti-malta/Makefile
@@ -7,9 +7,8 @@
 #
 obj-y				:= malta-amon.o malta-cmdline.o \
 				   malta-display.o malta-init.o malta-int.o \
-				   malta-memory.o malta-mtd.o \
-				   malta-platform.o malta-reset.o \
-				   malta-setup.o malta-time.o
+				   malta-memory.o malta-platform.o \
+				   malta-reset.o malta-setup.o malta-time.o
 
 obj-$(CONFIG_EARLY_PRINTK)	+= malta-console.o
 obj-$(CONFIG_PCI)		+= malta-pci.o
diff --git a/arch/mips/mti-malta/malta-mtd.c b/arch/mips/mti-malta/malta-mtd.c
deleted file mode 100644
index 8ad9bdf25dce..000000000000
--- a/arch/mips/mti-malta/malta-mtd.c
+++ /dev/null
@@ -1,63 +0,0 @@
-/*
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file "COPYING" in the main directory of this archive
- * for more details.
- *
- * Copyright (C) 2006 MIPS Technologies, Inc.
- *     written by Ralf Baechle <ralf@linux-mips.org>
- */
-
-#include <linux/init.h>
-#include <linux/platform_device.h>
-#include <linux/mtd/partitions.h>
-#include <linux/mtd/physmap.h>
-#include <mtd/mtd-abi.h>
-
-static struct mtd_partition malta_mtd_partitions[] = {
-	{
-		.name =		"YAMON",
-		.offset =	0x0,
-		.size =		0x100000,
-		.mask_flags =	MTD_WRITEABLE
-	}, {
-		.name =		"User FS",
-		.offset = 	0x100000,
-		.size =		0x2e0000
-	}, {
-		.name =		"Board Config",
-		.offset =	0x3e0000,
-		.size =		0x020000,
-		.mask_flags =	MTD_WRITEABLE
-	}
-};
-
-static struct physmap_flash_data malta_flash_data = {
-	.width		= 4,
-	.nr_parts	= ARRAY_SIZE(malta_mtd_partitions),
-	.parts		= malta_mtd_partitions
-};
-
-static struct resource malta_flash_resource = {
-	.start		= 0x1e000000,
-	.end		= 0x1e3fffff,
-	.flags		= IORESOURCE_MEM
-};
-
-static struct platform_device malta_flash = {
-	.name		= "physmap-flash",
-	.id		= 0,
-	.dev		= {
-		.platform_data	= &malta_flash_data,
-	},
-	.num_resources	= 1,
-	.resource	= &malta_flash_resource,
-};
-
-static int __init malta_mtd_init(void)
-{
-	platform_device_register(&malta_flash);
-
-	return 0;
-}
-
-module_init(malta_mtd_init)
diff --git a/arch/mips/mti-malta/malta-platform.c b/arch/mips/mti-malta/malta-platform.c
index 83b9bab3cd3f..72e32a7715be 100644
--- a/arch/mips/mti-malta/malta-platform.c
+++ b/arch/mips/mti-malta/malta-platform.c
@@ -3,10 +3,14 @@
  * License.  See the file "COPYING" in the main directory of this archive
  * for more details.
  *
- * Copyright (C) 2007 MIPS Technologies, Inc.
+ * Copyright (C) 2006, 07 MIPS Technologies, Inc.
  *   written by Ralf Baechle (ralf@linux-mips.org)
+ *     written by Ralf Baechle <ralf@linux-mips.org>
  *
- * Probe driver for the Malta's UART ports:
+ * Copyright (C) 2008 Wind River Systems, Inc.
+ *   updated by Tiejun Chen <tiejun.chen@windriver.com>
+ *
+ * 1. Probe driver for the Malta's UART ports:
  *
  *   o 2 ports in the SMC SuperIO
  *   o 1 port in the CBUS UART, a discrete 16550 which normally is only used
@@ -14,10 +18,17 @@
  *
  * We don't use 8250_platform.c on Malta as it would result in the CBUS
  * UART becoming ttyS0.
+ *
+ * 2. Register RTC-CMOS platform device on Malta.
  */
-#include <linux/module.h>
 #include <linux/init.h>
 #include <linux/serial_8250.h>
+#include <linux/mc146818rtc.h>
+#include <linux/module.h>
+#include <linux/mtd/partitions.h>
+#include <linux/mtd/physmap.h>
+#include <linux/platform_device.h>
+#include <mtd/mtd-abi.h>
 
 #define SMC_PORT(base, int)						\
 {									\
@@ -45,21 +56,93 @@ static struct plat_serial8250_port uart8250_data[] = {
 	{ },
 };
 
-static struct platform_device uart8250_device = {
+static struct platform_device malta_uart8250_device = {
 	.name			= "serial8250",
-	.id			= PLAT8250_DEV_PLATFORM2,
+	.id			= PLAT8250_DEV_PLATFORM,
 	.dev			= {
 		.platform_data	= uart8250_data,
 	},
 };
 
-static int __init uart8250_init(void)
+struct resource malta_rtc_resources[] = {
+	{
+		.start	= RTC_PORT(0),
+		.end	= RTC_PORT(7),
+		.flags	= IORESOURCE_IO,
+	}, {
+		.start	= RTC_IRQ,
+		.end	= RTC_IRQ,
+		.flags	= IORESOURCE_IRQ,
+	}
+};
+
+static struct platform_device malta_rtc_device = {
+	.name		= "rtc_cmos",
+	.id		= -1,
+	.resource	= malta_rtc_resources,
+	.num_resources	= ARRAY_SIZE(malta_rtc_resources),
+};
+
+static struct mtd_partition malta_mtd_partitions[] = {
+	{
+		.name =		"YAMON",
+		.offset =	0x0,
+		.size =		0x100000,
+		.mask_flags =	MTD_WRITEABLE
+	}, {
+		.name =		"User FS",
+		.offset = 	0x100000,
+		.size =		0x2e0000
+	}, {
+		.name =		"Board Config",
+		.offset =	0x3e0000,
+		.size =		0x020000,
+		.mask_flags =	MTD_WRITEABLE
+	}
+};
+
+static struct physmap_flash_data malta_flash_data = {
+	.width		= 4,
+	.nr_parts	= ARRAY_SIZE(malta_mtd_partitions),
+	.parts		= malta_mtd_partitions
+};
+
+static struct resource malta_flash_resource = {
+	.start		= 0x1e000000,
+	.end		= 0x1e3fffff,
+	.flags		= IORESOURCE_MEM
+};
+
+static struct platform_device malta_flash_device = {
+	.name		= "physmap-flash",
+	.id		= 0,
+	.dev		= {
+		.platform_data	= &malta_flash_data,
+	},
+	.num_resources	= 1,
+	.resource	= &malta_flash_resource,
+};
+
+static struct platform_device *malta_devices[] __initdata = {
+	&malta_uart8250_device,
+	&malta_rtc_device,
+	&malta_flash_device,
+};
+
+static int __init malta_add_devices(void)
 {
-	return platform_device_register(&uart8250_device);
-}
+	int err;
 
-module_init(uart8250_init);
+	err = platform_add_devices(malta_devices, ARRAY_SIZE(malta_devices));
+	if (err)
+		return err;
+
+	/*
+	 * Set RTC to BCD mode to support current alarm code.
+	 */
+	CMOS_WRITE(CMOS_READ(RTC_CONTROL) & ~RTC_DM_BINARY, RTC_CONTROL);
+
+	return 0;
+}
 
-MODULE_AUTHOR("Ralf Baechle <ralf@linux-mips.org>");
-MODULE_LICENSE("GPL");
-MODULE_DESCRIPTION("8250 UART probe driver for the Malta CBUS UART");
+device_initcall(malta_add_devices);
diff --git a/arch/mn10300/kernel/gdb-io-serial.c b/arch/mn10300/kernel/gdb-io-serial.c
index 9a6d4e8ebe73..11584c51acd9 100644
--- a/arch/mn10300/kernel/gdb-io-serial.c
+++ b/arch/mn10300/kernel/gdb-io-serial.c
@@ -99,6 +99,7 @@ int gdbstub_io_rx_char(unsigned char *_ch, int nonblock)
  try_again:
 	/* pull chars out of the buffer */
 	ix = gdbstub_rx_outp;
+	barrier();
 	if (ix == gdbstub_rx_inp) {
 		if (nonblock)
 			return -EAGAIN;
@@ -110,6 +111,7 @@ int gdbstub_io_rx_char(unsigned char *_ch, int nonblock)
 
 	ch = gdbstub_rx_buffer[ix++];
 	st = gdbstub_rx_buffer[ix++];
+	barrier();
 	gdbstub_rx_outp = ix & 0x00000fff;
 
 	if (st & UART_LSR_BI) {
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 525c13a4de93..e81893f9b238 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -141,7 +141,7 @@ config GENERIC_NVRAM
 	bool
 	default y if PPC32
 
-config SCHED_NO_NO_OMIT_FRAME_POINTER
+config SCHED_OMIT_FRAME_POINTER
 	bool
 	default y
 
@@ -285,6 +285,10 @@ config IOMMU_VMERGE
 config IOMMU_HELPER
 	def_bool PPC64
 
+config PPC_NEED_DMA_SYNC_OPS
+	def_bool y
+	depends on NOT_COHERENT_CACHE
+
 config HOTPLUG_CPU
 	bool "Support for enabling/disabling CPUs"
 	depends on SMP && HOTPLUG && EXPERIMENTAL && (PPC_PSERIES || PPC_PMAC)
diff --git a/arch/powerpc/Kconfig.debug b/arch/powerpc/Kconfig.debug
index 15eb27861fc7..08f7cc0a1953 100644
--- a/arch/powerpc/Kconfig.debug
+++ b/arch/powerpc/Kconfig.debug
@@ -2,6 +2,15 @@ menu "Kernel hacking"
 
 source "lib/Kconfig.debug"
 
+config PRINT_STACK_DEPTH
+	int "Stack depth to print" if DEBUG_KERNEL
+	default 64
+	help
+	  This option allows you to set the stack depth that the kernel
+	  prints in stack traces. This can be useful if your display is
+	  too small and stack traces cause important information to
+	  scroll off the screen.
+
 config DEBUG_STACKOVERFLOW
 	bool "Check for stack overflows"
 	depends on DEBUG_KERNEL
diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile
index 1f0667069940..72d17f50e54f 100644
--- a/arch/powerpc/Makefile
+++ b/arch/powerpc/Makefile
@@ -107,7 +107,6 @@ KBUILD_CFLAGS += $(call cc-option,-mno-altivec)
 # (We use all available options to help semi-broken compilers)
 KBUILD_CFLAGS += $(call cc-option,-mno-spe)
 KBUILD_CFLAGS += $(call cc-option,-mspe=no)
-KBUILD_CFLAGS += $(call cc-option,-mabi=no-spe)
 
 # Enable unit-at-a-time mode when possible. It shrinks the
 # kernel considerably.
diff --git a/arch/powerpc/boot/Makefile b/arch/powerpc/boot/Makefile
index 8fc6d72849ae..3d3daa674299 100644
--- a/arch/powerpc/boot/Makefile
+++ b/arch/powerpc/boot/Makefile
@@ -41,6 +41,7 @@ $(obj)/4xx.o: BOOTCFLAGS += -mcpu=405
 $(obj)/ebony.o: BOOTCFLAGS += -mcpu=405
 $(obj)/cuboot-taishan.o: BOOTCFLAGS += -mcpu=405
 $(obj)/cuboot-katmai.o: BOOTCFLAGS += -mcpu=405
+$(obj)/cuboot-acadia.o: BOOTCFLAGS += -mcpu=405
 $(obj)/treeboot-walnut.o: BOOTCFLAGS += -mcpu=405
 $(obj)/virtex405-head.o: BOOTAFLAGS += -mcpu=405
 
diff --git a/arch/powerpc/boot/dts/bamboo.dts b/arch/powerpc/boot/dts/bamboo.dts
index 6ce0cc2c0208..aa68911f6560 100644
--- a/arch/powerpc/boot/dts/bamboo.dts
+++ b/arch/powerpc/boot/dts/bamboo.dts
@@ -269,7 +269,8 @@
 			 * later cannot be changed. Chip supports a second
 			 * IO range but we don't use it for now
 			 */
-			ranges = <0x02000000 0x00000000 0xa0000000 0x00000000 0xa0000000 0x00000000 0x20000000
+			ranges = <0x02000000 0x00000000 0xa0000000 0x00000000 0xa0000000 0x00000000 0x40000000
+				  0x02000000 0x00000000 0x00000000 0x00000000 0xe0000000 0x00000000 0x00100000
 				  0x01000000 0x00000000 0x00000000 0x00000000 0xe8000000 0x00000000 0x00010000>;
 
 			/* Inbound 2GB range starting at 0 */
diff --git a/arch/powerpc/boot/dts/canyonlands.dts b/arch/powerpc/boot/dts/canyonlands.dts
index 79fe412c11c9..0c6d3184dada 100644
--- a/arch/powerpc/boot/dts/canyonlands.dts
+++ b/arch/powerpc/boot/dts/canyonlands.dts
@@ -343,6 +343,7 @@
 			 * later cannot be changed
 			 */
 			ranges = <0x02000000 0x00000000 0x80000000 0x0000000d 0x80000000 0x00000000 0x80000000
+				  0x02000000 0x00000000 0x00000000 0x0000000c 0x0ee00000 0x00000000 0x00100000
 				  0x01000000 0x00000000 0x00000000 0x0000000c 0x08000000 0x00000000 0x00010000>;
 
 			/* Inbound 2GB range starting at 0 */
@@ -373,6 +374,7 @@
 			 * later cannot be changed
 			 */
 			ranges = <0x02000000 0x00000000 0x80000000 0x0000000e 0x00000000 0x00000000 0x80000000
+				  0x02000000 0x00000000 0x00000000 0x0000000f 0x00000000 0x00000000 0x00100000
 				  0x01000000 0x00000000 0x00000000 0x0000000f 0x80000000 0x00000000 0x00010000>;
 
 			/* Inbound 2GB range starting at 0 */
@@ -414,6 +416,7 @@
 			 * later cannot be changed
 			 */
 			ranges = <0x02000000 0x00000000 0x80000000 0x0000000e 0x80000000 0x00000000 0x80000000
+				  0x02000000 0x00000000 0x00000000 0x0000000f 0x00100000 0x00000000 0x00100000
 				  0x01000000 0x00000000 0x00000000 0x0000000f 0x80010000 0x00000000 0x00010000>;
 
 			/* Inbound 2GB range starting at 0 */
diff --git a/arch/powerpc/boot/dts/gef_sbc610.dts b/arch/powerpc/boot/dts/gef_sbc610.dts
index e48cfa740c8a..9708b3423bbd 100644
--- a/arch/powerpc/boot/dts/gef_sbc610.dts
+++ b/arch/powerpc/boot/dts/gef_sbc610.dts
@@ -98,6 +98,12 @@
 			interrupt-parent = <&mpic>;
 
 		};
+		gef_gpio: gpio@7,14000 {
+			#gpio-cells = <2>;
+			compatible = "gef,sbc610-gpio";
+			reg = <0x7 0x14000 0x24>;
+			gpio-controller;
+		};
 	};
 
 	soc@fef00000 {
@@ -119,6 +125,11 @@
 			interrupt-parent = <&mpic>;
 			dfsrr;
 
+			rtc@51 {
+				compatible = "epson,rx8581";
+				reg = <0x00000051>;
+			};
+
 			eti@6b {
 				compatible = "dallas,ds1682";
 				reg = <0x6b>;
diff --git a/arch/powerpc/boot/dts/kuroboxHD.dts b/arch/powerpc/boot/dts/kuroboxHD.dts
index 2e5a1a1812b6..8d725d10882f 100644
--- a/arch/powerpc/boot/dts/kuroboxHD.dts
+++ b/arch/powerpc/boot/dts/kuroboxHD.dts
@@ -76,7 +76,6 @@ XXXX add flash parts, rtc, ??
 			interrupt-parent = <&mpic>;
 
 			rtc@32 {
-				device_type = "rtc";
 				compatible = "ricoh,rs5c372a";
 				reg = <0x32>;
 			};
diff --git a/arch/powerpc/boot/dts/kuroboxHG.dts b/arch/powerpc/boot/dts/kuroboxHG.dts
index e4916e69ad31..b13a11eb81b0 100644
--- a/arch/powerpc/boot/dts/kuroboxHG.dts
+++ b/arch/powerpc/boot/dts/kuroboxHG.dts
@@ -76,7 +76,6 @@ XXXX add flash parts, rtc, ??
 			interrupt-parent = <&mpic>;
 
 			rtc@32 {
-				device_type = "rtc";
 				compatible = "ricoh,rs5c372a";
 				reg = <0x32>;
 			};
diff --git a/arch/powerpc/boot/dts/lite5200.dts b/arch/powerpc/boot/dts/lite5200.dts
index 2cf9a8768f44..3f7a5dce8de0 100644
--- a/arch/powerpc/boot/dts/lite5200.dts
+++ b/arch/powerpc/boot/dts/lite5200.dts
@@ -130,7 +130,6 @@
 
 		rtc@800 {	// Real time clock
 			compatible = "fsl,mpc5200-rtc";
-			device_type = "rtc";
 			reg = <0x800 0x100>;
 			interrupts = <1 5 0 1 6 0>;
 			interrupt-parent = <&mpc5200_pic>;
diff --git a/arch/powerpc/boot/dts/lite5200b.dts b/arch/powerpc/boot/dts/lite5200b.dts
index 7bd5b9c399b8..63e3bb48e843 100644
--- a/arch/powerpc/boot/dts/lite5200b.dts
+++ b/arch/powerpc/boot/dts/lite5200b.dts
@@ -130,7 +130,6 @@
 
 		rtc@800 {	// Real time clock
 			compatible = "fsl,mpc5200b-rtc","fsl,mpc5200-rtc";
-			device_type = "rtc";
 			reg = <0x800 0x100>;
 			interrupts = <1 5 0 1 6 0>;
 			interrupt-parent = <&mpc5200_pic>;
diff --git a/arch/powerpc/boot/dts/motionpro.dts b/arch/powerpc/boot/dts/motionpro.dts
index 9e3c921be164..52ba6f98b273 100644
--- a/arch/powerpc/boot/dts/motionpro.dts
+++ b/arch/powerpc/boot/dts/motionpro.dts
@@ -248,7 +248,6 @@
 			fsl5200-clocking;
 
 			rtc@68 {
-				device_type = "rtc";
 				compatible = "dallas,ds1339";
 				reg = <0x68>;
 			};
diff --git a/arch/powerpc/boot/dts/mpc8315erdb.dts b/arch/powerpc/boot/dts/mpc8315erdb.dts
index 6b850670de1d..d3d3097b873a 100644
--- a/arch/powerpc/boot/dts/mpc8315erdb.dts
+++ b/arch/powerpc/boot/dts/mpc8315erdb.dts
@@ -117,7 +117,6 @@
 			interrupt-parent = <&ipic>;
 			dfsrr;
 			rtc@68 {
-				device_type = "rtc";
 				compatible = "dallas,ds1339";
 				reg = <0x68>;
 			};
diff --git a/arch/powerpc/boot/dts/mpc8349emitx.dts b/arch/powerpc/boot/dts/mpc8349emitx.dts
index 2c9d54a35bc3..5ba5c6633b81 100644
--- a/arch/powerpc/boot/dts/mpc8349emitx.dts
+++ b/arch/powerpc/boot/dts/mpc8349emitx.dts
@@ -85,12 +85,19 @@
 			dfsrr;
 
 			rtc@68 {
-				device_type = "rtc";
 				compatible = "dallas,ds1339";
 				reg = <0x68>;
 				interrupts = <18 0x8>;
 				interrupt-parent = <&ipic>;
 			};
+
+			mcu_pio: mcu@a {
+				#gpio-cells = <2>;
+				compatible = "fsl,mc9s08qg8-mpc8349emitx",
+					     "fsl,mcu-mpc8349emitx";
+				reg = <0x0a>;
+				gpio-controller;
+			};
 		};
 
 		spi@7000 {
@@ -139,14 +146,6 @@
 				interrupt-parent = <&ipic>;
 				interrupts = <71 8>;
 			};
-
-			mcu_pio: mcu@a {
-				#gpio-cells = <2>;
-				compatible = "fsl,mc9s08qg8-mpc8349emitx",
-					     "fsl,mcu-mpc8349emitx";
-				reg = <0x0a>;
-				gpio-controller;
-			};
 		};
 
 		usb@22000 {
diff --git a/arch/powerpc/boot/dts/mpc8349emitxgp.dts b/arch/powerpc/boot/dts/mpc8349emitxgp.dts
index fa40647ee62e..fd4bbc4cbe30 100644
--- a/arch/powerpc/boot/dts/mpc8349emitxgp.dts
+++ b/arch/powerpc/boot/dts/mpc8349emitxgp.dts
@@ -83,7 +83,6 @@
 			dfsrr;
 
 			rtc@68 {
-				device_type = "rtc";
 				compatible = "dallas,ds1339";
 				reg = <0x68>;
 				interrupts = <18 0x8>;
diff --git a/arch/powerpc/boot/dts/mpc8377_rdb.dts b/arch/powerpc/boot/dts/mpc8377_rdb.dts
index 435ef3dd022d..9fe8e4c96b18 100644
--- a/arch/powerpc/boot/dts/mpc8377_rdb.dts
+++ b/arch/powerpc/boot/dts/mpc8377_rdb.dts
@@ -117,7 +117,6 @@
 			interrupt-parent = <&ipic>;
 			dfsrr;
 			rtc@68 {
-				device_type = "rtc";
 				compatible = "dallas,ds1339";
 				reg = <0x68>;
 			};
diff --git a/arch/powerpc/boot/dts/mpc8378_rdb.dts b/arch/powerpc/boot/dts/mpc8378_rdb.dts
index b11e68f56a06..3a6d5287539c 100644
--- a/arch/powerpc/boot/dts/mpc8378_rdb.dts
+++ b/arch/powerpc/boot/dts/mpc8378_rdb.dts
@@ -117,7 +117,6 @@
 			interrupt-parent = <&ipic>;
 			dfsrr;
 			rtc@68 {
-				device_type = "rtc";
 				compatible = "dallas,ds1339";
 				reg = <0x68>;
 			};
diff --git a/arch/powerpc/boot/dts/mpc8379_rdb.dts b/arch/powerpc/boot/dts/mpc8379_rdb.dts
index 337af6ea26d3..ee64def19210 100644
--- a/arch/powerpc/boot/dts/mpc8379_rdb.dts
+++ b/arch/powerpc/boot/dts/mpc8379_rdb.dts
@@ -117,7 +117,6 @@
 			interrupt-parent = <&ipic>;
 			dfsrr;
 			rtc@68 {
-				device_type = "rtc";
 				compatible = "dallas,ds1339";
 				reg = <0x68>;
 			};
diff --git a/arch/powerpc/boot/dts/mpc8572ds.dts b/arch/powerpc/boot/dts/mpc8572ds.dts
index 5c69b2fafd32..f7dae307d74a 100644
--- a/arch/powerpc/boot/dts/mpc8572ds.dts
+++ b/arch/powerpc/boot/dts/mpc8572ds.dts
@@ -63,6 +63,119 @@
 		device_type = "memory";
 	};
 
+	localbus@ffe05000 {
+		#address-cells = <2>;
+		#size-cells = <1>;
+		compatible = "fsl,mpc8572-elbc", "fsl,elbc", "simple-bus";
+		reg = <0xffe05000 0x1000>;
+		interrupts = <19 2>;
+		interrupt-parent = <&mpic>;
+
+		ranges = <0x0 0x0 0xe8000000 0x08000000
+			  0x1 0x0 0xe0000000 0x08000000
+			  0x2 0x0 0xffa00000 0x00040000
+			  0x3 0x0 0xffdf0000 0x00008000
+			  0x4 0x0 0xffa40000 0x00040000
+			  0x5 0x0 0xffa80000 0x00040000
+			  0x6 0x0 0xffac0000 0x00040000>;
+
+		nor@0,0 {
+			#address-cells = <1>;
+			#size-cells = <1>;
+			compatible = "cfi-flash";
+			reg = <0x0 0x0 0x8000000>;
+			bank-width = <2>;
+			device-width = <1>;
+
+			ramdisk@0 {
+				reg = <0x0 0x03000000>;
+				readl-only;
+			};
+
+			diagnostic@3000000 {
+				reg = <0x03000000 0x00e00000>;
+				read-only;
+			};
+
+			dink@3e00000 {
+				reg = <0x03e00000 0x00200000>;
+				read-only;
+			};
+
+			kernel@4000000 {
+				reg = <0x04000000 0x00400000>;
+				read-only;
+			};
+
+			jffs2@4400000 {
+				reg = <0x04400000 0x03b00000>;
+			};
+
+			dtb@7f00000 {
+				reg = <0x07f00000 0x00080000>;
+				read-only;
+			};
+
+			u-boot@7f80000 {
+				reg = <0x07f80000 0x00080000>;
+				read-only;
+			};
+		};
+
+		nand@2,0 {
+			#address-cells = <1>;
+			#size-cells = <1>;
+			compatible = "fsl,mpc8572-fcm-nand",
+				     "fsl,elbc-fcm-nand";
+			reg = <0x2 0x0 0x40000>;
+
+			u-boot@0 {
+				reg = <0x0 0x02000000>;
+				read-only;
+			};
+
+			jffs2@2000000 {
+				reg = <0x02000000 0x10000000>;
+			};
+
+			ramdisk@12000000 {
+				reg = <0x12000000 0x08000000>;
+				read-only;
+			};
+
+			kernel@1a000000 {
+				reg = <0x1a000000 0x04000000>;
+			};
+
+			dtb@1e000000 {
+				reg = <0x1e000000 0x01000000>;
+				read-only;
+			};
+
+			empty@1f000000 {
+				reg = <0x1f000000 0x21000000>;
+			};
+		};
+
+		nand@4,0 {
+			compatible = "fsl,mpc8572-fcm-nand",
+				     "fsl,elbc-fcm-nand";
+			reg = <0x4 0x0 0x40000>;
+		};
+
+		nand@5,0 {
+			compatible = "fsl,mpc8572-fcm-nand",
+				     "fsl,elbc-fcm-nand";
+			reg = <0x5 0x0 0x40000>;
+		};
+
+		nand@6,0 {
+			compatible = "fsl,mpc8572-fcm-nand",
+				     "fsl,elbc-fcm-nand";
+			reg = <0x6 0x0 0x40000>;
+		};
+	};
+
 	soc8572@ffe00000 {
 		#address-cells = <1>;
 		#size-cells = <1>;
diff --git a/arch/powerpc/boot/dts/mpc8572ds_camp_core0.dts b/arch/powerpc/boot/dts/mpc8572ds_camp_core0.dts
new file mode 100644
index 000000000000..c114c4ee9931
--- /dev/null
+++ b/arch/powerpc/boot/dts/mpc8572ds_camp_core0.dts
@@ -0,0 +1,483 @@
+/*
+ * MPC8572 DS Core0 Device Tree Source in CAMP mode.
+ *
+ * In CAMP mode, each core needs to have its own dts. Only mpic and L2 cache
+ * can be shared, all the other devices must be assigned to one core only.
+ * This dts file allows core0 to have memory, l2, i2c, dma1, global-util, eth0,
+ * eth1, crypto, pci0, pci1.
+ *
+ * Copyright 2007, 2008 Freescale Semiconductor Inc.
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ */
+
+/dts-v1/;
+/ {
+	model = "fsl,MPC8572DS";
+	compatible = "fsl,MPC8572DS", "fsl,MPC8572DS-CAMP";
+	#address-cells = <1>;
+	#size-cells = <1>;
+
+	aliases {
+		ethernet0 = &enet0;
+		ethernet1 = &enet1;
+		serial0 = &serial0;
+		pci0 = &pci0;
+		pci1 = &pci1;
+	};
+
+	cpus {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		PowerPC,8572@0 {
+			device_type = "cpu";
+			reg = <0x0>;
+			d-cache-line-size = <32>;	// 32 bytes
+			i-cache-line-size = <32>;	// 32 bytes
+			d-cache-size = <0x8000>;		// L1, 32K
+			i-cache-size = <0x8000>;		// L1, 32K
+			timebase-frequency = <0>;
+			bus-frequency = <0>;
+			clock-frequency = <0>;
+			next-level-cache = <&L2>;
+		};
+
+	};
+
+	memory {
+		device_type = "memory";
+		reg = <0x0 0x0>;	// Filled by U-Boot
+	};
+
+	soc8572@ffe00000 {
+		#address-cells = <1>;
+		#size-cells = <1>;
+		device_type = "soc";
+		compatible = "simple-bus";
+		ranges = <0x0 0xffe00000 0x100000>;
+		reg = <0xffe00000 0x1000>;	// CCSRBAR & soc regs, remove once parse code for immrbase fixed
+		bus-frequency = <0>;		// Filled out by uboot.
+
+		memory-controller@2000 {
+			compatible = "fsl,mpc8572-memory-controller";
+			reg = <0x2000 0x1000>;
+			interrupt-parent = <&mpic>;
+			interrupts = <18 2>;
+		};
+
+		memory-controller@6000 {
+			compatible = "fsl,mpc8572-memory-controller";
+			reg = <0x6000 0x1000>;
+			interrupt-parent = <&mpic>;
+			interrupts = <18 2>;
+		};
+
+		L2: l2-cache-controller@20000 {
+			compatible = "fsl,mpc8572-l2-cache-controller";
+			reg = <0x20000 0x1000>;
+			cache-line-size = <32>;	// 32 bytes
+			cache-size = <0x80000>;	// L2, 512K
+			interrupt-parent = <&mpic>;
+			interrupts = <16 2>;
+		};
+
+		i2c@3000 {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			cell-index = <0>;
+			compatible = "fsl-i2c";
+			reg = <0x3000 0x100>;
+			interrupts = <43 2>;
+			interrupt-parent = <&mpic>;
+			dfsrr;
+		};
+
+		i2c@3100 {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			cell-index = <1>;
+			compatible = "fsl-i2c";
+			reg = <0x3100 0x100>;
+			interrupts = <43 2>;
+			interrupt-parent = <&mpic>;
+			dfsrr;
+		};
+
+		dma@21300 {
+			#address-cells = <1>;
+			#size-cells = <1>;
+			compatible = "fsl,mpc8572-dma", "fsl,eloplus-dma";
+			reg = <0x21300 0x4>;
+			ranges = <0x0 0x21100 0x200>;
+			cell-index = <0>;
+			dma-channel@0 {
+				compatible = "fsl,mpc8572-dma-channel",
+						"fsl,eloplus-dma-channel";
+				reg = <0x0 0x80>;
+				cell-index = <0>;
+				interrupt-parent = <&mpic>;
+				interrupts = <20 2>;
+			};
+			dma-channel@80 {
+				compatible = "fsl,mpc8572-dma-channel",
+						"fsl,eloplus-dma-channel";
+				reg = <0x80 0x80>;
+				cell-index = <1>;
+				interrupt-parent = <&mpic>;
+				interrupts = <21 2>;
+			};
+			dma-channel@100 {
+				compatible = "fsl,mpc8572-dma-channel",
+						"fsl,eloplus-dma-channel";
+				reg = <0x100 0x80>;
+				cell-index = <2>;
+				interrupt-parent = <&mpic>;
+				interrupts = <22 2>;
+			};
+			dma-channel@180 {
+				compatible = "fsl,mpc8572-dma-channel",
+						"fsl,eloplus-dma-channel";
+				reg = <0x180 0x80>;
+				cell-index = <3>;
+				interrupt-parent = <&mpic>;
+				interrupts = <23 2>;
+			};
+		};
+
+		mdio@24520 {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			compatible = "fsl,gianfar-mdio";
+			reg = <0x24520 0x20>;
+
+			phy0: ethernet-phy@0 {
+				interrupt-parent = <&mpic>;
+				interrupts = <10 1>;
+				reg = <0x0>;
+			};
+			phy1: ethernet-phy@1 {
+				interrupt-parent = <&mpic>;
+				interrupts = <10 1>;
+				reg = <0x1>;
+			};
+		};
+
+		enet0: ethernet@24000 {
+			cell-index = <0>;
+			device_type = "network";
+			model = "eTSEC";
+			compatible = "gianfar";
+			reg = <0x24000 0x1000>;
+			local-mac-address = [ 00 00 00 00 00 00 ];
+			interrupts = <29 2 30 2 34 2>;
+			interrupt-parent = <&mpic>;
+			phy-handle = <&phy0>;
+			phy-connection-type = "rgmii-id";
+		};
+
+		enet1: ethernet@25000 {
+			cell-index = <1>;
+			device_type = "network";
+			model = "eTSEC";
+			compatible = "gianfar";
+			reg = <0x25000 0x1000>;
+			local-mac-address = [ 00 00 00 00 00 00 ];
+			interrupts = <35 2 36 2 40 2>;
+			interrupt-parent = <&mpic>;
+			phy-handle = <&phy1>;
+			phy-connection-type = "rgmii-id";
+		};
+
+		serial0: serial@4500 {
+			cell-index = <0>;
+			device_type = "serial";
+			compatible = "ns16550";
+			reg = <0x4500 0x100>;
+			clock-frequency = <0>;
+		};
+
+		global-utilities@e0000 {	//global utilities block
+			compatible = "fsl,mpc8572-guts";
+			reg = <0xe0000 0x1000>;
+			fsl,has-rstcr;
+		};
+
+		crypto@30000 {
+			compatible = "fsl,sec3.0", "fsl,sec2.4", "fsl,sec2.2",
+				     "fsl,sec2.1", "fsl,sec2.0";
+			reg = <0x30000 0x10000>;
+			interrupts = <45 2 58 2>;
+			interrupt-parent = <&mpic>;
+			fsl,num-channels = <4>;
+			fsl,channel-fifo-len = <24>;
+			fsl,exec-units-mask = <0x9fe>;
+			fsl,descriptor-types-mask = <0x3ab0ebf>;
+		};
+
+		mpic: pic@40000 {
+			interrupt-controller;
+			#address-cells = <0>;
+			#interrupt-cells = <2>;
+			reg = <0x40000 0x40000>;
+			compatible = "chrp,open-pic";
+			device_type = "open-pic";
+			protected-sources = <
+			31 32 33 37 38 39       /* enet2 enet3 */
+			76 77 78 79 27 42	/* dma2 pci2 serial*/
+			0xe0 0xe1 0xe2 0xe3     /* msi */
+			0xe4 0xe5 0xe6 0xe7
+			>;
+		};
+	};
+
+	pci0: pcie@ffe08000 {
+		cell-index = <0>;
+		compatible = "fsl,mpc8548-pcie";
+		device_type = "pci";
+		#interrupt-cells = <1>;
+		#size-cells = <2>;
+		#address-cells = <3>;
+		reg = <0xffe08000 0x1000>;
+		bus-range = <0 255>;
+		ranges = <0x2000000 0x0 0x80000000 0x80000000 0x0 0x20000000
+			  0x1000000 0x0 0x0 0xffc00000 0x0 0x10000>;
+		clock-frequency = <33333333>;
+		interrupt-parent = <&mpic>;
+		interrupts = <24 2>;
+		interrupt-map-mask = <0xff00 0x0 0x0 0x7>;
+		interrupt-map = <
+			/* IDSEL 0x11 func 0 - PCI slot 1 */
+			0x8800 0x0 0x0 0x1 &mpic 0x2 0x1
+			0x8800 0x0 0x0 0x2 &mpic 0x3 0x1
+			0x8800 0x0 0x0 0x3 &mpic 0x4 0x1
+			0x8800 0x0 0x0 0x4 &mpic 0x1 0x1
+
+			/* IDSEL 0x11 func 1 - PCI slot 1 */
+			0x8900 0x0 0x0 0x1 &mpic 0x2 0x1
+			0x8900 0x0 0x0 0x2 &mpic 0x3 0x1
+			0x8900 0x0 0x0 0x3 &mpic 0x4 0x1
+			0x8900 0x0 0x0 0x4 &mpic 0x1 0x1
+
+			/* IDSEL 0x11 func 2 - PCI slot 1 */
+			0x8a00 0x0 0x0 0x1 &mpic 0x2 0x1
+			0x8a00 0x0 0x0 0x2 &mpic 0x3 0x1
+			0x8a00 0x0 0x0 0x3 &mpic 0x4 0x1
+			0x8a00 0x0 0x0 0x4 &mpic 0x1 0x1
+
+			/* IDSEL 0x11 func 3 - PCI slot 1 */
+			0x8b00 0x0 0x0 0x1 &mpic 0x2 0x1
+			0x8b00 0x0 0x0 0x2 &mpic 0x3 0x1
+			0x8b00 0x0 0x0 0x3 &mpic 0x4 0x1
+			0x8b00 0x0 0x0 0x4 &mpic 0x1 0x1
+
+			/* IDSEL 0x11 func 4 - PCI slot 1 */
+			0x8c00 0x0 0x0 0x1 &mpic 0x2 0x1
+			0x8c00 0x0 0x0 0x2 &mpic 0x3 0x1
+			0x8c00 0x0 0x0 0x3 &mpic 0x4 0x1
+			0x8c00 0x0 0x0 0x4 &mpic 0x1 0x1
+
+			/* IDSEL 0x11 func 5 - PCI slot 1 */
+			0x8d00 0x0 0x0 0x1 &mpic 0x2 0x1
+			0x8d00 0x0 0x0 0x2 &mpic 0x3 0x1
+			0x8d00 0x0 0x0 0x3 &mpic 0x4 0x1
+			0x8d00 0x0 0x0 0x4 &mpic 0x1 0x1
+
+			/* IDSEL 0x11 func 6 - PCI slot 1 */
+			0x8e00 0x0 0x0 0x1 &mpic 0x2 0x1
+			0x8e00 0x0 0x0 0x2 &mpic 0x3 0x1
+			0x8e00 0x0 0x0 0x3 &mpic 0x4 0x1
+			0x8e00 0x0 0x0 0x4 &mpic 0x1 0x1
+
+			/* IDSEL 0x11 func 7 - PCI slot 1 */
+			0x8f00 0x0 0x0 0x1 &mpic 0x2 0x1
+			0x8f00 0x0 0x0 0x2 &mpic 0x3 0x1
+			0x8f00 0x0 0x0 0x3 &mpic 0x4 0x1
+			0x8f00 0x0 0x0 0x4 &mpic 0x1 0x1
+
+			/* IDSEL 0x12 func 0 - PCI slot 2 */
+			0x9000 0x0 0x0 0x1 &mpic 0x3 0x1
+			0x9000 0x0 0x0 0x2 &mpic 0x4 0x1
+			0x9000 0x0 0x0 0x3 &mpic 0x1 0x1
+			0x9000 0x0 0x0 0x4 &mpic 0x2 0x1
+
+			/* IDSEL 0x12 func 1 - PCI slot 2 */
+			0x9100 0x0 0x0 0x1 &mpic 0x3 0x1
+			0x9100 0x0 0x0 0x2 &mpic 0x4 0x1
+			0x9100 0x0 0x0 0x3 &mpic 0x1 0x1
+			0x9100 0x0 0x0 0x4 &mpic 0x2 0x1
+
+			/* IDSEL 0x12 func 2 - PCI slot 2 */
+			0x9200 0x0 0x0 0x1 &mpic 0x3 0x1
+			0x9200 0x0 0x0 0x2 &mpic 0x4 0x1
+			0x9200 0x0 0x0 0x3 &mpic 0x1 0x1
+			0x9200 0x0 0x0 0x4 &mpic 0x2 0x1
+
+			/* IDSEL 0x12 func 3 - PCI slot 2 */
+			0x9300 0x0 0x0 0x1 &mpic 0x3 0x1
+			0x9300 0x0 0x0 0x2 &mpic 0x4 0x1
+			0x9300 0x0 0x0 0x3 &mpic 0x1 0x1
+			0x9300 0x0 0x0 0x4 &mpic 0x2 0x1
+
+			/* IDSEL 0x12 func 4 - PCI slot 2 */
+			0x9400 0x0 0x0 0x1 &mpic 0x3 0x1
+			0x9400 0x0 0x0 0x2 &mpic 0x4 0x1
+			0x9400 0x0 0x0 0x3 &mpic 0x1 0x1
+			0x9400 0x0 0x0 0x4 &mpic 0x2 0x1
+
+			/* IDSEL 0x12 func 5 - PCI slot 2 */
+			0x9500 0x0 0x0 0x1 &mpic 0x3 0x1
+			0x9500 0x0 0x0 0x2 &mpic 0x4 0x1
+			0x9500 0x0 0x0 0x3 &mpic 0x1 0x1
+			0x9500 0x0 0x0 0x4 &mpic 0x2 0x1
+
+			/* IDSEL 0x12 func 6 - PCI slot 2 */
+			0x9600 0x0 0x0 0x1 &mpic 0x3 0x1
+			0x9600 0x0 0x0 0x2 &mpic 0x4 0x1
+			0x9600 0x0 0x0 0x3 &mpic 0x1 0x1
+			0x9600 0x0 0x0 0x4 &mpic 0x2 0x1
+
+			/* IDSEL 0x12 func 7 - PCI slot 2 */
+			0x9700 0x0 0x0 0x1 &mpic 0x3 0x1
+			0x9700 0x0 0x0 0x2 &mpic 0x4 0x1
+			0x9700 0x0 0x0 0x3 &mpic 0x1 0x1
+			0x9700 0x0 0x0 0x4 &mpic 0x2 0x1
+
+			// IDSEL 0x1c  USB
+			0xe000 0x0 0x0 0x1 &i8259 0xc 0x2
+			0xe100 0x0 0x0 0x2 &i8259 0x9 0x2
+			0xe200 0x0 0x0 0x3 &i8259 0xa 0x2
+			0xe300 0x0 0x0 0x4 &i8259 0xb 0x2
+
+			// IDSEL 0x1d  Audio
+			0xe800 0x0 0x0 0x1 &i8259 0x6 0x2
+
+			// IDSEL 0x1e Legacy
+			0xf000 0x0 0x0 0x1 &i8259 0x7 0x2
+			0xf100 0x0 0x0 0x1 &i8259 0x7 0x2
+
+			// IDSEL 0x1f IDE/SATA
+			0xf800 0x0 0x0 0x1 &i8259 0xe 0x2
+			0xf900 0x0 0x0 0x1 &i8259 0x5 0x2
+
+			>;
+
+		pcie@0 {
+			reg = <0x0 0x0 0x0 0x0 0x0>;
+			#size-cells = <2>;
+			#address-cells = <3>;
+			device_type = "pci";
+			ranges = <0x2000000 0x0 0x80000000
+				  0x2000000 0x0 0x80000000
+				  0x0 0x20000000
+
+				  0x1000000 0x0 0x0
+				  0x1000000 0x0 0x0
+				  0x0 0x100000>;
+			uli1575@0 {
+				reg = <0x0 0x0 0x0 0x0 0x0>;
+				#size-cells = <2>;
+				#address-cells = <3>;
+				ranges = <0x2000000 0x0 0x80000000
+					  0x2000000 0x0 0x80000000
+					  0x0 0x20000000
+
+					  0x1000000 0x0 0x0
+					  0x1000000 0x0 0x0
+					  0x0 0x100000>;
+				isa@1e {
+					device_type = "isa";
+					#interrupt-cells = <2>;
+					#size-cells = <1>;
+					#address-cells = <2>;
+					reg = <0xf000 0x0 0x0 0x0 0x0>;
+					ranges = <0x1 0x0 0x1000000 0x0 0x0
+						  0x1000>;
+					interrupt-parent = <&i8259>;
+
+					i8259: interrupt-controller@20 {
+						reg = <0x1 0x20 0x2
+						       0x1 0xa0 0x2
+						       0x1 0x4d0 0x2>;
+						interrupt-controller;
+						device_type = "interrupt-controller";
+						#address-cells = <0>;
+						#interrupt-cells = <2>;
+						compatible = "chrp,iic";
+						interrupts = <9 2>;
+						interrupt-parent = <&mpic>;
+					};
+
+					i8042@60 {
+						#size-cells = <0>;
+						#address-cells = <1>;
+						reg = <0x1 0x60 0x1 0x1 0x64 0x1>;
+						interrupts = <1 3 12 3>;
+						interrupt-parent =
+							<&i8259>;
+
+						keyboard@0 {
+							reg = <0x0>;
+							compatible = "pnpPNP,303";
+						};
+
+						mouse@1 {
+							reg = <0x1>;
+							compatible = "pnpPNP,f03";
+						};
+					};
+
+					rtc@70 {
+						compatible = "pnpPNP,b00";
+						reg = <0x1 0x70 0x2>;
+					};
+
+					gpio@400 {
+						reg = <0x1 0x400 0x80>;
+					};
+				};
+			};
+		};
+
+	};
+
+	pci1: pcie@ffe09000 {
+		cell-index = <1>;
+		compatible = "fsl,mpc8548-pcie";
+		device_type = "pci";
+		#interrupt-cells = <1>;
+		#size-cells = <2>;
+		#address-cells = <3>;
+		reg = <0xffe09000 0x1000>;
+		bus-range = <0 255>;
+		ranges = <0x2000000 0x0 0xa0000000 0xa0000000 0x0 0x20000000
+			  0x1000000 0x0 0x0 0xffc10000 0x0 0x10000>;
+		clock-frequency = <33333333>;
+		interrupt-parent = <&mpic>;
+		interrupts = <26 2>;
+		interrupt-map-mask = <0xf800 0x0 0x0 0x7>;
+		interrupt-map = <
+			/* IDSEL 0x0 */
+			0000 0x0 0x0 0x1 &mpic 0x4 0x1
+			0000 0x0 0x0 0x2 &mpic 0x5 0x1
+			0000 0x0 0x0 0x3 &mpic 0x6 0x1
+			0000 0x0 0x0 0x4 &mpic 0x7 0x1
+			>;
+		pcie@0 {
+			reg = <0x0 0x0 0x0 0x0 0x0>;
+			#size-cells = <2>;
+			#address-cells = <3>;
+			device_type = "pci";
+			ranges = <0x2000000 0x0 0xa0000000
+				  0x2000000 0x0 0xa0000000
+				  0x0 0x20000000
+
+				  0x1000000 0x0 0x0
+				  0x1000000 0x0 0x0
+				  0x0 0x100000>;
+		};
+	};
+};
diff --git a/arch/powerpc/boot/dts/mpc8572ds_camp_core1.dts b/arch/powerpc/boot/dts/mpc8572ds_camp_core1.dts
new file mode 100644
index 000000000000..04ecda18d206
--- /dev/null
+++ b/arch/powerpc/boot/dts/mpc8572ds_camp_core1.dts
@@ -0,0 +1,234 @@
+/*
+ * MPC8572 DS Core1 Device Tree Source in CAMP mode.
+ *
+ * In CAMP mode, each core needs to have its own dts. Only mpic and L2 cache
+ * can be shared, all the other devices must be assigned to one core only.
+ * This dts allows core1 to have l2, dma2, eth2, eth3, pci2, msi.
+ *
+ * Please note to add "-b 1" for core1's dts compiling.
+ *
+ * Copyright 2007, 2008 Freescale Semiconductor Inc.
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ */
+
+/dts-v1/;
+/ {
+	model = "fsl,MPC8572DS";
+	compatible = "fsl,MPC8572DS", "fsl,MPC8572DS-CAMP";
+	#address-cells = <1>;
+	#size-cells = <1>;
+
+	aliases {
+		ethernet2 = &enet2;
+		ethernet3 = &enet3;
+		serial0 = &serial0;
+		pci2 = &pci2;
+	};
+
+	cpus {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		PowerPC,8572@1 {
+			device_type = "cpu";
+			reg = <0x1>;
+			d-cache-line-size = <32>;	// 32 bytes
+			i-cache-line-size = <32>;	// 32 bytes
+			d-cache-size = <0x8000>;		// L1, 32K
+			i-cache-size = <0x8000>;		// L1, 32K
+			timebase-frequency = <0>;
+			bus-frequency = <0>;
+			clock-frequency = <0>;
+			next-level-cache = <&L2>;
+		};
+	};
+
+	memory {
+		device_type = "memory";
+		reg = <0x0 0x0>;	// Filled by U-Boot
+	};
+
+	soc8572@ffe00000 {
+		#address-cells = <1>;
+		#size-cells = <1>;
+		device_type = "soc";
+		compatible = "simple-bus";
+		ranges = <0x0 0xffe00000 0x100000>;
+		reg = <0xffe00000 0x1000>;	// CCSRBAR & soc regs, remove once parse code for immrbase fixed
+		bus-frequency = <0>;		// Filled out by uboot.
+
+		L2: l2-cache-controller@20000 {
+			compatible = "fsl,mpc8572-l2-cache-controller";
+			reg = <0x20000 0x1000>;
+			cache-line-size = <32>; // 32 bytes
+			cache-size = <0x80000>; // L2, 512K
+			interrupt-parent = <&mpic>;
+		};
+
+		dma@c300 {
+			#address-cells = <1>;
+			#size-cells = <1>;
+			compatible = "fsl,mpc8572-dma", "fsl,eloplus-dma";
+			reg = <0xc300 0x4>;
+			ranges = <0x0 0xc100 0x200>;
+			cell-index = <0>;
+			dma-channel@0 {
+				compatible = "fsl,mpc8572-dma-channel",
+						"fsl,eloplus-dma-channel";
+				reg = <0x0 0x80>;
+				cell-index = <0>;
+				interrupt-parent = <&mpic>;
+				interrupts = <76 2>;
+			};
+			dma-channel@80 {
+				compatible = "fsl,mpc8572-dma-channel",
+						"fsl,eloplus-dma-channel";
+				reg = <0x80 0x80>;
+				cell-index = <1>;
+				interrupt-parent = <&mpic>;
+				interrupts = <77 2>;
+			};
+			dma-channel@100 {
+				compatible = "fsl,mpc8572-dma-channel",
+						"fsl,eloplus-dma-channel";
+				reg = <0x100 0x80>;
+				cell-index = <2>;
+				interrupt-parent = <&mpic>;
+				interrupts = <78 2>;
+			};
+			dma-channel@180 {
+				compatible = "fsl,mpc8572-dma-channel",
+						"fsl,eloplus-dma-channel";
+				reg = <0x180 0x80>;
+				cell-index = <3>;
+				interrupt-parent = <&mpic>;
+				interrupts = <79 2>;
+			};
+		};
+
+		mdio@24520 {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			compatible = "fsl,gianfar-mdio";
+			reg = <0x24520 0x20>;
+
+			phy2: ethernet-phy@2 {
+				interrupt-parent = <&mpic>;
+				reg = <0x2>;
+			};
+			phy3: ethernet-phy@3 {
+				interrupt-parent = <&mpic>;
+				reg = <0x3>;
+			};
+		};
+
+		enet2: ethernet@26000 {
+			cell-index = <2>;
+			device_type = "network";
+			model = "eTSEC";
+			compatible = "gianfar";
+			reg = <0x26000 0x1000>;
+			local-mac-address = [ 00 00 00 00 00 00 ];
+			interrupts = <31 2 32 2 33 2>;
+			interrupt-parent = <&mpic>;
+			phy-handle = <&phy2>;
+			phy-connection-type = "rgmii-id";
+		};
+
+		enet3: ethernet@27000 {
+			cell-index = <3>;
+			device_type = "network";
+			model = "eTSEC";
+			compatible = "gianfar";
+			reg = <0x27000 0x1000>;
+			local-mac-address = [ 00 00 00 00 00 00 ];
+			interrupts = <37 2 38 2 39 2>;
+			interrupt-parent = <&mpic>;
+			phy-handle = <&phy3>;
+			phy-connection-type = "rgmii-id";
+		};
+
+		msi@41600 {
+			compatible = "fsl,mpc8572-msi", "fsl,mpic-msi";
+			reg = <0x41600 0x80>;
+			msi-available-ranges = <0 0x100>;
+			interrupts = <
+				0xe0 0
+				0xe1 0
+				0xe2 0
+				0xe3 0
+				0xe4 0
+				0xe5 0
+				0xe6 0
+				0xe7 0>;
+			interrupt-parent = <&mpic>;
+		};
+
+		serial0: serial@4600 {
+			cell-index = <1>;
+			device_type = "serial";
+			compatible = "ns16550";
+			reg = <0x4600 0x100>;
+			clock-frequency = <0>;
+		};
+
+		mpic: pic@40000 {
+			interrupt-controller;
+			#address-cells = <0>;
+			#interrupt-cells = <2>;
+			reg = <0x40000 0x40000>;
+			compatible = "chrp,open-pic";
+			device_type = "open-pic";
+			protected-sources = <
+			18 16 10 42 45 58	/* MEM L2 mdio serial crypto */
+			29 30 34 35 36 40	/* enet0 enet1 */
+			24 26 20 21 22 23	/* pcie0 pcie1 dma1 */
+			43			/* i2c */
+			0x1 0x2 0x3 0x4         /* pci slot */
+			0x9 0xa 0xb 0xc         /* usb */
+			0x6 0x7 0xe 0x5         /* Audio elgacy SATA */
+			>;
+		};
+	};
+
+	pci2: pcie@ffe0a000 {
+		cell-index = <2>;
+		compatible = "fsl,mpc8548-pcie";
+		device_type = "pci";
+		#interrupt-cells = <1>;
+		#size-cells = <2>;
+		#address-cells = <3>;
+		reg = <0xffe0a000 0x1000>;
+		bus-range = <0 255>;
+		ranges = <0x2000000 0x0 0xc0000000 0xc0000000 0x0 0x20000000
+			  0x1000000 0x0 0x0 0xffc20000 0x0 0x10000>;
+		clock-frequency = <33333333>;
+		interrupt-parent = <&mpic>;
+		interrupts = <27 2>;
+		interrupt-map-mask = <0xf800 0x0 0x0 0x7>;
+		interrupt-map = <
+			/* IDSEL 0x0 */
+			0000 0x0 0x0 0x1 &mpic 0x0 0x1
+			0000 0x0 0x0 0x2 &mpic 0x1 0x1
+			0000 0x0 0x0 0x3 &mpic 0x2 0x1
+			0000 0x0 0x0 0x4 &mpic 0x3 0x1
+			>;
+		pcie@0 {
+			reg = <0x0 0x0 0x0 0x0 0x0>;
+			#size-cells = <2>;
+			#address-cells = <3>;
+			device_type = "pci";
+			ranges = <0x2000000 0x0 0xc0000000
+				  0x2000000 0x0 0xc0000000
+				  0x0 0x20000000
+
+				  0x1000000 0x0 0x0
+				  0x1000000 0x0 0x0
+				  0x0 0x100000>;
+		};
+	};
+};
diff --git a/arch/powerpc/boot/dts/pcm030.dts b/arch/powerpc/boot/dts/pcm030.dts
index 7c1bb952360c..be2c11ca0594 100644
--- a/arch/powerpc/boot/dts/pcm030.dts
+++ b/arch/powerpc/boot/dts/pcm030.dts
@@ -143,7 +143,6 @@
 
 		rtc@800 {	// Real time clock
 			compatible = "fsl,mpc5200b-rtc","fsl,mpc5200-rtc";
-			device_type = "rtc";
 			reg = <0x800 0x100>;
 			interrupts = <0x1 0x5 0x0 0x1 0x6 0x0>;
 			interrupt-parent = <&mpc5200_pic>;
@@ -301,7 +300,6 @@
 			interrupt-parent = <&mpc5200_pic>;
 			fsl5200-clocking;
 			rtc@51 {
-				device_type = "rtc";
 				compatible = "nxp,pcf8563";
 				reg = <0x51>;
 			};
diff --git a/arch/powerpc/boot/dts/sequoia.dts b/arch/powerpc/boot/dts/sequoia.dts
index 3b295e8df53f..43cc68bd3192 100644
--- a/arch/powerpc/boot/dts/sequoia.dts
+++ b/arch/powerpc/boot/dts/sequoia.dts
@@ -134,7 +134,7 @@
 		};
 
 		USB1: usb@e0000400 {
-			compatible = "ohci-be";
+			compatible = "ibm,usb-ohci-440epx", "ohci-be";
 			reg = <0x00000000 0xe0000400 0x00000060>;
 			interrupt-parent = <&UIC0>;
 			interrupts = <0x15 0x8>;
diff --git a/arch/powerpc/boot/dts/tqm5200.dts b/arch/powerpc/boot/dts/tqm5200.dts
index 3008bf8830c1..906302e26a62 100644
--- a/arch/powerpc/boot/dts/tqm5200.dts
+++ b/arch/powerpc/boot/dts/tqm5200.dts
@@ -181,7 +181,6 @@
 			fsl5200-clocking;
 
 			 rtc@68 {
-				device_type = "rtc";
 				compatible = "dallas,ds1307";
 				reg = <0x68>;
 			};
diff --git a/arch/powerpc/boot/libfdt-wrapper.c b/arch/powerpc/boot/libfdt-wrapper.c
index 9276327bc2bb..bb8b9b3505ee 100644
--- a/arch/powerpc/boot/libfdt-wrapper.c
+++ b/arch/powerpc/boot/libfdt-wrapper.c
@@ -185,7 +185,7 @@ void fdt_init(void *blob)
 
 	/* Make sure the dt blob is the right version and so forth */
 	fdt = blob;
-	bufsize = fdt_totalsize(fdt) + 4;
+	bufsize = fdt_totalsize(fdt) + EXPAND_GRANULARITY;
 	buf = malloc(bufsize);
 	if(!buf)
 		fatal("malloc failed. can't relocate the device tree\n\r");
diff --git a/arch/powerpc/configs/83xx/mpc834x_itx_defconfig b/arch/powerpc/configs/83xx/mpc834x_itx_defconfig
index e55ff7c47a36..07a674f5344e 100644
--- a/arch/powerpc/configs/83xx/mpc834x_itx_defconfig
+++ b/arch/powerpc/configs/83xx/mpc834x_itx_defconfig
@@ -723,7 +723,7 @@ CONFIG_CICADA_PHY=y
 # CONFIG_BROADCOM_PHY is not set
 # CONFIG_ICPLUS_PHY is not set
 # CONFIG_REALTEK_PHY is not set
-# CONFIG_FIXED_PHY is not set
+CONFIG_FIXED_PHY=y
 # CONFIG_MDIO_BITBANG is not set
 # CONFIG_NET_ETHERNET is not set
 CONFIG_NETDEV_1000=y
diff --git a/arch/powerpc/configs/86xx/gef_sbc610_defconfig b/arch/powerpc/configs/86xx/gef_sbc610_defconfig
index 07ccaf89f379..cd1ffa449327 100644
--- a/arch/powerpc/configs/86xx/gef_sbc610_defconfig
+++ b/arch/powerpc/configs/86xx/gef_sbc610_defconfig
@@ -1397,8 +1397,11 @@ CONFIG_USB_STORAGE=y
 # CONFIG_ACCESSIBILITY is not set
 # CONFIG_INFINIBAND is not set
 # CONFIG_EDAC is not set
-CONFIG_RTC_LIB=m
-CONFIG_RTC_CLASS=m
+CONFIG_RTC_LIB=y
+CONFIG_RTC_CLASS=y
+CONFIG_RTC_HCTOSYS=y
+CONFIG_RTC_HCTOSYS_DEVICE="rtc0"
+# CONFIG_RTC_DEBUG is not set
 
 #
 # RTC interfaces
@@ -1424,6 +1427,7 @@ CONFIG_RTC_INTF_DEV=y
 # CONFIG_RTC_DRV_M41T80 is not set
 # CONFIG_RTC_DRV_S35390A is not set
 # CONFIG_RTC_DRV_FM3130 is not set
+CONFIG_RTC_DRV_RX8581=y
 
 #
 # SPI RTC drivers
diff --git a/arch/powerpc/configs/mpc83xx_defconfig b/arch/powerpc/configs/mpc83xx_defconfig
index 15eb30c9b3f9..d582014b0a38 100644
--- a/arch/powerpc/configs/mpc83xx_defconfig
+++ b/arch/powerpc/configs/mpc83xx_defconfig
@@ -682,7 +682,7 @@ CONFIG_VITESSE_PHY=y
 # CONFIG_BROADCOM_PHY is not set
 CONFIG_ICPLUS_PHY=y
 # CONFIG_REALTEK_PHY is not set
-# CONFIG_FIXED_PHY is not set
+CONFIG_FIXED_PHY=y
 # CONFIG_MDIO_BITBANG is not set
 CONFIG_NET_ETHERNET=y
 CONFIG_MII=y
diff --git a/arch/powerpc/configs/ppc44x_defconfig b/arch/powerpc/configs/ppc44x_defconfig
index cfc94cfcf4cb..034a1fbdc887 100644
--- a/arch/powerpc/configs/ppc44x_defconfig
+++ b/arch/powerpc/configs/ppc44x_defconfig
@@ -267,7 +267,7 @@ CONFIG_PCI_SYSCALL=y
 # CONFIG_PCIEPORTBUS is not set
 CONFIG_ARCH_SUPPORTS_MSI=y
 # CONFIG_PCI_MSI is not set
-CONFIG_PCI_LEGACY=y
+# CONFIG_PCI_LEGACY is not set
 # CONFIG_PCI_DEBUG is not set
 # CONFIG_PCCARD is not set
 # CONFIG_HOTPLUG_PCI is not set
@@ -354,7 +354,7 @@ CONFIG_IPV6_NDISC_NODETYPE=y
 # CONFIG_IP_SCTP is not set
 # CONFIG_TIPC is not set
 # CONFIG_ATM is not set
-# CONFIG_BRIDGE is not set
+CONFIG_BRIDGE=m
 # CONFIG_NET_DSA is not set
 # CONFIG_VLAN_8021Q is not set
 # CONFIG_DECNET is not set
@@ -579,7 +579,7 @@ CONFIG_NETDEVICES=y
 # CONFIG_BONDING is not set
 # CONFIG_MACVLAN is not set
 # CONFIG_EQUALIZER is not set
-# CONFIG_TUN is not set
+CONFIG_TUN=m
 # CONFIG_VETH is not set
 # CONFIG_ARCNET is not set
 # CONFIG_PHYLIB is not set
@@ -1001,11 +1001,11 @@ CONFIG_USB_OHCI_LITTLE_ENDIAN=y
 # CONFIG_USB_TMC is not set
 
 #
-# NOTE: USB_STORAGE enables SCSI, and 'SCSI disk support'
+# NOTE: USB_STORAGE depends on SCSI but BLK_DEV_SD may also be needed;
 #
 
 #
-# may also be needed; see USB_STORAGE Help for more information
+# see USB_STORAGE Help for more information
 #
 CONFIG_USB_STORAGE=m
 # CONFIG_USB_STORAGE_DEBUG is not set
@@ -1418,6 +1418,6 @@ CONFIG_CRYPTO_LZO=m
 # CONFIG_PPC_CLOCK is not set
 CONFIG_VIRTUALIZATION=y
 CONFIG_KVM=y
-CONFIG_KVM_BOOKE_HOST=y
+CONFIG_KVM_440=y
 # CONFIG_VIRTIO_PCI is not set
 # CONFIG_VIRTIO_BALLOON is not set
diff --git a/arch/powerpc/include/asm/atomic.h b/arch/powerpc/include/asm/atomic.h
index f3fc733758f5..499be5bdd6fa 100644
--- a/arch/powerpc/include/asm/atomic.h
+++ b/arch/powerpc/include/asm/atomic.h
@@ -111,7 +111,7 @@ static __inline__ void atomic_inc(atomic_t *v)
 	bne-	1b"
 	: "=&r" (t), "+m" (v->counter)
 	: "r" (&v->counter)
-	: "cc");
+	: "cc", "xer");
 }
 
 static __inline__ int atomic_inc_return(atomic_t *v)
@@ -128,7 +128,7 @@ static __inline__ int atomic_inc_return(atomic_t *v)
 	ISYNC_ON_SMP
 	: "=&r" (t)
 	: "r" (&v->counter)
-	: "cc", "memory");
+	: "cc", "xer", "memory");
 
 	return t;
 }
@@ -155,7 +155,7 @@ static __inline__ void atomic_dec(atomic_t *v)
 	bne-	1b"
 	: "=&r" (t), "+m" (v->counter)
 	: "r" (&v->counter)
-	: "cc");
+	: "cc", "xer");
 }
 
 static __inline__ int atomic_dec_return(atomic_t *v)
@@ -172,7 +172,7 @@ static __inline__ int atomic_dec_return(atomic_t *v)
 	ISYNC_ON_SMP
 	: "=&r" (t)
 	: "r" (&v->counter)
-	: "cc", "memory");
+	: "cc", "xer", "memory");
 
 	return t;
 }
@@ -346,7 +346,7 @@ static __inline__ void atomic64_inc(atomic64_t *v)
 	bne-	1b"
 	: "=&r" (t), "+m" (v->counter)
 	: "r" (&v->counter)
-	: "cc");
+	: "cc", "xer");
 }
 
 static __inline__ long atomic64_inc_return(atomic64_t *v)
@@ -362,7 +362,7 @@ static __inline__ long atomic64_inc_return(atomic64_t *v)
 	ISYNC_ON_SMP
 	: "=&r" (t)
 	: "r" (&v->counter)
-	: "cc", "memory");
+	: "cc", "xer", "memory");
 
 	return t;
 }
@@ -388,7 +388,7 @@ static __inline__ void atomic64_dec(atomic64_t *v)
 	bne-	1b"
 	: "=&r" (t), "+m" (v->counter)
 	: "r" (&v->counter)
-	: "cc");
+	: "cc", "xer");
 }
 
 static __inline__ long atomic64_dec_return(atomic64_t *v)
@@ -404,7 +404,7 @@ static __inline__ long atomic64_dec_return(atomic64_t *v)
 	ISYNC_ON_SMP
 	: "=&r" (t)
 	: "r" (&v->counter)
-	: "cc", "memory");
+	: "cc", "xer", "memory");
 
 	return t;
 }
@@ -431,7 +431,7 @@ static __inline__ long atomic64_dec_if_positive(atomic64_t *v)
 	"\n\
 2:"	: "=&r" (t)
 	: "r" (&v->counter)
-	: "cc", "memory");
+	: "cc", "xer", "memory");
 
 	return t;
 }
diff --git a/arch/powerpc/include/asm/byteorder.h b/arch/powerpc/include/asm/byteorder.h
index b37752214a16..d5de325472e9 100644
--- a/arch/powerpc/include/asm/byteorder.h
+++ b/arch/powerpc/include/asm/byteorder.h
@@ -11,6 +11,8 @@
 #include <asm/types.h>
 #include <linux/compiler.h>
 
+#define __BIG_ENDIAN
+
 #ifdef __GNUC__
 #ifdef __KERNEL__
 
@@ -21,12 +23,19 @@ static __inline__ __u16 ld_le16(const volatile __u16 *addr)
 	__asm__ __volatile__ ("lhbrx %0,0,%1" : "=r" (val) : "r" (addr), "m" (*addr));
 	return val;
 }
+#define __arch_swab16p ld_le16
 
 static __inline__ void st_le16(volatile __u16 *addr, const __u16 val)
 {
 	__asm__ __volatile__ ("sthbrx %1,0,%2" : "=m" (*addr) : "r" (val), "r" (addr));
 }
 
+static inline void __arch_swab16s(__u16 *addr)
+{
+	st_le16(addr, *addr);
+}
+#define __arch_swab16s __arch_swab16s
+
 static __inline__ __u32 ld_le32(const volatile __u32 *addr)
 {
 	__u32 val;
@@ -34,13 +43,20 @@ static __inline__ __u32 ld_le32(const volatile __u32 *addr)
 	__asm__ __volatile__ ("lwbrx %0,0,%1" : "=r" (val) : "r" (addr), "m" (*addr));
 	return val;
 }
+#define __arch_swab32p ld_le32
 
 static __inline__ void st_le32(volatile __u32 *addr, const __u32 val)
 {
 	__asm__ __volatile__ ("stwbrx %1,0,%2" : "=m" (*addr) : "r" (val), "r" (addr));
 }
 
-static __inline__ __attribute_const__ __u16 ___arch__swab16(__u16 value)
+static inline void __arch_swab32s(__u32 *addr)
+{
+	st_le32(addr, *addr);
+}
+#define __arch_swab32s __arch_swab32s
+
+static inline __attribute_const__ __u16 __arch_swab16(__u16 value)
 {
 	__u16 result;
 
@@ -49,8 +65,9 @@ static __inline__ __attribute_const__ __u16 ___arch__swab16(__u16 value)
 	    : "r" (value), "0" (value >> 8));
 	return result;
 }
+#define __arch_swab16 __arch_swab16
 
-static __inline__ __attribute_const__ __u32 ___arch__swab32(__u32 value)
+static inline __attribute_const__ __u32 __arch_swab32(__u32 value)
 {
 	__u32 result;
 
@@ -61,29 +78,16 @@ static __inline__ __attribute_const__ __u32 ___arch__swab32(__u32 value)
 	    : "r" (value), "0" (value >> 24));
 	return result;
 }
-
-#define __arch__swab16(x) ___arch__swab16(x)
-#define __arch__swab32(x) ___arch__swab32(x)
-
-/* The same, but returns converted value from the location pointer by addr. */
-#define __arch__swab16p(addr) ld_le16(addr)
-#define __arch__swab32p(addr) ld_le32(addr)
-
-/* The same, but do the conversion in situ, ie. put the value back to addr. */
-#define __arch__swab16s(addr) st_le16(addr,*addr)
-#define __arch__swab32s(addr) st_le32(addr,*addr)
+#define __arch_swab32 __arch_swab32
 
 #endif /* __KERNEL__ */
 
-#ifndef __STRICT_ANSI__
-#define __BYTEORDER_HAS_U64__
 #ifndef __powerpc64__
 #define __SWAB_64_THRU_32__
 #endif /* __powerpc64__ */
-#endif /* __STRICT_ANSI__ */
 
 #endif /* __GNUC__ */
 
-#include <linux/byteorder/big_endian.h>
+#include <linux/byteorder.h>
 
 #endif /* _ASM_POWERPC_BYTEORDER_H */
diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h
index 1e94b07a020e..803d174dae29 100644
--- a/arch/powerpc/include/asm/cputable.h
+++ b/arch/powerpc/include/asm/cputable.h
@@ -194,6 +194,7 @@ extern const char *powerpc_base_platform;
 #define CPU_FTR_VSX			LONG_ASM_CONST(0x0010000000000000)
 #define CPU_FTR_SAO			LONG_ASM_CONST(0x0020000000000000)
 #define CPU_FTR_CP_USE_DCBTZ		LONG_ASM_CONST(0x0040000000000000)
+#define CPU_FTR_UNALIGNED_LD_STD	LONG_ASM_CONST(0x0080000000000000)
 
 #ifndef __ASSEMBLY__
 
@@ -404,7 +405,7 @@ extern const char *powerpc_base_platform;
 	    CPU_FTR_MMCRA | CPU_FTR_SMT | \
 	    CPU_FTR_COHERENT_ICACHE | CPU_FTR_LOCKLESS_TLBIE | \
 	    CPU_FTR_PURR | CPU_FTR_SPURR | CPU_FTR_REAL_LE | \
-	    CPU_FTR_DSCR)
+	    CPU_FTR_DSCR | CPU_FTR_UNALIGNED_LD_STD)
 #define CPU_FTRS_POWER7 (CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \
 	    CPU_FTR_HPTE_TABLE | CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \
 	    CPU_FTR_MMCRA | CPU_FTR_SMT | \
@@ -415,7 +416,8 @@ extern const char *powerpc_base_platform;
 	    CPU_FTR_HPTE_TABLE | CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \
 	    CPU_FTR_ALTIVEC_COMP | CPU_FTR_MMCRA | CPU_FTR_SMT | \
 	    CPU_FTR_PAUSE_ZERO | CPU_FTR_CI_LARGE_PAGE | \
-	    CPU_FTR_CELL_TB_BUG | CPU_FTR_CP_USE_DCBTZ)
+	    CPU_FTR_CELL_TB_BUG | CPU_FTR_CP_USE_DCBTZ | \
+	    CPU_FTR_UNALIGNED_LD_STD)
 #define CPU_FTRS_PA6T (CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \
 	    CPU_FTR_HPTE_TABLE | CPU_FTR_PPCAS_ARCH_V2 | \
 	    CPU_FTR_ALTIVEC_COMP | CPU_FTR_CI_LARGE_PAGE | \
diff --git a/arch/powerpc/include/asm/device.h b/arch/powerpc/include/asm/device.h
index dfd504caccc1..7d2277cef09a 100644
--- a/arch/powerpc/include/asm/device.h
+++ b/arch/powerpc/include/asm/device.h
@@ -18,4 +18,16 @@ struct dev_archdata {
 	void			*dma_data;
 };
 
+static inline void dev_archdata_set_node(struct dev_archdata *ad,
+					 struct device_node *np)
+{
+	ad->of_node = np;
+}
+
+static inline struct device_node *
+dev_archdata_get_node(const struct dev_archdata *ad)
+{
+	return ad->of_node;
+}
+
 #endif /* _ASM_POWERPC_DEVICE_H */
diff --git a/arch/powerpc/include/asm/dma-mapping.h b/arch/powerpc/include/asm/dma-mapping.h
index fddb229bd74f..9063184fa6fe 100644
--- a/arch/powerpc/include/asm/dma-mapping.h
+++ b/arch/powerpc/include/asm/dma-mapping.h
@@ -60,12 +60,6 @@ struct dma_mapping_ops {
 				dma_addr_t *dma_handle, gfp_t flag);
 	void		(*free_coherent)(struct device *dev, size_t size,
 				void *vaddr, dma_addr_t dma_handle);
-	dma_addr_t	(*map_single)(struct device *dev, void *ptr,
-				size_t size, enum dma_data_direction direction,
-				struct dma_attrs *attrs);
-	void		(*unmap_single)(struct device *dev, dma_addr_t dma_addr,
-				size_t size, enum dma_data_direction direction,
-				struct dma_attrs *attrs);
 	int		(*map_sg)(struct device *dev, struct scatterlist *sg,
 				int nents, enum dma_data_direction direction,
 				struct dma_attrs *attrs);
@@ -82,6 +76,22 @@ struct dma_mapping_ops {
 				dma_addr_t dma_address, size_t size,
 				enum dma_data_direction direction,
 				struct dma_attrs *attrs);
+#ifdef CONFIG_PPC_NEED_DMA_SYNC_OPS
+	void            (*sync_single_range_for_cpu)(struct device *hwdev,
+				dma_addr_t dma_handle, unsigned long offset,
+				size_t size,
+				enum dma_data_direction direction);
+	void            (*sync_single_range_for_device)(struct device *hwdev,
+				dma_addr_t dma_handle, unsigned long offset,
+				size_t size,
+				enum dma_data_direction direction);
+	void            (*sync_sg_for_cpu)(struct device *hwdev,
+				struct scatterlist *sg, int nelems,
+				enum dma_data_direction direction);
+	void            (*sync_sg_for_device)(struct device *hwdev,
+				struct scatterlist *sg, int nelems,
+				enum dma_data_direction direction);
+#endif
 };
 
 /*
@@ -149,10 +159,9 @@ static inline int dma_set_mask(struct device *dev, u64 dma_mask)
 }
 
 /*
- * TODO: map_/unmap_single will ideally go away, to be completely
- * replaced by map/unmap_page.   Until then, we allow dma_ops to have
- * one or the other, or both by checking to see if the specific
- * function requested exists; and if not, falling back on the other set.
+ * map_/unmap_single actually call through to map/unmap_page now that all the
+ * dma_mapping_ops have been converted over. We just have to get the page and
+ * offset to pass through to map_page
  */
 static inline dma_addr_t dma_map_single_attrs(struct device *dev,
 					      void *cpu_addr,
@@ -164,10 +173,6 @@ static inline dma_addr_t dma_map_single_attrs(struct device *dev,
 
 	BUG_ON(!dma_ops);
 
-	if (dma_ops->map_single)
-		return dma_ops->map_single(dev, cpu_addr, size, direction,
-					   attrs);
-
 	return dma_ops->map_page(dev, virt_to_page(cpu_addr),
 				 (unsigned long)cpu_addr % PAGE_SIZE, size,
 				 direction, attrs);
@@ -183,11 +188,6 @@ static inline void dma_unmap_single_attrs(struct device *dev,
 
 	BUG_ON(!dma_ops);
 
-	if (dma_ops->unmap_single) {
-		dma_ops->unmap_single(dev, dma_addr, size, direction, attrs);
-		return;
-	}
-
 	dma_ops->unmap_page(dev, dma_addr, size, direction, attrs);
 }
 
@@ -201,12 +201,7 @@ static inline dma_addr_t dma_map_page_attrs(struct device *dev,
 
 	BUG_ON(!dma_ops);
 
-	if (dma_ops->map_page)
-		return dma_ops->map_page(dev, page, offset, size, direction,
-					 attrs);
-
-	return dma_ops->map_single(dev, page_address(page) + offset, size,
-				   direction, attrs);
+	return dma_ops->map_page(dev, page, offset, size, direction, attrs);
 }
 
 static inline void dma_unmap_page_attrs(struct device *dev,
@@ -219,12 +214,7 @@ static inline void dma_unmap_page_attrs(struct device *dev,
 
 	BUG_ON(!dma_ops);
 
-	if (dma_ops->unmap_page) {
-		dma_ops->unmap_page(dev, dma_address, size, direction, attrs);
-		return;
-	}
-
-	dma_ops->unmap_single(dev, dma_address, size, direction, attrs);
+	dma_ops->unmap_page(dev, dma_address, size, direction, attrs);
 }
 
 static inline int dma_map_sg_attrs(struct device *dev, struct scatterlist *sg,
@@ -308,48 +298,79 @@ static inline void dma_unmap_sg(struct device *dev, struct scatterlist *sg,
 	dma_unmap_sg_attrs(dev, sg, nhwentries, direction, NULL);
 }
 
+#ifdef CONFIG_PPC_NEED_DMA_SYNC_OPS
 static inline void dma_sync_single_for_cpu(struct device *dev,
 		dma_addr_t dma_handle, size_t size,
 		enum dma_data_direction direction)
 {
-	BUG_ON(direction == DMA_NONE);
-	__dma_sync(bus_to_virt(dma_handle), size, direction);
+	struct dma_mapping_ops *dma_ops = get_dma_ops(dev);
+
+	BUG_ON(!dma_ops);
+	dma_ops->sync_single_range_for_cpu(dev, dma_handle, 0,
+					   size, direction);
 }
 
 static inline void dma_sync_single_for_device(struct device *dev,
 		dma_addr_t dma_handle, size_t size,
 		enum dma_data_direction direction)
 {
-	BUG_ON(direction == DMA_NONE);
-	__dma_sync(bus_to_virt(dma_handle), size, direction);
+	struct dma_mapping_ops *dma_ops = get_dma_ops(dev);
+
+	BUG_ON(!dma_ops);
+	dma_ops->sync_single_range_for_device(dev, dma_handle,
+					      0, size, direction);
 }
 
 static inline void dma_sync_sg_for_cpu(struct device *dev,
 		struct scatterlist *sgl, int nents,
 		enum dma_data_direction direction)
 {
-	struct scatterlist *sg;
-	int i;
-
-	BUG_ON(direction == DMA_NONE);
+	struct dma_mapping_ops *dma_ops = get_dma_ops(dev);
 
-	for_each_sg(sgl, sg, nents, i)
-		__dma_sync_page(sg_page(sg), sg->offset, sg->length, direction);
+	BUG_ON(!dma_ops);
+	dma_ops->sync_sg_for_cpu(dev, sgl, nents, direction);
 }
 
 static inline void dma_sync_sg_for_device(struct device *dev,
 		struct scatterlist *sgl, int nents,
 		enum dma_data_direction direction)
 {
-	struct scatterlist *sg;
-	int i;
+	struct dma_mapping_ops *dma_ops = get_dma_ops(dev);
 
-	BUG_ON(direction == DMA_NONE);
+	BUG_ON(!dma_ops);
+	dma_ops->sync_sg_for_device(dev, sgl, nents, direction);
+}
+
+static inline void dma_sync_single_range_for_cpu(struct device *dev,
+		dma_addr_t dma_handle, unsigned long offset, size_t size,
+		enum dma_data_direction direction)
+{
+	struct dma_mapping_ops *dma_ops = get_dma_ops(dev);
 
-	for_each_sg(sgl, sg, nents, i)
-		__dma_sync_page(sg_page(sg), sg->offset, sg->length, direction);
+	BUG_ON(!dma_ops);
+	dma_ops->sync_single_range_for_cpu(dev, dma_handle,
+					   offset, size, direction);
 }
 
+static inline void dma_sync_single_range_for_device(struct device *dev,
+		dma_addr_t dma_handle, unsigned long offset, size_t size,
+		enum dma_data_direction direction)
+{
+	struct dma_mapping_ops *dma_ops = get_dma_ops(dev);
+
+	BUG_ON(!dma_ops);
+	dma_ops->sync_single_range_for_device(dev, dma_handle, offset,
+					      size, direction);
+}
+#else /* CONFIG_PPC_NEED_DMA_SYNC_OPS */
+#define dma_sync_single_for_cpu(d, h, s, dir) ((void)0)
+#define dma_sync_single_for_device(d, h, s, dir) ((void)0)
+#define dma_sync_single_range_for_cpu(d, h, o, s, dir) ((void)0)
+#define dma_sync_single_range_for_device(d, h, o, s, dir) ((void)0)
+#define dma_sync_sg_for_cpu(d, s, n, dir) ((void)0)
+#define dma_sync_sg_for_device(d, s, n, dir) ((void)0)
+#endif
+
 static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
 {
 #ifdef CONFIG_PPC64
@@ -382,22 +403,6 @@ static inline int dma_get_cache_alignment(void)
 #endif
 }
 
-static inline void dma_sync_single_range_for_cpu(struct device *dev,
-		dma_addr_t dma_handle, unsigned long offset, size_t size,
-		enum dma_data_direction direction)
-{
-	/* just sync everything for now */
-	dma_sync_single_for_cpu(dev, dma_handle, offset + size, direction);
-}
-
-static inline void dma_sync_single_range_for_device(struct device *dev,
-		dma_addr_t dma_handle, unsigned long offset, size_t size,
-		enum dma_data_direction direction)
-{
-	/* just sync everything for now */
-	dma_sync_single_for_device(dev, dma_handle, offset + size, direction);
-}
-
 static inline void dma_cache_sync(struct device *dev, void *vaddr, size_t size,
 		enum dma_data_direction direction)
 {
diff --git a/arch/powerpc/include/asm/eeh.h b/arch/powerpc/include/asm/eeh.h
index b886bec67016..66ea9b8b95c5 100644
--- a/arch/powerpc/include/asm/eeh.h
+++ b/arch/powerpc/include/asm/eeh.h
@@ -17,8 +17,8 @@
  * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
  */
 
-#ifndef _PPC64_EEH_H
-#define _PPC64_EEH_H
+#ifndef _POWERPC_EEH_H
+#define _POWERPC_EEH_H
 #ifdef __KERNEL__
 
 #include <linux/init.h>
@@ -110,6 +110,7 @@ static inline void eeh_remove_bus_device(struct pci_dev *dev) { }
 #define EEH_IO_ERROR_VALUE(size) (-1UL)
 #endif /* CONFIG_EEH */
 
+#ifdef CONFIG_PPC64
 /*
  * MMIO read/write operations with EEH support.
  */
@@ -207,5 +208,6 @@ static inline void eeh_readsl(const volatile void __iomem *addr, void * buf,
 		eeh_check_failure(addr, *(u32*)buf);
 }
 
+#endif /* CONFIG_PPC64 */
 #endif /* __KERNEL__ */
-#endif /* _PPC64_EEH_H */
+#endif /* _POWERPC_EEH_H */
diff --git a/arch/powerpc/include/asm/elf.h b/arch/powerpc/include/asm/elf.h
index d812929390e4..cd46f023ec6d 100644
--- a/arch/powerpc/include/asm/elf.h
+++ b/arch/powerpc/include/asm/elf.h
@@ -267,7 +267,7 @@ extern int ucache_bsize;
 #define ARCH_HAS_SETUP_ADDITIONAL_PAGES
 struct linux_binprm;
 extern int arch_setup_additional_pages(struct linux_binprm *bprm,
-				       int executable_stack);
+				       int uses_interp);
 #define VDSO_AUX_ENT(a,b) NEW_AUX_ENT(a,b);
 
 #endif /* __KERNEL__ */
diff --git a/arch/powerpc/include/asm/ftrace.h b/arch/powerpc/include/asm/ftrace.h
index b298f7a631e6..e5f2ae8362f7 100644
--- a/arch/powerpc/include/asm/ftrace.h
+++ b/arch/powerpc/include/asm/ftrace.h
@@ -7,7 +7,19 @@
 
 #ifndef __ASSEMBLY__
 extern void _mcount(void);
-#endif
+
+#ifdef CONFIG_DYNAMIC_FTRACE
+static inline unsigned long ftrace_call_adjust(unsigned long addr)
+{
+       /* reloction of mcount call site is the same as the address */
+       return addr;
+}
+
+struct dyn_arch_ftrace {
+	struct module *mod;
+};
+#endif /*  CONFIG_DYNAMIC_FTRACE */
+#endif /* __ASSEMBLY__ */
 
 #endif
 
diff --git a/arch/powerpc/include/asm/highmem.h b/arch/powerpc/include/asm/highmem.h
index 91c589520c0a..7dc52eca8b67 100644
--- a/arch/powerpc/include/asm/highmem.h
+++ b/arch/powerpc/include/asm/highmem.h
@@ -85,7 +85,7 @@ static inline void *kmap_atomic_prot(struct page *page, enum km_type type, pgpro
 	BUG_ON(!pte_none(*(kmap_pte-idx)));
 #endif
 	__set_pte_at(&init_mm, vaddr, kmap_pte-idx, mk_pte(page, prot));
-	flush_tlb_page(NULL, vaddr);
+	local_flush_tlb_page(vaddr);
 
 	return (void*) vaddr;
 }
@@ -113,7 +113,7 @@ static inline void kunmap_atomic(void *kvaddr, enum km_type type)
 	 * this pte without first remap it
 	 */
 	pte_clear(&init_mm, vaddr, kmap_pte-idx);
-	flush_tlb_page(NULL, vaddr);
+	local_flush_tlb_page(vaddr);
 #endif
 	pagefault_enable();
 }
diff --git a/arch/powerpc/include/asm/local.h b/arch/powerpc/include/asm/local.h
index 612d83276653..84b457a3c1bc 100644
--- a/arch/powerpc/include/asm/local.h
+++ b/arch/powerpc/include/asm/local.h
@@ -67,7 +67,7 @@ static __inline__ long local_inc_return(local_t *l)
 	bne-	1b"
 	: "=&r" (t)
 	: "r" (&(l->a.counter))
-	: "cc", "memory");
+	: "cc", "xer", "memory");
 
 	return t;
 }
@@ -94,7 +94,7 @@ static __inline__ long local_dec_return(local_t *l)
 	bne-	1b"
 	: "=&r" (t)
 	: "r" (&(l->a.counter))
-	: "cc", "memory");
+	: "cc", "xer", "memory");
 
 	return t;
 }
diff --git a/arch/powerpc/include/asm/lppaca.h b/arch/powerpc/include/asm/lppaca.h
index 2fe268b10333..25aaa97facd8 100644
--- a/arch/powerpc/include/asm/lppaca.h
+++ b/arch/powerpc/include/asm/lppaca.h
@@ -133,7 +133,8 @@ struct lppaca {
 //=============================================================================
 // CACHE_LINE_4-5 0x0180 - 0x027F Contains PMC interrupt data
 //=============================================================================
-	u8	pmc_save_area[256];	// PMC interrupt Area           x00-xFF
+	u32	page_ins;			// CMO Hint - # page ins by OS  x00-x04
+	u8	pmc_save_area[252];	// PMC interrupt Area           x04-xFF
 } __attribute__((__aligned__(0x400)));
 
 extern struct lppaca lppaca[];
diff --git a/arch/powerpc/include/asm/mmu-fsl-booke.h b/arch/powerpc/include/asm/mmu-fsl-booke.h
index 925d93cf64d8..5588a41f439c 100644
--- a/arch/powerpc/include/asm/mmu-fsl-booke.h
+++ b/arch/powerpc/include/asm/mmu-fsl-booke.h
@@ -40,6 +40,8 @@
 #define MAS2_M		0x00000004
 #define MAS2_G		0x00000002
 #define MAS2_E		0x00000001
+#define MAS2_EPN_MASK(size)		(~0 << (2*(size) + 10))
+#define MAS2_VAL(addr, size, flags)	((addr) & MAS2_EPN_MASK(size) | (flags))
 
 #define MAS3_RPN	0xFFFFF000
 #define MAS3_U0		0x00000200
diff --git a/arch/powerpc/include/asm/mmu_context.h b/arch/powerpc/include/asm/mmu_context.h
index 6b993ef452ff..b570209b71a8 100644
--- a/arch/powerpc/include/asm/mmu_context.h
+++ b/arch/powerpc/include/asm/mmu_context.h
@@ -180,6 +180,9 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
 
 	tsk->thread.pgdir = next->pgd;
 
+	if (!cpu_isset(smp_processor_id(), next->cpu_vm_mask))
+		cpu_set(smp_processor_id(), next->cpu_vm_mask);
+
 	/* No need to flush userspace segments if the mm doesnt change */
 	if (prev == next)
 		return;
diff --git a/arch/powerpc/include/asm/module.h b/arch/powerpc/include/asm/module.h
index e5f14b13ccf0..08454880a2c0 100644
--- a/arch/powerpc/include/asm/module.h
+++ b/arch/powerpc/include/asm/module.h
@@ -34,11 +34,19 @@ struct mod_arch_specific {
 #ifdef __powerpc64__
 	unsigned int stubs_section;	/* Index of stubs section in module */
 	unsigned int toc_section;	/* What section is the TOC? */
-#else
+#ifdef CONFIG_DYNAMIC_FTRACE
+	unsigned long toc;
+	unsigned long tramp;
+#endif
+
+#else /* powerpc64 */
 	/* Indices of PLT sections within module. */
 	unsigned int core_plt_section;
 	unsigned int init_plt_section;
+#ifdef CONFIG_DYNAMIC_FTRACE
+	unsigned long tramp;
 #endif
+#endif /* powerpc64 */
 
 	/* List of BUG addresses, source line numbers and filenames */
 	struct list_head bug_list;
@@ -68,6 +76,12 @@ struct mod_arch_specific {
 #    endif	/* MODULE */
 #endif
 
+#ifdef CONFIG_DYNAMIC_FTRACE
+#    ifdef MODULE
+	asm(".section .ftrace.tramp,\"ax\",@nobits; .align 3; .previous");
+#    endif	/* MODULE */
+#endif
+
 
 struct exception_table_entry;
 void sort_ex_table(struct exception_table_entry *start,
diff --git a/arch/powerpc/include/asm/mutex.h b/arch/powerpc/include/asm/mutex.h
index 458c1f7fbc18..dabc01c727b8 100644
--- a/arch/powerpc/include/asm/mutex.h
+++ b/arch/powerpc/include/asm/mutex.h
@@ -1,9 +1,134 @@
 /*
- * Pull in the generic implementation for the mutex fastpath.
+ * Optimised mutex implementation of include/asm-generic/mutex-dec.h algorithm
+ */
+#ifndef _ASM_POWERPC_MUTEX_H
+#define _ASM_POWERPC_MUTEX_H
+
+static inline int __mutex_cmpxchg_lock(atomic_t *v, int old, int new)
+{
+	int t;
+
+	__asm__ __volatile__ (
+"1:	lwarx	%0,0,%1		# mutex trylock\n\
+	cmpw	0,%0,%2\n\
+	bne-	2f\n"
+	PPC405_ERR77(0,%1)
+"	stwcx.	%3,0,%1\n\
+	bne-	1b"
+	ISYNC_ON_SMP
+	"\n\
+2:"
+	: "=&r" (t)
+	: "r" (&v->counter), "r" (old), "r" (new)
+	: "cc", "memory");
+
+	return t;
+}
+
+static inline int __mutex_dec_return_lock(atomic_t *v)
+{
+	int t;
+
+	__asm__ __volatile__(
+"1:	lwarx	%0,0,%1		# mutex lock\n\
+	addic	%0,%0,-1\n"
+	PPC405_ERR77(0,%1)
+"	stwcx.	%0,0,%1\n\
+	bne-	1b"
+	ISYNC_ON_SMP
+	: "=&r" (t)
+	: "r" (&v->counter)
+	: "cc", "memory");
+
+	return t;
+}
+
+static inline int __mutex_inc_return_unlock(atomic_t *v)
+{
+	int t;
+
+	__asm__ __volatile__(
+	LWSYNC_ON_SMP
+"1:	lwarx	%0,0,%1		# mutex unlock\n\
+	addic	%0,%0,1\n"
+	PPC405_ERR77(0,%1)
+"	stwcx.	%0,0,%1 \n\
+	bne-	1b"
+	: "=&r" (t)
+	: "r" (&v->counter)
+	: "cc", "memory");
+
+	return t;
+}
+
+/**
+ *  __mutex_fastpath_lock - try to take the lock by moving the count
+ *                          from 1 to a 0 value
+ *  @count: pointer of type atomic_t
+ *  @fail_fn: function to call if the original value was not 1
+ *
+ * Change the count from 1 to a value lower than 1, and call <fail_fn> if
+ * it wasn't 1 originally. This function MUST leave the value lower than
+ * 1 even when the "1" assertion wasn't true.
+ */
+static inline void
+__mutex_fastpath_lock(atomic_t *count, void (*fail_fn)(atomic_t *))
+{
+	if (unlikely(__mutex_dec_return_lock(count) < 0))
+		fail_fn(count);
+}
+
+/**
+ *  __mutex_fastpath_lock_retval - try to take the lock by moving the count
+ *                                 from 1 to a 0 value
+ *  @count: pointer of type atomic_t
+ *  @fail_fn: function to call if the original value was not 1
+ *
+ * Change the count from 1 to a value lower than 1, and call <fail_fn> if
+ * it wasn't 1 originally. This function returns 0 if the fastpath succeeds,
+ * or anything the slow path function returns.
+ */
+static inline int
+__mutex_fastpath_lock_retval(atomic_t *count, int (*fail_fn)(atomic_t *))
+{
+	if (unlikely(__mutex_dec_return_lock(count) < 0))
+		return fail_fn(count);
+	return 0;
+}
+
+/**
+ *  __mutex_fastpath_unlock - try to promote the count from 0 to 1
+ *  @count: pointer of type atomic_t
+ *  @fail_fn: function to call if the original value was not 0
+ *
+ * Try to promote the count from 0 to 1. If it wasn't 0, call <fail_fn>.
+ * In the failure case, this function is allowed to either set the value to
+ * 1, or to set it to a value lower than 1.
+ */
+static inline void
+__mutex_fastpath_unlock(atomic_t *count, void (*fail_fn)(atomic_t *))
+{
+	if (unlikely(__mutex_inc_return_unlock(count) <= 0))
+		fail_fn(count);
+}
+
+#define __mutex_slowpath_needs_to_unlock()		1
+
+/**
+ * __mutex_fastpath_trylock - try to acquire the mutex, without waiting
+ *
+ *  @count: pointer of type atomic_t
+ *  @fail_fn: fallback function
  *
- * TODO: implement optimized primitives instead, or leave the generic
- * implementation in place, or pick the atomic_xchg() based generic
- * implementation. (see asm-generic/mutex-xchg.h for details)
+ * Change the count from 1 to 0, and return 1 (success), or if the count
+ * was not 1, then return 0 (failure).
  */
+static inline int
+__mutex_fastpath_trylock(atomic_t *count, int (*fail_fn)(atomic_t *))
+{
+	if (likely(__mutex_cmpxchg_lock(count, 1, 0) == 1))
+		return 1;
+	return 0;
+}
 
-#include <asm-generic/mutex-dec.h>
+#endif
diff --git a/arch/powerpc/include/asm/pci-bridge.h b/arch/powerpc/include/asm/pci-bridge.h
index 9047af7baa69..fa8b3b724438 100644
--- a/arch/powerpc/include/asm/pci-bridge.h
+++ b/arch/powerpc/include/asm/pci-bridge.h
@@ -241,9 +241,6 @@ extern void pcibios_remove_pci_devices(struct pci_bus *bus);
 
 /** Discover new pci devices under this bus, and add them */
 extern void pcibios_add_pci_devices(struct pci_bus *bus);
-extern void pcibios_fixup_new_pci_devices(struct pci_bus *bus);
-
-extern int pcibios_remove_root_bus(struct pci_controller *phb);
 
 static inline struct pci_controller *pci_bus_to_host(const struct pci_bus *bus)
 {
@@ -290,6 +287,7 @@ extern void pci_process_bridge_OF_ranges(struct pci_controller *hose,
 /* Allocate & free a PCI host bridge structure */
 extern struct pci_controller *pcibios_alloc_controller(struct device_node *dev);
 extern void pcibios_free_controller(struct pci_controller *phb);
+extern void pcibios_setup_phb_resources(struct pci_controller *hose);
 
 #ifdef CONFIG_PCI
 extern unsigned long pci_address_to_pio(phys_addr_t address);
diff --git a/arch/powerpc/include/asm/pci.h b/arch/powerpc/include/asm/pci.h
index 57a2a494886b..1c721a632d8e 100644
--- a/arch/powerpc/include/asm/pci.h
+++ b/arch/powerpc/include/asm/pci.h
@@ -204,15 +204,14 @@ static inline struct resource *pcibios_select_root(struct pci_dev *pdev,
 	return root;
 }
 
-extern void pcibios_setup_new_device(struct pci_dev *dev);
-
 extern void pcibios_claim_one_bus(struct pci_bus *b);
 
-extern void pcibios_allocate_bus_resources(struct pci_bus *bus);
+extern void pcibios_finish_adding_to_bus(struct pci_bus *bus);
 
 extern void pcibios_resource_survey(void);
 
 extern struct pci_controller *init_phb_dynamic(struct device_node *dn);
+extern int remove_phb_dynamic(struct pci_controller *phb);
 
 extern struct pci_dev *of_create_pci_dev(struct device_node *node,
 					struct pci_bus *bus, int devfn);
@@ -221,6 +220,7 @@ extern void of_scan_pci_bridge(struct device_node *node,
 				struct pci_dev *dev);
 
 extern void of_scan_bus(struct device_node *node, struct pci_bus *bus);
+extern void of_rescan_bus(struct device_node *node, struct pci_bus *bus);
 
 extern int pci_read_irq_line(struct pci_dev *dev);
 
@@ -235,9 +235,8 @@ extern void pci_resource_to_user(const struct pci_dev *dev, int bar,
 				 const struct resource *rsrc,
 				 resource_size_t *start, resource_size_t *end);
 
-extern void pcibios_do_bus_setup(struct pci_bus *bus);
-extern void pcibios_fixup_of_probed_bus(struct pci_bus *bus);
-
+extern void pcibios_setup_bus_devices(struct pci_bus *bus);
+extern void pcibios_setup_bus_self(struct pci_bus *bus);
 
 #endif	/* __KERNEL__ */
 #endif /* __ASM_POWERPC_PCI_H */
diff --git a/arch/powerpc/include/asm/pgalloc-32.h b/arch/powerpc/include/asm/pgalloc-32.h
index 58c07147b3ea..0815eb40acae 100644
--- a/arch/powerpc/include/asm/pgalloc-32.h
+++ b/arch/powerpc/include/asm/pgalloc-32.h
@@ -3,6 +3,8 @@
 
 #include <linux/threads.h>
 
+#define PTE_NONCACHE_NUM	0  /* dummy for now to share code w/ppc64 */
+
 extern void __bad_pte(pmd_t *pmd);
 
 extern pgd_t *pgd_alloc(struct mm_struct *mm);
@@ -33,10 +35,13 @@ extern void pgd_free(struct mm_struct *mm, pgd_t *pgd);
 
 extern pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long addr);
 extern pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long addr);
-extern void pte_free_kernel(struct mm_struct *mm, pte_t *pte);
-extern void pte_free(struct mm_struct *mm, pgtable_t pte);
 
-#define __pte_free_tlb(tlb, pte)	pte_free((tlb)->mm, (pte))
+static inline void pgtable_free(pgtable_free_t pgf)
+{
+	void *p = (void *)(pgf.val & ~PGF_CACHENUM_MASK);
+
+	free_page((unsigned long)p);
+}
 
 #define check_pgt_cache()	do { } while (0)
 
diff --git a/arch/powerpc/include/asm/pgalloc-64.h b/arch/powerpc/include/asm/pgalloc-64.h
index 812a1d8f35cb..afda2bdd860f 100644
--- a/arch/powerpc/include/asm/pgalloc-64.h
+++ b/arch/powerpc/include/asm/pgalloc-64.h
@@ -7,7 +7,6 @@
  * 2 of the License, or (at your option) any later version.
  */
 
-#include <linux/mm.h>
 #include <linux/slab.h>
 #include <linux/cpumask.h>
 #include <linux/percpu.h>
@@ -108,31 +107,6 @@ static inline pgtable_t pte_alloc_one(struct mm_struct *mm,
 	return page;
 }
 
-static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
-{
-	free_page((unsigned long)pte);
-}
-
-static inline void pte_free(struct mm_struct *mm, pgtable_t ptepage)
-{
-	pgtable_page_dtor(ptepage);
-	__free_page(ptepage);
-}
-
-#define PGF_CACHENUM_MASK	0x7
-
-typedef struct pgtable_free {
-	unsigned long val;
-} pgtable_free_t;
-
-static inline pgtable_free_t pgtable_free_cache(void *p, int cachenum,
-						unsigned long mask)
-{
-	BUG_ON(cachenum > PGF_CACHENUM_MASK);
-
-	return (pgtable_free_t){.val = ((unsigned long) p & ~mask) | cachenum};
-}
-
 static inline void pgtable_free(pgtable_free_t pgf)
 {
 	void *p = (void *)(pgf.val & ~PGF_CACHENUM_MASK);
@@ -144,14 +118,6 @@ static inline void pgtable_free(pgtable_free_t pgf)
 		kmem_cache_free(pgtable_cache[cachenum], p);
 }
 
-extern void pgtable_free_tlb(struct mmu_gather *tlb, pgtable_free_t pgf);
-
-#define __pte_free_tlb(tlb,ptepage)	\
-do { \
-	pgtable_page_dtor(ptepage); \
-	pgtable_free_tlb(tlb, pgtable_free_cache(page_address(ptepage), \
-		PTE_NONCACHE_NUM, PTE_TABLE_SIZE-1)); \
-} while (0)
 #define __pmd_free_tlb(tlb, pmd) 	\
 	pgtable_free_tlb(tlb, pgtable_free_cache(pmd, \
 		PMD_CACHE_NUM, PMD_TABLE_SIZE-1))
diff --git a/arch/powerpc/include/asm/pgalloc.h b/arch/powerpc/include/asm/pgalloc.h
index b4505ed0f0f2..5d8480265a77 100644
--- a/arch/powerpc/include/asm/pgalloc.h
+++ b/arch/powerpc/include/asm/pgalloc.h
@@ -2,11 +2,52 @@
 #define _ASM_POWERPC_PGALLOC_H
 #ifdef __KERNEL__
 
+#include <linux/mm.h>
+
+static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
+{
+	free_page((unsigned long)pte);
+}
+
+static inline void pte_free(struct mm_struct *mm, pgtable_t ptepage)
+{
+	pgtable_page_dtor(ptepage);
+	__free_page(ptepage);
+}
+
+typedef struct pgtable_free {
+	unsigned long val;
+} pgtable_free_t;
+
+#define PGF_CACHENUM_MASK	0x7
+
+static inline pgtable_free_t pgtable_free_cache(void *p, int cachenum,
+						unsigned long mask)
+{
+	BUG_ON(cachenum > PGF_CACHENUM_MASK);
+
+	return (pgtable_free_t){.val = ((unsigned long) p & ~mask) | cachenum};
+}
+
 #ifdef CONFIG_PPC64
 #include <asm/pgalloc-64.h>
 #else
 #include <asm/pgalloc-32.h>
 #endif
 
+extern void pgtable_free_tlb(struct mmu_gather *tlb, pgtable_free_t pgf);
+
+#ifdef CONFIG_SMP
+#define __pte_free_tlb(tlb,ptepage)	\
+do { \
+	pgtable_page_dtor(ptepage); \
+	pgtable_free_tlb(tlb, pgtable_free_cache(page_address(ptepage), \
+		PTE_NONCACHE_NUM, PTE_TABLE_SIZE-1)); \
+} while (0)
+#else
+#define __pte_free_tlb(tlb, pte)	pte_free((tlb)->mm, (pte))
+#endif
+
+
 #endif /* __KERNEL__ */
 #endif /* _ASM_POWERPC_PGALLOC_H */
diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h
index 101ed87f7d84..cd7a47860e5a 100644
--- a/arch/powerpc/include/asm/processor.h
+++ b/arch/powerpc/include/asm/processor.h
@@ -207,6 +207,11 @@ struct thread_struct {
 #define INIT_SP_LIMIT \
 	(_ALIGN_UP(sizeof(init_thread_info), 16) + (unsigned long) &init_stack)
 
+#ifdef CONFIG_SPE
+#define SPEFSCR_INIT .spefscr = SPEFSCR_FINVE | SPEFSCR_FDBZE | SPEFSCR_FUNFE | SPEFSCR_FOVFE,
+#else
+#define SPEFSCR_INIT
+#endif
 
 #ifdef CONFIG_PPC32
 #define INIT_THREAD { \
@@ -215,6 +220,7 @@ struct thread_struct {
 	.fs = KERNEL_DS, \
 	.pgdir = swapper_pg_dir, \
 	.fpexc_mode = MSR_FE0 | MSR_FE1, \
+	SPEFSCR_INIT \
 }
 #else
 #define INIT_THREAD  { \
diff --git a/arch/powerpc/include/asm/ps3.h b/arch/powerpc/include/asm/ps3.h
index f9e34c493cbb..4299365590d8 100644
--- a/arch/powerpc/include/asm/ps3.h
+++ b/arch/powerpc/include/asm/ps3.h
@@ -516,4 +516,7 @@ void ps3_sync_irq(int node);
 u32 ps3_get_hw_thread_id(int cpu);
 u64 ps3_get_spe_id(void *arg);
 
+/* mutex synchronizing GPU accesses and video mode changes */
+extern struct mutex ps3_gpu_mutex;
+
 #endif
diff --git a/arch/powerpc/include/asm/ps3av.h b/arch/powerpc/include/asm/ps3av.h
index 5aa22cffdbd6..cd24ac16660a 100644
--- a/arch/powerpc/include/asm/ps3av.h
+++ b/arch/powerpc/include/asm/ps3av.h
@@ -740,8 +740,4 @@ extern int ps3av_audio_mute(int);
 extern int ps3av_audio_mute_analog(int);
 extern int ps3av_dev_open(void);
 extern int ps3av_dev_close(void);
-extern void ps3av_register_flip_ctl(void (*flip_ctl)(int on, void *data),
-				    void *flip_data);
-extern void ps3av_flip_ctl(int on);
-
 #endif	/* _ASM_POWERPC_PS3AV_H_ */
diff --git a/arch/powerpc/include/asm/sfp-machine.h b/arch/powerpc/include/asm/sfp-machine.h
index ced34f1dc8f8..3d9f831c3c55 100644
--- a/arch/powerpc/include/asm/sfp-machine.h
+++ b/arch/powerpc/include/asm/sfp-machine.h
@@ -82,7 +82,7 @@
 #define _FP_MUL_MEAT_S(R,X,Y)   _FP_MUL_MEAT_1_wide(_FP_WFRACBITS_S,R,X,Y,umul_ppmm)
 #define _FP_MUL_MEAT_D(R,X,Y)   _FP_MUL_MEAT_2_wide(_FP_WFRACBITS_D,R,X,Y,umul_ppmm)
 
-#define _FP_DIV_MEAT_S(R,X,Y)	_FP_DIV_MEAT_1_udiv(S,R,X,Y)
+#define _FP_DIV_MEAT_S(R,X,Y)	_FP_DIV_MEAT_1_udiv_norm(S,R,X,Y)
 #define _FP_DIV_MEAT_D(R,X,Y)	_FP_DIV_MEAT_2_udiv(D,R,X,Y)
 
 /* These macros define what NaN looks like. They're supposed to expand to
@@ -97,6 +97,20 @@
 
 #define _FP_KEEPNANFRACP 1
 
+#ifdef FP_EX_BOOKE_E500_SPE
+#define FP_EX_INEXACT		(1 << 21)
+#define FP_EX_INVALID		(1 << 20)
+#define FP_EX_DIVZERO		(1 << 19)
+#define FP_EX_UNDERFLOW		(1 << 18)
+#define FP_EX_OVERFLOW		(1 << 17)
+#define FP_INHIBIT_RESULTS	0
+
+#define __FPU_FPSCR	(current->thread.spefscr)
+#define __FPU_ENABLED_EXC		\
+({					\
+	(__FPU_FPSCR >> 2) & 0x1f;	\
+})
+#else
 /* Exception flags.  We use the bit positions of the appropriate bits
    in the FPSCR, which also correspond to the FE_* bits.  This makes
    everything easier ;-).  */
@@ -111,22 +125,6 @@
 #define FP_EX_DIVZERO         (1 << (31 - 5))
 #define FP_EX_INEXACT         (1 << (31 - 6))
 
-/* This macro appears to be called when both X and Y are NaNs, and
- * has to choose one and copy it to R. i386 goes for the larger of the
- * two, sparc64 just picks Y. I don't understand this at all so I'll
- * go with sparc64 because it's shorter :->   -- PMM
- */
-#define _FP_CHOOSENAN(fs, wc, R, X, Y, OP)		\
-  do {							\
-    R##_s = Y##_s;					\
-    _FP_FRAC_COPY_##wc(R,Y);				\
-    R##_c = FP_CLS_NAN;					\
-  } while (0)
-
-
-#include <linux/kernel.h>
-#include <linux/sched.h>
-
 #define __FPU_FPSCR	(current->thread.fpscr.val)
 
 /* We only actually write to the destination register
@@ -137,6 +135,32 @@
 	(__FPU_FPSCR >> 3) & 0x1f;	\
 })
 
+#endif
+
+/*
+ * If one NaN is signaling and the other is not,
+ * we choose that one, otherwise we choose X.
+ */
+#define _FP_CHOOSENAN(fs, wc, R, X, Y, OP)			\
+  do {								\
+    if ((_FP_FRAC_HIGH_RAW_##fs(Y) & _FP_QNANBIT_##fs)		\
+	&& !(_FP_FRAC_HIGH_RAW_##fs(X) & _FP_QNANBIT_##fs))	\
+      {								\
+	R##_s = X##_s;						\
+	_FP_FRAC_COPY_##wc(R,X);				\
+      }								\
+    else							\
+      {								\
+	R##_s = Y##_s;						\
+	_FP_FRAC_COPY_##wc(R,Y);				\
+      }								\
+    R##_c = FP_CLS_NAN;						\
+  } while (0)
+
+
+#include <linux/kernel.h>
+#include <linux/sched.h>
+
 #define __FPU_TRAP_P(bits) \
 	((__FPU_ENABLED_EXC & (bits)) != 0)
 
diff --git a/arch/powerpc/include/asm/smp.h b/arch/powerpc/include/asm/smp.h
index 1866cec4f967..c25f73d1d842 100644
--- a/arch/powerpc/include/asm/smp.h
+++ b/arch/powerpc/include/asm/smp.h
@@ -81,6 +81,13 @@ extern int cpu_to_core_id(int cpu);
 #define PPC_MSG_CALL_FUNC_SINGLE	2
 #define PPC_MSG_DEBUGGER_BREAK  3
 
+/*
+ * irq controllers that have dedicated ipis per message and don't
+ * need additional code in the action handler may use this
+ */
+extern int smp_request_message_ipi(int virq, int message);
+extern const char *smp_ipi_name[];
+
 void smp_init_iSeries(void);
 void smp_init_pSeries(void);
 void smp_init_cell(void);
diff --git a/arch/powerpc/include/asm/spinlock.h b/arch/powerpc/include/asm/spinlock.h
index f56a843f4705..36864364e601 100644
--- a/arch/powerpc/include/asm/spinlock.h
+++ b/arch/powerpc/include/asm/spinlock.h
@@ -277,7 +277,7 @@ static inline void __raw_read_unlock(raw_rwlock_t *rw)
 	bne-		1b"
 	: "=&r"(tmp)
 	: "r"(&rw->lock)
-	: "cr0", "memory");
+	: "cr0", "xer", "memory");
 }
 
 static inline void __raw_write_unlock(raw_rwlock_t *rw)
diff --git a/arch/powerpc/include/asm/synch.h b/arch/powerpc/include/asm/synch.h
index 45963e80f557..28f6ddbff4cf 100644
--- a/arch/powerpc/include/asm/synch.h
+++ b/arch/powerpc/include/asm/synch.h
@@ -5,6 +5,10 @@
 #include <linux/stringify.h>
 #include <asm/feature-fixups.h>
 
+#if defined(__powerpc64__) || defined(CONFIG_PPC_E500MC)
+#define __SUBARCH_HAS_LWSYNC
+#endif
+
 #ifndef __ASSEMBLY__
 extern unsigned int __start___lwsync_fixup, __stop___lwsync_fixup;
 extern void do_lwsync_fixups(unsigned long value, void *fixup_start,
diff --git a/arch/powerpc/include/asm/system.h b/arch/powerpc/include/asm/system.h
index d6648c143322..2a4be19a92c4 100644
--- a/arch/powerpc/include/asm/system.h
+++ b/arch/powerpc/include/asm/system.h
@@ -23,15 +23,17 @@
  * read_barrier_depends() prevents data-dependent loads being reordered
  *	across this point (nop on PPC).
  *
- * We have to use the sync instructions for mb(), since lwsync doesn't
- * order loads with respect to previous stores.  Lwsync is fine for
- * rmb(), though. Note that rmb() actually uses a sync on 32-bit
- * architectures.
+ * *mb() variants without smp_ prefix must order all types of memory
+ * operations with one another. sync is the only instruction sufficient
+ * to do this.
  *
- * For wmb(), we use sync since wmb is used in drivers to order
- * stores to system memory with respect to writes to the device.
- * However, smp_wmb() can be a lighter-weight lwsync or eieio barrier
- * on SMP since it is only used to order updates to system memory.
+ * For the smp_ barriers, ordering is for cacheable memory operations
+ * only. We have to use the sync instruction for smp_mb(), since lwsync
+ * doesn't order loads with respect to previous stores.  Lwsync can be
+ * used for smp_rmb() and smp_wmb().
+ *
+ * However, on CPUs that don't support lwsync, lwsync actually maps to a
+ * heavy-weight sync, so smp_wmb() can be a lighter-weight eieio.
  */
 #define mb()   __asm__ __volatile__ ("sync" : : : "memory")
 #define rmb()  __asm__ __volatile__ ("sync" : : : "memory")
@@ -45,14 +47,14 @@
 #ifdef CONFIG_SMP
 
 #ifdef __SUBARCH_HAS_LWSYNC
-#    define SMPWMB      lwsync
+#    define SMPWMB      LWSYNC
 #else
 #    define SMPWMB      eieio
 #endif
 
 #define smp_mb()	mb()
-#define smp_rmb()	rmb()
-#define smp_wmb()	__asm__ __volatile__ (__stringify(SMPWMB) : : :"memory")
+#define smp_rmb()	__asm__ __volatile__ (stringify_in_c(LWSYNC) : : :"memory")
+#define smp_wmb()	__asm__ __volatile__ (stringify_in_c(SMPWMB) : : :"memory")
 #define smp_read_barrier_depends()	read_barrier_depends()
 #else
 #define smp_mb()	barrier()
diff --git a/arch/powerpc/include/asm/time.h b/arch/powerpc/include/asm/time.h
index febd581ec9b0..27ccb764fdab 100644
--- a/arch/powerpc/include/asm/time.h
+++ b/arch/powerpc/include/asm/time.h
@@ -48,26 +48,6 @@ extern unsigned long ppc_proc_freq;
 extern unsigned long ppc_tb_freq;
 #define DEFAULT_TB_FREQ		125000000UL
 
-/*
- * By putting all of this stuff into a single struct we 
- * reduce the number of cache lines touched by do_gettimeofday.
- * Both by collecting all of the data in one cache line and
- * by touching only one TOC entry on ppc64.
- */
-struct gettimeofday_vars {
-	u64 tb_to_xs;
-	u64 stamp_xsec;
-	u64 tb_orig_stamp;
-};
-
-struct gettimeofday_struct {
-	unsigned long tb_ticks_per_sec;
-	struct gettimeofday_vars vars[2];
-	struct gettimeofday_vars * volatile varp;
-	unsigned      var_idx;
-	unsigned      tb_to_us;
-};
-
 struct div_result {
 	u64 result_high;
 	u64 result_low;
diff --git a/arch/powerpc/include/asm/tlbflush.h b/arch/powerpc/include/asm/tlbflush.h
index a2c6bfd85fb7..93716a9f4e16 100644
--- a/arch/powerpc/include/asm/tlbflush.h
+++ b/arch/powerpc/include/asm/tlbflush.h
@@ -6,6 +6,7 @@
  *
  *  - flush_tlb_mm(mm) flushes the specified mm context TLB's
  *  - flush_tlb_page(vma, vmaddr) flushes one page
+ *  - local_flush_tlb_page(vmaddr) flushes one page on the local processor
  *  - flush_tlb_page_nohash(vma, vmaddr) flushes one page if SW loaded TLB
  *  - flush_tlb_range(vma, start, end) flushes a range of pages
  *  - flush_tlb_kernel_range(start, end) flushes a range of kernel pages
@@ -44,6 +45,11 @@ static inline void flush_tlb_mm(struct mm_struct *mm)
 	_tlbil_pid(mm->context.id);
 }
 
+static inline void local_flush_tlb_page(unsigned long vmaddr)
+{
+	_tlbil_va(vmaddr, 0);
+}
+
 static inline void flush_tlb_page(struct vm_area_struct *vma,
 				  unsigned long vmaddr)
 {
@@ -81,6 +87,10 @@ extern void flush_tlb_page_nohash(struct vm_area_struct *vma, unsigned long addr
 extern void flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
 			    unsigned long end);
 extern void flush_tlb_kernel_range(unsigned long start, unsigned long end);
+static inline void local_flush_tlb_page(unsigned long vmaddr)
+{
+	flush_tlb_page(NULL, vmaddr);
+}
 
 #else
 /*
@@ -138,6 +148,10 @@ static inline void flush_tlb_mm(struct mm_struct *mm)
 {
 }
 
+static inline void local_flush_tlb_page(unsigned long vmaddr)
+{
+}
+
 static inline void flush_tlb_page(struct vm_area_struct *vma,
 				  unsigned long vmaddr)
 {
diff --git a/arch/powerpc/include/asm/vdso_datapage.h b/arch/powerpc/include/asm/vdso_datapage.h
index f01393224b52..13c2c283e178 100644
--- a/arch/powerpc/include/asm/vdso_datapage.h
+++ b/arch/powerpc/include/asm/vdso_datapage.h
@@ -39,6 +39,7 @@
 #ifndef __ASSEMBLY__
 
 #include <linux/unistd.h>
+#include <linux/time.h>
 
 #define SYSCALL_MAP_SIZE      ((__NR_syscalls + 31) / 32)
 
@@ -83,6 +84,7 @@ struct vdso_data {
 	__u32 icache_log_block_size;		/* L1 i-cache log block size */
 	__s32 wtom_clock_sec;			/* Wall to monotonic clock */
 	__s32 wtom_clock_nsec;
+	struct timespec stamp_xtime;	/* xtime as at tb_orig_stamp */
    	__u32 syscall_map_64[SYSCALL_MAP_SIZE]; /* map of syscalls  */
    	__u32 syscall_map_32[SYSCALL_MAP_SIZE]; /* map of syscalls */
 };
@@ -102,6 +104,7 @@ struct vdso_data {
 	__u32 tz_dsttime;		/* Type of dst correction	0x5C */
 	__s32 wtom_clock_sec;			/* Wall to monotonic clock */
 	__s32 wtom_clock_nsec;
+	struct timespec stamp_xtime;	/* xtime as at tb_orig_stamp */
    	__u32 syscall_map_32[SYSCALL_MAP_SIZE]; /* map of syscalls */
 	__u32 dcache_block_size;	/* L1 d-cache block size     */
 	__u32 icache_block_size;	/* L1 i-cache block size     */
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 75c5dd0138fd..050abfd5c17c 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -306,6 +306,7 @@ int main(void)
 	DEFINE(CFG_SYSCALL_MAP32, offsetof(struct vdso_data, syscall_map_32));
 	DEFINE(WTOM_CLOCK_SEC, offsetof(struct vdso_data, wtom_clock_sec));
 	DEFINE(WTOM_CLOCK_NSEC, offsetof(struct vdso_data, wtom_clock_nsec));
+	DEFINE(STAMP_XTIME, offsetof(struct vdso_data, stamp_xtime));
 	DEFINE(CFG_ICACHE_BLOCKSZ, offsetof(struct vdso_data, icache_block_size));
 	DEFINE(CFG_DCACHE_BLOCKSZ, offsetof(struct vdso_data, dcache_block_size));
 	DEFINE(CFG_ICACHE_LOGBLOCKSZ, offsetof(struct vdso_data, icache_log_block_size));
diff --git a/arch/powerpc/kernel/dma.c b/arch/powerpc/kernel/dma.c
index 1562daf8839a..1c5c8a6fc129 100644
--- a/arch/powerpc/kernel/dma.c
+++ b/arch/powerpc/kernel/dma.c
@@ -75,6 +75,7 @@ static int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl,
 	for_each_sg(sgl, sg, nents, i) {
 		sg->dma_address = sg_phys(sg) + get_dma_direct_offset(dev);
 		sg->dma_length = sg->length;
+		__dma_sync_page(sg_page(sg), sg->offset, sg->length, direction);
 	}
 
 	return nents;
@@ -119,6 +120,26 @@ static inline void dma_direct_unmap_page(struct device *dev,
 {
 }
 
+#ifdef CONFIG_NOT_COHERENT_CACHE
+static inline void dma_direct_sync_sg(struct device *dev,
+		struct scatterlist *sgl, int nents,
+		enum dma_data_direction direction)
+{
+	struct scatterlist *sg;
+	int i;
+
+	for_each_sg(sgl, sg, nents, i)
+		__dma_sync_page(sg_page(sg), sg->offset, sg->length, direction);
+}
+
+static inline void dma_direct_sync_single_range(struct device *dev,
+		dma_addr_t dma_handle, unsigned long offset, size_t size,
+		enum dma_data_direction direction)
+{
+	__dma_sync(bus_to_virt(dma_handle+offset), size, direction);
+}
+#endif
+
 struct dma_mapping_ops dma_direct_ops = {
 	.alloc_coherent	= dma_direct_alloc_coherent,
 	.free_coherent	= dma_direct_free_coherent,
@@ -127,5 +148,11 @@ struct dma_mapping_ops dma_direct_ops = {
 	.dma_supported	= dma_direct_dma_supported,
 	.map_page	= dma_direct_map_page,
 	.unmap_page	= dma_direct_unmap_page,
+#ifdef CONFIG_NOT_COHERENT_CACHE
+	.sync_single_range_for_cpu 	= dma_direct_sync_single_range,
+	.sync_single_range_for_device 	= dma_direct_sync_single_range,
+	.sync_sg_for_cpu 		= dma_direct_sync_sg,
+	.sync_sg_for_device 		= dma_direct_sync_sg,
+#endif
 };
 EXPORT_SYMBOL(dma_direct_ops);
diff --git a/arch/powerpc/kernel/ftrace.c b/arch/powerpc/kernel/ftrace.c
index f4b006ed0ab1..3271cd698e4c 100644
--- a/arch/powerpc/kernel/ftrace.c
+++ b/arch/powerpc/kernel/ftrace.c
@@ -9,22 +9,30 @@
 
 #include <linux/spinlock.h>
 #include <linux/hardirq.h>
+#include <linux/uaccess.h>
+#include <linux/module.h>
 #include <linux/ftrace.h>
 #include <linux/percpu.h>
 #include <linux/init.h>
 #include <linux/list.h>
 
 #include <asm/cacheflush.h>
+#include <asm/code-patching.h>
 #include <asm/ftrace.h>
 
+#if 0
+#define DEBUGP printk
+#else
+#define DEBUGP(fmt , ...)	do { } while (0)
+#endif
 
-static unsigned int ftrace_nop = 0x60000000;
+static unsigned int ftrace_nop = PPC_NOP_INSTR;
 
 #ifdef CONFIG_PPC32
 # define GET_ADDR(addr) addr
 #else
 /* PowerPC64's functions are data that points to the functions */
-# define GET_ADDR(addr) *(unsigned long *)addr
+# define GET_ADDR(addr) (*(unsigned long *)addr)
 #endif
 
 
@@ -33,12 +41,12 @@ static unsigned int ftrace_calc_offset(long ip, long addr)
 	return (int)(addr - ip);
 }
 
-unsigned char *ftrace_nop_replace(void)
+static unsigned char *ftrace_nop_replace(void)
 {
 	return (char *)&ftrace_nop;
 }
 
-unsigned char *ftrace_call_replace(unsigned long ip, unsigned long addr)
+static unsigned char *ftrace_call_replace(unsigned long ip, unsigned long addr)
 {
 	static unsigned int op;
 
@@ -68,49 +76,434 @@ unsigned char *ftrace_call_replace(unsigned long ip, unsigned long addr)
 # define _ASM_PTR	" .long "
 #endif
 
-int
+static int
 ftrace_modify_code(unsigned long ip, unsigned char *old_code,
 		   unsigned char *new_code)
 {
-	unsigned replaced;
-	unsigned old = *(unsigned *)old_code;
-	unsigned new = *(unsigned *)new_code;
-	int faulted = 0;
+	unsigned char replaced[MCOUNT_INSN_SIZE];
 
 	/*
 	 * Note: Due to modules and __init, code can
 	 *  disappear and change, we need to protect against faulting
-	 *  as well as code changing.
+	 *  as well as code changing. We do this by using the
+	 *  probe_kernel_* functions.
 	 *
 	 * No real locking needed, this code is run through
-	 * kstop_machine.
+	 * kstop_machine, or before SMP starts.
 	 */
-	asm volatile (
-		"1: lwz		%1, 0(%2)\n"
-		"   cmpw	%1, %5\n"
-		"   bne		2f\n"
-		"   stwu	%3, 0(%2)\n"
-		"2:\n"
-		".section .fixup, \"ax\"\n"
-		"3:	li %0, 1\n"
-		"	b 2b\n"
-		".previous\n"
-		".section __ex_table,\"a\"\n"
-		_ASM_ALIGN "\n"
-		_ASM_PTR "1b, 3b\n"
-		".previous"
-		: "=r"(faulted), "=r"(replaced)
-		: "r"(ip), "r"(new),
-		  "0"(faulted), "r"(old)
-		: "memory");
-
-	if (replaced != old && replaced != new)
-		faulted = 2;
-
-	if (!faulted)
-		flush_icache_range(ip, ip + 8);
-
-	return faulted;
+
+	/* read the text we want to modify */
+	if (probe_kernel_read(replaced, (void *)ip, MCOUNT_INSN_SIZE))
+		return -EFAULT;
+
+	/* Make sure it is what we expect it to be */
+	if (memcmp(replaced, old_code, MCOUNT_INSN_SIZE) != 0)
+		return -EINVAL;
+
+	/* replace the text with the new text */
+	if (probe_kernel_write((void *)ip, new_code, MCOUNT_INSN_SIZE))
+		return -EPERM;
+
+	flush_icache_range(ip, ip + 8);
+
+	return 0;
+}
+
+/*
+ * Helper functions that are the same for both PPC64 and PPC32.
+ */
+static int test_24bit_addr(unsigned long ip, unsigned long addr)
+{
+	long diff;
+
+	/*
+	 * Can we get to addr from ip in 24 bits?
+	 *  (26 really, since we mulitply by 4 for 4 byte alignment)
+	 */
+	diff = addr - ip;
+
+	/*
+	 * Return true if diff is less than 1 << 25
+	 *  and greater than -1 << 26.
+	 */
+	return (diff < (1 << 25)) && (diff > (-1 << 26));
+}
+
+static int is_bl_op(unsigned int op)
+{
+	return (op & 0xfc000003) == 0x48000001;
+}
+
+static int test_offset(unsigned long offset)
+{
+	return (offset + 0x2000000 > 0x3ffffff) || ((offset & 3) != 0);
+}
+
+static unsigned long find_bl_target(unsigned long ip, unsigned int op)
+{
+	static int offset;
+
+	offset = (op & 0x03fffffc);
+	/* make it signed */
+	if (offset & 0x02000000)
+		offset |= 0xfe000000;
+
+	return ip + (long)offset;
+}
+
+static unsigned int branch_offset(unsigned long offset)
+{
+	/* return "bl ip+offset" */
+	return 0x48000001 | (offset & 0x03fffffc);
+}
+
+#ifdef CONFIG_PPC64
+static int
+__ftrace_make_nop(struct module *mod,
+		  struct dyn_ftrace *rec, unsigned long addr)
+{
+	unsigned char replaced[MCOUNT_INSN_SIZE * 2];
+	unsigned int *op = (unsigned *)&replaced;
+	unsigned char jmp[8];
+	unsigned long *ptr = (unsigned long *)&jmp;
+	unsigned long ip = rec->ip;
+	unsigned long tramp;
+	int offset;
+
+	/* read where this goes */
+	if (probe_kernel_read(replaced, (void *)ip, MCOUNT_INSN_SIZE))
+		return -EFAULT;
+
+	/* Make sure that that this is still a 24bit jump */
+	if (!is_bl_op(*op)) {
+		printk(KERN_ERR "Not expected bl: opcode is %x\n", *op);
+		return -EINVAL;
+	}
+
+	/* lets find where the pointer goes */
+	tramp = find_bl_target(ip, *op);
+
+	/*
+	 * On PPC64 the trampoline looks like:
+	 * 0x3d, 0x82, 0x00, 0x00,    addis   r12,r2, <high>
+	 * 0x39, 0x8c, 0x00, 0x00,    addi    r12,r12, <low>
+	 *   Where the bytes 2,3,6 and 7 make up the 32bit offset
+	 *   to the TOC that holds the pointer.
+	 *   to jump to.
+	 * 0xf8, 0x41, 0x00, 0x28,    std     r2,40(r1)
+	 * 0xe9, 0x6c, 0x00, 0x20,    ld      r11,32(r12)
+	 *   The actually address is 32 bytes from the offset
+	 *   into the TOC.
+	 * 0xe8, 0x4c, 0x00, 0x28,    ld      r2,40(r12)
+	 */
+
+	DEBUGP("ip:%lx jumps to %lx r2: %lx", ip, tramp, mod->arch.toc);
+
+	/* Find where the trampoline jumps to */
+	if (probe_kernel_read(jmp, (void *)tramp, 8)) {
+		printk(KERN_ERR "Failed to read %lx\n", tramp);
+		return -EFAULT;
+	}
+
+	DEBUGP(" %08x %08x",
+	       (unsigned)(*ptr >> 32),
+	       (unsigned)*ptr);
+
+	offset = (unsigned)jmp[2] << 24 |
+		(unsigned)jmp[3] << 16 |
+		(unsigned)jmp[6] << 8 |
+		(unsigned)jmp[7];
+
+	DEBUGP(" %x ", offset);
+
+	/* get the address this jumps too */
+	tramp = mod->arch.toc + offset + 32;
+	DEBUGP("toc: %lx", tramp);
+
+	if (probe_kernel_read(jmp, (void *)tramp, 8)) {
+		printk(KERN_ERR "Failed to read %lx\n", tramp);
+		return -EFAULT;
+	}
+
+	DEBUGP(" %08x %08x\n",
+	       (unsigned)(*ptr >> 32),
+	       (unsigned)*ptr);
+
+	/* This should match what was called */
+	if (*ptr != GET_ADDR(addr)) {
+		printk(KERN_ERR "addr does not match %lx\n", *ptr);
+		return -EINVAL;
+	}
+
+	/*
+	 * We want to nop the line, but the next line is
+	 *  0xe8, 0x41, 0x00, 0x28   ld r2,40(r1)
+	 * This needs to be turned to a nop too.
+	 */
+	if (probe_kernel_read(replaced, (void *)(ip+4), MCOUNT_INSN_SIZE))
+		return -EFAULT;
+
+	if (*op != 0xe8410028) {
+		printk(KERN_ERR "Next line is not ld! (%08x)\n", *op);
+		return -EINVAL;
+	}
+
+	/*
+	 * Milton Miller pointed out that we can not blindly do nops.
+	 * If a task was preempted when calling a trace function,
+	 * the nops will remove the way to restore the TOC in r2
+	 * and the r2 TOC will get corrupted.
+	 */
+
+	/*
+	 * Replace:
+	 *   bl <tramp>  <==== will be replaced with "b 1f"
+	 *   ld r2,40(r1)
+	 *  1:
+	 */
+	op[0] = 0x48000008;	/* b +8 */
+
+	if (probe_kernel_write((void *)ip, replaced, MCOUNT_INSN_SIZE))
+		return -EPERM;
+
+	return 0;
+}
+
+#else /* !PPC64 */
+static int
+__ftrace_make_nop(struct module *mod,
+		  struct dyn_ftrace *rec, unsigned long addr)
+{
+	unsigned char replaced[MCOUNT_INSN_SIZE];
+	unsigned int *op = (unsigned *)&replaced;
+	unsigned char jmp[8];
+	unsigned int *ptr = (unsigned int *)&jmp;
+	unsigned long ip = rec->ip;
+	unsigned long tramp;
+	int offset;
+
+	if (probe_kernel_read(replaced, (void *)ip, MCOUNT_INSN_SIZE))
+		return -EFAULT;
+
+	/* Make sure that that this is still a 24bit jump */
+	if (!is_bl_op(*op)) {
+		printk(KERN_ERR "Not expected bl: opcode is %x\n", *op);
+		return -EINVAL;
+	}
+
+	/* lets find where the pointer goes */
+	tramp = find_bl_target(ip, *op);
+
+	/*
+	 * On PPC32 the trampoline looks like:
+	 * lis r11,sym@ha
+	 * addi r11,r11,sym@l
+	 * mtctr r11
+	 * bctr
+	 */
+
+	DEBUGP("ip:%lx jumps to %lx", ip, tramp);
+
+	/* Find where the trampoline jumps to */
+	if (probe_kernel_read(jmp, (void *)tramp, 8)) {
+		printk(KERN_ERR "Failed to read %lx\n", tramp);
+		return -EFAULT;
+	}
+
+	DEBUGP(" %08x %08x ", ptr[0], ptr[1]);
+
+	tramp = (ptr[1] & 0xffff) |
+		((ptr[0] & 0xffff) << 16);
+	if (tramp & 0x8000)
+		tramp -= 0x10000;
+
+	DEBUGP(" %x ", tramp);
+
+	if (tramp != addr) {
+		printk(KERN_ERR
+		       "Trampoline location %08lx does not match addr\n",
+		       tramp);
+		return -EINVAL;
+	}
+
+	op[0] = PPC_NOP_INSTR;
+
+	if (probe_kernel_write((void *)ip, replaced, MCOUNT_INSN_SIZE))
+		return -EPERM;
+
+	return 0;
+}
+#endif /* PPC64 */
+
+int ftrace_make_nop(struct module *mod,
+		    struct dyn_ftrace *rec, unsigned long addr)
+{
+	unsigned char *old, *new;
+	unsigned long ip = rec->ip;
+
+	/*
+	 * If the calling address is more that 24 bits away,
+	 * then we had to use a trampoline to make the call.
+	 * Otherwise just update the call site.
+	 */
+	if (test_24bit_addr(ip, addr)) {
+		/* within range */
+		old = ftrace_call_replace(ip, addr);
+		new = ftrace_nop_replace();
+		return ftrace_modify_code(ip, old, new);
+	}
+
+	/*
+	 * Out of range jumps are called from modules.
+	 * We should either already have a pointer to the module
+	 * or it has been passed in.
+	 */
+	if (!rec->arch.mod) {
+		if (!mod) {
+			printk(KERN_ERR "No module loaded addr=%lx\n",
+			       addr);
+			return -EFAULT;
+		}
+		rec->arch.mod = mod;
+	} else if (mod) {
+		if (mod != rec->arch.mod) {
+			printk(KERN_ERR
+			       "Record mod %p not equal to passed in mod %p\n",
+			       rec->arch.mod, mod);
+			return -EINVAL;
+		}
+		/* nothing to do if mod == rec->arch.mod */
+	} else
+		mod = rec->arch.mod;
+
+	return __ftrace_make_nop(mod, rec, addr);
+
+}
+
+#ifdef CONFIG_PPC64
+static int
+__ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
+{
+	unsigned char replaced[MCOUNT_INSN_SIZE * 2];
+	unsigned int *op = (unsigned *)&replaced;
+	unsigned long ip = rec->ip;
+	unsigned long offset;
+
+	/* read where this goes */
+	if (probe_kernel_read(replaced, (void *)ip, MCOUNT_INSN_SIZE * 2))
+		return -EFAULT;
+
+	/*
+	 * It should be pointing to two nops or
+	 *  b +8; ld r2,40(r1)
+	 */
+	if (((op[0] != 0x48000008) || (op[1] != 0xe8410028)) &&
+	    ((op[0] != PPC_NOP_INSTR) || (op[1] != PPC_NOP_INSTR))) {
+		printk(KERN_ERR "Expected NOPs but have %x %x\n", op[0], op[1]);
+		return -EINVAL;
+	}
+
+	/* If we never set up a trampoline to ftrace_caller, then bail */
+	if (!rec->arch.mod->arch.tramp) {
+		printk(KERN_ERR "No ftrace trampoline\n");
+		return -EINVAL;
+	}
+
+	/* now calculate a jump to the ftrace caller trampoline */
+	offset = rec->arch.mod->arch.tramp - ip;
+
+	if (test_offset(offset)) {
+		printk(KERN_ERR "REL24 %li out of range!\n",
+		       (long int)offset);
+		return -EINVAL;
+	}
+
+	/* Set to "bl addr" */
+	op[0] = branch_offset(offset);
+	/* ld r2,40(r1) */
+	op[1] = 0xe8410028;
+
+	DEBUGP("write to %lx\n", rec->ip);
+
+	if (probe_kernel_write((void *)ip, replaced, MCOUNT_INSN_SIZE * 2))
+		return -EPERM;
+
+	return 0;
+}
+#else
+static int
+__ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
+{
+	unsigned char replaced[MCOUNT_INSN_SIZE];
+	unsigned int *op = (unsigned *)&replaced;
+	unsigned long ip = rec->ip;
+	unsigned long offset;
+
+	/* read where this goes */
+	if (probe_kernel_read(replaced, (void *)ip, MCOUNT_INSN_SIZE))
+		return -EFAULT;
+
+	/* It should be pointing to a nop */
+	if (op[0] != PPC_NOP_INSTR) {
+		printk(KERN_ERR "Expected NOP but have %x\n", op[0]);
+		return -EINVAL;
+	}
+
+	/* If we never set up a trampoline to ftrace_caller, then bail */
+	if (!rec->arch.mod->arch.tramp) {
+		printk(KERN_ERR "No ftrace trampoline\n");
+		return -EINVAL;
+	}
+
+	/* now calculate a jump to the ftrace caller trampoline */
+	offset = rec->arch.mod->arch.tramp - ip;
+
+	if (test_offset(offset)) {
+		printk(KERN_ERR "REL24 %li out of range!\n",
+		       (long int)offset);
+		return -EINVAL;
+	}
+
+	/* Set to "bl addr" */
+	op[0] = branch_offset(offset);
+
+	DEBUGP("write to %lx\n", rec->ip);
+
+	if (probe_kernel_write((void *)ip, replaced, MCOUNT_INSN_SIZE))
+		return -EPERM;
+
+	return 0;
+}
+#endif /* CONFIG_PPC64 */
+
+int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
+{
+	unsigned char *old, *new;
+	unsigned long ip = rec->ip;
+
+	/*
+	 * If the calling address is more that 24 bits away,
+	 * then we had to use a trampoline to make the call.
+	 * Otherwise just update the call site.
+	 */
+	if (test_24bit_addr(ip, addr)) {
+		/* within range */
+		old = ftrace_nop_replace();
+		new = ftrace_call_replace(ip, addr);
+		return ftrace_modify_code(ip, old, new);
+	}
+
+	/*
+	 * Out of range jumps are called from modules.
+	 * Being that we are converting from nop, it had better
+	 * already have a module defined.
+	 */
+	if (!rec->arch.mod) {
+		printk(KERN_ERR "No module loaded\n");
+		return -EINVAL;
+	}
+
+	return __ftrace_make_call(rec, addr);
 }
 
 int ftrace_update_ftrace_func(ftrace_func_t func)
@@ -128,10 +521,10 @@ int ftrace_update_ftrace_func(ftrace_func_t func)
 
 int __init ftrace_dyn_arch_init(void *data)
 {
-	/* This is running in kstop_machine */
+	/* caller expects data to be zero */
+	unsigned long *p = data;
 
-	ftrace_mcount_set(data);
+	*p = 0;
 
 	return 0;
 }
-
diff --git a/arch/powerpc/kernel/head_fsl_booke.S b/arch/powerpc/kernel/head_fsl_booke.S
index 590304c24dad..9a4639c459e6 100644
--- a/arch/powerpc/kernel/head_fsl_booke.S
+++ b/arch/powerpc/kernel/head_fsl_booke.S
@@ -92,6 +92,7 @@ _ENTRY(_start);
  * if needed
  */
 
+_ENTRY(__early_start)
 /* 1. Find the index of the entry we're executing in */
 	bl	invstr				/* Find our address */
 invstr:	mflr	r6				/* Make it accessible */
@@ -235,36 +236,40 @@ skpinv:	addi	r6,r6,1				/* Increment */
 	tlbivax 0,r9
 	TLBSYNC
 
+/* The mapping only needs to be cache-coherent on SMP */
+#ifdef CONFIG_SMP
+#define M_IF_SMP	MAS2_M
+#else
+#define M_IF_SMP	0
+#endif
+
 /* 6. Setup KERNELBASE mapping in TLB1[0] */
 	lis	r6,0x1000		/* Set MAS0(TLBSEL) = TLB1(1), ESEL = 0 */
 	mtspr	SPRN_MAS0,r6
 	lis	r6,(MAS1_VALID|MAS1_IPROT)@h
 	ori	r6,r6,(MAS1_TSIZE(BOOKE_PAGESZ_64M))@l
 	mtspr	SPRN_MAS1,r6
-	li	r7,0
-	lis	r6,PAGE_OFFSET@h
-	ori	r6,r6,PAGE_OFFSET@l
-	rlwimi	r6,r7,0,20,31
+	lis	r6,MAS2_VAL(PAGE_OFFSET, BOOKE_PAGESZ_64M, M_IF_SMP)@h
+	ori	r6,r6,MAS2_VAL(PAGE_OFFSET, BOOKE_PAGESZ_64M, M_IF_SMP)@l
 	mtspr	SPRN_MAS2,r6
 	mtspr	SPRN_MAS3,r8
 	tlbwe
 
 /* 7. Jump to KERNELBASE mapping */
-	lis	r6,KERNELBASE@h
-	ori	r6,r6,KERNELBASE@l
-	rlwimi	r6,r7,0,20,31
+	lis	r6,(KERNELBASE & ~0xfff)@h
+	ori	r6,r6,(KERNELBASE & ~0xfff)@l
 	lis	r7,MSR_KERNEL@h
 	ori	r7,r7,MSR_KERNEL@l
 	bl	1f			/* Find our address */
 1:	mflr	r9
 	rlwimi	r6,r9,0,20,31
-	addi	r6,r6,24
+	addi	r6,r6,(2f - 1b)
 	mtspr	SPRN_SRR0,r6
 	mtspr	SPRN_SRR1,r7
 	rfi				/* start execution out of TLB1[0] entry */
 
 /* 8. Clear out the temp mapping */
-	lis	r7,0x1000	/* Set MAS0(TLBSEL) = 1 */
+2:	lis	r7,0x1000	/* Set MAS0(TLBSEL) = 1 */
 	rlwimi	r7,r5,16,4,15	/* Setup MAS0 = TLBSEL | ESEL(r5) */
 	mtspr	SPRN_MAS0,r7
 	tlbre
@@ -344,6 +349,15 @@ skpinv:	addi	r6,r6,1				/* Increment */
 	mtspr	SPRN_DBSR,r2
 #endif
 
+#ifdef CONFIG_SMP
+	/* Check to see if we're the second processor, and jump
+	 * to the secondary_start code if so
+	 */
+	mfspr	r24,SPRN_PIR
+	cmpwi	r24,0
+	bne	__secondary_start
+#endif
+
 	/*
 	 * This is where the main kernel code starts.
 	 */
@@ -685,12 +699,13 @@ interrupt_base:
 	/* SPE Floating Point Data */
 #ifdef CONFIG_SPE
 	EXCEPTION(0x2030, SPEFloatingPointData, SPEFloatingPointException, EXC_XFER_EE);
-#else
-	EXCEPTION(0x2040, SPEFloatingPointData, unknown_exception, EXC_XFER_EE)
-#endif /* CONFIG_SPE */
 
 	/* SPE Floating Point Round */
+	EXCEPTION(0x2050, SPEFloatingPointRound, SPEFloatingPointRoundException, EXC_XFER_EE)
+#else
+	EXCEPTION(0x2040, SPEFloatingPointData, unknown_exception, EXC_XFER_EE)
 	EXCEPTION(0x2050, SPEFloatingPointRound, unknown_exception, EXC_XFER_EE)
+#endif /* CONFIG_SPE */
 
 	/* Performance Monitor */
 	EXCEPTION(0x2060, PerformanceMonitor, performance_monitor_exception, EXC_XFER_STD)
@@ -735,6 +750,9 @@ finish_tlb_load:
 #else
 	rlwimi	r12, r11, 26, 27, 31	/* extract WIMGE from pte */
 #endif
+#ifdef CONFIG_SMP
+	ori	r12, r12, MAS2_M
+#endif
 	mtspr	SPRN_MAS2, r12
 
 	li	r10, (_PAGE_HWEXEC | _PAGE_PRESENT)
@@ -746,7 +764,7 @@ finish_tlb_load:
 	iseleq	r12, r12, r10
 	
 #ifdef CONFIG_PTE_64BIT
-2:	rlwimi	r12, r13, 24, 0, 7	/* grab RPN[32:39] */
+	rlwimi	r12, r13, 24, 0, 7	/* grab RPN[32:39] */
 	rlwimi	r12, r11, 24, 8, 19	/* grab RPN[40:51] */
 	mtspr	SPRN_MAS3, r12
 BEGIN_FTR_SECTION
@@ -754,7 +772,7 @@ BEGIN_FTR_SECTION
 	mtspr	SPRN_MAS7, r10
 END_FTR_SECTION_IFSET(CPU_FTR_BIG_PHYS)
 #else
-2:	rlwimi	r11, r12, 0, 20, 31	/* Extract RPN from PTE and merge with perms */
+	rlwimi	r11, r12, 0, 20, 31	/* Extract RPN from PTE and merge with perms */
 	mtspr	SPRN_MAS3, r11
 #endif
 #ifdef CONFIG_E200
@@ -1037,6 +1055,63 @@ _GLOBAL(flush_dcache_L1)
 
 	blr
 
+#ifdef CONFIG_SMP
+/* When we get here, r24 needs to hold the CPU # */
+	.globl __secondary_start
+__secondary_start:
+	lis	r3,__secondary_hold_acknowledge@h
+	ori	r3,r3,__secondary_hold_acknowledge@l
+	stw	r24,0(r3)
+
+	li	r3,0
+	mr	r4,r24		/* Why? */
+	bl	call_setup_cpu
+
+	lis	r3,tlbcam_index@ha
+	lwz	r3,tlbcam_index@l(r3)
+	mtctr	r3
+	li	r26,0		/* r26 safe? */
+
+	/* Load each CAM entry */
+1:	mr	r3,r26
+	bl	loadcam_entry
+	addi	r26,r26,1
+	bdnz	1b
+
+	/* get current_thread_info and current */
+	lis	r1,secondary_ti@ha
+	lwz	r1,secondary_ti@l(r1)
+	lwz	r2,TI_TASK(r1)
+
+	/* stack */
+	addi	r1,r1,THREAD_SIZE-STACK_FRAME_OVERHEAD
+	li	r0,0
+	stw	r0,0(r1)
+
+	/* ptr to current thread */
+	addi	r4,r2,THREAD	/* address of our thread_struct */
+	mtspr	SPRN_SPRG3,r4
+
+	/* Setup the defaults for TLB entries */
+	li	r4,(MAS4_TSIZED(BOOKE_PAGESZ_4K))@l
+	mtspr	SPRN_MAS4,r4
+
+	/* Jump to start_secondary */
+	lis	r4,MSR_KERNEL@h
+	ori	r4,r4,MSR_KERNEL@l
+	lis	r3,start_secondary@h
+	ori	r3,r3,start_secondary@l
+	mtspr	SPRN_SRR0,r3
+	mtspr	SPRN_SRR1,r4
+	sync
+	rfi
+	sync
+
+	.globl __secondary_hold_acknowledge
+__secondary_hold_acknowledge:
+	.long	-1
+#endif
+
 /*
  * We put a few things here that have to be page-aligned. This stuff
  * goes at the beginning of the data segment, which is page-aligned.
diff --git a/arch/powerpc/kernel/ibmebus.c b/arch/powerpc/kernel/ibmebus.c
index 64299d28f364..6e3f62493659 100644
--- a/arch/powerpc/kernel/ibmebus.c
+++ b/arch/powerpc/kernel/ibmebus.c
@@ -47,7 +47,7 @@
 #include <asm/abs_addr.h>
 
 static struct device ibmebus_bus_device = { /* fake "parent" device */
-	.bus_id = "ibmebus",
+	.init_name = "ibmebus",
 };
 
 struct bus_type ibmebus_bus_type;
@@ -231,6 +231,7 @@ void ibmebus_free_irq(u32 ist, void *dev_id)
 	unsigned int irq = irq_find_mapping(NULL, ist);
 
 	free_irq(irq, dev_id);
+	irq_dispose_mapping(irq);
 }
 EXPORT_SYMBOL(ibmebus_free_irq);
 
diff --git a/arch/powerpc/kernel/idle.c b/arch/powerpc/kernel/idle.c
index 31982d05d81a..88d9c1d5e5fb 100644
--- a/arch/powerpc/kernel/idle.c
+++ b/arch/powerpc/kernel/idle.c
@@ -69,10 +69,15 @@ void cpu_idle(void)
 				smp_mb();
 				local_irq_disable();
 
+				/* Don't trace irqs off for idle */
+				stop_critical_timings();
+
 				/* check again after disabling irqs */
 				if (!need_resched() && !cpu_should_die())
 					ppc_md.power_save();
 
+				start_critical_timings();
+
 				local_irq_enable();
 				set_thread_flag(TIF_POLLING_NRFLAG);
 
diff --git a/arch/powerpc/kernel/module_32.c b/arch/powerpc/kernel/module_32.c
index 2df91a03462a..f832773fc28e 100644
--- a/arch/powerpc/kernel/module_32.c
+++ b/arch/powerpc/kernel/module_32.c
@@ -22,6 +22,7 @@
 #include <linux/fs.h>
 #include <linux/string.h>
 #include <linux/kernel.h>
+#include <linux/ftrace.h>
 #include <linux/cache.h>
 #include <linux/bug.h>
 #include <linux/sort.h>
@@ -53,6 +54,9 @@ static unsigned int count_relocs(const Elf32_Rela *rela, unsigned int num)
 			r_addend = rela[i].r_addend;
 		}
 
+#ifdef CONFIG_DYNAMIC_FTRACE
+	_count_relocs++;	/* add one for ftrace_caller */
+#endif
 	return _count_relocs;
 }
 
@@ -306,5 +310,11 @@ int apply_relocate_add(Elf32_Shdr *sechdrs,
 			return -ENOEXEC;
 		}
 	}
+#ifdef CONFIG_DYNAMIC_FTRACE
+	module->arch.tramp =
+		do_plt_call(module->module_core,
+			    (unsigned long)ftrace_caller,
+			    sechdrs, module);
+#endif
 	return 0;
 }
diff --git a/arch/powerpc/kernel/module_64.c b/arch/powerpc/kernel/module_64.c
index 1af2377e4992..8992b031a7b6 100644
--- a/arch/powerpc/kernel/module_64.c
+++ b/arch/powerpc/kernel/module_64.c
@@ -20,6 +20,7 @@
 #include <linux/moduleloader.h>
 #include <linux/err.h>
 #include <linux/vmalloc.h>
+#include <linux/ftrace.h>
 #include <linux/bug.h>
 #include <asm/module.h>
 #include <asm/firmware.h>
@@ -163,6 +164,11 @@ static unsigned long get_stubs_size(const Elf64_Ehdr *hdr,
 		}
 	}
 
+#ifdef CONFIG_DYNAMIC_FTRACE
+	/* make the trampoline to the ftrace_caller */
+	relocs++;
+#endif
+
 	DEBUGP("Looks like a total of %lu stubs, max\n", relocs);
 	return relocs * sizeof(struct ppc64_stub_entry);
 }
@@ -441,5 +447,12 @@ int apply_relocate_add(Elf64_Shdr *sechdrs,
 		}
 	}
 
+#ifdef CONFIG_DYNAMIC_FTRACE
+	me->arch.toc = my_r2(sechdrs, me);
+	me->arch.tramp = stub_for_addr(sechdrs,
+				       (unsigned long)ftrace_caller,
+				       me);
+#endif
+
 	return 0;
 }
diff --git a/arch/powerpc/kernel/of_device.c b/arch/powerpc/kernel/of_device.c
index f3c9cae01dd5..fa983a59c4ce 100644
--- a/arch/powerpc/kernel/of_device.c
+++ b/arch/powerpc/kernel/of_device.c
@@ -14,7 +14,6 @@ static void of_device_make_bus_id(struct of_device *dev)
 {
 	static atomic_t bus_no_reg_magic;
 	struct device_node *node = dev->node;
-	char *name = dev->dev.bus_id;
 	const u32 *reg;
 	u64 addr;
 	int magic;
@@ -27,14 +26,12 @@ static void of_device_make_bus_id(struct of_device *dev)
 	reg = of_get_property(node, "dcr-reg", NULL);
 	if (reg) {
 #ifdef CONFIG_PPC_DCR_NATIVE
-		snprintf(name, BUS_ID_SIZE, "d%x.%s",
-			 *reg, node->name);
+		dev_set_name(&dev->dev, "d%x.%s", *reg, node->name);
 #else /* CONFIG_PPC_DCR_NATIVE */
 		addr = of_translate_dcr_address(node, *reg, NULL);
 		if (addr != OF_BAD_ADDR) {
-			snprintf(name, BUS_ID_SIZE,
-				 "D%llx.%s", (unsigned long long)addr,
-				 node->name);
+			dev_set_name(&dev->dev, "D%llx.%s",
+				     (unsigned long long)addr, node->name);
 			return;
 		}
 #endif /* !CONFIG_PPC_DCR_NATIVE */
@@ -48,9 +45,8 @@ static void of_device_make_bus_id(struct of_device *dev)
 	if (reg) {
 		addr = of_translate_address(node, reg);
 		if (addr != OF_BAD_ADDR) {
-			snprintf(name, BUS_ID_SIZE,
-				 "%llx.%s", (unsigned long long)addr,
-				 node->name);
+			dev_set_name(&dev->dev, "%llx.%s",
+				     (unsigned long long)addr, node->name);
 			return;
 		}
 	}
@@ -60,7 +56,7 @@ static void of_device_make_bus_id(struct of_device *dev)
 	 * counter (and pray...)
 	 */
 	magic = atomic_add_return(1, &bus_no_reg_magic);
-	snprintf(name, BUS_ID_SIZE, "%s.%d", node->name, magic - 1);
+	dev_set_name(&dev->dev, "%s.%d", node->name, magic - 1);
 }
 
 struct of_device *of_device_alloc(struct device_node *np,
@@ -80,7 +76,7 @@ struct of_device *of_device_alloc(struct device_node *np,
 	dev->dev.archdata.of_node = np;
 
 	if (bus_id)
-		strlcpy(dev->dev.bus_id, bus_id, BUS_ID_SIZE);
+		dev_set_name(&dev->dev, bus_id);
 	else
 		of_device_make_bus_id(dev);
 
diff --git a/arch/powerpc/kernel/paca.c b/arch/powerpc/kernel/paca.c
index 48a347133f41..c744b327bcab 100644
--- a/arch/powerpc/kernel/paca.c
+++ b/arch/powerpc/kernel/paca.c
@@ -37,6 +37,7 @@ struct lppaca lppaca[] = {
 		.end_of_quantum = 0xfffffffffffffffful,
 		.slb_count = 64,
 		.vmxregs_in_use = 0,
+		.page_ins = 0,
 	},
 };
 
diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c
index f36936d9fda3..91c3f52e33a8 100644
--- a/arch/powerpc/kernel/pci-common.c
+++ b/arch/powerpc/kernel/pci-common.c
@@ -37,13 +37,7 @@
 #include <asm/machdep.h>
 #include <asm/ppc-pci.h>
 #include <asm/firmware.h>
-
-#ifdef DEBUG
-#include <asm/udbg.h>
-#define DBG(fmt...) printk(fmt)
-#else
-#define DBG(fmt...)
-#endif
+#include <asm/eeh.h>
 
 static DEFINE_SPINLOCK(hose_spinlock);
 
@@ -53,8 +47,9 @@ static int global_phb_number;		/* Global phb counter */
 /* ISA Memory physical address */
 resource_size_t isa_mem_base;
 
-/* Default PCI flags is 0 */
-unsigned int ppc_pci_flags;
+/* Default PCI flags is 0 on ppc32, modified at boot on ppc64 */
+unsigned int ppc_pci_flags = 0;
+
 
 static struct dma_mapping_ops *pci_dma_ops;
 
@@ -208,26 +203,6 @@ char __devinit *pcibios_setup(char *str)
 	return str;
 }
 
-void __devinit pcibios_setup_new_device(struct pci_dev *dev)
-{
-	struct dev_archdata *sd = &dev->dev.archdata;
-
-	sd->of_node = pci_device_to_OF_node(dev);
-
-	DBG("PCI: device %s OF node: %s\n", pci_name(dev),
-	    sd->of_node ? sd->of_node->full_name : "<none>");
-
-	sd->dma_ops = pci_dma_ops;
-#ifdef CONFIG_PPC32
-	sd->dma_data = (void *)PCI_DRAM_OFFSET;
-#endif
-	set_dev_node(&dev->dev, pcibus_to_node(dev->bus));
-
-	if (ppc_md.pci_dma_dev_setup)
-		ppc_md.pci_dma_dev_setup(dev);
-}
-EXPORT_SYMBOL(pcibios_setup_new_device);
-
 /*
  * Reads the interrupt pin to determine if interrupt is use by card.
  * If the interrupt is used, then gets the interrupt line from the
@@ -252,7 +227,7 @@ int pci_read_irq_line(struct pci_dev *pci_dev)
 		return -1;
 #endif
 
-	DBG("Try to map irq for %s...\n", pci_name(pci_dev));
+	pr_debug("PCI: Try to map irq for %s...\n", pci_name(pci_dev));
 
 #ifdef DEBUG
 	memset(&oirq, 0xff, sizeof(oirq));
@@ -276,26 +251,26 @@ int pci_read_irq_line(struct pci_dev *pci_dev)
 		    line == 0xff || line == 0) {
 			return -1;
 		}
-		DBG(" -> no map ! Using line %d (pin %d) from PCI config\n",
-		    line, pin);
+		pr_debug(" No map ! Using line %d (pin %d) from PCI config\n",
+			 line, pin);
 
 		virq = irq_create_mapping(NULL, line);
 		if (virq != NO_IRQ)
 			set_irq_type(virq, IRQ_TYPE_LEVEL_LOW);
 	} else {
-		DBG(" -> got one, spec %d cells (0x%08x 0x%08x...) on %s\n",
-		    oirq.size, oirq.specifier[0], oirq.specifier[1],
+		pr_debug(" Got one, spec %d cells (0x%08x 0x%08x...) on %s\n",
+			 oirq.size, oirq.specifier[0], oirq.specifier[1],
 		    oirq.controller->full_name);
 
 		virq = irq_create_of_mapping(oirq.controller, oirq.specifier,
 					     oirq.size);
 	}
 	if(virq == NO_IRQ) {
-		DBG(" -> failed to map !\n");
+		pr_debug(" Failed to map !\n");
 		return -1;
 	}
 
-	DBG(" -> mapped to linux irq %d\n", virq);
+	pr_debug(" Mapped to linux irq %d\n", virq);
 
 	pci_dev->irq = virq;
 
@@ -451,8 +426,8 @@ pgprot_t pci_phys_mem_access_prot(struct file *file,
 		pci_dev_put(pdev);
 	}
 
-	DBG("non-PCI map for %llx, prot: %lx\n",
-	    (unsigned long long)offset, prot);
+	pr_debug("PCI: Non-PCI map for %llx, prot: %lx\n",
+		 (unsigned long long)offset, prot);
 
 	return __pgprot(prot);
 }
@@ -853,15 +828,12 @@ void __devinit pci_process_bridge_OF_ranges(struct pci_controller *hose,
 int pci_proc_domain(struct pci_bus *bus)
 {
 	struct pci_controller *hose = pci_bus_to_host(bus);
-#ifdef CONFIG_PPC64
-	return hose->buid != 0;
-#else
+
 	if (!(ppc_pci_flags & PPC_PCI_ENABLE_PROC_DOMAINS))
 		return 0;
 	if (ppc_pci_flags & PPC_PCI_COMPAT_DOMAIN_0)
 		return hose->global_number != 0;
 	return 1;
-#endif
 }
 
 void pcibios_resource_to_bus(struct pci_dev *dev, struct pci_bus_region *region,
@@ -1083,27 +1055,50 @@ static void __devinit pcibios_fixup_bridge(struct pci_bus *bus)
 	}
 }
 
-static void __devinit __pcibios_fixup_bus(struct pci_bus *bus)
+void __devinit pcibios_setup_bus_self(struct pci_bus *bus)
 {
-	struct pci_dev *dev = bus->self;
-
-	pr_debug("PCI: Fixup bus %d (%s)\n", bus->number, dev ? pci_name(dev) : "PHB");
-
-	/* Fixup PCI<->PCI bridges. Host bridges are handled separately, for
-	 * now differently between 32 and 64 bits.
-	 */
-	if (dev != NULL)
+	/* Fix up the bus resources for P2P bridges */
+	if (bus->self != NULL)
 		pcibios_fixup_bridge(bus);
 
-	/* Additional setup that is different between 32 and 64 bits for now */
-	pcibios_do_bus_setup(bus);
-
-	/* Platform specific bus fixups */
+	/* Platform specific bus fixups. This is currently only used
+	 * by fsl_pci and I'm hoping to get rid of it at some point
+	 */
 	if (ppc_md.pcibios_fixup_bus)
 		ppc_md.pcibios_fixup_bus(bus);
 
-	/* Read default IRQs and fixup if necessary */
+	/* Setup bus DMA mappings */
+	if (ppc_md.pci_dma_bus_setup)
+		ppc_md.pci_dma_bus_setup(bus);
+}
+
+void __devinit pcibios_setup_bus_devices(struct pci_bus *bus)
+{
+	struct pci_dev *dev;
+
+	pr_debug("PCI: Fixup bus devices %d (%s)\n",
+		 bus->number, bus->self ? pci_name(bus->self) : "PHB");
+
 	list_for_each_entry(dev, &bus->devices, bus_list) {
+		struct dev_archdata *sd = &dev->dev.archdata;
+
+		/* Setup OF node pointer in archdata */
+		sd->of_node = pci_device_to_OF_node(dev);
+
+		/* Fixup NUMA node as it may not be setup yet by the generic
+		 * code and is needed by the DMA init
+		 */
+		set_dev_node(&dev->dev, pcibus_to_node(dev->bus));
+
+		/* Hook up default DMA ops */
+		sd->dma_ops = pci_dma_ops;
+		sd->dma_data = (void *)PCI_DRAM_OFFSET;
+
+		/* Additional platform DMA/iommu setup */
+		if (ppc_md.pci_dma_dev_setup)
+			ppc_md.pci_dma_dev_setup(dev);
+
+		/* Read default IRQs and fixup if necessary */
 		pci_read_irq_line(dev);
 		if (ppc_md.pci_irq_fixup)
 			ppc_md.pci_irq_fixup(dev);
@@ -1113,22 +1108,19 @@ static void __devinit __pcibios_fixup_bus(struct pci_bus *bus)
 void __devinit pcibios_fixup_bus(struct pci_bus *bus)
 {
 	/* When called from the generic PCI probe, read PCI<->PCI bridge
-	 * bases before proceeding
+	 * bases. This is -not- called when generating the PCI tree from
+	 * the OF device-tree.
 	 */
 	if (bus->self != NULL)
 		pci_read_bridge_bases(bus);
-	__pcibios_fixup_bus(bus);
-}
-EXPORT_SYMBOL(pcibios_fixup_bus);
 
-/* When building a bus from the OF tree rather than probing, we need a
- * slightly different version of the fixup which doesn't read the
- * bridge bases using config space accesses
- */
-void __devinit pcibios_fixup_of_probed_bus(struct pci_bus *bus)
-{
-	__pcibios_fixup_bus(bus);
+	/* Now fixup the bus bus */
+	pcibios_setup_bus_self(bus);
+
+	/* Now fixup devices on that bus */
+	pcibios_setup_bus_devices(bus);
 }
+EXPORT_SYMBOL(pcibios_fixup_bus);
 
 static int skip_isa_ioresource_align(struct pci_dev *dev)
 {
@@ -1198,10 +1190,10 @@ static int __init reparent_resources(struct resource *parent,
 	*pp = NULL;
 	for (p = res->child; p != NULL; p = p->sibling) {
 		p->parent = res;
-		DBG(KERN_INFO "PCI: reparented %s [%llx..%llx] under %s\n",
-		    p->name,
-		    (unsigned long long)p->start,
-		    (unsigned long long)p->end, res->name);
+		pr_debug("PCI: Reparented %s [%llx..%llx] under %s\n",
+			 p->name,
+			 (unsigned long long)p->start,
+			 (unsigned long long)p->end, res->name);
 	}
 	return 0;
 }
@@ -1245,9 +1237,12 @@ void pcibios_allocate_bus_resources(struct pci_bus *bus)
 	int i;
 	struct resource *res, *pr;
 
+	pr_debug("PCI: Allocating bus resources for %04x:%02x...\n",
+		 pci_domain_nr(bus), bus->number);
+
 	for (i = 0; i < PCI_BUS_NUM_RESOURCES; ++i) {
 		if ((res = bus->resource[i]) == NULL || !res->flags
-		    || res->start > res->end)
+		    || res->start > res->end || res->parent)
 			continue;
 		if (bus->parent == NULL)
 			pr = (res->flags & IORESOURCE_IO) ?
@@ -1271,14 +1266,14 @@ void pcibios_allocate_bus_resources(struct pci_bus *bus)
 			}
 		}
 
-		DBG("PCI: %s (bus %d) bridge rsrc %d: %016llx-%016llx "
-		    "[0x%x], parent %p (%s)\n",
-		    bus->self ? pci_name(bus->self) : "PHB",
-		    bus->number, i,
-		    (unsigned long long)res->start,
-		    (unsigned long long)res->end,
-		    (unsigned int)res->flags,
-		    pr, (pr && pr->name) ? pr->name : "nil");
+		pr_debug("PCI: %s (bus %d) bridge rsrc %d: %016llx-%016llx "
+			 "[0x%x], parent %p (%s)\n",
+			 bus->self ? pci_name(bus->self) : "PHB",
+			 bus->number, i,
+			 (unsigned long long)res->start,
+			 (unsigned long long)res->end,
+			 (unsigned int)res->flags,
+			 pr, (pr && pr->name) ? pr->name : "nil");
 
 		if (pr && !(pr->flags & IORESOURCE_UNSET)) {
 			if (request_resource(pr, res) == 0)
@@ -1305,11 +1300,11 @@ static inline void __devinit alloc_resource(struct pci_dev *dev, int idx)
 {
 	struct resource *pr, *r = &dev->resource[idx];
 
-	DBG("PCI: Allocating %s: Resource %d: %016llx..%016llx [%x]\n",
-	    pci_name(dev), idx,
-	    (unsigned long long)r->start,
-	    (unsigned long long)r->end,
-	    (unsigned int)r->flags);
+	pr_debug("PCI: Allocating %s: Resource %d: %016llx..%016llx [%x]\n",
+		 pci_name(dev), idx,
+		 (unsigned long long)r->start,
+		 (unsigned long long)r->end,
+		 (unsigned int)r->flags);
 
 	pr = pci_find_parent_resource(dev, r);
 	if (!pr || (pr->flags & IORESOURCE_UNSET) ||
@@ -1317,10 +1312,11 @@ static inline void __devinit alloc_resource(struct pci_dev *dev, int idx)
 		printk(KERN_WARNING "PCI: Cannot allocate resource region %d"
 		       " of device %s, will remap\n", idx, pci_name(dev));
 		if (pr)
-			DBG("PCI:  parent is %p: %016llx-%016llx [%x]\n", pr,
-			    (unsigned long long)pr->start,
-			    (unsigned long long)pr->end,
-			    (unsigned int)pr->flags);
+			pr_debug("PCI:  parent is %p: %016llx-%016llx [%x]\n",
+				 pr,
+				 (unsigned long long)pr->start,
+				 (unsigned long long)pr->end,
+				 (unsigned int)pr->flags);
 		/* We'll assign a new address later */
 		r->flags |= IORESOURCE_UNSET;
 		r->end -= r->start;
@@ -1358,7 +1354,8 @@ static void __init pcibios_allocate_resources(int pass)
 			 * but keep it unregistered.
 			 */
 			u32 reg;
-			DBG("PCI: Switching off ROM of %s\n", pci_name(dev));
+			pr_debug("PCI: Switching off ROM of %s\n",
+				 pci_name(dev));
 			r->flags &= ~IORESOURCE_ROM_ENABLE;
 			pci_read_config_dword(dev, dev->rom_base_reg, &reg);
 			pci_write_config_dword(dev, dev->rom_base_reg,
@@ -1383,7 +1380,7 @@ void __init pcibios_resource_survey(void)
 	}
 
 	if (!(ppc_pci_flags & PPC_PCI_PROBE_ONLY)) {
-		DBG("PCI: Assigning unassigned resouces...\n");
+		pr_debug("PCI: Assigning unassigned resouces...\n");
 		pci_assign_unassigned_resources();
 	}
 
@@ -1393,9 +1390,11 @@ void __init pcibios_resource_survey(void)
 }
 
 #ifdef CONFIG_HOTPLUG
-/* This is used by the pSeries hotplug driver to allocate resource
+
+/* This is used by the PCI hotplug driver to allocate resource
  * of newly plugged busses. We can try to consolidate with the
- * rest of the code later, for now, keep it as-is
+ * rest of the code later, for now, keep it as-is as our main
+ * resource allocation function doesn't deal with sub-trees yet.
  */
 void __devinit pcibios_claim_one_bus(struct pci_bus *bus)
 {
@@ -1410,6 +1409,14 @@ void __devinit pcibios_claim_one_bus(struct pci_bus *bus)
 
 			if (r->parent || !r->start || !r->flags)
 				continue;
+
+			pr_debug("PCI: Claiming %s: "
+				 "Resource %d: %016llx..%016llx [%x]\n",
+				 pci_name(dev), i,
+				 (unsigned long long)r->start,
+				 (unsigned long long)r->end,
+				 (unsigned int)r->flags);
+
 			pci_claim_resource(dev, i);
 		}
 	}
@@ -1418,6 +1425,31 @@ void __devinit pcibios_claim_one_bus(struct pci_bus *bus)
 		pcibios_claim_one_bus(child_bus);
 }
 EXPORT_SYMBOL_GPL(pcibios_claim_one_bus);
+
+
+/* pcibios_finish_adding_to_bus
+ *
+ * This is to be called by the hotplug code after devices have been
+ * added to a bus, this include calling it for a PHB that is just
+ * being added
+ */
+void pcibios_finish_adding_to_bus(struct pci_bus *bus)
+{
+	pr_debug("PCI: Finishing adding to hotplug bus %04x:%02x\n",
+		 pci_domain_nr(bus), bus->number);
+
+	/* Allocate bus and devices resources */
+	pcibios_allocate_bus_resources(bus);
+	pcibios_claim_one_bus(bus);
+
+	/* Add new devices to global lists.  Register in proc, sysfs. */
+	pci_bus_add_devices(bus);
+
+	/* Fixup EEH */
+	eeh_add_device_tree_late(bus);
+}
+EXPORT_SYMBOL_GPL(pcibios_finish_adding_to_bus);
+
 #endif /* CONFIG_HOTPLUG */
 
 int pcibios_enable_device(struct pci_dev *dev, int mask)
@@ -1428,3 +1460,61 @@ int pcibios_enable_device(struct pci_dev *dev, int mask)
 
 	return pci_enable_resources(dev, mask);
 }
+
+void __devinit pcibios_setup_phb_resources(struct pci_controller *hose)
+{
+	struct pci_bus *bus = hose->bus;
+	struct resource *res;
+	int i;
+
+	/* Hookup PHB IO resource */
+	bus->resource[0] = res = &hose->io_resource;
+
+	if (!res->flags) {
+		printk(KERN_WARNING "PCI: I/O resource not set for host"
+		       " bridge %s (domain %d)\n",
+		       hose->dn->full_name, hose->global_number);
+#ifdef CONFIG_PPC32
+		/* Workaround for lack of IO resource only on 32-bit */
+		res->start = (unsigned long)hose->io_base_virt - isa_io_base;
+		res->end = res->start + IO_SPACE_LIMIT;
+		res->flags = IORESOURCE_IO;
+#endif /* CONFIG_PPC32 */
+	}
+
+	pr_debug("PCI: PHB IO resource    = %016llx-%016llx [%lx]\n",
+		 (unsigned long long)res->start,
+		 (unsigned long long)res->end,
+		 (unsigned long)res->flags);
+
+	/* Hookup PHB Memory resources */
+	for (i = 0; i < 3; ++i) {
+		res = &hose->mem_resources[i];
+		if (!res->flags) {
+			if (i > 0)
+				continue;
+			printk(KERN_ERR "PCI: Memory resource 0 not set for "
+			       "host bridge %s (domain %d)\n",
+			       hose->dn->full_name, hose->global_number);
+#ifdef CONFIG_PPC32
+			/* Workaround for lack of MEM resource only on 32-bit */
+			res->start = hose->pci_mem_offset;
+			res->end = (resource_size_t)-1LL;
+			res->flags = IORESOURCE_MEM;
+#endif /* CONFIG_PPC32 */
+		}
+		bus->resource[i+1] = res;
+
+		pr_debug("PCI: PHB MEM resource %d = %016llx-%016llx [%lx]\n", i,
+			 (unsigned long long)res->start,
+			 (unsigned long long)res->end,
+			 (unsigned long)res->flags);
+	}
+
+	pr_debug("PCI: PHB MEM offset     = %016llx\n",
+		 (unsigned long long)hose->pci_mem_offset);
+	pr_debug("PCI: PHB IO  offset     = %08lx\n",
+		 (unsigned long)hose->io_base_virt - _IO_BASE);
+
+}
+
diff --git a/arch/powerpc/kernel/pci_32.c b/arch/powerpc/kernel/pci_32.c
index 131b1dfa68c6..7ad11e592f2b 100644
--- a/arch/powerpc/kernel/pci_32.c
+++ b/arch/powerpc/kernel/pci_32.c
@@ -26,12 +26,6 @@
 
 #undef DEBUG
 
-#ifdef DEBUG
-#define DBG(x...) printk(x)
-#else
-#define DBG(x...)
-#endif
-
 unsigned long isa_io_base     = 0;
 unsigned long pci_dram_offset = 0;
 int pcibios_assign_bus_offset = 1;
@@ -275,14 +269,14 @@ pci_busdev_to_OF_node(struct pci_bus *bus, int devfn)
 	if (!have_of)
 		return NULL;
 
-	DBG("pci_busdev_to_OF_node(%d,0x%x)\n", bus->number, devfn);
+	pr_debug("pci_busdev_to_OF_node(%d,0x%x)\n", bus->number, devfn);
 	parent = scan_OF_for_pci_bus(bus);
 	if (parent == NULL)
 		return NULL;
-	DBG(" parent is %s\n", parent ? parent->full_name : "<NULL>");
+	pr_debug(" parent is %s\n", parent ? parent->full_name : "<NULL>");
 	np = scan_OF_for_pci_dev(parent, devfn);
 	of_node_put(parent);
-	DBG(" result is %s\n", np ? np->full_name : "<NULL>");
+	pr_debug(" result is %s\n", np ? np->full_name : "<NULL>");
 
 	/* XXX most callers don't release the returned node
 	 * mostly because ppc64 doesn't increase the refcount,
@@ -379,10 +373,41 @@ void pcibios_make_OF_bus_map(void)
 }
 #endif /* CONFIG_PPC_OF */
 
+static void __devinit pcibios_scan_phb(struct pci_controller *hose)
+{
+	struct pci_bus *bus;
+	struct device_node *node = hose->dn;
+	unsigned long io_offset;
+	struct resource *res = &hose->io_resource;
+
+	pr_debug("PCI: Scanning PHB %s\n",
+		 node ? node->full_name : "<NO NAME>");
+
+	/* Create an empty bus for the toplevel */
+	bus = pci_create_bus(hose->parent, hose->first_busno, hose->ops, hose);
+	if (bus == NULL) {
+		printk(KERN_ERR "Failed to create bus for PCI domain %04x\n",
+		       hose->global_number);
+		return;
+	}
+	bus->secondary = hose->first_busno;
+	hose->bus = bus;
+
+	/* Fixup IO space offset */
+	io_offset = (unsigned long)hose->io_base_virt - isa_io_base;
+	res->start = (res->start + io_offset) & 0xffffffffu;
+	res->end = (res->end + io_offset) & 0xffffffffu;
+
+	/* Wire up PHB bus resources */
+	pcibios_setup_phb_resources(hose);
+
+	/* Scan children */
+	hose->last_busno = bus->subordinate = pci_scan_child_bus(bus);
+}
+
 static int __init pcibios_init(void)
 {
 	struct pci_controller *hose, *tmp;
-	struct pci_bus *bus;
 	int next_busno = 0;
 
 	printk(KERN_INFO "PCI: Probing PCI hardware\n");
@@ -395,12 +420,8 @@ static int __init pcibios_init(void)
 		if (pci_assign_all_buses)
 			hose->first_busno = next_busno;
 		hose->last_busno = 0xff;
-		bus = pci_scan_bus_parented(hose->parent, hose->first_busno,
-					    hose->ops, hose);
-		if (bus) {
-			pci_bus_add_devices(bus);
-			hose->last_busno = bus->subordinate;
-		}
+		pcibios_scan_phb(hose);
+		pci_bus_add_devices(hose->bus);
 		if (pci_assign_all_buses || next_busno <= hose->last_busno)
 			next_busno = hose->last_busno + pcibios_assign_bus_offset;
 	}
@@ -425,54 +446,6 @@ static int __init pcibios_init(void)
 
 subsys_initcall(pcibios_init);
 
-void __devinit pcibios_do_bus_setup(struct pci_bus *bus)
-{
-	struct pci_controller *hose = (struct pci_controller *) bus->sysdata;
-	unsigned long io_offset;
-	struct resource *res;
-	int i;
-	struct pci_dev *dev;
-
-	/* Hookup PHB resources */
-	io_offset = (unsigned long)hose->io_base_virt - isa_io_base;
-	if (bus->parent == NULL) {
-		/* This is a host bridge - fill in its resources */
-		hose->bus = bus;
-
-		bus->resource[0] = res = &hose->io_resource;
-		if (!res->flags) {
-			if (io_offset)
-				printk(KERN_ERR "I/O resource not set for host"
-				       " bridge %d\n", hose->global_number);
-			res->start = 0;
-			res->end = IO_SPACE_LIMIT;
-			res->flags = IORESOURCE_IO;
-		}
-		res->start = (res->start + io_offset) & 0xffffffffu;
-		res->end = (res->end + io_offset) & 0xffffffffu;
-
-		for (i = 0; i < 3; ++i) {
-			res = &hose->mem_resources[i];
-			if (!res->flags) {
-				if (i > 0)
-					continue;
-				printk(KERN_ERR "Memory resource not set for "
-				       "host bridge %d\n", hose->global_number);
-				res->start = hose->pci_mem_offset;
-				res->end = ~0U;
-				res->flags = IORESOURCE_MEM;
-			}
-			bus->resource[i+1] = res;
-		}
-	}
-
-	if (ppc_md.pci_dma_bus_setup)
-		ppc_md.pci_dma_bus_setup(bus);
-
-	list_for_each_entry(dev, &bus->devices, bus_list)
-		pcibios_setup_new_device(dev);
-}
-
 /* the next one is stolen from the alpha port... */
 void __init
 pcibios_update_irq(struct pci_dev *dev, int irq)
diff --git a/arch/powerpc/kernel/pci_64.c b/arch/powerpc/kernel/pci_64.c
index 3502b9101e6b..39fadc6e1492 100644
--- a/arch/powerpc/kernel/pci_64.c
+++ b/arch/powerpc/kernel/pci_64.c
@@ -32,13 +32,6 @@
 #include <asm/machdep.h>
 #include <asm/ppc-pci.h>
 
-#ifdef DEBUG
-#include <asm/udbg.h>
-#define DBG(fmt...) printk(fmt)
-#else
-#define DBG(fmt...)
-#endif
-
 unsigned long pci_probe_only = 1;
 
 /* pci_io_base -- the base address from which io bars are offsets.
@@ -102,7 +95,7 @@ static void pci_parse_of_addrs(struct device_node *node, struct pci_dev *dev)
 	addrs = of_get_property(node, "assigned-addresses", &proplen);
 	if (!addrs)
 		return;
-	DBG("    parse addresses (%d bytes) @ %p\n", proplen, addrs);
+	pr_debug("    parse addresses (%d bytes) @ %p\n", proplen, addrs);
 	for (; proplen >= 20; proplen -= 20, addrs += 5) {
 		flags = pci_parse_of_flags(addrs[0]);
 		if (!flags)
@@ -112,8 +105,9 @@ static void pci_parse_of_addrs(struct device_node *node, struct pci_dev *dev)
 		if (!size)
 			continue;
 		i = addrs[0] & 0xff;
-		DBG("  base: %llx, size: %llx, i: %x\n",
-		    (unsigned long long)base, (unsigned long long)size, i);
+		pr_debug("  base: %llx, size: %llx, i: %x\n",
+			 (unsigned long long)base,
+			 (unsigned long long)size, i);
 
 		if (PCI_BASE_ADDRESS_0 <= i && i <= PCI_BASE_ADDRESS_5) {
 			res = &dev->resource[(i - PCI_BASE_ADDRESS_0) >> 2];
@@ -144,7 +138,7 @@ struct pci_dev *of_create_pci_dev(struct device_node *node,
 	if (type == NULL)
 		type = "";
 
-	DBG("    create device, devfn: %x, type: %s\n", devfn, type);
+	pr_debug("    create device, devfn: %x, type: %s\n", devfn, type);
 
 	dev->bus = bus;
 	dev->sysdata = node;
@@ -165,8 +159,8 @@ struct pci_dev *of_create_pci_dev(struct device_node *node,
 	dev->class = get_int_prop(node, "class-code", 0);
 	dev->revision = get_int_prop(node, "revision-id", 0);
 
-	DBG("    class: 0x%x\n", dev->class);
-	DBG("    revision: 0x%x\n", dev->revision);
+	pr_debug("    class: 0x%x\n", dev->class);
+	pr_debug("    revision: 0x%x\n", dev->revision);
 
 	dev->current_state = 4;		/* unknown power state */
 	dev->error_state = pci_channel_io_normal;
@@ -187,7 +181,7 @@ struct pci_dev *of_create_pci_dev(struct device_node *node,
 
 	pci_parse_of_addrs(node, dev);
 
-	DBG("    adding to system ...\n");
+	pr_debug("    adding to system ...\n");
 
 	pci_device_add(dev, bus);
 
@@ -195,19 +189,20 @@ struct pci_dev *of_create_pci_dev(struct device_node *node,
 }
 EXPORT_SYMBOL(of_create_pci_dev);
 
-void __devinit of_scan_bus(struct device_node *node,
-			   struct pci_bus *bus)
+static void __devinit __of_scan_bus(struct device_node *node,
+				    struct pci_bus *bus, int rescan_existing)
 {
 	struct device_node *child;
 	const u32 *reg;
 	int reglen, devfn;
 	struct pci_dev *dev;
 
-	DBG("of_scan_bus(%s) bus no %d... \n", node->full_name, bus->number);
+	pr_debug("of_scan_bus(%s) bus no %d... \n",
+		 node->full_name, bus->number);
 
 	/* Scan direct children */
 	for_each_child_of_node(node, child) {
-		DBG("  * %s\n", child->full_name);
+		pr_debug("  * %s\n", child->full_name);
 		reg = of_get_property(child, "reg", &reglen);
 		if (reg == NULL || reglen < 20)
 			continue;
@@ -217,11 +212,15 @@ void __devinit of_scan_bus(struct device_node *node,
 		dev = of_create_pci_dev(child, bus, devfn);
 		if (!dev)
 			continue;
-		DBG("    dev header type: %x\n", dev->hdr_type);
+		pr_debug("    dev header type: %x\n", dev->hdr_type);
 	}
 
-	/* Ally all fixups */
-	pcibios_fixup_of_probed_bus(bus);
+	/* Apply all fixups necessary. We don't fixup the bus "self"
+	 * for an existing bridge that is being rescanned
+	 */
+	if (!rescan_existing)
+		pcibios_setup_bus_self(bus);
+	pcibios_setup_bus_devices(bus);
 
 	/* Now scan child busses */
 	list_for_each_entry(dev, &bus->devices, bus_list) {
@@ -233,7 +232,20 @@ void __devinit of_scan_bus(struct device_node *node,
 		}
 	}
 }
-EXPORT_SYMBOL(of_scan_bus);
+
+void __devinit of_scan_bus(struct device_node *node,
+			   struct pci_bus *bus)
+{
+	__of_scan_bus(node, bus, 0);
+}
+EXPORT_SYMBOL_GPL(of_scan_bus);
+
+void __devinit of_rescan_bus(struct device_node *node,
+			     struct pci_bus *bus)
+{
+	__of_scan_bus(node, bus, 1);
+}
+EXPORT_SYMBOL_GPL(of_rescan_bus);
 
 void __devinit of_scan_pci_bridge(struct device_node *node,
 				  struct pci_dev *dev)
@@ -245,7 +257,7 @@ void __devinit of_scan_pci_bridge(struct device_node *node,
 	unsigned int flags;
 	u64 size;
 
-	DBG("of_scan_pci_bridge(%s)\n", node->full_name);
+	pr_debug("of_scan_pci_bridge(%s)\n", node->full_name);
 
 	/* parse bus-range property */
 	busrange = of_get_property(node, "bus-range", &len);
@@ -309,12 +321,12 @@ void __devinit of_scan_pci_bridge(struct device_node *node,
 	}
 	sprintf(bus->name, "PCI Bus %04x:%02x", pci_domain_nr(bus),
 		bus->number);
-	DBG("    bus name: %s\n", bus->name);
+	pr_debug("    bus name: %s\n", bus->name);
 
 	mode = PCI_PROBE_NORMAL;
 	if (ppc_md.pci_probe_mode)
 		mode = ppc_md.pci_probe_mode(bus);
-	DBG("    probe mode: %d\n", mode);
+	pr_debug("    probe mode: %d\n", mode);
 
 	if (mode == PCI_PROBE_DEVTREE)
 		of_scan_bus(node, bus);
@@ -327,9 +339,10 @@ void __devinit scan_phb(struct pci_controller *hose)
 {
 	struct pci_bus *bus;
 	struct device_node *node = hose->dn;
-	int i, mode;
+	int mode;
 
-	DBG("PCI: Scanning PHB %s\n", node ? node->full_name : "<NO NAME>");
+	pr_debug("PCI: Scanning PHB %s\n",
+		 node ? node->full_name : "<NO NAME>");
 
 	/* Create an empty bus for the toplevel */
 	bus = pci_create_bus(hose->parent, hose->first_busno, hose->ops, node);
@@ -345,26 +358,13 @@ void __devinit scan_phb(struct pci_controller *hose)
 	pcibios_map_io_space(bus);
 
 	/* Wire up PHB bus resources */
-	DBG("PCI: PHB IO resource    = %016lx-%016lx [%lx]\n",
-	    hose->io_resource.start, hose->io_resource.end,
-	    hose->io_resource.flags);
-	bus->resource[0] = &hose->io_resource;
-	for (i = 0; i < 3; ++i) {
-		DBG("PCI: PHB MEM resource %d = %016lx-%016lx [%lx]\n", i,
-		    hose->mem_resources[i].start,
-		    hose->mem_resources[i].end,
-		    hose->mem_resources[i].flags);
-		bus->resource[i+1] = &hose->mem_resources[i];
-	}
-	DBG("PCI: PHB MEM offset     = %016lx\n", hose->pci_mem_offset);
-	DBG("PCI: PHB IO  offset     = %08lx\n",
-	    (unsigned long)hose->io_base_virt - _IO_BASE);
+	pcibios_setup_phb_resources(hose);
 
 	/* Get probe mode and perform scan */
 	mode = PCI_PROBE_NORMAL;
 	if (node && ppc_md.pci_probe_mode)
 		mode = ppc_md.pci_probe_mode(bus);
-	DBG("    probe mode: %d\n", mode);
+	pr_debug("    probe mode: %d\n", mode);
 	if (mode == PCI_PROBE_DEVTREE) {
 		bus->subordinate = hose->last_busno;
 		of_scan_bus(node, bus);
@@ -380,7 +380,7 @@ static int __init pcibios_init(void)
 
 	printk(KERN_INFO "PCI: Probing PCI hardware\n");
 
-	/* For now, override phys_mem_access_prot. If we need it,
+	/* For now, override phys_mem_access_prot. If we need it,g
 	 * later, we may move that initialization to each ppc_md
 	 */
 	ppc_md.phys_mem_access_prot = pci_phys_mem_access_prot;
@@ -388,6 +388,11 @@ static int __init pcibios_init(void)
 	if (pci_probe_only)
 		ppc_pci_flags |= PPC_PCI_PROBE_ONLY;
 
+	/* On ppc64, we always enable PCI domains and we keep domain 0
+	 * backward compatible in /proc for video cards
+	 */
+	ppc_pci_flags |= PPC_PCI_ENABLE_PROC_DOMAINS | PPC_PCI_COMPAT_DOMAIN_0;
+
 	/* Scan all of the recorded PCI controllers.  */
 	list_for_each_entry_safe(hose, tmp, &hose_list, list_node) {
 		scan_phb(hose);
@@ -422,8 +427,8 @@ int pcibios_unmap_io_space(struct pci_bus *bus)
 	if (bus->self) {
 		struct resource *res = bus->resource[0];
 
-		DBG("IO unmapping for PCI-PCI bridge %s\n",
-		    pci_name(bus->self));
+		pr_debug("IO unmapping for PCI-PCI bridge %s\n",
+			 pci_name(bus->self));
 
 		__flush_hash_table_range(&init_mm, res->start + _IO_BASE,
 					 res->end + _IO_BASE + 1);
@@ -437,8 +442,8 @@ int pcibios_unmap_io_space(struct pci_bus *bus)
 	if (hose->io_base_alloc == 0)
 		return 0;
 
-	DBG("IO unmapping for PHB %s\n", hose->dn->full_name);
-	DBG("  alloc=0x%p\n", hose->io_base_alloc);
+	pr_debug("IO unmapping for PHB %s\n", hose->dn->full_name);
+	pr_debug("  alloc=0x%p\n", hose->io_base_alloc);
 
 	/* This is a PHB, we fully unmap the IO area */
 	vunmap(hose->io_base_alloc);
@@ -463,11 +468,11 @@ int __devinit pcibios_map_io_space(struct pci_bus *bus)
 	 * thus HPTEs will be faulted in when needed
 	 */
 	if (bus->self) {
-		DBG("IO mapping for PCI-PCI bridge %s\n",
-		    pci_name(bus->self));
-		DBG("  virt=0x%016lx...0x%016lx\n",
-		    bus->resource[0]->start + _IO_BASE,
-		    bus->resource[0]->end + _IO_BASE);
+		pr_debug("IO mapping for PCI-PCI bridge %s\n",
+			 pci_name(bus->self));
+		pr_debug("  virt=0x%016lx...0x%016lx\n",
+			 bus->resource[0]->start + _IO_BASE,
+			 bus->resource[0]->end + _IO_BASE);
 		return 0;
 	}
 
@@ -496,11 +501,11 @@ int __devinit pcibios_map_io_space(struct pci_bus *bus)
 	hose->io_base_virt = (void __iomem *)(area->addr +
 					      hose->io_base_phys - phys_page);
 
-	DBG("IO mapping for PHB %s\n", hose->dn->full_name);
-	DBG("  phys=0x%016lx, virt=0x%p (alloc=0x%p)\n",
-	    hose->io_base_phys, hose->io_base_virt, hose->io_base_alloc);
-	DBG("  size=0x%016lx (alloc=0x%016lx)\n",
-	    hose->pci_io_size, size_page);
+	pr_debug("IO mapping for PHB %s\n", hose->dn->full_name);
+	pr_debug("  phys=0x%016lx, virt=0x%p (alloc=0x%p)\n",
+		 hose->io_base_phys, hose->io_base_virt, hose->io_base_alloc);
+	pr_debug("  size=0x%016lx (alloc=0x%016lx)\n",
+		 hose->pci_io_size, size_page);
 
 	/* Establish the mapping */
 	if (__ioremap_at(phys_page, area->addr, size_page,
@@ -512,24 +517,13 @@ int __devinit pcibios_map_io_space(struct pci_bus *bus)
 	hose->io_resource.start += io_virt_offset;
 	hose->io_resource.end += io_virt_offset;
 
-	DBG("  hose->io_resource=0x%016lx...0x%016lx\n",
-	    hose->io_resource.start, hose->io_resource.end);
+	pr_debug("  hose->io_resource=0x%016lx...0x%016lx\n",
+		 hose->io_resource.start, hose->io_resource.end);
 
 	return 0;
 }
 EXPORT_SYMBOL_GPL(pcibios_map_io_space);
 
-void __devinit pcibios_do_bus_setup(struct pci_bus *bus)
-{
-	struct pci_dev *dev;
-
-	if (ppc_md.pci_dma_bus_setup)
-		ppc_md.pci_dma_bus_setup(bus);
-
-	list_for_each_entry(dev, &bus->devices, bus_list)
-		pcibios_setup_new_device(dev);
-}
-
 unsigned long pci_address_to_pio(phys_addr_t address)
 {
 	struct pci_controller *hose, *tmp;
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 957bded0020d..51b201ddf9a1 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -467,6 +467,8 @@ static struct regbit {
 	{MSR_VEC,	"VEC"},
 	{MSR_VSX,	"VSX"},
 	{MSR_ME,	"ME"},
+	{MSR_CE,	"CE"},
+	{MSR_DE,	"DE"},
 	{MSR_IR,	"IR"},
 	{MSR_DR,	"DR"},
 	{0,		NULL}
@@ -998,7 +1000,7 @@ unsigned long get_wchan(struct task_struct *p)
 	return 0;
 }
 
-static int kstack_depth_to_print = 64;
+static int kstack_depth_to_print = CONFIG_PRINT_STACK_DEPTH;
 
 void show_stack(struct task_struct *tsk, unsigned long *stack)
 {
diff --git a/arch/powerpc/kernel/prom_parse.c b/arch/powerpc/kernel/prom_parse.c
index a11d68976dc8..8c1335566089 100644
--- a/arch/powerpc/kernel/prom_parse.c
+++ b/arch/powerpc/kernel/prom_parse.c
@@ -734,10 +734,7 @@ void of_irq_map_init(unsigned int flags)
 	if (flags & OF_IMAP_NO_PHANDLE) {
 		struct device_node *np;
 
-		for(np = NULL; (np = of_find_all_nodes(np)) != NULL;) {
-			if (of_get_property(np, "interrupt-controller", NULL)
-			    == NULL)
-				continue;
+		for_each_node_with_property(np, "interrupt-controller") {
 			/* Skip /chosen/interrupt-controller */
 			if (strcmp(np->name, "chosen") == 0)
 				continue;
diff --git a/arch/powerpc/kernel/rtas_pci.c b/arch/powerpc/kernel/rtas_pci.c
index 589a2797eac2..8869001ab5d7 100644
--- a/arch/powerpc/kernel/rtas_pci.c
+++ b/arch/powerpc/kernel/rtas_pci.c
@@ -301,51 +301,3 @@ void __init find_and_init_phbs(void)
 #endif /* CONFIG_PPC32 */
 	}
 }
-
-/* RPA-specific bits for removing PHBs */
-int pcibios_remove_root_bus(struct pci_controller *phb)
-{
-	struct pci_bus *b = phb->bus;
-	struct resource *res;
-	int rc, i;
-
-	res = b->resource[0];
-	if (!res->flags) {
-		printk(KERN_ERR "%s: no IO resource for PHB %s\n", __func__,
-				b->name);
-		return 1;
-	}
-
-	rc = pcibios_unmap_io_space(b);
-	if (rc) {
-		printk(KERN_ERR "%s: failed to unmap IO on bus %s\n",
-			__func__, b->name);
-		return 1;
-	}
-
-	if (release_resource(res)) {
-		printk(KERN_ERR "%s: failed to release IO on bus %s\n",
-				__func__, b->name);
-		return 1;
-	}
-
-	for (i = 1; i < 3; ++i) {
-		res = b->resource[i];
-		if (!res->flags && i == 0) {
-			printk(KERN_ERR "%s: no MEM resource for PHB %s\n",
-				__func__, b->name);
-			return 1;
-		}
-		if (res->flags && release_resource(res)) {
-			printk(KERN_ERR
-			       "%s: failed to release IO %d on bus %s\n",
-				__func__, i, b->name);
-			return 1;
-		}
-	}
-
-	pcibios_free_controller(phb);
-
-	return 0;
-}
-EXPORT_SYMBOL(pcibios_remove_root_bus);
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index 169d74cef157..93c875ae985a 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -606,8 +606,6 @@ void __init setup_per_cpu_areas(void)
 
 	for_each_possible_cpu(i) {
 		ptr = alloc_bootmem_pages_node(NODE_DATA(cpu_to_node(i)), size);
-		if (!ptr)
-			panic("Cannot allocate cpu data for CPU %d\n", i);
 
 		paca[i].data_offset = ptr - __per_cpu_start;
 		memcpy(ptr, __per_cpu_start, __per_cpu_end - __per_cpu_start);
diff --git a/arch/powerpc/kernel/smp-tbsync.c b/arch/powerpc/kernel/smp-tbsync.c
index bc892e69b4f7..a5e54526403d 100644
--- a/arch/powerpc/kernel/smp-tbsync.c
+++ b/arch/powerpc/kernel/smp-tbsync.c
@@ -113,7 +113,7 @@ void __devinit smp_generic_give_timebase(void)
 {
 	int i, score, score2, old, min=0, max=5000, offset=1000;
 
-	printk("Synchronizing timebase\n");
+	pr_debug("Software timebase sync\n");
 
 	/* if this fails then this kernel won't work anyway... */
 	tbsync = kzalloc( sizeof(*tbsync), GFP_KERNEL );
@@ -123,13 +123,13 @@ void __devinit smp_generic_give_timebase(void)
 	while (!tbsync->ack)
 		barrier();
 
-	printk("Got ack\n");
+	pr_debug("Got ack\n");
 
 	/* binary search */
 	for (old = -1; old != offset ; offset = (min+max) / 2) {
 		score = start_contest(kSetAndTest, offset, NUM_ITER);
 
-		printk("score %d, offset %d\n", score, offset );
+		pr_debug("score %d, offset %d\n", score, offset );
 
 		if( score > 0 )
 			max = offset;
@@ -140,8 +140,8 @@ void __devinit smp_generic_give_timebase(void)
 	score = start_contest(kSetAndTest, min, NUM_ITER);
 	score2 = start_contest(kSetAndTest, max, NUM_ITER);
 
-	printk("Min %d (score %d), Max %d (score %d)\n",
-	       min, score, max, score2);
+	pr_debug("Min %d (score %d), Max %d (score %d)\n",
+		 min, score, max, score2);
 	score = abs(score);
 	score2 = abs(score2);
 	offset = (score < score2) ? min : max;
@@ -155,7 +155,7 @@ void __devinit smp_generic_give_timebase(void)
 		if (score2 <= score || score2 < 20)
 			break;
 	}
-	printk("Final offset: %d (%d/%d)\n", offset, score2, NUM_ITER );
+	pr_debug("Final offset: %d (%d/%d)\n", offset, score2, NUM_ITER );
 
 	/* exiting */
 	tbsync->cmd = kExit;
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index ff9f7010097d..a59d8d72bb97 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -123,6 +123,65 @@ void smp_message_recv(int msg)
 	}
 }
 
+static irqreturn_t call_function_action(int irq, void *data)
+{
+	generic_smp_call_function_interrupt();
+	return IRQ_HANDLED;
+}
+
+static irqreturn_t reschedule_action(int irq, void *data)
+{
+	/* we just need the return path side effect of checking need_resched */
+	return IRQ_HANDLED;
+}
+
+static irqreturn_t call_function_single_action(int irq, void *data)
+{
+	generic_smp_call_function_single_interrupt();
+	return IRQ_HANDLED;
+}
+
+static irqreturn_t debug_ipi_action(int irq, void *data)
+{
+	smp_message_recv(PPC_MSG_DEBUGGER_BREAK);
+	return IRQ_HANDLED;
+}
+
+static irq_handler_t smp_ipi_action[] = {
+	[PPC_MSG_CALL_FUNCTION] =  call_function_action,
+	[PPC_MSG_RESCHEDULE] = reschedule_action,
+	[PPC_MSG_CALL_FUNC_SINGLE] = call_function_single_action,
+	[PPC_MSG_DEBUGGER_BREAK] = debug_ipi_action,
+};
+
+const char *smp_ipi_name[] = {
+	[PPC_MSG_CALL_FUNCTION] =  "ipi call function",
+	[PPC_MSG_RESCHEDULE] = "ipi reschedule",
+	[PPC_MSG_CALL_FUNC_SINGLE] = "ipi call function single",
+	[PPC_MSG_DEBUGGER_BREAK] = "ipi debugger",
+};
+
+/* optional function to request ipi, for controllers with >= 4 ipis */
+int smp_request_message_ipi(int virq, int msg)
+{
+	int err;
+
+	if (msg < 0 || msg > PPC_MSG_DEBUGGER_BREAK) {
+		return -EINVAL;
+	}
+#if !defined(CONFIG_DEBUGGER) && !defined(CONFIG_KEXEC)
+	if (msg == PPC_MSG_DEBUGGER_BREAK) {
+		return 1;
+	}
+#endif
+	err = request_irq(virq, smp_ipi_action[msg], IRQF_DISABLED|IRQF_PERCPU,
+			  smp_ipi_name[msg], 0);
+	WARN(err < 0, "unable to request_irq %d for %s (rc %d)\n",
+		virq, smp_ipi_name[msg], err);
+
+	return err;
+}
+
 void smp_send_reschedule(int cpu)
 {
 	if (likely(smp_ops))
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index e2ee66b5831d..e1f3a5140429 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -164,8 +164,6 @@ static u64 tb_to_ns_scale __read_mostly;
 static unsigned tb_to_ns_shift __read_mostly;
 static unsigned long boot_tb __read_mostly;
 
-static struct gettimeofday_struct do_gtod;
-
 extern struct timezone sys_tz;
 static long timezone_offset;
 
@@ -415,31 +413,9 @@ void udelay(unsigned long usecs)
 }
 EXPORT_SYMBOL(udelay);
 
-
-/*
- * There are two copies of tb_to_xs and stamp_xsec so that no
- * lock is needed to access and use these values in
- * do_gettimeofday.  We alternate the copies and as long as a
- * reasonable time elapses between changes, there will never
- * be inconsistent values.  ntpd has a minimum of one minute
- * between updates.
- */
 static inline void update_gtod(u64 new_tb_stamp, u64 new_stamp_xsec,
 			       u64 new_tb_to_xs)
 {
-	unsigned temp_idx;
-	struct gettimeofday_vars *temp_varp;
-
-	temp_idx = (do_gtod.var_idx == 0);
-	temp_varp = &do_gtod.vars[temp_idx];
-
-	temp_varp->tb_to_xs = new_tb_to_xs;
-	temp_varp->tb_orig_stamp = new_tb_stamp;
-	temp_varp->stamp_xsec = new_stamp_xsec;
-	smp_mb();
-	do_gtod.varp = temp_varp;
-	do_gtod.var_idx = temp_idx;
-
 	/*
 	 * tb_update_count is used to allow the userspace gettimeofday code
 	 * to assure itself that it sees a consistent view of the tb_to_xs and
@@ -456,6 +432,7 @@ static inline void update_gtod(u64 new_tb_stamp, u64 new_stamp_xsec,
 	vdso_data->tb_to_xs = new_tb_to_xs;
 	vdso_data->wtom_clock_sec = wall_to_monotonic.tv_sec;
 	vdso_data->wtom_clock_nsec = wall_to_monotonic.tv_nsec;
+	vdso_data->stamp_xtime = xtime;
 	smp_wmb();
 	++(vdso_data->tb_update_count);
 }
@@ -514,9 +491,7 @@ static int __init iSeries_tb_recal(void)
 				tb_ticks_per_sec   = new_tb_ticks_per_sec;
 				calc_cputime_factors();
 				div128_by_32( XSEC_PER_SEC, 0, tb_ticks_per_sec, &divres );
-				do_gtod.tb_ticks_per_sec = tb_ticks_per_sec;
 				tb_to_xs = divres.result_low;
-				do_gtod.varp->tb_to_xs = tb_to_xs;
 				vdso_data->tb_ticks_per_sec = tb_ticks_per_sec;
 				vdso_data->tb_to_xs = tb_to_xs;
 			}
@@ -988,15 +963,6 @@ void __init time_init(void)
 		sys_tz.tz_dsttime = 0;
         }
 
-	do_gtod.varp = &do_gtod.vars[0];
-	do_gtod.var_idx = 0;
-	do_gtod.varp->tb_orig_stamp = tb_last_jiffy;
-	__get_cpu_var(last_jiffy) = tb_last_jiffy;
-	do_gtod.varp->stamp_xsec = (u64) xtime.tv_sec * XSEC_PER_SEC;
-	do_gtod.tb_ticks_per_sec = tb_ticks_per_sec;
-	do_gtod.varp->tb_to_xs = tb_to_xs;
-	do_gtod.tb_to_us = tb_to_us;
-
 	vdso_data->tb_orig_stamp = tb_last_jiffy;
 	vdso_data->tb_update_count = 0;
 	vdso_data->tb_ticks_per_sec = tb_ticks_per_sec;
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index f5def6cf5cd6..5457e9575685 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -1160,37 +1160,85 @@ void CacheLockingException(struct pt_regs *regs, unsigned long address,
 #ifdef CONFIG_SPE
 void SPEFloatingPointException(struct pt_regs *regs)
 {
+	extern int do_spe_mathemu(struct pt_regs *regs);
 	unsigned long spefscr;
 	int fpexc_mode;
 	int code = 0;
+	int err;
+
+	preempt_disable();
+	if (regs->msr & MSR_SPE)
+		giveup_spe(current);
+	preempt_enable();
 
 	spefscr = current->thread.spefscr;
 	fpexc_mode = current->thread.fpexc_mode;
 
-	/* Hardware does not neccessarily set sticky
-	 * underflow/overflow/invalid flags */
 	if ((spefscr & SPEFSCR_FOVF) && (fpexc_mode & PR_FP_EXC_OVF)) {
 		code = FPE_FLTOVF;
-		spefscr |= SPEFSCR_FOVFS;
 	}
 	else if ((spefscr & SPEFSCR_FUNF) && (fpexc_mode & PR_FP_EXC_UND)) {
 		code = FPE_FLTUND;
-		spefscr |= SPEFSCR_FUNFS;
 	}
 	else if ((spefscr & SPEFSCR_FDBZ) && (fpexc_mode & PR_FP_EXC_DIV))
 		code = FPE_FLTDIV;
 	else if ((spefscr & SPEFSCR_FINV) && (fpexc_mode & PR_FP_EXC_INV)) {
 		code = FPE_FLTINV;
-		spefscr |= SPEFSCR_FINVS;
 	}
 	else if ((spefscr & (SPEFSCR_FG | SPEFSCR_FX)) && (fpexc_mode & PR_FP_EXC_RES))
 		code = FPE_FLTRES;
 
-	current->thread.spefscr = spefscr;
+	err = do_spe_mathemu(regs);
+	if (err == 0) {
+		regs->nip += 4;		/* skip emulated instruction */
+		emulate_single_step(regs);
+		return;
+	}
+
+	if (err == -EFAULT) {
+		/* got an error reading the instruction */
+		_exception(SIGSEGV, regs, SEGV_ACCERR, regs->nip);
+	} else if (err == -EINVAL) {
+		/* didn't recognize the instruction */
+		printk(KERN_ERR "unrecognized spe instruction "
+		       "in %s at %lx\n", current->comm, regs->nip);
+	} else {
+		_exception(SIGFPE, regs, code, regs->nip);
+	}
 
-	_exception(SIGFPE, regs, code, regs->nip);
 	return;
 }
+
+void SPEFloatingPointRoundException(struct pt_regs *regs)
+{
+	extern int speround_handler(struct pt_regs *regs);
+	int err;
+
+	preempt_disable();
+	if (regs->msr & MSR_SPE)
+		giveup_spe(current);
+	preempt_enable();
+
+	regs->nip -= 4;
+	err = speround_handler(regs);
+	if (err == 0) {
+		regs->nip += 4;		/* skip emulated instruction */
+		emulate_single_step(regs);
+		return;
+	}
+
+	if (err == -EFAULT) {
+		/* got an error reading the instruction */
+		_exception(SIGSEGV, regs, SEGV_ACCERR, regs->nip);
+	} else if (err == -EINVAL) {
+		/* didn't recognize the instruction */
+		printk(KERN_ERR "unrecognized spe instruction "
+		       "in %s at %lx\n", current->comm, regs->nip);
+	} else {
+		_exception(SIGFPE, regs, 0, regs->nip);
+		return;
+	}
+}
 #endif
 
 /*
diff --git a/arch/powerpc/kernel/vdso.c b/arch/powerpc/kernel/vdso.c
index 65639a43e644..f7ec7d0888fe 100644
--- a/arch/powerpc/kernel/vdso.c
+++ b/arch/powerpc/kernel/vdso.c
@@ -184,8 +184,7 @@ static void dump_vdso_pages(struct vm_area_struct * vma)
  * This is called from binfmt_elf, we create the special vma for the
  * vDSO and insert it into the mm struct tree
  */
-int arch_setup_additional_pages(struct linux_binprm *bprm,
-				int executable_stack)
+int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
 {
 	struct mm_struct *mm = current->mm;
 	struct page **vdso_pagelist;
diff --git a/arch/powerpc/kernel/vdso32/gettimeofday.S b/arch/powerpc/kernel/vdso32/gettimeofday.S
index 72ca26df457e..ee038d4bf252 100644
--- a/arch/powerpc/kernel/vdso32/gettimeofday.S
+++ b/arch/powerpc/kernel/vdso32/gettimeofday.S
@@ -16,6 +16,13 @@
 #include <asm/asm-offsets.h>
 #include <asm/unistd.h>
 
+/* Offset for the low 32-bit part of a field of long type */
+#ifdef CONFIG_PPC64
+#define LOPART	4
+#else
+#define LOPART	0
+#endif
+
 	.text
 /*
  * Exact prototype of gettimeofday
@@ -90,101 +97,53 @@ V_FUNCTION_BEGIN(__kernel_clock_gettime)
 
 	mflr	r12			/* r12 saves lr */
   .cfi_register lr,r12
-	mr	r10,r3			/* r10 saves id */
 	mr	r11,r4			/* r11 saves tp */
 	bl	__get_datapage@local	/* get data page */
 	mr	r9,r3			/* datapage ptr in r9 */
-	beq	cr1,50f			/* if monotonic -> jump there */
-
-	/*
-	 * CLOCK_REALTIME
-	 */
-
-	bl	__do_get_xsec@local	/* get xsec from tb & kernel */
-	bne-	98f			/* out of line -> do syscall */
-
-	/* seconds are xsec >> 20 */
-	rlwinm	r5,r4,12,20,31
-	rlwimi	r5,r3,12,0,19
-	stw	r5,TSPC32_TV_SEC(r11)
 
-	/* get remaining xsec and convert to nsec. we scale
-	 * up remaining xsec by 12 bits and get the top 32 bits
-	 * of the multiplication, then we multiply by 1000
-	 */
-	rlwinm	r5,r4,12,0,19
-	lis	r6,1000000@h
-	ori	r6,r6,1000000@l
-	mulhwu	r5,r5,r6
-	mulli	r5,r5,1000
-	stw	r5,TSPC32_TV_NSEC(r11)
-	mtlr	r12
-	crclr	cr0*4+so
-	li	r3,0
-	blr
+50:	bl	__do_get_tspec@local	/* get sec/nsec from tb & kernel */
+	bne	cr1,80f			/* not monotonic -> all done */
 
 	/*
 	 * CLOCK_MONOTONIC
 	 */
 
-50:	bl	__do_get_xsec@local	/* get xsec from tb & kernel */
-	bne-	98f			/* out of line -> do syscall */
-
-	/* seconds are xsec >> 20 */
-	rlwinm	r6,r4,12,20,31
-	rlwimi	r6,r3,12,0,19
-
-	/* get remaining xsec and convert to nsec. we scale
-	 * up remaining xsec by 12 bits and get the top 32 bits
-	 * of the multiplication, then we multiply by 1000
-	 */
-	rlwinm	r7,r4,12,0,19
-	lis	r5,1000000@h
-	ori	r5,r5,1000000@l
-	mulhwu	r7,r7,r5
-	mulli	r7,r7,1000
-
 	/* now we must fixup using wall to monotonic. We need to snapshot
 	 * that value and do the counter trick again. Fortunately, we still
 	 * have the counter value in r8 that was returned by __do_get_xsec.
-	 * At this point, r6,r7 contain our sec/nsec values, r3,r4 and r5
-	 * can be used
+	 * At this point, r3,r4 contain our sec/nsec values, r5 and r6
+	 * can be used, r7 contains NSEC_PER_SEC.
 	 */
 
-	lwz	r3,WTOM_CLOCK_SEC(r9)
-	lwz	r4,WTOM_CLOCK_NSEC(r9)
+	lwz	r5,WTOM_CLOCK_SEC(r9)
+	lwz	r6,WTOM_CLOCK_NSEC(r9)
 
-	/* We now have our result in r3,r4. We create a fake dependency
-	 * on that result and re-check the counter
+	/* We now have our offset in r5,r6. We create a fake dependency
+	 * on that value and re-check the counter
 	 */
-	or	r5,r4,r3
-	xor	r0,r5,r5
+	or	r0,r6,r5
+	xor	r0,r0,r0
 	add	r9,r9,r0
-#ifdef CONFIG_PPC64
-	lwz	r0,(CFG_TB_UPDATE_COUNT+4)(r9)
-#else
-	lwz	r0,(CFG_TB_UPDATE_COUNT)(r9)
-#endif
+	lwz	r0,(CFG_TB_UPDATE_COUNT+LOPART)(r9)
         cmpl    cr0,r8,r0		/* check if updated */
 	bne-	50b
 
-	/* Calculate and store result. Note that this mimmics the C code,
+	/* Calculate and store result. Note that this mimics the C code,
 	 * which may cause funny results if nsec goes negative... is that
 	 * possible at all ?
 	 */
-	add	r3,r3,r6
-	add	r4,r4,r7
-	lis	r5,NSEC_PER_SEC@h
-	ori	r5,r5,NSEC_PER_SEC@l
-	cmpl	cr0,r4,r5
-	cmpli	cr1,r4,0
+	add	r3,r3,r5
+	add	r4,r4,r6
+	cmpw	cr0,r4,r7
+	cmpwi	cr1,r4,0
 	blt	1f
-	subf	r4,r5,r4
+	subf	r4,r7,r4
 	addi	r3,r3,1
-1:	bge	cr1,1f
+1:	bge	cr1,80f
 	addi	r3,r3,-1
-	add	r4,r4,r5
-1:	stw	r3,TSPC32_TV_SEC(r11)
+	add	r4,r4,r7
+
+80:	stw	r3,TSPC32_TV_SEC(r11)
 	stw	r4,TSPC32_TV_NSEC(r11)
 
 	mtlr	r12
@@ -195,10 +154,6 @@ V_FUNCTION_BEGIN(__kernel_clock_gettime)
 	/*
 	 * syscall fallback
 	 */
-98:
-	mtlr	r12
-	mr	r3,r10
-	mr	r4,r11
 99:
 	li	r0,__NR_clock_gettime
 	sc
@@ -254,11 +209,7 @@ __do_get_xsec:
 	/* Check for update count & load values. We use the low
 	 * order 32 bits of the update count
 	 */
-#ifdef CONFIG_PPC64
-1:	lwz	r8,(CFG_TB_UPDATE_COUNT+4)(r9)
-#else
-1:	lwz	r8,(CFG_TB_UPDATE_COUNT)(r9)
-#endif
+1:	lwz	r8,(CFG_TB_UPDATE_COUNT+LOPART)(r9)
 	andi.	r0,r8,1			/* pending update ? loop */
 	bne-	1b
 	xor	r0,r8,r8		/* create dependency */
@@ -305,11 +256,7 @@ __do_get_xsec:
 	or	r6,r4,r3
 	xor	r0,r6,r6
 	add	r9,r9,r0
-#ifdef CONFIG_PPC64
-	lwz	r0,(CFG_TB_UPDATE_COUNT+4)(r9)
-#else
-	lwz	r0,(CFG_TB_UPDATE_COUNT)(r9)
-#endif
+	lwz	r0,(CFG_TB_UPDATE_COUNT+LOPART)(r9)
         cmpl    cr0,r8,r0		/* check if updated */
 	bne-	1b
 
@@ -322,3 +269,98 @@ __do_get_xsec:
 	 */
 3:	blr
   .cfi_endproc
+
+/*
+ * This is the core of clock_gettime(), it returns the current
+ * time in seconds and nanoseconds in r3 and r4.
+ * It expects the datapage ptr in r9 and doesn't clobber it.
+ * It clobbers r0, r5, r6, r10 and returns NSEC_PER_SEC in r7.
+ * On return, r8 contains the counter value that can be reused.
+ * This clobbers cr0 but not any other cr field.
+ */
+__do_get_tspec:
+  .cfi_startproc
+	/* Check for update count & load values. We use the low
+	 * order 32 bits of the update count
+	 */
+1:	lwz	r8,(CFG_TB_UPDATE_COUNT+LOPART)(r9)
+	andi.	r0,r8,1			/* pending update ? loop */
+	bne-	1b
+	xor	r0,r8,r8		/* create dependency */
+	add	r9,r9,r0
+
+	/* Load orig stamp (offset to TB) */
+	lwz	r5,CFG_TB_ORIG_STAMP(r9)
+	lwz	r6,(CFG_TB_ORIG_STAMP+4)(r9)
+
+	/* Get a stable TB value */
+2:	mftbu	r3
+	mftbl	r4
+	mftbu	r0
+	cmpl	cr0,r3,r0
+	bne-	2b
+
+	/* Subtract tb orig stamp and shift left 12 bits.
+	 */
+	subfc	r7,r6,r4
+	subfe	r0,r5,r3
+	slwi	r0,r0,12
+	rlwimi.	r0,r7,12,20,31
+	slwi	r7,r7,12
+
+	/* Load scale factor & do multiplication */
+	lwz	r5,CFG_TB_TO_XS(r9)	/* load values */
+	lwz	r6,(CFG_TB_TO_XS+4)(r9)
+	mulhwu	r3,r7,r6
+	mullw	r10,r7,r5
+	mulhwu	r4,r7,r5
+	addc	r10,r3,r10
+	li	r3,0
+
+	beq+	4f			/* skip high part computation if 0 */
+	mulhwu	r3,r0,r5
+	mullw	r7,r0,r5
+	mulhwu	r5,r0,r6
+	mullw	r6,r0,r6
+	adde	r4,r4,r7
+	addze	r3,r3
+	addc	r4,r4,r5
+	addze	r3,r3
+	addc	r10,r10,r6
+
+4:	addze	r4,r4			/* add in carry */
+	lis	r7,NSEC_PER_SEC@h
+	ori	r7,r7,NSEC_PER_SEC@l
+	mulhwu	r4,r4,r7		/* convert to nanoseconds */
+
+	/* At this point, we have seconds & nanoseconds since the xtime
+	 * stamp in r3+CA and r4.  Load & add the xtime stamp.
+	 */
+#ifdef CONFIG_PPC64
+	lwz	r5,STAMP_XTIME+TSPC64_TV_SEC+LOPART(r9)
+	lwz	r6,STAMP_XTIME+TSPC64_TV_NSEC+LOPART(r9)
+#else
+	lwz	r5,STAMP_XTIME+TSPC32_TV_SEC(r9)
+	lwz	r6,STAMP_XTIME+TSPC32_TV_NSEC(r9)
+#endif
+	add	r4,r4,r6
+	adde	r3,r3,r5
+
+	/* We now have our result in r3,r4. We create a fake dependency
+	 * on that result and re-check the counter
+	 */
+	or	r6,r4,r3
+	xor	r0,r6,r6
+	add	r9,r9,r0
+	lwz	r0,(CFG_TB_UPDATE_COUNT+LOPART)(r9)
+        cmpl    cr0,r8,r0		/* check if updated */
+	bne-	1b
+
+	/* check for nanosecond overflow and adjust if necessary */
+	cmpw	r4,r7
+	bltlr				/* all done if no overflow */
+	subf	r4,r7,r4		/* adjust if overflow */
+	addi	r3,r3,1
+
+	blr
+  .cfi_endproc
diff --git a/arch/powerpc/kernel/vdso64/gettimeofday.S b/arch/powerpc/kernel/vdso64/gettimeofday.S
index c6401f9e37f1..262cd5857a56 100644
--- a/arch/powerpc/kernel/vdso64/gettimeofday.S
+++ b/arch/powerpc/kernel/vdso64/gettimeofday.S
@@ -75,90 +75,49 @@ V_FUNCTION_BEGIN(__kernel_clock_gettime)
 
 	mflr	r12			/* r12 saves lr */
   .cfi_register lr,r12
-	mr	r10,r3			/* r10 saves id */
 	mr	r11,r4			/* r11 saves tp */
 	bl	V_LOCAL_FUNC(__get_datapage)	/* get data page */
-	beq	cr1,50f			/* if monotonic -> jump there */
-
-	/*
-	 * CLOCK_REALTIME
-	 */
-
-	bl	V_LOCAL_FUNC(__do_get_xsec)	/* get xsec from tb & kernel */
-
-	lis     r7,15			/* r7 = 1000000 = USEC_PER_SEC */
-	ori     r7,r7,16960
-	rldicl  r5,r4,44,20		/* r5 = sec = xsec / XSEC_PER_SEC */
-	rldicr  r6,r5,20,43		/* r6 = sec * XSEC_PER_SEC */
-	std	r5,TSPC64_TV_SEC(r11)	/* store sec in tv */
-	subf	r0,r6,r4		/* r0 = xsec = (xsec - r6) */
-	mulld   r0,r0,r7		/* usec = (xsec * USEC_PER_SEC) /
-					 * XSEC_PER_SEC
-					 */
-	rldicl  r0,r0,44,20
-	mulli	r0,r0,1000		/* nsec = usec * 1000 */
-	std	r0,TSPC64_TV_NSEC(r11)	/* store nsec in tp */
-
-	mtlr	r12
-	crclr	cr0*4+so
-	li	r3,0
-	blr
+50:	bl	V_LOCAL_FUNC(__do_get_tspec)	/* get time from tb & kernel */
+	bne	cr1,80f			/* if not monotonic, all done */
 
 	/*
 	 * CLOCK_MONOTONIC
 	 */
 
-50:	bl	V_LOCAL_FUNC(__do_get_xsec)	/* get xsec from tb & kernel */
-
-	lis     r7,15			/* r7 = 1000000 = USEC_PER_SEC */
-	ori     r7,r7,16960
-	rldicl  r5,r4,44,20		/* r5 = sec = xsec / XSEC_PER_SEC */
-	rldicr  r6,r5,20,43		/* r6 = sec * XSEC_PER_SEC */
-	subf	r0,r6,r4		/* r0 = xsec = (xsec - r6) */
-	mulld   r0,r0,r7		/* usec = (xsec * USEC_PER_SEC) /
-					 * XSEC_PER_SEC
-					 */
-	rldicl  r6,r0,44,20
-	mulli	r6,r6,1000		/* nsec = usec * 1000 */
-
 	/* now we must fixup using wall to monotonic. We need to snapshot
 	 * that value and do the counter trick again. Fortunately, we still
-	 * have the counter value in r8 that was returned by __do_get_xsec.
-	 * At this point, r5,r6 contain our sec/nsec values.
-	 * can be used
+	 * have the counter value in r8 that was returned by __do_get_tspec.
+	 * At this point, r4,r5 contain our sec/nsec values.
 	 */
 
-	lwa	r4,WTOM_CLOCK_SEC(r3)
-	lwa	r7,WTOM_CLOCK_NSEC(r3)
+	lwa	r6,WTOM_CLOCK_SEC(r3)
+	lwa	r9,WTOM_CLOCK_NSEC(r3)
 
-	/* We now have our result in r4,r7. We create a fake dependency
+	/* We now have our result in r6,r9. We create a fake dependency
 	 * on that result and re-check the counter
 	 */
-	or	r9,r4,r7
-	xor	r0,r9,r9
+	or	r0,r6,r9
+	xor	r0,r0,r0
 	add	r3,r3,r0
 	ld	r0,CFG_TB_UPDATE_COUNT(r3)
         cmpld   cr0,r0,r8		/* check if updated */
 	bne-	50b
 
-	/* Calculate and store result. Note that this mimmics the C code,
-	 * which may cause funny results if nsec goes negative... is that
-	 * possible at all ?
+	/* Add wall->monotonic offset and check for overflow or underflow.
 	 */
-	add	r4,r4,r5
-	add	r7,r7,r6
-	lis	r9,NSEC_PER_SEC@h
-	ori	r9,r9,NSEC_PER_SEC@l
-	cmpl	cr0,r7,r9
-	cmpli	cr1,r7,0
+	add	r4,r4,r6
+	add	r5,r5,r9
+	cmpd	cr0,r5,r7
+	cmpdi	cr1,r5,0
 	blt	1f
-	subf	r7,r9,r7
+	subf	r5,r7,r5
 	addi	r4,r4,1
-1:	bge	cr1,1f
+1:	bge	cr1,80f
 	addi	r4,r4,-1
-	add	r7,r7,r9
-1:	std	r4,TSPC64_TV_SEC(r11)
-	std	r7,TSPC64_TV_NSEC(r11)
+	add	r5,r5,r7
+
+80:	std	r4,TSPC64_TV_SEC(r11)
+	std	r5,TSPC64_TV_NSEC(r11)
 
 	mtlr	r12
 	crclr	cr0*4+so
@@ -168,10 +127,6 @@ V_FUNCTION_BEGIN(__kernel_clock_gettime)
 	/*
 	 * syscall fallback
 	 */
-98:
-	mtlr	r12
-	mr	r3,r10
-	mr	r4,r11
 99:
 	li	r0,__NR_clock_gettime
 	sc
@@ -253,3 +208,59 @@ V_FUNCTION_BEGIN(__do_get_xsec)
 	blr
   .cfi_endproc
 V_FUNCTION_END(__do_get_xsec)
+
+/*
+ * This is the core of clock_gettime(), it returns the current
+ * time in seconds and nanoseconds in r4 and r5.
+ * It expects the datapage ptr in r3 and doesn't clobber it.
+ * It clobbers r0 and r6 and returns NSEC_PER_SEC in r7.
+ * On return, r8 contains the counter value that can be reused.
+ * This clobbers cr0 but not any other cr field.
+ */
+V_FUNCTION_BEGIN(__do_get_tspec)
+  .cfi_startproc
+	/* check for update count & load values */
+1:	ld	r8,CFG_TB_UPDATE_COUNT(r3)
+	andi.	r0,r8,1			/* pending update ? loop */
+	bne-	1b
+	xor	r0,r8,r8		/* create dependency */
+	add	r3,r3,r0
+
+	/* Get TB & offset it. We use the MFTB macro which will generate
+	 * workaround code for Cell.
+	 */
+	MFTB(r7)
+	ld	r9,CFG_TB_ORIG_STAMP(r3)
+	subf	r7,r9,r7
+
+	/* Scale result */
+	ld	r5,CFG_TB_TO_XS(r3)
+	sldi	r7,r7,12		/* compute time since stamp_xtime */
+	mulhdu	r6,r7,r5		/* in units of 2^-32 seconds */
+
+	/* Add stamp since epoch */
+	ld	r4,STAMP_XTIME+TSPC64_TV_SEC(r3)
+	ld	r5,STAMP_XTIME+TSPC64_TV_NSEC(r3)
+	or	r0,r4,r5
+	or	r0,r0,r6
+	xor	r0,r0,r0
+	add	r3,r3,r0
+	ld	r0,CFG_TB_UPDATE_COUNT(r3)
+	cmpld   r0,r8			/* check if updated */
+	bne-	1b			/* reload if so */
+
+	/* convert to seconds & nanoseconds and add to stamp */
+	lis	r7,NSEC_PER_SEC@h
+	ori	r7,r7,NSEC_PER_SEC@l
+	mulhwu	r0,r6,r7		/* compute nanoseconds and */
+	srdi	r6,r6,32		/* seconds since stamp_xtime */
+	clrldi	r0,r0,32
+	add	r5,r5,r0		/* add nanoseconds together */
+	cmpd	r5,r7			/* overflow? */
+	add	r4,r4,r6
+	bltlr				/* all done if no overflow */
+	subf	r5,r7,r5		/* if overflow, adjust */
+	addi	r4,r4,1
+	blr
+  .cfi_endproc
+V_FUNCTION_END(__do_get_tspec)
diff --git a/arch/powerpc/kernel/vio.c b/arch/powerpc/kernel/vio.c
index a11e6bc59b30..94aa7b011b27 100644
--- a/arch/powerpc/kernel/vio.c
+++ b/arch/powerpc/kernel/vio.c
@@ -41,9 +41,9 @@
 static struct bus_type vio_bus_type;
 
 static struct vio_dev vio_bus_device  = { /* fake "parent" device */
-	.name = vio_bus_device.dev.bus_id,
+	.name = "vio",
 	.type = "",
-	.dev.bus_id = "vio",
+	.dev.init_name = "vio",
 	.dev.bus = &vio_bus_type,
 };
 
@@ -1216,7 +1216,7 @@ struct vio_dev *vio_register_device_node(struct device_node *of_node)
 
 	viodev->irq = irq_of_parse_and_map(of_node, 0);
 
-	snprintf(viodev->dev.bus_id, BUS_ID_SIZE, "%x", *unit_address);
+	dev_set_name(&viodev->dev, "%x", *unit_address);
 	viodev->name = of_node->name;
 	viodev->type = of_node->type;
 	viodev->unit_address = *unit_address;
@@ -1243,7 +1243,7 @@ struct vio_dev *vio_register_device_node(struct device_node *of_node)
 	/* register with generic device framework */
 	if (device_register(&viodev->dev)) {
 		printk(KERN_ERR "%s: failed to register device %s\n",
-				__func__, viodev->dev.bus_id);
+				__func__, dev_name(&viodev->dev));
 		/* XXX free TCE table */
 		kfree(viodev);
 		return NULL;
@@ -1400,13 +1400,13 @@ static struct vio_dev *vio_find_name(const char *name)
 struct vio_dev *vio_find_node(struct device_node *vnode)
 {
 	const uint32_t *unit_address;
-	char kobj_name[BUS_ID_SIZE];
+	char kobj_name[20];
 
 	/* construct the kobject name from the device node */
 	unit_address = of_get_property(vnode, "reg", NULL);
 	if (!unit_address)
 		return NULL;
-	snprintf(kobj_name, BUS_ID_SIZE, "%x", *unit_address);
+	snprintf(kobj_name, sizeof(kobj_name), "%x", *unit_address);
 
 	return vio_find_name(kobj_name);
 }
diff --git a/arch/powerpc/lib/copyuser_64.S b/arch/powerpc/lib/copyuser_64.S
index 25ec5378afa4..70693a5c12a1 100644
--- a/arch/powerpc/lib/copyuser_64.S
+++ b/arch/powerpc/lib/copyuser_64.S
@@ -26,11 +26,24 @@ _GLOBAL(__copy_tofrom_user)
 	andi.	r6,r6,7
 	PPC_MTOCRF	0x01,r5
 	blt	cr1,.Lshort_copy
+/* Below we want to nop out the bne if we're on a CPU that has the
+ * CPU_FTR_UNALIGNED_LD_STD bit set and the CPU_FTR_CP_USE_DCBTZ bit
+ * cleared.
+ * At the time of writing the only CPU that has this combination of bits
+ * set is Power6.
+ */
+BEGIN_FTR_SECTION
+	nop
+FTR_SECTION_ELSE
 	bne	.Ldst_unaligned
+ALT_FTR_SECTION_END(CPU_FTR_UNALIGNED_LD_STD | CPU_FTR_CP_USE_DCBTZ, \
+		    CPU_FTR_UNALIGNED_LD_STD)
 .Ldst_aligned:
-	andi.	r0,r4,7
 	addi	r3,r3,-16
+BEGIN_FTR_SECTION
+	andi.	r0,r4,7
 	bne	.Lsrc_unaligned
+END_FTR_SECTION_IFCLR(CPU_FTR_UNALIGNED_LD_STD)
 	srdi	r7,r5,4
 20:	ld	r9,0(r4)
 	addi	r4,r4,-8
@@ -138,7 +151,7 @@ _GLOBAL(__copy_tofrom_user)
 	PPC_MTOCRF	0x01,r6		/* put #bytes to 8B bdry into cr7 */
 	subf	r5,r6,r5
 	li	r7,0
-	cmpldi	r1,r5,16
+	cmpldi	cr1,r5,16
 	bf	cr7*4+3,1f
 35:	lbz	r0,0(r4)
 81:	stb	r0,0(r3)
diff --git a/arch/powerpc/lib/dma-noncoherent.c b/arch/powerpc/lib/dma-noncoherent.c
index 31734c0969cd..2b1ce1849344 100644
--- a/arch/powerpc/lib/dma-noncoherent.c
+++ b/arch/powerpc/lib/dma-noncoherent.c
@@ -320,7 +320,6 @@ static int __init dma_alloc_init(void)
 			ret = -ENOMEM;
 			break;
 		}
-		WARN_ON(!pmd_none(*pmd));
 
 		pte = pte_alloc_kernel(pmd, CONSISTENT_BASE);
 		if (!pte) {
diff --git a/arch/powerpc/lib/memcpy_64.S b/arch/powerpc/lib/memcpy_64.S
index 3f131129d1c1..fe2d34e5332d 100644
--- a/arch/powerpc/lib/memcpy_64.S
+++ b/arch/powerpc/lib/memcpy_64.S
@@ -18,11 +18,23 @@ _GLOBAL(memcpy)
 	andi.	r6,r6,7
 	dcbt	0,r4
 	blt	cr1,.Lshort_copy
+/* Below we want to nop out the bne if we're on a CPU that has the
+   CPU_FTR_UNALIGNED_LD_STD bit set and the CPU_FTR_CP_USE_DCBTZ bit
+   cleared.
+   At the time of writing the only CPU that has this combination of bits
+   set is Power6. */
+BEGIN_FTR_SECTION
+	nop
+FTR_SECTION_ELSE
 	bne	.Ldst_unaligned
+ALT_FTR_SECTION_END(CPU_FTR_UNALIGNED_LD_STD | CPU_FTR_CP_USE_DCBTZ, \
+                    CPU_FTR_UNALIGNED_LD_STD)
 .Ldst_aligned:
-	andi.	r0,r4,7
 	addi	r3,r3,-16
+BEGIN_FTR_SECTION
+	andi.	r0,r4,7
 	bne	.Lsrc_unaligned
+END_FTR_SECTION_IFCLR(CPU_FTR_UNALIGNED_LD_STD)
 	srdi	r7,r5,4
 	ld	r9,0(r4)
 	addi	r4,r4,-8
@@ -131,7 +143,7 @@ _GLOBAL(memcpy)
 	PPC_MTOCRF	0x01,r6		# put #bytes to 8B bdry into cr7
 	subf	r5,r6,r5
 	li	r7,0
-	cmpldi	r1,r5,16
+	cmpldi	cr1,r5,16
 	bf	cr7*4+3,1f
 	lbz	r0,0(r4)
 	stb	r0,0(r3)
diff --git a/arch/powerpc/math-emu/Makefile b/arch/powerpc/math-emu/Makefile
index 03aa98dd9f0a..f9e506a735ae 100644
--- a/arch/powerpc/math-emu/Makefile
+++ b/arch/powerpc/math-emu/Makefile
@@ -11,6 +11,8 @@ obj-$(CONFIG_MATH_EMULATION)	+= fabs.o fadd.o fadds.o fcmpo.o fcmpu.o \
 					mcrfs.o mffs.o mtfsb0.o mtfsb1.o \
 					mtfsf.o mtfsfi.o stfiwx.o stfs.o
 
+obj-$(CONFIG_SPE)		+= math_efp.o
+
 CFLAGS_fabs.o = -fno-builtin-fabs
 CFLAGS_math.o = -fno-builtin-fabs
 
diff --git a/arch/powerpc/math-emu/fadd.c b/arch/powerpc/math-emu/fadd.c
index 04d3b4aa32ce..0158a16e2b82 100644
--- a/arch/powerpc/math-emu/fadd.c
+++ b/arch/powerpc/math-emu/fadd.c
@@ -13,7 +13,6 @@ fadd(void *frD, void *frA, void *frB)
 	FP_DECL_D(B);
 	FP_DECL_D(R);
 	FP_DECL_EX;
-	int ret = 0;
 
 #ifdef DEBUG
 	printk("%s: %p %p %p\n", __func__, frD, frA, frB);
diff --git a/arch/powerpc/math-emu/fcmpo.c b/arch/powerpc/math-emu/fcmpo.c
index b5dc4498cd71..5bce011c2aec 100644
--- a/arch/powerpc/math-emu/fcmpo.c
+++ b/arch/powerpc/math-emu/fcmpo.c
@@ -14,7 +14,6 @@ fcmpo(u32 *ccr, int crfD, void *frA, void *frB)
 	FP_DECL_EX;
 	int code[4] = { (1 << 3), (1 << 1), (1 << 2), (1 << 0) };
 	long cmp;
-	int ret = 0;
 
 #ifdef DEBUG
 	printk("%s: %p (%08x) %d %p %p\n", __func__, ccr, *ccr, crfD, frA, frB);
@@ -29,7 +28,7 @@ fcmpo(u32 *ccr, int crfD, void *frA, void *frB)
 #endif
 
 	if (A_c == FP_CLS_NAN || B_c == FP_CLS_NAN)
-		ret |= EFLAG_VXVC;
+		FP_SET_EXCEPTION(EFLAG_VXVC);
 
 	FP_CMP_D(cmp, A, B, 2);
 	cmp = code[(cmp + 1) & 3];
@@ -44,5 +43,5 @@ fcmpo(u32 *ccr, int crfD, void *frA, void *frB)
 	printk("CR: %08x\n", *ccr);
 #endif
 
-	return ret;
+	return FP_CUR_EXCEPTIONS;
 }
diff --git a/arch/powerpc/math-emu/fdiv.c b/arch/powerpc/math-emu/fdiv.c
index 2db15097d98e..a29239c05e3e 100644
--- a/arch/powerpc/math-emu/fdiv.c
+++ b/arch/powerpc/math-emu/fdiv.c
@@ -13,7 +13,6 @@ fdiv(void *frD, void *frA, void *frB)
 	FP_DECL_D(B);
 	FP_DECL_D(R);
 	FP_DECL_EX;
-	int ret = 0;
 
 #ifdef DEBUG
 	printk("%s: %p %p %p\n", __func__, frD, frA, frB);
@@ -28,22 +27,22 @@ fdiv(void *frD, void *frA, void *frB)
 #endif
 
 	if (A_c == FP_CLS_ZERO && B_c == FP_CLS_ZERO) {
-		ret |= EFLAG_VXZDZ;
+		FP_SET_EXCEPTION(EFLAG_VXZDZ);
 #ifdef DEBUG
 		printk("%s: FPSCR_VXZDZ raised\n", __func__);
 #endif
 	}
 	if (A_c == FP_CLS_INF && B_c == FP_CLS_INF) {
-		ret |= EFLAG_VXIDI;
+		FP_SET_EXCEPTION(EFLAG_VXIDI);
 #ifdef DEBUG
 		printk("%s: FPSCR_VXIDI raised\n", __func__);
 #endif
 	}
 
 	if (B_c == FP_CLS_ZERO && A_c != FP_CLS_ZERO) {
-		ret |= EFLAG_DIVZERO;
+		FP_SET_EXCEPTION(EFLAG_DIVZERO);
 		if (__FPU_TRAP_P(EFLAG_DIVZERO))
-			return ret;
+			return FP_CUR_EXCEPTIONS;
 	}
 	FP_DIV_D(R, A, B);
 
diff --git a/arch/powerpc/math-emu/fdivs.c b/arch/powerpc/math-emu/fdivs.c
index 797f6a9a20b5..526bc261275f 100644
--- a/arch/powerpc/math-emu/fdivs.c
+++ b/arch/powerpc/math-emu/fdivs.c
@@ -14,7 +14,6 @@ fdivs(void *frD, void *frA, void *frB)
 	FP_DECL_D(B);
 	FP_DECL_D(R);
 	FP_DECL_EX;
-	int ret = 0;
 
 #ifdef DEBUG
 	printk("%s: %p %p %p\n", __func__, frD, frA, frB);
@@ -29,22 +28,22 @@ fdivs(void *frD, void *frA, void *frB)
 #endif
 
 	if (A_c == FP_CLS_ZERO && B_c == FP_CLS_ZERO) {
-		ret |= EFLAG_VXZDZ;
+		FP_SET_EXCEPTION(EFLAG_VXZDZ);
 #ifdef DEBUG
 		printk("%s: FPSCR_VXZDZ raised\n", __func__);
 #endif
 	}
 	if (A_c == FP_CLS_INF && B_c == FP_CLS_INF) {
-		ret |= EFLAG_VXIDI;
+		FP_SET_EXCEPTION(EFLAG_VXIDI);
 #ifdef DEBUG
 		printk("%s: FPSCR_VXIDI raised\n", __func__);
 #endif
 	}
 
 	if (B_c == FP_CLS_ZERO && A_c != FP_CLS_ZERO) {
-		ret |= EFLAG_DIVZERO;
+		FP_SET_EXCEPTION(EFLAG_DIVZERO);
 		if (__FPU_TRAP_P(EFLAG_DIVZERO))
-			return ret;
+			return FP_CUR_EXCEPTIONS;
 	}
 
 	FP_DIV_D(R, A, B);
diff --git a/arch/powerpc/math-emu/fmadd.c b/arch/powerpc/math-emu/fmadd.c
index 925313aa6f82..8c3f20aa5a95 100644
--- a/arch/powerpc/math-emu/fmadd.c
+++ b/arch/powerpc/math-emu/fmadd.c
@@ -15,7 +15,6 @@ fmadd(void *frD, void *frA, void *frB, void *frC)
 	FP_DECL_D(C);
 	FP_DECL_D(T);
 	FP_DECL_EX;
-	int ret = 0;
 
 #ifdef DEBUG
 	printk("%s: %p %p %p %p\n", __func__, frD, frA, frB, frC);
@@ -33,12 +32,12 @@ fmadd(void *frD, void *frA, void *frB, void *frC)
 
 	if ((A_c == FP_CLS_INF && C_c == FP_CLS_ZERO) ||
 	    (A_c == FP_CLS_ZERO && C_c == FP_CLS_INF))
-                ret |= EFLAG_VXIMZ;
+                FP_SET_EXCEPTION(EFLAG_VXIMZ);
 
 	FP_MUL_D(T, A, C);
 
 	if (T_s != B_s && T_c == FP_CLS_INF && B_c == FP_CLS_INF)
-		ret |= EFLAG_VXISI;
+		FP_SET_EXCEPTION(EFLAG_VXISI);
 
 	FP_ADD_D(R, T, B);
 
diff --git a/arch/powerpc/math-emu/fmadds.c b/arch/powerpc/math-emu/fmadds.c
index aea80ef79399..794fb31e59d1 100644
--- a/arch/powerpc/math-emu/fmadds.c
+++ b/arch/powerpc/math-emu/fmadds.c
@@ -16,7 +16,6 @@ fmadds(void *frD, void *frA, void *frB, void *frC)
 	FP_DECL_D(C);
 	FP_DECL_D(T);
 	FP_DECL_EX;
-	int ret = 0;
 
 #ifdef DEBUG
 	printk("%s: %p %p %p %p\n", __func__, frD, frA, frB, frC);
@@ -34,12 +33,12 @@ fmadds(void *frD, void *frA, void *frB, void *frC)
 
 	if ((A_c == FP_CLS_INF && C_c == FP_CLS_ZERO) ||
 	    (A_c == FP_CLS_ZERO && C_c == FP_CLS_INF))
-                ret |= EFLAG_VXIMZ;
+                FP_SET_EXCEPTION(EFLAG_VXIMZ);
 
 	FP_MUL_D(T, A, C);
 
 	if (T_s != B_s && T_c == FP_CLS_INF && B_c == FP_CLS_INF)
-		ret |= EFLAG_VXISI;
+		FP_SET_EXCEPTION(EFLAG_VXISI);
 
 	FP_ADD_D(R, T, B);
 
diff --git a/arch/powerpc/math-emu/fmsub.c b/arch/powerpc/math-emu/fmsub.c
index a644d525fca6..626f6fed84ac 100644
--- a/arch/powerpc/math-emu/fmsub.c
+++ b/arch/powerpc/math-emu/fmsub.c
@@ -15,7 +15,6 @@ fmsub(void *frD, void *frA, void *frB, void *frC)
 	FP_DECL_D(C);
 	FP_DECL_D(T);
 	FP_DECL_EX;
-	int ret = 0;
 
 #ifdef DEBUG
 	printk("%s: %p %p %p %p\n", __func__, frD, frA, frB, frC);
@@ -33,7 +32,7 @@ fmsub(void *frD, void *frA, void *frB, void *frC)
 
 	if ((A_c == FP_CLS_INF && C_c == FP_CLS_ZERO) ||
 	    (A_c == FP_CLS_ZERO && C_c == FP_CLS_INF))
-		ret |= EFLAG_VXIMZ;
+		FP_SET_EXCEPTION(EFLAG_VXIMZ);
 
 	FP_MUL_D(T, A, C);
 
@@ -41,7 +40,7 @@ fmsub(void *frD, void *frA, void *frB, void *frC)
 		B_s ^= 1;
 
 	if (T_s != B_s && T_c == FP_CLS_INF && B_c == FP_CLS_INF)
-		ret |= EFLAG_VXISI;
+		FP_SET_EXCEPTION(EFLAG_VXISI);
 
 	FP_ADD_D(R, T, B);
 
diff --git a/arch/powerpc/math-emu/fmsubs.c b/arch/powerpc/math-emu/fmsubs.c
index 2fdeeb9bb569..3425bc899760 100644
--- a/arch/powerpc/math-emu/fmsubs.c
+++ b/arch/powerpc/math-emu/fmsubs.c
@@ -16,7 +16,6 @@ fmsubs(void *frD, void *frA, void *frB, void *frC)
 	FP_DECL_D(C);
 	FP_DECL_D(T);
 	FP_DECL_EX;
-	int ret = 0;
 
 #ifdef DEBUG
 	printk("%s: %p %p %p %p\n", __func__, frD, frA, frB, frC);
@@ -34,7 +33,7 @@ fmsubs(void *frD, void *frA, void *frB, void *frC)
 
 	if ((A_c == FP_CLS_INF && C_c == FP_CLS_ZERO) ||
 	    (A_c == FP_CLS_ZERO && C_c == FP_CLS_INF))
-		ret |= EFLAG_VXIMZ;
+		FP_SET_EXCEPTION(EFLAG_VXIMZ);
 
 	FP_MUL_D(T, A, C);
 
@@ -42,7 +41,7 @@ fmsubs(void *frD, void *frA, void *frB, void *frC)
 		B_s ^= 1;
 
 	if (T_s != B_s && T_c == FP_CLS_INF && B_c == FP_CLS_INF)
-		ret |= EFLAG_VXISI;
+		FP_SET_EXCEPTION(EFLAG_VXISI);
 
 	FP_ADD_D(R, T, B);
 
diff --git a/arch/powerpc/math-emu/fmul.c b/arch/powerpc/math-emu/fmul.c
index 391fd17d3440..2c1929779892 100644
--- a/arch/powerpc/math-emu/fmul.c
+++ b/arch/powerpc/math-emu/fmul.c
@@ -13,7 +13,6 @@ fmul(void *frD, void *frA, void *frB)
 	FP_DECL_D(B);
 	FP_DECL_D(R);
 	FP_DECL_EX;
-	int ret = 0;
 
 #ifdef DEBUG
 	printk("%s: %p %p %p\n", __func__, frD, frA, frB);
@@ -31,7 +30,7 @@ fmul(void *frD, void *frA, void *frB)
 
 	if ((A_c == FP_CLS_INF && B_c == FP_CLS_ZERO) ||
 	    (A_c == FP_CLS_ZERO && B_c == FP_CLS_INF))
-		ret |= EFLAG_VXIMZ;
+		FP_SET_EXCEPTION(EFLAG_VXIMZ);
 
 	FP_MUL_D(R, A, B);
 
diff --git a/arch/powerpc/math-emu/fmuls.c b/arch/powerpc/math-emu/fmuls.c
index 2d3ec5f7da20..f5ad5c9c77d0 100644
--- a/arch/powerpc/math-emu/fmuls.c
+++ b/arch/powerpc/math-emu/fmuls.c
@@ -14,7 +14,6 @@ fmuls(void *frD, void *frA, void *frB)
 	FP_DECL_D(B);
 	FP_DECL_D(R);
 	FP_DECL_EX;
-	int ret = 0;
 
 #ifdef DEBUG
 	printk("%s: %p %p %p\n", __func__, frD, frA, frB);
@@ -32,7 +31,7 @@ fmuls(void *frD, void *frA, void *frB)
 
 	if ((A_c == FP_CLS_INF && B_c == FP_CLS_ZERO) ||
 	    (A_c == FP_CLS_ZERO && B_c == FP_CLS_INF))
-		ret |= EFLAG_VXIMZ;
+		FP_SET_EXCEPTION(EFLAG_VXIMZ);
 
 	FP_MUL_D(R, A, B);
 
diff --git a/arch/powerpc/math-emu/fnmadd.c b/arch/powerpc/math-emu/fnmadd.c
index 2497b86494e5..e817bc5453ef 100644
--- a/arch/powerpc/math-emu/fnmadd.c
+++ b/arch/powerpc/math-emu/fnmadd.c
@@ -15,7 +15,6 @@ fnmadd(void *frD, void *frA, void *frB, void *frC)
 	FP_DECL_D(C);
 	FP_DECL_D(T);
 	FP_DECL_EX;
-	int ret = 0;
 
 #ifdef DEBUG
 	printk("%s: %p %p %p %p\n", __func__, frD, frA, frB, frC);
@@ -33,12 +32,12 @@ fnmadd(void *frD, void *frA, void *frB, void *frC)
 
 	if ((A_c == FP_CLS_INF && C_c == FP_CLS_ZERO) ||
 	    (A_c == FP_CLS_ZERO && C_c == FP_CLS_INF))
-                ret |= EFLAG_VXIMZ;
+                FP_SET_EXCEPTION(EFLAG_VXIMZ);
 
 	FP_MUL_D(T, A, C);
 
 	if (T_s != B_s && T_c == FP_CLS_INF && B_c == FP_CLS_INF)
-		ret |= EFLAG_VXISI;
+		FP_SET_EXCEPTION(EFLAG_VXISI);
 
 	FP_ADD_D(R, T, B);
 
diff --git a/arch/powerpc/math-emu/fnmadds.c b/arch/powerpc/math-emu/fnmadds.c
index ee9d71e0b376..4db4b7d9ba8d 100644
--- a/arch/powerpc/math-emu/fnmadds.c
+++ b/arch/powerpc/math-emu/fnmadds.c
@@ -16,7 +16,6 @@ fnmadds(void *frD, void *frA, void *frB, void *frC)
 	FP_DECL_D(C);
 	FP_DECL_D(T);
 	FP_DECL_EX;
-	int ret = 0;
 
 #ifdef DEBUG
 	printk("%s: %p %p %p %p\n", __func__, frD, frA, frB, frC);
@@ -34,12 +33,12 @@ fnmadds(void *frD, void *frA, void *frB, void *frC)
 
 	if ((A_c == FP_CLS_INF && C_c == FP_CLS_ZERO) ||
 	    (A_c == FP_CLS_ZERO && C_c == FP_CLS_INF))
-                ret |= EFLAG_VXIMZ;
+                FP_SET_EXCEPTION(EFLAG_VXIMZ);
 
 	FP_MUL_D(T, A, C);
 
 	if (T_s != B_s && T_c == FP_CLS_INF && B_c == FP_CLS_INF)
-		ret |= EFLAG_VXISI;
+		FP_SET_EXCEPTION(EFLAG_VXISI);
 
 	FP_ADD_D(R, T, B);
 
diff --git a/arch/powerpc/math-emu/fnmsub.c b/arch/powerpc/math-emu/fnmsub.c
index 3885a77acc93..f65979fa770e 100644
--- a/arch/powerpc/math-emu/fnmsub.c
+++ b/arch/powerpc/math-emu/fnmsub.c
@@ -15,7 +15,6 @@ fnmsub(void *frD, void *frA, void *frB, void *frC)
 	FP_DECL_D(C);
 	FP_DECL_D(T);
 	FP_DECL_EX;
-	int ret = 0;
 
 #ifdef DEBUG
 	printk("%s: %p %p %p %p\n", __func__, frD, frA, frB, frC);
@@ -33,7 +32,7 @@ fnmsub(void *frD, void *frA, void *frB, void *frC)
 
 	if ((A_c == FP_CLS_INF && C_c == FP_CLS_ZERO) ||
 	    (A_c == FP_CLS_ZERO && C_c == FP_CLS_INF))
-		ret |= EFLAG_VXIMZ;
+		FP_SET_EXCEPTION(EFLAG_VXIMZ);
 
 	FP_MUL_D(T, A, C);
 
@@ -41,7 +40,7 @@ fnmsub(void *frD, void *frA, void *frB, void *frC)
 		B_s ^= 1;
 
 	if (T_s != B_s && T_c == FP_CLS_INF && B_c == FP_CLS_INF)
-		ret |= EFLAG_VXISI;
+		FP_SET_EXCEPTION(EFLAG_VXISI);
 
 	FP_ADD_D(R, T, B);
 
diff --git a/arch/powerpc/math-emu/fnmsubs.c b/arch/powerpc/math-emu/fnmsubs.c
index f835dfeb0fd1..9021dacc03b8 100644
--- a/arch/powerpc/math-emu/fnmsubs.c
+++ b/arch/powerpc/math-emu/fnmsubs.c
@@ -16,7 +16,6 @@ fnmsubs(void *frD, void *frA, void *frB, void *frC)
 	FP_DECL_D(C);
 	FP_DECL_D(T);
 	FP_DECL_EX;
-	int ret = 0;
 
 #ifdef DEBUG
 	printk("%s: %p %p %p %p\n", __func__, frD, frA, frB, frC);
@@ -34,7 +33,7 @@ fnmsubs(void *frD, void *frA, void *frB, void *frC)
 
 	if ((A_c == FP_CLS_INF && C_c == FP_CLS_ZERO) ||
 	    (A_c == FP_CLS_ZERO && C_c == FP_CLS_INF))
-		ret |= EFLAG_VXIMZ;
+		FP_SET_EXCEPTION(EFLAG_VXIMZ);
 
 	FP_MUL_D(T, A, C);
 
@@ -42,7 +41,7 @@ fnmsubs(void *frD, void *frA, void *frB, void *frC)
 		B_s ^= 1;
 
 	if (T_s != B_s && T_c == FP_CLS_INF && B_c == FP_CLS_INF)
-		ret |= EFLAG_VXISI;
+		FP_SET_EXCEPTION(EFLAG_VXISI);
 
 	FP_ADD_D(R, T, B);
 
diff --git a/arch/powerpc/math-emu/fsqrt.c b/arch/powerpc/math-emu/fsqrt.c
index 3e90072693a0..a55fc7d49983 100644
--- a/arch/powerpc/math-emu/fsqrt.c
+++ b/arch/powerpc/math-emu/fsqrt.c
@@ -12,7 +12,6 @@ fsqrt(void *frD, void *frB)
 	FP_DECL_D(B);
 	FP_DECL_D(R);
 	FP_DECL_EX;
-	int ret = 0;
 
 #ifdef DEBUG
 	printk("%s: %p %p %p %p\n", __func__, frD, frB);
@@ -25,9 +24,9 @@ fsqrt(void *frD, void *frB)
 #endif
 
 	if (B_s && B_c != FP_CLS_ZERO)
-		ret |= EFLAG_VXSQRT;
+		FP_SET_EXCEPTION(EFLAG_VXSQRT);
 	if (B_c == FP_CLS_NAN)
-		ret |= EFLAG_VXSNAN;
+		FP_SET_EXCEPTION(EFLAG_VXSNAN);
 
 	FP_SQRT_D(R, B);
 
diff --git a/arch/powerpc/math-emu/fsqrts.c b/arch/powerpc/math-emu/fsqrts.c
index 2843be986e2e..31dccbfc39ff 100644
--- a/arch/powerpc/math-emu/fsqrts.c
+++ b/arch/powerpc/math-emu/fsqrts.c
@@ -13,7 +13,6 @@ fsqrts(void *frD, void *frB)
 	FP_DECL_D(B);
 	FP_DECL_D(R);
 	FP_DECL_EX;
-	int ret = 0;
 
 #ifdef DEBUG
 	printk("%s: %p %p %p %p\n", __func__, frD, frB);
@@ -26,9 +25,9 @@ fsqrts(void *frD, void *frB)
 #endif
 
 	if (B_s && B_c != FP_CLS_ZERO)
-		ret |= EFLAG_VXSQRT;
+		FP_SET_EXCEPTION(EFLAG_VXSQRT);
 	if (B_c == FP_CLS_NAN)
-		ret |= EFLAG_VXSNAN;
+		FP_SET_EXCEPTION(EFLAG_VXSNAN);
 
 	FP_SQRT_D(R, B);
 
diff --git a/arch/powerpc/math-emu/fsub.c b/arch/powerpc/math-emu/fsub.c
index 78b09446a0e1..02c5dff458ba 100644
--- a/arch/powerpc/math-emu/fsub.c
+++ b/arch/powerpc/math-emu/fsub.c
@@ -13,7 +13,6 @@ fsub(void *frD, void *frA, void *frB)
 	FP_DECL_D(B);
 	FP_DECL_D(R);
 	FP_DECL_EX;
-	int ret = 0;
 
 #ifdef DEBUG
 	printk("%s: %p %p %p\n", __func__, frD, frA, frB);
@@ -31,7 +30,7 @@ fsub(void *frD, void *frA, void *frB)
 		B_s ^= 1;
 
 	if (A_s != B_s && A_c == FP_CLS_INF && B_c == FP_CLS_INF)
-		ret |= EFLAG_VXISI;
+		FP_SET_EXCEPTION(EFLAG_VXISI);
 
 	FP_ADD_D(R, A, B);
 
diff --git a/arch/powerpc/math-emu/fsubs.c b/arch/powerpc/math-emu/fsubs.c
index d3bf90863cf2..5d9b18c35e07 100644
--- a/arch/powerpc/math-emu/fsubs.c
+++ b/arch/powerpc/math-emu/fsubs.c
@@ -14,7 +14,6 @@ fsubs(void *frD, void *frA, void *frB)
 	FP_DECL_D(B);
 	FP_DECL_D(R);
 	FP_DECL_EX;
-	int ret = 0;
 
 #ifdef DEBUG
 	printk("%s: %p %p %p\n", __func__, frD, frA, frB);
@@ -32,7 +31,7 @@ fsubs(void *frD, void *frA, void *frB)
 		B_s ^= 1;
 
 	if (A_s != B_s && A_c == FP_CLS_INF && B_c == FP_CLS_INF)
-		ret |= EFLAG_VXISI;
+		FP_SET_EXCEPTION(EFLAG_VXISI);
 
 	FP_ADD_D(R, A, B);
 
diff --git a/arch/powerpc/math-emu/math_efp.c b/arch/powerpc/math-emu/math_efp.c
new file mode 100644
index 000000000000..41f4ef30e480
--- /dev/null
+++ b/arch/powerpc/math-emu/math_efp.c
@@ -0,0 +1,720 @@
+/*
+ * arch/powerpc/math-emu/math_efp.c
+ *
+ * Copyright (C) 2006-2008 Freescale Semiconductor, Inc. All rights reserved.
+ *
+ * Author: Ebony Zhu,	<ebony.zhu@freescale.com>
+ *         Yu Liu,	<yu.liu@freescale.com>
+ *
+ * Derived from arch/alpha/math-emu/math.c
+ *              arch/powerpc/math-emu/math.c
+ *
+ * Description:
+ * This file is the exception handler to make E500 SPE instructions
+ * fully comply with IEEE-754 floating point standard.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/types.h>
+
+#include <asm/uaccess.h>
+#include <asm/reg.h>
+
+#define FP_EX_BOOKE_E500_SPE
+#include <asm/sfp-machine.h>
+
+#include <math-emu/soft-fp.h>
+#include <math-emu/single.h>
+#include <math-emu/double.h>
+
+#define EFAPU		0x4
+
+#define VCT		0x4
+#define SPFP		0x6
+#define DPFP		0x7
+
+#define EFSADD		0x2c0
+#define EFSSUB		0x2c1
+#define EFSABS		0x2c4
+#define EFSNABS		0x2c5
+#define EFSNEG		0x2c6
+#define EFSMUL		0x2c8
+#define EFSDIV		0x2c9
+#define EFSCMPGT	0x2cc
+#define EFSCMPLT	0x2cd
+#define EFSCMPEQ	0x2ce
+#define EFSCFD		0x2cf
+#define EFSCFSI		0x2d1
+#define EFSCTUI		0x2d4
+#define EFSCTSI		0x2d5
+#define EFSCTUF		0x2d6
+#define EFSCTSF		0x2d7
+#define EFSCTUIZ	0x2d8
+#define EFSCTSIZ	0x2da
+
+#define EVFSADD		0x280
+#define EVFSSUB		0x281
+#define EVFSABS		0x284
+#define EVFSNABS	0x285
+#define EVFSNEG		0x286
+#define EVFSMUL		0x288
+#define EVFSDIV		0x289
+#define EVFSCMPGT	0x28c
+#define EVFSCMPLT	0x28d
+#define EVFSCMPEQ	0x28e
+#define EVFSCTUI	0x294
+#define EVFSCTSI	0x295
+#define EVFSCTUF	0x296
+#define EVFSCTSF	0x297
+#define EVFSCTUIZ	0x298
+#define EVFSCTSIZ	0x29a
+
+#define EFDADD		0x2e0
+#define EFDSUB		0x2e1
+#define EFDABS		0x2e4
+#define EFDNABS		0x2e5
+#define EFDNEG		0x2e6
+#define EFDMUL		0x2e8
+#define EFDDIV		0x2e9
+#define EFDCTUIDZ	0x2ea
+#define EFDCTSIDZ	0x2eb
+#define EFDCMPGT	0x2ec
+#define EFDCMPLT	0x2ed
+#define EFDCMPEQ	0x2ee
+#define EFDCFS		0x2ef
+#define EFDCTUI		0x2f4
+#define EFDCTSI		0x2f5
+#define EFDCTUF		0x2f6
+#define EFDCTSF		0x2f7
+#define EFDCTUIZ	0x2f8
+#define EFDCTSIZ	0x2fa
+
+#define AB	2
+#define XA	3
+#define XB	4
+#define XCR	5
+#define NOTYPE	0
+
+#define SIGN_BIT_S	(1UL << 31)
+#define SIGN_BIT_D	(1ULL << 63)
+#define FP_EX_MASK	(FP_EX_INEXACT | FP_EX_INVALID | FP_EX_DIVZERO | \
+			FP_EX_UNDERFLOW | FP_EX_OVERFLOW)
+
+union dw_union {
+	u64 dp[1];
+	u32 wp[2];
+};
+
+static unsigned long insn_type(unsigned long speinsn)
+{
+	unsigned long ret = NOTYPE;
+
+	switch (speinsn & 0x7ff) {
+	case EFSABS:	ret = XA;	break;
+	case EFSADD:	ret = AB;	break;
+	case EFSCFD:	ret = XB;	break;
+	case EFSCMPEQ:	ret = XCR;	break;
+	case EFSCMPGT:	ret = XCR;	break;
+	case EFSCMPLT:	ret = XCR;	break;
+	case EFSCTSF:	ret = XB;	break;
+	case EFSCTSI:	ret = XB;	break;
+	case EFSCTSIZ:	ret = XB;	break;
+	case EFSCTUF:	ret = XB;	break;
+	case EFSCTUI:	ret = XB;	break;
+	case EFSCTUIZ:	ret = XB;	break;
+	case EFSDIV:	ret = AB;	break;
+	case EFSMUL:	ret = AB;	break;
+	case EFSNABS:	ret = XA;	break;
+	case EFSNEG:	ret = XA;	break;
+	case EFSSUB:	ret = AB;	break;
+	case EFSCFSI:	ret = XB;	break;
+
+	case EVFSABS:	ret = XA;	break;
+	case EVFSADD:	ret = AB;	break;
+	case EVFSCMPEQ:	ret = XCR;	break;
+	case EVFSCMPGT:	ret = XCR;	break;
+	case EVFSCMPLT:	ret = XCR;	break;
+	case EVFSCTSF:	ret = XB;	break;
+	case EVFSCTSI:	ret = XB;	break;
+	case EVFSCTSIZ:	ret = XB;	break;
+	case EVFSCTUF:	ret = XB;	break;
+	case EVFSCTUI:	ret = XB;	break;
+	case EVFSCTUIZ:	ret = XB;	break;
+	case EVFSDIV:	ret = AB;	break;
+	case EVFSMUL:	ret = AB;	break;
+	case EVFSNABS:	ret = XA;	break;
+	case EVFSNEG:	ret = XA;	break;
+	case EVFSSUB:	ret = AB;	break;
+
+	case EFDABS:	ret = XA;	break;
+	case EFDADD:	ret = AB;	break;
+	case EFDCFS:	ret = XB;	break;
+	case EFDCMPEQ:	ret = XCR;	break;
+	case EFDCMPGT:	ret = XCR;	break;
+	case EFDCMPLT:	ret = XCR;	break;
+	case EFDCTSF:	ret = XB;	break;
+	case EFDCTSI:	ret = XB;	break;
+	case EFDCTSIDZ:	ret = XB;	break;
+	case EFDCTSIZ:	ret = XB;	break;
+	case EFDCTUF:	ret = XB;	break;
+	case EFDCTUI:	ret = XB;	break;
+	case EFDCTUIDZ:	ret = XB;	break;
+	case EFDCTUIZ:	ret = XB;	break;
+	case EFDDIV:	ret = AB;	break;
+	case EFDMUL:	ret = AB;	break;
+	case EFDNABS:	ret = XA;	break;
+	case EFDNEG:	ret = XA;	break;
+	case EFDSUB:	ret = AB;	break;
+
+	default:
+		printk(KERN_ERR "\nOoops! SPE instruction no type found.");
+		printk(KERN_ERR "\ninst code: %08lx\n", speinsn);
+	}
+
+	return ret;
+}
+
+int do_spe_mathemu(struct pt_regs *regs)
+{
+	FP_DECL_EX;
+	int IR, cmp;
+
+	unsigned long type, func, fc, fa, fb, src, speinsn;
+	union dw_union vc, va, vb;
+
+	if (get_user(speinsn, (unsigned int __user *) regs->nip))
+		return -EFAULT;
+	if ((speinsn >> 26) != EFAPU)
+		return -EINVAL;         /* not an spe instruction */
+
+	type = insn_type(speinsn);
+	if (type == NOTYPE)
+		return -ENOSYS;
+
+	func = speinsn & 0x7ff;
+	fc = (speinsn >> 21) & 0x1f;
+	fa = (speinsn >> 16) & 0x1f;
+	fb = (speinsn >> 11) & 0x1f;
+	src = (speinsn >> 5) & 0x7;
+
+	vc.wp[0] = current->thread.evr[fc];
+	vc.wp[1] = regs->gpr[fc];
+	va.wp[0] = current->thread.evr[fa];
+	va.wp[1] = regs->gpr[fa];
+	vb.wp[0] = current->thread.evr[fb];
+	vb.wp[1] = regs->gpr[fb];
+
+	__FPU_FPSCR = mfspr(SPRN_SPEFSCR);
+
+#ifdef DEBUG
+	printk("speinsn:%08lx spefscr:%08lx\n", speinsn, __FPU_FPSCR);
+	printk("vc: %08x  %08x\n", vc.wp[0], vc.wp[1]);
+	printk("va: %08x  %08x\n", va.wp[0], va.wp[1]);
+	printk("vb: %08x  %08x\n", vb.wp[0], vb.wp[1]);
+#endif
+
+	switch (src) {
+	case SPFP: {
+		FP_DECL_S(SA); FP_DECL_S(SB); FP_DECL_S(SR);
+
+		switch (type) {
+		case AB:
+		case XCR:
+			FP_UNPACK_SP(SA, va.wp + 1);
+		case XB:
+			FP_UNPACK_SP(SB, vb.wp + 1);
+			break;
+		case XA:
+			FP_UNPACK_SP(SA, va.wp + 1);
+			break;
+		}
+
+#ifdef DEBUG
+		printk("SA: %ld %08lx %ld (%ld)\n", SA_s, SA_f, SA_e, SA_c);
+		printk("SB: %ld %08lx %ld (%ld)\n", SB_s, SB_f, SB_e, SB_c);
+#endif
+
+		switch (func) {
+		case EFSABS:
+			vc.wp[1] = va.wp[1] & ~SIGN_BIT_S;
+			goto update_regs;
+
+		case EFSNABS:
+			vc.wp[1] = va.wp[1] | SIGN_BIT_S;
+			goto update_regs;
+
+		case EFSNEG:
+			vc.wp[1] = va.wp[1] ^ SIGN_BIT_S;
+			goto update_regs;
+
+		case EFSADD:
+			FP_ADD_S(SR, SA, SB);
+			goto pack_s;
+
+		case EFSSUB:
+			FP_SUB_S(SR, SA, SB);
+			goto pack_s;
+
+		case EFSMUL:
+			FP_MUL_S(SR, SA, SB);
+			goto pack_s;
+
+		case EFSDIV:
+			FP_DIV_S(SR, SA, SB);
+			goto pack_s;
+
+		case EFSCMPEQ:
+			cmp = 0;
+			goto cmp_s;
+
+		case EFSCMPGT:
+			cmp = 1;
+			goto cmp_s;
+
+		case EFSCMPLT:
+			cmp = -1;
+			goto cmp_s;
+
+		case EFSCTSF:
+		case EFSCTUF:
+			if (!((vb.wp[1] >> 23) == 0xff && ((vb.wp[1] & 0x7fffff) > 0))) {
+				/* NaN */
+				if (((vb.wp[1] >> 23) & 0xff) == 0) {
+					/* denorm */
+					vc.wp[1] = 0x0;
+				} else if ((vb.wp[1] >> 31) == 0) {
+					/* positive normal */
+					vc.wp[1] = (func == EFSCTSF) ?
+						0x7fffffff : 0xffffffff;
+				} else { /* negative normal */
+					vc.wp[1] = (func == EFSCTSF) ?
+						0x80000000 : 0x0;
+				}
+			} else { /* rB is NaN */
+				vc.wp[1] = 0x0;
+			}
+			goto update_regs;
+
+		case EFSCFD: {
+			FP_DECL_D(DB);
+			FP_CLEAR_EXCEPTIONS;
+			FP_UNPACK_DP(DB, vb.dp);
+#ifdef DEBUG
+			printk("DB: %ld %08lx %08lx %ld (%ld)\n",
+					DB_s, DB_f1, DB_f0, DB_e, DB_c);
+#endif
+			FP_CONV(S, D, 1, 2, SR, DB);
+			goto pack_s;
+		}
+
+		case EFSCTSI:
+		case EFSCTSIZ:
+		case EFSCTUI:
+		case EFSCTUIZ:
+			if (func & 0x4) {
+				_FP_ROUND(1, SB);
+			} else {
+				_FP_ROUND_ZERO(1, SB);
+			}
+			FP_TO_INT_S(vc.wp[1], SB, 32, ((func & 0x3) != 0));
+			goto update_regs;
+
+		default:
+			goto illegal;
+		}
+		break;
+
+pack_s:
+#ifdef DEBUG
+		printk("SR: %ld %08lx %ld (%ld)\n", SR_s, SR_f, SR_e, SR_c);
+#endif
+		FP_PACK_SP(vc.wp + 1, SR);
+		goto update_regs;
+
+cmp_s:
+		FP_CMP_S(IR, SA, SB, 3);
+		if (IR == 3 && (FP_ISSIGNAN_S(SA) || FP_ISSIGNAN_S(SB)))
+			FP_SET_EXCEPTION(FP_EX_INVALID);
+		if (IR == cmp) {
+			IR = 0x4;
+		} else {
+			IR = 0;
+		}
+		goto update_ccr;
+	}
+
+	case DPFP: {
+		FP_DECL_D(DA); FP_DECL_D(DB); FP_DECL_D(DR);
+
+		switch (type) {
+		case AB:
+		case XCR:
+			FP_UNPACK_DP(DA, va.dp);
+		case XB:
+			FP_UNPACK_DP(DB, vb.dp);
+			break;
+		case XA:
+			FP_UNPACK_DP(DA, va.dp);
+			break;
+		}
+
+#ifdef DEBUG
+		printk("DA: %ld %08lx %08lx %ld (%ld)\n",
+				DA_s, DA_f1, DA_f0, DA_e, DA_c);
+		printk("DB: %ld %08lx %08lx %ld (%ld)\n",
+				DB_s, DB_f1, DB_f0, DB_e, DB_c);
+#endif
+
+		switch (func) {
+		case EFDABS:
+			vc.dp[0] = va.dp[0] & ~SIGN_BIT_D;
+			goto update_regs;
+
+		case EFDNABS:
+			vc.dp[0] = va.dp[0] | SIGN_BIT_D;
+			goto update_regs;
+
+		case EFDNEG:
+			vc.dp[0] = va.dp[0] ^ SIGN_BIT_D;
+			goto update_regs;
+
+		case EFDADD:
+			FP_ADD_D(DR, DA, DB);
+			goto pack_d;
+
+		case EFDSUB:
+			FP_SUB_D(DR, DA, DB);
+			goto pack_d;
+
+		case EFDMUL:
+			FP_MUL_D(DR, DA, DB);
+			goto pack_d;
+
+		case EFDDIV:
+			FP_DIV_D(DR, DA, DB);
+			goto pack_d;
+
+		case EFDCMPEQ:
+			cmp = 0;
+			goto cmp_d;
+
+		case EFDCMPGT:
+			cmp = 1;
+			goto cmp_d;
+
+		case EFDCMPLT:
+			cmp = -1;
+			goto cmp_d;
+
+		case EFDCTSF:
+		case EFDCTUF:
+			if (!((vb.wp[0] >> 20) == 0x7ff &&
+			   ((vb.wp[0] & 0xfffff) > 0 || (vb.wp[1] > 0)))) {
+				/* not a NaN */
+				if (((vb.wp[0] >> 20) & 0x7ff) == 0) {
+					/* denorm */
+					vc.wp[1] = 0x0;
+				} else if ((vb.wp[0] >> 31) == 0) {
+					/* positive normal */
+					vc.wp[1] = (func == EFDCTSF) ?
+						0x7fffffff : 0xffffffff;
+				} else { /* negative normal */
+					vc.wp[1] = (func == EFDCTSF) ?
+						0x80000000 : 0x0;
+				}
+			} else { /* NaN */
+				vc.wp[1] = 0x0;
+			}
+			goto update_regs;
+
+		case EFDCFS: {
+			FP_DECL_S(SB);
+			FP_CLEAR_EXCEPTIONS;
+			FP_UNPACK_SP(SB, vb.wp + 1);
+#ifdef DEBUG
+			printk("SB: %ld %08lx %ld (%ld)\n",
+					SB_s, SB_f, SB_e, SB_c);
+#endif
+			FP_CONV(D, S, 2, 1, DR, SB);
+			goto pack_d;
+		}
+
+		case EFDCTUIDZ:
+		case EFDCTSIDZ:
+			_FP_ROUND_ZERO(2, DB);
+			FP_TO_INT_D(vc.dp[0], DB, 64, ((func & 0x1) == 0));
+			goto update_regs;
+
+		case EFDCTUI:
+		case EFDCTSI:
+		case EFDCTUIZ:
+		case EFDCTSIZ:
+			if (func & 0x4) {
+				_FP_ROUND(2, DB);
+			} else {
+				_FP_ROUND_ZERO(2, DB);
+			}
+			FP_TO_INT_D(vc.wp[1], DB, 32, ((func & 0x3) != 0));
+			goto update_regs;
+
+		default:
+			goto illegal;
+		}
+		break;
+
+pack_d:
+#ifdef DEBUG
+		printk("DR: %ld %08lx %08lx %ld (%ld)\n",
+				DR_s, DR_f1, DR_f0, DR_e, DR_c);
+#endif
+		FP_PACK_DP(vc.dp, DR);
+		goto update_regs;
+
+cmp_d:
+		FP_CMP_D(IR, DA, DB, 3);
+		if (IR == 3 && (FP_ISSIGNAN_D(DA) || FP_ISSIGNAN_D(DB)))
+			FP_SET_EXCEPTION(FP_EX_INVALID);
+		if (IR == cmp) {
+			IR = 0x4;
+		} else {
+			IR = 0;
+		}
+		goto update_ccr;
+
+	}
+
+	case VCT: {
+		FP_DECL_S(SA0); FP_DECL_S(SB0); FP_DECL_S(SR0);
+		FP_DECL_S(SA1); FP_DECL_S(SB1); FP_DECL_S(SR1);
+		int IR0, IR1;
+
+		switch (type) {
+		case AB:
+		case XCR:
+			FP_UNPACK_SP(SA0, va.wp);
+			FP_UNPACK_SP(SA1, va.wp + 1);
+		case XB:
+			FP_UNPACK_SP(SB0, vb.wp);
+			FP_UNPACK_SP(SB1, vb.wp + 1);
+			break;
+		case XA:
+			FP_UNPACK_SP(SA0, va.wp);
+			FP_UNPACK_SP(SA1, va.wp + 1);
+			break;
+		}
+
+#ifdef DEBUG
+		printk("SA0: %ld %08lx %ld (%ld)\n", SA0_s, SA0_f, SA0_e, SA0_c);
+		printk("SA1: %ld %08lx %ld (%ld)\n", SA1_s, SA1_f, SA1_e, SA1_c);
+		printk("SB0: %ld %08lx %ld (%ld)\n", SB0_s, SB0_f, SB0_e, SB0_c);
+		printk("SB1: %ld %08lx %ld (%ld)\n", SB1_s, SB1_f, SB1_e, SB1_c);
+#endif
+
+		switch (func) {
+		case EVFSABS:
+			vc.wp[0] = va.wp[0] & ~SIGN_BIT_S;
+			vc.wp[1] = va.wp[1] & ~SIGN_BIT_S;
+			goto update_regs;
+
+		case EVFSNABS:
+			vc.wp[0] = va.wp[0] | SIGN_BIT_S;
+			vc.wp[1] = va.wp[1] | SIGN_BIT_S;
+			goto update_regs;
+
+		case EVFSNEG:
+			vc.wp[0] = va.wp[0] ^ SIGN_BIT_S;
+			vc.wp[1] = va.wp[1] ^ SIGN_BIT_S;
+			goto update_regs;
+
+		case EVFSADD:
+			FP_ADD_S(SR0, SA0, SB0);
+			FP_ADD_S(SR1, SA1, SB1);
+			goto pack_vs;
+
+		case EVFSSUB:
+			FP_SUB_S(SR0, SA0, SB0);
+			FP_SUB_S(SR1, SA1, SB1);
+			goto pack_vs;
+
+		case EVFSMUL:
+			FP_MUL_S(SR0, SA0, SB0);
+			FP_MUL_S(SR1, SA1, SB1);
+			goto pack_vs;
+
+		case EVFSDIV:
+			FP_DIV_S(SR0, SA0, SB0);
+			FP_DIV_S(SR1, SA1, SB1);
+			goto pack_vs;
+
+		case EVFSCMPEQ:
+			cmp = 0;
+			goto cmp_vs;
+
+		case EVFSCMPGT:
+			cmp = 1;
+			goto cmp_vs;
+
+		case EVFSCMPLT:
+			cmp = -1;
+			goto cmp_vs;
+
+		case EVFSCTSF:
+			__asm__ __volatile__ ("mtspr 512, %4\n"
+				"efsctsf %0, %2\n"
+				"efsctsf %1, %3\n"
+				: "=r" (vc.wp[0]), "=r" (vc.wp[1])
+				: "r" (vb.wp[0]), "r" (vb.wp[1]), "r" (0));
+			goto update_regs;
+
+		case EVFSCTUF:
+			__asm__ __volatile__ ("mtspr 512, %4\n"
+				"efsctuf %0, %2\n"
+				"efsctuf %1, %3\n"
+				: "=r" (vc.wp[0]), "=r" (vc.wp[1])
+				: "r" (vb.wp[0]), "r" (vb.wp[1]), "r" (0));
+			goto update_regs;
+
+		case EVFSCTUI:
+		case EVFSCTSI:
+		case EVFSCTUIZ:
+		case EVFSCTSIZ:
+			if (func & 0x4) {
+				_FP_ROUND(1, SB0);
+				_FP_ROUND(1, SB1);
+			} else {
+				_FP_ROUND_ZERO(1, SB0);
+				_FP_ROUND_ZERO(1, SB1);
+			}
+			FP_TO_INT_S(vc.wp[0], SB0, 32, ((func & 0x3) != 0));
+			FP_TO_INT_S(vc.wp[1], SB1, 32, ((func & 0x3) != 0));
+			goto update_regs;
+
+		default:
+			goto illegal;
+		}
+		break;
+
+pack_vs:
+#ifdef DEBUG
+		printk("SR0: %ld %08lx %ld (%ld)\n", SR0_s, SR0_f, SR0_e, SR0_c);
+		printk("SR1: %ld %08lx %ld (%ld)\n", SR1_s, SR1_f, SR1_e, SR1_c);
+#endif
+		FP_PACK_SP(vc.wp, SR0);
+		FP_PACK_SP(vc.wp + 1, SR1);
+		goto update_regs;
+
+cmp_vs:
+		{
+			int ch, cl;
+
+			FP_CMP_S(IR0, SA0, SB0, 3);
+			FP_CMP_S(IR1, SA1, SB1, 3);
+			if (IR0 == 3 && (FP_ISSIGNAN_S(SA0) || FP_ISSIGNAN_S(SB0)))
+				FP_SET_EXCEPTION(FP_EX_INVALID);
+			if (IR1 == 3 && (FP_ISSIGNAN_S(SA1) || FP_ISSIGNAN_S(SB1)))
+				FP_SET_EXCEPTION(FP_EX_INVALID);
+			ch = (IR0 == cmp) ? 1 : 0;
+			cl = (IR1 == cmp) ? 1 : 0;
+			IR = (ch << 3) | (cl << 2) | ((ch | cl) << 1) |
+				((ch & cl) << 0);
+			goto update_ccr;
+		}
+	}
+	default:
+		return -EINVAL;
+	}
+
+update_ccr:
+	regs->ccr &= ~(15 << ((7 - ((speinsn >> 23) & 0x7)) << 2));
+	regs->ccr |= (IR << ((7 - ((speinsn >> 23) & 0x7)) << 2));
+
+update_regs:
+	__FPU_FPSCR &= ~FP_EX_MASK;
+	__FPU_FPSCR |= (FP_CUR_EXCEPTIONS & FP_EX_MASK);
+	mtspr(SPRN_SPEFSCR, __FPU_FPSCR);
+
+	current->thread.evr[fc] = vc.wp[0];
+	regs->gpr[fc] = vc.wp[1];
+
+#ifdef DEBUG
+	printk("ccr = %08lx\n", regs->ccr);
+	printk("cur exceptions = %08x spefscr = %08lx\n",
+			FP_CUR_EXCEPTIONS, __FPU_FPSCR);
+	printk("vc: %08x  %08x\n", vc.wp[0], vc.wp[1]);
+	printk("va: %08x  %08x\n", va.wp[0], va.wp[1]);
+	printk("vb: %08x  %08x\n", vb.wp[0], vb.wp[1]);
+#endif
+
+	return 0;
+
+illegal:
+	printk(KERN_ERR "\nOoops! IEEE-754 compliance handler encountered un-supported instruction.\ninst code: %08lx\n", speinsn);
+	return -ENOSYS;
+}
+
+int speround_handler(struct pt_regs *regs)
+{
+	union dw_union fgpr;
+	int s_lo, s_hi;
+	unsigned long speinsn, type, fc;
+
+	if (get_user(speinsn, (unsigned int __user *) regs->nip))
+		return -EFAULT;
+	if ((speinsn >> 26) != 4)
+		return -EINVAL;         /* not an spe instruction */
+
+	type = insn_type(speinsn & 0x7ff);
+	if (type == XCR) return -ENOSYS;
+
+	fc = (speinsn >> 21) & 0x1f;
+	s_lo = regs->gpr[fc] & SIGN_BIT_S;
+	s_hi = current->thread.evr[fc] & SIGN_BIT_S;
+	fgpr.wp[0] = current->thread.evr[fc];
+	fgpr.wp[1] = regs->gpr[fc];
+
+	__FPU_FPSCR = mfspr(SPRN_SPEFSCR);
+
+	switch ((speinsn >> 5) & 0x7) {
+	/* Since SPE instructions on E500 core can handle round to nearest
+	 * and round toward zero with IEEE-754 complied, we just need
+	 * to handle round toward +Inf and round toward -Inf by software.
+	 */
+	case SPFP:
+		if ((FP_ROUNDMODE) == FP_RND_PINF) {
+			if (!s_lo) fgpr.wp[1]++; /* Z > 0, choose Z1 */
+		} else { /* round to -Inf */
+			if (s_lo) fgpr.wp[1]++; /* Z < 0, choose Z2 */
+		}
+		break;
+
+	case DPFP:
+		if (FP_ROUNDMODE == FP_RND_PINF) {
+			if (!s_hi) fgpr.dp[0]++; /* Z > 0, choose Z1 */
+		} else { /* round to -Inf */
+			if (s_hi) fgpr.dp[0]++; /* Z < 0, choose Z2 */
+		}
+		break;
+
+	case VCT:
+		if (FP_ROUNDMODE == FP_RND_PINF) {
+			if (!s_lo) fgpr.wp[1]++; /* Z_low > 0, choose Z1 */
+			if (!s_hi) fgpr.wp[0]++; /* Z_high word > 0, choose Z1 */
+		} else { /* round to -Inf */
+			if (s_lo) fgpr.wp[1]++; /* Z_low < 0, choose Z2 */
+			if (s_hi) fgpr.wp[0]++; /* Z_high < 0, choose Z2 */
+		}
+		break;
+
+	default:
+		return -EINVAL;
+	}
+
+	current->thread.evr[fc] = fgpr.wp[0];
+	regs->gpr[fc] = fgpr.wp[1];
+
+	return 0;
+}
diff --git a/arch/powerpc/mm/Makefile b/arch/powerpc/mm/Makefile
index e7392b45a5ef..86e657bcfa7e 100644
--- a/arch/powerpc/mm/Makefile
+++ b/arch/powerpc/mm/Makefile
@@ -6,7 +6,7 @@ ifeq ($(CONFIG_PPC64),y)
 EXTRA_CFLAGS	+= -mno-minimal-toc
 endif
 
-obj-y				:= fault.o mem.o \
+obj-y				:= fault.o mem.o pgtable.o \
 				   init_$(CONFIG_WORD_SIZE).o \
 				   pgtable_$(CONFIG_WORD_SIZE).o \
 				   mmu_context_$(CONFIG_WORD_SIZE).o
diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index 565b7a237c84..7df0409107ad 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -30,6 +30,7 @@
 #include <linux/kprobes.h>
 #include <linux/kdebug.h>
 
+#include <asm/firmware.h>
 #include <asm/page.h>
 #include <asm/pgtable.h>
 #include <asm/mmu.h>
@@ -318,9 +319,16 @@ good_area:
 			goto do_sigbus;
 		BUG();
 	}
-	if (ret & VM_FAULT_MAJOR)
+	if (ret & VM_FAULT_MAJOR) {
 		current->maj_flt++;
-	else
+#ifdef CONFIG_PPC_SMLPAR
+		if (firmware_has_feature(FW_FEATURE_CMO)) {
+			preempt_disable();
+			get_lppaca()->page_ins += (1 << PAGE_FACTOR);
+			preempt_enable();
+		}
+#endif
+	} else
 		current->min_flt++;
 	up_read(&mm->mmap_sem);
 	return 0;
diff --git a/arch/powerpc/mm/hash_low_32.S b/arch/powerpc/mm/hash_low_32.S
index 7bffb70b9fe2..c5536b8b37a9 100644
--- a/arch/powerpc/mm/hash_low_32.S
+++ b/arch/powerpc/mm/hash_low_32.S
@@ -36,36 +36,6 @@ mmu_hash_lock:
 #endif /* CONFIG_SMP */
 
 /*
- * Sync CPUs with hash_page taking & releasing the hash
- * table lock
- */
-#ifdef CONFIG_SMP
-	.text
-_GLOBAL(hash_page_sync)
-	mfmsr   r10
-	rlwinm  r0,r10,0,17,15          /* clear bit 16 (MSR_EE) */
-	mtmsr   r0
-	lis	r8,mmu_hash_lock@h
-	ori	r8,r8,mmu_hash_lock@l
-	lis	r0,0x0fff
-	b	10f
-11:	lwz	r6,0(r8)
-	cmpwi	0,r6,0
-	bne	11b
-10:	lwarx	r6,0,r8
-	cmpwi	0,r6,0
-	bne-	11b
-	stwcx.	r0,0,r8
-	bne-	10b
-	isync
-	eieio
-	li	r0,0
-	stw	r0,0(r8)
-	mtmsr	r10
-	blr
-#endif /* CONFIG_SMP */
-
-/*
  * Load a PTE into the hash table, if possible.
  * The address is in r4, and r3 contains an access flag:
  * _PAGE_RW (0x400) if a write.
diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
index 7bbf4e4ed430..deb494687a65 100644
--- a/arch/powerpc/mm/hugetlbpage.c
+++ b/arch/powerpc/mm/hugetlbpage.c
@@ -53,8 +53,7 @@ unsigned int mmu_huge_psizes[MMU_PAGE_COUNT] = { }; /* initialize all to 0 */
 
 /* Subtract one from array size because we don't need a cache for 4K since
  * is not a huge page size */
-#define huge_pgtable_cache(psize)	(pgtable_cache[HUGEPTE_CACHE_NUM \
-							+ psize-1])
+#define HUGE_PGTABLE_INDEX(psize)	(HUGEPTE_CACHE_NUM + psize - 1)
 #define HUGEPTE_CACHE_NAME(psize)	(huge_pgtable_cache_name[psize])
 
 static const char *huge_pgtable_cache_name[MMU_PAGE_COUNT] = {
@@ -113,7 +112,7 @@ static inline pte_t *hugepte_offset(hugepd_t *hpdp, unsigned long addr,
 static int __hugepte_alloc(struct mm_struct *mm, hugepd_t *hpdp,
 			   unsigned long address, unsigned int psize)
 {
-	pte_t *new = kmem_cache_zalloc(huge_pgtable_cache(psize),
+	pte_t *new = kmem_cache_zalloc(pgtable_cache[HUGE_PGTABLE_INDEX(psize)],
 				      GFP_KERNEL|__GFP_REPEAT);
 
 	if (! new)
@@ -121,7 +120,7 @@ static int __hugepte_alloc(struct mm_struct *mm, hugepd_t *hpdp,
 
 	spin_lock(&mm->page_table_lock);
 	if (!hugepd_none(*hpdp))
-		kmem_cache_free(huge_pgtable_cache(psize), new);
+		kmem_cache_free(pgtable_cache[HUGE_PGTABLE_INDEX(psize)], new);
 	else
 		hpdp->pd = (unsigned long)new | HUGEPD_OK;
 	spin_unlock(&mm->page_table_lock);
@@ -760,13 +759,14 @@ static int __init hugetlbpage_init(void)
 
 	for (psize = 0; psize < MMU_PAGE_COUNT; ++psize) {
 		if (mmu_huge_psizes[psize]) {
-			huge_pgtable_cache(psize) = kmem_cache_create(
-						HUGEPTE_CACHE_NAME(psize),
-						HUGEPTE_TABLE_SIZE(psize),
-						HUGEPTE_TABLE_SIZE(psize),
-						0,
-						NULL);
-			if (!huge_pgtable_cache(psize))
+			pgtable_cache[HUGE_PGTABLE_INDEX(psize)] =
+				kmem_cache_create(
+					HUGEPTE_CACHE_NAME(psize),
+					HUGEPTE_TABLE_SIZE(psize),
+					HUGEPTE_TABLE_SIZE(psize),
+					0,
+					NULL);
+			if (!pgtable_cache[HUGE_PGTABLE_INDEX(psize)])
 				panic("hugetlbpage_init(): could not create %s"\
 				      "\n", HUGEPTE_CACHE_NAME(psize));
 		}
diff --git a/arch/powerpc/mm/pgtable.c b/arch/powerpc/mm/pgtable.c
new file mode 100644
index 000000000000..6d94116fdea1
--- /dev/null
+++ b/arch/powerpc/mm/pgtable.c
@@ -0,0 +1,117 @@
+/*
+ * This file contains common routines for dealing with free of page tables
+ *
+ *  Derived from arch/powerpc/mm/tlb_64.c:
+ *    Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
+ *
+ *  Modifications by Paul Mackerras (PowerMac) (paulus@cs.anu.edu.au)
+ *  and Cort Dougan (PReP) (cort@cs.nmt.edu)
+ *    Copyright (C) 1996 Paul Mackerras
+ *
+ *  Derived from "arch/i386/mm/init.c"
+ *    Copyright (C) 1991, 1992, 1993, 1994  Linus Torvalds
+ *
+ *  Dave Engebretsen <engebret@us.ibm.com>
+ *      Rework for PPC64 port.
+ *
+ *  This program is free software; you can redistribute it and/or
+ *  modify it under the terms of the GNU General Public License
+ *  as published by the Free Software Foundation; either version
+ *  2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/init.h>
+#include <linux/percpu.h>
+#include <linux/hardirq.h>
+#include <asm/pgalloc.h>
+#include <asm/tlbflush.h>
+#include <asm/tlb.h>
+
+static DEFINE_PER_CPU(struct pte_freelist_batch *, pte_freelist_cur);
+static unsigned long pte_freelist_forced_free;
+
+struct pte_freelist_batch
+{
+	struct rcu_head	rcu;
+	unsigned int	index;
+	pgtable_free_t	tables[0];
+};
+
+#define PTE_FREELIST_SIZE \
+	((PAGE_SIZE - sizeof(struct pte_freelist_batch)) \
+	  / sizeof(pgtable_free_t))
+
+static void pte_free_smp_sync(void *arg)
+{
+	/* Do nothing, just ensure we sync with all CPUs */
+}
+
+/* This is only called when we are critically out of memory
+ * (and fail to get a page in pte_free_tlb).
+ */
+static void pgtable_free_now(pgtable_free_t pgf)
+{
+	pte_freelist_forced_free++;
+
+	smp_call_function(pte_free_smp_sync, NULL, 1);
+
+	pgtable_free(pgf);
+}
+
+static void pte_free_rcu_callback(struct rcu_head *head)
+{
+	struct pte_freelist_batch *batch =
+		container_of(head, struct pte_freelist_batch, rcu);
+	unsigned int i;
+
+	for (i = 0; i < batch->index; i++)
+		pgtable_free(batch->tables[i]);
+
+	free_page((unsigned long)batch);
+}
+
+static void pte_free_submit(struct pte_freelist_batch *batch)
+{
+	INIT_RCU_HEAD(&batch->rcu);
+	call_rcu(&batch->rcu, pte_free_rcu_callback);
+}
+
+void pgtable_free_tlb(struct mmu_gather *tlb, pgtable_free_t pgf)
+{
+	/* This is safe since tlb_gather_mmu has disabled preemption */
+        cpumask_t local_cpumask = cpumask_of_cpu(smp_processor_id());
+	struct pte_freelist_batch **batchp = &__get_cpu_var(pte_freelist_cur);
+
+	if (atomic_read(&tlb->mm->mm_users) < 2 ||
+	    cpus_equal(tlb->mm->cpu_vm_mask, local_cpumask)) {
+		pgtable_free(pgf);
+		return;
+	}
+
+	if (*batchp == NULL) {
+		*batchp = (struct pte_freelist_batch *)__get_free_page(GFP_ATOMIC);
+		if (*batchp == NULL) {
+			pgtable_free_now(pgf);
+			return;
+		}
+		(*batchp)->index = 0;
+	}
+	(*batchp)->tables[(*batchp)->index++] = pgf;
+	if ((*batchp)->index == PTE_FREELIST_SIZE) {
+		pte_free_submit(*batchp);
+		*batchp = NULL;
+	}
+}
+
+void pte_free_finish(void)
+{
+	/* This is safe since tlb_gather_mmu has disabled preemption */
+	struct pte_freelist_batch **batchp = &__get_cpu_var(pte_freelist_cur);
+
+	if (*batchp == NULL)
+		return;
+	pte_free_submit(*batchp);
+	*batchp = NULL;
+}
diff --git a/arch/powerpc/mm/pgtable_32.c b/arch/powerpc/mm/pgtable_32.c
index c31d6d26f0b5..c7b755cba26a 100644
--- a/arch/powerpc/mm/pgtable_32.c
+++ b/arch/powerpc/mm/pgtable_32.c
@@ -48,10 +48,6 @@ EXPORT_SYMBOL(ioremap_bot);	/* aka VMALLOC_END */
 
 extern char etext[], _stext[];
 
-#ifdef CONFIG_SMP
-extern void hash_page_sync(void);
-#endif
-
 #ifdef HAVE_BATS
 extern phys_addr_t v_mapped_by_bats(unsigned long va);
 extern unsigned long p_mapped_by_bats(phys_addr_t pa);
@@ -125,23 +121,6 @@ pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long address)
 	return ptepage;
 }
 
-void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
-{
-#ifdef CONFIG_SMP
-	hash_page_sync();
-#endif
-	free_page((unsigned long)pte);
-}
-
-void pte_free(struct mm_struct *mm, pgtable_t ptepage)
-{
-#ifdef CONFIG_SMP
-	hash_page_sync();
-#endif
-	pgtable_page_dtor(ptepage);
-	__free_page(ptepage);
-}
-
 void __iomem *
 ioremap(phys_addr_t addr, unsigned long size)
 {
diff --git a/arch/powerpc/mm/tlb_64.c b/arch/powerpc/mm/tlb_64.c
index be7dd422c0fa..c931bc7d1079 100644
--- a/arch/powerpc/mm/tlb_64.c
+++ b/arch/powerpc/mm/tlb_64.c
@@ -37,81 +37,6 @@ DEFINE_PER_CPU(struct ppc64_tlb_batch, ppc64_tlb_batch);
  * arch/powerpc/include/asm/tlb.h file -- tgall
  */
 DEFINE_PER_CPU(struct mmu_gather, mmu_gathers);
-static DEFINE_PER_CPU(struct pte_freelist_batch *, pte_freelist_cur);
-static unsigned long pte_freelist_forced_free;
-
-struct pte_freelist_batch
-{
-	struct rcu_head	rcu;
-	unsigned int	index;
-	pgtable_free_t	tables[0];
-};
-
-#define PTE_FREELIST_SIZE \
-	((PAGE_SIZE - sizeof(struct pte_freelist_batch)) \
-	  / sizeof(pgtable_free_t))
-
-static void pte_free_smp_sync(void *arg)
-{
-	/* Do nothing, just ensure we sync with all CPUs */
-}
-
-/* This is only called when we are critically out of memory
- * (and fail to get a page in pte_free_tlb).
- */
-static void pgtable_free_now(pgtable_free_t pgf)
-{
-	pte_freelist_forced_free++;
-
-	smp_call_function(pte_free_smp_sync, NULL, 1);
-
-	pgtable_free(pgf);
-}
-
-static void pte_free_rcu_callback(struct rcu_head *head)
-{
-	struct pte_freelist_batch *batch =
-		container_of(head, struct pte_freelist_batch, rcu);
-	unsigned int i;
-
-	for (i = 0; i < batch->index; i++)
-		pgtable_free(batch->tables[i]);
-
-	free_page((unsigned long)batch);
-}
-
-static void pte_free_submit(struct pte_freelist_batch *batch)
-{
-	INIT_RCU_HEAD(&batch->rcu);
-	call_rcu(&batch->rcu, pte_free_rcu_callback);
-}
-
-void pgtable_free_tlb(struct mmu_gather *tlb, pgtable_free_t pgf)
-{
-	/* This is safe since tlb_gather_mmu has disabled preemption */
-        cpumask_t local_cpumask = cpumask_of_cpu(smp_processor_id());
-	struct pte_freelist_batch **batchp = &__get_cpu_var(pte_freelist_cur);
-
-	if (atomic_read(&tlb->mm->mm_users) < 2 ||
-	    cpus_equal(tlb->mm->cpu_vm_mask, local_cpumask)) {
-		pgtable_free(pgf);
-		return;
-	}
-
-	if (*batchp == NULL) {
-		*batchp = (struct pte_freelist_batch *)__get_free_page(GFP_ATOMIC);
-		if (*batchp == NULL) {
-			pgtable_free_now(pgf);
-			return;
-		}
-		(*batchp)->index = 0;
-	}
-	(*batchp)->tables[(*batchp)->index++] = pgf;
-	if ((*batchp)->index == PTE_FREELIST_SIZE) {
-		pte_free_submit(*batchp);
-		*batchp = NULL;
-	}
-}
 
 /*
  * A linux PTE was changed and the corresponding hash table entry
@@ -229,17 +154,6 @@ void __flush_tlb_pending(struct ppc64_tlb_batch *batch)
 	batch->index = 0;
 }
 
-void pte_free_finish(void)
-{
-	/* This is safe since tlb_gather_mmu has disabled preemption */
-	struct pte_freelist_batch **batchp = &__get_cpu_var(pte_freelist_cur);
-
-	if (*batchp == NULL)
-		return;
-	pte_free_submit(*batchp);
-	*batchp = NULL;
-}
-
 /**
  * __flush_hash_table_range - Flush all HPTEs for a given address range
  *                            from the hash table (and the TLB). But keeps
diff --git a/arch/powerpc/platforms/85xx/Makefile b/arch/powerpc/platforms/85xx/Makefile
index cb3054e1001d..f0798c09980f 100644
--- a/arch/powerpc/platforms/85xx/Makefile
+++ b/arch/powerpc/platforms/85xx/Makefile
@@ -1,6 +1,8 @@
 #
 # Makefile for the PowerPC 85xx linux kernel.
 #
+obj-$(CONFIG_SMP) += smp.o
+
 obj-$(CONFIG_MPC8540_ADS) += mpc85xx_ads.o
 obj-$(CONFIG_MPC8560_ADS) += mpc85xx_ads.o
 obj-$(CONFIG_MPC85xx_CDS) += mpc85xx_cds.o
diff --git a/arch/powerpc/platforms/85xx/mpc85xx_ds.c b/arch/powerpc/platforms/85xx/mpc85xx_ds.c
index 613bf8c2e30d..a8301c8ad537 100644
--- a/arch/powerpc/platforms/85xx/mpc85xx_ds.c
+++ b/arch/powerpc/platforms/85xx/mpc85xx_ds.c
@@ -63,6 +63,7 @@ void __init mpc85xx_ds_pic_init(void)
 	struct device_node *cascade_node = NULL;
 	int cascade_irq;
 #endif
+	unsigned long root = of_get_flat_dt_root();
 
 	np = of_find_node_by_type(NULL, "open-pic");
 	if (np == NULL) {
@@ -76,11 +77,19 @@ void __init mpc85xx_ds_pic_init(void)
 		return;
 	}
 
-	mpic = mpic_alloc(np, r.start,
+	if (of_flat_dt_is_compatible(root, "fsl,MPC8572DS-CAMP")) {
+		mpic = mpic_alloc(np, r.start,
+			MPIC_PRIMARY |
+			MPIC_BIG_ENDIAN | MPIC_BROKEN_FRR_NIRQS,
+			0, 256, " OpenPIC  ");
+	} else {
+		mpic = mpic_alloc(np, r.start,
 			  MPIC_PRIMARY | MPIC_WANTS_RESET |
 			  MPIC_BIG_ENDIAN | MPIC_BROKEN_FRR_NIRQS |
 			  MPIC_SINGLE_DEST_CPU,
 			0, 256, " OpenPIC  ");
+	}
+
 	BUG_ON(mpic == NULL);
 	of_node_put(np);
 
diff --git a/arch/powerpc/platforms/85xx/mpc85xx_mds.c b/arch/powerpc/platforms/85xx/mpc85xx_mds.c
index 2494c5155919..658a36fab3ab 100644
--- a/arch/powerpc/platforms/85xx/mpc85xx_mds.c
+++ b/arch/powerpc/platforms/85xx/mpc85xx_mds.c
@@ -231,7 +231,7 @@ static void __init mpc85xx_mds_setup_arch(void)
 
 static int __init board_fixups(void)
 {
-	char phy_id[BUS_ID_SIZE];
+	char phy_id[20];
 	char *compstrs[2] = {"fsl,gianfar-mdio", "fsl,ucc-mdio"};
 	struct device_node *mdio;
 	struct resource res;
@@ -241,13 +241,15 @@ static int __init board_fixups(void)
 		mdio = of_find_compatible_node(NULL, NULL, compstrs[i]);
 
 		of_address_to_resource(mdio, 0, &res);
-		snprintf(phy_id, BUS_ID_SIZE, "%x:%02x", res.start, 1);
+		snprintf(phy_id, sizeof(phy_id), "%llx:%02x",
+			(unsigned long long)res.start, 1);
 
 		phy_register_fixup_for_id(phy_id, mpc8568_fixup_125_clock);
 		phy_register_fixup_for_id(phy_id, mpc8568_mds_phy_fixups);
 
 		/* Register a workaround for errata */
-		snprintf(phy_id, BUS_ID_SIZE, "%x:%02x", res.start, 7);
+		snprintf(phy_id, sizeof(phy_id), "%llx:%02x",
+			(unsigned long long)res.start, 7);
 		phy_register_fixup_for_id(phy_id, mpc8568_mds_phy_fixups);
 
 		of_node_put(mdio);
diff --git a/arch/powerpc/platforms/85xx/smp.c b/arch/powerpc/platforms/85xx/smp.c
new file mode 100644
index 000000000000..d652c713f496
--- /dev/null
+++ b/arch/powerpc/platforms/85xx/smp.c
@@ -0,0 +1,104 @@
+/*
+ * Author: Andy Fleming <afleming@freescale.com>
+ * 	   Kumar Gala <galak@kernel.crashing.org>
+ *
+ * Copyright 2006-2008 Freescale Semiconductor Inc.
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ */
+
+#include <linux/stddef.h>
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/delay.h>
+#include <linux/of.h>
+
+#include <asm/machdep.h>
+#include <asm/pgtable.h>
+#include <asm/page.h>
+#include <asm/mpic.h>
+#include <asm/cacheflush.h>
+
+#include <sysdev/fsl_soc.h>
+
+extern volatile unsigned long __secondary_hold_acknowledge;
+extern void __early_start(void);
+
+#define BOOT_ENTRY_ADDR_UPPER	0
+#define BOOT_ENTRY_ADDR_LOWER	1
+#define BOOT_ENTRY_R3_UPPER	2
+#define BOOT_ENTRY_R3_LOWER	3
+#define BOOT_ENTRY_RESV		4
+#define BOOT_ENTRY_PIR		5
+#define BOOT_ENTRY_R6_UPPER	6
+#define BOOT_ENTRY_R6_LOWER	7
+#define NUM_BOOT_ENTRY		8
+#define SIZE_BOOT_ENTRY		(NUM_BOOT_ENTRY * sizeof(u32))
+
+static void __init
+smp_85xx_kick_cpu(int nr)
+{
+	unsigned long flags;
+	const u64 *cpu_rel_addr;
+	__iomem u32 *bptr_vaddr;
+	struct device_node *np;
+	int n = 0;
+
+	WARN_ON (nr < 0 || nr >= NR_CPUS);
+
+	pr_debug("smp_85xx_kick_cpu: kick CPU #%d\n", nr);
+
+	local_irq_save(flags);
+
+	np = of_get_cpu_node(nr, NULL);
+	cpu_rel_addr = of_get_property(np, "cpu-release-addr", NULL);
+
+	if (cpu_rel_addr == NULL) {
+		printk(KERN_ERR "No cpu-release-addr for cpu %d\n", nr);
+		return;
+	}
+
+	/* Map the spin table */
+	bptr_vaddr = ioremap(*cpu_rel_addr, SIZE_BOOT_ENTRY);
+
+	out_be32(bptr_vaddr + BOOT_ENTRY_PIR, nr);
+	out_be32(bptr_vaddr + BOOT_ENTRY_ADDR_LOWER, __pa(__early_start));
+
+	/* Wait a bit for the CPU to ack. */
+	while ((__secondary_hold_acknowledge != nr) && (++n < 1000))
+		mdelay(1);
+
+	iounmap(bptr_vaddr);
+
+	local_irq_restore(flags);
+
+	pr_debug("waited %d msecs for CPU #%d.\n", n, nr);
+}
+
+static void __init
+smp_85xx_setup_cpu(int cpu_nr)
+{
+	mpic_setup_this_cpu();
+
+	/* Clear any pending timer interrupts */
+	mtspr(SPRN_TSR, TSR_ENW | TSR_WIS | TSR_DIS | TSR_FIS);
+
+	/* Enable decrementer interrupt */
+	mtspr(SPRN_TCR, TCR_DIE);
+}
+
+struct smp_ops_t smp_85xx_ops = {
+	.message_pass = smp_mpic_message_pass,
+	.probe = smp_mpic_probe,
+	.kick_cpu = smp_85xx_kick_cpu,
+	.setup_cpu = smp_85xx_setup_cpu,
+};
+
+void __init
+mpc85xx_smp_init(void)
+{
+	smp_ops = &smp_85xx_ops;
+}
diff --git a/arch/powerpc/platforms/86xx/Kconfig b/arch/powerpc/platforms/86xx/Kconfig
index 77dd797a2580..8e5693935975 100644
--- a/arch/powerpc/platforms/86xx/Kconfig
+++ b/arch/powerpc/platforms/86xx/Kconfig
@@ -34,6 +34,8 @@ config MPC8610_HPCD
 config GEF_SBC610
 	bool "GE Fanuc SBC610"
 	select DEFAULT_UIMAGE
+	select GENERIC_GPIO
+	select ARCH_REQUIRE_GPIOLIB
 	select HAS_RAPIDIO
 	help
 	  This option enables support for GE Fanuc's SBC610.
diff --git a/arch/powerpc/platforms/86xx/Makefile b/arch/powerpc/platforms/86xx/Makefile
index 4a56ff619afd..31e540c2ebbc 100644
--- a/arch/powerpc/platforms/86xx/Makefile
+++ b/arch/powerpc/platforms/86xx/Makefile
@@ -7,4 +7,5 @@ obj-$(CONFIG_SMP)		+= mpc86xx_smp.o
 obj-$(CONFIG_MPC8641_HPCN)	+= mpc86xx_hpcn.o
 obj-$(CONFIG_SBC8641D)		+= sbc8641d.o
 obj-$(CONFIG_MPC8610_HPCD)	+= mpc8610_hpcd.o
-obj-$(CONFIG_GEF_SBC610)	+= gef_sbc610.o gef_pic.o
+gef-gpio-$(CONFIG_GPIOLIB)	+= gef_gpio.o
+obj-$(CONFIG_GEF_SBC610)	+= gef_sbc610.o gef_pic.o $(gef-gpio-y)
diff --git a/arch/powerpc/platforms/86xx/gef_gpio.c b/arch/powerpc/platforms/86xx/gef_gpio.c
new file mode 100644
index 000000000000..85b2800f4cb7
--- /dev/null
+++ b/arch/powerpc/platforms/86xx/gef_gpio.c
@@ -0,0 +1,143 @@
+/*
+ * Driver for GE Fanuc's FPGA based GPIO pins
+ *
+ * Author: Martyn Welch <martyn.welch@gefanuc.com>
+ *
+ * 2008 (c) GE Fanuc Intelligent Platforms Embedded Systems, Inc.
+ *
+ * This file is licensed under the terms of the GNU General Public License
+ * version 2.  This program is licensed "as is" without any warranty of any
+ * kind, whether express or implied.
+ */
+
+/* TODO
+ *
+ * Configuration of output modes (totem-pole/open-drain)
+ * Interrupt configuration - interrupts are always generated the FPGA relies on
+ * 	the I/O interrupt controllers mask to stop them propergating
+ */
+
+#include <linux/kernel.h>
+#include <linux/compiler.h>
+#include <linux/init.h>
+#include <linux/io.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/of_platform.h>
+#include <linux/of_gpio.h>
+#include <linux/gpio.h>
+
+#define GEF_GPIO_DIRECT		0x00
+#define GEF_GPIO_IN		0x04
+#define GEF_GPIO_OUT		0x08
+#define GEF_GPIO_TRIG		0x0C
+#define GEF_GPIO_POLAR_A	0x10
+#define GEF_GPIO_POLAR_B	0x14
+#define GEF_GPIO_INT_STAT	0x18
+#define GEF_GPIO_OVERRUN	0x1C
+#define GEF_GPIO_MODE		0x20
+
+#define NUM_GPIO 19
+
+static void _gef_gpio_set(void __iomem *reg, unsigned int offset, int value)
+{
+	unsigned int data;
+
+	data = ioread32be(reg);
+	/* value: 0=low; 1=high */
+	if (value & 0x1)
+		data = data | (0x1 << offset);
+	else
+		data = data & ~(0x1 << offset);
+
+	iowrite32be(data, reg);
+}
+
+
+static int gef_gpio_dir_in(struct gpio_chip *chip, unsigned offset)
+{
+	unsigned int data;
+	struct of_mm_gpio_chip *mmchip = to_of_mm_gpio_chip(chip);
+
+	data = ioread32be(mmchip->regs + GEF_GPIO_DIRECT);
+	data = data | (0x1 << offset);
+	iowrite32be(data, mmchip->regs + GEF_GPIO_DIRECT);
+
+	return 0;
+}
+
+static int gef_gpio_dir_out(struct gpio_chip *chip, unsigned offset, int value)
+{
+	unsigned int data;
+	struct of_mm_gpio_chip *mmchip = to_of_mm_gpio_chip(chip);
+
+	/* Set direction before switching to input */
+	_gef_gpio_set(mmchip->regs + GEF_GPIO_OUT, offset, value);
+
+	data = ioread32be(mmchip->regs + GEF_GPIO_DIRECT);
+	data = data & ~(0x1 << offset);
+	iowrite32be(data, mmchip->regs + GEF_GPIO_DIRECT);
+
+	return 0;
+}
+
+static int gef_gpio_get(struct gpio_chip *chip, unsigned offset)
+{
+	unsigned int data;
+	int state = 0;
+	struct of_mm_gpio_chip *mmchip = to_of_mm_gpio_chip(chip);
+
+	data = ioread32be(mmchip->regs + GEF_GPIO_IN);
+	state = (int)((data >> offset) & 0x1);
+
+	return state;
+}
+
+static void gef_gpio_set(struct gpio_chip *chip, unsigned offset, int value)
+{
+	struct of_mm_gpio_chip *mmchip = to_of_mm_gpio_chip(chip);
+
+	_gef_gpio_set(mmchip->regs + GEF_GPIO_OUT, offset, value);
+}
+
+static int __init gef_gpio_init(void)
+{
+	struct device_node *np;
+
+	for_each_compatible_node(np, NULL, "gef,sbc610-gpio") {
+		int retval;
+		struct of_mm_gpio_chip *gef_gpio_chip;
+
+		pr_debug("%s: Initialising GEF GPIO\n", np->full_name);
+
+		/* Allocate chip structure */
+		gef_gpio_chip = kzalloc(sizeof(*gef_gpio_chip), GFP_KERNEL);
+		if (!gef_gpio_chip) {
+			pr_err("%s: Unable to allocate structure\n",
+				np->full_name);
+			continue;
+		}
+
+		/* Setup pointers to chip functions */
+		gef_gpio_chip->of_gc.gpio_cells = 2;
+		gef_gpio_chip->of_gc.gc.ngpio = NUM_GPIO;
+		gef_gpio_chip->of_gc.gc.direction_input = gef_gpio_dir_in;
+		gef_gpio_chip->of_gc.gc.direction_output = gef_gpio_dir_out;
+		gef_gpio_chip->of_gc.gc.get = gef_gpio_get;
+		gef_gpio_chip->of_gc.gc.set = gef_gpio_set;
+
+		/* This function adds a memory mapped GPIO chip */
+		retval = of_mm_gpiochip_add(np, gef_gpio_chip);
+		if (retval) {
+			kfree(gef_gpio_chip);
+			pr_err("%s: Unable to add GPIO\n", np->full_name);
+		}
+	}
+
+	return 0;
+};
+arch_initcall(gef_gpio_init);
+
+MODULE_DESCRIPTION("GE Fanuc I/O FPGA GPIO driver");
+MODULE_AUTHOR("Martyn Welch <martyn.welch@gefanuc.com");
+MODULE_LICENSE("GPL");
diff --git a/arch/powerpc/platforms/cell/iommu.c b/arch/powerpc/platforms/cell/iommu.c
index 3168272ab0d7..86db4dd170a0 100644
--- a/arch/powerpc/platforms/cell/iommu.c
+++ b/arch/powerpc/platforms/cell/iommu.c
@@ -1053,10 +1053,7 @@ static int __init cell_iommu_fixed_mapping_init(void)
 	}
 
 	/* We must have dma-ranges properties for fixed mapping to work */
-	for (np = NULL; (np = of_find_all_nodes(np));) {
-		if (of_find_property(np, "dma-ranges", NULL))
-			break;
-	}
+	np = of_find_node_with_property(NULL, "dma-ranges");
 	of_node_put(np);
 
 	if (!np) {
diff --git a/arch/powerpc/platforms/powermac/setup.c b/arch/powerpc/platforms/powermac/setup.c
index 82c14d203d8b..12937725f869 100644
--- a/arch/powerpc/platforms/powermac/setup.c
+++ b/arch/powerpc/platforms/powermac/setup.c
@@ -310,9 +310,7 @@ static void __init pmac_setup_arch(void)
 	}
 
 	/* See if newworld or oldworld */
-	for (ic = NULL; (ic = of_find_all_nodes(ic)) != NULL; )
-		if (of_get_property(ic, "interrupt-controller", NULL))
-			break;
+	ic = of_find_node_with_property(NULL, "interrupt-controller");
 	if (ic) {
 		pmac_newworld = 1;
 		of_node_put(ic);
diff --git a/arch/powerpc/platforms/ps3/device-init.c b/arch/powerpc/platforms/ps3/device-init.c
index ffdd8e963fbd..43816da25ca6 100644
--- a/arch/powerpc/platforms/ps3/device-init.c
+++ b/arch/powerpc/platforms/ps3/device-init.c
@@ -314,11 +314,17 @@ static int __init ps3_setup_vuart_device(enum ps3_match_id match_id,
 
 	result = ps3_system_bus_device_register(&p->dev);
 
-	if (result)
+	if (result) {
 		pr_debug("%s:%d ps3_system_bus_device_register failed\n",
 			__func__, __LINE__);
-
+		goto fail_device_register;
+	}
 	pr_debug(" <- %s:%d\n", __func__, __LINE__);
+	return 0;
+
+fail_device_register:
+	kfree(p);
+	pr_debug(" <- %s:%d fail\n", __func__, __LINE__);
 	return result;
 }
 
@@ -463,11 +469,17 @@ static int __init ps3_register_sound_devices(void)
 
 	result = ps3_system_bus_device_register(&p->dev);
 
-	if (result)
+	if (result) {
 		pr_debug("%s:%d ps3_system_bus_device_register failed\n",
 			__func__, __LINE__);
-
+		goto fail_device_register;
+	}
 	pr_debug(" <- %s:%d\n", __func__, __LINE__);
+	return 0;
+
+fail_device_register:
+	kfree(p);
+	pr_debug(" <- %s:%d failed\n", __func__, __LINE__);
 	return result;
 }
 
@@ -491,11 +503,18 @@ static int __init ps3_register_graphics_devices(void)
 
 	result = ps3_system_bus_device_register(&p->dev);
 
-	if (result)
+	if (result) {
 		pr_debug("%s:%d ps3_system_bus_device_register failed\n",
 			__func__, __LINE__);
+		goto fail_device_register;
+	}
 
 	pr_debug(" <- %s:%d\n", __func__, __LINE__);
+	return 0;
+
+fail_device_register:
+	kfree(p);
+	pr_debug(" <- %s:%d failed\n", __func__, __LINE__);
 	return result;
 }
 
diff --git a/arch/powerpc/platforms/ps3/setup.c b/arch/powerpc/platforms/ps3/setup.c
index 77bc330263c4..bfc33fb2c7c4 100644
--- a/arch/powerpc/platforms/ps3/setup.c
+++ b/arch/powerpc/platforms/ps3/setup.c
@@ -42,6 +42,10 @@
 #define DBG pr_debug
 #endif
 
+/* mutex synchronizing GPU accesses and video mode changes */
+DEFINE_MUTEX(ps3_gpu_mutex);
+EXPORT_SYMBOL_GPL(ps3_gpu_mutex);
+
 #if !defined(CONFIG_SMP)
 static void smp_send_stop(void) {}
 #endif
diff --git a/arch/powerpc/platforms/ps3/system-bus.c b/arch/powerpc/platforms/ps3/system-bus.c
index 661e9f77ebf6..91fb0b09287b 100644
--- a/arch/powerpc/platforms/ps3/system-bus.c
+++ b/arch/powerpc/platforms/ps3/system-bus.c
@@ -31,7 +31,7 @@
 #include "platform.h"
 
 static struct device ps3_system_bus = {
-	.bus_id = "ps3_system",
+	.init_name = "ps3_system",
 };
 
 /* FIXME: need device usage counters! */
@@ -356,12 +356,12 @@ static int ps3_system_bus_match(struct device *_dev,
 	if (result)
 		pr_info("%s:%d: dev=%u.%u(%s), drv=%u.%u(%s): match\n",
 			__func__, __LINE__,
-			dev->match_id, dev->match_sub_id, dev->core.bus_id,
+			dev->match_id, dev->match_sub_id, dev_name(&dev->core),
 			drv->match_id, drv->match_sub_id, drv->core.name);
 	else
 		pr_debug("%s:%d: dev=%u.%u(%s), drv=%u.%u(%s): miss\n",
 			__func__, __LINE__,
-			dev->match_id, dev->match_sub_id, dev->core.bus_id,
+			dev->match_id, dev->match_sub_id, dev_name(&dev->core),
 			drv->match_id, drv->match_sub_id, drv->core.name);
 
 	return result;
@@ -383,9 +383,9 @@ static int ps3_system_bus_probe(struct device *_dev)
 		result = drv->probe(dev);
 	else
 		pr_debug("%s:%d: %s no probe method\n", __func__, __LINE__,
-			dev->core.bus_id);
+			dev_name(&dev->core));
 
-	pr_debug(" <- %s:%d: %s\n", __func__, __LINE__, dev->core.bus_id);
+	pr_debug(" <- %s:%d: %s\n", __func__, __LINE__, dev_name(&dev->core));
 	return result;
 }
 
@@ -407,7 +407,7 @@ static int ps3_system_bus_remove(struct device *_dev)
 		dev_dbg(&dev->core, "%s:%d %s: no remove method\n",
 			__func__, __LINE__, drv->core.name);
 
-	pr_debug(" <- %s:%d: %s\n", __func__, __LINE__, dev->core.bus_id);
+	pr_debug(" <- %s:%d: %s\n", __func__, __LINE__, dev_name(&dev->core));
 	return result;
 }
 
@@ -432,7 +432,7 @@ static void ps3_system_bus_shutdown(struct device *_dev)
 	BUG_ON(!drv);
 
 	dev_dbg(&dev->core, "%s:%d: %s -> %s\n", __func__, __LINE__,
-		dev->core.bus_id, drv->core.name);
+		dev_name(&dev->core), drv->core.name);
 
 	if (drv->shutdown)
 		drv->shutdown(dev);
@@ -742,22 +742,18 @@ int ps3_system_bus_device_register(struct ps3_system_bus_device *dev)
 	switch (dev->dev_type) {
 	case PS3_DEVICE_TYPE_IOC0:
 		dev->core.archdata.dma_ops = &ps3_ioc0_dma_ops;
-		snprintf(dev->core.bus_id, sizeof(dev->core.bus_id),
-			"ioc0_%02x", ++dev_ioc0_count);
+		dev_set_name(&dev->core, "ioc0_%02x", ++dev_ioc0_count);
 		break;
 	case PS3_DEVICE_TYPE_SB:
 		dev->core.archdata.dma_ops = &ps3_sb_dma_ops;
-		snprintf(dev->core.bus_id, sizeof(dev->core.bus_id),
-			"sb_%02x", ++dev_sb_count);
+		dev_set_name(&dev->core, "sb_%02x", ++dev_sb_count);
 
 		break;
 	case PS3_DEVICE_TYPE_VUART:
-		snprintf(dev->core.bus_id, sizeof(dev->core.bus_id),
-			"vuart_%02x", ++dev_vuart_count);
+		dev_set_name(&dev->core, "vuart_%02x", ++dev_vuart_count);
 		break;
 	case PS3_DEVICE_TYPE_LPM:
-		snprintf(dev->core.bus_id, sizeof(dev->core.bus_id),
-			"lpm_%02x", ++dev_lpm_count);
+		dev_set_name(&dev->core, "lpm_%02x", ++dev_lpm_count);
 		break;
 	default:
 		BUG();
@@ -766,7 +762,7 @@ int ps3_system_bus_device_register(struct ps3_system_bus_device *dev)
 	dev->core.archdata.of_node = NULL;
 	set_dev_node(&dev->core, 0);
 
-	pr_debug("%s:%d add %s\n", __func__, __LINE__, dev->core.bus_id);
+	pr_debug("%s:%d add %s\n", __func__, __LINE__, dev_name(&dev->core));
 
 	result = device_register(&dev->core);
 	return result;
diff --git a/arch/powerpc/platforms/pseries/eeh.c b/arch/powerpc/platforms/pseries/eeh.c
index 54816d75b578..989d6462c154 100644
--- a/arch/powerpc/platforms/pseries/eeh.c
+++ b/arch/powerpc/platforms/pseries/eeh.c
@@ -21,6 +21,8 @@
  * Please address comments and feedback to Linas Vepstas <linas@austin.ibm.com>
  */
 
+#undef DEBUG
+
 #include <linux/delay.h>
 #include <linux/init.h>
 #include <linux/list.h>
@@ -488,10 +490,8 @@ int eeh_dn_check_failure(struct device_node *dn, struct pci_dev *dev)
 	if (!(pdn->eeh_mode & EEH_MODE_SUPPORTED) ||
 	    pdn->eeh_mode & EEH_MODE_NOCHECK) {
 		ignored_check++;
-#ifdef DEBUG
-		printk ("EEH:ignored check (%x) for %s %s\n", 
-		        pdn->eeh_mode, pci_name (dev), dn->full_name);
-#endif
+		pr_debug("EEH: Ignored check (%x) for %s %s\n",
+			 pdn->eeh_mode, pci_name (dev), dn->full_name);
 		return 0;
 	}
 
@@ -1014,10 +1014,9 @@ static void *early_enable_eeh(struct device_node *dn, void *data)
 			eeh_subsystem_enabled = 1;
 			pdn->eeh_mode |= EEH_MODE_SUPPORTED;
 
-#ifdef DEBUG
-			printk(KERN_DEBUG "EEH: %s: eeh enabled, config=%x pe_config=%x\n",
-			       dn->full_name, pdn->eeh_config_addr, pdn->eeh_pe_config_addr);
-#endif
+			pr_debug("EEH: %s: eeh enabled, config=%x pe_config=%x\n",
+				 dn->full_name, pdn->eeh_config_addr,
+				 pdn->eeh_pe_config_addr);
 		} else {
 
 			/* This device doesn't support EEH, but it may have an
@@ -1161,13 +1160,17 @@ static void eeh_add_device_late(struct pci_dev *dev)
 	if (!dev || !eeh_subsystem_enabled)
 		return;
 
-#ifdef DEBUG
-	printk(KERN_DEBUG "EEH: adding device %s\n", pci_name(dev));
-#endif
+	pr_debug("EEH: Adding device %s\n", pci_name(dev));
 
-	pci_dev_get (dev);
 	dn = pci_device_to_OF_node(dev);
 	pdn = PCI_DN(dn);
+	if (pdn->pcidev == dev) {
+		pr_debug("EEH: Already referenced !\n");
+		return;
+	}
+	WARN_ON(pdn->pcidev);
+
+	pci_dev_get (dev);
 	pdn->pcidev = dev;
 
 	pci_addr_cache_insert_device(dev);
@@ -1206,17 +1209,18 @@ static void eeh_remove_device(struct pci_dev *dev)
 		return;
 
 	/* Unregister the device with the EEH/PCI address search system */
-#ifdef DEBUG
-	printk(KERN_DEBUG "EEH: remove device %s\n", pci_name(dev));
-#endif
-	pci_addr_cache_remove_device(dev);
-	eeh_sysfs_remove_device(dev);
+	pr_debug("EEH: Removing device %s\n", pci_name(dev));
 
 	dn = pci_device_to_OF_node(dev);
-	if (PCI_DN(dn)->pcidev) {
-		PCI_DN(dn)->pcidev = NULL;
-		pci_dev_put (dev);
+	if (PCI_DN(dn)->pcidev == NULL) {
+		pr_debug("EEH: Not referenced !\n");
+		return;
 	}
+	PCI_DN(dn)->pcidev = NULL;
+	pci_dev_put (dev);
+
+	pci_addr_cache_remove_device(dev);
+	eeh_sysfs_remove_device(dev);
 }
 
 void eeh_remove_bus_device(struct pci_dev *dev)
diff --git a/arch/powerpc/platforms/pseries/pci_dlpar.c b/arch/powerpc/platforms/pseries/pci_dlpar.c
index 7190493e9bdc..5e1ed3d60ee5 100644
--- a/arch/powerpc/platforms/pseries/pci_dlpar.c
+++ b/arch/powerpc/platforms/pseries/pci_dlpar.c
@@ -25,6 +25,8 @@
  * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
+#undef DEBUG
+
 #include <linux/pci.h>
 #include <asm/pci-bridge.h>
 #include <asm/ppc-pci.h>
@@ -69,74 +71,25 @@ EXPORT_SYMBOL_GPL(pcibios_find_pci_bus);
  * Remove all of the PCI devices under this bus both from the
  * linux pci device tree, and from the powerpc EEH address cache.
  */
-void
-pcibios_remove_pci_devices(struct pci_bus *bus)
+void pcibios_remove_pci_devices(struct pci_bus *bus)
 {
-	struct pci_dev *dev, *tmp;
+ 	struct pci_dev *dev, *tmp;
+	struct pci_bus *child_bus;
+
+	/* First go down child busses */
+	list_for_each_entry(child_bus, &bus->children, node)
+		pcibios_remove_pci_devices(child_bus);
 
+	pr_debug("PCI: Removing devices on bus %04x:%02x\n",
+		 pci_domain_nr(bus),  bus->number);
 	list_for_each_entry_safe(dev, tmp, &bus->devices, bus_list) {
+		pr_debug("     * Removing %s...\n", pci_name(dev));
 		eeh_remove_bus_device(dev);
-		pci_remove_bus_device(dev);
-	}
+ 		pci_remove_bus_device(dev);
+ 	}
 }
 EXPORT_SYMBOL_GPL(pcibios_remove_pci_devices);
 
-/* Must be called before pci_bus_add_devices */
-void
-pcibios_fixup_new_pci_devices(struct pci_bus *bus)
-{
-	struct pci_dev *dev;
-
-	list_for_each_entry(dev, &bus->devices, bus_list) {
-		/* Skip already-added devices */
-		if (!dev->is_added) {
-			int i;
-
-			/* Fill device archdata and setup iommu table */
-			pcibios_setup_new_device(dev);
-
-			pci_read_irq_line(dev);
-			for (i = 0; i < PCI_NUM_RESOURCES; i++) {
-				struct resource *r = &dev->resource[i];
-
-				if (r->parent || !r->start || !r->flags)
-					continue;
-				pci_claim_resource(dev, i);
-			}
-		}
-	}
-}
-EXPORT_SYMBOL_GPL(pcibios_fixup_new_pci_devices);
-
-static int
-pcibios_pci_config_bridge(struct pci_dev *dev)
-{
-	u8 sec_busno;
-	struct pci_bus *child_bus;
-
-	/* Get busno of downstream bus */
-	pci_read_config_byte(dev, PCI_SECONDARY_BUS, &sec_busno);
-
-	/* Add to children of PCI bridge dev->bus */
-	child_bus = pci_add_new_bus(dev->bus, dev, sec_busno);
-	if (!child_bus) {
-		printk (KERN_ERR "%s: could not add second bus\n", __func__);
-		return -EIO;
-	}
-	sprintf(child_bus->name, "PCI Bus #%02x", child_bus->number);
-
-	pci_scan_child_bus(child_bus);
-
-	/* Fixup new pci devices */
-	pcibios_fixup_new_pci_devices(child_bus);
-
-	/* Make the discovered devices available */
-	pci_bus_add_devices(child_bus);
-
-	eeh_add_device_tree_late(child_bus);
-	return 0;
-}
-
 /**
  * pcibios_add_pci_devices - adds new pci devices to bus
  *
@@ -147,10 +100,9 @@ pcibios_pci_config_bridge(struct pci_dev *dev)
  * is how this routine differs from other, similar pcibios
  * routines.)
  */
-void
-pcibios_add_pci_devices(struct pci_bus * bus)
+void pcibios_add_pci_devices(struct pci_bus * bus)
 {
-	int slotno, num, mode;
+	int slotno, num, mode, pass, max;
 	struct pci_dev *dev;
 	struct device_node *dn = pci_bus_to_OF_node(bus);
 
@@ -162,26 +114,23 @@ pcibios_add_pci_devices(struct pci_bus * bus)
 
 	if (mode == PCI_PROBE_DEVTREE) {
 		/* use ofdt-based probe */
-		of_scan_bus(dn, bus);
-		if (!list_empty(&bus->devices)) {
-			pcibios_fixup_new_pci_devices(bus);
-			pci_bus_add_devices(bus);
-			eeh_add_device_tree_late(bus);
-		}
+		of_rescan_bus(dn, bus);
 	} else if (mode == PCI_PROBE_NORMAL) {
 		/* use legacy probe */
 		slotno = PCI_SLOT(PCI_DN(dn->child)->devfn);
 		num = pci_scan_slot(bus, PCI_DEVFN(slotno, 0));
-		if (num) {
-			pcibios_fixup_new_pci_devices(bus);
-			pci_bus_add_devices(bus);
-			eeh_add_device_tree_late(bus);
+		if (!num)
+			return;
+		pcibios_setup_bus_devices(bus);
+		max = bus->secondary;
+		for (pass=0; pass < 2; pass++)
+			list_for_each_entry(dev, &bus->devices, bus_list) {
+			if (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE ||
+			    dev->hdr_type == PCI_HEADER_TYPE_CARDBUS)
+				max = pci_scan_bridge(bus, dev, max, pass);
 		}
-
-		list_for_each_entry(dev, &bus->devices, bus_list)
-			if (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE)
-				pcibios_pci_config_bridge(dev);
 	}
+	pcibios_finish_adding_to_bus(bus);
 }
 EXPORT_SYMBOL_GPL(pcibios_add_pci_devices);
 
@@ -190,6 +139,8 @@ struct pci_controller * __devinit init_phb_dynamic(struct device_node *dn)
 	struct pci_controller *phb;
 	int primary;
 
+	pr_debug("PCI: Initializing new hotplug PHB %s\n", dn->full_name);
+
 	primary = list_empty(&hose_list);
 	phb = pcibios_alloc_controller(dn);
 	if (!phb)
@@ -203,11 +154,59 @@ struct pci_controller * __devinit init_phb_dynamic(struct device_node *dn)
 		eeh_add_device_tree_early(dn);
 
 	scan_phb(phb);
-	pcibios_allocate_bus_resources(phb->bus);
-	pcibios_fixup_new_pci_devices(phb->bus);
-	pci_bus_add_devices(phb->bus);
-	eeh_add_device_tree_late(phb->bus);
+	pcibios_finish_adding_to_bus(phb->bus);
 
 	return phb;
 }
 EXPORT_SYMBOL_GPL(init_phb_dynamic);
+
+/* RPA-specific bits for removing PHBs */
+int remove_phb_dynamic(struct pci_controller *phb)
+{
+	struct pci_bus *b = phb->bus;
+	struct resource *res;
+	int rc, i;
+
+	pr_debug("PCI: Removing PHB %04x:%02x... \n",
+		 pci_domain_nr(b), b->number);
+
+	/* We cannot to remove a root bus that has children */
+	if (!(list_empty(&b->children) && list_empty(&b->devices)))
+		return -EBUSY;
+
+	/* We -know- there aren't any child devices anymore at this stage
+	 * and thus, we can safely unmap the IO space as it's not in use
+	 */
+	res = &phb->io_resource;
+	if (res->flags & IORESOURCE_IO) {
+		rc = pcibios_unmap_io_space(b);
+		if (rc) {
+			printk(KERN_ERR "%s: failed to unmap IO on bus %s\n",
+			       __func__, b->name);
+			return 1;
+		}
+	}
+
+	/* Unregister the bridge device from sysfs and remove the PCI bus */
+	device_unregister(b->bridge);
+	phb->bus = NULL;
+	pci_remove_bus(b);
+
+	/* Now release the IO resource */
+	if (res->flags & IORESOURCE_IO)
+		release_resource(res);
+
+	/* Release memory resources */
+	for (i = 0; i < 3; ++i) {
+		res = &phb->mem_resources[i];
+		if (!(res->flags & IORESOURCE_MEM))
+			continue;
+		release_resource(res);
+	}
+
+	/* Free pci_controller data structure */
+	pcibios_free_controller(phb);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(remove_phb_dynamic);
diff --git a/arch/powerpc/platforms/pseries/xics.c b/arch/powerpc/platforms/pseries/xics.c
index e1904774a70f..75a289ba66b8 100644
--- a/arch/powerpc/platforms/pseries/xics.c
+++ b/arch/powerpc/platforms/pseries/xics.c
@@ -579,7 +579,7 @@ static void xics_update_irq_servers(void)
 	int i, j;
 	struct device_node *np;
 	u32 ilen;
-	const u32 *ireg, *isize;
+	const u32 *ireg;
 	u32 hcpuid;
 
 	/* Find the server numbers for the boot cpu. */
@@ -607,11 +607,6 @@ static void xics_update_irq_servers(void)
 		}
 	}
 
-	/* get the bit size of server numbers */
-	isize = of_get_property(np, "ibm,interrupt-server#-size", NULL);
-	if (isize)
-		interrupt_server_size = *isize;
-
 	of_node_put(np);
 }
 
@@ -682,6 +677,7 @@ void __init xics_init_IRQ(void)
 	struct device_node *np;
 	u32 indx = 0;
 	int found = 0;
+	const u32 *isize;
 
 	ppc64_boot_msg(0x20, "XICS Init");
 
@@ -701,6 +697,26 @@ void __init xics_init_IRQ(void)
 	if (found == 0)
 		return;
 
+	/* get the bit size of server numbers */
+	found = 0;
+
+	for_each_compatible_node(np, NULL, "ibm,ppc-xics") {
+		isize = of_get_property(np, "ibm,interrupt-server#-size", NULL);
+
+		if (!isize)
+			continue;
+
+		if (!found) {
+			interrupt_server_size = *isize;
+			found = 1;
+		} else if (*isize != interrupt_server_size) {
+			printk(KERN_WARNING "XICS: "
+			       "mismatched ibm,interrupt-server#-size\n");
+			interrupt_server_size = max(*isize,
+						    interrupt_server_size);
+		}
+	}
+
 	xics_update_irq_servers();
 	xics_init_host();
 
diff --git a/arch/powerpc/sysdev/mpic.c b/arch/powerpc/sysdev/mpic.c
index 1890fb085cde..c82babb70074 100644
--- a/arch/powerpc/sysdev/mpic.c
+++ b/arch/powerpc/sysdev/mpic.c
@@ -661,17 +661,6 @@ static inline void mpic_eoi(struct mpic *mpic)
 	(void)mpic_cpu_read(MPIC_INFO(CPU_WHOAMI));
 }
 
-#ifdef CONFIG_SMP
-static irqreturn_t mpic_ipi_action(int irq, void *data)
-{
-	long ipi = (long)data;
-
-	smp_message_recv(ipi);
-
-	return IRQ_HANDLED;
-}
-#endif /* CONFIG_SMP */
-
 /*
  * Linux descriptor level callbacks
  */
@@ -1548,13 +1537,7 @@ unsigned int mpic_get_mcirq(void)
 void mpic_request_ipis(void)
 {
 	struct mpic *mpic = mpic_primary;
-	long i, err;
-	static char *ipi_names[] = {
-		"IPI0 (call function)",
-		"IPI1 (reschedule)",
-		"IPI2 (call function single)",
-		"IPI3 (debugger break)",
-	};
+	int i;
 	BUG_ON(mpic == NULL);
 
 	printk(KERN_INFO "mpic: requesting IPIs ... \n");
@@ -1563,17 +1546,10 @@ void mpic_request_ipis(void)
 		unsigned int vipi = irq_create_mapping(mpic->irqhost,
 						       mpic->ipi_vecs[0] + i);
 		if (vipi == NO_IRQ) {
-			printk(KERN_ERR "Failed to map IPI %ld\n", i);
-			break;
-		}
-		err = request_irq(vipi, mpic_ipi_action,
-				  IRQF_DISABLED|IRQF_PERCPU,
-				  ipi_names[i], (void *)i);
-		if (err) {
-			printk(KERN_ERR "Request of irq %d for IPI %ld failed\n",
-			       vipi, i);
-			break;
+			printk(KERN_ERR "Failed to map %s\n", smp_ipi_name[i]);
+			continue;
 		}
+		smp_request_message_ipi(vipi, i);
 	}
 }
 
diff --git a/arch/powerpc/sysdev/ppc4xx_pci.c b/arch/powerpc/sysdev/ppc4xx_pci.c
index d3e4d61030b5..77fae5f64f2e 100644
--- a/arch/powerpc/sysdev/ppc4xx_pci.c
+++ b/arch/powerpc/sysdev/ppc4xx_pci.c
@@ -194,11 +194,41 @@ static int __init ppc4xx_parse_dma_ranges(struct pci_controller *hose,
  * 4xx PCI 2.x part
  */
 
+static int __init ppc4xx_setup_one_pci_PMM(struct pci_controller	*hose,
+					   void __iomem			*reg,
+					   u64				plb_addr,
+					   u64				pci_addr,
+					   u64				size,
+					   unsigned int			flags,
+					   int				index)
+{
+	u32 ma, pcila, pciha;
+
+	if ((plb_addr + size) > 0xffffffffull || !is_power_of_2(size) ||
+	    size < 0x1000 || (plb_addr & (size - 1)) != 0) {
+		printk(KERN_WARNING "%s: Resource out of range\n",
+		       hose->dn->full_name);
+		return -1;
+	}
+	ma = (0xffffffffu << ilog2(size)) | 1;
+	if (flags & IORESOURCE_PREFETCH)
+		ma |= 2;
+
+	pciha = RES_TO_U32_HIGH(pci_addr);
+	pcila = RES_TO_U32_LOW(pci_addr);
+
+	writel(plb_addr, reg + PCIL0_PMM0LA + (0x10 * index));
+	writel(pcila, reg + PCIL0_PMM0PCILA + (0x10 * index));
+	writel(pciha, reg + PCIL0_PMM0PCIHA + (0x10 * index));
+	writel(ma, reg + PCIL0_PMM0MA + (0x10 * index));
+
+	return 0;
+}
+
 static void __init ppc4xx_configure_pci_PMMs(struct pci_controller *hose,
 					     void __iomem *reg)
 {
-	u32 la, ma, pcila, pciha;
-	int i, j;
+	int i, j, found_isa_hole = 0;
 
 	/* Setup outbound memory windows */
 	for (i = j = 0; i < 3; i++) {
@@ -213,28 +243,29 @@ static void __init ppc4xx_configure_pci_PMMs(struct pci_controller *hose,
 			break;
 		}
 
-		/* Calculate register values */
-		la = res->start;
-		pciha = RES_TO_U32_HIGH(res->start - hose->pci_mem_offset);
-		pcila = RES_TO_U32_LOW(res->start - hose->pci_mem_offset);
-
-		ma = res->end + 1 - res->start;
-		if (!is_power_of_2(ma) || ma < 0x1000 || ma > 0xffffffffu) {
-			printk(KERN_WARNING "%s: Resource out of range\n",
-			       hose->dn->full_name);
-			continue;
+		/* Configure the resource */
+		if (ppc4xx_setup_one_pci_PMM(hose, reg,
+					     res->start,
+					     res->start - hose->pci_mem_offset,
+					     res->end + 1 - res->start,
+					     res->flags,
+					     j) == 0) {
+			j++;
+
+			/* If the resource PCI address is 0 then we have our
+			 * ISA memory hole
+			 */
+			if (res->start == hose->pci_mem_offset)
+				found_isa_hole = 1;
 		}
-		ma = (0xffffffffu << ilog2(ma)) | 0x1;
-		if (res->flags & IORESOURCE_PREFETCH)
-			ma |= 0x2;
-
-		/* Program register values */
-		writel(la, reg + PCIL0_PMM0LA + (0x10 * j));
-		writel(pcila, reg + PCIL0_PMM0PCILA + (0x10 * j));
-		writel(pciha, reg + PCIL0_PMM0PCIHA + (0x10 * j));
-		writel(ma, reg + PCIL0_PMM0MA + (0x10 * j));
-		j++;
 	}
+
+	/* Handle ISA memory hole if not already covered */
+	if (j <= 2 && !found_isa_hole && hose->isa_mem_size)
+		if (ppc4xx_setup_one_pci_PMM(hose, reg, hose->isa_mem_phys, 0,
+					     hose->isa_mem_size, 0, j) == 0)
+			printk(KERN_INFO "%s: Legacy ISA memory support enabled\n",
+			       hose->dn->full_name);
 }
 
 static void __init ppc4xx_configure_pci_PTMs(struct pci_controller *hose,
@@ -352,11 +383,52 @@ static void __init ppc4xx_probe_pci_bridge(struct device_node *np)
  * 4xx PCI-X part
  */
 
+static int __init ppc4xx_setup_one_pcix_POM(struct pci_controller	*hose,
+					    void __iomem		*reg,
+					    u64				plb_addr,
+					    u64				pci_addr,
+					    u64				size,
+					    unsigned int		flags,
+					    int				index)
+{
+	u32 lah, lal, pciah, pcial, sa;
+
+	if (!is_power_of_2(size) || size < 0x1000 ||
+	    (plb_addr & (size - 1)) != 0) {
+		printk(KERN_WARNING "%s: Resource out of range\n",
+		       hose->dn->full_name);
+		return -1;
+	}
+
+	/* Calculate register values */
+	lah = RES_TO_U32_HIGH(plb_addr);
+	lal = RES_TO_U32_LOW(plb_addr);
+	pciah = RES_TO_U32_HIGH(pci_addr);
+	pcial = RES_TO_U32_LOW(pci_addr);
+	sa = (0xffffffffu << ilog2(size)) | 0x1;
+
+	/* Program register values */
+	if (index == 0) {
+		writel(lah, reg + PCIX0_POM0LAH);
+		writel(lal, reg + PCIX0_POM0LAL);
+		writel(pciah, reg + PCIX0_POM0PCIAH);
+		writel(pcial, reg + PCIX0_POM0PCIAL);
+		writel(sa, reg + PCIX0_POM0SA);
+	} else {
+		writel(lah, reg + PCIX0_POM1LAH);
+		writel(lal, reg + PCIX0_POM1LAL);
+		writel(pciah, reg + PCIX0_POM1PCIAH);
+		writel(pcial, reg + PCIX0_POM1PCIAL);
+		writel(sa, reg + PCIX0_POM1SA);
+	}
+
+	return 0;
+}
+
 static void __init ppc4xx_configure_pcix_POMs(struct pci_controller *hose,
 					      void __iomem *reg)
 {
-	u32 lah, lal, pciah, pcial, sa;
-	int i, j;
+	int i, j, found_isa_hole = 0;
 
 	/* Setup outbound memory windows */
 	for (i = j = 0; i < 3; i++) {
@@ -371,36 +443,29 @@ static void __init ppc4xx_configure_pcix_POMs(struct pci_controller *hose,
 			break;
 		}
 
-		/* Calculate register values */
-		lah = RES_TO_U32_HIGH(res->start);
-		lal = RES_TO_U32_LOW(res->start);
-		pciah = RES_TO_U32_HIGH(res->start - hose->pci_mem_offset);
-		pcial = RES_TO_U32_LOW(res->start - hose->pci_mem_offset);
-		sa = res->end + 1 - res->start;
-		if (!is_power_of_2(sa) || sa < 0x100000 ||
-		    sa > 0xffffffffu) {
-			printk(KERN_WARNING "%s: Resource out of range\n",
-			       hose->dn->full_name);
-			continue;
+		/* Configure the resource */
+		if (ppc4xx_setup_one_pcix_POM(hose, reg,
+					      res->start,
+					      res->start - hose->pci_mem_offset,
+					      res->end + 1 - res->start,
+					      res->flags,
+					      j) == 0) {
+			j++;
+
+			/* If the resource PCI address is 0 then we have our
+			 * ISA memory hole
+			 */
+			if (res->start == hose->pci_mem_offset)
+				found_isa_hole = 1;
 		}
-		sa = (0xffffffffu << ilog2(sa)) | 0x1;
-
-		/* Program register values */
-		if (j == 0) {
-			writel(lah, reg + PCIX0_POM0LAH);
-			writel(lal, reg + PCIX0_POM0LAL);
-			writel(pciah, reg + PCIX0_POM0PCIAH);
-			writel(pcial, reg + PCIX0_POM0PCIAL);
-			writel(sa, reg + PCIX0_POM0SA);
-		} else {
-			writel(lah, reg + PCIX0_POM1LAH);
-			writel(lal, reg + PCIX0_POM1LAL);
-			writel(pciah, reg + PCIX0_POM1PCIAH);
-			writel(pcial, reg + PCIX0_POM1PCIAL);
-			writel(sa, reg + PCIX0_POM1SA);
-		}
-		j++;
 	}
+
+	/* Handle ISA memory hole if not already covered */
+	if (j <= 1 && !found_isa_hole && hose->isa_mem_size)
+		if (ppc4xx_setup_one_pcix_POM(hose, reg, hose->isa_mem_phys, 0,
+					      hose->isa_mem_size, 0, j) == 0)
+			printk(KERN_INFO "%s: Legacy ISA memory support enabled\n",
+			       hose->dn->full_name);
 }
 
 static void __init ppc4xx_configure_pcix_PIMs(struct pci_controller *hose,
@@ -1317,12 +1382,72 @@ static struct pci_ops ppc4xx_pciex_pci_ops =
 	.write = ppc4xx_pciex_write_config,
 };
 
+static int __init ppc4xx_setup_one_pciex_POM(struct ppc4xx_pciex_port	*port,
+					     struct pci_controller	*hose,
+					     void __iomem		*mbase,
+					     u64			plb_addr,
+					     u64			pci_addr,
+					     u64			size,
+					     unsigned int		flags,
+					     int			index)
+{
+	u32 lah, lal, pciah, pcial, sa;
+
+	if (!is_power_of_2(size) ||
+	    (index < 2 && size < 0x100000) ||
+	    (index == 2 && size < 0x100) ||
+	    (plb_addr & (size - 1)) != 0) {
+		printk(KERN_WARNING "%s: Resource out of range\n",
+		       hose->dn->full_name);
+		return -1;
+	}
+
+	/* Calculate register values */
+	lah = RES_TO_U32_HIGH(plb_addr);
+	lal = RES_TO_U32_LOW(plb_addr);
+	pciah = RES_TO_U32_HIGH(pci_addr);
+	pcial = RES_TO_U32_LOW(pci_addr);
+	sa = (0xffffffffu << ilog2(size)) | 0x1;
+
+	/* Program register values */
+	switch (index) {
+	case 0:
+		out_le32(mbase + PECFG_POM0LAH, pciah);
+		out_le32(mbase + PECFG_POM0LAL, pcial);
+		dcr_write(port->dcrs, DCRO_PEGPL_OMR1BAH, lah);
+		dcr_write(port->dcrs, DCRO_PEGPL_OMR1BAL, lal);
+		dcr_write(port->dcrs, DCRO_PEGPL_OMR1MSKH, 0x7fffffff);
+		/* Note that 3 here means enabled | single region */
+		dcr_write(port->dcrs, DCRO_PEGPL_OMR1MSKL, sa | 3);
+		break;
+	case 1:
+		out_le32(mbase + PECFG_POM1LAH, pciah);
+		out_le32(mbase + PECFG_POM1LAL, pcial);
+		dcr_write(port->dcrs, DCRO_PEGPL_OMR2BAH, lah);
+		dcr_write(port->dcrs, DCRO_PEGPL_OMR2BAL, lal);
+		dcr_write(port->dcrs, DCRO_PEGPL_OMR2MSKH, 0x7fffffff);
+		/* Note that 3 here means enabled | single region */
+		dcr_write(port->dcrs, DCRO_PEGPL_OMR2MSKL, sa | 3);
+		break;
+	case 2:
+		out_le32(mbase + PECFG_POM2LAH, pciah);
+		out_le32(mbase + PECFG_POM2LAL, pcial);
+		dcr_write(port->dcrs, DCRO_PEGPL_OMR3BAH, lah);
+		dcr_write(port->dcrs, DCRO_PEGPL_OMR3BAL, lal);
+		dcr_write(port->dcrs, DCRO_PEGPL_OMR3MSKH, 0x7fffffff);
+		/* Note that 3 here means enabled | IO space !!! */
+		dcr_write(port->dcrs, DCRO_PEGPL_OMR3MSKL, sa | 3);
+		break;
+	}
+
+	return 0;
+}
+
 static void __init ppc4xx_configure_pciex_POMs(struct ppc4xx_pciex_port *port,
 					       struct pci_controller *hose,
 					       void __iomem *mbase)
 {
-	u32 lah, lal, pciah, pcial, sa;
-	int i, j;
+	int i, j, found_isa_hole = 0;
 
 	/* Setup outbound memory windows */
 	for (i = j = 0; i < 3; i++) {
@@ -1337,53 +1462,38 @@ static void __init ppc4xx_configure_pciex_POMs(struct ppc4xx_pciex_port *port,
 			break;
 		}
 
-		/* Calculate register values */
-		lah = RES_TO_U32_HIGH(res->start);
-		lal = RES_TO_U32_LOW(res->start);
-		pciah = RES_TO_U32_HIGH(res->start - hose->pci_mem_offset);
-		pcial = RES_TO_U32_LOW(res->start - hose->pci_mem_offset);
-		sa = res->end + 1 - res->start;
-		if (!is_power_of_2(sa) || sa < 0x100000 ||
-		    sa > 0xffffffffu) {
-			printk(KERN_WARNING "%s: Resource out of range\n",
-			       port->node->full_name);
-			continue;
-		}
-		sa = (0xffffffffu << ilog2(sa)) | 0x1;
-
-		/* Program register values */
-		switch (j) {
-		case 0:
-			out_le32(mbase + PECFG_POM0LAH, pciah);
-			out_le32(mbase + PECFG_POM0LAL, pcial);
-			dcr_write(port->dcrs, DCRO_PEGPL_OMR1BAH, lah);
-			dcr_write(port->dcrs, DCRO_PEGPL_OMR1BAL, lal);
-			dcr_write(port->dcrs, DCRO_PEGPL_OMR1MSKH, 0x7fffffff);
-			dcr_write(port->dcrs, DCRO_PEGPL_OMR1MSKL, sa | 3);
-			break;
-		case 1:
-			out_le32(mbase + PECFG_POM1LAH, pciah);
-			out_le32(mbase + PECFG_POM1LAL, pcial);
-			dcr_write(port->dcrs, DCRO_PEGPL_OMR2BAH, lah);
-			dcr_write(port->dcrs, DCRO_PEGPL_OMR2BAL, lal);
-			dcr_write(port->dcrs, DCRO_PEGPL_OMR2MSKH, 0x7fffffff);
-			dcr_write(port->dcrs, DCRO_PEGPL_OMR2MSKL, sa | 3);
-			break;
+		/* Configure the resource */
+		if (ppc4xx_setup_one_pciex_POM(port, hose, mbase,
+					       res->start,
+					       res->start - hose->pci_mem_offset,
+					       res->end + 1 - res->start,
+					       res->flags,
+					       j) == 0) {
+			j++;
+
+			/* If the resource PCI address is 0 then we have our
+			 * ISA memory hole
+			 */
+			if (res->start == hose->pci_mem_offset)
+				found_isa_hole = 1;
 		}
-		j++;
 	}
 
-	/* Configure IO, always 64K starting at 0 */
-	if (hose->io_resource.flags & IORESOURCE_IO) {
-		lah = RES_TO_U32_HIGH(hose->io_base_phys);
-		lal = RES_TO_U32_LOW(hose->io_base_phys);
-		out_le32(mbase + PECFG_POM2LAH, 0);
-		out_le32(mbase + PECFG_POM2LAL, 0);
-		dcr_write(port->dcrs, DCRO_PEGPL_OMR3BAH, lah);
-		dcr_write(port->dcrs, DCRO_PEGPL_OMR3BAL, lal);
-		dcr_write(port->dcrs, DCRO_PEGPL_OMR3MSKH, 0x7fffffff);
-		dcr_write(port->dcrs, DCRO_PEGPL_OMR3MSKL, 0xffff0000 | 3);
-	}
+	/* Handle ISA memory hole if not already covered */
+	if (j <= 1 && !found_isa_hole && hose->isa_mem_size)
+		if (ppc4xx_setup_one_pciex_POM(port, hose, mbase,
+					       hose->isa_mem_phys, 0,
+					       hose->isa_mem_size, 0, j) == 0)
+			printk(KERN_INFO "%s: Legacy ISA memory support enabled\n",
+			       hose->dn->full_name);
+
+	/* Configure IO, always 64K starting at 0. We hard wire it to 64K !
+	 * Note also that it -has- to be region index 2 on this HW
+	 */
+	if (hose->io_resource.flags & IORESOURCE_IO)
+		ppc4xx_setup_one_pciex_POM(port, hose, mbase,
+					   hose->io_base_phys, 0,
+					   0x10000, IORESOURCE_IO, 2);
 }
 
 static void __init ppc4xx_configure_pciex_PIMs(struct ppc4xx_pciex_port *port,
diff --git a/arch/powerpc/sysdev/qe_lib/qe.c b/arch/powerpc/sysdev/qe_lib/qe.c
index b3b73ae57d6d..01bce3784b0a 100644
--- a/arch/powerpc/sysdev/qe_lib/qe.c
+++ b/arch/powerpc/sysdev/qe_lib/qe.c
@@ -19,6 +19,7 @@
 #include <linux/kernel.h>
 #include <linux/param.h>
 #include <linux/string.h>
+#include <linux/spinlock.h>
 #include <linux/mm.h>
 #include <linux/interrupt.h>
 #include <linux/bootmem.h>
@@ -38,6 +39,8 @@ static void qe_snums_init(void);
 static int qe_sdma_init(void);
 
 static DEFINE_SPINLOCK(qe_lock);
+DEFINE_SPINLOCK(cmxgcr_lock);
+EXPORT_SYMBOL(cmxgcr_lock);
 
 /* QE snum state */
 enum qe_snum_state {
diff --git a/arch/powerpc/sysdev/qe_lib/ucc.c b/arch/powerpc/sysdev/qe_lib/ucc.c
index 1d78071aad7d..ebb442ea1917 100644
--- a/arch/powerpc/sysdev/qe_lib/ucc.c
+++ b/arch/powerpc/sysdev/qe_lib/ucc.c
@@ -18,6 +18,7 @@
 #include <linux/errno.h>
 #include <linux/slab.h>
 #include <linux/stddef.h>
+#include <linux/spinlock.h>
 #include <linux/module.h>
 
 #include <asm/irq.h>
@@ -26,9 +27,6 @@
 #include <asm/qe.h>
 #include <asm/ucc.h>
 
-DEFINE_SPINLOCK(cmxgcr_lock);
-EXPORT_SYMBOL(cmxgcr_lock);
-
 int ucc_set_qe_mux_mii_mng(unsigned int ucc_num)
 {
 	unsigned long flags;
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index 8116a3328a19..7a18d2380e2c 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -43,6 +43,9 @@ config GENERIC_HWEIGHT
 config GENERIC_TIME
 	def_bool y
 
+config GENERIC_TIME_VSYSCALL
+	def_bool y
+
 config GENERIC_CLOCKEVENTS
 	def_bool y
 
@@ -70,6 +73,8 @@ mainmenu "Linux Kernel Configuration"
 
 config S390
 	def_bool y
+	select USE_GENERIC_SMP_HELPERS if SMP
+	select HAVE_FUNCTION_TRACER
 	select HAVE_OPROFILE
 	select HAVE_KPROBES
 	select HAVE_KRETPROBES
@@ -225,6 +230,14 @@ config MARCH_Z9_109
 	  Class (z9 BC). The kernel will be slightly faster but will not
 	  work on older machines such as the z990, z890, z900, and z800.
 
+config MARCH_Z10
+	bool "IBM System z10"
+	help
+	  Select this to enable optimizations for IBM System z10. The
+	  kernel will be slightly faster but will not work on older
+	  machines such as the z990, z890, z900, z800, z9-109, z9-ec
+	  and z9-bc.
+
 endchoice
 
 config PACK_STACK
@@ -343,16 +356,6 @@ config QDIO
 
 	  If unsure, say Y.
 
-config QDIO_DEBUG
-	bool "Extended debugging information"
-	depends on QDIO
-	help
-	  Say Y here to get extended debugging output in
-	    /sys/kernel/debug/s390dbf/qdio...
-	  Warning: this option reduces the performance of the QDIO module.
-
-	  If unsure, say N.
-
 config CHSC_SCH
 	tristate "Support for CHSC subchannels"
 	help
diff --git a/arch/s390/Makefile b/arch/s390/Makefile
index 792a4e7743ce..578c61f15a4b 100644
--- a/arch/s390/Makefile
+++ b/arch/s390/Makefile
@@ -34,6 +34,7 @@ cflags-$(CONFIG_MARCH_G5)   += $(call cc-option,-march=g5)
 cflags-$(CONFIG_MARCH_Z900) += $(call cc-option,-march=z900)
 cflags-$(CONFIG_MARCH_Z990) += $(call cc-option,-march=z990)
 cflags-$(CONFIG_MARCH_Z9_109) += $(call cc-option,-march=z9-109)
+cflags-$(CONFIG_MARCH_Z10) += $(call cc-option,-march=z10)
 
 #KBUILD_IMAGE is necessary for make rpm
 KBUILD_IMAGE	:=arch/s390/boot/image
diff --git a/arch/s390/appldata/appldata.h b/arch/s390/appldata/appldata.h
index 17a2636fec0a..f0b23fc759ba 100644
--- a/arch/s390/appldata/appldata.h
+++ b/arch/s390/appldata/appldata.h
@@ -26,10 +26,6 @@
 #define CTL_APPLDATA_NET_SUM	2125
 #define CTL_APPLDATA_PROC	2126
 
-#define P_INFO(x...)	printk(KERN_INFO MY_PRINT_NAME " info: " x)
-#define P_ERROR(x...)	printk(KERN_ERR MY_PRINT_NAME " error: " x)
-#define P_WARNING(x...)	printk(KERN_WARNING MY_PRINT_NAME " status: " x)
-
 struct appldata_ops {
 	struct list_head list;
 	struct ctl_table_header *sysctl_header;
diff --git a/arch/s390/appldata/appldata_base.c b/arch/s390/appldata/appldata_base.c
index a06a47cdd5e0..27b70d8a359c 100644
--- a/arch/s390/appldata/appldata_base.c
+++ b/arch/s390/appldata/appldata_base.c
@@ -10,6 +10,9 @@
  * Author: Gerald Schaefer <gerald.schaefer@de.ibm.com>
  */
 
+#define KMSG_COMPONENT	"appldata"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
 #include <linux/module.h>
 #include <linux/init.h>
 #include <linux/slab.h>
@@ -32,7 +35,6 @@
 #include "appldata.h"
 
 
-#define MY_PRINT_NAME	"appldata"		/* for debug messages, etc. */
 #define APPLDATA_CPU_INTERVAL	10000		/* default (CPU) time for
 						   sampling interval in
 						   milliseconds */
@@ -390,8 +392,8 @@ appldata_generic_handler(ctl_table *ctl, int write, struct file *filp,
 					(unsigned long) ops->data, ops->size,
 					ops->mod_lvl);
 		if (rc != 0) {
-			P_ERROR("START DIAG 0xDC for %s failed, "
-				"return code: %d\n", ops->name, rc);
+			pr_err("Starting the data collection for %s "
+			       "failed with rc=%d\n", ops->name, rc);
 			module_put(ops->owner);
 		} else
 			ops->active = 1;
@@ -401,8 +403,8 @@ appldata_generic_handler(ctl_table *ctl, int write, struct file *filp,
 				(unsigned long) ops->data, ops->size,
 				ops->mod_lvl);
 		if (rc != 0)
-			P_ERROR("STOP DIAG 0xDC for %s failed, "
-				"return code: %d\n", ops->name, rc);
+			pr_err("Stopping the data collection for %s "
+			       "failed with rc=%d\n", ops->name, rc);
 		module_put(ops->owner);
 	}
 	spin_unlock(&appldata_ops_lock);
diff --git a/arch/s390/appldata/appldata_os.c b/arch/s390/appldata/appldata_os.c
index eb44f9f8ab91..55c80ffd42b9 100644
--- a/arch/s390/appldata/appldata_os.c
+++ b/arch/s390/appldata/appldata_os.c
@@ -9,6 +9,9 @@
  * Author: Gerald Schaefer <gerald.schaefer@de.ibm.com>
  */
 
+#define KMSG_COMPONENT	"appldata"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
 #include <linux/module.h>
 #include <linux/init.h>
 #include <linux/slab.h>
@@ -22,7 +25,6 @@
 #include "appldata.h"
 
 
-#define MY_PRINT_NAME	"appldata_os"		/* for debug messages, etc. */
 #define LOAD_INT(x) ((x) >> FSHIFT)
 #define LOAD_FRAC(x) LOAD_INT(((x) & (FIXED_1-1)) * 100)
 
@@ -143,21 +145,16 @@ static void appldata_get_os_data(void *data)
 					   (unsigned long) ops.data, new_size,
 					   ops.mod_lvl);
 			if (rc != 0)
-				P_ERROR("os: START NEW DIAG 0xDC failed, "
-					"return code: %d, new size = %i\n", rc,
-					new_size);
+				pr_err("Starting a new OS data collection "
+				       "failed with rc=%d\n", rc);
 
 			rc = appldata_diag(APPLDATA_RECORD_OS_ID,
 					   APPLDATA_STOP_REC,
 					   (unsigned long) ops.data, ops.size,
 					   ops.mod_lvl);
 			if (rc != 0)
-				P_ERROR("os: STOP OLD DIAG 0xDC failed, "
-					"return code: %d, old size = %i\n", rc,
-					ops.size);
-			else
-				P_INFO("os: old record size = %i stopped\n",
-					ops.size);
+				pr_err("Stopping a faulty OS data "
+				       "collection failed with rc=%d\n", rc);
 		}
 		ops.size = new_size;
 	}
@@ -178,8 +175,8 @@ static int __init appldata_os_init(void)
 	max_size = sizeof(struct appldata_os_data) +
 		   (NR_CPUS * sizeof(struct appldata_os_per_cpu));
 	if (max_size > APPLDATA_MAX_REC_SIZE) {
-		P_ERROR("Max. size of OS record = %i, bigger than maximum "
-			"record size (%i)\n", max_size, APPLDATA_MAX_REC_SIZE);
+		pr_err("Maximum OS record size %i exceeds the maximum "
+		       "record size %i\n", max_size, APPLDATA_MAX_REC_SIZE);
 		rc = -ENOMEM;
 		goto out;
 	}
diff --git a/arch/s390/crypto/aes_s390.c b/arch/s390/crypto/aes_s390.c
index e33f32b54c08..c42cd898f68b 100644
--- a/arch/s390/crypto/aes_s390.c
+++ b/arch/s390/crypto/aes_s390.c
@@ -17,6 +17,9 @@
  *
  */
 
+#define KMSG_COMPONENT "aes_s390"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
 #include <crypto/aes.h>
 #include <crypto/algapi.h>
 #include <linux/err.h>
@@ -169,7 +172,8 @@ static int fallback_init_cip(struct crypto_tfm *tfm)
 			CRYPTO_ALG_ASYNC | CRYPTO_ALG_NEED_FALLBACK);
 
 	if (IS_ERR(sctx->fallback.cip)) {
-		printk(KERN_ERR "Error allocating fallback algo %s\n", name);
+		pr_err("Allocating AES fallback algorithm %s failed\n",
+		       name);
 		return PTR_ERR(sctx->fallback.blk);
 	}
 
@@ -349,7 +353,8 @@ static int fallback_init_blk(struct crypto_tfm *tfm)
 			CRYPTO_ALG_ASYNC | CRYPTO_ALG_NEED_FALLBACK);
 
 	if (IS_ERR(sctx->fallback.blk)) {
-		printk(KERN_ERR "Error allocating fallback algo %s\n", name);
+		pr_err("Allocating AES fallback algorithm %s failed\n",
+		       name);
 		return PTR_ERR(sctx->fallback.blk);
 	}
 
@@ -515,9 +520,8 @@ static int __init aes_s390_init(void)
 
 	/* z9 109 and z9 BC/EC only support 128 bit key length */
 	if (keylen_flag == AES_KEYLEN_128)
-		printk(KERN_INFO
-		       "aes_s390: hardware acceleration only available for "
-		       "128 bit keys\n");
+		pr_info("AES hardware acceleration is only available for"
+			" 128-bit keys\n");
 
 	ret = crypto_register_alg(&aes_alg);
 	if (ret)
diff --git a/arch/s390/hypfs/hypfs_diag.c b/arch/s390/hypfs/hypfs_diag.c
index b9a1ce1f28e4..b1e892a43816 100644
--- a/arch/s390/hypfs/hypfs_diag.c
+++ b/arch/s390/hypfs/hypfs_diag.c
@@ -3,10 +3,13 @@
  *    Hypervisor filesystem for Linux on s390. Diag 204 and 224
  *    implementation.
  *
- *    Copyright (C) IBM Corp. 2006
+ *    Copyright IBM Corp. 2006, 2008
  *    Author(s): Michael Holzheu <holzheu@de.ibm.com>
  */
 
+#define KMSG_COMPONENT "hypfs"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
 #include <linux/types.h>
 #include <linux/errno.h>
 #include <linux/string.h>
@@ -527,13 +530,14 @@ __init int hypfs_diag_init(void)
 	int rc;
 
 	if (diag204_probe()) {
-		printk(KERN_ERR "hypfs: diag 204 not working.");
+		pr_err("The hardware system does not support hypfs\n");
 		return -ENODATA;
 	}
 	rc = diag224_get_name_table();
 	if (rc) {
 		diag204_free_buffer();
-		printk(KERN_ERR "hypfs: could not get name table.\n");
+		pr_err("The hardware system does not provide all "
+		       "functions required by hypfs\n");
 	}
 	return rc;
 }
diff --git a/arch/s390/hypfs/inode.c b/arch/s390/hypfs/inode.c
index 36313801cd5c..65e93c7ce784 100644
--- a/arch/s390/hypfs/inode.c
+++ b/arch/s390/hypfs/inode.c
@@ -2,10 +2,13 @@
  *  arch/s390/hypfs/inode.c
  *    Hypervisor filesystem for Linux on s390.
  *
- *    Copyright (C) IBM Corp. 2006
+ *    Copyright IBM Corp. 2006, 2008
  *    Author(s): Michael Holzheu <holzheu@de.ibm.com>
  */
 
+#define KMSG_COMPONENT "hypfs"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
 #include <linux/types.h>
 #include <linux/errno.h>
 #include <linux/fs.h>
@@ -200,7 +203,7 @@ static ssize_t hypfs_aio_write(struct kiocb *iocb, const struct iovec *iov,
 	else
 		rc = hypfs_diag_create_files(sb, sb->s_root);
 	if (rc) {
-		printk(KERN_ERR "hypfs: Update failed\n");
+		pr_err("Updating the hypfs tree failed\n");
 		hypfs_delete_tree(sb->s_root);
 		goto out;
 	}
@@ -252,8 +255,7 @@ static int hypfs_parse_options(char *options, struct super_block *sb)
 			break;
 		case opt_err:
 		default:
-			printk(KERN_ERR "hypfs: Unrecognized mount option "
-			       "\"%s\" or missing value\n", str);
+			pr_err("%s is not a valid mount option\n", str);
 			return -EINVAL;
 		}
 	}
@@ -317,7 +319,7 @@ static int hypfs_fill_super(struct super_block *sb, void *data, int silent)
 	}
 	hypfs_update_update(sb);
 	sb->s_root = root_dentry;
-	printk(KERN_INFO "hypfs: Hypervisor filesystem mounted\n");
+	pr_info("Hypervisor filesystem mounted\n");
 	return 0;
 
 err_tree:
@@ -513,7 +515,7 @@ fail_sysfs:
 	if (!MACHINE_IS_VM)
 		hypfs_diag_exit();
 fail_diag:
-	printk(KERN_ERR "hypfs: Initialization failed with rc = %i.\n", rc);
+	pr_err("Initialization of hypfs failed with rc=%i\n", rc);
 	return rc;
 }
 
diff --git a/arch/s390/include/asm/auxvec.h b/arch/s390/include/asm/auxvec.h
index 0d340720fd99..a1f153e89133 100644
--- a/arch/s390/include/asm/auxvec.h
+++ b/arch/s390/include/asm/auxvec.h
@@ -1,4 +1,6 @@
 #ifndef __ASMS390_AUXVEC_H
 #define __ASMS390_AUXVEC_H
 
+#define AT_SYSINFO_EHDR		33
+
 #endif
diff --git a/arch/s390/include/asm/bug.h b/arch/s390/include/asm/bug.h
index 384e3621e341..7efd0abe8887 100644
--- a/arch/s390/include/asm/bug.h
+++ b/arch/s390/include/asm/bug.h
@@ -47,7 +47,10 @@
 
 #endif /* CONFIG_DEBUG_BUGVERBOSE */
 
-#define BUG()	__EMIT_BUG(0)
+#define BUG() do {					\
+	__EMIT_BUG(0);					\
+	for (;;);					\
+} while (0)
 
 #define WARN_ON(x) ({					\
 	int __ret_warn_on = !!(x);			\
diff --git a/arch/s390/include/asm/byteorder.h b/arch/s390/include/asm/byteorder.h
index 1fe2492baa8d..8bcf277c8468 100644
--- a/arch/s390/include/asm/byteorder.h
+++ b/arch/s390/include/asm/byteorder.h
@@ -11,32 +11,39 @@
 
 #include <asm/types.h>
 
-#ifdef __GNUC__
+#define __BIG_ENDIAN
+
+#ifndef __s390x__
+# define __SWAB_64_THRU_32__
+#endif
 
 #ifdef __s390x__
-static inline __u64 ___arch__swab64p(const __u64 *x)
+static inline __u64 __arch_swab64p(const __u64 *x)
 {
 	__u64 result;
 
 	asm volatile("lrvg %0,%1" : "=d" (result) : "m" (*x));
 	return result;
 }
+#define __arch_swab64p __arch_swab64p
 
-static inline __u64 ___arch__swab64(__u64 x)
+static inline __u64 __arch_swab64(__u64 x)
 {
 	__u64 result;
 
 	asm volatile("lrvgr %0,%1" : "=d" (result) : "d" (x));
 	return result;
 }
+#define __arch_swab64 __arch_swab64
 
-static inline void ___arch__swab64s(__u64 *x)
+static inline void __arch_swab64s(__u64 *x)
 {
-	*x = ___arch__swab64p(x);
+	*x = __arch_swab64p(x);
 }
+#define __arch_swab64s __arch_swab64s
 #endif /* __s390x__ */
 
-static inline __u32 ___arch__swab32p(const __u32 *x)
+static inline __u32 __arch_swab32p(const __u32 *x)
 {
 	__u32 result;
 	
@@ -53,25 +60,20 @@ static inline __u32 ___arch__swab32p(const __u32 *x)
 #endif /* __s390x__ */
 	return result;
 }
+#define __arch_swab32p __arch_swab32p
 
-static inline __u32 ___arch__swab32(__u32 x)
+#ifdef __s390x__
+static inline __u32 __arch_swab32(__u32 x)
 {
-#ifndef __s390x__
-	return ___arch__swab32p(&x);
-#else /* __s390x__ */
 	__u32 result;
 	
 	asm volatile("lrvr  %0,%1" : "=d" (result) : "d" (x));
 	return result;
-#endif /* __s390x__ */
-}
-
-static __inline__ void ___arch__swab32s(__u32 *x)
-{
-	*x = ___arch__swab32p(x);
 }
+#define __arch_swab32 __arch_swab32
+#endif /* __s390x__ */
 
-static __inline__ __u16 ___arch__swab16p(const __u16 *x)
+static inline __u16 __arch_swab16p(const __u16 *x)
 {
 	__u16 result;
 	
@@ -86,40 +88,8 @@ static __inline__ __u16 ___arch__swab16p(const __u16 *x)
 #endif /* __s390x__ */
 	return result;
 }
+#define __arch_swab16p __arch_swab16p
 
-static __inline__ __u16 ___arch__swab16(__u16 x)
-{
-	return ___arch__swab16p(&x);
-}
-
-static __inline__ void ___arch__swab16s(__u16 *x)
-{
-	*x = ___arch__swab16p(x);
-}
-
-#ifdef __s390x__
-#define __arch__swab64(x) ___arch__swab64(x)
-#define __arch__swab64p(x) ___arch__swab64p(x)
-#define __arch__swab64s(x) ___arch__swab64s(x)
-#endif /* __s390x__ */
-#define __arch__swab32(x) ___arch__swab32(x)
-#define __arch__swab16(x) ___arch__swab16(x)
-#define __arch__swab32p(x) ___arch__swab32p(x)
-#define __arch__swab16p(x) ___arch__swab16p(x)
-#define __arch__swab32s(x) ___arch__swab32s(x)
-#define __arch__swab16s(x) ___arch__swab16s(x)
-
-#ifndef __s390x__
-#if !defined(__STRICT_ANSI__) || defined(__KERNEL__)
-#  define __BYTEORDER_HAS_U64__
-#  define __SWAB_64_THRU_32__
-#endif
-#else /* __s390x__ */
-#define __BYTEORDER_HAS_U64__
-#endif /* __s390x__ */
-
-#endif /* __GNUC__ */
-
-#include <linux/byteorder/big_endian.h>
+#include <linux/byteorder.h>
 
 #endif /* _S390_BYTEORDER_H */
diff --git a/arch/s390/include/asm/elf.h b/arch/s390/include/asm/elf.h
index 261785ab5b22..d480f39d65e6 100644
--- a/arch/s390/include/asm/elf.h
+++ b/arch/s390/include/asm/elf.h
@@ -120,6 +120,10 @@ typedef s390_compat_regs compat_elf_gregset_t;
 #include <asm/system.h>		/* for save_access_regs */
 #include <asm/mmu_context.h>
 
+#include <asm/vdso.h>
+
+extern unsigned int vdso_enabled;
+
 /*
  * This is used to ensure we don't load something for the wrong architecture.
  */
@@ -191,4 +195,16 @@ do {							\
 	current->mm->context.noexec == 0;		\
 })
 
+#define ARCH_DLINFO							    \
+do {									    \
+	if (vdso_enabled)						    \
+		NEW_AUX_ENT(AT_SYSINFO_EHDR,				    \
+			    (unsigned long)current->mm->context.vdso_base); \
+} while (0)
+
+struct linux_binprm;
+
+#define ARCH_HAS_SETUP_ADDITIONAL_PAGES 1
+int arch_setup_additional_pages(struct linux_binprm *, int);
+
 #endif
diff --git a/arch/s390/include/asm/fcx.h b/arch/s390/include/asm/fcx.h
index 8be1f3a58042..ef6170995076 100644
--- a/arch/s390/include/asm/fcx.h
+++ b/arch/s390/include/asm/fcx.h
@@ -248,8 +248,8 @@ struct dcw {
 #define TCCB_MAX_SIZE		(sizeof(struct tccb_tcah) + \
 				 TCCB_MAX_DCW * sizeof(struct dcw) + \
 				 sizeof(struct tccb_tcat))
-#define TCCB_SAC_DEFAULT	0xf901
-#define TCCB_SAC_INTRG		0xf902
+#define TCCB_SAC_DEFAULT	0x1ffe
+#define TCCB_SAC_INTRG		0x1fff
 
 /**
  * struct tccb_tcah - Transport-Command-Area Header (TCAH)
diff --git a/arch/s390/include/asm/ftrace.h b/arch/s390/include/asm/ftrace.h
new file mode 100644
index 000000000000..5a5bc75e19d4
--- /dev/null
+++ b/arch/s390/include/asm/ftrace.h
@@ -0,0 +1,8 @@
+#ifndef _ASM_S390_FTRACE_H
+#define _ASM_S390_FTRACE_H
+
+#ifndef __ASSEMBLY__
+extern void _mcount(void);
+#endif
+
+#endif /* _ASM_S390_FTRACE_H */
diff --git a/arch/s390/include/asm/isc.h b/arch/s390/include/asm/isc.h
index 34bb8916db4f..1420a1115948 100644
--- a/arch/s390/include/asm/isc.h
+++ b/arch/s390/include/asm/isc.h
@@ -17,6 +17,7 @@
 #define CHSC_SCH_ISC 7			/* CHSC subchannels */
 /* Adapter interrupts. */
 #define QDIO_AIRQ_ISC IO_SCH_ISC	/* I/O subchannel in qdio mode */
+#define AP_ISC 6			/* adjunct processor (crypto) devices */
 
 /* Functions for registration of I/O interruption subclasses */
 void isc_register(unsigned int isc);
diff --git a/arch/s390/include/asm/mmu.h b/arch/s390/include/asm/mmu.h
index d2b4ff831477..3b59216e6284 100644
--- a/arch/s390/include/asm/mmu.h
+++ b/arch/s390/include/asm/mmu.h
@@ -6,6 +6,7 @@ typedef struct {
 	struct list_head pgtable_list;
 	unsigned long asce_bits;
 	unsigned long asce_limit;
+	unsigned long vdso_base;
 	int noexec;
 	int has_pgste;	 /* The mmu context has extended page tables */
 	int alloc_pgste; /* cloned contexts will have extended page tables */
diff --git a/arch/s390/include/asm/page.h b/arch/s390/include/asm/page.h
index 991ba939408c..32e8f6aa4384 100644
--- a/arch/s390/include/asm/page.h
+++ b/arch/s390/include/asm/page.h
@@ -152,4 +152,6 @@ void arch_alloc_page(struct page *page, int order);
 #include <asm-generic/memory_model.h>
 #include <asm-generic/page.h>
 
+#define __HAVE_ARCH_GATE_AREA 1
+
 #endif /* _S390_PAGE_H */
diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h
index 4af80af2a88f..066b99502e09 100644
--- a/arch/s390/include/asm/processor.h
+++ b/arch/s390/include/asm/processor.h
@@ -13,6 +13,7 @@
 #ifndef __ASM_S390_PROCESSOR_H
 #define __ASM_S390_PROCESSOR_H
 
+#include <linux/linkage.h>
 #include <asm/ptrace.h>
 
 #ifdef __KERNEL__
@@ -258,7 +259,7 @@ static inline void enabled_wait(void)
  * Function to drop a processor into disabled wait state
  */
 
-static inline void disabled_wait(unsigned long code)
+static inline void ATTRIB_NORET disabled_wait(unsigned long code)
 {
         unsigned long ctl_buf;
         psw_t dw_psw;
@@ -322,6 +323,7 @@ static inline void disabled_wait(unsigned long code)
 		: "=m" (ctl_buf)
 		: "a" (&dw_psw), "a" (&ctl_buf), "m" (dw_psw) : "cc", "0");
 #endif /* __s390x__ */
+	while (1);
 }
 
 /*
diff --git a/arch/s390/include/asm/qdio.h b/arch/s390/include/asm/qdio.h
index 4734c3f05354..27fc1746de15 100644
--- a/arch/s390/include/asm/qdio.h
+++ b/arch/s390/include/asm/qdio.h
@@ -373,16 +373,16 @@ struct qdio_initialize {
 #define QDIO_FLAG_SYNC_OUTPUT		0x02
 #define QDIO_FLAG_PCI_OUT		0x10
 
-extern int qdio_initialize(struct qdio_initialize *init_data);
-extern int qdio_allocate(struct qdio_initialize *init_data);
-extern int qdio_establish(struct qdio_initialize *init_data);
+extern int qdio_initialize(struct qdio_initialize *);
+extern int qdio_allocate(struct qdio_initialize *);
+extern int qdio_establish(struct qdio_initialize *);
 extern int qdio_activate(struct ccw_device *);
 
-extern int do_QDIO(struct ccw_device*, unsigned int flags,
-		   int q_nr, int qidx, int count);
-extern int qdio_cleanup(struct ccw_device*, int how);
-extern int qdio_shutdown(struct ccw_device*, int how);
+extern int do_QDIO(struct ccw_device *cdev, unsigned int callflags,
+		   int q_nr, int bufnr, int count);
+extern int qdio_cleanup(struct ccw_device*, int);
+extern int qdio_shutdown(struct ccw_device*, int);
 extern int qdio_free(struct ccw_device *);
-extern struct qdio_ssqd_desc *qdio_get_ssqd_desc(struct ccw_device *cdev);
+extern int qdio_get_ssqd_desc(struct ccw_device *dev, struct qdio_ssqd_desc*);
 
 #endif /* __QDIO_H__ */
diff --git a/arch/s390/include/asm/sigp.h b/arch/s390/include/asm/sigp.h
index e16d56f8dfe1..ec403d4304f8 100644
--- a/arch/s390/include/asm/sigp.h
+++ b/arch/s390/include/asm/sigp.h
@@ -61,6 +61,7 @@ typedef enum
 {
 	ec_schedule=0,
 	ec_call_function,
+	ec_call_function_single,
 	ec_bit_last
 } ec_bit_sig;
 
diff --git a/arch/s390/include/asm/smp.h b/arch/s390/include/asm/smp.h
index ae89cf2478fc..024b91e06239 100644
--- a/arch/s390/include/asm/smp.h
+++ b/arch/s390/include/asm/smp.h
@@ -91,8 +91,9 @@ extern int __cpu_up (unsigned int cpu);
 extern struct mutex smp_cpu_state_mutex;
 extern int smp_cpu_polarization[];
 
-extern int smp_call_function_mask(cpumask_t mask, void (*func)(void *),
-	void *info, int wait);
+extern void arch_send_call_function_single_ipi(int cpu);
+extern void arch_send_call_function_ipi(cpumask_t mask);
+
 #endif
 
 #ifndef CONFIG_SMP
diff --git a/arch/s390/include/asm/sysinfo.h b/arch/s390/include/asm/sysinfo.h
index 79d01343f8b0..ad93212d9e16 100644
--- a/arch/s390/include/asm/sysinfo.h
+++ b/arch/s390/include/asm/sysinfo.h
@@ -118,4 +118,15 @@ static inline int stsi(void *sysinfo, int fc, int sel1, int sel2)
 	return r0;
 }
 
+/*
+ * Service level reporting interface.
+ */
+struct service_level {
+	struct list_head list;
+	void (*seq_print)(struct seq_file *, struct service_level *);
+};
+
+int register_service_level(struct service_level *);
+int unregister_service_level(struct service_level *);
+
 #endif /* __ASM_S390_SYSINFO_H */
diff --git a/arch/s390/include/asm/system.h b/arch/s390/include/asm/system.h
index 819e7d99ca0c..c17a3cfbe242 100644
--- a/arch/s390/include/asm/system.h
+++ b/arch/s390/include/asm/system.h
@@ -12,6 +12,7 @@
 #define __ASM_SYSTEM_H
 
 #include <linux/kernel.h>
+#include <linux/errno.h>
 #include <asm/types.h>
 #include <asm/ptrace.h>
 #include <asm/setup.h>
@@ -413,8 +414,6 @@ __set_psw_mask(unsigned long mask)
 #define local_mcck_enable()  __set_psw_mask(psw_kernel_bits)
 #define local_mcck_disable() __set_psw_mask(psw_kernel_bits & ~PSW_MASK_MCHECK)
 
-int stfle(unsigned long long *list, int doublewords);
-
 #ifdef CONFIG_SMP
 
 extern void smp_ctl_set_bit(int cr, int bit);
@@ -438,6 +437,23 @@ static inline unsigned int stfl(void)
 	return S390_lowcore.stfl_fac_list;
 }
 
+static inline int __stfle(unsigned long long *list, int doublewords)
+{
+	typedef struct { unsigned long long _[doublewords]; } addrtype;
+	register unsigned long __nr asm("0") = doublewords - 1;
+
+	asm volatile(".insn s,0xb2b00000,%0" /* stfle */
+		     : "=m" (*(addrtype *) list), "+d" (__nr) : : "cc");
+	return __nr + 1;
+}
+
+static inline int stfle(unsigned long long *list, int doublewords)
+{
+	if (!(stfl() & (1UL << 24)))
+		return -EOPNOTSUPP;
+	return __stfle(list, doublewords);
+}
+
 static inline unsigned short stap(void)
 {
 	unsigned short cpu_address;
diff --git a/arch/s390/include/asm/vdso.h b/arch/s390/include/asm/vdso.h
new file mode 100644
index 000000000000..a44f4fe16a35
--- /dev/null
+++ b/arch/s390/include/asm/vdso.h
@@ -0,0 +1,39 @@
+#ifndef __S390_VDSO_H__
+#define __S390_VDSO_H__
+
+#ifdef __KERNEL__
+
+/* Default link addresses for the vDSOs */
+#define VDSO32_LBASE	0
+#define VDSO64_LBASE	0
+
+#define VDSO_VERSION_STRING	LINUX_2.6.26
+
+#ifndef __ASSEMBLY__
+
+/*
+ * Note about this structure:
+ *
+ * NEVER USE THIS IN USERSPACE CODE DIRECTLY. The layout of this
+ * structure is supposed to be known only to the function in the vdso
+ * itself and may change without notice.
+ */
+
+struct vdso_data {
+	__u64 tb_update_count;		/* Timebase atomicity ctr	0x00 */
+	__u64 xtime_tod_stamp;		/* TOD clock for xtime		0x08 */
+	__u64 xtime_clock_sec;		/* Kernel time			0x10 */
+	__u64 xtime_clock_nsec;		/*				0x18 */
+	__u64 wtom_clock_sec;		/* Wall to monotonic clock	0x20 */
+	__u64 wtom_clock_nsec;		/*				0x28 */
+	__u32 tz_minuteswest;		/* Minutes west of Greenwich	0x30 */
+	__u32 tz_dsttime;		/* Type of dst correction	0x34 */
+};
+
+extern struct vdso_data *vdso_data;
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* __KERNEL__ */
+
+#endif /* __S390_VDSO_H__ */
diff --git a/arch/s390/kernel/Makefile b/arch/s390/kernel/Makefile
index 50f657e77344..00c888408864 100644
--- a/arch/s390/kernel/Makefile
+++ b/arch/s390/kernel/Makefile
@@ -2,6 +2,11 @@
 # Makefile for the linux kernel.
 #
 
+ifdef CONFIG_FUNCTION_TRACER
+# Do not trace early boot code
+CFLAGS_REMOVE_early.o = -pg
+endif
+
 #
 # Passing null pointers is ok for smp code, since we access the lowcore here.
 #
@@ -12,9 +17,10 @@ CFLAGS_smp.o	:= -Wno-nonnull
 #
 CFLAGS_ptrace.o		+= -DUTS_MACHINE='"$(UTS_MACHINE)"'
 
-obj-y	:=  bitmap.o traps.o time.o process.o base.o early.o \
-            setup.o sys_s390.o ptrace.o signal.o cpcmd.o ebcdic.o \
-	    s390_ext.o debug.o irq.o ipl.o dis.o diag.o mem_detect.o
+obj-y	:=  bitmap.o traps.o time.o process.o base.o early.o setup.o \
+	    processor.o sys_s390.o ptrace.o signal.o cpcmd.o ebcdic.o \
+	    s390_ext.o debug.o irq.o ipl.o dis.o diag.o mem_detect.o \
+	    vdso.o
 
 obj-y	+= $(if $(CONFIG_64BIT),entry64.o,entry.o)
 obj-y	+= $(if $(CONFIG_64BIT),reipl64.o,reipl.o)
@@ -33,9 +39,14 @@ obj-$(CONFIG_COMPAT)		+= compat_linux.o compat_signal.o \
 obj-$(CONFIG_VIRT_TIMER)	+= vtime.o
 obj-$(CONFIG_STACKTRACE)	+= stacktrace.o
 obj-$(CONFIG_KPROBES)		+= kprobes.o
+obj-$(CONFIG_FUNCTION_TRACER)	+= mcount.o
 
 # Kexec part
 S390_KEXEC_OBJS := machine_kexec.o crash.o
 S390_KEXEC_OBJS += $(if $(CONFIG_64BIT),relocate_kernel64.o,relocate_kernel.o)
 obj-$(CONFIG_KEXEC) += $(S390_KEXEC_OBJS)
 
+# vdso
+obj-$(CONFIG_64BIT)		+= vdso64/
+obj-$(CONFIG_32BIT)		+= vdso32/
+obj-$(CONFIG_COMPAT)		+= vdso32/
diff --git a/arch/s390/kernel/asm-offsets.c b/arch/s390/kernel/asm-offsets.c
index 3d144e6020c6..e641f60bac99 100644
--- a/arch/s390/kernel/asm-offsets.c
+++ b/arch/s390/kernel/asm-offsets.c
@@ -6,6 +6,7 @@
 
 #include <linux/sched.h>
 #include <linux/kbuild.h>
+#include <asm/vdso.h>
 
 int main(void)
 {
@@ -38,5 +39,19 @@ int main(void)
 	DEFINE(__SF_BACKCHAIN, offsetof(struct stack_frame, back_chain));
 	DEFINE(__SF_GPRS, offsetof(struct stack_frame, gprs));
 	DEFINE(__SF_EMPTY, offsetof(struct stack_frame, empty1));
+	BLANK();
+	/* timeval/timezone offsets for use by vdso */
+	DEFINE(__VDSO_UPD_COUNT, offsetof(struct vdso_data, tb_update_count));
+	DEFINE(__VDSO_XTIME_STAMP, offsetof(struct vdso_data, xtime_tod_stamp));
+	DEFINE(__VDSO_XTIME_SEC, offsetof(struct vdso_data, xtime_clock_sec));
+	DEFINE(__VDSO_XTIME_NSEC, offsetof(struct vdso_data, xtime_clock_nsec));
+	DEFINE(__VDSO_WTOM_SEC, offsetof(struct vdso_data, wtom_clock_sec));
+	DEFINE(__VDSO_WTOM_NSEC, offsetof(struct vdso_data, wtom_clock_nsec));
+	DEFINE(__VDSO_TIMEZONE, offsetof(struct vdso_data, tz_minuteswest));
+	/* constants used by the vdso */
+	DEFINE(CLOCK_REALTIME, CLOCK_REALTIME);
+	DEFINE(CLOCK_MONOTONIC, CLOCK_MONOTONIC);
+	DEFINE(CLOCK_REALTIME_RES, MONOTONIC_RES_NSEC);
+
 	return 0;
 }
diff --git a/arch/s390/kernel/cpcmd.c b/arch/s390/kernel/cpcmd.c
index d8c1131e0815..3e8b8816f309 100644
--- a/arch/s390/kernel/cpcmd.c
+++ b/arch/s390/kernel/cpcmd.c
@@ -7,6 +7,9 @@
  *               Christian Borntraeger (cborntra@de.ibm.com),
  */
 
+#define KMSG_COMPONENT "cpcmd"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/slab.h>
@@ -104,8 +107,8 @@ int cpcmd(const char *cmd, char *response, int rlen, int *response_code)
 			(((unsigned long)response + rlen) >> 31)) {
 		lowbuf = kmalloc(rlen, GFP_KERNEL | GFP_DMA);
 		if (!lowbuf) {
-			printk(KERN_WARNING
-				"cpcmd: could not allocate response buffer\n");
+			pr_warning("The cpcmd kernel function failed to "
+				   "allocate a response buffer\n");
 			return -ENOMEM;
 		}
 		spin_lock_irqsave(&cpcmd_lock, flags);
diff --git a/arch/s390/kernel/debug.c b/arch/s390/kernel/debug.c
index d80fcd4a7fe1..3665b18dedfa 100644
--- a/arch/s390/kernel/debug.c
+++ b/arch/s390/kernel/debug.c
@@ -10,6 +10,9 @@
  *    Bugreports to: <Linux390@de.ibm.com>
  */
 
+#define KMSG_COMPONENT "s390dbf"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
 #include <linux/stddef.h>
 #include <linux/kernel.h>
 #include <linux/errno.h>
@@ -693,8 +696,8 @@ debug_info_t *debug_register_mode(const char *name, int pages_per_area,
 	/* Since debugfs currently does not support uid/gid other than root, */
 	/* we do not allow gid/uid != 0 until we get support for that. */
 	if ((uid != 0) || (gid != 0))
-		printk(KERN_WARNING "debug: Warning - Currently only uid/gid "
-		       "= 0 are supported. Using root as owner now!");
+		pr_warning("Root becomes the owner of all s390dbf files "
+			   "in sysfs\n");
 	if (!initialized)
 		BUG();
 	mutex_lock(&debug_mutex);
@@ -709,7 +712,7 @@ debug_info_t *debug_register_mode(const char *name, int pages_per_area,
 	debug_register_view(rc, &debug_pages_view);
 out:
         if (!rc){
-		printk(KERN_ERR "debug: debug_register failed for %s\n",name);
+		pr_err("Registering debug feature %s failed\n", name);
         }
 	mutex_unlock(&debug_mutex);
 	return rc;
@@ -763,8 +766,8 @@ debug_set_size(debug_info_t* id, int nr_areas, int pages_per_area)
 	if(pages_per_area > 0){
 		new_areas = debug_areas_alloc(pages_per_area, nr_areas);
 		if(!new_areas) {
-			printk(KERN_WARNING "debug: could not allocate memory "\
-					 "for pagenumber: %i\n",pages_per_area);
+			pr_info("Allocating memory for %i pages failed\n",
+				pages_per_area);
 			rc = -ENOMEM;
 			goto out;
 		}
@@ -780,8 +783,7 @@ debug_set_size(debug_info_t* id, int nr_areas, int pages_per_area)
 	memset(id->active_entries,0,sizeof(int)*id->nr_areas);
 	memset(id->active_pages, 0, sizeof(int)*id->nr_areas);
 	spin_unlock_irqrestore(&id->lock,flags);
-	printk(KERN_INFO "debug: %s: set new size (%i pages)\n"\
-			 ,id->name, pages_per_area);
+	pr_info("%s: set new size (%i pages)\n" ,id->name, pages_per_area);
 out:
 	return rc;
 }
@@ -800,10 +802,9 @@ debug_set_level(debug_info_t* id, int new_level)
 	spin_lock_irqsave(&id->lock,flags);
         if(new_level == DEBUG_OFF_LEVEL){
                 id->level = DEBUG_OFF_LEVEL;
-                printk(KERN_INFO "debug: %s: switched off\n",id->name);
+		pr_info("%s: switched off\n",id->name);
         } else if ((new_level > DEBUG_MAX_LEVEL) || (new_level < 0)) {
-                printk(KERN_INFO
-                        "debug: %s: level %i is out of range (%i - %i)\n",
+		pr_info("%s: level %i is out of range (%i - %i)\n",
                         id->name, new_level, 0, DEBUG_MAX_LEVEL);
         } else {
                 id->level = new_level;
@@ -1108,8 +1109,8 @@ debug_register_view(debug_info_t * id, struct debug_view *view)
 	pde = debugfs_create_file(view->name, mode, id->debugfs_root_entry,
 				id , &debug_file_ops);
 	if (!pde){
-		printk(KERN_WARNING "debug: debugfs_create_file() failed!"\
-			" Cannot register view %s/%s\n", id->name,view->name);
+		pr_err("Registering view %s/%s failed due to out of "
+		       "memory\n", id->name,view->name);
 		rc = -1;
 		goto out;
 	}
@@ -1119,10 +1120,8 @@ debug_register_view(debug_info_t * id, struct debug_view *view)
 			break;
 	}
 	if (i == DEBUG_MAX_VIEWS) {
-		printk(KERN_WARNING "debug: cannot register view %s/%s\n",
-			id->name,view->name);
-		printk(KERN_WARNING 
-			"debug: maximum number of views reached (%i)!\n", i);
+		pr_err("Registering view %s/%s would exceed the maximum "
+		       "number of views %i\n", id->name, view->name, i);
 		debugfs_remove(pde);
 		rc = -1;
 	} else {
@@ -1303,7 +1302,8 @@ debug_input_level_fn(debug_info_t * id, struct debug_view *view,
 		new_level = debug_get_uint(str);
 	}
 	if(new_level < 0) {
-		printk(KERN_INFO "debug: level `%s` is not valid\n", str);
+		pr_warning("%s is not a valid level for a debug "
+			   "feature\n", str);
 		rc = -EINVAL;
 	} else {
 		debug_set_level(id, new_level);
@@ -1380,7 +1380,8 @@ debug_input_flush_fn(debug_info_t * id, struct debug_view *view,
                 goto out;
         }
 
-        printk(KERN_INFO "debug: area `%c` is not valid\n", input_buf[0]);
+	pr_info("Flushing debug data failed because %c is not a valid "
+		 "area\n", input_buf[0]);
 
 out:
         *offset += user_len;
diff --git a/arch/s390/kernel/head.S b/arch/s390/kernel/head.S
index 83477c7dc743..ec7e35f6055b 100644
--- a/arch/s390/kernel/head.S
+++ b/arch/s390/kernel/head.S
@@ -461,6 +461,55 @@ start:
 	.byte 0xf0,0xf1,0xf2,0xf3,0xf4,0xf5,0xf6,0xf7
 	.byte 0xf8,0xf9,0xfa,0xfb,0xfc,0xfd,0xfe,0xff
 
+#
+# startup-code at 0x10000, running in absolute addressing mode
+# this is called either by the ipl loader or directly by PSW restart
+# or linload or SALIPL
+#
+	.org	0x10000
+startup:basr	%r13,0			# get base
+.LPG0:
+
+#ifndef CONFIG_MARCH_G5
+	# check processor version against MARCH_{G5,Z900,Z990,Z9_109,Z10}
+	stidp	__LC_CPUID		# store cpuid
+	lhi	%r0,(3f-2f) / 2
+	la	%r1,2f-.LPG0(%r13)
+0:	clc	__LC_CPUID+4(2),0(%r1)
+	jne	3f
+	lpsw	1f-.LPG0(13)		# machine type not good enough, crash
+	.align 16
+1:	.long	0x000a0000,0x00000000
+2:
+#if defined(CONFIG_MARCH_Z10)
+	.short 0x9672, 0x2064, 0x2066, 0x2084, 0x2086, 0x2094, 0x2096
+#elif defined(CONFIG_MARCH_Z9_109)
+	.short 0x9672, 0x2064, 0x2066, 0x2084, 0x2086
+#elif defined(CONFIG_MARCH_Z990)
+	.short 0x9672, 0x2064, 0x2066
+#elif defined(CONFIG_MARCH_Z900)
+	.short 0x9672
+#endif
+3:	la	%r1,2(%r1)
+	brct	%r0,0b
+#endif
+
+	l	%r13,0f-.LPG0(%r13)
+	b	0(%r13)
+0:	.long	startup_continue
+
+#
+# params at 10400 (setup.h)
+#
+	.org	PARMAREA
+	.long	0,0			# IPL_DEVICE
+	.long	0,0			# INITRD_START
+	.long	0,0			# INITRD_SIZE
+
+	.org	COMMAND_LINE
+	.byte	"root=/dev/ram0 ro"
+	.byte	0
+
 #ifdef CONFIG_64BIT
 #include "head64.S"
 #else
diff --git a/arch/s390/kernel/head31.S b/arch/s390/kernel/head31.S
index a816e2de32b9..db476d114caa 100644
--- a/arch/s390/kernel/head31.S
+++ b/arch/s390/kernel/head31.S
@@ -10,34 +10,13 @@
  *
  */
 
-#
-# startup-code at 0x10000, running in absolute addressing mode
-# this is called either by the ipl loader or directly by PSW restart
-# or linload or SALIPL
-#
-	.org	0x10000
-startup:basr	%r13,0			# get base
-.LPG0:	l	%r13,0f-.LPG0(%r13)
-	b	0(%r13)
-0:	.long	startup_continue
-
-#
-# params at 10400 (setup.h)
-#
-	.org	PARMAREA
-	.long	0,0			# IPL_DEVICE
-	.long	0,0			# INITRD_START
-	.long	0,0			# INITRD_SIZE
-
-	.org	COMMAND_LINE
-	.byte	"root=/dev/ram0 ro"
-	.byte	0
-
 	.org	0x11000
 
 startup_continue:
 	basr	%r13,0			# get base
-.LPG1:	mvi	__LC_AR_MODE_ID,0	# set ESA flag (mode 0)
+.LPG1:
+
+	mvi	__LC_AR_MODE_ID,0	# set ESA flag (mode 0)
 	lctl	%c0,%c15,.Lctl-.LPG1(%r13) # load control registers
 	l	%r12,.Lparmaddr-.LPG1(%r13) # pointer to parameter area
 					# move IPL device to lowcore
@@ -50,7 +29,6 @@ startup_continue:
 	ahi	%r15,1<<(PAGE_SHIFT+THREAD_ORDER) # init_task_union+THREAD_SIZE
 	st	%r15,__LC_KERNEL_STACK	# set end of kernel stack
 	ahi	%r15,-96
-	xc	__SF_BACKCHAIN(4,%r15),__SF_BACKCHAIN(%r15) # clear backchain
 #
 # Save ipl parameters, clear bss memory, initialize storage key for kernel pages,
 # and create a kernel NSS if the SAVESYS= parm is defined
diff --git a/arch/s390/kernel/head64.S b/arch/s390/kernel/head64.S
index 1d06961e87b3..3ccd36b24b8f 100644
--- a/arch/s390/kernel/head64.S
+++ b/arch/s390/kernel/head64.S
@@ -10,29 +10,6 @@
  *
  */
 
-#
-# startup-code at 0x10000, running in absolute addressing mode
-# this is called either by the ipl loader or directly by PSW restart
-# or linload or SALIPL
-#
-	.org	0x10000
-startup:basr	%r13,0			# get base
-.LPG0:	l	%r13,0f-.LPG0(%r13)
-	b	0(%r13)
-0:	.long	startup_continue
-
-#
-# params at 10400 (setup.h)
-#
-	.org	PARMAREA
-	.quad	0			# IPL_DEVICE
-	.quad	0			# INITRD_START
-	.quad	0			# INITRD_SIZE
-
-	.org	COMMAND_LINE
-	.byte	"root=/dev/ram0 ro"
-	.byte	0
-
 	.org	0x11000
 
 startup_continue:
@@ -119,7 +96,6 @@ startup_continue:
 	aghi	%r15,1<<(PAGE_SHIFT+THREAD_ORDER) # init_task_union + THREAD_SIZE
 	stg	%r15,__LC_KERNEL_STACK	# set end of kernel stack
 	aghi	%r15,-160
-	xc	__SF_BACKCHAIN(4,%r15),__SF_BACKCHAIN(%r15) # clear backchain
 #
 # Save ipl parameters, clear bss memory, initialize storage key for kernel pages,
 # and create a kernel NSS if the SAVESYS= parm is defined
diff --git a/arch/s390/kernel/mcount.S b/arch/s390/kernel/mcount.S
new file mode 100644
index 000000000000..397d131a345f
--- /dev/null
+++ b/arch/s390/kernel/mcount.S
@@ -0,0 +1,56 @@
+/*
+ * Copyright IBM Corp. 2008
+ *
+ *   Author(s): Heiko Carstens <heiko.carstens@de.ibm.com>,
+ *
+ */
+
+#ifndef CONFIG_64BIT
+.globl _mcount
+_mcount:
+	stm	%r0,%r5,8(%r15)
+	st	%r14,56(%r15)
+	lr	%r1,%r15
+	ahi	%r15,-96
+	l	%r3,100(%r15)
+	la	%r2,0(%r14)
+	st	%r1,0(%r15)
+	la	%r3,0(%r3)
+	bras	%r14,0f
+	.long	ftrace_trace_function
+0:	l	%r14,0(%r14)
+	l	%r14,0(%r14)
+	basr	%r14,%r14
+	ahi	%r15,96
+	lm	%r0,%r5,8(%r15)
+	l	%r14,56(%r15)
+	br	%r14
+
+.globl ftrace_stub
+ftrace_stub:
+	br	%r14
+
+#else /* CONFIG_64BIT */
+
+.globl _mcount
+_mcount:
+	stmg	%r0,%r5,16(%r15)
+	stg	%r14,112(%r15)
+	lgr	%r1,%r15
+	aghi	%r15,-160
+	stg	%r1,0(%r15)
+	lgr	%r2,%r14
+	lg	%r3,168(%r15)
+	larl	%r14,ftrace_trace_function
+	lg	%r14,0(%r14)
+	basr	%r14,%r14
+	aghi	%r15,160
+	lmg	%r0,%r5,16(%r15)
+	lg	%r14,112(%r15)
+	br	%r14
+
+.globl ftrace_stub
+ftrace_stub:
+	br	%r14
+
+#endif /* CONFIG_64BIT */
diff --git a/arch/s390/kernel/processor.c b/arch/s390/kernel/processor.c
new file mode 100644
index 000000000000..82c1872cfe80
--- /dev/null
+++ b/arch/s390/kernel/processor.c
@@ -0,0 +1,98 @@
+/*
+ *  arch/s390/kernel/processor.c
+ *
+ *  Copyright IBM Corp. 2008
+ *  Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com)
+ */
+
+#define KMSG_COMPONENT "cpu"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/smp.h>
+#include <linux/seq_file.h>
+#include <linux/delay.h>
+
+#include <asm/elf.h>
+#include <asm/lowcore.h>
+#include <asm/param.h>
+
+void __cpuinit print_cpu_info(struct cpuinfo_S390 *cpuinfo)
+{
+	pr_info("Processor %d started, address %d, identification %06X\n",
+		cpuinfo->cpu_nr, cpuinfo->cpu_addr, cpuinfo->cpu_id.ident);
+}
+
+/*
+ * show_cpuinfo - Get information on one CPU for use by procfs.
+ */
+
+static int show_cpuinfo(struct seq_file *m, void *v)
+{
+	static const char *hwcap_str[8] = {
+		"esan3", "zarch", "stfle", "msa", "ldisp", "eimm", "dfp",
+		"edat"
+	};
+       struct cpuinfo_S390 *cpuinfo;
+       unsigned long n = (unsigned long) v - 1;
+       int i;
+
+       s390_adjust_jiffies();
+       preempt_disable();
+       if (!n) {
+	       seq_printf(m, "vendor_id       : IBM/S390\n"
+			  "# processors    : %i\n"
+			  "bogomips per cpu: %lu.%02lu\n",
+			  num_online_cpus(), loops_per_jiffy/(500000/HZ),
+			  (loops_per_jiffy/(5000/HZ))%100);
+	       seq_puts(m, "features\t: ");
+	       for (i = 0; i < 8; i++)
+		       if (hwcap_str[i] && (elf_hwcap & (1UL << i)))
+			       seq_printf(m, "%s ", hwcap_str[i]);
+	       seq_puts(m, "\n");
+       }
+
+       if (cpu_online(n)) {
+#ifdef CONFIG_SMP
+	       if (smp_processor_id() == n)
+		       cpuinfo = &S390_lowcore.cpu_data;
+	       else
+		       cpuinfo = &lowcore_ptr[n]->cpu_data;
+#else
+	       cpuinfo = &S390_lowcore.cpu_data;
+#endif
+	       seq_printf(m, "processor %li: "
+			  "version = %02X,  "
+			  "identification = %06X,  "
+			  "machine = %04X\n",
+			  n, cpuinfo->cpu_id.version,
+			  cpuinfo->cpu_id.ident,
+			  cpuinfo->cpu_id.machine);
+       }
+       preempt_enable();
+       return 0;
+}
+
+static void *c_start(struct seq_file *m, loff_t *pos)
+{
+	return *pos < NR_CPUS ? (void *)((unsigned long) *pos + 1) : NULL;
+}
+
+static void *c_next(struct seq_file *m, void *v, loff_t *pos)
+{
+	++*pos;
+	return c_start(m, pos);
+}
+
+static void c_stop(struct seq_file *m, void *v)
+{
+}
+
+const struct seq_operations cpuinfo_op = {
+	.start	= c_start,
+	.next	= c_next,
+	.stop	= c_stop,
+	.show	= show_cpuinfo,
+};
+
diff --git a/arch/s390/kernel/ptrace.c b/arch/s390/kernel/ptrace.c
index 38ff2bce1203..75c496f4f16d 100644
--- a/arch/s390/kernel/ptrace.c
+++ b/arch/s390/kernel/ptrace.c
@@ -204,7 +204,6 @@ static unsigned long __peek_user(struct task_struct *child, addr_t addr)
 static int
 peek_user(struct task_struct *child, addr_t addr, addr_t data)
 {
-	struct user *dummy = NULL;
 	addr_t tmp, mask;
 
 	/*
@@ -213,8 +212,8 @@ peek_user(struct task_struct *child, addr_t addr, addr_t data)
 	 */
 	mask = __ADDR_MASK;
 #ifdef CONFIG_64BIT
-	if (addr >= (addr_t) &dummy->regs.acrs &&
-	    addr < (addr_t) &dummy->regs.orig_gpr2)
+	if (addr >= (addr_t) &((struct user *) NULL)->regs.acrs &&
+	    addr < (addr_t) &((struct user *) NULL)->regs.orig_gpr2)
 		mask = 3;
 #endif
 	if ((addr & mask) || addr > sizeof(struct user) - __ADDR_MASK)
@@ -312,7 +311,6 @@ static int __poke_user(struct task_struct *child, addr_t addr, addr_t data)
 static int
 poke_user(struct task_struct *child, addr_t addr, addr_t data)
 {
-	struct user *dummy = NULL;
 	addr_t mask;
 
 	/*
@@ -321,8 +319,8 @@ poke_user(struct task_struct *child, addr_t addr, addr_t data)
 	 */
 	mask = __ADDR_MASK;
 #ifdef CONFIG_64BIT
-	if (addr >= (addr_t) &dummy->regs.acrs &&
-	    addr < (addr_t) &dummy->regs.orig_gpr2)
+	if (addr >= (addr_t) &((struct user *) NULL)->regs.acrs &&
+	    addr < (addr_t) &((struct user *) NULL)->regs.orig_gpr2)
 		mask = 3;
 #endif
 	if ((addr & mask) || addr > sizeof(struct user) - __ADDR_MASK)
diff --git a/arch/s390/kernel/s390_ksyms.c b/arch/s390/kernel/s390_ksyms.c
index 48238a114ce9..46b90cb03707 100644
--- a/arch/s390/kernel/s390_ksyms.c
+++ b/arch/s390/kernel/s390_ksyms.c
@@ -14,6 +14,7 @@
 #include <asm/delay.h>
 #include <asm/pgalloc.h>
 #include <asm/setup.h>
+#include <asm/ftrace.h>
 #ifdef CONFIG_IP_MULTICAST
 #include <net/arp.h>
 #endif
@@ -43,3 +44,7 @@ EXPORT_SYMBOL(csum_fold);
 EXPORT_SYMBOL(console_mode);
 EXPORT_SYMBOL(console_devno);
 EXPORT_SYMBOL(console_irq);
+
+#ifdef CONFIG_FUNCTION_TRACER
+EXPORT_SYMBOL(_mcount);
+#endif
diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index 400b040df7fa..40d8c011cfea 100644
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@@ -14,6 +14,9 @@
  * This file handles the architecture-dependent parts of initialization
  */
 
+#define KMSG_COMPONENT "setup"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
 #include <linux/errno.h>
 #include <linux/module.h>
 #include <linux/sched.h>
@@ -32,7 +35,6 @@
 #include <linux/bootmem.h>
 #include <linux/root_dev.h>
 #include <linux/console.h>
-#include <linux/seq_file.h>
 #include <linux/kernel_stat.h>
 #include <linux/device.h>
 #include <linux/notifier.h>
@@ -291,8 +293,8 @@ unsigned int switch_amode = 0;
 #endif
 EXPORT_SYMBOL_GPL(switch_amode);
 
-static void set_amode_and_uaccess(unsigned long user_amode,
-				  unsigned long user32_amode)
+static int set_amode_and_uaccess(unsigned long user_amode,
+				 unsigned long user32_amode)
 {
 	psw_user_bits = PSW_BASE_BITS | PSW_MASK_DAT | user_amode |
 			PSW_MASK_IO | PSW_MASK_EXT | PSW_MASK_MCHECK |
@@ -309,11 +311,11 @@ static void set_amode_and_uaccess(unsigned long user_amode,
 			  PSW_MASK_MCHECK | PSW_DEFAULT_KEY;
 
 	if (MACHINE_HAS_MVCOS) {
-		printk("mvcos available.\n");
 		memcpy(&uaccess, &uaccess_mvcos_switch, sizeof(uaccess));
+		return 1;
 	} else {
-		printk("mvcos not available.\n");
 		memcpy(&uaccess, &uaccess_pt, sizeof(uaccess));
+		return 0;
 	}
 }
 
@@ -328,9 +330,10 @@ static int __init early_parse_switch_amode(char *p)
 early_param("switch_amode", early_parse_switch_amode);
 
 #else /* CONFIG_S390_SWITCH_AMODE */
-static inline void set_amode_and_uaccess(unsigned long user_amode,
-					 unsigned long user32_amode)
+static inline int set_amode_and_uaccess(unsigned long user_amode,
+					unsigned long user32_amode)
 {
+	return 0;
 }
 #endif /* CONFIG_S390_SWITCH_AMODE */
 
@@ -355,11 +358,20 @@ early_param("noexec", early_parse_noexec);
 static void setup_addressing_mode(void)
 {
 	if (s390_noexec) {
-		printk("S390 execute protection active, ");
-		set_amode_and_uaccess(PSW_ASC_SECONDARY, PSW32_ASC_SECONDARY);
+		if (set_amode_and_uaccess(PSW_ASC_SECONDARY,
+					  PSW32_ASC_SECONDARY))
+			pr_info("Execute protection active, "
+				"mvcos available\n");
+		else
+			pr_info("Execute protection active, "
+				"mvcos not available\n");
 	} else if (switch_amode) {
-		printk("S390 address spaces switched, ");
-		set_amode_and_uaccess(PSW_ASC_PRIMARY, PSW32_ASC_PRIMARY);
+		if (set_amode_and_uaccess(PSW_ASC_PRIMARY, PSW32_ASC_PRIMARY))
+			pr_info("Address spaces switched, "
+				"mvcos available\n");
+		else
+			pr_info("Address spaces switched, "
+				"mvcos not available\n");
 	}
 #ifdef CONFIG_TRACE_IRQFLAGS
 	sysc_restore_trace_psw.mask = psw_kernel_bits & ~PSW_MASK_MCHECK;
@@ -572,15 +584,15 @@ setup_memory(void)
 			start = PFN_PHYS(start_pfn) + bmap_size + PAGE_SIZE;
 
 			if (start + INITRD_SIZE > memory_end) {
-				printk("initrd extends beyond end of memory "
-				       "(0x%08lx > 0x%08lx)\n"
+				pr_err("initrd extends beyond end of "
+				       "memory (0x%08lx > 0x%08lx) "
 				       "disabling initrd\n",
 				       start + INITRD_SIZE, memory_end);
 				INITRD_START = INITRD_SIZE = 0;
 			} else {
-				printk("Moving initrd (0x%08lx -> 0x%08lx, "
-				       "size: %ld)\n",
-				       INITRD_START, start, INITRD_SIZE);
+				pr_info("Moving initrd (0x%08lx -> "
+					"0x%08lx, size: %ld)\n",
+					INITRD_START, start, INITRD_SIZE);
 				memmove((void *) start, (void *) INITRD_START,
 					INITRD_SIZE);
 				INITRD_START = start;
@@ -642,8 +654,9 @@ setup_memory(void)
 			initrd_start = INITRD_START;
 			initrd_end = initrd_start + INITRD_SIZE;
 		} else {
-			printk("initrd extends beyond end of memory "
-			       "(0x%08lx > 0x%08lx)\ndisabling initrd\n",
+			pr_err("initrd extends beyond end of "
+			       "memory (0x%08lx > 0x%08lx) "
+			       "disabling initrd\n",
 			       initrd_start + INITRD_SIZE, memory_end);
 			initrd_start = initrd_end = 0;
 		}
@@ -651,23 +664,6 @@ setup_memory(void)
 #endif
 }
 
-static int __init __stfle(unsigned long long *list, int doublewords)
-{
-	typedef struct { unsigned long long _[doublewords]; } addrtype;
-	register unsigned long __nr asm("0") = doublewords - 1;
-
-	asm volatile(".insn s,0xb2b00000,%0" /* stfle */
-		     : "=m" (*(addrtype *) list), "+d" (__nr) : : "cc");
-	return __nr + 1;
-}
-
-int __init stfle(unsigned long long *list, int doublewords)
-{
-	if (!(stfl() & (1UL << 24)))
-		return -EOPNOTSUPP;
-	return __stfle(list, doublewords);
-}
-
 /*
  * Setup hardware capabilities.
  */
@@ -739,8 +735,13 @@ static void __init setup_hwcaps(void)
 		strcpy(elf_platform, "z990");
 		break;
 	case 0x2094:
+	case 0x2096:
 		strcpy(elf_platform, "z9-109");
 		break;
+	case 0x2097:
+	case 0x2098:
+		strcpy(elf_platform, "z10");
+		break;
 	}
 }
 
@@ -756,21 +757,27 @@ setup_arch(char **cmdline_p)
          * print what head.S has found out about the machine
          */
 #ifndef CONFIG_64BIT
-	printk((MACHINE_IS_VM) ?
-	       "We are running under VM (31 bit mode)\n" :
-	       "We are running native (31 bit mode)\n");
-	printk((MACHINE_HAS_IEEE) ?
-	       "This machine has an IEEE fpu\n" :
-	       "This machine has no IEEE fpu\n");
+	if (MACHINE_IS_VM)
+		pr_info("Linux is running as a z/VM "
+			"guest operating system in 31-bit mode\n");
+	else
+		pr_info("Linux is running natively in 31-bit mode\n");
+	if (MACHINE_HAS_IEEE)
+		pr_info("The hardware system has IEEE compatible "
+			"floating point units\n");
+	else
+		pr_info("The hardware system has no IEEE compatible "
+			"floating point units\n");
 #else /* CONFIG_64BIT */
 	if (MACHINE_IS_VM)
-		printk("We are running under VM (64 bit mode)\n");
+		pr_info("Linux is running as a z/VM "
+			"guest operating system in 64-bit mode\n");
 	else if (MACHINE_IS_KVM) {
-		printk("We are running under KVM (64 bit mode)\n");
+		pr_info("Linux is running under KVM in 64-bit mode\n");
 		add_preferred_console("hvc", 0, NULL);
 		s390_virtio_console_init();
 	} else
-		printk("We are running native (64 bit mode)\n");
+		pr_info("Linux is running natively in 64-bit mode\n");
 #endif /* CONFIG_64BIT */
 
 	/* Have one command line that is parsed and saved in /proc/cmdline */
@@ -818,90 +825,3 @@ setup_arch(char **cmdline_p)
 	/* Setup zfcpdump support */
 	setup_zfcpdump(console_devno);
 }
-
-void __cpuinit print_cpu_info(struct cpuinfo_S390 *cpuinfo)
-{
-   printk(KERN_INFO "cpu %d "
-#ifdef CONFIG_SMP
-           "phys_idx=%d "
-#endif
-           "vers=%02X ident=%06X machine=%04X unused=%04X\n",
-           cpuinfo->cpu_nr,
-#ifdef CONFIG_SMP
-           cpuinfo->cpu_addr,
-#endif
-           cpuinfo->cpu_id.version,
-           cpuinfo->cpu_id.ident,
-           cpuinfo->cpu_id.machine,
-           cpuinfo->cpu_id.unused);
-}
-
-/*
- * show_cpuinfo - Get information on one CPU for use by procfs.
- */
-
-static int show_cpuinfo(struct seq_file *m, void *v)
-{
-	static const char *hwcap_str[8] = {
-		"esan3", "zarch", "stfle", "msa", "ldisp", "eimm", "dfp",
-		"edat"
-	};
-        struct cpuinfo_S390 *cpuinfo;
-	unsigned long n = (unsigned long) v - 1;
-	int i;
-
-	s390_adjust_jiffies();
-	preempt_disable();
-	if (!n) {
-		seq_printf(m, "vendor_id       : IBM/S390\n"
-			       "# processors    : %i\n"
-			       "bogomips per cpu: %lu.%02lu\n",
-			       num_online_cpus(), loops_per_jiffy/(500000/HZ),
-			       (loops_per_jiffy/(5000/HZ))%100);
-		seq_puts(m, "features\t: ");
-		for (i = 0; i < 8; i++)
-			if (hwcap_str[i] && (elf_hwcap & (1UL << i)))
-				seq_printf(m, "%s ", hwcap_str[i]);
-		seq_puts(m, "\n");
-	}
-
-	if (cpu_online(n)) {
-#ifdef CONFIG_SMP
-		if (smp_processor_id() == n)
-			cpuinfo = &S390_lowcore.cpu_data;
-		else
-			cpuinfo = &lowcore_ptr[n]->cpu_data;
-#else
-		cpuinfo = &S390_lowcore.cpu_data;
-#endif
-		seq_printf(m, "processor %li: "
-			       "version = %02X,  "
-			       "identification = %06X,  "
-			       "machine = %04X\n",
-			       n, cpuinfo->cpu_id.version,
-			       cpuinfo->cpu_id.ident,
-			       cpuinfo->cpu_id.machine);
-	}
-	preempt_enable();
-        return 0;
-}
-
-static void *c_start(struct seq_file *m, loff_t *pos)
-{
-	return *pos < NR_CPUS ? (void *)((unsigned long) *pos + 1) : NULL;
-}
-static void *c_next(struct seq_file *m, void *v, loff_t *pos)
-{
-	++*pos;
-	return c_start(m, pos);
-}
-static void c_stop(struct seq_file *m, void *v)
-{
-}
-const struct seq_operations cpuinfo_op = {
-	.start	= c_start,
-	.next	= c_next,
-	.stop	= c_stop,
-	.show	= show_cpuinfo,
-};
-
diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c
index b5595688a477..19ee3d19da69 100644
--- a/arch/s390/kernel/smp.c
+++ b/arch/s390/kernel/smp.c
@@ -20,6 +20,9 @@
  * cpu_number_map in other architectures.
  */
 
+#define KMSG_COMPONENT "cpu"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
 #include <linux/module.h>
 #include <linux/init.h>
 #include <linux/mm.h>
@@ -77,159 +80,6 @@ static DEFINE_PER_CPU(struct cpu, cpu_devices);
 
 static void smp_ext_bitcall(int, ec_bit_sig);
 
-/*
- * Structure and data for __smp_call_function_map(). This is designed to
- * minimise static memory requirements. It also looks cleaner.
- */
-static DEFINE_SPINLOCK(call_lock);
-
-struct call_data_struct {
-	void (*func) (void *info);
-	void *info;
-	cpumask_t started;
-	cpumask_t finished;
-	int wait;
-};
-
-static struct call_data_struct *call_data;
-
-/*
- * 'Call function' interrupt callback
- */
-static void do_call_function(void)
-{
-	void (*func) (void *info) = call_data->func;
-	void *info = call_data->info;
-	int wait = call_data->wait;
-
-	cpu_set(smp_processor_id(), call_data->started);
-	(*func)(info);
-	if (wait)
-		cpu_set(smp_processor_id(), call_data->finished);;
-}
-
-static void __smp_call_function_map(void (*func) (void *info), void *info,
-				    int wait, cpumask_t map)
-{
-	struct call_data_struct data;
-	int cpu, local = 0;
-
-	/*
-	 * Can deadlock when interrupts are disabled or if in wrong context.
-	 */
-	WARN_ON(irqs_disabled() || in_irq());
-
-	/*
-	 * Check for local function call. We have to have the same call order
-	 * as in on_each_cpu() because of machine_restart_smp().
-	 */
-	if (cpu_isset(smp_processor_id(), map)) {
-		local = 1;
-		cpu_clear(smp_processor_id(), map);
-	}
-
-	cpus_and(map, map, cpu_online_map);
-	if (cpus_empty(map))
-		goto out;
-
-	data.func = func;
-	data.info = info;
-	data.started = CPU_MASK_NONE;
-	data.wait = wait;
-	if (wait)
-		data.finished = CPU_MASK_NONE;
-
-	call_data = &data;
-
-	for_each_cpu_mask(cpu, map)
-		smp_ext_bitcall(cpu, ec_call_function);
-
-	/* Wait for response */
-	while (!cpus_equal(map, data.started))
-		cpu_relax();
-	if (wait)
-		while (!cpus_equal(map, data.finished))
-			cpu_relax();
-out:
-	if (local) {
-		local_irq_disable();
-		func(info);
-		local_irq_enable();
-	}
-}
-
-/*
- * smp_call_function:
- * @func: the function to run; this must be fast and non-blocking
- * @info: an arbitrary pointer to pass to the function
- * @wait: if true, wait (atomically) until function has completed on other CPUs
- *
- * Run a function on all other CPUs.
- *
- * You must not call this function with disabled interrupts, from a
- * hardware interrupt handler or from a bottom half.
- */
-int smp_call_function(void (*func) (void *info), void *info, int wait)
-{
-	cpumask_t map;
-
-	spin_lock(&call_lock);
-	map = cpu_online_map;
-	cpu_clear(smp_processor_id(), map);
-	__smp_call_function_map(func, info, wait, map);
-	spin_unlock(&call_lock);
-	return 0;
-}
-EXPORT_SYMBOL(smp_call_function);
-
-/*
- * smp_call_function_single:
- * @cpu: the CPU where func should run
- * @func: the function to run; this must be fast and non-blocking
- * @info: an arbitrary pointer to pass to the function
- * @wait: if true, wait (atomically) until function has completed on other CPUs
- *
- * Run a function on one processor.
- *
- * You must not call this function with disabled interrupts, from a
- * hardware interrupt handler or from a bottom half.
- */
-int smp_call_function_single(int cpu, void (*func) (void *info), void *info,
-			     int wait)
-{
-	spin_lock(&call_lock);
-	__smp_call_function_map(func, info, wait, cpumask_of_cpu(cpu));
-	spin_unlock(&call_lock);
-	return 0;
-}
-EXPORT_SYMBOL(smp_call_function_single);
-
-/**
- * smp_call_function_mask(): Run a function on a set of other CPUs.
- * @mask: The set of cpus to run on.  Must not include the current cpu.
- * @func: The function to run. This must be fast and non-blocking.
- * @info: An arbitrary pointer to pass to the function.
- * @wait: If true, wait (atomically) until function has completed on other CPUs.
- *
- * Returns 0 on success, else a negative status code.
- *
- * If @wait is true, then returns once @func has returned; otherwise
- * it returns just before the target cpu calls @func.
- *
- * You must not call this function with disabled interrupts or from a
- * hardware interrupt handler or from a bottom half handler.
- */
-int smp_call_function_mask(cpumask_t mask, void (*func)(void *), void *info,
-			   int wait)
-{
-	spin_lock(&call_lock);
-	cpu_clear(smp_processor_id(), mask);
-	__smp_call_function_map(func, info, wait, mask);
-	spin_unlock(&call_lock);
-	return 0;
-}
-EXPORT_SYMBOL(smp_call_function_mask);
-
 void smp_send_stop(void)
 {
 	int cpu, rc;
@@ -271,7 +121,10 @@ static void do_ext_call_interrupt(__u16 code)
 	bits = xchg(&S390_lowcore.ext_call_fast, 0);
 
 	if (test_bit(ec_call_function, &bits))
-		do_call_function();
+		generic_smp_call_function_interrupt();
+
+	if (test_bit(ec_call_function_single, &bits))
+		generic_smp_call_function_single_interrupt();
 }
 
 /*
@@ -288,6 +141,19 @@ static void smp_ext_bitcall(int cpu, ec_bit_sig sig)
 		udelay(10);
 }
 
+void arch_send_call_function_ipi(cpumask_t mask)
+{
+	int cpu;
+
+	for_each_cpu_mask(cpu, mask)
+		smp_ext_bitcall(cpu, ec_call_function);
+}
+
+void arch_send_call_function_single_ipi(int cpu)
+{
+	smp_ext_bitcall(cpu, ec_call_function_single);
+}
+
 #ifndef CONFIG_64BIT
 /*
  * this function sends a 'purge tlb' signal to another CPU.
@@ -388,8 +254,8 @@ static void __init smp_get_save_area(unsigned int cpu, unsigned int phy_cpu)
 	if (ipl_info.type != IPL_TYPE_FCP_DUMP)
 		return;
 	if (cpu >= NR_CPUS) {
-		printk(KERN_WARNING "Registers for cpu %i not saved since dump "
-		       "kernel was compiled with NR_CPUS=%i\n", cpu, NR_CPUS);
+		pr_warning("CPU %i exceeds the maximum %i and is excluded from "
+			   "the dump\n", cpu, NR_CPUS - 1);
 		return;
 	}
 	zfcpdump_save_areas[cpu] = kmalloc(sizeof(union save_area), GFP_KERNEL);
@@ -562,7 +428,7 @@ static void __init smp_detect_cpus(void)
 	}
 out:
 	kfree(info);
-	printk(KERN_INFO "CPUs: %d configured, %d standby\n", c_cpus, s_cpus);
+	pr_info("%d configured CPUs, %d standby CPUs\n", c_cpus, s_cpus);
 	get_online_cpus();
 	__smp_rescan_cpus();
 	put_online_cpus();
@@ -588,9 +454,9 @@ int __cpuinit start_secondary(void *cpuvoid)
 	/* call cpu notifiers */
 	notify_cpu_starting(smp_processor_id());
 	/* Mark this cpu as online */
-	spin_lock(&call_lock);
+	ipi_call_lock();
 	cpu_set(smp_processor_id(), cpu_online_map);
-	spin_unlock(&call_lock);
+	ipi_call_unlock();
 	/* Switch on interrupts */
 	local_irq_enable();
 	/* Print info about this processor */
@@ -690,12 +556,8 @@ int __cpuinit __cpu_up(unsigned int cpu)
 
 	ccode = signal_processor_p((__u32)(unsigned long)(lowcore_ptr[cpu]),
 				   cpu, sigp_set_prefix);
-	if (ccode) {
-		printk("sigp_set_prefix failed for cpu %d "
-		       "with condition code %d\n",
-		       (int) cpu, (int) ccode);
+	if (ccode)
 		return -EIO;
-	}
 
 	idle = current_set[cpu];
 	cpu_lowcore = lowcore_ptr[cpu];
@@ -778,7 +640,7 @@ void __cpu_die(unsigned int cpu)
 	while (!smp_cpu_not_running(cpu))
 		cpu_relax();
 	smp_free_lowcore(cpu);
-	printk(KERN_INFO "Processor %d spun down\n", cpu);
+	pr_info("Processor %d stopped\n", cpu);
 }
 
 void cpu_die(void)
diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c
index eccefbbff887..cda77776264c 100644
--- a/arch/s390/kernel/time.c
+++ b/arch/s390/kernel/time.c
@@ -12,6 +12,9 @@
  *    Copyright (C) 1991, 1992, 1995  Linus Torvalds
  */
 
+#define KMSG_COMPONENT "time"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
 #include <linux/errno.h>
 #include <linux/module.h>
 #include <linux/sched.h>
@@ -20,6 +23,8 @@
 #include <linux/string.h>
 #include <linux/mm.h>
 #include <linux/interrupt.h>
+#include <linux/cpu.h>
+#include <linux/stop_machine.h>
 #include <linux/time.h>
 #include <linux/sysdev.h>
 #include <linux/delay.h>
@@ -36,6 +41,7 @@
 #include <asm/delay.h>
 #include <asm/s390_ext.h>
 #include <asm/div64.h>
+#include <asm/vdso.h>
 #include <asm/irq.h>
 #include <asm/irq_regs.h>
 #include <asm/timer.h>
@@ -223,6 +229,36 @@ static struct clocksource clocksource_tod = {
 };
 
 
+void update_vsyscall(struct timespec *wall_time, struct clocksource *clock)
+{
+	if (clock != &clocksource_tod)
+		return;
+
+	/* Make userspace gettimeofday spin until we're done. */
+	++vdso_data->tb_update_count;
+	smp_wmb();
+	vdso_data->xtime_tod_stamp = clock->cycle_last;
+	vdso_data->xtime_clock_sec = xtime.tv_sec;
+	vdso_data->xtime_clock_nsec = xtime.tv_nsec;
+	vdso_data->wtom_clock_sec = wall_to_monotonic.tv_sec;
+	vdso_data->wtom_clock_nsec = wall_to_monotonic.tv_nsec;
+	smp_wmb();
+	++vdso_data->tb_update_count;
+}
+
+extern struct timezone sys_tz;
+
+void update_vsyscall_tz(void)
+{
+	/* Make userspace gettimeofday spin until we're done. */
+	++vdso_data->tb_update_count;
+	smp_wmb();
+	vdso_data->tz_minuteswest = sys_tz.tz_minuteswest;
+	vdso_data->tz_dsttime = sys_tz.tz_dsttime;
+	smp_wmb();
+	++vdso_data->tb_update_count;
+}
+
 /*
  * Initialize the TOD clock and the CPU timer of
  * the boot cpu.
@@ -288,8 +324,8 @@ static unsigned long long adjust_time(unsigned long long old,
 	}
 	sched_clock_base_cc += delta;
 	if (adjust.offset != 0) {
-		printk(KERN_NOTICE "etr: time adjusted by %li micro-seconds\n",
-		       adjust.offset);
+		pr_notice("The ETR interface has adjusted the clock "
+			  "by %li microseconds\n", adjust.offset);
 		adjust.modes = ADJ_OFFSET_SINGLESHOT;
 		do_adjtimex(&adjust);
 	}
@@ -360,6 +396,15 @@ static void enable_sync_clock(void)
 	atomic_set_mask(0x80000000, sw_ptr);
 }
 
+/* Single threaded workqueue used for etr and stp sync events */
+static struct workqueue_struct *time_sync_wq;
+
+static void __init time_init_wq(void)
+{
+	if (!time_sync_wq)
+		time_sync_wq = create_singlethread_workqueue("timesync");
+}
+
 /*
  * External Time Reference (ETR) code.
  */
@@ -425,6 +470,7 @@ static struct timer_list etr_timer;
 
 static void etr_timeout(unsigned long dummy);
 static void etr_work_fn(struct work_struct *work);
+static DEFINE_MUTEX(etr_work_mutex);
 static DECLARE_WORK(etr_work, etr_work_fn);
 
 /*
@@ -440,8 +486,8 @@ static void etr_reset(void)
 		etr_tolec = get_clock();
 		set_bit(CLOCK_SYNC_HAS_ETR, &clock_sync_flags);
 	} else if (etr_port0_online || etr_port1_online) {
-		printk(KERN_WARNING "Running on non ETR capable "
-		       "machine, only local mode available.\n");
+		pr_warning("The real or virtual hardware system does "
+			   "not provide an ETR interface\n");
 		etr_port0_online = etr_port1_online = 0;
 	}
 }
@@ -452,17 +498,18 @@ static int __init etr_init(void)
 
 	if (!test_bit(CLOCK_SYNC_HAS_ETR, &clock_sync_flags))
 		return 0;
+	time_init_wq();
 	/* Check if this machine has the steai instruction. */
 	if (etr_steai(&aib, ETR_STEAI_STEPPING_PORT) == 0)
 		etr_steai_available = 1;
 	setup_timer(&etr_timer, etr_timeout, 0UL);
 	if (etr_port0_online) {
 		set_bit(ETR_EVENT_PORT0_CHANGE, &etr_events);
-		schedule_work(&etr_work);
+		queue_work(time_sync_wq, &etr_work);
 	}
 	if (etr_port1_online) {
 		set_bit(ETR_EVENT_PORT1_CHANGE, &etr_events);
-		schedule_work(&etr_work);
+		queue_work(time_sync_wq, &etr_work);
 	}
 	return 0;
 }
@@ -489,7 +536,7 @@ void etr_switch_to_local(void)
 	if (test_bit(CLOCK_SYNC_ETR, &clock_sync_flags))
 		disable_sync_clock(NULL);
 	set_bit(ETR_EVENT_SWITCH_LOCAL, &etr_events);
-	schedule_work(&etr_work);
+	queue_work(time_sync_wq, &etr_work);
 }
 
 /*
@@ -505,7 +552,7 @@ void etr_sync_check(void)
 	if (test_bit(CLOCK_SYNC_ETR, &clock_sync_flags))
 		disable_sync_clock(NULL);
 	set_bit(ETR_EVENT_SYNC_CHECK, &etr_events);
-	schedule_work(&etr_work);
+	queue_work(time_sync_wq, &etr_work);
 }
 
 /*
@@ -529,13 +576,13 @@ static void etr_timing_alert(struct etr_irq_parm *intparm)
 		 * Both ports are not up-to-date now.
 		 */
 		set_bit(ETR_EVENT_PORT_ALERT, &etr_events);
-	schedule_work(&etr_work);
+	queue_work(time_sync_wq, &etr_work);
 }
 
 static void etr_timeout(unsigned long dummy)
 {
 	set_bit(ETR_EVENT_UPDATE, &etr_events);
-	schedule_work(&etr_work);
+	queue_work(time_sync_wq, &etr_work);
 }
 
 /*
@@ -642,14 +689,16 @@ static int etr_aib_follows(struct etr_aib *a1, struct etr_aib *a2, int p)
 }
 
 struct clock_sync_data {
+	atomic_t cpus;
 	int in_sync;
 	unsigned long long fixup_cc;
+	int etr_port;
+	struct etr_aib *etr_aib;
 };
 
-static void clock_sync_cpu_start(void *dummy)
+static void clock_sync_cpu(struct clock_sync_data *sync)
 {
-	struct clock_sync_data *sync = dummy;
-
+	atomic_dec(&sync->cpus);
 	enable_sync_clock();
 	/*
 	 * This looks like a busy wait loop but it isn't. etr_sync_cpus
@@ -675,39 +724,35 @@ static void clock_sync_cpu_start(void *dummy)
 	fixup_clock_comparator(sync->fixup_cc);
 }
 
-static void clock_sync_cpu_end(void *dummy)
-{
-}
-
 /*
  * Sync the TOD clock using the port refered to by aibp. This port
  * has to be enabled and the other port has to be disabled. The
  * last eacr update has to be more than 1.6 seconds in the past.
  */
-static int etr_sync_clock(struct etr_aib *aib, int port)
+static int etr_sync_clock(void *data)
 {
-	struct etr_aib *sync_port;
-	struct clock_sync_data etr_sync;
+	static int first;
 	unsigned long long clock, old_clock, delay, delta;
-	int follows;
+	struct clock_sync_data *etr_sync;
+	struct etr_aib *sync_port, *aib;
+	int port;
 	int rc;
 
-	/* Check if the current aib is adjacent to the sync port aib. */
-	sync_port = (port == 0) ? &etr_port0 : &etr_port1;
-	follows = etr_aib_follows(sync_port, aib, port);
-	memcpy(sync_port, aib, sizeof(*aib));
-	if (!follows)
-		return -EAGAIN;
+	etr_sync = data;
 
-	/*
-	 * Catch all other cpus and make them wait until we have
-	 * successfully synced the clock. smp_call_function will
-	 * return after all other cpus are in etr_sync_cpu_start.
-	 */
-	memset(&etr_sync, 0, sizeof(etr_sync));
-	preempt_disable();
-	smp_call_function(clock_sync_cpu_start, &etr_sync, 0);
-	local_irq_disable();
+	if (xchg(&first, 1) == 1) {
+		/* Slave */
+		clock_sync_cpu(etr_sync);
+		return 0;
+	}
+
+	/* Wait until all other cpus entered the sync function. */
+	while (atomic_read(&etr_sync->cpus) != 0)
+		cpu_relax();
+
+	port = etr_sync->etr_port;
+	aib = etr_sync->etr_aib;
+	sync_port = (port == 0) ? &etr_port0 : &etr_port1;
 	enable_sync_clock();
 
 	/* Set clock to next OTE. */
@@ -724,16 +769,16 @@ static int etr_sync_clock(struct etr_aib *aib, int port)
 		delay = (unsigned long long)
 			(aib->edf2.etv - sync_port->edf2.etv) << 32;
 		delta = adjust_time(old_clock, clock, delay);
-		etr_sync.fixup_cc = delta;
+		etr_sync->fixup_cc = delta;
 		fixup_clock_comparator(delta);
 		/* Verify that the clock is properly set. */
 		if (!etr_aib_follows(sync_port, aib, port)) {
 			/* Didn't work. */
 			disable_sync_clock(NULL);
-			etr_sync.in_sync = -EAGAIN;
+			etr_sync->in_sync = -EAGAIN;
 			rc = -EAGAIN;
 		} else {
-			etr_sync.in_sync = 1;
+			etr_sync->in_sync = 1;
 			rc = 0;
 		}
 	} else {
@@ -741,12 +786,33 @@ static int etr_sync_clock(struct etr_aib *aib, int port)
 		__ctl_clear_bit(0, 29);
 		__ctl_clear_bit(14, 21);
 		disable_sync_clock(NULL);
-		etr_sync.in_sync = -EAGAIN;
+		etr_sync->in_sync = -EAGAIN;
 		rc = -EAGAIN;
 	}
-	local_irq_enable();
-	smp_call_function(clock_sync_cpu_end, NULL, 0);
-	preempt_enable();
+	xchg(&first, 0);
+	return rc;
+}
+
+static int etr_sync_clock_stop(struct etr_aib *aib, int port)
+{
+	struct clock_sync_data etr_sync;
+	struct etr_aib *sync_port;
+	int follows;
+	int rc;
+
+	/* Check if the current aib is adjacent to the sync port aib. */
+	sync_port = (port == 0) ? &etr_port0 : &etr_port1;
+	follows = etr_aib_follows(sync_port, aib, port);
+	memcpy(sync_port, aib, sizeof(*aib));
+	if (!follows)
+		return -EAGAIN;
+	memset(&etr_sync, 0, sizeof(etr_sync));
+	etr_sync.etr_aib = aib;
+	etr_sync.etr_port = port;
+	get_online_cpus();
+	atomic_set(&etr_sync.cpus, num_online_cpus() - 1);
+	rc = stop_machine(etr_sync_clock, &etr_sync, &cpu_online_map);
+	put_online_cpus();
 	return rc;
 }
 
@@ -903,7 +969,7 @@ static void etr_update_eacr(struct etr_eacr eacr)
 }
 
 /*
- * ETR tasklet. In this function you'll find the main logic. In
+ * ETR work. In this function you'll find the main logic. In
  * particular this is the only function that calls etr_update_eacr(),
  * it "controls" the etr control register.
  */
@@ -914,6 +980,9 @@ static void etr_work_fn(struct work_struct *work)
 	struct etr_aib aib;
 	int sync_port;
 
+	/* prevent multiple execution. */
+	mutex_lock(&etr_work_mutex);
+
 	/* Create working copy of etr_eacr. */
 	eacr = etr_eacr;
 
@@ -929,7 +998,7 @@ static void etr_work_fn(struct work_struct *work)
 		del_timer_sync(&etr_timer);
 		etr_update_eacr(eacr);
 		clear_bit(CLOCK_SYNC_ETR, &clock_sync_flags);
-		return;
+		goto out_unlock;
 	}
 
 	/* Store aib to get the current ETR status word. */
@@ -1016,7 +1085,7 @@ static void etr_work_fn(struct work_struct *work)
 	    eacr.es || sync_port < 0) {
 		etr_update_eacr(eacr);
 		etr_set_tolec_timeout(now);
-		return;
+		goto out_unlock;
 	}
 
 	/*
@@ -1036,7 +1105,7 @@ static void etr_work_fn(struct work_struct *work)
 	etr_update_eacr(eacr);
 	set_bit(CLOCK_SYNC_ETR, &clock_sync_flags);
 	if (now < etr_tolec + (1600000 << 12) ||
-	    etr_sync_clock(&aib, sync_port) != 0) {
+	    etr_sync_clock_stop(&aib, sync_port) != 0) {
 		/* Sync failed. Try again in 1/2 second. */
 		eacr.es = 0;
 		etr_update_eacr(eacr);
@@ -1044,6 +1113,8 @@ static void etr_work_fn(struct work_struct *work)
 		etr_set_sync_timeout();
 	} else
 		etr_set_tolec_timeout(now);
+out_unlock:
+	mutex_unlock(&etr_work_mutex);
 }
 
 /*
@@ -1125,13 +1196,13 @@ static ssize_t etr_online_store(struct sys_device *dev,
 			return count;	/* Nothing to do. */
 		etr_port0_online = value;
 		set_bit(ETR_EVENT_PORT0_CHANGE, &etr_events);
-		schedule_work(&etr_work);
+		queue_work(time_sync_wq, &etr_work);
 	} else {
 		if (etr_port1_online == value)
 			return count;	/* Nothing to do. */
 		etr_port1_online = value;
 		set_bit(ETR_EVENT_PORT1_CHANGE, &etr_events);
-		schedule_work(&etr_work);
+		queue_work(time_sync_wq, &etr_work);
 	}
 	return count;
 }
@@ -1332,6 +1403,7 @@ static struct stp_sstpi stp_info;
 static void *stp_page;
 
 static void stp_work_fn(struct work_struct *work);
+static DEFINE_MUTEX(stp_work_mutex);
 static DECLARE_WORK(stp_work, stp_work_fn);
 
 static int __init early_parse_stp(char *p)
@@ -1356,7 +1428,8 @@ static void __init stp_reset(void)
 	if (rc == 0)
 		set_bit(CLOCK_SYNC_HAS_STP, &clock_sync_flags);
 	else if (stp_online) {
-		printk(KERN_WARNING "Running on non STP capable machine.\n");
+		pr_warning("The real or virtual hardware system does "
+			   "not provide an STP interface\n");
 		free_bootmem((unsigned long) stp_page, PAGE_SIZE);
 		stp_page = NULL;
 		stp_online = 0;
@@ -1365,8 +1438,12 @@ static void __init stp_reset(void)
 
 static int __init stp_init(void)
 {
-	if (test_bit(CLOCK_SYNC_HAS_STP, &clock_sync_flags) && stp_online)
-		schedule_work(&stp_work);
+	if (!test_bit(CLOCK_SYNC_HAS_STP, &clock_sync_flags))
+		return 0;
+	time_init_wq();
+	if (!stp_online)
+		return 0;
+	queue_work(time_sync_wq, &stp_work);
 	return 0;
 }
 
@@ -1383,7 +1460,7 @@ arch_initcall(stp_init);
 static void stp_timing_alert(struct stp_irq_parm *intparm)
 {
 	if (intparm->tsc || intparm->lac || intparm->tcpc)
-		schedule_work(&stp_work);
+		queue_work(time_sync_wq, &stp_work);
 }
 
 /*
@@ -1397,7 +1474,7 @@ void stp_sync_check(void)
 	if (!test_bit(CLOCK_SYNC_STP, &clock_sync_flags))
 		return;
 	disable_sync_clock(NULL);
-	schedule_work(&stp_work);
+	queue_work(time_sync_wq, &stp_work);
 }
 
 /*
@@ -1411,46 +1488,34 @@ void stp_island_check(void)
 	if (!test_bit(CLOCK_SYNC_STP, &clock_sync_flags))
 		return;
 	disable_sync_clock(NULL);
-	schedule_work(&stp_work);
+	queue_work(time_sync_wq, &stp_work);
 }
 
-/*
- * STP tasklet. Check for the STP state and take over the clock
- * synchronization if the STP clock source is usable.
- */
-static void stp_work_fn(struct work_struct *work)
+
+static int stp_sync_clock(void *data)
 {
-	struct clock_sync_data stp_sync;
+	static int first;
 	unsigned long long old_clock, delta;
+	struct clock_sync_data *stp_sync;
 	int rc;
 
-	if (!stp_online) {
-		chsc_sstpc(stp_page, STP_OP_CTRL, 0x0000);
-		return;
-	}
+	stp_sync = data;
 
-	rc = chsc_sstpc(stp_page, STP_OP_CTRL, 0xb0e0);
-	if (rc)
-		return;
+	if (xchg(&first, 1) == 1) {
+		/* Slave */
+		clock_sync_cpu(stp_sync);
+		return 0;
+	}
 
-	rc = chsc_sstpi(stp_page, &stp_info, sizeof(struct stp_sstpi));
-	if (rc || stp_info.c == 0)
-		return;
+	/* Wait until all other cpus entered the sync function. */
+	while (atomic_read(&stp_sync->cpus) != 0)
+		cpu_relax();
 
-	/*
-	 * Catch all other cpus and make them wait until we have
-	 * successfully synced the clock. smp_call_function will
-	 * return after all other cpus are in clock_sync_cpu_start.
-	 */
-	memset(&stp_sync, 0, sizeof(stp_sync));
-	preempt_disable();
-	smp_call_function(clock_sync_cpu_start, &stp_sync, 0);
-	local_irq_disable();
 	enable_sync_clock();
 
 	set_bit(CLOCK_SYNC_STP, &clock_sync_flags);
 	if (test_and_clear_bit(CLOCK_SYNC_ETR, &clock_sync_flags))
-		schedule_work(&etr_work);
+		queue_work(time_sync_wq, &etr_work);
 
 	rc = 0;
 	if (stp_info.todoff[0] || stp_info.todoff[1] ||
@@ -1469,16 +1534,49 @@ static void stp_work_fn(struct work_struct *work)
 	}
 	if (rc) {
 		disable_sync_clock(NULL);
-		stp_sync.in_sync = -EAGAIN;
+		stp_sync->in_sync = -EAGAIN;
 		clear_bit(CLOCK_SYNC_STP, &clock_sync_flags);
 		if (etr_port0_online || etr_port1_online)
-			schedule_work(&etr_work);
+			queue_work(time_sync_wq, &etr_work);
 	} else
-		stp_sync.in_sync = 1;
+		stp_sync->in_sync = 1;
+	xchg(&first, 0);
+	return 0;
+}
+
+/*
+ * STP work. Check for the STP state and take over the clock
+ * synchronization if the STP clock source is usable.
+ */
+static void stp_work_fn(struct work_struct *work)
+{
+	struct clock_sync_data stp_sync;
+	int rc;
+
+	/* prevent multiple execution. */
+	mutex_lock(&stp_work_mutex);
+
+	if (!stp_online) {
+		chsc_sstpc(stp_page, STP_OP_CTRL, 0x0000);
+		goto out_unlock;
+	}
+
+	rc = chsc_sstpc(stp_page, STP_OP_CTRL, 0xb0e0);
+	if (rc)
+		goto out_unlock;
+
+	rc = chsc_sstpi(stp_page, &stp_info, sizeof(struct stp_sstpi));
+	if (rc || stp_info.c == 0)
+		goto out_unlock;
+
+	memset(&stp_sync, 0, sizeof(stp_sync));
+	get_online_cpus();
+	atomic_set(&stp_sync.cpus, num_online_cpus() - 1);
+	stop_machine(stp_sync_clock, &stp_sync, &cpu_online_map);
+	put_online_cpus();
 
-	local_irq_enable();
-	smp_call_function(clock_sync_cpu_end, NULL, 0);
-	preempt_enable();
+out_unlock:
+	mutex_unlock(&stp_work_mutex);
 }
 
 /*
@@ -1587,7 +1685,7 @@ static ssize_t stp_online_store(struct sysdev_class *class,
 	if (!test_bit(CLOCK_SYNC_HAS_STP, &clock_sync_flags))
 		return -EOPNOTSUPP;
 	stp_online = value;
-	schedule_work(&stp_work);
+	queue_work(time_sync_wq, &stp_work);
 	return count;
 }
 
diff --git a/arch/s390/kernel/topology.c b/arch/s390/kernel/topology.c
index a947899dcba1..42e6cb354017 100644
--- a/arch/s390/kernel/topology.c
+++ b/arch/s390/kernel/topology.c
@@ -3,6 +3,9 @@
  *    Author(s): Heiko Carstens <heiko.carstens@de.ibm.com>
  */
 
+#define KMSG_COMPONENT "cpu"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
 #include <linux/kernel.h>
 #include <linux/mm.h>
 #include <linux/init.h>
@@ -57,6 +60,7 @@ struct core_info {
 	cpumask_t mask;
 };
 
+static int topology_enabled;
 static void topology_work_fn(struct work_struct *work);
 static struct tl_info *tl_info;
 static struct core_info core_info;
@@ -77,8 +81,8 @@ cpumask_t cpu_coregroup_map(unsigned int cpu)
 	cpumask_t mask;
 
 	cpus_clear(mask);
-	if (!machine_has_topology)
-		return cpu_present_map;
+	if (!topology_enabled || !machine_has_topology)
+		return cpu_possible_map;
 	spin_lock_irqsave(&topology_lock, flags);
 	while (core) {
 		if (cpu_isset(cpu, core->mask)) {
@@ -168,7 +172,7 @@ static void topology_update_polarization_simple(void)
 	int cpu;
 
 	mutex_lock(&smp_cpu_state_mutex);
-	for_each_present_cpu(cpu)
+	for_each_possible_cpu(cpu)
 		smp_cpu_polarization[cpu] = POLARIZATION_HRZ;
 	mutex_unlock(&smp_cpu_state_mutex);
 }
@@ -199,7 +203,7 @@ int topology_set_cpu_management(int fc)
 		rc = ptf(PTF_HORIZONTAL);
 	if (rc)
 		return -EBUSY;
-	for_each_present_cpu(cpu)
+	for_each_possible_cpu(cpu)
 		smp_cpu_polarization[cpu] = POLARIZATION_UNKNWN;
 	return rc;
 }
@@ -208,7 +212,7 @@ static void update_cpu_core_map(void)
 {
 	int cpu;
 
-	for_each_present_cpu(cpu)
+	for_each_possible_cpu(cpu)
 		cpu_core_map[cpu] = cpu_coregroup_map(cpu);
 }
 
@@ -262,6 +266,15 @@ static void topology_interrupt(__u16 code)
 	schedule_work(&topology_work);
 }
 
+static int __init early_parse_topology(char *p)
+{
+	if (strncmp(p, "on", 2))
+		return 0;
+	topology_enabled = 1;
+	return 0;
+}
+early_param("topology", early_parse_topology);
+
 static int __init init_topology_update(void)
 {
 	int rc;
@@ -311,7 +324,7 @@ void __init s390_init_cpu_topology(void)
 	for (i = 0; i < info->mnest - 2; i++)
 		nr_cores *= info->mag[NR_MAG - 3 - i];
 
-	printk(KERN_INFO "CPU topology:");
+	pr_info("The CPU configuration topology of the machine is:");
 	for (i = 0; i < NR_MAG; i++)
 		printk(" %d", info->mag[i]);
 	printk(" / %d\n", info->mnest);
diff --git a/arch/s390/kernel/vdso.c b/arch/s390/kernel/vdso.c
new file mode 100644
index 000000000000..f3ba49020211
--- /dev/null
+++ b/arch/s390/kernel/vdso.c
@@ -0,0 +1,232 @@
+/*
+ * vdso setup for s390
+ *
+ *  Copyright IBM Corp. 2008
+ *  Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License (version 2 only)
+ * as published by the Free Software Foundation.
+ */
+
+#include <linux/module.h>
+#include <linux/errno.h>
+#include <linux/sched.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/smp.h>
+#include <linux/stddef.h>
+#include <linux/unistd.h>
+#include <linux/slab.h>
+#include <linux/user.h>
+#include <linux/elf.h>
+#include <linux/security.h>
+#include <linux/bootmem.h>
+
+#include <asm/pgtable.h>
+#include <asm/system.h>
+#include <asm/processor.h>
+#include <asm/mmu.h>
+#include <asm/mmu_context.h>
+#include <asm/sections.h>
+#include <asm/vdso.h>
+
+/* Max supported size for symbol names */
+#define MAX_SYMNAME	64
+
+#if defined(CONFIG_32BIT) || defined(CONFIG_COMPAT)
+extern char vdso32_start, vdso32_end;
+static void *vdso32_kbase = &vdso32_start;
+static unsigned int vdso32_pages;
+static struct page **vdso32_pagelist;
+#endif
+
+#ifdef CONFIG_64BIT
+extern char vdso64_start, vdso64_end;
+static void *vdso64_kbase = &vdso64_start;
+static unsigned int vdso64_pages;
+static struct page **vdso64_pagelist;
+#endif /* CONFIG_64BIT */
+
+/*
+ * Should the kernel map a VDSO page into processes and pass its
+ * address down to glibc upon exec()?
+ */
+unsigned int __read_mostly vdso_enabled = 1;
+
+static int __init vdso_setup(char *s)
+{
+	vdso_enabled = simple_strtoul(s, NULL, 0);
+	return 1;
+}
+__setup("vdso=", vdso_setup);
+
+/*
+ * The vdso data page
+ */
+static union {
+	struct vdso_data	data;
+	u8			page[PAGE_SIZE];
+} vdso_data_store __attribute__((__section__(".data.page_aligned")));
+struct vdso_data *vdso_data = &vdso_data_store.data;
+
+/*
+ * This is called from binfmt_elf, we create the special vma for the
+ * vDSO and insert it into the mm struct tree
+ */
+int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
+{
+	struct mm_struct *mm = current->mm;
+	struct page **vdso_pagelist;
+	unsigned long vdso_pages;
+	unsigned long vdso_base;
+	int rc;
+
+	/*
+	 * Only map the vdso for dynamically linked elf binaries.
+	 */
+	if (!uses_interp)
+		return 0;
+
+	vdso_base = mm->mmap_base;
+#ifdef CONFIG_64BIT
+	vdso_pagelist = vdso64_pagelist;
+	vdso_pages = vdso64_pages;
+#ifdef CONFIG_COMPAT
+	if (test_thread_flag(TIF_31BIT)) {
+		vdso_pagelist = vdso32_pagelist;
+		vdso_pages = vdso32_pages;
+	}
+#endif
+#else
+	vdso_pagelist = vdso32_pagelist;
+	vdso_pages = vdso32_pages;
+#endif
+
+	/*
+	 * vDSO has a problem and was disabled, just don't "enable" it for
+	 * the process
+	 */
+	if (vdso_pages == 0)
+		return 0;
+
+	current->mm->context.vdso_base = 0;
+
+	/*
+	 * pick a base address for the vDSO in process space. We try to put
+	 * it at vdso_base which is the "natural" base for it, but we might
+	 * fail and end up putting it elsewhere.
+	 */
+	down_write(&mm->mmap_sem);
+	vdso_base = get_unmapped_area(NULL, vdso_base,
+				      vdso_pages << PAGE_SHIFT, 0, 0);
+	if (IS_ERR_VALUE(vdso_base)) {
+		rc = vdso_base;
+		goto out_up;
+	}
+
+	/*
+	 * our vma flags don't have VM_WRITE so by default, the process
+	 * isn't allowed to write those pages.
+	 * gdb can break that with ptrace interface, and thus trigger COW
+	 * on those pages but it's then your responsibility to never do that
+	 * on the "data" page of the vDSO or you'll stop getting kernel
+	 * updates and your nice userland gettimeofday will be totally dead.
+	 * It's fine to use that for setting breakpoints in the vDSO code
+	 * pages though
+	 *
+	 * Make sure the vDSO gets into every core dump.
+	 * Dumping its contents makes post-mortem fully interpretable later
+	 * without matching up the same kernel and hardware config to see
+	 * what PC values meant.
+	 */
+	rc = install_special_mapping(mm, vdso_base, vdso_pages << PAGE_SHIFT,
+				     VM_READ|VM_EXEC|
+				     VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC|
+				     VM_ALWAYSDUMP,
+				     vdso_pagelist);
+	if (rc)
+		goto out_up;
+
+	/* Put vDSO base into mm struct */
+	current->mm->context.vdso_base = vdso_base;
+
+	up_write(&mm->mmap_sem);
+	return 0;
+
+out_up:
+	up_write(&mm->mmap_sem);
+	return rc;
+}
+
+const char *arch_vma_name(struct vm_area_struct *vma)
+{
+	if (vma->vm_mm && vma->vm_start == vma->vm_mm->context.vdso_base)
+		return "[vdso]";
+	return NULL;
+}
+
+static int __init vdso_init(void)
+{
+	int i;
+
+#if defined(CONFIG_32BIT) || defined(CONFIG_COMPAT)
+	/* Calculate the size of the 32 bit vDSO */
+	vdso32_pages = ((&vdso32_end - &vdso32_start
+			 + PAGE_SIZE - 1) >> PAGE_SHIFT) + 1;
+
+	/* Make sure pages are in the correct state */
+	vdso32_pagelist = kzalloc(sizeof(struct page *) * (vdso32_pages + 1),
+				  GFP_KERNEL);
+	BUG_ON(vdso32_pagelist == NULL);
+	for (i = 0; i < vdso32_pages - 1; i++) {
+		struct page *pg = virt_to_page(vdso32_kbase + i*PAGE_SIZE);
+		ClearPageReserved(pg);
+		get_page(pg);
+		vdso32_pagelist[i] = pg;
+	}
+	vdso32_pagelist[vdso32_pages - 1] = virt_to_page(vdso_data);
+	vdso32_pagelist[vdso32_pages] = NULL;
+#endif
+
+#ifdef CONFIG_64BIT
+	/* Calculate the size of the 64 bit vDSO */
+	vdso64_pages = ((&vdso64_end - &vdso64_start
+			 + PAGE_SIZE - 1) >> PAGE_SHIFT) + 1;
+
+	/* Make sure pages are in the correct state */
+	vdso64_pagelist = kzalloc(sizeof(struct page *) * (vdso64_pages + 1),
+				  GFP_KERNEL);
+	BUG_ON(vdso64_pagelist == NULL);
+	for (i = 0; i < vdso64_pages - 1; i++) {
+		struct page *pg = virt_to_page(vdso64_kbase + i*PAGE_SIZE);
+		ClearPageReserved(pg);
+		get_page(pg);
+		vdso64_pagelist[i] = pg;
+	}
+	vdso64_pagelist[vdso64_pages - 1] = virt_to_page(vdso_data);
+	vdso64_pagelist[vdso64_pages] = NULL;
+#endif /* CONFIG_64BIT */
+
+	get_page(virt_to_page(vdso_data));
+
+	smp_wmb();
+
+	return 0;
+}
+arch_initcall(vdso_init);
+
+int in_gate_area_no_task(unsigned long addr)
+{
+	return 0;
+}
+
+int in_gate_area(struct task_struct *task, unsigned long addr)
+{
+	return 0;
+}
+
+struct vm_area_struct *get_gate_vma(struct task_struct *tsk)
+{
+	return NULL;
+}
diff --git a/arch/s390/kernel/vdso32/Makefile b/arch/s390/kernel/vdso32/Makefile
new file mode 100644
index 000000000000..ca78ad60ba24
--- /dev/null
+++ b/arch/s390/kernel/vdso32/Makefile
@@ -0,0 +1,55 @@
+# List of files in the vdso, has to be asm only for now
+
+obj-vdso32 = gettimeofday.o clock_getres.o clock_gettime.o note.o
+
+# Build rules
+
+targets := $(obj-vdso32) vdso32.so vdso32.so.dbg
+obj-vdso32 := $(addprefix $(obj)/, $(obj-vdso32))
+
+KBUILD_AFLAGS_31 := $(filter-out -m64,$(KBUILD_AFLAGS))
+KBUILD_AFLAGS_31 += -m31 -s
+
+KBUILD_CFLAGS_31 := $(filter-out -m64,$(KBUILD_CFLAGS))
+KBUILD_CFLAGS_31 += -m31 -fPIC -shared -fno-common -fno-builtin
+KBUILD_CFLAGS_31 += -nostdlib -Wl,-soname=linux-vdso32.so.1 \
+			$(call ld-option, -Wl$(comma)--hash-style=sysv)
+
+$(targets:%=$(obj)/%.dbg): KBUILD_CFLAGS = $(KBUILD_CFLAGS_31)
+$(targets:%=$(obj)/%.dbg): KBUILD_AFLAGS = $(KBUILD_AFLAGS_31)
+
+obj-y += vdso32_wrapper.o
+extra-y += vdso32.lds
+CPPFLAGS_vdso32.lds += -P -C -U$(ARCH)
+
+# Force dependency (incbin is bad)
+$(obj)/vdso32_wrapper.o : $(obj)/vdso32.so
+
+# link rule for the .so file, .lds has to be first
+$(obj)/vdso32.so.dbg: $(src)/vdso32.lds $(obj-vdso32)
+	$(call if_changed,vdso32ld)
+
+# strip rule for the .so file
+$(obj)/%.so: OBJCOPYFLAGS := -S
+$(obj)/%.so: $(obj)/%.so.dbg FORCE
+	$(call if_changed,objcopy)
+
+# assembly rules for the .S files
+$(obj-vdso32): %.o: %.S
+	$(call if_changed_dep,vdso32as)
+
+# actual build commands
+quiet_cmd_vdso32ld = VDSO32L $@
+      cmd_vdso32ld = $(CC) $(c_flags) -Wl,-T $^ -o $@
+quiet_cmd_vdso32as = VDSO32A $@
+      cmd_vdso32as = $(CC) $(a_flags) -c -o $@ $<
+
+# install commands for the unstripped file
+quiet_cmd_vdso_install = INSTALL $@
+      cmd_vdso_install = cp $(obj)/$@.dbg $(MODLIB)/vdso/$@
+
+vdso32.so: $(obj)/vdso32.so.dbg
+	@mkdir -p $(MODLIB)/vdso
+	$(call cmd,vdso_install)
+
+vdso_install: vdso32.so
diff --git a/arch/s390/kernel/vdso32/clock_getres.S b/arch/s390/kernel/vdso32/clock_getres.S
new file mode 100644
index 000000000000..9532c4e6a9d2
--- /dev/null
+++ b/arch/s390/kernel/vdso32/clock_getres.S
@@ -0,0 +1,39 @@
+/*
+ * Userland implementation of clock_getres() for 32 bits processes in a
+ * s390 kernel for use in the vDSO
+ *
+ *  Copyright IBM Corp. 2008
+ *  Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License (version 2 only)
+ * as published by the Free Software Foundation.
+ */
+#include <asm/vdso.h>
+#include <asm/asm-offsets.h>
+#include <asm/unistd.h>
+
+	.text
+	.align 4
+	.globl __kernel_clock_getres
+	.type  __kernel_clock_getres,@function
+__kernel_clock_getres:
+	.cfi_startproc
+	chi	%r2,CLOCK_REALTIME
+	je	0f
+	chi	%r2,CLOCK_MONOTONIC
+	jne	3f
+0:	ltr	%r3,%r3
+	jz	2f				/* res == NULL */
+	basr	%r1,0
+1:	l	%r0,4f-1b(%r1)
+	xc	0(4,%r3),0(%r3)			/* set tp->tv_sec to zero */
+	st	%r0,4(%r3)			/* store tp->tv_usec */
+2:	lhi	%r2,0
+	br	%r14
+3:	lhi	%r1,__NR_clock_getres		/* fallback to svc */
+	svc	0
+	br	%r14
+4:	.long	CLOCK_REALTIME_RES
+	.cfi_endproc
+	.size	__kernel_clock_getres,.-__kernel_clock_getres
diff --git a/arch/s390/kernel/vdso32/clock_gettime.S b/arch/s390/kernel/vdso32/clock_gettime.S
new file mode 100644
index 000000000000..4a98909a8310
--- /dev/null
+++ b/arch/s390/kernel/vdso32/clock_gettime.S
@@ -0,0 +1,128 @@
+/*
+ * Userland implementation of clock_gettime() for 32 bits processes in a
+ * s390 kernel for use in the vDSO
+ *
+ *  Copyright IBM Corp. 2008
+ *  Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License (version 2 only)
+ * as published by the Free Software Foundation.
+ */
+#include <asm/vdso.h>
+#include <asm/asm-offsets.h>
+#include <asm/unistd.h>
+
+	.text
+	.align 4
+	.globl __kernel_clock_gettime
+	.type  __kernel_clock_gettime,@function
+__kernel_clock_gettime:
+	.cfi_startproc
+	basr	%r5,0
+0:	al	%r5,21f-0b(%r5)			/* get &_vdso_data */
+	chi	%r2,CLOCK_REALTIME
+	je	10f
+	chi	%r2,CLOCK_MONOTONIC
+	jne	19f
+
+	/* CLOCK_MONOTONIC */
+	ltr	%r3,%r3
+	jz	9f				/* tp == NULL */
+1:	l	%r4,__VDSO_UPD_COUNT+4(%r5)	/* load update counter */
+	tml	%r4,0x0001			/* pending update ? loop */
+	jnz	1b
+	stck	24(%r15)			/* Store TOD clock */
+	lm	%r0,%r1,24(%r15)
+	s	%r0,__VDSO_XTIME_STAMP(%r5)	/* TOD - cycle_last */
+	sl	%r1,__VDSO_XTIME_STAMP+4(%r5)
+	brc	3,2f
+	ahi	%r0,-1
+2:	mhi	%r0,1000			/* cyc2ns(clock,cycle_delta) */
+	lr	%r2,%r0
+	lhi	%r0,1000
+	ltr	%r1,%r1
+	mr	%r0,%r0
+	jnm	3f
+	ahi	%r0,1000
+3:	alr	%r0,%r2
+	srdl	%r0,12
+	al	%r0,__VDSO_XTIME_NSEC(%r5)	/*  + xtime */
+	al	%r1,__VDSO_XTIME_NSEC+4(%r5)
+	brc	12,4f
+	ahi	%r0,1
+4:	l	%r2,__VDSO_XTIME_SEC+4(%r5)
+	al	%r0,__VDSO_WTOM_NSEC(%r5)	/*  + wall_to_monotonic */
+	al	%r1,__VDSO_WTOM_NSEC+4(%r5)
+	brc	12,5f
+	ahi	%r0,1
+5:	al	%r2,__VDSO_WTOM_SEC+4(%r5)
+	cl	%r4,__VDSO_UPD_COUNT+4(%r5)	/* check update counter */
+	jne	1b
+	basr	%r5,0
+6:	ltr	%r0,%r0
+	jnz	7f
+	cl	%r1,20f-6b(%r5)
+	jl	8f
+7:	ahi	%r2,1
+	sl	%r1,20f-6b(%r5)
+	brc	3,6b
+	ahi	%r0,-1
+	j	6b
+8:	st	%r2,0(%r3)			/* store tp->tv_sec */
+	st	%r1,4(%r3)			/* store tp->tv_nsec */
+9:	lhi	%r2,0
+	br	%r14
+
+	/* CLOCK_REALTIME */
+10:	ltr	%r3,%r3				/* tp == NULL */
+	jz	18f
+11:	l	%r4,__VDSO_UPD_COUNT+4(%r5)	/* load update counter */
+	tml	%r4,0x0001			/* pending update ? loop */
+	jnz	11b
+	stck	24(%r15)			/* Store TOD clock */
+	lm	%r0,%r1,24(%r15)
+	s	%r0,__VDSO_XTIME_STAMP(%r5)	/* TOD - cycle_last */
+	sl	%r1,__VDSO_XTIME_STAMP+4(%r5)
+	brc	3,12f
+	ahi	%r0,-1
+12:	mhi	%r0,1000			/* cyc2ns(clock,cycle_delta) */
+	lr	%r2,%r0
+	lhi	%r0,1000
+	ltr	%r1,%r1
+	mr	%r0,%r0
+	jnm	13f
+	ahi	%r0,1000
+13:	alr	%r0,%r2
+	srdl	%r0,12
+	al	%r0,__VDSO_XTIME_NSEC(%r5)	/*  + xtime */
+	al	%r1,__VDSO_XTIME_NSEC+4(%r5)
+	brc	12,14f
+	ahi	%r0,1
+14:	l	%r2,__VDSO_XTIME_SEC+4(%r5)
+	cl	%r4,__VDSO_UPD_COUNT+4(%r5)	/* check update counter */
+	jne	11b
+	basr	%r5,0
+15:	ltr	%r0,%r0
+	jnz	16f
+	cl	%r1,20f-15b(%r5)
+	jl	17f
+16:	ahi	%r2,1
+	sl	%r1,20f-15b(%r5)
+	brc	3,15b
+	ahi	%r0,-1
+	j	15b
+17:	st	%r2,0(%r3)			/* store tp->tv_sec */
+	st	%r1,4(%r3)			/* store tp->tv_nsec */
+18:	lhi	%r2,0
+	br	%r14
+
+	/* Fallback to system call */
+19:	lhi	%r1,__NR_clock_gettime
+	svc	0
+	br	%r14
+
+20:	.long	1000000000
+21:	.long	_vdso_data - 0b
+	.cfi_endproc
+	.size	__kernel_clock_gettime,.-__kernel_clock_gettime
diff --git a/arch/s390/kernel/vdso32/gettimeofday.S b/arch/s390/kernel/vdso32/gettimeofday.S
new file mode 100644
index 000000000000..c32f29c3d70c
--- /dev/null
+++ b/arch/s390/kernel/vdso32/gettimeofday.S
@@ -0,0 +1,82 @@
+/*
+ * Userland implementation of gettimeofday() for 32 bits processes in a
+ * s390 kernel for use in the vDSO
+ *
+ *  Copyright IBM Corp. 2008
+ *  Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License (version 2 only)
+ * as published by the Free Software Foundation.
+ */
+#include <asm/vdso.h>
+#include <asm/asm-offsets.h>
+#include <asm/unistd.h>
+
+#include <asm/vdso.h>
+#include <asm/asm-offsets.h>
+#include <asm/unistd.h>
+
+	.text
+	.align 4
+	.globl __kernel_gettimeofday
+	.type  __kernel_gettimeofday,@function
+__kernel_gettimeofday:
+	.cfi_startproc
+	basr	%r5,0
+0:	al	%r5,13f-0b(%r5)			/* get &_vdso_data */
+1:	ltr	%r3,%r3				/* check if tz is NULL */
+	je	2f
+	mvc	0(8,%r3),__VDSO_TIMEZONE(%r5)
+2:	ltr	%r2,%r2				/* check if tv is NULL */
+	je	10f
+	l	%r4,__VDSO_UPD_COUNT+4(%r5)	/* load update counter */
+	tml	%r4,0x0001			/* pending update ? loop */
+	jnz	1b
+	stck	24(%r15)			/* Store TOD clock */
+	lm	%r0,%r1,24(%r15)
+	s	%r0,__VDSO_XTIME_STAMP(%r5)	/* TOD - cycle_last */
+	sl	%r1,__VDSO_XTIME_STAMP+4(%r5)
+	brc	3,3f
+	ahi	%r0,-1
+3:	mhi	%r0,1000			/* cyc2ns(clock,cycle_delta) */
+	st	%r0,24(%r15)
+	lhi	%r0,1000
+	ltr	%r1,%r1
+	mr	%r0,%r0
+	jnm	4f
+	ahi	%r0,1000
+4:	al	%r0,24(%r15)
+	srdl	%r0,12
+	al	%r0,__VDSO_XTIME_NSEC(%r5)	/*  + xtime */
+	al	%r1,__VDSO_XTIME_NSEC+4(%r5)
+	brc	12,5f
+	ahi	%r0,1
+5:	mvc	24(4,%r15),__VDSO_XTIME_SEC+4(%r5)
+	cl	%r4,__VDSO_UPD_COUNT+4(%r5)	/* check update counter */
+	jne	1b
+	l	%r4,24(%r15)			/* get tv_sec from stack */
+	basr	%r5,0
+6:	ltr	%r0,%r0
+	jnz	7f
+	cl	%r1,11f-6b(%r5)
+	jl	8f
+7:	ahi	%r4,1
+	sl	%r1,11f-6b(%r5)
+	brc	3,6b
+	ahi	%r0,-1
+	j	6b
+8:	st	%r4,0(%r2)			/* store tv->tv_sec */
+	ltr	%r1,%r1
+	m	%r0,12f-6b(%r5)
+	jnm	9f
+	al	%r0,12f-6b(%r5)
+9:	srl	%r0,6
+	st	%r0,4(%r2)			/* store tv->tv_usec */
+10:	slr	%r2,%r2
+	br	%r14
+11:	.long	1000000000
+12:	.long	274877907
+13:	.long	_vdso_data - 0b
+	.cfi_endproc
+	.size	__kernel_gettimeofday,.-__kernel_gettimeofday
diff --git a/arch/s390/kernel/vdso32/note.S b/arch/s390/kernel/vdso32/note.S
new file mode 100644
index 000000000000..79a071e4357e
--- /dev/null
+++ b/arch/s390/kernel/vdso32/note.S
@@ -0,0 +1,12 @@
+/*
+ * This supplies .note.* sections to go into the PT_NOTE inside the vDSO text.
+ * Here we can supply some information useful to userland.
+ */
+
+#include <linux/uts.h>
+#include <linux/version.h>
+#include <linux/elfnote.h>
+
+ELFNOTE_START(Linux, 0, "a")
+	.long LINUX_VERSION_CODE
+ELFNOTE_END
diff --git a/arch/s390/kernel/vdso32/vdso32.lds.S b/arch/s390/kernel/vdso32/vdso32.lds.S
new file mode 100644
index 000000000000..a8c379fa1247
--- /dev/null
+++ b/arch/s390/kernel/vdso32/vdso32.lds.S
@@ -0,0 +1,138 @@
+/*
+ * This is the infamous ld script for the 32 bits vdso
+ * library
+ */
+#include <asm/vdso.h>
+
+OUTPUT_FORMAT("elf32-s390", "elf32-s390", "elf32-s390")
+OUTPUT_ARCH(s390:31-bit)
+ENTRY(_start)
+
+SECTIONS
+{
+	. = VDSO32_LBASE + SIZEOF_HEADERS;
+
+	.hash		: { *(.hash) }			:text
+	.gnu.hash	: { *(.gnu.hash) }
+	.dynsym		: { *(.dynsym) }
+	.dynstr		: { *(.dynstr) }
+	.gnu.version	: { *(.gnu.version) }
+	.gnu.version_d	: { *(.gnu.version_d) }
+	.gnu.version_r	: { *(.gnu.version_r) }
+
+	.note		: { *(.note.*) }		:text	:note
+
+	. = ALIGN(16);
+	.text		: {
+		*(.text .stub .text.* .gnu.linkonce.t.*)
+	} :text
+	PROVIDE(__etext = .);
+	PROVIDE(_etext = .);
+	PROVIDE(etext = .);
+
+	/*
+	 * Other stuff is appended to the text segment:
+	 */
+	.rodata		: { *(.rodata .rodata.* .gnu.linkonce.r.*) }
+	.rodata1	: { *(.rodata1) }
+
+	.dynamic	: { *(.dynamic) }		:text	:dynamic
+
+	.eh_frame_hdr	: { *(.eh_frame_hdr) }		:text	:eh_frame_hdr
+	.eh_frame	: { KEEP (*(.eh_frame)) }	:text
+	.gcc_except_table : { *(.gcc_except_table .gcc_except_table.*) }
+
+	.rela.dyn ALIGN(8) : { *(.rela.dyn) }
+	.got ALIGN(8)	: { *(.got .toc) }
+
+	_end = .;
+	PROVIDE(end = .);
+
+	/*
+	 * Stabs debugging sections are here too.
+	 */
+	.stab	       0 : { *(.stab) }
+	.stabstr       0 : { *(.stabstr) }
+	.stab.excl     0 : { *(.stab.excl) }
+	.stab.exclstr  0 : { *(.stab.exclstr) }
+	.stab.index    0 : { *(.stab.index) }
+	.stab.indexstr 0 : { *(.stab.indexstr) }
+	.comment       0 : { *(.comment) }
+
+	/*
+	 * DWARF debug sections.
+	 * Symbols in the DWARF debugging sections are relative to the
+	 * beginning of the section so we begin them at 0.
+	 */
+	/* DWARF 1 */
+	.debug		0 : { *(.debug) }
+	.line		0 : { *(.line) }
+	/* GNU DWARF 1 extensions */
+	.debug_srcinfo	0 : { *(.debug_srcinfo) }
+	.debug_sfnames	0 : { *(.debug_sfnames) }
+	/* DWARF 1.1 and DWARF 2 */
+	.debug_aranges	0 : { *(.debug_aranges) }
+	.debug_pubnames 0 : { *(.debug_pubnames) }
+	/* DWARF 2 */
+	.debug_info	0 : { *(.debug_info .gnu.linkonce.wi.*) }
+	.debug_abbrev	0 : { *(.debug_abbrev) }
+	.debug_line	0 : { *(.debug_line) }
+	.debug_frame	0 : { *(.debug_frame) }
+	.debug_str	0 : { *(.debug_str) }
+	.debug_loc	0 : { *(.debug_loc) }
+	.debug_macinfo	0 : { *(.debug_macinfo) }
+	/* SGI/MIPS DWARF 2 extensions */
+	.debug_weaknames 0 : { *(.debug_weaknames) }
+	.debug_funcnames 0 : { *(.debug_funcnames) }
+	.debug_typenames 0 : { *(.debug_typenames) }
+	.debug_varnames  0 : { *(.debug_varnames) }
+	/* DWARF 3 */
+	.debug_pubtypes 0 : { *(.debug_pubtypes) }
+	.debug_ranges	0 : { *(.debug_ranges) }
+	.gnu.attributes 0 : { KEEP (*(.gnu.attributes)) }
+
+	. = ALIGN(4096);
+	PROVIDE(_vdso_data = .);
+
+	/DISCARD/	: {
+		*(.note.GNU-stack)
+		*(.branch_lt)
+		*(.data .data.* .gnu.linkonce.d.* .sdata*)
+		*(.bss .sbss .dynbss .dynsbss)
+	}
+}
+
+/*
+ * Very old versions of ld do not recognize this name token; use the constant.
+ */
+#define PT_GNU_EH_FRAME	0x6474e550
+
+/*
+ * We must supply the ELF program headers explicitly to get just one
+ * PT_LOAD segment, and set the flags explicitly to make segments read-only.
+ */
+PHDRS
+{
+	text		PT_LOAD FILEHDR PHDRS FLAGS(5);	/* PF_R|PF_X */
+	dynamic		PT_DYNAMIC FLAGS(4);		/* PF_R */
+	note		PT_NOTE FLAGS(4);		/* PF_R */
+	eh_frame_hdr	PT_GNU_EH_FRAME;
+}
+
+/*
+ * This controls what symbols we export from the DSO.
+ */
+VERSION
+{
+	VDSO_VERSION_STRING {
+	global:
+		/*
+		 * Has to be there for the kernel to find
+		 */
+		__kernel_gettimeofday;
+		__kernel_clock_gettime;
+		__kernel_clock_getres;
+
+	local: *;
+	};
+}
diff --git a/arch/s390/kernel/vdso32/vdso32_wrapper.S b/arch/s390/kernel/vdso32/vdso32_wrapper.S
new file mode 100644
index 000000000000..61639a89e70b
--- /dev/null
+++ b/arch/s390/kernel/vdso32/vdso32_wrapper.S
@@ -0,0 +1,13 @@
+#include <linux/init.h>
+#include <asm/page.h>
+
+	.section ".data.page_aligned"
+
+	.globl vdso32_start, vdso32_end
+	.balign PAGE_SIZE
+vdso32_start:
+	.incbin "arch/s390/kernel/vdso32/vdso32.so"
+	.balign PAGE_SIZE
+vdso32_end:
+
+	.previous
diff --git a/arch/s390/kernel/vdso64/Makefile b/arch/s390/kernel/vdso64/Makefile
new file mode 100644
index 000000000000..6fc8e829258c
--- /dev/null
+++ b/arch/s390/kernel/vdso64/Makefile
@@ -0,0 +1,55 @@
+# List of files in the vdso, has to be asm only for now
+
+obj-vdso64 = gettimeofday.o clock_getres.o clock_gettime.o note.o
+
+# Build rules
+
+targets := $(obj-vdso64) vdso64.so vdso64.so.dbg
+obj-vdso64 := $(addprefix $(obj)/, $(obj-vdso64))
+
+KBUILD_AFLAGS_64 := $(filter-out -m64,$(KBUILD_AFLAGS))
+KBUILD_AFLAGS_64 += -m64 -s
+
+KBUILD_CFLAGS_64 := $(filter-out -m64,$(KBUILD_CFLAGS))
+KBUILD_CFLAGS_64 += -m64 -fPIC -shared -fno-common -fno-builtin
+KBUILD_CFLAGS_64 += -nostdlib -Wl,-soname=linux-vdso64.so.1 \
+			$(call ld-option, -Wl$(comma)--hash-style=sysv)
+
+$(targets:%=$(obj)/%.dbg): KBUILD_CFLAGS = $(KBUILD_CFLAGS_64)
+$(targets:%=$(obj)/%.dbg): KBUILD_AFLAGS = $(KBUILD_AFLAGS_64)
+
+obj-y += vdso64_wrapper.o
+extra-y += vdso64.lds
+CPPFLAGS_vdso64.lds += -P -C -U$(ARCH)
+
+# Force dependency (incbin is bad)
+$(obj)/vdso64_wrapper.o : $(obj)/vdso64.so
+
+# link rule for the .so file, .lds has to be first
+$(obj)/vdso64.so.dbg: $(src)/vdso64.lds $(obj-vdso64)
+	$(call if_changed,vdso64ld)
+
+# strip rule for the .so file
+$(obj)/%.so: OBJCOPYFLAGS := -S
+$(obj)/%.so: $(obj)/%.so.dbg FORCE
+	$(call if_changed,objcopy)
+
+# assembly rules for the .S files
+$(obj-vdso64): %.o: %.S
+	$(call if_changed_dep,vdso64as)
+
+# actual build commands
+quiet_cmd_vdso64ld = VDSO64L $@
+      cmd_vdso64ld = $(CC) $(c_flags) -Wl,-T $^ -o $@
+quiet_cmd_vdso64as = VDSO64A $@
+      cmd_vdso64as = $(CC) $(a_flags) -c -o $@ $<
+
+# install commands for the unstripped file
+quiet_cmd_vdso_install = INSTALL $@
+      cmd_vdso_install = cp $(obj)/$@.dbg $(MODLIB)/vdso/$@
+
+vdso64.so: $(obj)/vdso64.so.dbg
+	@mkdir -p $(MODLIB)/vdso
+	$(call cmd,vdso_install)
+
+vdso_install: vdso64.so
diff --git a/arch/s390/kernel/vdso64/clock_getres.S b/arch/s390/kernel/vdso64/clock_getres.S
new file mode 100644
index 000000000000..488e31a3c0e7
--- /dev/null
+++ b/arch/s390/kernel/vdso64/clock_getres.S
@@ -0,0 +1,39 @@
+/*
+ * Userland implementation of clock_getres() for 64 bits processes in a
+ * s390 kernel for use in the vDSO
+ *
+ *  Copyright IBM Corp. 2008
+ *  Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License (version 2 only)
+ * as published by the Free Software Foundation.
+ */
+#include <asm/vdso.h>
+#include <asm/asm-offsets.h>
+#include <asm/unistd.h>
+
+	.text
+	.align 4
+	.globl __kernel_clock_getres
+	.type  __kernel_clock_getres,@function
+__kernel_clock_getres:
+	.cfi_startproc
+	cghi	%r2,CLOCK_REALTIME
+	je	0f
+	cghi	%r2,CLOCK_MONOTONIC
+	jne	2f
+0:	ltgr	%r3,%r3
+	jz	1f				/* res == NULL */
+	larl	%r1,3f
+	lg	%r0,0(%r1)
+	xc	0(8,%r3),0(%r3)			/* set tp->tv_sec to zero */
+	stg	%r0,8(%r3)			/* store tp->tv_usec */
+1:	lghi	%r2,0
+	br	%r14
+2:	lghi	%r1,__NR_clock_getres		/* fallback to svc */
+	svc	0
+	br	%r14
+3:	.quad	CLOCK_REALTIME_RES
+	.cfi_endproc
+	.size	__kernel_clock_getres,.-__kernel_clock_getres
diff --git a/arch/s390/kernel/vdso64/clock_gettime.S b/arch/s390/kernel/vdso64/clock_gettime.S
new file mode 100644
index 000000000000..738a410b7eb2
--- /dev/null
+++ b/arch/s390/kernel/vdso64/clock_gettime.S
@@ -0,0 +1,89 @@
+/*
+ * Userland implementation of clock_gettime() for 64 bits processes in a
+ * s390 kernel for use in the vDSO
+ *
+ *  Copyright IBM Corp. 2008
+ *  Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License (version 2 only)
+ * as published by the Free Software Foundation.
+ */
+#include <asm/vdso.h>
+#include <asm/asm-offsets.h>
+#include <asm/unistd.h>
+
+	.text
+	.align 4
+	.globl __kernel_clock_gettime
+	.type  __kernel_clock_gettime,@function
+__kernel_clock_gettime:
+	.cfi_startproc
+	larl	%r5,_vdso_data
+	cghi	%r2,CLOCK_REALTIME
+	je	4f
+	cghi	%r2,CLOCK_MONOTONIC
+	jne	9f
+
+	/* CLOCK_MONOTONIC */
+	ltgr	%r3,%r3
+	jz	3f				/* tp == NULL */
+0:	lg	%r4,__VDSO_UPD_COUNT(%r5)	/* load update counter */
+	tmll	%r4,0x0001			/* pending update ? loop */
+	jnz	0b
+	stck	48(%r15)			/* Store TOD clock */
+	lg	%r1,48(%r15)
+	sg	%r1,__VDSO_XTIME_STAMP(%r5)	/* TOD - cycle_last */
+	mghi	%r1,1000
+	srlg	%r1,%r1,12			/* cyc2ns(clock,cycle_delta) */
+	alg	%r1,__VDSO_XTIME_NSEC(%r5)	/*  + xtime */
+	lg	%r0,__VDSO_XTIME_SEC(%r5)
+	alg	%r1,__VDSO_WTOM_NSEC(%r5)	/*  + wall_to_monotonic */
+	alg	%r0,__VDSO_WTOM_SEC(%r5)
+	clg	%r4,__VDSO_UPD_COUNT(%r5)	/* check update counter */
+	jne	0b
+	larl	%r5,10f
+1:	clg	%r1,0(%r5)
+	jl	2f
+	slg	%r1,0(%r5)
+	aghi	%r0,1
+	j	1b
+2:	stg	%r0,0(%r3)			/* store tp->tv_sec */
+	stg	%r1,8(%r3)			/* store tp->tv_nsec */
+3:	lghi	%r2,0
+	br	%r14
+
+	/* CLOCK_REALTIME */
+4:	ltr	%r3,%r3				/* tp == NULL */
+	jz	8f
+5:	lg	%r4,__VDSO_UPD_COUNT(%r5)	/* load update counter */
+	tmll	%r4,0x0001			/* pending update ? loop */
+	jnz	5b
+	stck	48(%r15)			/* Store TOD clock */
+	lg	%r1,48(%r15)
+	sg	%r1,__VDSO_XTIME_STAMP(%r5)	/* TOD - cycle_last */
+	mghi	%r1,1000
+	srlg	%r1,%r1,12			/* cyc2ns(clock,cycle_delta) */
+	alg	%r1,__VDSO_XTIME_NSEC(%r5)	/*  + xtime */
+	lg	%r0,__VDSO_XTIME_SEC(%r5)
+	clg	%r4,__VDSO_UPD_COUNT(%r5)	/* check update counter */
+	jne	5b
+	larl	%r5,10f
+6:	clg	%r1,0(%r5)
+	jl	7f
+	slg	%r1,0(%r5)
+	aghi	%r0,1
+	j	6b
+7:	stg	%r0,0(%r3)			/* store tp->tv_sec */
+	stg	%r1,8(%r3)			/* store tp->tv_nsec */
+8:	lghi	%r2,0
+	br	%r14
+
+	/* Fallback to system call */
+9:	lghi	%r1,__NR_clock_gettime
+	svc	0
+	br	%r14
+
+10:	.quad	1000000000
+	.cfi_endproc
+	.size	__kernel_clock_gettime,.-__kernel_clock_gettime
diff --git a/arch/s390/kernel/vdso64/gettimeofday.S b/arch/s390/kernel/vdso64/gettimeofday.S
new file mode 100644
index 000000000000..f873e75634e1
--- /dev/null
+++ b/arch/s390/kernel/vdso64/gettimeofday.S
@@ -0,0 +1,56 @@
+/*
+ * Userland implementation of gettimeofday() for 64 bits processes in a
+ * s390 kernel for use in the vDSO
+ *
+ *  Copyright IBM Corp. 2008
+ *  Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License (version 2 only)
+ * as published by the Free Software Foundation.
+ */
+#include <asm/vdso.h>
+#include <asm/asm-offsets.h>
+#include <asm/unistd.h>
+
+	.text
+	.align 4
+	.globl __kernel_gettimeofday
+	.type  __kernel_gettimeofday,@function
+__kernel_gettimeofday:
+	.cfi_startproc
+	larl	%r5,_vdso_data
+0:	ltgr	%r3,%r3				/* check if tz is NULL */
+	je	1f
+	mvc	0(8,%r3),__VDSO_TIMEZONE(%r5)
+1:	ltgr	%r2,%r2				/* check if tv is NULL */
+	je	4f
+	lg	%r4,__VDSO_UPD_COUNT(%r5)	/* load update counter */
+	tmll	%r4,0x0001			/* pending update ? loop */
+	jnz	0b
+	stck	48(%r15)			/* Store TOD clock */
+	lg	%r1,48(%r15)
+	sg	%r1,__VDSO_XTIME_STAMP(%r5)	/* TOD - cycle_last */
+	mghi	%r1,1000
+	srlg	%r1,%r1,12			/* cyc2ns(clock,cycle_delta) */
+	alg	%r1,__VDSO_XTIME_NSEC(%r5)	/*  + xtime.tv_nsec */
+	lg	%r0,__VDSO_XTIME_SEC(%r5)	/* xtime.tv_sec */
+	clg	%r4,__VDSO_UPD_COUNT(%r5)	/* check update counter */
+	jne	0b
+	larl	%r5,5f
+2:	clg	%r1,0(%r5)
+	jl	3f
+	slg	%r1,0(%r5)
+	aghi	%r0,1
+	j	2b
+3:	stg	%r0,0(%r2)			/* store tv->tv_sec */
+	slgr	%r0,%r0				/* tv_nsec -> tv_usec */
+	ml	%r0,8(%r5)
+	srlg	%r0,%r0,6
+	stg	%r0,8(%r2)			/* store tv->tv_usec */
+4:	lghi	%r2,0
+	br	%r14
+5:	.quad	1000000000
+	.long	274877907
+	.cfi_endproc
+	.size	__kernel_gettimeofday,.-__kernel_gettimeofday
diff --git a/arch/s390/kernel/vdso64/note.S b/arch/s390/kernel/vdso64/note.S
new file mode 100644
index 000000000000..79a071e4357e
--- /dev/null
+++ b/arch/s390/kernel/vdso64/note.S
@@ -0,0 +1,12 @@
+/*
+ * This supplies .note.* sections to go into the PT_NOTE inside the vDSO text.
+ * Here we can supply some information useful to userland.
+ */
+
+#include <linux/uts.h>
+#include <linux/version.h>
+#include <linux/elfnote.h>
+
+ELFNOTE_START(Linux, 0, "a")
+	.long LINUX_VERSION_CODE
+ELFNOTE_END
diff --git a/arch/s390/kernel/vdso64/vdso64.lds.S b/arch/s390/kernel/vdso64/vdso64.lds.S
new file mode 100644
index 000000000000..9f5979d102a9
--- /dev/null
+++ b/arch/s390/kernel/vdso64/vdso64.lds.S
@@ -0,0 +1,138 @@
+/*
+ * This is the infamous ld script for the 64 bits vdso
+ * library
+ */
+#include <asm/vdso.h>
+
+OUTPUT_FORMAT("elf64-s390", "elf64-s390", "elf64-s390")
+OUTPUT_ARCH(s390:64-bit)
+ENTRY(_start)
+
+SECTIONS
+{
+	. = VDSO64_LBASE + SIZEOF_HEADERS;
+
+	.hash		: { *(.hash) }			:text
+	.gnu.hash	: { *(.gnu.hash) }
+	.dynsym		: { *(.dynsym) }
+	.dynstr		: { *(.dynstr) }
+	.gnu.version	: { *(.gnu.version) }
+	.gnu.version_d	: { *(.gnu.version_d) }
+	.gnu.version_r	: { *(.gnu.version_r) }
+
+	.note		: { *(.note.*) }		:text	:note
+
+	. = ALIGN(16);
+	.text		: {
+		*(.text .stub .text.* .gnu.linkonce.t.*)
+	} :text
+	PROVIDE(__etext = .);
+	PROVIDE(_etext = .);
+	PROVIDE(etext = .);
+
+	/*
+	 * Other stuff is appended to the text segment:
+	 */
+	.rodata		: { *(.rodata .rodata.* .gnu.linkonce.r.*) }
+	.rodata1	: { *(.rodata1) }
+
+	.dynamic	: { *(.dynamic) }		:text	:dynamic
+
+	.eh_frame_hdr	: { *(.eh_frame_hdr) }		:text	:eh_frame_hdr
+	.eh_frame	: { KEEP (*(.eh_frame)) }	:text
+	.gcc_except_table : { *(.gcc_except_table .gcc_except_table.*) }
+
+	.rela.dyn ALIGN(8) : { *(.rela.dyn) }
+	.got ALIGN(8)	: { *(.got .toc) }
+
+	_end = .;
+	PROVIDE(end = .);
+
+	/*
+	 * Stabs debugging sections are here too.
+	 */
+	.stab	       0 : { *(.stab) }
+	.stabstr       0 : { *(.stabstr) }
+	.stab.excl     0 : { *(.stab.excl) }
+	.stab.exclstr  0 : { *(.stab.exclstr) }
+	.stab.index    0 : { *(.stab.index) }
+	.stab.indexstr 0 : { *(.stab.indexstr) }
+	.comment       0 : { *(.comment) }
+
+	/*
+	 * DWARF debug sections.
+	 * Symbols in the DWARF debugging sections are relative to the
+	 * beginning of the section so we begin them at 0.
+	 */
+	/* DWARF 1 */
+	.debug		0 : { *(.debug) }
+	.line		0 : { *(.line) }
+	/* GNU DWARF 1 extensions */
+	.debug_srcinfo	0 : { *(.debug_srcinfo) }
+	.debug_sfnames	0 : { *(.debug_sfnames) }
+	/* DWARF 1.1 and DWARF 2 */
+	.debug_aranges	0 : { *(.debug_aranges) }
+	.debug_pubnames 0 : { *(.debug_pubnames) }
+	/* DWARF 2 */
+	.debug_info	0 : { *(.debug_info .gnu.linkonce.wi.*) }
+	.debug_abbrev	0 : { *(.debug_abbrev) }
+	.debug_line	0 : { *(.debug_line) }
+	.debug_frame	0 : { *(.debug_frame) }
+	.debug_str	0 : { *(.debug_str) }
+	.debug_loc	0 : { *(.debug_loc) }
+	.debug_macinfo	0 : { *(.debug_macinfo) }
+	/* SGI/MIPS DWARF 2 extensions */
+	.debug_weaknames 0 : { *(.debug_weaknames) }
+	.debug_funcnames 0 : { *(.debug_funcnames) }
+	.debug_typenames 0 : { *(.debug_typenames) }
+	.debug_varnames  0 : { *(.debug_varnames) }
+	/* DWARF 3 */
+	.debug_pubtypes 0 : { *(.debug_pubtypes) }
+	.debug_ranges	0 : { *(.debug_ranges) }
+	.gnu.attributes 0 : { KEEP (*(.gnu.attributes)) }
+
+	. = ALIGN(4096);
+	PROVIDE(_vdso_data = .);
+
+	/DISCARD/	: {
+		*(.note.GNU-stack)
+		*(.branch_lt)
+		*(.data .data.* .gnu.linkonce.d.* .sdata*)
+		*(.bss .sbss .dynbss .dynsbss)
+	}
+}
+
+/*
+ * Very old versions of ld do not recognize this name token; use the constant.
+ */
+#define PT_GNU_EH_FRAME	0x6474e550
+
+/*
+ * We must supply the ELF program headers explicitly to get just one
+ * PT_LOAD segment, and set the flags explicitly to make segments read-only.
+ */
+PHDRS
+{
+	text		PT_LOAD FILEHDR PHDRS FLAGS(5);	/* PF_R|PF_X */
+	dynamic		PT_DYNAMIC FLAGS(4);		/* PF_R */
+	note		PT_NOTE FLAGS(4);		/* PF_R */
+	eh_frame_hdr	PT_GNU_EH_FRAME;
+}
+
+/*
+ * This controls what symbols we export from the DSO.
+ */
+VERSION
+{
+	VDSO_VERSION_STRING {
+	global:
+		/*
+		 * Has to be there for the kernel to find
+		 */
+		__kernel_gettimeofday;
+		__kernel_clock_gettime;
+		__kernel_clock_getres;
+
+	local: *;
+	};
+}
diff --git a/arch/s390/kernel/vdso64/vdso64_wrapper.S b/arch/s390/kernel/vdso64/vdso64_wrapper.S
new file mode 100644
index 000000000000..d8e2ac14d564
--- /dev/null
+++ b/arch/s390/kernel/vdso64/vdso64_wrapper.S
@@ -0,0 +1,13 @@
+#include <linux/init.h>
+#include <asm/page.h>
+
+	.section ".data.page_aligned"
+
+	.globl vdso64_start, vdso64_end
+	.balign PAGE_SIZE
+vdso64_start:
+	.incbin "arch/s390/kernel/vdso64/vdso64.so"
+	.balign PAGE_SIZE
+vdso64_end:
+
+	.previous
diff --git a/arch/s390/mm/extmem.c b/arch/s390/mm/extmem.c
index 580fc64cc735..5c8457129603 100644
--- a/arch/s390/mm/extmem.c
+++ b/arch/s390/mm/extmem.c
@@ -7,6 +7,9 @@
  * (C) IBM Corporation 2002-2004
  */
 
+#define KMSG_COMPONENT "extmem"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
 #include <linux/kernel.h>
 #include <linux/string.h>
 #include <linux/spinlock.h>
@@ -24,19 +27,6 @@
 #include <asm/cpcmd.h>
 #include <asm/setup.h>
 
-#define DCSS_DEBUG	/* Debug messages on/off */
-
-#define DCSS_NAME "extmem"
-#ifdef DCSS_DEBUG
-#define PRINT_DEBUG(x...)	printk(KERN_DEBUG DCSS_NAME " debug:" x)
-#else
-#define PRINT_DEBUG(x...)   do {} while (0)
-#endif
-#define PRINT_INFO(x...)	printk(KERN_INFO DCSS_NAME " info:" x)
-#define PRINT_WARN(x...)	printk(KERN_WARNING DCSS_NAME " warning:" x)
-#define PRINT_ERR(x...)		printk(KERN_ERR DCSS_NAME " error:" x)
-
-
 #define DCSS_LOADSHR    0x00
 #define DCSS_LOADNSR    0x04
 #define DCSS_PURGESEG   0x08
@@ -286,7 +276,7 @@ query_segment_type (struct dcss_segment *seg)
 		goto out_free;
 	}
 	if (diag_cc > 1) {
-		PRINT_WARN ("segment_type: diag returned error %ld\n", vmrc);
+		pr_warning("Querying a DCSS type failed with rc=%ld\n", vmrc);
 		rc = dcss_diag_translate_rc (vmrc);
 		goto out_free;
 	}
@@ -368,7 +358,6 @@ query_segment_type (struct dcss_segment *seg)
  * -EIO     : could not perform query diagnose
  * -ENOENT  : no such segment
  * -ENOTSUPP: multi-part segment cannot be used with linux
- * -ENOSPC  : segment cannot be used (overlaps with storage)
  * -ENOMEM  : out of memory
  * 0 .. 6   : type of segment as defined in include/asm-s390/extmem.h
  */
@@ -480,9 +469,8 @@ __segment_load (char *name, int do_nonshared, unsigned long *addr, unsigned long
 		goto out_resource;
 	}
 	if (diag_cc > 1) {
-		PRINT_WARN ("segment_load: could not load segment %s - "
-				"diag returned error (%ld)\n",
-				name, end_addr);
+		pr_warning("Loading DCSS %s failed with rc=%ld\n", name,
+			   end_addr);
 		rc = dcss_diag_translate_rc(end_addr);
 		dcss_diag(&purgeseg_scode, seg->dcss_name,
 				&dummy, &dummy);
@@ -496,15 +484,13 @@ __segment_load (char *name, int do_nonshared, unsigned long *addr, unsigned long
 	*addr = seg->start_addr;
 	*end  = seg->end;
 	if (do_nonshared)
-		PRINT_INFO ("segment_load: loaded segment %s range %p .. %p "
-				"type %s in non-shared mode\n", name,
-				(void*)seg->start_addr, (void*)seg->end,
-				segtype_string[seg->vm_segtype]);
+		pr_info("DCSS %s of range %p to %p and type %s loaded as "
+			"exclusive-writable\n", name, (void*) seg->start_addr,
+			(void*) seg->end, segtype_string[seg->vm_segtype]);
 	else {
-		PRINT_INFO ("segment_load: loaded segment %s range %p .. %p "
-				"type %s in shared mode\n", name,
-				(void*)seg->start_addr, (void*)seg->end,
-				segtype_string[seg->vm_segtype]);
+		pr_info("DCSS %s of range %p to %p and type %s loaded in "
+			"shared access mode\n", name, (void*) seg->start_addr,
+			(void*) seg->end, segtype_string[seg->vm_segtype]);
 	}
 	goto out;
  out_resource:
@@ -593,14 +579,14 @@ segment_modify_shared (char *name, int do_nonshared)
 		goto out_unlock;
 	}
 	if (do_nonshared == seg->do_nonshared) {
-		PRINT_INFO ("segment_modify_shared: not reloading segment %s"
-				" - already in requested mode\n",name);
+		pr_info("DCSS %s is already in the requested access "
+			"mode\n", name);
 		rc = 0;
 		goto out_unlock;
 	}
 	if (atomic_read (&seg->ref_count) != 1) {
-		PRINT_WARN ("segment_modify_shared: not reloading segment %s - "
-				"segment is in use by other driver(s)\n",name);
+		pr_warning("DCSS %s is in use and cannot be reloaded\n",
+			   name);
 		rc = -EAGAIN;
 		goto out_unlock;
 	}
@@ -613,8 +599,8 @@ segment_modify_shared (char *name, int do_nonshared)
 			seg->res->flags |= IORESOURCE_READONLY;
 
 	if (request_resource(&iomem_resource, seg->res)) {
-		PRINT_WARN("segment_modify_shared: could not reload segment %s"
-			   " - overlapping resources\n", name);
+		pr_warning("DCSS %s overlaps with used memory resources "
+			   "and cannot be reloaded\n", name);
 		rc = -EBUSY;
 		kfree(seg->res);
 		goto out_del_mem;
@@ -632,9 +618,8 @@ segment_modify_shared (char *name, int do_nonshared)
 		goto out_del_res;
 	}
 	if (diag_cc > 1) {
-		PRINT_WARN ("segment_modify_shared: could not reload segment %s"
-				" - diag returned error (%ld)\n",
-				name, end_addr);
+		pr_warning("Reloading DCSS %s failed with rc=%ld\n", name,
+			   end_addr);
 		rc = dcss_diag_translate_rc(end_addr);
 		goto out_del_res;
 	}
@@ -673,8 +658,7 @@ segment_unload(char *name)
 	mutex_lock(&dcss_lock);
 	seg = segment_by_name (name);
 	if (seg == NULL) {
-		PRINT_ERR ("could not find segment %s in segment_unload, "
-				"please report to linux390@de.ibm.com\n",name);
+		pr_err("Unloading unknown DCSS %s failed\n", name);
 		goto out_unlock;
 	}
 	if (atomic_dec_return(&seg->ref_count) != 0)
@@ -709,8 +693,7 @@ segment_save(char *name)
 	seg = segment_by_name (name);
 
 	if (seg == NULL) {
-		PRINT_ERR("could not find segment %s in segment_save, please "
-			  "report to linux390@de.ibm.com\n", name);
+		pr_err("Saving unknown DCSS %s failed\n", name);
 		goto out;
 	}
 
@@ -727,14 +710,14 @@ segment_save(char *name)
 	response = 0;
 	cpcmd(cmd1, NULL, 0, &response);
 	if (response) {
-		PRINT_ERR("segment_save: DEFSEG failed with response code %i\n",
-			  response);
+		pr_err("Saving a DCSS failed with DEFSEG response code "
+		       "%i\n", response);
 		goto out;
 	}
 	cpcmd(cmd2, NULL, 0, &response);
 	if (response) {
-		PRINT_ERR("segment_save: SAVESEG failed with response code %i\n",
-			  response);
+		pr_err("Saving a DCSS failed with SAVESEG response code "
+		       "%i\n", response);
 		goto out;
 	}
 out:
@@ -749,44 +732,41 @@ void segment_warning(int rc, char *seg_name)
 {
 	switch (rc) {
 	case -ENOENT:
-		PRINT_WARN("cannot load/query segment %s, "
-			   "does not exist\n", seg_name);
+		pr_err("DCSS %s cannot be loaded or queried\n", seg_name);
 		break;
 	case -ENOSYS:
-		PRINT_WARN("cannot load/query segment %s, "
-			   "not running on VM\n", seg_name);
+		pr_err("DCSS %s cannot be loaded or queried without "
+		       "z/VM\n", seg_name);
 		break;
 	case -EIO:
-		PRINT_WARN("cannot load/query segment %s, "
-			   "hardware error\n", seg_name);
+		pr_err("Loading or querying DCSS %s resulted in a "
+		       "hardware error\n", seg_name);
 		break;
 	case -ENOTSUPP:
-		PRINT_WARN("cannot load/query segment %s, "
-			   "is a multi-part segment\n", seg_name);
+		pr_err("DCSS %s has multiple page ranges and cannot be "
+		       "loaded or queried\n", seg_name);
 		break;
 	case -ENOSPC:
-		PRINT_WARN("cannot load/query segment %s, "
-			   "overlaps with storage\n", seg_name);
+		pr_err("DCSS %s overlaps with used storage and cannot "
+		       "be loaded\n", seg_name);
 		break;
 	case -EBUSY:
-		PRINT_WARN("cannot load/query segment %s, "
-			   "overlaps with already loaded dcss\n", seg_name);
+		pr_err("%s needs used memory resources and cannot be "
+		       "loaded or queried\n", seg_name);
 		break;
 	case -EPERM:
-		PRINT_WARN("cannot load/query segment %s, "
-			   "already loaded in incompatible mode\n", seg_name);
+		pr_err("DCSS %s is already loaded in a different access "
+		       "mode\n", seg_name);
 		break;
 	case -ENOMEM:
-		PRINT_WARN("cannot load/query segment %s, "
-			   "out of memory\n", seg_name);
+		pr_err("There is not enough memory to load or query "
+		       "DCSS %s\n", seg_name);
 		break;
 	case -ERANGE:
-		PRINT_WARN("cannot load/query segment %s, "
-			   "exceeds kernel mapping range\n", seg_name);
+		pr_err("DCSS %s exceeds the kernel mapping range (%lu) "
+		       "and cannot be loaded\n", seg_name, VMEM_MAX_PHYS);
 		break;
 	default:
-		PRINT_WARN("cannot load/query segment %s, "
-			   "return value %i\n", seg_name, rc);
 		break;
 	}
 }
diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig
index 80119b3398e7..777d7f65c5ef 100644
--- a/arch/sh/Kconfig
+++ b/arch/sh/Kconfig
@@ -25,6 +25,8 @@ config SUPERH32
 	select HAVE_KRETPROBES
 	select HAVE_ARCH_TRACEHOOK
 	select HAVE_FUNCTION_TRACER
+	select HAVE_FTRACE_MCOUNT_RECORD
+	select HAVE_DYNAMIC_FTRACE
 
 config SUPERH64
 	def_bool y if CPU_SH5
@@ -54,7 +56,7 @@ config GENERIC_HARDIRQS
 	def_bool y
 
 config GENERIC_HARDIRQS_NO__DO_IRQ
-	def_bool y
+	def_bool y if !HD64461
 
 config GENERIC_IRQ_PROBE
 	def_bool y
@@ -83,10 +85,17 @@ config GENERIC_LOCKBREAK
 
 config SYS_SUPPORTS_PM
 	bool
+	depends on !SMP
+
+config ARCH_SUSPEND_POSSIBLE
+	def_bool n
+
+config ARCH_HIBERNATION_POSSIBLE
+	def_bool n
 
 config SYS_SUPPORTS_APM_EMULATION
 	bool
-	select SYS_SUPPORTS_PM
+	select ARCH_SUSPEND_POSSIBLE
 
 config SYS_SUPPORTS_SMP
 	bool
@@ -181,6 +190,11 @@ config CPU_SUBTYPE_SH7619
 
 # SH-2A Processor Support
 
+config CPU_SUBTYPE_SH7201
+	bool "Support SH7201 processor"
+	select CPU_SH2A
+	select CPU_HAS_FPU
+ 
 config CPU_SUBTYPE_SH7203
 	bool "Support SH7203 processor"
 	select CPU_SH2A
@@ -746,13 +760,11 @@ source "fs/Kconfig.binfmt"
 endmenu
 
 menu "Power management options (EXPERIMENTAL)"
-depends on EXPERIMENTAL && SYS_SUPPORTS_PM
+depends on EXPERIMENTAL
 
-config ARCH_SUSPEND_POSSIBLE
-	def_bool y
-	depends on !SMP
+source "kernel/power/Kconfig"
 
-source kernel/power/Kconfig
+source "drivers/cpuidle/Kconfig"
 
 endmenu
 
diff --git a/arch/sh/Makefile b/arch/sh/Makefile
index c43eb0d7fa3b..ad0096151781 100644
--- a/arch/sh/Makefile
+++ b/arch/sh/Makefile
@@ -32,6 +32,7 @@ cflags-$(CONFIG_CPU_SH4)		:= $(call cc-option,-m4,) \
 	$(call cc-option,-mno-implicit-fp,-m4-nofpu)
 cflags-$(CONFIG_CPU_SH4A)		+= $(call cc-option,-m4a,) \
 					   $(call cc-option,-m4a-nofpu,)
+cflags-$(CONFIG_CPU_SH4AL_DSP)		+= $(call cc-option,-m4al,)
 cflags-$(CONFIG_CPU_SH5)		:= $(call cc-option,-m5-32media-nofpu,)
 
 ifeq ($(cflags-y),)
@@ -39,22 +40,16 @@ ifeq ($(cflags-y),)
 # In the case where we are stuck with a compiler that has been uselessly
 # restricted to a particular ISA, a favourite default of newer GCCs when
 # extensive multilib targets are not provided, ensure we get the best fit
-# regarding FP generation. This is necessary to avoid references to FP
-# variants in libgcc where integer variants exist, which otherwise result
-# in link errors. This is intentionally stupid (albeit many orders of
-# magnitude less than GCC's default behaviour), as anything with a large
-# number of multilib targets better have been built correctly for
-# the target in mind.
+# regarding FP generation. This is intentionally stupid (albeit many
+# orders of magnitude less than GCC's default behaviour), as anything
+# with a large number of multilib targets better have been built
+# correctly for the target in mind.
 #
 cflags-y	+= $(shell $(CC) $(KBUILD_CFLAGS) -print-multi-lib | \
 		     grep nofpu | sed q | sed -e 's/^/-/;s/;.*$$//')
-endif
-
-cflags-$(CONFIG_CPU_BIG_ENDIAN)		+= -mb
-cflags-$(CONFIG_CPU_LITTLE_ENDIAN)	+= -ml
-
-cflags-y	+= $(call cc-option,-mno-fdpic)
-
+# At this point, anything goes.
+isaflags-y	:= $(call as-option,-Wa$(comma)-isa=any,)
+else
 #
 # -Wa,-isa= tuning implies -Wa,-dsp for the versions of binutils that
 # support it, while -Wa,-dsp by itself limits the range of usable opcodes
@@ -67,7 +62,12 @@ isaflags-y	:= $(call as-option,-Wa$(comma)-isa=$(isa-y),)
 
 isaflags-$(CONFIG_SH_DSP)		:= \
 	$(call as-option,-Wa$(comma)-isa=$(isa-y),-Wa$(comma)-dsp)
+endif
+
+cflags-$(CONFIG_CPU_BIG_ENDIAN)		+= -mb
+cflags-$(CONFIG_CPU_LITTLE_ENDIAN)	+= -ml
 
+cflags-y	+= $(call cc-option,-mno-fdpic)
 cflags-y	+= $(isaflags-y) -ffreestanding
 
 cflags-$(CONFIG_MORE_COMPILE_OPTIONS)	+= \
@@ -79,6 +79,9 @@ OBJCOPYFLAGS	:= -O binary -R .note -R .note.gnu.build-id -R .comment \
 # Give the various platforms the opportunity to set default image types
 defaultimage-$(CONFIG_SUPERH32)			:= zImage
 defaultimage-$(CONFIG_SH_SH7785LCR)		:= uImage
+defaultimage-$(CONFIG_SH_RSK7203)		:= uImage
+defaultimage-$(CONFIG_SH_7206_SOLUTION_ENGINE)	:= vmlinux
+defaultimage-$(CONFIG_SH_7619_SOLUTION_ENGINE)	:= vmlinux
 
 # Set some sensible Kbuild defaults
 KBUILD_DEFCONFIG	:= shx3_defconfig
@@ -176,8 +179,7 @@ KBUILD_AFLAGS		+= $(cflags-y)
 LIBGCC := $(shell $(CC) $(KBUILD_CFLAGS) -print-libgcc-file-name)
 
 libs-$(CONFIG_SUPERH32)		:= arch/sh/lib/	$(libs-y)
-libs-$(CONFIG_SUPERH64)		:= arch/sh/lib64/ $(libs-y)
-libs-y				+= $(LIBGCC)
+libs-$(CONFIG_SUPERH64)		:= arch/sh/lib64/ $(libs-y) $(LIBGCC)
 
 PHONY += maketools FORCE
 
diff --git a/arch/sh/boards/Kconfig b/arch/sh/boards/Kconfig
index 50467f9d0d0b..2bf3f6c73c12 100644
--- a/arch/sh/boards/Kconfig
+++ b/arch/sh/boards/Kconfig
@@ -126,6 +126,10 @@ config SH_RTS7751R2D
 	  Select RTS7751R2D if configuring for a Renesas Technology
 	  Sales SH-Graphics board.
 
+config SH_RSK7201
+	bool "RSK7201"
+	depends on CPU_SUBTYPE_SH7201
+
 config SH_RSK7203
 	bool "RSK7203"
 	select GENERIC_GPIO
diff --git a/arch/sh/boards/Makefile b/arch/sh/boards/Makefile
index d9efa3923721..ce4d4d465185 100644
--- a/arch/sh/boards/Makefile
+++ b/arch/sh/boards/Makefile
@@ -3,6 +3,7 @@
 #
 obj-$(CONFIG_SH_AP325RXA)	+= board-ap325rxa.o
 obj-$(CONFIG_SH_MAGIC_PANEL_R2)	+= board-magicpanelr2.o
+obj-$(CONFIG_SH_RSK7201)	+= board-rsk7201.o
 obj-$(CONFIG_SH_RSK7203)	+= board-rsk7203.o
 obj-$(CONFIG_SH_SH7785LCR)	+= board-sh7785lcr.o
 obj-$(CONFIG_SH_SHMIN)		+= board-shmin.o
diff --git a/arch/sh/boards/board-ap325rxa.c b/arch/sh/boards/board-ap325rxa.c
index 8881a643ac32..cc3540423614 100644
--- a/arch/sh/boards/board-ap325rxa.c
+++ b/arch/sh/boards/board-ap325rxa.c
@@ -303,6 +303,7 @@ static struct resource ceu_resources[] = {
 
 static struct platform_device ceu_device = {
 	.name		= "sh_mobile_ceu",
+	.id             = 0, /* "ceu0" clock */
 	.num_resources	= ARRAY_SIZE(ceu_resources),
 	.resource	= ceu_resources,
 	.dev		= {
@@ -344,7 +345,6 @@ static int __init ap325rxa_devices_setup(void)
 	gpio_export(GPIO_PTF7, 0);
 
 	/* LCDC */
-	clk_always_enable("mstp200");
 	gpio_request(GPIO_FN_LCDD15, NULL);
 	gpio_request(GPIO_FN_LCDD14, NULL);
 	gpio_request(GPIO_FN_LCDD13, NULL);
@@ -375,7 +375,6 @@ static int __init ap325rxa_devices_setup(void)
 	gpio_direction_output(GPIO_PTS3, 1);
 
 	/* CEU */
-	clk_always_enable("mstp203");
 	gpio_request(GPIO_FN_VIO_CLK2, NULL);
 	gpio_request(GPIO_FN_VIO_VD2, NULL);
 	gpio_request(GPIO_FN_VIO_HD2, NULL);
diff --git a/arch/sh/boards/board-rsk7201.c b/arch/sh/boards/board-rsk7201.c
new file mode 100644
index 000000000000..6fcf64453752
--- /dev/null
+++ b/arch/sh/boards/board-rsk7201.c
@@ -0,0 +1,105 @@
+/*
+ * Renesas Technology Europe RSK+ 7201 Support.
+ *
+ * Copyright (C) 2008 Peter Griffin <pgriffin@mpc-data.co.uk>
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ */
+#include <linux/init.h>
+#include <linux/types.h>
+#include <linux/platform_device.h>
+#include <linux/interrupt.h>
+#include <linux/mtd/mtd.h>
+#include <linux/mtd/partitions.h>
+#include <linux/mtd/physmap.h>
+#include <linux/mtd/map.h>
+#include <asm/machvec.h>
+#include <asm/io.h>
+
+static const char *probes[] = { "cmdlinepart", NULL };
+
+static struct mtd_partition *parsed_partitions;
+
+static struct mtd_partition rsk7201_partitions[] = {
+	{
+		.name		= "Bootloader",
+		.offset		= 0x00000000,
+		.size		= 0x00040000,
+		.mask_flags	= MTD_WRITEABLE,
+	}, {
+		.name		= "Kernel",
+		.offset		= MTDPART_OFS_NXTBLK,
+		.size		= 0x001c0000,
+	}, {
+		.name		= "Flash_FS",
+		.offset		= MTDPART_OFS_NXTBLK,
+		.size		= MTDPART_SIZ_FULL,
+	}
+};
+
+static struct physmap_flash_data flash_data = {
+	.width		= 2,
+};
+
+static struct resource flash_resource = {
+	.start		= 0x20000000,
+	.end		= 0x20400000,
+	.flags		= IORESOURCE_MEM,
+};
+
+static struct platform_device flash_device = {
+	.name		= "physmap-flash",
+	.id		= -1,
+	.resource	= &flash_resource,
+	.num_resources	= 1,
+	.dev		= {
+		.platform_data = &flash_data,
+	},
+};
+
+static struct mtd_info *flash_mtd;
+
+static struct map_info rsk7201_flash_map = {
+	.name		= "RSK+ Flash",
+	.size		= 0x400000,
+	.bankwidth	= 2,
+};
+
+static void __init set_mtd_partitions(void)
+{
+	int nr_parts = 0;
+
+	simple_map_init(&rsk7201_flash_map);
+	flash_mtd = do_map_probe("cfi_probe", &rsk7201_flash_map);
+	nr_parts = parse_mtd_partitions(flash_mtd, probes,
+					&parsed_partitions, 0);
+	/* If there is no partition table, used the hard coded table */
+	if (nr_parts <= 0) {
+		flash_data.parts = rsk7201_partitions;
+		flash_data.nr_parts = ARRAY_SIZE(rsk7201_partitions);
+	} else {
+		flash_data.nr_parts = nr_parts;
+		flash_data.parts = parsed_partitions;
+	}
+}
+
+static struct platform_device *rsk7201_devices[] __initdata = {
+	&flash_device,
+};
+
+static int __init rsk7201_devices_setup(void)
+{
+	set_mtd_partitions();
+	return platform_add_devices(rsk7201_devices,
+				    ARRAY_SIZE(rsk7201_devices));
+}
+device_initcall(rsk7201_devices_setup);
+
+/*
+ * The Machine Vector
+ */
+static struct sh_machine_vector mv_rsk7201 __initmv = {
+	.mv_name        = "RSK+7201",
+};
diff --git a/arch/sh/boards/mach-hp6xx/pm.c b/arch/sh/boards/mach-hp6xx/pm.c
index 64af1f2eef05..d936c1af7620 100644
--- a/arch/sh/boards/mach-hp6xx/pm.c
+++ b/arch/sh/boards/mach-hp6xx/pm.c
@@ -10,15 +10,91 @@
 #include <linux/suspend.h>
 #include <linux/errno.h>
 #include <linux/time.h>
+#include <linux/delay.h>
+#include <linux/gfp.h>
 #include <asm/io.h>
 #include <asm/hd64461.h>
 #include <mach/hp6xx.h>
 #include <cpu/dac.h>
-#include <asm/pm.h>
+#include <asm/freq.h>
+#include <asm/watchdog.h>
+
+#define INTR_OFFSET	0x600
 
 #define STBCR		0xffffff82
 #define STBCR2		0xffffff88
 
+#define STBCR_STBY	0x80
+#define STBCR_MSTP2	0x04
+
+#define MCR		0xffffff68
+#define RTCNT		0xffffff70
+
+#define MCR_RMODE	2
+#define MCR_RFSH	4
+
+extern u8 wakeup_start;
+extern u8 wakeup_end;
+
+static void pm_enter(void)
+{
+	u8 stbcr, csr;
+	u16 frqcr, mcr;
+	u32 vbr_new, vbr_old;
+
+	set_bl_bit();
+
+	/* set wdt */
+	csr = sh_wdt_read_csr();
+	csr &= ~WTCSR_TME;
+	csr |= WTCSR_CKS_4096;
+	sh_wdt_write_csr(csr);
+	csr = sh_wdt_read_csr();
+	sh_wdt_write_cnt(0);
+
+	/* disable PLL1 */
+	frqcr = ctrl_inw(FRQCR);
+	frqcr &= ~(FRQCR_PLLEN | FRQCR_PSTBY);
+	ctrl_outw(frqcr, FRQCR);
+
+	/* enable standby */
+	stbcr = ctrl_inb(STBCR);
+	ctrl_outb(stbcr | STBCR_STBY | STBCR_MSTP2, STBCR);
+
+	/* set self-refresh */
+	mcr = ctrl_inw(MCR);
+	ctrl_outw(mcr & ~MCR_RFSH, MCR);
+
+	/* set interrupt handler */
+	asm volatile("stc vbr, %0" : "=r" (vbr_old));
+	vbr_new = get_zeroed_page(GFP_ATOMIC);
+	udelay(50);
+	memcpy((void*)(vbr_new + INTR_OFFSET),
+	       &wakeup_start, &wakeup_end - &wakeup_start);
+	asm volatile("ldc %0, vbr" : : "r" (vbr_new));
+
+	ctrl_outw(0, RTCNT);
+	ctrl_outw(mcr | MCR_RFSH | MCR_RMODE, MCR);
+
+	cpu_sleep();
+
+	asm volatile("ldc %0, vbr" : : "r" (vbr_old));
+
+	free_page(vbr_new);
+
+	/* enable PLL1 */
+	frqcr = ctrl_inw(FRQCR);
+	frqcr |= FRQCR_PSTBY;
+	ctrl_outw(frqcr, FRQCR);
+	udelay(50);
+	frqcr |= FRQCR_PLLEN;
+	ctrl_outw(frqcr, FRQCR);
+
+	ctrl_outb(stbcr, STBCR);
+
+	clear_bl_bit();
+}
+
 static int hp6x0_pm_enter(suspend_state_t state)
 {
 	u8 stbcr, stbcr2;
diff --git a/arch/sh/boards/mach-migor/setup.c b/arch/sh/boards/mach-migor/setup.c
index 975281980299..03d2dea05dab 100644
--- a/arch/sh/boards/mach-migor/setup.c
+++ b/arch/sh/boards/mach-migor/setup.c
@@ -89,6 +89,7 @@ static struct resource sh_keysc_resources[] = {
 
 static struct platform_device sh_keysc_device = {
 	.name           = "sh_keysc",
+	.id             = 0, /* "keysc0" clock */
 	.num_resources  = ARRAY_SIZE(sh_keysc_resources),
 	.resource       = sh_keysc_resources,
 	.dev	= {
@@ -432,6 +433,7 @@ static struct resource migor_ceu_resources[] = {
 
 static struct platform_device migor_ceu_device = {
 	.name		= "sh_mobile_ceu",
+	.id             = 0, /* "ceu0" clock */
 	.num_resources	= ARRAY_SIZE(migor_ceu_resources),
 	.resource	= migor_ceu_resources,
 	.dev	= {
@@ -479,7 +481,6 @@ static int __init migor_devices_setup(void)
 	ctrl_outl(0x00110080, BSC_CS4WCR);
 
 	/* KEYSC */
-	clk_always_enable("mstp214"); /* KEYSC */
 	gpio_request(GPIO_FN_KEYOUT0, NULL);
 	gpio_request(GPIO_FN_KEYOUT1, NULL);
 	gpio_request(GPIO_FN_KEYOUT2, NULL);
@@ -501,7 +502,6 @@ static int __init migor_devices_setup(void)
 	gpio_request(GPIO_FN_IRQ6, NULL);
 
 	/* LCD Panel */
-	clk_always_enable("mstp200"); /* LCDC */
 #ifdef CONFIG_SH_MIGOR_QVGA /* LCDC - QVGA - Enable SYS Interface signals */
 	gpio_request(GPIO_FN_LCDD17, NULL);
 	gpio_request(GPIO_FN_LCDD16, NULL);
@@ -554,7 +554,6 @@ static int __init migor_devices_setup(void)
 #endif
 
 	/* CEU */
-	clk_always_enable("mstp203"); /* CEU */
 	gpio_request(GPIO_FN_VIO_CLK2, NULL);
 	gpio_request(GPIO_FN_VIO_VD2, NULL);
 	gpio_request(GPIO_FN_VIO_HD2, NULL);
diff --git a/arch/sh/boards/mach-se/7343/Makefile b/arch/sh/boards/mach-se/7343/Makefile
index 3024796c6203..4c3666a93790 100644
--- a/arch/sh/boards/mach-se/7343/Makefile
+++ b/arch/sh/boards/mach-se/7343/Makefile
@@ -2,4 +2,4 @@
 # Makefile for the 7343 SolutionEngine specific parts of the kernel
 #
 
-obj-y	 := setup.o io.o irq.o
+obj-y	 := setup.o irq.o
diff --git a/arch/sh/boards/mach-se/7343/io.c b/arch/sh/boards/mach-se/7343/io.c
deleted file mode 100644
index 8741abc1da7b..000000000000
--- a/arch/sh/boards/mach-se/7343/io.c
+++ /dev/null
@@ -1,273 +0,0 @@
-/*
- * arch/sh/boards/se/7343/io.c
- *
- * I/O routine for SH-Mobile3AS 7343 SolutionEngine.
- *
- */
-#include <linux/kernel.h>
-#include <asm/io.h>
-#include <mach-se/mach/se7343.h>
-
-#define badio(fn, a) panic("bad i/o operation %s for %08lx.", #fn, a)
-
-struct iop {
-	unsigned long start, end;
-	unsigned long base;
-	struct iop *(*check) (struct iop * p, unsigned long port);
-	unsigned char (*inb) (struct iop * p, unsigned long port);
-	unsigned short (*inw) (struct iop * p, unsigned long port);
-	void (*outb) (struct iop * p, unsigned char value, unsigned long port);
-	void (*outw) (struct iop * p, unsigned short value, unsigned long port);
-};
-
-struct iop *
-simple_check(struct iop *p, unsigned long port)
-{
-	static int count;
-
-	if (count < 100)
-		count++;
-
-	port &= 0xFFFF;
-
-	if ((p->start <= port) && (port <= p->end))
-		return p;
-	else
-		badio(check, port);
-}
-
-struct iop *
-ide_check(struct iop *p, unsigned long port)
-{
-	if (((0x1f0 <= port) && (port <= 0x1f7)) || (port == 0x3f7))
-		return p;
-	return NULL;
-}
-
-unsigned char
-simple_inb(struct iop *p, unsigned long port)
-{
-	return *(unsigned char *) (p->base + port);
-}
-
-unsigned short
-simple_inw(struct iop *p, unsigned long port)
-{
-	return *(unsigned short *) (p->base + port);
-}
-
-void
-simple_outb(struct iop *p, unsigned char value, unsigned long port)
-{
-	*(unsigned char *) (p->base + port) = value;
-}
-
-void
-simple_outw(struct iop *p, unsigned short value, unsigned long port)
-{
-	*(unsigned short *) (p->base + port) = value;
-}
-
-unsigned char
-pcc_inb(struct iop *p, unsigned long port)
-{
-	unsigned long addr = p->base + port + 0x40000;
-	unsigned long v;
-
-	if (port & 1)
-		addr += 0x00400000;
-	v = *(volatile unsigned char *) addr;
-	return v;
-}
-
-void
-pcc_outb(struct iop *p, unsigned char value, unsigned long port)
-{
-	unsigned long addr = p->base + port + 0x40000;
-
-	if (port & 1)
-		addr += 0x00400000;
-	*(volatile unsigned char *) addr = value;
-}
-
-unsigned char
-bad_inb(struct iop *p, unsigned long port)
-{
-	badio(inb, port);
-}
-
-void
-bad_outb(struct iop *p, unsigned char value, unsigned long port)
-{
-	badio(inw, port);
-}
-
-#ifdef CONFIG_SMC91X
-/* MSTLANEX01 LAN at 0xb400:0000 */
-static struct iop laniop = {
-	.start = 0x00,
-	.end = 0x0F,
-	.base = 0x04000000,
-	.check = simple_check,
-	.inb = simple_inb,
-	.inw = simple_inw,
-	.outb = simple_outb,
-	.outw = simple_outw,
-};
-#endif
-
-#ifdef CONFIG_NE2000
-/* NE2000 pc card NIC */
-static struct iop neiop = {
-	.start = 0x280,
-	.end = 0x29f,
-	.base = 0xb0600000 + 0x80,	/* soft 0x280 -> hard 0x300 */
-	.check = simple_check,
-	.inb = pcc_inb,
-	.inw = simple_inw,
-	.outb = pcc_outb,
-	.outw = simple_outw,
-};
-#endif
-
-#ifdef CONFIG_IDE
-/* CF in CF slot */
-static struct iop cfiop = {
-	.base = 0xb0600000,
-	.check = ide_check,
-	.inb = pcc_inb,
-	.inw = simple_inw,
-	.outb = pcc_outb,
-	.outw = simple_outw,
-};
-#endif
-
-static __inline__ struct iop *
-port2iop(unsigned long port)
-{
-	if (0) ;
-#if defined(CONFIG_SMC91X)
-	else if (laniop.check(&laniop, port))
-		return &laniop;
-#endif
-#if defined(CONFIG_NE2000)
-	else if (neiop.check(&neiop, port))
-		return &neiop;
-#endif
-#if defined(CONFIG_IDE)
-	else if (cfiop.check(&cfiop, port))
-		return &cfiop;
-#endif
-	else
-		return NULL;
-}
-
-static inline void
-delay(void)
-{
-	ctrl_inw(0xac000000);
-	ctrl_inw(0xac000000);
-}
-
-unsigned char
-sh7343se_inb(unsigned long port)
-{
-	struct iop *p = port2iop(port);
-	return (p->inb) (p, port);
-}
-
-unsigned char
-sh7343se_inb_p(unsigned long port)
-{
-	unsigned char v = sh7343se_inb(port);
-	delay();
-	return v;
-}
-
-unsigned short
-sh7343se_inw(unsigned long port)
-{
-	struct iop *p = port2iop(port);
-	return (p->inw) (p, port);
-}
-
-unsigned int
-sh7343se_inl(unsigned long port)
-{
-	badio(inl, port);
-}
-
-void
-sh7343se_outb(unsigned char value, unsigned long port)
-{
-	struct iop *p = port2iop(port);
-	(p->outb) (p, value, port);
-}
-
-void
-sh7343se_outb_p(unsigned char value, unsigned long port)
-{
-	sh7343se_outb(value, port);
-	delay();
-}
-
-void
-sh7343se_outw(unsigned short value, unsigned long port)
-{
-	struct iop *p = port2iop(port);
-	(p->outw) (p, value, port);
-}
-
-void
-sh7343se_outl(unsigned int value, unsigned long port)
-{
-	badio(outl, port);
-}
-
-void
-sh7343se_insb(unsigned long port, void *addr, unsigned long count)
-{
-	unsigned char *a = addr;
-	struct iop *p = port2iop(port);
-	while (count--)
-		*a++ = (p->inb) (p, port);
-}
-
-void
-sh7343se_insw(unsigned long port, void *addr, unsigned long count)
-{
-	unsigned short *a = addr;
-	struct iop *p = port2iop(port);
-	while (count--)
-		*a++ = (p->inw) (p, port);
-}
-
-void
-sh7343se_insl(unsigned long port, void *addr, unsigned long count)
-{
-	badio(insl, port);
-}
-
-void
-sh7343se_outsb(unsigned long port, const void *addr, unsigned long count)
-{
-	unsigned char *a = (unsigned char *) addr;
-	struct iop *p = port2iop(port);
-	while (count--)
-		(p->outb) (p, *a++, port);
-}
-
-void
-sh7343se_outsw(unsigned long port, const void *addr, unsigned long count)
-{
-	unsigned short *a = (unsigned short *) addr;
-	struct iop *p = port2iop(port);
-	while (count--)
-		(p->outw) (p, *a++, port);
-}
-
-void
-sh7343se_outsl(unsigned long port, const void *addr, unsigned long count)
-{
-	badio(outsw, port);
-}
diff --git a/arch/sh/boards/mach-se/7343/setup.c b/arch/sh/boards/mach-se/7343/setup.c
index 486f40bf9274..4de56f35f419 100644
--- a/arch/sh/boards/mach-se/7343/setup.c
+++ b/arch/sh/boards/mach-se/7343/setup.c
@@ -1,36 +1,16 @@
 #include <linux/init.h>
 #include <linux/platform_device.h>
 #include <linux/mtd/physmap.h>
+#include <linux/serial_8250.h>
+#include <linux/serial_reg.h>
+#include <linux/usb/isp116x.h>
+#include <linux/delay.h>
 #include <asm/machvec.h>
 #include <mach-se/mach/se7343.h>
 #include <asm/heartbeat.h>
 #include <asm/irq.h>
 #include <asm/io.h>
 
-static struct resource smc91x_resources[] = {
-	[0] = {
-		.start	= 0x10000000,
-		.end	= 0x1000000F,
-		.flags	= IORESOURCE_MEM,
-	},
-	[1] = {
-		/*
-		 * shared with other devices via externel
-		 * interrupt controller in FPGA...
-		 */
-		.start	= SMC_IRQ,
-		.end	= SMC_IRQ,
-		.flags	= IORESOURCE_IRQ,
-	},
-};
-
-static struct platform_device smc91x_device = {
-	.name		= "smc91x",
-	.id		= 0,
-	.num_resources	= ARRAY_SIZE(smc91x_resources),
-	.resource	= smc91x_resources,
-};
-
 static struct resource heartbeat_resources[] = {
 	[0] = {
 		.start	= PA_LED,
@@ -94,10 +74,83 @@ static struct platform_device nor_flash_device = {
 	.resource	= nor_flash_resources,
 };
 
+#define ST16C2550C_FLAGS (UPF_BOOT_AUTOCONF | UPF_IOREMAP)
+
+static struct plat_serial8250_port serial_platform_data[] = {
+	[0] = {
+		.iotype		= UPIO_MEM,
+		.mapbase	= 0x16000000,
+		.regshift	= 1,
+		.flags		= ST16C2550C_FLAGS,
+		.irq		= UARTA_IRQ,
+		.uartclk	= 7372800,
+	},
+	[1] = {
+		.iotype		= UPIO_MEM,
+		.mapbase	= 0x17000000,
+		.regshift	= 1,
+		.flags		= ST16C2550C_FLAGS,
+		.irq		= UARTB_IRQ,
+		.uartclk	= 7372800,
+	},
+	{ },
+};
+
+static struct platform_device uart_device = {
+	.name			= "serial8250",
+	.id			= PLAT8250_DEV_PLATFORM,
+	.dev			= {
+		.platform_data	= serial_platform_data,
+	},
+};
+
+static void isp116x_delay(struct device *dev, int delay)
+{
+	ndelay(delay);
+}
+
+static struct resource usb_resources[] = {
+	[0] = {
+		.start  = 0x11800000,
+		.end    = 0x11800001,
+		.flags  = IORESOURCE_MEM,
+	},
+	[1] = {
+		.start  = 0x11800002,
+		.end    = 0x11800003,
+		.flags  = IORESOURCE_MEM,
+	},
+	[2] = {
+		.start  = USB_IRQ,
+		.flags  = IORESOURCE_IRQ,
+	},
+};
+
+static struct isp116x_platform_data usb_platform_data = {
+	.sel15Kres		= 1,
+	.oc_enable		= 1,
+	.int_act_high		= 0,
+	.int_edge_triggered	= 0,
+	.remote_wakeup_enable	= 0,
+	.delay			= isp116x_delay,
+};
+
+static struct platform_device usb_device = {
+	.name			= "isp116x-hcd",
+	.id			= -1,
+	.num_resources  	= ARRAY_SIZE(usb_resources),
+	.resource       	= usb_resources,
+	.dev			= {
+		.platform_data	= &usb_platform_data,
+	},
+
+};
+
 static struct platform_device *sh7343se_platform_devices[] __initdata = {
-	&smc91x_device,
 	&heartbeat_device,
 	&nor_flash_device,
+	&uart_device,
+	&usb_device,
 };
 
 static int __init sh7343se_devices_setup(void)
@@ -126,27 +179,6 @@ static void __init sh7343se_setup(char **cmdline_p)
 static struct sh_machine_vector mv_7343se __initmv = {
 	.mv_name = "SolutionEngine 7343",
 	.mv_setup = sh7343se_setup,
-	.mv_nr_irqs = 108,
-	.mv_inb = sh7343se_inb,
-	.mv_inw = sh7343se_inw,
-	.mv_inl = sh7343se_inl,
-	.mv_outb = sh7343se_outb,
-	.mv_outw = sh7343se_outw,
-	.mv_outl = sh7343se_outl,
-
-	.mv_inb_p = sh7343se_inb_p,
-	.mv_inw_p = sh7343se_inw,
-	.mv_inl_p = sh7343se_inl,
-	.mv_outb_p = sh7343se_outb_p,
-	.mv_outw_p = sh7343se_outw,
-	.mv_outl_p = sh7343se_outl,
-
-	.mv_insb = sh7343se_insb,
-	.mv_insw = sh7343se_insw,
-	.mv_insl = sh7343se_insl,
-	.mv_outsb = sh7343se_outsb,
-	.mv_outsw = sh7343se_outsw,
-	.mv_outsl = sh7343se_outsl,
-
+	.mv_nr_irqs = SE7343_FPGA_IRQ_BASE + SE7343_FPGA_IRQ_NR,
 	.mv_init_irq = init_7343se_IRQ,
 };
diff --git a/arch/sh/boards/mach-se/7722/setup.c b/arch/sh/boards/mach-se/7722/setup.c
index fe6f96517e12..02035bbf2cc2 100644
--- a/arch/sh/boards/mach-se/7722/setup.c
+++ b/arch/sh/boards/mach-se/7722/setup.c
@@ -130,6 +130,7 @@ static struct resource sh_keysc_resources[] = {
 
 static struct platform_device sh_keysc_device = {
 	.name           = "sh_keysc",
+	.id             = 0, /* "keysc0" clock */
 	.num_resources  = ARRAY_SIZE(sh_keysc_resources),
 	.resource       = sh_keysc_resources,
 	.dev	= {
@@ -146,8 +147,6 @@ static struct platform_device *se7722_devices[] __initdata = {
 
 static int __init se7722_devices_setup(void)
 {
-	clk_always_enable("mstp214"); /* KEYSC */
-
 	return platform_add_devices(se7722_devices,
 		ARRAY_SIZE(se7722_devices));
 }
diff --git a/arch/sh/cchips/hd6446x/hd64461.c b/arch/sh/cchips/hd6446x/hd64461.c
index f1a4a0763c59..27ceeb948bb1 100644
--- a/arch/sh/cchips/hd6446x/hd64461.c
+++ b/arch/sh/cchips/hd6446x/hd64461.c
@@ -10,99 +10,49 @@
 #include <linux/interrupt.h>
 #include <linux/init.h>
 #include <linux/irq.h>
-#include <asm/io.h>
+#include <linux/io.h>
 #include <asm/irq.h>
 #include <asm/hd64461.h>
 
 /* This belongs in cpu specific */
 #define INTC_ICR1 0xA4140010UL
 
-static void disable_hd64461_irq(unsigned int irq)
+static void hd64461_mask_irq(unsigned int irq)
 {
 	unsigned short nimr;
 	unsigned short mask = 1 << (irq - HD64461_IRQBASE);
 
-	nimr = inw(HD64461_NIMR);
+	nimr = __raw_readw(HD64461_NIMR);
 	nimr |= mask;
-	outw(nimr, HD64461_NIMR);
+	__raw_writew(nimr, HD64461_NIMR);
 }
 
-static void enable_hd64461_irq(unsigned int irq)
+static void hd64461_unmask_irq(unsigned int irq)
 {
 	unsigned short nimr;
 	unsigned short mask = 1 << (irq - HD64461_IRQBASE);
 
-	nimr = inw(HD64461_NIMR);
+	nimr = __raw_readw(HD64461_NIMR);
 	nimr &= ~mask;
-	outw(nimr, HD64461_NIMR);
+	__raw_writew(nimr, HD64461_NIMR);
 }
 
-static void mask_and_ack_hd64461(unsigned int irq)
+static void hd64461_mask_and_ack_irq(unsigned int irq)
 {
-	disable_hd64461_irq(irq);
+	hd64461_mask_irq(irq);
 #ifdef CONFIG_HD64461_ENABLER
 	if (irq == HD64461_IRQBASE + 13)
-		outb(0x00, HD64461_PCC1CSCR);
+		__raw_writeb(0x00, HD64461_PCC1CSCR);
 #endif
 }
 
-static void end_hd64461_irq(unsigned int irq)
-{
-	if (!(irq_desc[irq].status & (IRQ_DISABLED|IRQ_INPROGRESS)))
-		enable_hd64461_irq(irq);
-}
-
-static unsigned int startup_hd64461_irq(unsigned int irq)
-{
-	enable_hd64461_irq(irq);
-	return 0;
-}
-
-static void shutdown_hd64461_irq(unsigned int irq)
-{
-	disable_hd64461_irq(irq);
-}
-
-static struct hw_interrupt_type hd64461_irq_type = {
-	.typename	= "HD64461-IRQ",
-	.startup	= startup_hd64461_irq,
-	.shutdown	= shutdown_hd64461_irq,
-	.enable		= enable_hd64461_irq,
-	.disable	= disable_hd64461_irq,
-	.ack		= mask_and_ack_hd64461,
-	.end		= end_hd64461_irq,
+static struct irq_chip hd64461_irq_chip = {
+	.name		= "HD64461-IRQ",
+	.mask		= hd64461_mask_irq,
+	.mask_ack	= hd64461_mask_and_ack_irq,
+	.unmask		= hd64461_unmask_irq,
 };
 
-static irqreturn_t hd64461_interrupt(int irq, void *dev_id)
-{
-	printk(KERN_INFO
-	       "HD64461: spurious interrupt, nirr: 0x%x nimr: 0x%x\n",
-	       inw(HD64461_NIRR), inw(HD64461_NIMR));
-
-	return IRQ_NONE;
-}
-
-static struct {
-	int (*func) (int, void *);
-	void *dev;
-} hd64461_demux[HD64461_IRQ_NUM];
-
-void hd64461_register_irq_demux(int irq,
-				int (*demux) (int irq, void *dev), void *dev)
-{
-	hd64461_demux[irq - HD64461_IRQBASE].func = demux;
-	hd64461_demux[irq - HD64461_IRQBASE].dev = dev;
-}
-
-EXPORT_SYMBOL(hd64461_register_irq_demux);
-
-void hd64461_unregister_irq_demux(int irq)
-{
-	hd64461_demux[irq - HD64461_IRQBASE].func = 0;
-}
-
-EXPORT_SYMBOL(hd64461_unregister_irq_demux);
-
 int hd64461_irq_demux(int irq)
 {
 	if (irq == CONFIG_HD64461_IRQ) {
@@ -115,25 +65,11 @@ int hd64461_irq_demux(int irq)
 		for (bit = 1, i = 0; i < 16; bit <<= 1, i++)
 			if (nirr & bit)
 				break;
-		if (i == 16)
-			irq = CONFIG_HD64461_IRQ;
-		else {
-			irq = HD64461_IRQBASE + i;
-			if (hd64461_demux[i].func != 0) {
-				irq = hd64461_demux[i].func(irq, hd64461_demux[i].dev);
-			}
-		}
+		irq = HD64461_IRQBASE + i;
 	}
 	return irq;
 }
 
-static struct irqaction irq0 = {
-	.handler = hd64461_interrupt,
-	.flags = IRQF_DISABLED,
-	.mask = CPU_MASK_NONE,
-	.name = "HD64461",
-};
-
 int __init setup_hd64461(void)
 {
 	int i;
@@ -146,22 +82,21 @@ int __init setup_hd64461(void)
 	       CONFIG_HD64461_IOBASE, CONFIG_HD64461_IRQ, HD64461_IRQBASE,
 	       HD64461_IRQBASE + 15);
 
-#if defined(CONFIG_CPU_SUBTYPE_SH7709)	/* Should be at processor specific part.. */
-	outw(0x2240, INTC_ICR1);
+/* Should be at processor specific part.. */
+#if defined(CONFIG_CPU_SUBTYPE_SH7709)
+	__raw_writew(0x2240, INTC_ICR1);
 #endif
-	outw(0xffff, HD64461_NIMR);
+	__raw_writew(0xffff, HD64461_NIMR);
 
 	/*  IRQ 80 -> 95 belongs to HD64461  */
-	for (i = HD64461_IRQBASE; i < HD64461_IRQBASE + 16; i++) {
-		irq_desc[i].chip = &hd64461_irq_type;
-	}
-
-	setup_irq(CONFIG_HD64461_IRQ, &irq0);
+	for (i = HD64461_IRQBASE; i < HD64461_IRQBASE + 16; i++)
+		set_irq_chip_and_handler(i, &hd64461_irq_chip,
+					 handle_level_irq);
 
 #ifdef CONFIG_HD64461_ENABLER
 	printk(KERN_INFO "HD64461: enabling PCMCIA devices\n");
-	outb(0x4c, HD64461_PCC1CSCIER);
-	outb(0x00, HD64461_PCC1CSCR);
+	__raw_writeb(0x4c, HD64461_PCC1CSCIER);
+	__raw_writeb(0x00, HD64461_PCC1CSCR);
 #endif
 
 	return 0;
diff --git a/arch/sh/configs/rsk7201_defconfig b/arch/sh/configs/rsk7201_defconfig
new file mode 100644
index 000000000000..4a75584721fc
--- /dev/null
+++ b/arch/sh/configs/rsk7201_defconfig
@@ -0,0 +1,691 @@
+#
+# Automatically generated make config: don't edit
+# Linux kernel version: 2.6.28-rc6
+# Thu Nov 27 12:14:18 2008
+#
+CONFIG_SUPERH=y
+CONFIG_SUPERH32=y
+CONFIG_ARCH_DEFCONFIG="arch/sh/configs/shx3_defconfig"
+CONFIG_RWSEM_GENERIC_SPINLOCK=y
+CONFIG_GENERIC_BUG=y
+CONFIG_GENERIC_FIND_NEXT_BIT=y
+CONFIG_GENERIC_HWEIGHT=y
+CONFIG_GENERIC_HARDIRQS=y
+CONFIG_GENERIC_HARDIRQS_NO__DO_IRQ=y
+CONFIG_GENERIC_IRQ_PROBE=y
+# CONFIG_GENERIC_GPIO is not set
+# CONFIG_GENERIC_TIME is not set
+# CONFIG_GENERIC_CLOCKEVENTS is not set
+CONFIG_STACKTRACE_SUPPORT=y
+CONFIG_LOCKDEP_SUPPORT=y
+CONFIG_HAVE_LATENCYTOP_SUPPORT=y
+# CONFIG_ARCH_HAS_ILOG2_U32 is not set
+# CONFIG_ARCH_HAS_ILOG2_U64 is not set
+CONFIG_ARCH_NO_VIRT_TO_BUS=y
+CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config"
+
+#
+# General setup
+#
+CONFIG_EXPERIMENTAL=y
+CONFIG_BROKEN_ON_SMP=y
+CONFIG_INIT_ENV_ARG_LIMIT=32
+CONFIG_LOCALVERSION=""
+# CONFIG_LOCALVERSION_AUTO is not set
+CONFIG_SYSVIPC=y
+CONFIG_SYSVIPC_SYSCTL=y
+CONFIG_BSD_PROCESS_ACCT=y
+# CONFIG_BSD_PROCESS_ACCT_V3 is not set
+CONFIG_IKCONFIG=y
+# CONFIG_IKCONFIG_PROC is not set
+CONFIG_LOG_BUF_SHIFT=14
+# CONFIG_CGROUPS is not set
+# CONFIG_GROUP_SCHED is not set
+# CONFIG_SYSFS_DEPRECATED_V2 is not set
+# CONFIG_RELAY is not set
+CONFIG_NAMESPACES=y
+CONFIG_UTS_NS=y
+CONFIG_IPC_NS=y
+CONFIG_USER_NS=y
+CONFIG_PID_NS=y
+CONFIG_BLK_DEV_INITRD=y
+CONFIG_INITRAMFS_SOURCE=""
+CONFIG_CC_OPTIMIZE_FOR_SIZE=y
+CONFIG_SYSCTL=y
+CONFIG_EMBEDDED=y
+CONFIG_UID16=y
+CONFIG_SYSCTL_SYSCALL=y
+CONFIG_KALLSYMS=y
+# CONFIG_KALLSYMS_EXTRA_PASS is not set
+CONFIG_HOTPLUG=y
+CONFIG_PRINTK=y
+CONFIG_BUG=y
+CONFIG_ELF_CORE=y
+CONFIG_COMPAT_BRK=y
+CONFIG_BASE_FULL=y
+CONFIG_FUTEX=y
+CONFIG_ANON_INODES=y
+CONFIG_EPOLL=y
+CONFIG_SIGNALFD=y
+CONFIG_TIMERFD=y
+CONFIG_EVENTFD=y
+# CONFIG_AIO is not set
+CONFIG_VM_EVENT_COUNTERS=y
+# CONFIG_SLAB is not set
+# CONFIG_SLUB is not set
+CONFIG_SLOB=y
+CONFIG_PROFILING=y
+# CONFIG_MARKERS is not set
+CONFIG_OPROFILE=y
+CONFIG_HAVE_OPROFILE=y
+# CONFIG_KPROBES is not set
+CONFIG_HAVE_KPROBES=y
+CONFIG_HAVE_KRETPROBES=y
+CONFIG_HAVE_ARCH_TRACEHOOK=y
+CONFIG_HAVE_CLK=y
+CONFIG_HAVE_GENERIC_DMA_COHERENT=y
+CONFIG_RT_MUTEXES=y
+CONFIG_TINY_SHMEM=y
+CONFIG_BASE_SMALL=0
+CONFIG_MODULES=y
+# CONFIG_MODULE_FORCE_LOAD is not set
+# CONFIG_MODULE_UNLOAD is not set
+# CONFIG_MODVERSIONS is not set
+# CONFIG_MODULE_SRCVERSION_ALL is not set
+CONFIG_KMOD=y
+CONFIG_BLOCK=y
+# CONFIG_LBD is not set
+# CONFIG_BLK_DEV_IO_TRACE is not set
+# CONFIG_LSF is not set
+# CONFIG_BLK_DEV_BSG is not set
+# CONFIG_BLK_DEV_INTEGRITY is not set
+
+#
+# IO Schedulers
+#
+CONFIG_IOSCHED_NOOP=y
+# CONFIG_IOSCHED_AS is not set
+# CONFIG_IOSCHED_DEADLINE is not set
+# CONFIG_IOSCHED_CFQ is not set
+# CONFIG_DEFAULT_AS is not set
+# CONFIG_DEFAULT_DEADLINE is not set
+# CONFIG_DEFAULT_CFQ is not set
+CONFIG_DEFAULT_NOOP=y
+CONFIG_DEFAULT_IOSCHED="noop"
+CONFIG_CLASSIC_RCU=y
+# CONFIG_FREEZER is not set
+
+#
+# System type
+#
+CONFIG_CPU_SH2=y
+CONFIG_CPU_SH2A=y
+# CONFIG_CPU_SUBTYPE_SH7619 is not set
+CONFIG_CPU_SUBTYPE_SH7201=y
+# CONFIG_CPU_SUBTYPE_SH7203 is not set
+# CONFIG_CPU_SUBTYPE_SH7206 is not set
+# CONFIG_CPU_SUBTYPE_SH7263 is not set
+# CONFIG_CPU_SUBTYPE_MXG is not set
+# CONFIG_CPU_SUBTYPE_SH7705 is not set
+# CONFIG_CPU_SUBTYPE_SH7706 is not set
+# CONFIG_CPU_SUBTYPE_SH7707 is not set
+# CONFIG_CPU_SUBTYPE_SH7708 is not set
+# CONFIG_CPU_SUBTYPE_SH7709 is not set
+# CONFIG_CPU_SUBTYPE_SH7710 is not set
+# CONFIG_CPU_SUBTYPE_SH7712 is not set
+# CONFIG_CPU_SUBTYPE_SH7720 is not set
+# CONFIG_CPU_SUBTYPE_SH7721 is not set
+# CONFIG_CPU_SUBTYPE_SH7750 is not set
+# CONFIG_CPU_SUBTYPE_SH7091 is not set
+# CONFIG_CPU_SUBTYPE_SH7750R is not set
+# CONFIG_CPU_SUBTYPE_SH7750S is not set
+# CONFIG_CPU_SUBTYPE_SH7751 is not set
+# CONFIG_CPU_SUBTYPE_SH7751R is not set
+# CONFIG_CPU_SUBTYPE_SH7760 is not set
+# CONFIG_CPU_SUBTYPE_SH4_202 is not set
+# CONFIG_CPU_SUBTYPE_SH7723 is not set
+# CONFIG_CPU_SUBTYPE_SH7763 is not set
+# CONFIG_CPU_SUBTYPE_SH7770 is not set
+# CONFIG_CPU_SUBTYPE_SH7780 is not set
+# CONFIG_CPU_SUBTYPE_SH7785 is not set
+# CONFIG_CPU_SUBTYPE_SHX3 is not set
+# CONFIG_CPU_SUBTYPE_SH7343 is not set
+# CONFIG_CPU_SUBTYPE_SH7722 is not set
+# CONFIG_CPU_SUBTYPE_SH7366 is not set
+# CONFIG_CPU_SUBTYPE_SH5_101 is not set
+# CONFIG_CPU_SUBTYPE_SH5_103 is not set
+
+#
+# Memory management options
+#
+CONFIG_QUICKLIST=y
+CONFIG_PAGE_OFFSET=0x00000000
+CONFIG_MEMORY_START=0x08000000
+CONFIG_MEMORY_SIZE=0x01000000
+CONFIG_29BIT=y
+CONFIG_ARCH_FLATMEM_ENABLE=y
+CONFIG_ARCH_SPARSEMEM_ENABLE=y
+CONFIG_ARCH_SPARSEMEM_DEFAULT=y
+CONFIG_MAX_ACTIVE_REGIONS=1
+CONFIG_ARCH_POPULATES_NODE_MAP=y
+CONFIG_ARCH_SELECT_MEMORY_MODEL=y
+CONFIG_PAGE_SIZE_4KB=y
+# CONFIG_PAGE_SIZE_8KB is not set
+# CONFIG_PAGE_SIZE_16KB is not set
+# CONFIG_PAGE_SIZE_64KB is not set
+CONFIG_ENTRY_OFFSET=0x00001000
+CONFIG_SELECT_MEMORY_MODEL=y
+CONFIG_FLATMEM_MANUAL=y
+# CONFIG_DISCONTIGMEM_MANUAL is not set
+# CONFIG_SPARSEMEM_MANUAL is not set
+CONFIG_FLATMEM=y
+CONFIG_FLAT_NODE_MEM_MAP=y
+CONFIG_SPARSEMEM_STATIC=y
+CONFIG_PAGEFLAGS_EXTENDED=y
+CONFIG_SPLIT_PTLOCK_CPUS=4
+# CONFIG_RESOURCES_64BIT is not set
+# CONFIG_PHYS_ADDR_T_64BIT is not set
+CONFIG_ZONE_DMA_FLAG=0
+CONFIG_NR_QUICK=2
+
+#
+# Cache configuration
+#
+# CONFIG_SH_DIRECT_MAPPED is not set
+CONFIG_CACHE_WRITEBACK=y
+# CONFIG_CACHE_WRITETHROUGH is not set
+# CONFIG_CACHE_OFF is not set
+
+#
+# Processor features
+#
+# CONFIG_CPU_LITTLE_ENDIAN is not set
+CONFIG_CPU_BIG_ENDIAN=y
+CONFIG_SH_FPU=y
+CONFIG_CPU_HAS_FPU=y
+
+#
+# Board support
+#
+CONFIG_SH_RSK7201=y
+
+#
+# Timer and clock configuration
+#
+# CONFIG_SH_CMT is not set
+CONFIG_SH_MTU2=y
+CONFIG_SH_TIMER_IRQ=16
+CONFIG_SH_PCLK_FREQ=40000000
+CONFIG_SH_CLK_MD=0
+
+#
+# CPU Frequency scaling
+#
+# CONFIG_CPU_FREQ is not set
+
+#
+# DMA support
+#
+
+#
+# Companion Chips
+#
+
+#
+# Additional SuperH Device Drivers
+#
+# CONFIG_HEARTBEAT is not set
+# CONFIG_PUSH_SWITCH is not set
+
+#
+# Kernel features
+#
+# CONFIG_HZ_100 is not set
+# CONFIG_HZ_250 is not set
+# CONFIG_HZ_300 is not set
+CONFIG_HZ_1000=y
+CONFIG_HZ=1000
+# CONFIG_SCHED_HRTICK is not set
+# CONFIG_KEXEC is not set
+# CONFIG_CRASH_DUMP is not set
+# CONFIG_SECCOMP is not set
+CONFIG_PREEMPT_NONE=y
+# CONFIG_PREEMPT_VOLUNTARY is not set
+# CONFIG_PREEMPT is not set
+CONFIG_GUSA=y
+
+#
+# Boot options
+#
+CONFIG_ZERO_PAGE_OFFSET=0x00001000
+CONFIG_BOOT_LINK_OFFSET=0x00800000
+CONFIG_CMDLINE_BOOL=y
+CONFIG_CMDLINE="console=ttySC0,115200 earlyprintk=serial ignore_loglevel"
+
+#
+# Bus options
+#
+# CONFIG_ARCH_SUPPORTS_MSI is not set
+# CONFIG_PCCARD is not set
+
+#
+# Executable file formats
+#
+CONFIG_BINFMT_ELF_FDPIC=y
+CONFIG_BINFMT_FLAT=y
+CONFIG_BINFMT_ZFLAT=y
+CONFIG_BINFMT_SHARED_FLAT=y
+# CONFIG_HAVE_AOUT is not set
+# CONFIG_BINFMT_MISC is not set
+# CONFIG_NET is not set
+
+#
+# Device Drivers
+#
+
+#
+# Generic Driver Options
+#
+CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
+# CONFIG_STANDALONE is not set
+# CONFIG_PREVENT_FIRMWARE_BUILD is not set
+# CONFIG_FW_LOADER is not set
+# CONFIG_SYS_HYPERVISOR is not set
+CONFIG_MTD=y
+# CONFIG_MTD_DEBUG is not set
+CONFIG_MTD_CONCAT=y
+CONFIG_MTD_PARTITIONS=y
+CONFIG_MTD_REDBOOT_PARTS=y
+CONFIG_MTD_REDBOOT_DIRECTORY_BLOCK=-1
+# CONFIG_MTD_REDBOOT_PARTS_UNALLOCATED is not set
+# CONFIG_MTD_REDBOOT_PARTS_READONLY is not set
+# CONFIG_MTD_CMDLINE_PARTS is not set
+# CONFIG_MTD_AR7_PARTS is not set
+
+#
+# User Modules And Translation Layers
+#
+CONFIG_MTD_CHAR=y
+CONFIG_MTD_BLKDEVS=y
+CONFIG_MTD_BLOCK=y
+# CONFIG_FTL is not set
+# CONFIG_NFTL is not set
+# CONFIG_INFTL is not set
+# CONFIG_RFD_FTL is not set
+# CONFIG_SSFDC is not set
+# CONFIG_MTD_OOPS is not set
+
+#
+# RAM/ROM/Flash chip drivers
+#
+CONFIG_MTD_CFI=y
+# CONFIG_MTD_JEDECPROBE is not set
+CONFIG_MTD_GEN_PROBE=y
+# CONFIG_MTD_CFI_ADV_OPTIONS is not set
+CONFIG_MTD_MAP_BANK_WIDTH_1=y
+CONFIG_MTD_MAP_BANK_WIDTH_2=y
+CONFIG_MTD_MAP_BANK_WIDTH_4=y
+# CONFIG_MTD_MAP_BANK_WIDTH_8 is not set
+# CONFIG_MTD_MAP_BANK_WIDTH_16 is not set
+# CONFIG_MTD_MAP_BANK_WIDTH_32 is not set
+CONFIG_MTD_CFI_I1=y
+CONFIG_MTD_CFI_I2=y
+# CONFIG_MTD_CFI_I4 is not set
+# CONFIG_MTD_CFI_I8 is not set
+# CONFIG_MTD_CFI_INTELEXT is not set
+CONFIG_MTD_CFI_AMDSTD=y
+# CONFIG_MTD_CFI_STAA is not set
+CONFIG_MTD_CFI_UTIL=y
+# CONFIG_MTD_RAM is not set
+# CONFIG_MTD_ROM is not set
+# CONFIG_MTD_ABSENT is not set
+
+#
+# Mapping drivers for chip access
+#
+# CONFIG_MTD_COMPLEX_MAPPINGS is not set
+CONFIG_MTD_PHYSMAP=y
+CONFIG_MTD_PHYSMAP_START=0x0
+CONFIG_MTD_PHYSMAP_LEN=0x0
+CONFIG_MTD_PHYSMAP_BANKWIDTH=4
+# CONFIG_MTD_PLATRAM is not set
+
+#
+# Self-contained MTD device drivers
+#
+# CONFIG_MTD_SLRAM is not set
+# CONFIG_MTD_PHRAM is not set
+# CONFIG_MTD_MTDRAM is not set
+# CONFIG_MTD_BLOCK2MTD is not set
+
+#
+# Disk-On-Chip Device Drivers
+#
+# CONFIG_MTD_DOC2000 is not set
+# CONFIG_MTD_DOC2001 is not set
+# CONFIG_MTD_DOC2001PLUS is not set
+# CONFIG_MTD_NAND is not set
+# CONFIG_MTD_ONENAND is not set
+
+#
+# UBI - Unsorted block images
+#
+# CONFIG_MTD_UBI is not set
+# CONFIG_PARPORT is not set
+CONFIG_BLK_DEV=y
+# CONFIG_BLK_DEV_COW_COMMON is not set
+# CONFIG_BLK_DEV_LOOP is not set
+# CONFIG_BLK_DEV_RAM is not set
+# CONFIG_CDROM_PKTCDVD is not set
+# CONFIG_BLK_DEV_HD is not set
+CONFIG_MISC_DEVICES=y
+# CONFIG_EEPROM_93CX6 is not set
+# CONFIG_ENCLOSURE_SERVICES is not set
+# CONFIG_C2PORT is not set
+CONFIG_HAVE_IDE=y
+# CONFIG_IDE is not set
+
+#
+# SCSI device support
+#
+# CONFIG_RAID_ATTRS is not set
+# CONFIG_SCSI is not set
+# CONFIG_SCSI_DMA is not set
+# CONFIG_SCSI_NETLINK is not set
+# CONFIG_ATA is not set
+# CONFIG_MD is not set
+# CONFIG_PHONE is not set
+
+#
+# Input device support
+#
+CONFIG_INPUT=y
+# CONFIG_INPUT_FF_MEMLESS is not set
+# CONFIG_INPUT_POLLDEV is not set
+
+#
+# Userland interfaces
+#
+# CONFIG_INPUT_MOUSEDEV is not set
+# CONFIG_INPUT_JOYDEV is not set
+# CONFIG_INPUT_EVDEV is not set
+# CONFIG_INPUT_EVBUG is not set
+
+#
+# Input Device Drivers
+#
+# CONFIG_INPUT_KEYBOARD is not set
+# CONFIG_INPUT_MOUSE is not set
+# CONFIG_INPUT_JOYSTICK is not set
+# CONFIG_INPUT_TABLET is not set
+# CONFIG_INPUT_TOUCHSCREEN is not set
+# CONFIG_INPUT_MISC is not set
+
+#
+# Hardware I/O ports
+#
+# CONFIG_SERIO is not set
+# CONFIG_GAMEPORT is not set
+
+#
+# Character devices
+#
+# CONFIG_VT is not set
+CONFIG_DEVKMEM=y
+# CONFIG_SERIAL_NONSTANDARD is not set
+
+#
+# Serial drivers
+#
+# CONFIG_SERIAL_8250 is not set
+
+#
+# Non-8250 serial port support
+#
+CONFIG_SERIAL_SH_SCI=y
+CONFIG_SERIAL_SH_SCI_NR_UARTS=8
+CONFIG_SERIAL_SH_SCI_CONSOLE=y
+CONFIG_SERIAL_CORE=y
+CONFIG_SERIAL_CORE_CONSOLE=y
+# CONFIG_UNIX98_PTYS is not set
+# CONFIG_LEGACY_PTYS is not set
+# CONFIG_IPMI_HANDLER is not set
+# CONFIG_HW_RANDOM is not set
+# CONFIG_R3964 is not set
+# CONFIG_RAW_DRIVER is not set
+# CONFIG_TCG_TPM is not set
+# CONFIG_I2C is not set
+# CONFIG_SPI is not set
+# CONFIG_W1 is not set
+# CONFIG_POWER_SUPPLY is not set
+# CONFIG_HWMON is not set
+CONFIG_THERMAL=y
+# CONFIG_WATCHDOG is not set
+CONFIG_SSB_POSSIBLE=y
+
+#
+# Sonics Silicon Backplane
+#
+# CONFIG_SSB is not set
+
+#
+# Multifunction device drivers
+#
+# CONFIG_MFD_CORE is not set
+# CONFIG_MFD_SM501 is not set
+# CONFIG_HTC_PASIC3 is not set
+# CONFIG_MFD_TMIO is not set
+# CONFIG_REGULATOR is not set
+
+#
+# Multimedia devices
+#
+
+#
+# Multimedia core support
+#
+# CONFIG_VIDEO_DEV is not set
+# CONFIG_VIDEO_MEDIA is not set
+
+#
+# Multimedia drivers
+#
+CONFIG_DAB=y
+
+#
+# Graphics support
+#
+# CONFIG_VGASTATE is not set
+CONFIG_VIDEO_OUTPUT_CONTROL=y
+# CONFIG_FB is not set
+# CONFIG_BACKLIGHT_LCD_SUPPORT is not set
+
+#
+# Display device support
+#
+# CONFIG_DISPLAY_SUPPORT is not set
+# CONFIG_SOUND is not set
+# CONFIG_HID_SUPPORT is not set
+# CONFIG_USB_SUPPORT is not set
+# CONFIG_MMC is not set
+# CONFIG_MEMSTICK is not set
+# CONFIG_NEW_LEDS is not set
+# CONFIG_ACCESSIBILITY is not set
+CONFIG_RTC_LIB=y
+CONFIG_RTC_CLASS=y
+CONFIG_RTC_HCTOSYS=y
+CONFIG_RTC_HCTOSYS_DEVICE="rtc0"
+# CONFIG_RTC_DEBUG is not set
+
+#
+# RTC interfaces
+#
+CONFIG_RTC_INTF_SYSFS=y
+CONFIG_RTC_INTF_PROC=y
+CONFIG_RTC_INTF_DEV=y
+# CONFIG_RTC_INTF_DEV_UIE_EMUL is not set
+# CONFIG_RTC_DRV_TEST is not set
+
+#
+# SPI RTC drivers
+#
+
+#
+# Platform RTC drivers
+#
+# CONFIG_RTC_DRV_DS1286 is not set
+# CONFIG_RTC_DRV_DS1511 is not set
+# CONFIG_RTC_DRV_DS1553 is not set
+# CONFIG_RTC_DRV_DS1742 is not set
+# CONFIG_RTC_DRV_STK17TA8 is not set
+# CONFIG_RTC_DRV_M48T86 is not set
+# CONFIG_RTC_DRV_M48T35 is not set
+# CONFIG_RTC_DRV_M48T59 is not set
+# CONFIG_RTC_DRV_BQ4802 is not set
+# CONFIG_RTC_DRV_V3020 is not set
+
+#
+# on-CPU RTC drivers
+#
+CONFIG_RTC_DRV_SH=y
+# CONFIG_DMADEVICES is not set
+# CONFIG_UIO is not set
+# CONFIG_STAGING is not set
+CONFIG_STAGING_EXCLUDE_BUILD=y
+
+#
+# File systems
+#
+CONFIG_EXT2_FS=y
+# CONFIG_EXT2_FS_XATTR is not set
+# CONFIG_EXT3_FS is not set
+# CONFIG_EXT4_FS is not set
+# CONFIG_REISERFS_FS is not set
+# CONFIG_JFS_FS is not set
+# CONFIG_FS_POSIX_ACL is not set
+# CONFIG_FILE_LOCKING is not set
+# CONFIG_XFS_FS is not set
+# CONFIG_DNOTIFY is not set
+# CONFIG_INOTIFY is not set
+# CONFIG_QUOTA is not set
+# CONFIG_AUTOFS_FS is not set
+# CONFIG_AUTOFS4_FS is not set
+# CONFIG_FUSE_FS is not set
+
+#
+# CD-ROM/DVD Filesystems
+#
+# CONFIG_ISO9660_FS is not set
+# CONFIG_UDF_FS is not set
+
+#
+# DOS/FAT/NT Filesystems
+#
+# CONFIG_MSDOS_FS is not set
+# CONFIG_VFAT_FS is not set
+# CONFIG_NTFS_FS is not set
+
+#
+# Pseudo filesystems
+#
+CONFIG_PROC_FS=y
+CONFIG_PROC_SYSCTL=y
+CONFIG_SYSFS=y
+# CONFIG_TMPFS is not set
+# CONFIG_HUGETLB_PAGE is not set
+# CONFIG_CONFIGFS_FS is not set
+
+#
+# Miscellaneous filesystems
+#
+# CONFIG_ADFS_FS is not set
+# CONFIG_AFFS_FS is not set
+# CONFIG_HFS_FS is not set
+# CONFIG_HFSPLUS_FS is not set
+# CONFIG_BEFS_FS is not set
+# CONFIG_BFS_FS is not set
+# CONFIG_EFS_FS is not set
+CONFIG_JFFS2_FS=y
+CONFIG_JFFS2_FS_DEBUG=0
+CONFIG_JFFS2_FS_WRITEBUFFER=y
+# CONFIG_JFFS2_FS_WBUF_VERIFY is not set
+# CONFIG_JFFS2_SUMMARY is not set
+# CONFIG_JFFS2_FS_XATTR is not set
+# CONFIG_JFFS2_COMPRESSION_OPTIONS is not set
+CONFIG_JFFS2_ZLIB=y
+# CONFIG_JFFS2_LZO is not set
+CONFIG_JFFS2_RTIME=y
+# CONFIG_JFFS2_RUBIN is not set
+# CONFIG_CRAMFS is not set
+# CONFIG_VXFS_FS is not set
+# CONFIG_MINIX_FS is not set
+# CONFIG_OMFS_FS is not set
+# CONFIG_HPFS_FS is not set
+# CONFIG_QNX4FS_FS is not set
+CONFIG_ROMFS_FS=y
+# CONFIG_SYSV_FS is not set
+# CONFIG_UFS_FS is not set
+
+#
+# Partition Types
+#
+# CONFIG_PARTITION_ADVANCED is not set
+CONFIG_MSDOS_PARTITION=y
+# CONFIG_NLS is not set
+
+#
+# Kernel hacking
+#
+CONFIG_TRACE_IRQFLAGS_SUPPORT=y
+# CONFIG_PRINTK_TIME is not set
+CONFIG_ENABLE_WARN_DEPRECATED=y
+# CONFIG_ENABLE_MUST_CHECK is not set
+CONFIG_FRAME_WARN=1024
+CONFIG_MAGIC_SYSRQ=y
+# CONFIG_UNUSED_SYMBOLS is not set
+CONFIG_DEBUG_FS=y
+# CONFIG_HEADERS_CHECK is not set
+# CONFIG_DEBUG_KERNEL is not set
+# CONFIG_DEBUG_BUGVERBOSE is not set
+# CONFIG_DEBUG_MEMORY_INIT is not set
+# CONFIG_RCU_CPU_STALL_DETECTOR is not set
+# CONFIG_LATENCYTOP is not set
+CONFIG_SYSCTL_SYSCALL_CHECK=y
+CONFIG_HAVE_FUNCTION_TRACER=y
+CONFIG_HAVE_DYNAMIC_FTRACE=y
+CONFIG_HAVE_FTRACE_MCOUNT_RECORD=y
+
+#
+# Tracers
+#
+# CONFIG_DYNAMIC_PRINTK_DEBUG is not set
+# CONFIG_SAMPLES is not set
+# CONFIG_SH_STANDARD_BIOS is not set
+# CONFIG_EARLY_SCIF_CONSOLE is not set
+
+#
+# Security options
+#
+# CONFIG_KEYS is not set
+# CONFIG_SECURITY is not set
+# CONFIG_SECURITYFS is not set
+# CONFIG_SECURITY_FILE_CAPABILITIES is not set
+# CONFIG_CRYPTO is not set
+
+#
+# Library routines
+#
+CONFIG_BITREVERSE=y
+# CONFIG_CRC_CCITT is not set
+# CONFIG_CRC16 is not set
+# CONFIG_CRC_T10DIF is not set
+# CONFIG_CRC_ITU_T is not set
+CONFIG_CRC32=y
+# CONFIG_CRC7 is not set
+# CONFIG_LIBCRC32C is not set
+CONFIG_ZLIB_INFLATE=y
+CONFIG_ZLIB_DEFLATE=y
+CONFIG_PLIST=y
+CONFIG_HAS_IOMEM=y
+CONFIG_HAS_IOPORT=y
+CONFIG_HAS_DMA=y
diff --git a/arch/sh/configs/se7343_defconfig b/arch/sh/configs/se7343_defconfig
index 075f42ed5b09..be246f381507 100644
--- a/arch/sh/configs/se7343_defconfig
+++ b/arch/sh/configs/se7343_defconfig
@@ -1,7 +1,7 @@
 #
 # Automatically generated make config: don't edit
-# Linux kernel version: 2.6.27
-# Wed Oct 22 19:00:21 2008
+# Linux kernel version: 2.6.28-rc6
+# Thu Dec  4 16:40:25 2008
 #
 CONFIG_SUPERH=y
 CONFIG_SUPERH32=y
@@ -74,7 +74,6 @@ CONFIG_EVENTFD=y
 # CONFIG_SHMEM is not set
 CONFIG_AIO=y
 CONFIG_VM_EVENT_COUNTERS=y
-CONFIG_PCI_QUIRKS=y
 CONFIG_SLAB=y
 # CONFIG_SLUB is not set
 # CONFIG_SLOB is not set
@@ -127,6 +126,7 @@ CONFIG_CPU_SH4=y
 CONFIG_CPU_SH4A=y
 CONFIG_CPU_SH4AL_DSP=y
 # CONFIG_CPU_SUBTYPE_SH7619 is not set
+# CONFIG_CPU_SUBTYPE_SH7201 is not set
 # CONFIG_CPU_SUBTYPE_SH7203 is not set
 # CONFIG_CPU_SUBTYPE_SH7206 is not set
 # CONFIG_CPU_SUBTYPE_SH7263 is not set
@@ -227,7 +227,7 @@ CONFIG_SH_7343_SOLUTION_ENGINE=y
 #
 CONFIG_SH_TMU=y
 CONFIG_SH_TIMER_IRQ=16
-CONFIG_SH_PCLK_FREQ=27000000
+CONFIG_SH_PCLK_FREQ=33333333
 # CONFIG_NO_HZ is not set
 # CONFIG_HIGH_RES_TIMERS is not set
 CONFIG_GENERIC_CLOCKEVENTS_BUILD=y
@@ -274,7 +274,8 @@ CONFIG_GUSA=y
 #
 CONFIG_ZERO_PAGE_OFFSET=0x00001000
 CONFIG_BOOT_LINK_OFFSET=0x00800000
-# CONFIG_CMDLINE_BOOL is not set
+CONFIG_CMDLINE_BOOL=y
+CONFIG_CMDLINE="console=ttySC0,115200"
 
 #
 # Bus options
@@ -463,6 +464,7 @@ CONFIG_BLK_DEV=y
 # CONFIG_BLK_DEV_COW_COMMON is not set
 # CONFIG_BLK_DEV_LOOP is not set
 # CONFIG_BLK_DEV_NBD is not set
+# CONFIG_BLK_DEV_UB is not set
 # CONFIG_BLK_DEV_RAM is not set
 # CONFIG_CDROM_PKTCDVD is not set
 # CONFIG_ATA_OVER_ETH is not set
@@ -519,23 +521,10 @@ CONFIG_NETDEVICES=y
 # CONFIG_EQUALIZER is not set
 # CONFIG_TUN is not set
 # CONFIG_VETH is not set
-# CONFIG_PHYLIB is not set
-CONFIG_NET_ETHERNET=y
+# CONFIG_NET_ETHERNET is not set
 CONFIG_MII=y
-# CONFIG_AX88796 is not set
-# CONFIG_STNIC is not set
-CONFIG_SMC91X=y
-# CONFIG_SMC911X is not set
-# CONFIG_IBM_NEW_EMAC_ZMII is not set
-# CONFIG_IBM_NEW_EMAC_RGMII is not set
-# CONFIG_IBM_NEW_EMAC_TAH is not set
-# CONFIG_IBM_NEW_EMAC_EMAC4 is not set
-# CONFIG_IBM_NEW_EMAC_NO_FLOW_CTRL is not set
-# CONFIG_IBM_NEW_EMAC_MAL_CLR_ICINTSTAT is not set
-# CONFIG_IBM_NEW_EMAC_MAL_COMMON_ERR is not set
-# CONFIG_B44 is not set
-CONFIG_NETDEV_1000=y
-CONFIG_NETDEV_10000=y
+# CONFIG_NETDEV_1000 is not set
+# CONFIG_NETDEV_10000 is not set
 
 #
 # Wireless LAN
@@ -543,6 +532,26 @@ CONFIG_NETDEV_10000=y
 # CONFIG_WLAN_PRE80211 is not set
 # CONFIG_WLAN_80211 is not set
 # CONFIG_IWLWIFI_LEDS is not set
+
+#
+# USB Network Adapters
+#
+# CONFIG_USB_CATC is not set
+# CONFIG_USB_KAWETH is not set
+# CONFIG_USB_PEGASUS is not set
+# CONFIG_USB_RTL8150 is not set
+CONFIG_USB_USBNET=y
+# CONFIG_USB_NET_AX8817X is not set
+CONFIG_USB_NET_CDCETHER=y
+CONFIG_USB_NET_DM9601=y
+# CONFIG_USB_NET_SMSC95XX is not set
+# CONFIG_USB_NET_GL620A is not set
+# CONFIG_USB_NET_NET1080 is not set
+# CONFIG_USB_NET_PLUSB is not set
+# CONFIG_USB_NET_MCS7830 is not set
+# CONFIG_USB_NET_RNDIS_HOST is not set
+# CONFIG_USB_NET_CDC_SUBSET is not set
+# CONFIG_USB_NET_ZAURUS is not set
 # CONFIG_WAN is not set
 # CONFIG_PPP is not set
 # CONFIG_SLIP is not set
@@ -597,13 +606,17 @@ CONFIG_DEVKMEM=y
 #
 # Serial drivers
 #
-# CONFIG_SERIAL_8250 is not set
+CONFIG_SERIAL_8250=y
+# CONFIG_SERIAL_8250_CONSOLE is not set
+CONFIG_SERIAL_8250_NR_UARTS=2
+CONFIG_SERIAL_8250_RUNTIME_UARTS=2
+# CONFIG_SERIAL_8250_EXTENDED is not set
 
 #
 # Non-8250 serial port support
 #
 CONFIG_SERIAL_SH_SCI=y
-CONFIG_SERIAL_SH_SCI_NR_UARTS=2
+CONFIG_SERIAL_SH_SCI_NR_UARTS=4
 CONFIG_SERIAL_SH_SCI_CONSOLE=y
 CONFIG_SERIAL_CORE=y
 CONFIG_SERIAL_CORE_CONSOLE=y
@@ -615,7 +628,51 @@ CONFIG_HW_RANDOM=y
 # CONFIG_R3964 is not set
 # CONFIG_RAW_DRIVER is not set
 # CONFIG_TCG_TPM is not set
-# CONFIG_I2C is not set
+CONFIG_I2C=y
+CONFIG_I2C_BOARDINFO=y
+# CONFIG_I2C_CHARDEV is not set
+CONFIG_I2C_HELPER_AUTO=y
+
+#
+# I2C Hardware Bus support
+#
+
+#
+# I2C system bus drivers (mostly embedded / system-on-chip)
+#
+# CONFIG_I2C_OCORES is not set
+CONFIG_I2C_SH_MOBILE=y
+# CONFIG_I2C_SIMTEC is not set
+
+#
+# External I2C/SMBus adapter drivers
+#
+# CONFIG_I2C_PARPORT_LIGHT is not set
+# CONFIG_I2C_TAOS_EVM is not set
+# CONFIG_I2C_TINY_USB is not set
+
+#
+# Other I2C/SMBus bus drivers
+#
+# CONFIG_I2C_PCA_PLATFORM is not set
+# CONFIG_I2C_STUB is not set
+
+#
+# Miscellaneous I2C Chip support
+#
+# CONFIG_DS1682 is not set
+# CONFIG_AT24 is not set
+# CONFIG_SENSORS_EEPROM is not set
+# CONFIG_SENSORS_PCF8574 is not set
+# CONFIG_PCF8575 is not set
+# CONFIG_SENSORS_PCA9539 is not set
+# CONFIG_SENSORS_PCF8591 is not set
+# CONFIG_SENSORS_MAX6875 is not set
+# CONFIG_SENSORS_TSL2550 is not set
+# CONFIG_I2C_DEBUG_CORE is not set
+# CONFIG_I2C_DEBUG_ALGO is not set
+# CONFIG_I2C_DEBUG_BUS is not set
+# CONFIG_I2C_DEBUG_CHIP is not set
 # CONFIG_SPI is not set
 # CONFIG_W1 is not set
 # CONFIG_POWER_SUPPLY is not set
@@ -623,11 +680,11 @@ CONFIG_HW_RANDOM=y
 # CONFIG_THERMAL is not set
 # CONFIG_THERMAL_HWMON is not set
 # CONFIG_WATCHDOG is not set
+CONFIG_SSB_POSSIBLE=y
 
 #
 # Sonics Silicon Backplane
 #
-CONFIG_SSB_POSSIBLE=y
 # CONFIG_SSB is not set
 
 #
@@ -637,7 +694,10 @@ CONFIG_SSB_POSSIBLE=y
 # CONFIG_MFD_SM501 is not set
 # CONFIG_HTC_PASIC3 is not set
 # CONFIG_MFD_TMIO is not set
+# CONFIG_PMIC_DA903X is not set
 # CONFIG_MFD_WM8400 is not set
+# CONFIG_MFD_WM8350_I2C is not set
+# CONFIG_REGULATOR is not set
 
 #
 # Multimedia devices
@@ -657,6 +717,16 @@ CONFIG_VIDEO_MEDIA=y
 # Multimedia drivers
 #
 # CONFIG_MEDIA_ATTACH is not set
+CONFIG_MEDIA_TUNER=y
+# CONFIG_MEDIA_TUNER_CUSTOMIZE is not set
+CONFIG_MEDIA_TUNER_SIMPLE=y
+CONFIG_MEDIA_TUNER_TDA8290=y
+CONFIG_MEDIA_TUNER_TDA9887=y
+CONFIG_MEDIA_TUNER_TEA5761=y
+CONFIG_MEDIA_TUNER_TEA5767=y
+CONFIG_MEDIA_TUNER_MT20XX=y
+CONFIG_MEDIA_TUNER_XC2028=y
+CONFIG_MEDIA_TUNER_XC5000=y
 CONFIG_VIDEO_V4L2=y
 CONFIG_VIDEO_V4L1=y
 CONFIG_VIDEO_CAPTURE_DRIVERS=y
@@ -665,8 +735,57 @@ CONFIG_VIDEO_CAPTURE_DRIVERS=y
 CONFIG_VIDEO_HELPER_CHIPS_AUTO=y
 # CONFIG_VIDEO_VIVI is not set
 # CONFIG_VIDEO_CPIA is not set
+# CONFIG_VIDEO_CPIA2 is not set
+# CONFIG_VIDEO_SAA5246A is not set
+# CONFIG_VIDEO_SAA5249 is not set
 # CONFIG_SOC_CAMERA is not set
+CONFIG_V4L_USB_DRIVERS=y
+# CONFIG_USB_VIDEO_CLASS is not set
+CONFIG_USB_GSPCA=m
+# CONFIG_USB_M5602 is not set
+# CONFIG_USB_GSPCA_CONEX is not set
+# CONFIG_USB_GSPCA_ETOMS is not set
+# CONFIG_USB_GSPCA_FINEPIX is not set
+# CONFIG_USB_GSPCA_MARS is not set
+# CONFIG_USB_GSPCA_OV519 is not set
+# CONFIG_USB_GSPCA_PAC207 is not set
+# CONFIG_USB_GSPCA_PAC7311 is not set
+# CONFIG_USB_GSPCA_SONIXB is not set
+# CONFIG_USB_GSPCA_SONIXJ is not set
+# CONFIG_USB_GSPCA_SPCA500 is not set
+# CONFIG_USB_GSPCA_SPCA501 is not set
+# CONFIG_USB_GSPCA_SPCA505 is not set
+# CONFIG_USB_GSPCA_SPCA506 is not set
+# CONFIG_USB_GSPCA_SPCA508 is not set
+# CONFIG_USB_GSPCA_SPCA561 is not set
+# CONFIG_USB_GSPCA_STK014 is not set
+# CONFIG_USB_GSPCA_SUNPLUS is not set
+# CONFIG_USB_GSPCA_T613 is not set
+# CONFIG_USB_GSPCA_TV8532 is not set
+# CONFIG_USB_GSPCA_VC032X is not set
+# CONFIG_USB_GSPCA_ZC3XX is not set
+# CONFIG_VIDEO_PVRUSB2 is not set
+# CONFIG_VIDEO_EM28XX is not set
+# CONFIG_VIDEO_USBVISION is not set
+# CONFIG_USB_VICAM is not set
+# CONFIG_USB_IBMCAM is not set
+# CONFIG_USB_KONICAWC is not set
+# CONFIG_USB_QUICKCAM_MESSENGER is not set
+# CONFIG_USB_ET61X251 is not set
+# CONFIG_VIDEO_OVCAMCHIP is not set
+# CONFIG_USB_OV511 is not set
+# CONFIG_USB_SE401 is not set
+# CONFIG_USB_SN9C102 is not set
+# CONFIG_USB_STV680 is not set
+# CONFIG_USB_ZC0301 is not set
+# CONFIG_USB_PWC is not set
+# CONFIG_USB_ZR364XX is not set
+# CONFIG_USB_STKWEBCAM is not set
+# CONFIG_USB_S2255 is not set
 CONFIG_RADIO_ADAPTERS=y
+# CONFIG_USB_DSBR is not set
+# CONFIG_USB_SI470X is not set
+# CONFIG_USB_MR800 is not set
 # CONFIG_DAB is not set
 
 #
@@ -700,6 +819,7 @@ CONFIG_FB_CFB_IMAGEBLIT=m
 CONFIG_FB_SH_MOBILE_LCDC=m
 # CONFIG_FB_VIRTUAL is not set
 # CONFIG_FB_METRONOME is not set
+# CONFIG_FB_MB862XX is not set
 # CONFIG_BACKLIGHT_LCD_SUPPORT is not set
 
 #
@@ -737,27 +857,147 @@ CONFIG_SND_DRIVERS=y
 # CONFIG_SND_SERIAL_U16550 is not set
 # CONFIG_SND_MPU401 is not set
 CONFIG_SND_SUPERH=y
+CONFIG_SND_USB=y
+# CONFIG_SND_USB_AUDIO is not set
+# CONFIG_SND_USB_CAIAQ is not set
 # CONFIG_SND_SOC is not set
 # CONFIG_SOUND_PRIME is not set
 CONFIG_HID_SUPPORT=y
 CONFIG_HID=y
 # CONFIG_HID_DEBUG is not set
 # CONFIG_HIDRAW is not set
+
+#
+# USB Input Devices
+#
+CONFIG_USB_HID=y
 # CONFIG_HID_PID is not set
+# CONFIG_USB_HIDDEV is not set
 
 #
 # Special HID drivers
 #
 CONFIG_HID_COMPAT=y
-# CONFIG_USB_SUPPORT is not set
+CONFIG_HID_A4TECH=y
+CONFIG_HID_APPLE=y
+CONFIG_HID_BELKIN=y
+CONFIG_HID_BRIGHT=y
+CONFIG_HID_CHERRY=y
+CONFIG_HID_CHICONY=y
+CONFIG_HID_CYPRESS=y
+CONFIG_HID_DELL=y
+CONFIG_HID_EZKEY=y
+CONFIG_HID_GYRATION=y
+CONFIG_HID_LOGITECH=y
+# CONFIG_LOGITECH_FF is not set
+# CONFIG_LOGIRUMBLEPAD2_FF is not set
+CONFIG_HID_MICROSOFT=y
+CONFIG_HID_MONTEREY=y
+CONFIG_HID_PANTHERLORD=y
+# CONFIG_PANTHERLORD_FF is not set
+CONFIG_HID_PETALYNX=y
+CONFIG_HID_SAMSUNG=y
+CONFIG_HID_SONY=y
+CONFIG_HID_SUNPLUS=y
+# CONFIG_THRUSTMASTER_FF is not set
+# CONFIG_ZEROPLUS_FF is not set
+CONFIG_USB_SUPPORT=y
+CONFIG_USB_ARCH_HAS_HCD=y
+# CONFIG_USB_ARCH_HAS_OHCI is not set
+# CONFIG_USB_ARCH_HAS_EHCI is not set
+CONFIG_USB=y
+CONFIG_USB_DEBUG=y
+CONFIG_USB_ANNOUNCE_NEW_DEVICES=y
+
+#
+# Miscellaneous USB options
+#
+CONFIG_USB_DEVICEFS=y
+CONFIG_USB_DEVICE_CLASS=y
+# CONFIG_USB_DYNAMIC_MINORS is not set
+# CONFIG_USB_OTG is not set
+# CONFIG_USB_OTG_WHITELIST is not set
+# CONFIG_USB_OTG_BLACKLIST_HUB is not set
+# CONFIG_USB_MON is not set
+# CONFIG_USB_WUSB is not set
+# CONFIG_USB_WUSB_CBAF is not set
+
+#
+# USB Host Controller Drivers
+#
+# CONFIG_USB_C67X00_HCD is not set
+CONFIG_USB_ISP116X_HCD=y
+# CONFIG_USB_SL811_HCD is not set
+# CONFIG_USB_R8A66597_HCD is not set
+# CONFIG_USB_HWA_HCD is not set
+
+#
+# USB Device Class drivers
+#
+# CONFIG_USB_ACM is not set
+# CONFIG_USB_PRINTER is not set
+# CONFIG_USB_WDM is not set
+# CONFIG_USB_TMC is not set
+
+#
+# NOTE: USB_STORAGE depends on SCSI but BLK_DEV_SD may also be needed;
+#
+
+#
+# see USB_STORAGE Help for more information
+#
+# CONFIG_USB_STORAGE is not set
+# CONFIG_USB_LIBUSUAL is not set
+
+#
+# USB Imaging devices
+#
+# CONFIG_USB_MDC800 is not set
+# CONFIG_USB_MICROTEK is not set
+
+#
+# USB port drivers
+#
+# CONFIG_USB_SERIAL is not set
+
+#
+# USB Miscellaneous drivers
+#
+# CONFIG_USB_EMI62 is not set
+# CONFIG_USB_EMI26 is not set
+# CONFIG_USB_ADUTUX is not set
+# CONFIG_USB_SEVSEG is not set
+# CONFIG_USB_RIO500 is not set
+# CONFIG_USB_LEGOTOWER is not set
+# CONFIG_USB_LCD is not set
+# CONFIG_USB_BERRY_CHARGE is not set
+# CONFIG_USB_LED is not set
+# CONFIG_USB_CYPRESS_CY7C63 is not set
+# CONFIG_USB_CYTHERM is not set
+# CONFIG_USB_PHIDGET is not set
+# CONFIG_USB_IDMOUSE is not set
+# CONFIG_USB_FTDI_ELAN is not set
+# CONFIG_USB_APPLEDISPLAY is not set
+# CONFIG_USB_LD is not set
+# CONFIG_USB_TRANCEVIBRATOR is not set
+# CONFIG_USB_IOWARRIOR is not set
+# CONFIG_USB_TEST is not set
+# CONFIG_USB_ISIGHTFW is not set
+# CONFIG_USB_VST is not set
+# CONFIG_USB_GADGET is not set
 # CONFIG_MMC is not set
 # CONFIG_MEMSTICK is not set
 # CONFIG_NEW_LEDS is not set
 # CONFIG_ACCESSIBILITY is not set
 # CONFIG_RTC_CLASS is not set
 # CONFIG_DMADEVICES is not set
-# CONFIG_UIO is not set
+CONFIG_UIO=y
+# CONFIG_UIO_PDRV is not set
+# CONFIG_UIO_PDRV_GENIRQ is not set
+# CONFIG_UIO_SMX is not set
+# CONFIG_UIO_SERCOS3 is not set
 # CONFIG_STAGING is not set
+CONFIG_STAGING_EXCLUDE_BUILD=y
 
 #
 # File systems
@@ -889,8 +1129,13 @@ CONFIG_FRAME_WARN=1024
 # CONFIG_DEBUG_MEMORY_INIT is not set
 # CONFIG_RCU_CPU_STALL_DETECTOR is not set
 # CONFIG_LATENCYTOP is not set
-CONFIG_NOP_TRACER=y
-CONFIG_HAVE_FTRACE=y
+CONFIG_HAVE_FUNCTION_TRACER=y
+CONFIG_HAVE_DYNAMIC_FTRACE=y
+CONFIG_HAVE_FTRACE_MCOUNT_RECORD=y
+
+#
+# Tracers
+#
 # CONFIG_DYNAMIC_PRINTK_DEBUG is not set
 # CONFIG_SAMPLES is not set
 # CONFIG_SH_STANDARD_BIOS is not set
diff --git a/arch/sh/drivers/dma/dma-sh.c b/arch/sh/drivers/dma/dma-sh.c
index b2ffe649c7c0..50887a592dd0 100644
--- a/arch/sh/drivers/dma/dma-sh.c
+++ b/arch/sh/drivers/dma/dma-sh.c
@@ -205,7 +205,8 @@ static int sh_dmac_get_dma_residue(struct dma_channel *chan)
 
 #if defined(CONFIG_CPU_SUBTYPE_SH7720) || \
     defined(CONFIG_CPU_SUBTYPE_SH7721) || \
-    defined(CONFIG_CPU_SUBTYPE_SH7780)
+    defined(CONFIG_CPU_SUBTYPE_SH7780) || \
+    defined(CONFIG_CPU_SUBTYPE_SH7709)
 #define dmaor_read_reg()	ctrl_inw(DMAOR)
 #define dmaor_write_reg(data)	ctrl_outw(data, DMAOR)
 #else
diff --git a/arch/sh/drivers/dma/dma-sh.h b/arch/sh/drivers/dma/dma-sh.h
index b05af34fc15d..05fecd5428e4 100644
--- a/arch/sh/drivers/dma/dma-sh.h
+++ b/arch/sh/drivers/dma/dma-sh.h
@@ -29,6 +29,7 @@
 #define RS_IN	0x00000200
 #define RS_OUT	0x00000300
 #define TS_BLK	0x00000040
+#define TM_BUR	0x00000020
 #define CHCR_DE 0x00000001
 #define CHCR_TE 0x00000002
 #define CHCR_IE 0x00000004
diff --git a/arch/sh/drivers/pci/pci-sh7780.c b/arch/sh/drivers/pci/pci-sh7780.c
index b2a2bfa3c1bd..078dc44d6b08 100644
--- a/arch/sh/drivers/pci/pci-sh7780.c
+++ b/arch/sh/drivers/pci/pci-sh7780.c
@@ -123,16 +123,14 @@ int __init sh7780_pcic_init(struct sh4_pci_address_map *map)
 	 * Window0 = map->window0.size @ non-cached area base = SDRAM
 	 * Window1 = map->window1.size @ cached area base = SDRAM
 	 */
-	word = ((map->window0.size - 1) & 0x1ff00001) | 0x01;
-	pci_write_reg(0x07f00001, SH4_PCILSR0);
-	word = ((map->window1.size - 1) & 0x1ff00001) | 0x01;
+	word = (CONFIG_MEMORY_SIZE - 0x00100000) | 0x00000001;
+	pci_write_reg(word, SH4_PCILSR0);
 	pci_write_reg(0x00000001, SH4_PCILSR1);
 	/* Set the values on window 0 PCI config registers */
-	word = P2SEGADDR(map->window0.base);
-	pci_write_reg(0xa8000000, SH4_PCILAR0);
-	pci_write_reg(0x08000000, SH7780_PCIMBAR0);
+	word = (CONFIG_MEMORY_SIZE > 0x08000000) ? 0x10000000 : 0x08000000;
+	pci_write_reg(word | 0xa0000000, SH4_PCILAR0);
+	pci_write_reg(word, SH7780_PCIMBAR0);
 	/* Set the values on window 1 PCI config registers */
-	word = P2SEGADDR(map->window1.base);
 	pci_write_reg(0x00000000, SH4_PCILAR1);
 	pci_write_reg(0x00000000, SH7780_PCIMBAR1);
 
diff --git a/arch/sh/include/asm/addrspace.h b/arch/sh/include/asm/addrspace.h
index 2702d81bfc0d..36736c7e93db 100644
--- a/arch/sh/include/asm/addrspace.h
+++ b/arch/sh/include/asm/addrspace.h
@@ -49,5 +49,16 @@
 /* Check if an address can be reached in 29 bits */
 #define IS_29BIT(a)	(((unsigned long)(a)) < 0x20000000)
 
+#ifdef CONFIG_SH_STORE_QUEUES
+/*
+ * This is a special case for the SH-4 store queues, as pages for this
+ * space still need to be faulted in before it's possible to flush the
+ * store queue cache for writeout to the remapped region.
+ */
+#define P3_ADDR_MAX		(P4SEG_STORE_QUE + 0x04000000)
+#else
+#define P3_ADDR_MAX		P4SEG
+#endif
+
 #endif /* __KERNEL__ */
 #endif /* __ASM_SH_ADDRSPACE_H */
diff --git a/arch/sh/include/asm/bitops-grb.h b/arch/sh/include/asm/bitops-grb.h
index a5907b94395b..e73af33acbf4 100644
--- a/arch/sh/include/asm/bitops-grb.h
+++ b/arch/sh/include/asm/bitops-grb.h
@@ -166,4 +166,7 @@ static inline int test_and_change_bit(int nr, volatile void * addr)
 
         return retval;
 }
+
+#include <asm-generic/bitops/non-atomic.h>
+
 #endif /* __ASM_SH_BITOPS_GRB_H */
diff --git a/arch/sh/include/asm/bitops-irq.h b/arch/sh/include/asm/bitops-irq.h
deleted file mode 100644
index 653a12750584..000000000000
--- a/arch/sh/include/asm/bitops-irq.h
+++ /dev/null
@@ -1,91 +0,0 @@
-#ifndef __ASM_SH_BITOPS_IRQ_H
-#define __ASM_SH_BITOPS_IRQ_H
-
-static inline void set_bit(int nr, volatile void *addr)
-{
-	int	mask;
-	volatile unsigned int *a = addr;
-	unsigned long flags;
-
-	a += nr >> 5;
-	mask = 1 << (nr & 0x1f);
-	local_irq_save(flags);
-	*a |= mask;
-	local_irq_restore(flags);
-}
-
-static inline void clear_bit(int nr, volatile void *addr)
-{
-	int	mask;
-	volatile unsigned int *a = addr;
-	unsigned long flags;
-
-	a += nr >> 5;
-	mask = 1 << (nr & 0x1f);
-	local_irq_save(flags);
-	*a &= ~mask;
-	local_irq_restore(flags);
-}
-
-static inline void change_bit(int nr, volatile void *addr)
-{
-	int	mask;
-	volatile unsigned int *a = addr;
-	unsigned long flags;
-
-	a += nr >> 5;
-	mask = 1 << (nr & 0x1f);
-	local_irq_save(flags);
-	*a ^= mask;
-	local_irq_restore(flags);
-}
-
-static inline int test_and_set_bit(int nr, volatile void *addr)
-{
-	int	mask, retval;
-	volatile unsigned int *a = addr;
-	unsigned long flags;
-
-	a += nr >> 5;
-	mask = 1 << (nr & 0x1f);
-	local_irq_save(flags);
-	retval = (mask & *a) != 0;
-	*a |= mask;
-	local_irq_restore(flags);
-
-	return retval;
-}
-
-static inline int test_and_clear_bit(int nr, volatile void *addr)
-{
-	int	mask, retval;
-	volatile unsigned int *a = addr;
-	unsigned long flags;
-
-	a += nr >> 5;
-	mask = 1 << (nr & 0x1f);
-	local_irq_save(flags);
-	retval = (mask & *a) != 0;
-	*a &= ~mask;
-	local_irq_restore(flags);
-
-	return retval;
-}
-
-static inline int test_and_change_bit(int nr, volatile void *addr)
-{
-	int	mask, retval;
-	volatile unsigned int *a = addr;
-	unsigned long flags;
-
-	a += nr >> 5;
-	mask = 1 << (nr & 0x1f);
-	local_irq_save(flags);
-	retval = (mask & *a) != 0;
-	*a ^= mask;
-	local_irq_restore(flags);
-
-	return retval;
-}
-
-#endif /* __ASM_SH_BITOPS_IRQ_H */
diff --git a/arch/sh/include/asm/bitops-llsc.h b/arch/sh/include/asm/bitops-llsc.h
index 43b8e1a8239e..1d2fc0b010ad 100644
--- a/arch/sh/include/asm/bitops-llsc.h
+++ b/arch/sh/include/asm/bitops-llsc.h
@@ -141,4 +141,6 @@ static inline int test_and_change_bit(int nr, volatile void * addr)
 	return retval != 0;
 }
 
+#include <asm-generic/bitops/non-atomic.h>
+
 #endif /* __ASM_SH_BITOPS_LLSC_H */
diff --git a/arch/sh/include/asm/bitops-op32.h b/arch/sh/include/asm/bitops-op32.h
new file mode 100644
index 000000000000..f0ae7e9218e0
--- /dev/null
+++ b/arch/sh/include/asm/bitops-op32.h
@@ -0,0 +1,142 @@
+#ifndef __ASM_SH_BITOPS_OP32_H
+#define __ASM_SH_BITOPS_OP32_H
+
+/*
+ * The bit modifying instructions on SH-2A are only capable of working
+ * with a 3-bit immediate, which signifies the shift position for the bit
+ * being worked on.
+ */
+#if defined(__BIG_ENDIAN)
+#define BITOP_LE_SWIZZLE	((BITS_PER_LONG-1) & ~0x7)
+#define BYTE_NUMBER(nr)		((nr ^ BITOP_LE_SWIZZLE) / BITS_PER_BYTE)
+#define BYTE_OFFSET(nr)		((nr ^ BITOP_LE_SWIZZLE) % BITS_PER_BYTE)
+#else
+#define BYTE_NUMBER(nr)		((nr) / BITS_PER_BYTE)
+#define BYTE_OFFSET(nr)		((nr) % BITS_PER_BYTE)
+#endif
+
+#define IS_IMMEDIATE(nr)	(__builtin_constant_p(nr))
+
+static inline void __set_bit(int nr, volatile unsigned long *addr)
+{
+	if (IS_IMMEDIATE(nr)) {
+		__asm__ __volatile__ (
+			"bset.b %1, @(%O2,%0)		! __set_bit\n\t"
+			: "+r" (addr)
+			: "i" (BYTE_OFFSET(nr)), "i" (BYTE_NUMBER(nr))
+			: "t", "memory"
+		);
+	} else {
+		unsigned long mask = BIT_MASK(nr);
+		unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+
+		*p |= mask;
+	}
+}
+
+static inline void __clear_bit(int nr, volatile unsigned long *addr)
+{
+	if (IS_IMMEDIATE(nr)) {
+		__asm__ __volatile__ (
+			"bclr.b %1, @(%O2,%0)		! __clear_bit\n\t"
+			: "+r" (addr)
+			: "i" (BYTE_OFFSET(nr)),
+			  "i" (BYTE_NUMBER(nr))
+			: "t", "memory"
+		);
+	} else {
+		unsigned long mask = BIT_MASK(nr);
+		unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+
+		*p &= ~mask;
+	}
+}
+
+/**
+ * __change_bit - Toggle a bit in memory
+ * @nr: the bit to change
+ * @addr: the address to start counting from
+ *
+ * Unlike change_bit(), this function is non-atomic and may be reordered.
+ * If it's called on the same region of memory simultaneously, the effect
+ * may be that only one operation succeeds.
+ */
+static inline void __change_bit(int nr, volatile unsigned long *addr)
+{
+	if (IS_IMMEDIATE(nr)) {
+		__asm__ __volatile__ (
+			"bxor.b %1, @(%O2,%0)		! __change_bit\n\t"
+			: "+r" (addr)
+			: "i" (BYTE_OFFSET(nr)),
+			  "i" (BYTE_NUMBER(nr))
+			: "t", "memory"
+		);
+	} else {
+		unsigned long mask = BIT_MASK(nr);
+		unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+
+		*p ^= mask;
+	}
+}
+
+/**
+ * __test_and_set_bit - Set a bit and return its old value
+ * @nr: Bit to set
+ * @addr: Address to count from
+ *
+ * This operation is non-atomic and can be reordered.
+ * If two examples of this operation race, one can appear to succeed
+ * but actually fail.  You must protect multiple accesses with a lock.
+ */
+static inline int __test_and_set_bit(int nr, volatile unsigned long *addr)
+{
+	unsigned long mask = BIT_MASK(nr);
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	unsigned long old = *p;
+
+	*p = old | mask;
+	return (old & mask) != 0;
+}
+
+/**
+ * __test_and_clear_bit - Clear a bit and return its old value
+ * @nr: Bit to clear
+ * @addr: Address to count from
+ *
+ * This operation is non-atomic and can be reordered.
+ * If two examples of this operation race, one can appear to succeed
+ * but actually fail.  You must protect multiple accesses with a lock.
+ */
+static inline int __test_and_clear_bit(int nr, volatile unsigned long *addr)
+{
+	unsigned long mask = BIT_MASK(nr);
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	unsigned long old = *p;
+
+	*p = old & ~mask;
+	return (old & mask) != 0;
+}
+
+/* WARNING: non atomic and it can be reordered! */
+static inline int __test_and_change_bit(int nr,
+					    volatile unsigned long *addr)
+{
+	unsigned long mask = BIT_MASK(nr);
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	unsigned long old = *p;
+
+	*p = old ^ mask;
+	return (old & mask) != 0;
+}
+
+/**
+ * test_bit - Determine whether a bit is set
+ * @nr: bit number to test
+ * @addr: Address to start counting from
+ */
+static inline int test_bit(int nr, const volatile unsigned long *addr)
+{
+	return 1UL & (addr[BIT_WORD(nr)] >> (nr & (BITS_PER_LONG-1)));
+}
+
+#endif /* __ASM_SH_BITOPS_OP32_H */
diff --git a/arch/sh/include/asm/bitops.h b/arch/sh/include/asm/bitops.h
index 367930d8e5ae..ebe595b7ab1f 100644
--- a/arch/sh/include/asm/bitops.h
+++ b/arch/sh/include/asm/bitops.h
@@ -13,21 +13,22 @@
 
 #ifdef CONFIG_GUSA_RB
 #include <asm/bitops-grb.h>
+#elif defined(CONFIG_CPU_SH2A)
+#include <asm-generic/bitops/atomic.h>
+#include <asm/bitops-op32.h>
 #elif defined(CONFIG_CPU_SH4A)
 #include <asm/bitops-llsc.h>
 #else
-#include <asm/bitops-irq.h>
+#include <asm-generic/bitops/atomic.h>
+#include <asm-generic/bitops/non-atomic.h>
 #endif
 
-
 /*
  * clear_bit() doesn't provide any barrier for the compiler.
  */
 #define smp_mb__before_clear_bit()	barrier()
 #define smp_mb__after_clear_bit()	barrier()
 
-#include <asm-generic/bitops/non-atomic.h>
-
 #ifdef CONFIG_SUPERH32
 static inline unsigned long ffz(unsigned long word)
 {
diff --git a/arch/sh/include/asm/bugs.h b/arch/sh/include/asm/bugs.h
index 121b2ecddfc3..4924ff6f5439 100644
--- a/arch/sh/include/asm/bugs.h
+++ b/arch/sh/include/asm/bugs.h
@@ -25,7 +25,7 @@ static void __init check_bugs(void)
 	case CPU_SH7619:
 		*p++ = '2';
 		break;
-	case CPU_SH7203 ... CPU_MXG:
+	case CPU_SH7201 ... CPU_MXG:
 		*p++ = '2';
 		*p++ = 'a';
 		break;
diff --git a/arch/sh/include/asm/elf.h b/arch/sh/include/asm/elf.h
index 9eb9036a1bdc..9381397ebeb8 100644
--- a/arch/sh/include/asm/elf.h
+++ b/arch/sh/include/asm/elf.h
@@ -204,7 +204,7 @@ do {									\
 #define ARCH_HAS_SETUP_ADDITIONAL_PAGES
 struct linux_binprm;
 extern int arch_setup_additional_pages(struct linux_binprm *bprm,
-				       int executable_stack);
+				       int uses_interp);
 
 extern unsigned int vdso_enabled;
 extern void __kernel_vsyscall;
diff --git a/arch/sh/include/asm/ftrace.h b/arch/sh/include/asm/ftrace.h
index 3aed362c9463..8fea7d8c8258 100644
--- a/arch/sh/include/asm/ftrace.h
+++ b/arch/sh/include/asm/ftrace.h
@@ -1,8 +1,34 @@
 #ifndef __ASM_SH_FTRACE_H
 #define __ASM_SH_FTRACE_H
 
+#ifdef CONFIG_FUNCTION_TRACER
+
+#define MCOUNT_INSN_SIZE	4 /* sizeof mcount call */
+
 #ifndef __ASSEMBLY__
 extern void mcount(void);
-#endif
+
+#define MCOUNT_ADDR		((long)(mcount))
+
+#ifdef CONFIG_DYNAMIC_FTRACE
+#define CALLER_ADDR		((long)(ftrace_caller))
+#define STUB_ADDR		((long)(ftrace_stub))
+
+#define MCOUNT_INSN_OFFSET	((STUB_ADDR - CALLER_ADDR) >> 1)
+
+struct dyn_arch_ftrace {
+	/* No extra data needed on sh */
+};
+
+#endif /* CONFIG_DYNAMIC_FTRACE */
+
+static inline unsigned long ftrace_call_adjust(unsigned long addr)
+{
+	/* 'addr' is the memory table address. */
+	return addr;
+}
+
+#endif /* __ASSEMBLY__ */
+#endif /* CONFIG_FUNCTION_TRACER */
 
 #endif /* __ASM_SH_FTRACE_H */
diff --git a/arch/sh/include/asm/io.h b/arch/sh/include/asm/io.h
index 65eaae34e753..61f6dae40534 100644
--- a/arch/sh/include/asm/io.h
+++ b/arch/sh/include/asm/io.h
@@ -260,6 +260,10 @@ __ioremap_mode(unsigned long offset, unsigned long size, unsigned long flags)
 
 		return (void __iomem *)P2SEGADDR(offset);
 	}
+
+	/* P4 above the store queues are always mapped. */
+	if (unlikely(offset >= P3_ADDR_MAX))
+		return (void __iomem *)P4SEGADDR(offset);
 #endif
 
 	return __ioremap(offset, size, flags);
diff --git a/arch/sh/include/asm/mutex-llsc.h b/arch/sh/include/asm/mutex-llsc.h
new file mode 100644
index 000000000000..7c75af5e734b
--- /dev/null
+++ b/arch/sh/include/asm/mutex-llsc.h
@@ -0,0 +1,107 @@
+/*
+ * arch/sh/include/asm/mutex-llsc.h
+ *
+ * SH-4A optimized mutex locking primitives
+ *
+ * Please look into asm-generic/mutex-xchg.h for a formal definition.
+ */
+#ifndef __ASM_SH_MUTEX_LLSC_H
+#define __ASM_SH_MUTEX_LLSC_H
+
+/*
+ * Attempting to lock a mutex on SH4A is done like in ARMv6+ architecure.
+ * with a bastardized atomic decrement (it is not a reliable atomic decrement
+ * but it satisfies the defined semantics for our purpose, while being
+ * smaller and faster than a real atomic decrement or atomic swap.
+ * The idea is to attempt  decrementing the lock value only once. If once
+ * decremented it isn't zero, or if its store-back fails due to a dispute
+ * on the exclusive store, we simply bail out immediately through the slow
+ * path where the lock will be reattempted until it succeeds.
+ */
+static inline void
+__mutex_fastpath_lock(atomic_t *count, void (*fail_fn)(atomic_t *))
+{
+	int __res;
+
+	__asm__ __volatile__ (
+		"movli.l	@%1, %0	\n"
+		"dt		%0	\n"
+		"movco.l	%0, @%1	\n"
+		: "=&z" (__res)
+		: "r" (&(count)->counter)
+		: "t");
+
+	if (unlikely(__res != 0))
+		fail_fn(count);
+}
+
+static inline int
+__mutex_fastpath_lock_retval(atomic_t *count, int (*fail_fn)(atomic_t *))
+{
+	int __res;
+
+	__asm__ __volatile__ (
+		"movli.l	@%1, %0	\n"
+		"dt		%0	\n"
+		"movco.l	%0, @%1	\n"
+		: "=&z" (__res)
+		: "r" (&(count)->counter)
+		: "t");
+
+	if (unlikely(__res != 0))
+		__res = fail_fn(count);
+
+	return __res;
+}
+
+static inline void
+__mutex_fastpath_unlock(atomic_t *count, void (*fail_fn)(atomic_t *))
+{
+	int __res;
+
+	__asm__ __volatile__ (
+		"1: movli.l	@%1, %0	\n\t"
+		"add		#1, %0	\n\t"
+		"movco.l	%0, @%1 \n\t"
+		"bf		1b\n\t"
+		: "=&z" (__res)
+		: "r" (&(count)->counter)
+		: "t");
+
+	if (unlikely(__res <= 0))
+		fail_fn(count);
+}
+
+/*
+ * If the unlock was done on a contended lock, or if the unlock simply fails
+ * then the mutex remains locked.
+ */
+#define __mutex_slowpath_needs_to_unlock()	1
+
+/*
+ * For __mutex_fastpath_trylock we do an atomic decrement and check the
+ * result and put it in the __res variable.
+ */
+static inline int
+__mutex_fastpath_trylock(atomic_t *count, int (*fail_fn)(atomic_t *))
+{
+	int __res, __orig;
+
+	__asm__ __volatile__ (
+		"1: movli.l	@%2, %0		\n\t"
+		"dt		%0		\n\t"
+		"movco.l	%0,@%2		\n\t"
+		"bf		1b		\n\t"
+		"cmp/eq		#0,%0		\n\t"
+		"bt		2f		\n\t"
+		"mov		#0, %1		\n\t"
+		"bf		3f		\n\t"
+		"2: mov		#1, %1		\n\t"
+		"3:				"
+		: "=&z" (__orig), "=&r" (__res)
+		: "r" (&count->counter)
+		: "t");
+
+	return __res;
+}
+#endif /* __ASM_SH_MUTEX_LLSC_H */
diff --git a/arch/sh/include/asm/mutex.h b/arch/sh/include/asm/mutex.h
index 458c1f7fbc18..d8e37716a4a0 100644
--- a/arch/sh/include/asm/mutex.h
+++ b/arch/sh/include/asm/mutex.h
@@ -5,5 +5,8 @@
  * implementation in place, or pick the atomic_xchg() based generic
  * implementation. (see asm-generic/mutex-xchg.h for details)
  */
-
+#if defined(CONFIG_CPU_SH4A)
+#include <asm/mutex-llsc.h>
+#else
 #include <asm-generic/mutex-dec.h>
+#endif
diff --git a/arch/sh/include/asm/pm.h b/arch/sh/include/asm/pm.h
deleted file mode 100644
index 56fdbd6b1c94..000000000000
--- a/arch/sh/include/asm/pm.h
+++ /dev/null
@@ -1,17 +0,0 @@
-/*
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file "COPYING" in the main directory of this archive
- * for more details.
- *
- * Copyright 2006 (c) Andriy Skulysh <askulysh@gmail.com>
- *
- */
-#ifndef __ASM_SH_PM_H
-#define __ASM_SH_PM_H
-
-extern u8 wakeup_start;
-extern u8 wakeup_end;
-
-void pm_enter(void);
-
-#endif
diff --git a/arch/sh/include/asm/processor.h b/arch/sh/include/asm/processor.h
index 693364a20ad7..1ef4b24d7619 100644
--- a/arch/sh/include/asm/processor.h
+++ b/arch/sh/include/asm/processor.h
@@ -18,7 +18,7 @@ enum cpu_type {
 	CPU_SH7619,
 
 	/* SH-2A types */
-	CPU_SH7203, CPU_SH7206, CPU_SH7263, CPU_MXG,
+	CPU_SH7201, CPU_SH7203, CPU_SH7206, CPU_SH7263, CPU_MXG,
 
 	/* SH-3 types */
 	CPU_SH7705, CPU_SH7706, CPU_SH7707,
@@ -82,6 +82,9 @@ extern struct sh_cpuinfo cpu_data[];
 #define current_cpu_data cpu_data[smp_processor_id()]
 #define raw_current_cpu_data cpu_data[raw_smp_processor_id()]
 
+#define cpu_sleep()	__asm__ __volatile__ ("sleep" : : : "memory")
+#define cpu_relax()	barrier()
+
 /* Forward decl */
 struct seq_operations;
 
diff --git a/arch/sh/include/asm/processor_32.h b/arch/sh/include/asm/processor_32.h
index a46a0207e977..2bfb7353493a 100644
--- a/arch/sh/include/asm/processor_32.h
+++ b/arch/sh/include/asm/processor_32.h
@@ -175,6 +175,7 @@ static __inline__ void enable_fpu(void)
 
 void show_trace(struct task_struct *tsk, unsigned long *sp,
 		struct pt_regs *regs);
+void show_code(struct pt_regs *regs);
 extern unsigned long get_wchan(struct task_struct *p);
 
 #define KSTK_EIP(tsk)  (task_pt_regs(tsk)->pc)
@@ -182,9 +183,6 @@ extern unsigned long get_wchan(struct task_struct *p);
 
 #define user_stack_pointer(regs)	((regs)->regs[15])
 
-#define cpu_sleep()	__asm__ __volatile__ ("sleep" : : : "memory")
-#define cpu_relax()	barrier()
-
 #if defined(CONFIG_CPU_SH2A) || defined(CONFIG_CPU_SH3) || \
     defined(CONFIG_CPU_SH4)
 #define PREFETCH_STRIDE		L1_CACHE_BYTES
diff --git a/arch/sh/include/asm/processor_64.h b/arch/sh/include/asm/processor_64.h
index b0b4824dfc4c..96067e9397ea 100644
--- a/arch/sh/include/asm/processor_64.h
+++ b/arch/sh/include/asm/processor_64.h
@@ -228,7 +228,5 @@ extern unsigned long get_wchan(struct task_struct *p);
 
 #define user_stack_pointer(regs)	((regs)->sp)
 
-#define cpu_relax()	barrier()
-
 #endif	/* __ASSEMBLY__ */
 #endif /* __ASM_SH_PROCESSOR_64_H */
diff --git a/arch/sh/include/asm/unaligned-sh4a.h b/arch/sh/include/asm/unaligned-sh4a.h
new file mode 100644
index 000000000000..d8f89770275b
--- /dev/null
+++ b/arch/sh/include/asm/unaligned-sh4a.h
@@ -0,0 +1,258 @@
+#ifndef __ASM_SH_UNALIGNED_SH4A_H
+#define __ASM_SH_UNALIGNED_SH4A_H
+
+/*
+ * SH-4A has support for unaligned 32-bit loads, and 32-bit loads only.
+ * Support for 16 and 64-bit accesses are done through shifting and
+ * masking relative to the endianness. Unaligned stores are not supported
+ * by the instruction encoding, so these continue to use the packed
+ * struct.
+ *
+ * The same note as with the movli.l/movco.l pair applies here, as long
+ * as the load is gauranteed to be inlined, nothing else will hook in to
+ * r0 and we get the return value for free.
+ *
+ * NOTE: Due to the fact we require r0 encoding, care should be taken to
+ * avoid mixing these heavily with other r0 consumers, such as the atomic
+ * ops. Failure to adhere to this can result in the compiler running out
+ * of spill registers and blowing up when building at low optimization
+ * levels. See http://gcc.gnu.org/bugzilla/show_bug.cgi?id=34777.
+ */
+#include <linux/types.h>
+#include <asm/byteorder.h>
+
+static __always_inline u32 __get_unaligned_cpu32(const u8 *p)
+{
+	unsigned long unaligned;
+
+	__asm__ __volatile__ (
+		"movua.l	@%1, %0\n\t"
+		 : "=z" (unaligned)
+		 : "r" (p)
+	);
+
+	return unaligned;
+}
+
+struct __una_u16 { u16 x __attribute__((packed)); };
+struct __una_u32 { u32 x __attribute__((packed)); };
+struct __una_u64 { u64 x __attribute__((packed)); };
+
+static inline u16 __get_unaligned_cpu16(const u8 *p)
+{
+#ifdef __LITTLE_ENDIAN
+	return __get_unaligned_cpu32(p) & 0xffff;
+#else
+	return __get_unaligned_cpu32(p) >> 16;
+#endif
+}
+
+/*
+ * Even though movua.l supports auto-increment on the read side, it can
+ * only store to r0 due to instruction encoding constraints, so just let
+ * the compiler sort it out on its own.
+ */
+static inline u64 __get_unaligned_cpu64(const u8 *p)
+{
+#ifdef __LITTLE_ENDIAN
+	return (u64)__get_unaligned_cpu32(p + 4) << 32 |
+		    __get_unaligned_cpu32(p);
+#else
+	return (u64)__get_unaligned_cpu32(p) << 32 |
+		    __get_unaligned_cpu32(p + 4);
+#endif
+}
+
+static inline u16 get_unaligned_le16(const void *p)
+{
+	return le16_to_cpu(__get_unaligned_cpu16(p));
+}
+
+static inline u32 get_unaligned_le32(const void *p)
+{
+	return le32_to_cpu(__get_unaligned_cpu32(p));
+}
+
+static inline u64 get_unaligned_le64(const void *p)
+{
+	return le64_to_cpu(__get_unaligned_cpu64(p));
+}
+
+static inline u16 get_unaligned_be16(const void *p)
+{
+	return be16_to_cpu(__get_unaligned_cpu16(p));
+}
+
+static inline u32 get_unaligned_be32(const void *p)
+{
+	return be32_to_cpu(__get_unaligned_cpu32(p));
+}
+
+static inline u64 get_unaligned_be64(const void *p)
+{
+	return be64_to_cpu(__get_unaligned_cpu64(p));
+}
+
+static inline void __put_le16_noalign(u8 *p, u16 val)
+{
+	*p++ = val;
+	*p++ = val >> 8;
+}
+
+static inline void __put_le32_noalign(u8 *p, u32 val)
+{
+	__put_le16_noalign(p, val);
+	__put_le16_noalign(p + 2, val >> 16);
+}
+
+static inline void __put_le64_noalign(u8 *p, u64 val)
+{
+	__put_le32_noalign(p, val);
+	__put_le32_noalign(p + 4, val >> 32);
+}
+
+static inline void __put_be16_noalign(u8 *p, u16 val)
+{
+	*p++ = val >> 8;
+	*p++ = val;
+}
+
+static inline void __put_be32_noalign(u8 *p, u32 val)
+{
+	__put_be16_noalign(p, val >> 16);
+	__put_be16_noalign(p + 2, val);
+}
+
+static inline void __put_be64_noalign(u8 *p, u64 val)
+{
+	__put_be32_noalign(p, val >> 32);
+	__put_be32_noalign(p + 4, val);
+}
+
+static inline void put_unaligned_le16(u16 val, void *p)
+{
+#ifdef __LITTLE_ENDIAN
+	((struct __una_u16 *)p)->x = val;
+#else
+	__put_le16_noalign(p, val);
+#endif
+}
+
+static inline void put_unaligned_le32(u32 val, void *p)
+{
+#ifdef __LITTLE_ENDIAN
+	((struct __una_u32 *)p)->x = val;
+#else
+	__put_le32_noalign(p, val);
+#endif
+}
+
+static inline void put_unaligned_le64(u64 val, void *p)
+{
+#ifdef __LITTLE_ENDIAN
+	((struct __una_u64 *)p)->x = val;
+#else
+	__put_le64_noalign(p, val);
+#endif
+}
+
+static inline void put_unaligned_be16(u16 val, void *p)
+{
+#ifdef __BIG_ENDIAN
+	((struct __una_u16 *)p)->x = val;
+#else
+	__put_be16_noalign(p, val);
+#endif
+}
+
+static inline void put_unaligned_be32(u32 val, void *p)
+{
+#ifdef __BIG_ENDIAN
+	((struct __una_u32 *)p)->x = val;
+#else
+	__put_be32_noalign(p, val);
+#endif
+}
+
+static inline void put_unaligned_be64(u64 val, void *p)
+{
+#ifdef __BIG_ENDIAN
+	((struct __una_u64 *)p)->x = val;
+#else
+	__put_be64_noalign(p, val);
+#endif
+}
+
+/*
+ * Cause a link-time error if we try an unaligned access other than
+ * 1,2,4 or 8 bytes long
+ */
+extern void __bad_unaligned_access_size(void);
+
+#define __get_unaligned_le(ptr) ((__force typeof(*(ptr)))({			\
+	__builtin_choose_expr(sizeof(*(ptr)) == 1, *(ptr),			\
+	__builtin_choose_expr(sizeof(*(ptr)) == 2, get_unaligned_le16((ptr)),	\
+	__builtin_choose_expr(sizeof(*(ptr)) == 4, get_unaligned_le32((ptr)),	\
+	__builtin_choose_expr(sizeof(*(ptr)) == 8, get_unaligned_le64((ptr)),	\
+	__bad_unaligned_access_size()))));					\
+	}))
+
+#define __get_unaligned_be(ptr) ((__force typeof(*(ptr)))({			\
+	__builtin_choose_expr(sizeof(*(ptr)) == 1, *(ptr),			\
+	__builtin_choose_expr(sizeof(*(ptr)) == 2, get_unaligned_be16((ptr)),	\
+	__builtin_choose_expr(sizeof(*(ptr)) == 4, get_unaligned_be32((ptr)),	\
+	__builtin_choose_expr(sizeof(*(ptr)) == 8, get_unaligned_be64((ptr)),	\
+	__bad_unaligned_access_size()))));					\
+	}))
+
+#define __put_unaligned_le(val, ptr) ({					\
+	void *__gu_p = (ptr);						\
+	switch (sizeof(*(ptr))) {					\
+	case 1:								\
+		*(u8 *)__gu_p = (__force u8)(val);			\
+		break;							\
+	case 2:								\
+		put_unaligned_le16((__force u16)(val), __gu_p);		\
+		break;							\
+	case 4:								\
+		put_unaligned_le32((__force u32)(val), __gu_p);		\
+		break;							\
+	case 8:								\
+		put_unaligned_le64((__force u64)(val), __gu_p);		\
+		break;							\
+	default:							\
+		__bad_unaligned_access_size();				\
+		break;							\
+	}								\
+	(void)0; })
+
+#define __put_unaligned_be(val, ptr) ({					\
+	void *__gu_p = (ptr);						\
+	switch (sizeof(*(ptr))) {					\
+	case 1:								\
+		*(u8 *)__gu_p = (__force u8)(val);			\
+		break;							\
+	case 2:								\
+		put_unaligned_be16((__force u16)(val), __gu_p);		\
+		break;							\
+	case 4:								\
+		put_unaligned_be32((__force u32)(val), __gu_p);		\
+		break;							\
+	case 8:								\
+		put_unaligned_be64((__force u64)(val), __gu_p);		\
+		break;							\
+	default:							\
+		__bad_unaligned_access_size();				\
+		break;							\
+	}								\
+	(void)0; })
+
+#ifdef __LITTLE_ENDIAN
+# define get_unaligned __get_unaligned_le
+# define put_unaligned __put_unaligned_le
+#else
+# define get_unaligned __get_unaligned_be
+# define put_unaligned __put_unaligned_be
+#endif
+
+#endif /* __ASM_SH_UNALIGNED_SH4A_H */
diff --git a/arch/sh/include/asm/unaligned.h b/arch/sh/include/asm/unaligned.h
index c1641a01d50f..8c0ad5e4487a 100644
--- a/arch/sh/include/asm/unaligned.h
+++ b/arch/sh/include/asm/unaligned.h
@@ -1,7 +1,11 @@
 #ifndef _ASM_SH_UNALIGNED_H
 #define _ASM_SH_UNALIGNED_H
 
-/* SH can't handle unaligned accesses. */
+#ifdef CONFIG_CPU_SH4A
+/* SH-4A can handle unaligned loads in a relatively neutered fashion. */
+#include <asm/unaligned-sh4a.h>
+#else
+/* Otherwise, SH can't handle unaligned accesses. */
 #ifdef __LITTLE_ENDIAN__
 # include <linux/unaligned/le_struct.h>
 # include <linux/unaligned/be_byteshift.h>
@@ -15,5 +19,6 @@
 # define get_unaligned	__get_unaligned_be
 # define put_unaligned	__put_unaligned_be
 #endif
+#endif
 
 #endif /* _ASM_SH_UNALIGNED_H */
diff --git a/arch/sh/include/cpu-sh3/cpu/gpio.h b/arch/sh/include/cpu-sh3/cpu/gpio.h
index 4e53eb314b8f..9a22b882f3dc 100644
--- a/arch/sh/include/cpu-sh3/cpu/gpio.h
+++ b/arch/sh/include/cpu-sh3/cpu/gpio.h
@@ -62,6 +62,20 @@
 #define PORT_PSELC	0xA4050128UL
 #define PORT_PSELD	0xA405012AUL
 
+#elif defined(CONFIG_CPU_SUBTYPE_SH7709)
+
+/* Control registers */
+#define PORT_PACR       0xa4000100UL
+#define PORT_PBCR       0xa4000102UL
+#define PORT_PCCR       0xa4000104UL
+#define PORT_PFCR       0xa400010aUL
+
+/* Data registers */
+#define PORT_PADR       0xa4000120UL
+#define PORT_PBDR       0xa4000122UL
+#define PORT_PCDR       0xa4000124UL
+#define PORT_PFDR       0xa400012aUL
+
 #endif
 
 #endif
diff --git a/arch/sh/include/mach-se/mach/se.h b/arch/sh/include/mach-se/mach/se.h
index eb23000e1bbe..14be91c5a2f0 100644
--- a/arch/sh/include/mach-se/mach/se.h
+++ b/arch/sh/include/mach-se/mach/se.h
@@ -68,6 +68,24 @@
 #define BCR_ILCRF	(PA_BCR + 10)
 #define BCR_ILCRG	(PA_BCR + 12)
 
+#if defined(CONFIG_CPU_SUBTYPE_SH7709)
+#define INTC_IRR0       0xa4000004UL
+#define INTC_IRR1       0xa4000006UL
+#define INTC_IRR2       0xa4000008UL
+
+#define INTC_ICR0       0xfffffee0UL
+#define INTC_ICR1       0xa4000010UL
+#define INTC_ICR2       0xa4000012UL
+#define INTC_INTER      0xa4000014UL
+
+#define INTC_IPRC       0xa4000016UL
+#define INTC_IPRD       0xa4000018UL
+#define INTC_IPRE       0xa400001aUL
+
+#define IRQ0_IRQ        32
+#define IRQ1_IRQ        33
+#endif
+
 #if defined(CONFIG_CPU_SUBTYPE_SH7705)
 #define IRQ_STNIC	12
 #define IRQ_CFCARD	14
diff --git a/arch/sh/include/mach-se/mach/se7343.h b/arch/sh/include/mach-se/mach/se7343.h
index 98458460e632..749914b400fb 100644
--- a/arch/sh/include/mach-se/mach/se7343.h
+++ b/arch/sh/include/mach-se/mach/se7343.h
@@ -118,9 +118,6 @@
 #define FPGA_IN		0xb1400000
 #define FPGA_OUT	0xb1400002
 
-#define __IO_PREFIX	sh7343se
-#include <asm/io_generic.h>
-
 #define IRQ0_IRQ        32
 #define IRQ1_IRQ        33
 #define IRQ4_IRQ        36
@@ -132,8 +129,10 @@
 #define SE7343_FPGA_IRQ_MRSHPC3	3
 #define SE7343_FPGA_IRQ_SMC	6	/* EXT_IRQ2 */
 #define SE7343_FPGA_IRQ_USB	8
+#define SE7343_FPGA_IRQ_UARTA	10
+#define SE7343_FPGA_IRQ_UARTB	11
 
-#define SE7343_FPGA_IRQ_NR	11
+#define SE7343_FPGA_IRQ_NR	12
 #define SE7343_FPGA_IRQ_BASE	120
 
 #define MRSHPC_IRQ3    	(SE7343_FPGA_IRQ_BASE + SE7343_FPGA_IRQ_MRSHPC3)
@@ -142,6 +141,8 @@
 #define MRSHPC_IRQ0    	(SE7343_FPGA_IRQ_BASE + SE7343_FPGA_IRQ_MRSHPC0)
 #define SMC_IRQ		(SE7343_FPGA_IRQ_BASE + SE7343_FPGA_IRQ_SMC)
 #define USB_IRQ		(SE7343_FPGA_IRQ_BASE + SE7343_FPGA_IRQ_USB)
+#define UARTA_IRQ	(SE7343_FPGA_IRQ_BASE + SE7343_FPGA_IRQ_UARTA)
+#define UARTB_IRQ	(SE7343_FPGA_IRQ_BASE + SE7343_FPGA_IRQ_UARTB)
 
 /* arch/sh/boards/se/7343/irq.c */
 void init_7343se_IRQ(void);
diff --git a/arch/sh/kernel/Makefile_32 b/arch/sh/kernel/Makefile_32
index 48edfb145fb4..10a34c3ae647 100644
--- a/arch/sh/kernel/Makefile_32
+++ b/arch/sh/kernel/Makefile_32
@@ -4,9 +4,15 @@
 
 extra-y	:= head_32.o init_task.o vmlinux.lds
 
-obj-y	:= debugtraps.o io.o io_generic.o irq.o machvec.o process_32.o \
-	   ptrace_32.o setup.o signal_32.o sys_sh.o sys_sh32.o \
-	   syscalls_32.o time_32.o topology.o traps.o traps_32.o
+ifdef CONFIG_FUNCTION_TRACER
+# Do not profile debug and lowlevel utilities
+CFLAGS_REMOVE_ftrace.o = -pg
+endif
+
+obj-y	:= debugtraps.o disassemble.o idle.o io.o io_generic.o irq.o	\
+	   machvec.o process_32.o ptrace_32.o setup.o signal_32.o	\
+	   sys_sh.o sys_sh32.o syscalls_32.o time_32.o topology.o	\
+	   traps.o traps_32.o
 
 obj-y				+= cpu/ timers/
 obj-$(CONFIG_VSYSCALL)		+= vsyscall/
@@ -19,10 +25,10 @@ obj-$(CONFIG_MODULES)		+= sh_ksyms_32.o module.o
 obj-$(CONFIG_EARLY_PRINTK)	+= early_printk.o
 obj-$(CONFIG_KEXEC)		+= machine_kexec.o relocate_kernel.o
 obj-$(CONFIG_CRASH_DUMP)	+= crash_dump.o
-obj-$(CONFIG_PM)		+= pm.o
 obj-$(CONFIG_STACKTRACE)	+= stacktrace.o
 obj-$(CONFIG_IO_TRAPPED)	+= io_trapped.o
 obj-$(CONFIG_KPROBES)		+= kprobes.o
 obj-$(CONFIG_GENERIC_GPIO)	+= gpio.o
+obj-$(CONFIG_DYNAMIC_FTRACE)	+= ftrace.o
 
 EXTRA_CFLAGS += -Werror
diff --git a/arch/sh/kernel/Makefile_64 b/arch/sh/kernel/Makefile_64
index c97660b2b48d..ae4afc090062 100644
--- a/arch/sh/kernel/Makefile_64
+++ b/arch/sh/kernel/Makefile_64
@@ -1,6 +1,6 @@
 extra-y	:= head_64.o init_task.o vmlinux.lds
 
-obj-y	:= debugtraps.o io.o io_generic.o irq.o machvec.o process_64.o \
+obj-y	:= debugtraps.o idle.o io.o io_generic.o irq.o machvec.o process_64.o \
 	   ptrace_64.o setup.o signal_64.o sys_sh.o sys_sh64.o \
 	   syscalls_64.o time_64.o topology.o traps.o traps_64.o
 
@@ -15,7 +15,6 @@ obj-$(CONFIG_MODULES)		+= sh_ksyms_64.o module.o
 obj-$(CONFIG_EARLY_PRINTK)	+= early_printk.o
 obj-$(CONFIG_KEXEC)		+= machine_kexec.o relocate_kernel.o
 obj-$(CONFIG_CRASH_DUMP)	+= crash_dump.o
-obj-$(CONFIG_PM)		+= pm.o
 obj-$(CONFIG_STACKTRACE)	+= stacktrace.o
 obj-$(CONFIG_IO_TRAPPED)	+= io_trapped.o
 obj-$(CONFIG_GENERIC_GPIO)	+= gpio.o
diff --git a/arch/sh/kernel/cpu/clock.c b/arch/sh/kernel/cpu/clock.c
index b7e46d5bba43..7b17137536d6 100644
--- a/arch/sh/kernel/cpu/clock.c
+++ b/arch/sh/kernel/cpu/clock.c
@@ -117,6 +117,11 @@ int clk_enable(struct clk *clk)
 	unsigned long flags;
 	int ret;
 
+	if (!clk)
+		return -EINVAL;
+
+	clk_enable(clk->parent);
+
 	spin_lock_irqsave(&clock_lock, flags);
 	ret = __clk_enable(clk);
 	spin_unlock_irqrestore(&clock_lock, flags);
@@ -147,9 +152,14 @@ void clk_disable(struct clk *clk)
 {
 	unsigned long flags;
 
+	if (!clk)
+		return;
+
 	spin_lock_irqsave(&clock_lock, flags);
 	__clk_disable(clk);
 	spin_unlock_irqrestore(&clock_lock, flags);
+
+	clk_disable(clk->parent);
 }
 EXPORT_SYMBOL_GPL(clk_disable);
 
diff --git a/arch/sh/kernel/cpu/init.c b/arch/sh/kernel/cpu/init.c
index 75fb03d35670..d29e69c156f0 100644
--- a/arch/sh/kernel/cpu/init.c
+++ b/arch/sh/kernel/cpu/init.c
@@ -261,9 +261,11 @@ asmlinkage void __init sh_cpu_init(void)
 	cache_init();
 
 	if (raw_smp_processor_id() == 0) {
+#ifdef CONFIG_MMU
 		shm_align_mask = max_t(unsigned long,
 				       current_cpu_data.dcache.way_size - 1,
 				       PAGE_SIZE - 1);
+#endif
 
 		/* Boot CPU sets the cache shape */
 		detect_cache_shape();
diff --git a/arch/sh/kernel/cpu/sh2a/Makefile b/arch/sh/kernel/cpu/sh2a/Makefile
index 428450cc0809..45f85c77ef75 100644
--- a/arch/sh/kernel/cpu/sh2a/Makefile
+++ b/arch/sh/kernel/cpu/sh2a/Makefile
@@ -8,9 +8,10 @@ common-y	+= ex.o entry.o
 
 obj-$(CONFIG_SH_FPU)	+= fpu.o
 
-obj-$(CONFIG_CPU_SUBTYPE_SH7206)	+= setup-sh7206.o clock-sh7206.o
+obj-$(CONFIG_CPU_SUBTYPE_SH7201)	+= setup-sh7201.o clock-sh7201.o
 obj-$(CONFIG_CPU_SUBTYPE_SH7203)	+= setup-sh7203.o clock-sh7203.o
 obj-$(CONFIG_CPU_SUBTYPE_SH7263)	+= setup-sh7203.o clock-sh7203.o
+obj-$(CONFIG_CPU_SUBTYPE_SH7206)	+= setup-sh7206.o clock-sh7206.o
 obj-$(CONFIG_CPU_SUBTYPE_MXG)		+= setup-mxg.o clock-sh7206.o
 
 # Pinmux setup
diff --git a/arch/sh/kernel/cpu/sh2a/clock-sh7201.c b/arch/sh/kernel/cpu/sh2a/clock-sh7201.c
new file mode 100644
index 000000000000..020a96fe961a
--- /dev/null
+++ b/arch/sh/kernel/cpu/sh2a/clock-sh7201.c
@@ -0,0 +1,85 @@
+/*
+ * arch/sh/kernel/cpu/sh2a/clock-sh7201.c
+ *
+ * SH7201 support for the clock framework
+ *
+ *  Copyright (C) 2008 Peter Griffin  <pgriffin@mpc-data.co.uk>
+ *
+ * Based on clock-sh4.c
+ *  Copyright (C) 2005  Paul Mundt
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ */
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <asm/clock.h>
+#include <asm/freq.h>
+#include <asm/io.h>
+
+const static int pll1rate[]={1,2,3,4,6,8};
+const static int pfc_divisors[]={1,2,3,4,6,8,12};
+#define ifc_divisors pfc_divisors
+
+#if (CONFIG_SH_CLK_MD == 0)
+#define PLL2 (4)
+#elif (CONFIG_SH_CLK_MD == 2)
+#define PLL2 (2)
+#elif (CONFIG_SH_CLK_MD == 3)
+#define PLL2 (1)
+#else
+#error "Illegal Clock Mode!"
+#endif
+
+static void master_clk_init(struct clk *clk)
+{
+	clk->rate = 10000000 * PLL2 * pll1rate[(ctrl_inw(FREQCR) >> 8) & 0x0007];
+}
+
+static struct clk_ops sh7201_master_clk_ops = {
+	.init		= master_clk_init,
+};
+
+static void module_clk_recalc(struct clk *clk)
+{
+	int idx = (ctrl_inw(FREQCR) & 0x0007);
+	clk->rate = clk->parent->rate / pfc_divisors[idx];
+}
+
+static struct clk_ops sh7201_module_clk_ops = {
+	.recalc		= module_clk_recalc,
+};
+
+static void bus_clk_recalc(struct clk *clk)
+{
+	int idx = (ctrl_inw(FREQCR) & 0x0007);
+	clk->rate = clk->parent->rate / pfc_divisors[idx];
+}
+
+static struct clk_ops sh7201_bus_clk_ops = {
+	.recalc		= bus_clk_recalc,
+};
+
+static void cpu_clk_recalc(struct clk *clk)
+{
+	int idx = ((ctrl_inw(FREQCR) >> 4) & 0x0007);
+	clk->rate = clk->parent->rate / ifc_divisors[idx];
+}
+
+static struct clk_ops sh7201_cpu_clk_ops = {
+	.recalc		= cpu_clk_recalc,
+};
+
+static struct clk_ops *sh7201_clk_ops[] = {
+	&sh7201_master_clk_ops,
+	&sh7201_module_clk_ops,
+	&sh7201_bus_clk_ops,
+	&sh7201_cpu_clk_ops,
+};
+
+void __init arch_init_clk_ops(struct clk_ops **ops, int idx)
+{
+	if (idx < ARRAY_SIZE(sh7201_clk_ops))
+		*ops = sh7201_clk_ops[idx];
+}
diff --git a/arch/sh/kernel/cpu/sh2a/probe.c b/arch/sh/kernel/cpu/sh2a/probe.c
index 6e79132f6f30..e098e2f6aa08 100644
--- a/arch/sh/kernel/cpu/sh2a/probe.c
+++ b/arch/sh/kernel/cpu/sh2a/probe.c
@@ -18,16 +18,17 @@ int __init detect_cpu_and_cache_system(void)
 	/* All SH-2A CPUs have support for 16 and 32-bit opcodes.. */
 	boot_cpu_data.flags			|= CPU_HAS_OP32;
 
-#if defined(CONFIG_CPU_SUBTYPE_SH7203)
+#if defined(CONFIG_CPU_SUBTYPE_SH7201)
+	boot_cpu_data.type			= CPU_SH7201;
+	boot_cpu_data.flags			|= CPU_HAS_FPU;
+#elif defined(CONFIG_CPU_SUBTYPE_SH7203)
 	boot_cpu_data.type			= CPU_SH7203;
-	/* SH7203 has an FPU.. */
 	boot_cpu_data.flags			|= CPU_HAS_FPU;
 #elif defined(CONFIG_CPU_SUBTYPE_SH7263)
 	boot_cpu_data.type			= CPU_SH7263;
 	boot_cpu_data.flags			|= CPU_HAS_FPU;
 #elif defined(CONFIG_CPU_SUBTYPE_SH7206)
 	boot_cpu_data.type			= CPU_SH7206;
-	/* While SH7206 has a DSP.. */
 	boot_cpu_data.flags			|= CPU_HAS_DSP;
 #elif defined(CONFIG_CPU_SUBTYPE_MXG)
 	boot_cpu_data.type			= CPU_MXG;
diff --git a/arch/sh/kernel/cpu/sh2a/setup-sh7201.c b/arch/sh/kernel/cpu/sh2a/setup-sh7201.c
new file mode 100644
index 000000000000..0631e421c022
--- /dev/null
+++ b/arch/sh/kernel/cpu/sh2a/setup-sh7201.c
@@ -0,0 +1,331 @@
+/*
+ *  SH7201 setup
+ *
+ *  Copyright (C) 2008  Peter Griffin pgriffin@mpc-data.co.uk
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ */
+#include <linux/platform_device.h>
+#include <linux/init.h>
+#include <linux/serial.h>
+#include <linux/serial_sci.h>
+
+enum {
+	UNUSED = 0,
+
+	/* interrupt sources */
+	IRQ0, IRQ1, IRQ2, IRQ3, IRQ4, IRQ5, IRQ6, IRQ7,
+	PINT0, PINT1, PINT2, PINT3, PINT4, PINT5, PINT6, PINT7,
+	ADC_ADI,
+	MTU2_TGI0A, MTU2_TGI0B, MTU2_TGI0C, MTU2_TGI0D,
+	MTU2_TCI0V, MTU2_TGI0E, MTU2_TGI0F,
+	MTU2_TGI1A, MTU2_TGI1B, MTU2_TCI1V, MTU2_TCI1U,
+	MTU2_TGI2A, MTU2_TGI2B, MTU2_TCI2V, MTU2_TCI2U,
+	MTU2_TGI3A, MTU2_TGI3B, MTU2_TGI3C, MTU2_TGI3D, MTU2_TCI3V,
+	MTU2_TGI4A, MTU2_TGI4B, MTU2_TGI4C, MTU2_TGI4D, MTU2_TCI4V,
+	MTU2_TGI5U, MTU2_TGI5V, MTU2_TGI5W,
+	RTC_ARM, RTC_PRD, RTC_CUP,
+	WDT,
+	IIC30_STPI, IIC30_NAKI, IIC30_RXI, IIC30_TXI, IIC30_TEI,
+	IIC31_STPI, IIC31_NAKI, IIC31_RXI, IIC31_TXI, IIC31_TEI,
+	IIC32_STPI, IIC32_NAKI, IIC32_RXI, IIC32_TXI, IIC32_TEI,
+
+	DMAC0_DMINT0, DMAC1_DMINT1,
+	DMAC2_DMINT2, DMAC3_DMINT3,
+
+	SCIF0_BRI, SCIF0_ERI, SCIF0_RXI, SCIF0_TXI,
+	SCIF1_BRI, SCIF1_ERI, SCIF1_RXI, SCIF1_TXI,
+	SCIF2_BRI, SCIF2_ERI, SCIF2_RXI, SCIF2_TXI,
+	SCIF3_BRI, SCIF3_ERI, SCIF3_RXI, SCIF3_TXI,
+	SCIF4_BRI, SCIF4_ERI, SCIF4_RXI, SCIF4_TXI,
+	SCIF5_BRI, SCIF5_ERI, SCIF5_RXI, SCIF5_TXI,
+	SCIF6_BRI, SCIF6_ERI, SCIF6_RXI, SCIF6_TXI,
+	SCIF7_BRI, SCIF7_ERI, SCIF7_RXI, SCIF7_TXI,
+
+	DMAC0_DMINTA, DMAC4_DMINT4, DMAC5_DMINT5, DMAC6_DMINT6,
+	DMAC7_DMINT7,
+
+	RCAN0_ERS, RCAN0_OVR,
+	RCAN0_SLE,
+	RCAN0_RM0, RCAN0_RM1,
+
+	RCAN1_ERS, RCAN1_OVR,
+	RCAN1_SLE,
+	RCAN1_RM0, RCAN1_RM1,
+
+	SSI0_SSII, SSI1_SSII,
+
+	TMR0_CMIA0, TMR0_CMIB0, TMR0_OVI0,
+	TMR1_CMIA1, TMR1_CMIB1, TMR1_OVI1,
+
+	/* interrupt groups */
+
+	IRQ, PINT, ADC,
+	MTU20_ABCD, MTU20_VEF, MTU21_AB, MTU21_VU, MTU22_AB, MTU22_VU,
+	MTU23_ABCD, MTU24_ABCD, MTU25_UVW,
+	RTC, IIC30, IIC31, IIC32,
+	SCIF0, SCIF1, SCIF2, SCIF3, SCIF4, SCIF5, SCIF6, SCIF7,
+	RCAN0, RCAN1, TMR0, TMR1
+
+};
+
+static struct intc_vect vectors[] __initdata = {
+	INTC_IRQ(IRQ0, 64), INTC_IRQ(IRQ1, 65),
+	INTC_IRQ(IRQ2, 66), INTC_IRQ(IRQ3, 67),
+	INTC_IRQ(IRQ4, 68), INTC_IRQ(IRQ5, 69),
+	INTC_IRQ(IRQ6, 70), INTC_IRQ(IRQ7, 71),
+	INTC_IRQ(PINT0, 80), INTC_IRQ(PINT1, 81),
+	INTC_IRQ(PINT2, 82), INTC_IRQ(PINT3, 83),
+	INTC_IRQ(PINT4, 84), INTC_IRQ(PINT5, 85),
+	INTC_IRQ(PINT6, 86), INTC_IRQ(PINT7, 87),
+
+	INTC_IRQ(ADC_ADI, 92),
+
+	INTC_IRQ(MTU2_TGI0A, 108), INTC_IRQ(MTU2_TGI0B, 109),
+	INTC_IRQ(MTU2_TGI0C, 110), INTC_IRQ(MTU2_TGI0D, 111),
+	INTC_IRQ(MTU2_TCI0V, 112),
+	INTC_IRQ(MTU2_TGI0E, 113), INTC_IRQ(MTU2_TGI0F, 114),
+
+	INTC_IRQ(MTU2_TGI1A, 116), INTC_IRQ(MTU2_TGI1B, 117),
+	INTC_IRQ(MTU2_TCI1V, 120), INTC_IRQ(MTU2_TCI1U, 121),
+
+	INTC_IRQ(MTU2_TGI2A, 124), INTC_IRQ(MTU2_TGI2B, 125),
+	INTC_IRQ(MTU2_TCI2V, 128), INTC_IRQ(MTU2_TCI2U, 129),
+
+	INTC_IRQ(MTU2_TGI3A, 132), INTC_IRQ(MTU2_TGI3B, 133),
+	INTC_IRQ(MTU2_TGI3C, 134), INTC_IRQ(MTU2_TGI3D, 135),
+	INTC_IRQ(MTU2_TCI3V, 136),
+
+	INTC_IRQ(MTU2_TGI4A, 140), INTC_IRQ(MTU2_TGI4B, 141),
+	INTC_IRQ(MTU2_TGI4C, 142), INTC_IRQ(MTU2_TGI4D, 143),
+	INTC_IRQ(MTU2_TCI4V, 144),
+
+	INTC_IRQ(MTU2_TGI5U, 148), INTC_IRQ(MTU2_TGI5V, 149),
+	INTC_IRQ(MTU2_TGI5W, 150),
+
+	INTC_IRQ(RTC_ARM, 152), INTC_IRQ(RTC_PRD, 153),
+	INTC_IRQ(RTC_CUP, 154), INTC_IRQ(WDT, 156),
+
+	INTC_IRQ(IIC30_STPI, 157), INTC_IRQ(IIC30_NAKI, 158),
+	INTC_IRQ(IIC30_RXI, 159), INTC_IRQ(IIC30_TXI, 160),
+	INTC_IRQ(IIC30_TEI, 161),
+
+	INTC_IRQ(IIC31_STPI, 164), INTC_IRQ(IIC31_NAKI, 165),
+	INTC_IRQ(IIC31_RXI, 166), INTC_IRQ(IIC31_TXI, 167),
+	INTC_IRQ(IIC31_TEI, 168),
+
+	INTC_IRQ(IIC32_STPI, 170), INTC_IRQ(IIC32_NAKI, 171),
+	INTC_IRQ(IIC32_RXI, 172), INTC_IRQ(IIC32_TXI, 173),
+	INTC_IRQ(IIC32_TEI, 174),
+
+	INTC_IRQ(DMAC0_DMINT0, 176), INTC_IRQ(DMAC1_DMINT1, 177),
+	INTC_IRQ(DMAC2_DMINT2, 178), INTC_IRQ(DMAC3_DMINT3, 179),
+
+	INTC_IRQ(SCIF0_BRI, 180), INTC_IRQ(SCIF0_ERI, 181),
+	INTC_IRQ(SCIF0_RXI, 182), INTC_IRQ(SCIF0_TXI, 183),
+	INTC_IRQ(SCIF1_BRI, 184), INTC_IRQ(SCIF1_ERI, 185),
+	INTC_IRQ(SCIF1_RXI, 186), INTC_IRQ(SCIF1_TXI, 187),
+	INTC_IRQ(SCIF2_BRI, 188), INTC_IRQ(SCIF2_ERI, 189),
+	INTC_IRQ(SCIF2_RXI, 190), INTC_IRQ(SCIF2_TXI, 191),
+	INTC_IRQ(SCIF3_BRI, 192), INTC_IRQ(SCIF3_ERI, 193),
+	INTC_IRQ(SCIF3_RXI, 194), INTC_IRQ(SCIF3_TXI, 195),
+	INTC_IRQ(SCIF4_BRI, 196), INTC_IRQ(SCIF4_ERI, 197),
+	INTC_IRQ(SCIF4_RXI, 198), INTC_IRQ(SCIF4_TXI, 199),
+	INTC_IRQ(SCIF5_BRI, 200), INTC_IRQ(SCIF5_ERI, 201),
+	INTC_IRQ(SCIF5_RXI, 202), INTC_IRQ(SCIF5_TXI, 203),
+	INTC_IRQ(SCIF6_BRI, 204), INTC_IRQ(SCIF6_ERI, 205),
+	INTC_IRQ(SCIF6_RXI, 206), INTC_IRQ(SCIF6_TXI, 207),
+	INTC_IRQ(SCIF7_BRI, 208), INTC_IRQ(SCIF7_ERI, 209),
+	INTC_IRQ(SCIF7_RXI, 210), INTC_IRQ(SCIF7_TXI, 211),
+
+	INTC_IRQ(DMAC0_DMINTA, 212), INTC_IRQ(DMAC4_DMINT4, 216),
+	INTC_IRQ(DMAC5_DMINT5, 217), INTC_IRQ(DMAC6_DMINT6, 218),
+	INTC_IRQ(DMAC7_DMINT7, 219),
+
+	INTC_IRQ(RCAN0_ERS, 228), INTC_IRQ(RCAN0_OVR, 229),
+	INTC_IRQ(RCAN0_SLE, 230),
+	INTC_IRQ(RCAN0_RM0, 231), INTC_IRQ(RCAN0_RM1, 232),
+
+	INTC_IRQ(RCAN1_ERS, 234), INTC_IRQ(RCAN1_OVR, 235),
+	INTC_IRQ(RCAN1_SLE, 236),
+	INTC_IRQ(RCAN1_RM0, 237), INTC_IRQ(RCAN1_RM1, 238),
+
+	INTC_IRQ(SSI0_SSII, 244), INTC_IRQ(SSI1_SSII, 245),
+
+	INTC_IRQ(TMR0_CMIA0, 246), INTC_IRQ(TMR0_CMIB0, 247),
+	INTC_IRQ(TMR0_OVI0, 248),
+
+	INTC_IRQ(TMR1_CMIA1, 252), INTC_IRQ(TMR1_CMIB1, 253),
+	INTC_IRQ(TMR1_OVI1, 254),
+
+};
+
+static struct intc_group groups[] __initdata = {
+	INTC_GROUP(PINT, PINT0, PINT1, PINT2, PINT3,
+		   PINT4, PINT5, PINT6, PINT7),
+	INTC_GROUP(MTU20_ABCD, MTU2_TGI0A, MTU2_TGI0B, MTU2_TGI0C, MTU2_TGI0D),
+	INTC_GROUP(MTU20_VEF, MTU2_TCI0V, MTU2_TGI0E, MTU2_TGI0F),
+
+	INTC_GROUP(MTU21_AB, MTU2_TGI1A, MTU2_TGI1B),
+	INTC_GROUP(MTU21_VU, MTU2_TCI1V, MTU2_TCI1U),
+	INTC_GROUP(MTU22_AB, MTU2_TGI2A, MTU2_TGI2B),
+	INTC_GROUP(MTU22_VU, MTU2_TCI2V, MTU2_TCI2U),
+	INTC_GROUP(MTU23_ABCD, MTU2_TGI3A, MTU2_TGI3B, MTU2_TGI3C, MTU2_TGI3D),
+	INTC_GROUP(MTU24_ABCD, MTU2_TGI4A, MTU2_TGI4B, MTU2_TGI4C, MTU2_TGI4D),
+	INTC_GROUP(MTU25_UVW, MTU2_TGI5U, MTU2_TGI5V, MTU2_TGI5W),
+	INTC_GROUP(RTC, RTC_ARM, RTC_PRD, RTC_CUP ),
+
+	INTC_GROUP(IIC30, IIC30_STPI, IIC30_NAKI, IIC30_RXI, IIC30_TXI,
+		   IIC30_TEI),
+	INTC_GROUP(IIC31, IIC31_STPI, IIC31_NAKI, IIC31_RXI, IIC31_TXI,
+		   IIC31_TEI),
+	INTC_GROUP(IIC32, IIC32_STPI, IIC32_NAKI, IIC32_RXI, IIC32_TXI,
+		   IIC32_TEI),
+
+	INTC_GROUP(SCIF0, SCIF0_BRI, SCIF0_ERI, SCIF0_RXI, SCIF0_TXI),
+	INTC_GROUP(SCIF1, SCIF1_BRI, SCIF1_ERI, SCIF1_RXI, SCIF1_TXI),
+	INTC_GROUP(SCIF2, SCIF2_BRI, SCIF2_ERI, SCIF2_RXI, SCIF2_TXI),
+	INTC_GROUP(SCIF3, SCIF3_BRI, SCIF3_ERI, SCIF3_RXI, SCIF3_TXI),
+	INTC_GROUP(SCIF4, SCIF4_BRI, SCIF4_ERI, SCIF4_RXI, SCIF4_TXI),
+	INTC_GROUP(SCIF5, SCIF5_BRI, SCIF5_ERI, SCIF5_RXI, SCIF5_TXI),
+	INTC_GROUP(SCIF6, SCIF6_BRI, SCIF6_ERI, SCIF6_RXI, SCIF6_TXI),
+	INTC_GROUP(SCIF7, SCIF7_BRI, SCIF7_ERI, SCIF7_RXI, SCIF7_TXI),
+
+	INTC_GROUP(RCAN0, RCAN0_ERS, RCAN0_OVR, RCAN0_RM0, RCAN0_RM1,
+		   RCAN0_SLE),
+	INTC_GROUP(RCAN1, RCAN1_ERS, RCAN1_OVR, RCAN1_RM0, RCAN1_RM1,
+		   RCAN1_SLE),
+
+	INTC_GROUP(TMR0, TMR0_CMIA0, TMR0_CMIB0, TMR0_OVI0),
+	INTC_GROUP(TMR1, TMR1_CMIA1, TMR1_CMIB1, TMR1_OVI1),
+};
+
+static struct intc_prio_reg prio_registers[] __initdata = {
+	{ 0xfffe9418, 0, 16, 4, /* IPR01 */ { IRQ0, IRQ1, IRQ2, IRQ3 } },
+	{ 0xfffe941a, 0, 16, 4, /* IPR02 */ { IRQ4, IRQ5, IRQ6, IRQ7 } },
+	{ 0xfffe9420, 0, 16, 4, /* IPR05 */ { PINT, 0, ADC_ADI, 0 } },
+	{ 0xfffe9800, 0, 16, 4, /* IPR06 */ { 0, MTU20_ABCD, MTU20_VEF, MTU21_AB } },
+	{ 0xfffe9802, 0, 16, 4, /* IPR07 */ { MTU21_VU, MTU22_AB, MTU22_VU,  MTU23_ABCD } },
+	{ 0xfffe9804, 0, 16, 4, /* IPR08 */ { MTU2_TCI3V, MTU24_ABCD, MTU2_TCI4V, MTU25_UVW } },
+
+	{ 0xfffe9806, 0, 16, 4, /* IPR09 */ { RTC, WDT, IIC30, 0 } },
+	{ 0xfffe9808, 0, 16, 4, /* IPR10 */ { IIC31, IIC32, DMAC0_DMINT0, DMAC1_DMINT1 } },
+	{ 0xfffe980a, 0, 16, 4, /* IPR11 */ { DMAC2_DMINT2, DMAC3_DMINT3, SCIF0 , SCIF1 } },
+	{ 0xfffe980c, 0, 16, 4, /* IPR12 */ { SCIF2, SCIF3, SCIF4, SCIF5 } },
+	{ 0xfffe980e, 0, 16, 4, /* IPR13 */ { SCIF6, SCIF7, DMAC0_DMINTA, DMAC4_DMINT4  } },
+	{ 0xfffe9810, 0, 16, 4, /* IPR14 */ { DMAC5_DMINT5, DMAC6_DMINT6, DMAC7_DMINT7, 0 } },
+	{ 0xfffe9812, 0, 16, 4, /* IPR15 */ { 0, RCAN0, RCAN1, 0 } },
+	{ 0xfffe9814, 0, 16, 4, /* IPR16 */ { SSI0_SSII, SSI1_SSII, TMR0, TMR1 } },
+};
+
+static struct intc_mask_reg mask_registers[] __initdata = {
+	{ 0xfffe9408, 0, 16, /* PINTER */
+	  { 0, 0, 0, 0, 0, 0, 0, 0,
+	    PINT7, PINT6, PINT5, PINT4, PINT3, PINT2, PINT1, PINT0 } },
+};
+
+static DECLARE_INTC_DESC(intc_desc, "sh7201", vectors, groups,
+			 mask_registers, prio_registers, NULL);
+
+static struct plat_sci_port sci_platform_data[] = {
+	{
+		.mapbase	= 0xfffe8000,
+		.flags		= UPF_BOOT_AUTOCONF,
+		.type		= PORT_SCIF,
+		.irqs		= { 181, 182, 183, 180}
+	}, {
+		.mapbase	= 0xfffe8800,
+		.flags		= UPF_BOOT_AUTOCONF,
+		.type		= PORT_SCIF,
+		.irqs		= { 185, 186, 187, 184}
+	}, {
+		.mapbase	= 0xfffe9000,
+		.flags		= UPF_BOOT_AUTOCONF,
+		.type		= PORT_SCIF,
+		.irqs		= { 189, 186, 187, 188}
+	}, {
+		.mapbase	= 0xfffe9800,
+		.flags		= UPF_BOOT_AUTOCONF,
+		.type		= PORT_SCIF,
+		.irqs		= { 193, 194, 195, 192}
+	}, {
+		.mapbase	= 0xfffea000,
+		.flags		= UPF_BOOT_AUTOCONF,
+		.type		= PORT_SCIF,
+		.irqs		= { 196, 198, 199, 196}
+	}, {
+		.mapbase	= 0xfffea800,
+		.flags		= UPF_BOOT_AUTOCONF,
+		.type		= PORT_SCIF,
+		.irqs		= { 201, 202, 203, 200}
+	}, {
+		.mapbase	= 0xfffeb000,
+		.flags		= UPF_BOOT_AUTOCONF,
+		.type		= PORT_SCIF,
+		.irqs		= { 205, 206, 207, 204}
+	}, {
+		.mapbase	= 0xfffeb800,
+		.flags		= UPF_BOOT_AUTOCONF,
+		.type		= PORT_SCIF,
+		.irqs		= { 209, 210, 211, 208}
+	}, {
+		.flags = 0,
+	}
+};
+
+static struct platform_device sci_device = {
+	.name		= "sh-sci",
+	.id		= -1,
+	.dev		= {
+		.platform_data	= sci_platform_data,
+	},
+};
+
+static struct resource rtc_resources[] = {
+	[0] = {
+		.start	= 0xffff0800,
+		.end	= 0xffff2000 + 0x58 - 1,
+		.flags	= IORESOURCE_IO,
+	},
+	[1] = {
+		/* Period IRQ */
+		.start	= 153,
+		.flags	= IORESOURCE_IRQ,
+	},
+	[2] = {
+		/* Carry IRQ */
+		.start	= 154,
+		.flags	= IORESOURCE_IRQ,
+	},
+	[3] = {
+		/* Alarm IRQ */
+		.start	= 152,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device rtc_device = {
+	.name		= "sh-rtc",
+	.id		= -1,
+	.num_resources	= ARRAY_SIZE(rtc_resources),
+	.resource	= rtc_resources,
+};
+
+static struct platform_device *sh7201_devices[] __initdata = {
+	&sci_device,
+	&rtc_device,
+};
+
+static int __init sh7201_devices_setup(void)
+{
+	return platform_add_devices(sh7201_devices,
+				    ARRAY_SIZE(sh7201_devices));
+}
+__initcall(sh7201_devices_setup);
+
+void __init plat_irq_setup(void)
+{
+	register_intc_controller(&intc_desc);
+}
diff --git a/arch/sh/kernel/cpu/sh4/softfloat.c b/arch/sh/kernel/cpu/sh4/softfloat.c
index 2b747f3b02bd..42edf2e54e85 100644
--- a/arch/sh/kernel/cpu/sh4/softfloat.c
+++ b/arch/sh/kernel/cpu/sh4/softfloat.c
@@ -37,6 +37,7 @@
  */
 #include <linux/kernel.h>
 #include <cpu/fpu.h>
+#include <asm/div64.h>
 
 #define LIT64( a ) a##LL
 
@@ -67,16 +68,16 @@ typedef unsigned long long float64;
 extern void float_raise(unsigned int flags);	/* in fpu.c */
 extern int float_rounding_mode(void);	/* in fpu.c */
 
-inline bits64 extractFloat64Frac(float64 a);
-inline flag extractFloat64Sign(float64 a);
-inline int16 extractFloat64Exp(float64 a);
-inline int16 extractFloat32Exp(float32 a);
-inline flag extractFloat32Sign(float32 a);
-inline bits32 extractFloat32Frac(float32 a);
-inline float64 packFloat64(flag zSign, int16 zExp, bits64 zSig);
-inline void shift64RightJamming(bits64 a, int16 count, bits64 * zPtr);
-inline float32 packFloat32(flag zSign, int16 zExp, bits32 zSig);
-inline void shift32RightJamming(bits32 a, int16 count, bits32 * zPtr);
+bits64 extractFloat64Frac(float64 a);
+flag extractFloat64Sign(float64 a);
+int16 extractFloat64Exp(float64 a);
+int16 extractFloat32Exp(float32 a);
+flag extractFloat32Sign(float32 a);
+bits32 extractFloat32Frac(float32 a);
+float64 packFloat64(flag zSign, int16 zExp, bits64 zSig);
+void shift64RightJamming(bits64 a, int16 count, bits64 * zPtr);
+float32 packFloat32(flag zSign, int16 zExp, bits32 zSig);
+void shift32RightJamming(bits32 a, int16 count, bits32 * zPtr);
 float64 float64_sub(float64 a, float64 b);
 float32 float32_sub(float32 a, float32 b);
 float32 float32_add(float32 a, float32 b);
@@ -86,11 +87,11 @@ float32 float32_div(float32 a, float32 b);
 float32 float32_mul(float32 a, float32 b);
 float64 float64_mul(float64 a, float64 b);
 float32 float64_to_float32(float64 a);
-inline void add128(bits64 a0, bits64 a1, bits64 b0, bits64 b1, bits64 * z0Ptr,
+void add128(bits64 a0, bits64 a1, bits64 b0, bits64 b1, bits64 * z0Ptr,
 		   bits64 * z1Ptr);
-inline void sub128(bits64 a0, bits64 a1, bits64 b0, bits64 b1, bits64 * z0Ptr,
+void sub128(bits64 a0, bits64 a1, bits64 b0, bits64 b1, bits64 * z0Ptr,
 		   bits64 * z1Ptr);
-inline void mul64To128(bits64 a, bits64 b, bits64 * z0Ptr, bits64 * z1Ptr);
+void mul64To128(bits64 a, bits64 b, bits64 * z0Ptr, bits64 * z1Ptr);
 
 static int8 countLeadingZeros32(bits32 a);
 static int8 countLeadingZeros64(bits64 a);
@@ -110,42 +111,42 @@ static bits64 estimateDiv128To64(bits64 a0, bits64 a1, bits64 b);
 static void normalizeFloat32Subnormal(bits32 aSig, int16 * zExpPtr,
 				      bits32 * zSigPtr);
 
-inline bits64 extractFloat64Frac(float64 a)
+bits64 extractFloat64Frac(float64 a)
 {
 	return a & LIT64(0x000FFFFFFFFFFFFF);
 }
 
-inline flag extractFloat64Sign(float64 a)
+flag extractFloat64Sign(float64 a)
 {
 	return a >> 63;
 }
 
-inline int16 extractFloat64Exp(float64 a)
+int16 extractFloat64Exp(float64 a)
 {
 	return (a >> 52) & 0x7FF;
 }
 
-inline int16 extractFloat32Exp(float32 a)
+int16 extractFloat32Exp(float32 a)
 {
 	return (a >> 23) & 0xFF;
 }
 
-inline flag extractFloat32Sign(float32 a)
+flag extractFloat32Sign(float32 a)
 {
 	return a >> 31;
 }
 
-inline bits32 extractFloat32Frac(float32 a)
+bits32 extractFloat32Frac(float32 a)
 {
 	return a & 0x007FFFFF;
 }
 
-inline float64 packFloat64(flag zSign, int16 zExp, bits64 zSig)
+float64 packFloat64(flag zSign, int16 zExp, bits64 zSig)
 {
 	return (((bits64) zSign) << 63) + (((bits64) zExp) << 52) + zSig;
 }
 
-inline void shift64RightJamming(bits64 a, int16 count, bits64 * zPtr)
+void shift64RightJamming(bits64 a, int16 count, bits64 * zPtr)
 {
 	bits64 z;
 
@@ -338,12 +339,12 @@ static float64 addFloat64Sigs(float64 a, float64 b, flag zSign)
 
 }
 
-inline float32 packFloat32(flag zSign, int16 zExp, bits32 zSig)
+float32 packFloat32(flag zSign, int16 zExp, bits32 zSig)
 {
 	return (((bits32) zSign) << 31) + (((bits32) zExp) << 23) + zSig;
 }
 
-inline void shift32RightJamming(bits32 a, int16 count, bits32 * zPtr)
+void shift32RightJamming(bits32 a, int16 count, bits32 * zPtr)
 {
 	bits32 z;
 	if (count == 0) {
@@ -634,7 +635,7 @@ normalizeFloat64Subnormal(bits64 aSig, int16 * zExpPtr, bits64 * zSigPtr)
 	*zExpPtr = 1 - shiftCount;
 }
 
-inline void add128(bits64 a0, bits64 a1, bits64 b0, bits64 b1, bits64 * z0Ptr,
+void add128(bits64 a0, bits64 a1, bits64 b0, bits64 b1, bits64 * z0Ptr,
 		   bits64 * z1Ptr)
 {
 	bits64 z1;
@@ -644,7 +645,7 @@ inline void add128(bits64 a0, bits64 a1, bits64 b0, bits64 b1, bits64 * z0Ptr,
 	*z0Ptr = a0 + b0 + (z1 < a1);
 }
 
-inline void
+void
 sub128(bits64 a0, bits64 a1, bits64 b0, bits64 b1, bits64 * z0Ptr,
        bits64 * z1Ptr)
 {
@@ -656,11 +657,14 @@ static bits64 estimateDiv128To64(bits64 a0, bits64 a1, bits64 b)
 {
 	bits64 b0, b1;
 	bits64 rem0, rem1, term0, term1;
-	bits64 z;
+	bits64 z, tmp;
 	if (b <= a0)
 		return LIT64(0xFFFFFFFFFFFFFFFF);
 	b0 = b >> 32;
-	z = (b0 << 32 <= a0) ? LIT64(0xFFFFFFFF00000000) : (a0 / b0) << 32;
+	tmp = a0;
+	do_div(tmp, b0);
+
+	z = (b0 << 32 <= a0) ? LIT64(0xFFFFFFFF00000000) : tmp << 32;
 	mul64To128(b, z, &term0, &term1);
 	sub128(a0, a1, term0, term1, &rem0, &rem1);
 	while (((sbits64) rem0) < 0) {
@@ -669,11 +673,13 @@ static bits64 estimateDiv128To64(bits64 a0, bits64 a1, bits64 b)
 		add128(rem0, rem1, b0, b1, &rem0, &rem1);
 	}
 	rem0 = (rem0 << 32) | (rem1 >> 32);
-	z |= (b0 << 32 <= rem0) ? 0xFFFFFFFF : rem0 / b0;
+	tmp = rem0;
+	do_div(tmp, b0);
+	z |= (b0 << 32 <= rem0) ? 0xFFFFFFFF : tmp;
 	return z;
 }
 
-inline void mul64To128(bits64 a, bits64 b, bits64 * z0Ptr, bits64 * z1Ptr)
+void mul64To128(bits64 a, bits64 b, bits64 * z0Ptr, bits64 * z1Ptr)
 {
 	bits32 aHigh, aLow, bHigh, bLow;
 	bits64 z0, zMiddleA, zMiddleB, z1;
@@ -769,7 +775,8 @@ float32 float32_div(float32 a, float32 b)
 {
 	flag aSign, bSign, zSign;
 	int16 aExp, bExp, zExp;
-	bits32 aSig, bSig, zSig;
+	bits32 aSig, bSig;
+	uint64_t zSig;
 
 	aSig = extractFloat32Frac(a);
 	aExp = extractFloat32Exp(a);
@@ -804,11 +811,13 @@ float32 float32_div(float32 a, float32 b)
 		aSig >>= 1;
 		++zExp;
 	}
-	zSig = (((bits64) aSig) << 32) / bSig;
+	zSig = (((bits64) aSig) << 32);
+	do_div(zSig, bSig);
+
 	if ((zSig & 0x3F) == 0) {
 		zSig |= (((bits64) bSig) * zSig != ((bits64) aSig) << 32);
 	}
-	return roundAndPackFloat32(zSign, zExp, zSig);
+	return roundAndPackFloat32(zSign, zExp, (bits32)zSig);
 
 }
 
diff --git a/arch/sh/kernel/cpu/sh4a/clock-sh7722.c b/arch/sh/kernel/cpu/sh4a/clock-sh7722.c
index db913855c2fd..0e174af21874 100644
--- a/arch/sh/kernel/cpu/sh4a/clock-sh7722.c
+++ b/arch/sh/kernel/cpu/sh4a/clock-sh7722.c
@@ -229,7 +229,7 @@ struct frqcr_context sh7722_get_clk_context(const char *name)
 }
 
 /**
- * sh7722_find_divisors - find divisor for setting rate
+ * sh7722_find_div_index - find divisor for setting rate
  *
  * All sh7722 clocks use the same set of multipliers/divisors. This function
  * chooses correct divisor to set the rate of clock with parent clock that
@@ -238,7 +238,7 @@ struct frqcr_context sh7722_get_clk_context(const char *name)
  * @parent_rate: rate of parent clock
  * @rate: requested rate to be set
  */
-static int sh7722_find_divisors(unsigned long parent_rate, unsigned rate)
+static int sh7722_find_div_index(unsigned long parent_rate, unsigned rate)
 {
 	unsigned div2 = parent_rate * 2 / rate;
 	int index;
@@ -247,12 +247,12 @@ static int sh7722_find_divisors(unsigned long parent_rate, unsigned rate)
 		return -EINVAL;
 
 	for (index = 1; index < ARRAY_SIZE(divisors2); index++) {
-		if (div2 > divisors2[index] && div2 <= divisors2[index])
+		if (div2 > divisors2[index - 1] && div2 <= divisors2[index])
 			break;
 	}
 	if (index >= ARRAY_SIZE(divisors2))
 		index = ARRAY_SIZE(divisors2) - 1;
-	return divisors2[index];
+	return index;
 }
 
 static void sh7722_frqcr_recalc(struct clk *clk)
@@ -279,12 +279,12 @@ static int sh7722_frqcr_set_rate(struct clk *clk, unsigned long rate,
 		return -EINVAL;
 
 	/* look for multiplier/divisor pair */
-	div = sh7722_find_divisors(parent_rate, rate);
+	div = sh7722_find_div_index(parent_rate, rate);
 	if (div<0)
 		return div;
 
 	/* calculate new value of clock rate */
-	clk->rate = parent_rate * 2 / div;
+	clk->rate = parent_rate * 2 / divisors2[div];
 	frqcr = ctrl_inl(FRQCR);
 
 	/* FIXME: adjust as algo_id specifies */
@@ -353,7 +353,7 @@ static int sh7722_frqcr_set_rate(struct clk *clk, unsigned long rate,
 			int part_div;
 
 			if (likely(!err)) {
-				part_div = sh7722_find_divisors(parent_rate,
+				part_div = sh7722_find_div_index(parent_rate,
 								rate);
 				if (part_div > 0) {
 					part_ctx = sh7722_get_clk_context(
@@ -394,12 +394,12 @@ static long sh7722_frqcr_round_rate(struct clk *clk, unsigned long rate)
 	int div;
 
 	/* look for multiplier/divisor pair */
-	div = sh7722_find_divisors(parent_rate, rate);
+	div = sh7722_find_div_index(parent_rate, rate);
 	if (div < 0)
 		return clk->rate;
 
 	/* calculate new value of clock rate */
-	return parent_rate * 2 / div;
+	return parent_rate * 2 / divisors2[div];
 }
 
 static struct clk_ops sh7722_frqcr_clk_ops = {
@@ -421,7 +421,7 @@ static int sh7722_siu_set_rate(struct clk *clk, unsigned long rate, int algo_id)
 	int div;
 
 	r = ctrl_inl(clk->arch_flags);
-	div = sh7722_find_divisors(clk->parent->rate, rate);
+	div = sh7722_find_div_index(clk->parent->rate, rate);
 	if (div < 0)
 		return div;
 	r = (r & ~0xF) | div;
@@ -516,16 +516,19 @@ static struct clk_ops sh7722_video_clk_ops = {
 static struct clk sh7722_umem_clock = {
 	.name = "umem_clk",
 	.ops = &sh7722_frqcr_clk_ops,
+	.flags = CLK_RATE_PROPAGATES,
 };
 
 static struct clk sh7722_sh_clock = {
 	.name = "sh_clk",
 	.ops = &sh7722_frqcr_clk_ops,
+	.flags = CLK_RATE_PROPAGATES,
 };
 
 static struct clk sh7722_peripheral_clock = {
 	.name = "peripheral_clk",
 	.ops = &sh7722_frqcr_clk_ops,
+	.flags = CLK_RATE_PROPAGATES,
 };
 
 static struct clk sh7722_sdram_clock = {
@@ -533,6 +536,11 @@ static struct clk sh7722_sdram_clock = {
 	.ops = &sh7722_frqcr_clk_ops,
 };
 
+static struct clk sh7722_r_clock = {
+	.name = "r_clk",
+	.rate = 32768,
+	.flags = CLK_RATE_PROPAGATES,
+};
 
 #ifndef CONFIG_CPU_SUBTYPE_SH7343
 
@@ -567,12 +575,30 @@ static struct clk sh7722_video_clock = {
 	.ops = &sh7722_video_clk_ops,
 };
 
-static int sh7722_mstpcr_start_stop(struct clk *clk, unsigned long reg,
-				    int enable)
+#define MSTPCR_ARCH_FLAGS(reg, bit) (((reg) << 8) | (bit))
+#define MSTPCR_ARCH_FLAGS_REG(value) ((value) >> 8)
+#define MSTPCR_ARCH_FLAGS_BIT(value) ((value) & 0xff)
+
+static int sh7722_mstpcr_start_stop(struct clk *clk, int enable)
 {
-	unsigned long bit = clk->arch_flags;
+	unsigned long bit = MSTPCR_ARCH_FLAGS_BIT(clk->arch_flags);
+	unsigned long reg;
 	unsigned long r;
 
+	switch(MSTPCR_ARCH_FLAGS_REG(clk->arch_flags)) {
+	case 0:
+		reg = MSTPCR0;
+		break;
+	case 1:
+		reg = MSTPCR1;
+		break;
+	case 2:
+		reg = MSTPCR2;
+		break;
+	default:
+		return -EINVAL;
+	}  
+
 	r = ctrl_inl(reg);
 
 	if (enable)
@@ -584,96 +610,175 @@ static int sh7722_mstpcr_start_stop(struct clk *clk, unsigned long reg,
 	return 0;
 }
 
-static void sh7722_mstpcr0_enable(struct clk *clk)
-{
-	sh7722_mstpcr_start_stop(clk, MSTPCR0, 1);
-}
-
-static void sh7722_mstpcr0_disable(struct clk *clk)
-{
-	sh7722_mstpcr_start_stop(clk, MSTPCR0, 0);
-}
-
-static void sh7722_mstpcr1_enable(struct clk *clk)
-{
-	sh7722_mstpcr_start_stop(clk, MSTPCR1, 1);
-}
-
-static void sh7722_mstpcr1_disable(struct clk *clk)
+static void sh7722_mstpcr_enable(struct clk *clk)
 {
-	sh7722_mstpcr_start_stop(clk, MSTPCR1, 0);
+	sh7722_mstpcr_start_stop(clk, 1);
 }
 
-static void sh7722_mstpcr2_enable(struct clk *clk)
+static void sh7722_mstpcr_disable(struct clk *clk)
 {
-	sh7722_mstpcr_start_stop(clk, MSTPCR2, 1);
+	sh7722_mstpcr_start_stop(clk, 0);
 }
 
-static void sh7722_mstpcr2_disable(struct clk *clk)
+static void sh7722_mstpcr_recalc(struct clk *clk)
 {
-	sh7722_mstpcr_start_stop(clk, MSTPCR2, 0);
+	if (clk->parent)
+		clk->rate = clk->parent->rate;
 }
 
-static struct clk_ops sh7722_mstpcr0_clk_ops = {
-	.enable = sh7722_mstpcr0_enable,
-	.disable = sh7722_mstpcr0_disable,
-};
-
-static struct clk_ops sh7722_mstpcr1_clk_ops = {
-	.enable = sh7722_mstpcr1_enable,
-	.disable = sh7722_mstpcr1_disable,
+static struct clk_ops sh7722_mstpcr_clk_ops = {
+	.enable = sh7722_mstpcr_enable,
+	.disable = sh7722_mstpcr_disable,
+	.recalc = sh7722_mstpcr_recalc,
 };
 
-static struct clk_ops sh7722_mstpcr2_clk_ops = {
-	.enable = sh7722_mstpcr2_enable,
-	.disable = sh7722_mstpcr2_disable,
-};
-
-#define DECLARE_MSTPCRN(regnr, bitnr, bitstr)		\
-{							\
-	.name = "mstp" __stringify(regnr) bitstr,	\
-	.arch_flags = bitnr,				\
-	.ops = &sh7722_mstpcr ## regnr ## _clk_ops,	\
+#define MSTPCR(_name, _parent, regnr, bitnr) \
+{						\
+	.name = _name,				\
+	.arch_flags = MSTPCR_ARCH_FLAGS(regnr, bitnr),	\
+	.ops = (void *)_parent,		\
 }
 
-#define DECLARE_MSTPCR(regnr) \
-	DECLARE_MSTPCRN(regnr, 31, "31"), \
-	DECLARE_MSTPCRN(regnr, 30, "30"), \
-	DECLARE_MSTPCRN(regnr, 29, "29"), \
-	DECLARE_MSTPCRN(regnr, 28, "28"), \
-	DECLARE_MSTPCRN(regnr, 27, "27"), \
-	DECLARE_MSTPCRN(regnr, 26, "26"), \
-	DECLARE_MSTPCRN(regnr, 25, "25"), \
-	DECLARE_MSTPCRN(regnr, 24, "24"), \
-	DECLARE_MSTPCRN(regnr, 23, "23"), \
-	DECLARE_MSTPCRN(regnr, 22, "22"), \
-	DECLARE_MSTPCRN(regnr, 21, "21"), \
-	DECLARE_MSTPCRN(regnr, 20, "20"), \
-	DECLARE_MSTPCRN(regnr, 19, "19"), \
-	DECLARE_MSTPCRN(regnr, 18, "18"), \
-	DECLARE_MSTPCRN(regnr, 17, "17"), \
-	DECLARE_MSTPCRN(regnr, 16, "16"), \
-	DECLARE_MSTPCRN(regnr, 15, "15"), \
-	DECLARE_MSTPCRN(regnr, 14, "14"), \
-	DECLARE_MSTPCRN(regnr, 13, "13"), \
-	DECLARE_MSTPCRN(regnr, 12, "12"), \
-	DECLARE_MSTPCRN(regnr, 11, "11"), \
-	DECLARE_MSTPCRN(regnr, 10, "10"), \
-	DECLARE_MSTPCRN(regnr, 9, "09"), \
-	DECLARE_MSTPCRN(regnr, 8, "08"), \
-	DECLARE_MSTPCRN(regnr, 7, "07"), \
-	DECLARE_MSTPCRN(regnr, 6, "06"), \
-	DECLARE_MSTPCRN(regnr, 5, "05"), \
-	DECLARE_MSTPCRN(regnr, 4, "04"), \
-	DECLARE_MSTPCRN(regnr, 3, "03"), \
-	DECLARE_MSTPCRN(regnr, 2, "02"), \
-	DECLARE_MSTPCRN(regnr, 1, "01"), \
-	DECLARE_MSTPCRN(regnr, 0, "00")
-
-static struct clk sh7722_mstpcr[] = {
-	DECLARE_MSTPCR(0),
-	DECLARE_MSTPCR(1),
-	DECLARE_MSTPCR(2),
+static struct clk sh7722_mstpcr_clocks[] = {
+#if defined(CONFIG_CPU_SUBTYPE_SH7722)
+	MSTPCR("uram0", "umem_clk", 0, 28),
+	MSTPCR("xymem0", "bus_clk", 0, 26),
+	MSTPCR("tmu0", "peripheral_clk", 0, 15),
+	MSTPCR("cmt0", "r_clk", 0, 14),
+	MSTPCR("rwdt0", "r_clk", 0, 13),
+	MSTPCR("flctl0", "peripheral_clk", 0, 10),
+	MSTPCR("scif0", "peripheral_clk", 0, 7),
+	MSTPCR("scif1", "peripheral_clk", 0, 6),
+	MSTPCR("scif2", "peripheral_clk", 0, 5),
+	MSTPCR("i2c0", "peripheral_clk", 1, 9),
+	MSTPCR("rtc0", "r_clk", 1, 8),
+	MSTPCR("sdhi0", "peripheral_clk", 2, 18),
+	MSTPCR("keysc0", "r_clk", 2, 14),
+	MSTPCR("usbf0", "peripheral_clk", 2, 11),
+	MSTPCR("2dg0", "bus_clk", 2, 9),
+	MSTPCR("siu0", "bus_clk", 2, 8),
+	MSTPCR("vou0", "bus_clk", 2, 5),
+	MSTPCR("jpu0", "bus_clk", 2, 6),
+	MSTPCR("beu0", "bus_clk", 2, 4),
+	MSTPCR("ceu0", "bus_clk", 2, 3),
+	MSTPCR("veu0", "bus_clk", 2, 2),
+	MSTPCR("vpu0", "bus_clk", 2, 1),
+	MSTPCR("lcdc0", "bus_clk", 2, 0),
+#endif
+#if defined(CONFIG_CPU_SUBTYPE_SH7723)
+	/* See page 60 of Datasheet V1.0: Overview -> Block Diagram */
+	MSTPCR("tlb0", "cpu_clk", 0, 31),
+	MSTPCR("ic0", "cpu_clk", 0, 30),
+	MSTPCR("oc0", "cpu_clk", 0, 29),
+	MSTPCR("l2c0", "sh_clk", 0, 28),
+	MSTPCR("ilmem0", "cpu_clk", 0, 27),
+	MSTPCR("fpu0", "cpu_clk", 0, 24),
+	MSTPCR("intc0", "cpu_clk", 0, 22),
+	MSTPCR("dmac0", "bus_clk", 0, 21),
+	MSTPCR("sh0", "sh_clk", 0, 20),
+	MSTPCR("hudi0", "peripheral_clk", 0, 19),
+	MSTPCR("ubc0", "cpu_clk", 0, 17),
+	MSTPCR("tmu0", "peripheral_clk", 0, 15),
+	MSTPCR("cmt0", "r_clk", 0, 14),
+	MSTPCR("rwdt0", "r_clk", 0, 13),
+	MSTPCR("dmac1", "bus_clk", 0, 12),
+	MSTPCR("tmu1", "peripheral_clk", 0, 11),
+	MSTPCR("flctl0", "peripheral_clk", 0, 10),
+	MSTPCR("scif0", "peripheral_clk", 0, 9),
+	MSTPCR("scif1", "peripheral_clk", 0, 8),
+	MSTPCR("scif2", "peripheral_clk", 0, 7),
+	MSTPCR("scif3", "bus_clk", 0, 6),
+	MSTPCR("scif4", "bus_clk", 0, 5),
+	MSTPCR("scif5", "bus_clk", 0, 4),
+	MSTPCR("msiof0", "bus_clk", 0, 2),
+	MSTPCR("msiof1", "bus_clk", 0, 1),
+	MSTPCR("meram0", "sh_clk", 0, 0),
+	MSTPCR("i2c0", "peripheral_clk", 1, 9),
+	MSTPCR("rtc0", "r_clk", 1, 8),
+	MSTPCR("atapi0", "sh_clk", 2, 28),
+	MSTPCR("adc0", "peripheral_clk", 2, 28),
+	MSTPCR("tpu0", "bus_clk", 2, 25),
+	MSTPCR("irda0", "peripheral_clk", 2, 24),
+	MSTPCR("tsif0", "bus_clk", 2, 22),
+	MSTPCR("icb0", "bus_clk", 2, 21),
+	MSTPCR("sdhi0", "bus_clk", 2, 18),
+	MSTPCR("sdhi1", "bus_clk", 2, 17),
+	MSTPCR("keysc0", "r_clk", 2, 14),
+	MSTPCR("usb0", "bus_clk", 2, 11),
+	MSTPCR("2dg0", "bus_clk", 2, 10),
+	MSTPCR("siu0", "bus_clk", 2, 8),
+	MSTPCR("veu1", "bus_clk", 2, 6),
+	MSTPCR("vou0", "bus_clk", 2, 5),
+	MSTPCR("beu0", "bus_clk", 2, 4),
+	MSTPCR("ceu0", "bus_clk", 2, 3),
+	MSTPCR("veu0", "bus_clk", 2, 2),
+	MSTPCR("vpu0", "bus_clk", 2, 1),
+	MSTPCR("lcdc0", "bus_clk", 2, 0),
+#endif
+#if defined(CONFIG_CPU_SUBTYPE_SH7343)
+	MSTPCR("uram0", "umem_clk", 0, 28),
+	MSTPCR("xymem0", "bus_clk", 0, 26),
+	MSTPCR("tmu0", "peripheral_clk", 0, 15),
+	MSTPCR("cmt0", "r_clk", 0, 14),
+	MSTPCR("rwdt0", "r_clk", 0, 13),
+	MSTPCR("scif0", "peripheral_clk", 0, 7),
+	MSTPCR("scif1", "peripheral_clk", 0, 6),
+	MSTPCR("scif2", "peripheral_clk", 0, 5),
+	MSTPCR("scif3", "peripheral_clk", 0, 4),
+	MSTPCR("i2c0", "peripheral_clk", 1, 9),
+	MSTPCR("i2c1", "peripheral_clk", 1, 8),
+	MSTPCR("sdhi0", "peripheral_clk", 2, 18),
+	MSTPCR("keysc0", "r_clk", 2, 14),
+	MSTPCR("usbf0", "peripheral_clk", 2, 11),
+	MSTPCR("siu0", "bus_clk", 2, 8),
+	MSTPCR("jpu0", "bus_clk", 2, 6),
+	MSTPCR("vou0", "bus_clk", 2, 5),
+	MSTPCR("beu0", "bus_clk", 2, 4),
+	MSTPCR("ceu0", "bus_clk", 2, 3),
+	MSTPCR("veu0", "bus_clk", 2, 2),
+	MSTPCR("vpu0", "bus_clk", 2, 1),
+	MSTPCR("lcdc0", "bus_clk", 2, 0),
+#endif
+#if defined(CONFIG_CPU_SUBTYPE_SH7366)
+	/* See page 52 of Datasheet V0.40: Overview -> Block Diagram */
+	MSTPCR("tlb0", "cpu_clk", 0, 31),
+	MSTPCR("ic0", "cpu_clk", 0, 30),
+	MSTPCR("oc0", "cpu_clk", 0, 29),
+	MSTPCR("rsmem0", "sh_clk", 0, 28),
+	MSTPCR("xymem0", "cpu_clk", 0, 26),
+	MSTPCR("intc30", "peripheral_clk", 0, 23),
+	MSTPCR("intc0", "peripheral_clk", 0, 22),
+	MSTPCR("dmac0", "bus_clk", 0, 21),
+	MSTPCR("sh0", "sh_clk", 0, 20),
+	MSTPCR("hudi0", "peripheral_clk", 0, 19),
+	MSTPCR("ubc0", "cpu_clk", 0, 17),
+	MSTPCR("tmu0", "peripheral_clk", 0, 15),
+	MSTPCR("cmt0", "r_clk", 0, 14),
+	MSTPCR("rwdt0", "r_clk", 0, 13),
+	MSTPCR("flctl0", "peripheral_clk", 0, 10),
+	MSTPCR("scif0", "peripheral_clk", 0, 7),
+	MSTPCR("scif1", "bus_clk", 0, 6),
+	MSTPCR("scif2", "bus_clk", 0, 5),
+	MSTPCR("msiof0", "peripheral_clk", 0, 2),
+	MSTPCR("sbr0", "peripheral_clk", 0, 1),
+	MSTPCR("i2c0", "peripheral_clk", 1, 9),
+	MSTPCR("icb0", "bus_clk", 2, 27),
+	MSTPCR("meram0", "sh_clk", 2, 26),
+	MSTPCR("dacc0", "peripheral_clk", 2, 24),
+	MSTPCR("dacy0", "peripheral_clk", 2, 23),
+	MSTPCR("tsif0", "bus_clk", 2, 22),
+	MSTPCR("sdhi0", "bus_clk", 2, 18),
+	MSTPCR("mmcif0", "bus_clk", 2, 17),
+	MSTPCR("usb0", "bus_clk", 2, 11),
+	MSTPCR("siu0", "bus_clk", 2, 8),
+	MSTPCR("veu1", "bus_clk", 2, 7),
+	MSTPCR("vou0", "bus_clk", 2, 5),
+	MSTPCR("beu0", "bus_clk", 2, 4),
+	MSTPCR("ceu0", "bus_clk", 2, 3),
+	MSTPCR("veu0", "bus_clk", 2, 2),
+	MSTPCR("vpu0", "bus_clk", 2, 1),
+	MSTPCR("lcdc0", "bus_clk", 2, 0),
+#endif
 };
 
 static struct clk *sh7722_clocks[] = {
@@ -710,21 +815,30 @@ arch_init_clk_ops(struct clk_ops **ops, int type)
 
 int __init arch_clk_init(void)
 {
-	struct clk *master;
+	struct clk *clk;
 	int i;
 
-	master = clk_get(NULL, "master_clk");
+	clk = clk_get(NULL, "master_clk");
 	for (i = 0; i < ARRAY_SIZE(sh7722_clocks); i++) {
 		pr_debug( "Registering clock '%s'\n", sh7722_clocks[i]->name);
-		sh7722_clocks[i]->parent = master;
+		sh7722_clocks[i]->parent = clk;
 		clk_register(sh7722_clocks[i]);
 	}
-	clk_put(master);
-
-	for (i = 0; i < ARRAY_SIZE(sh7722_mstpcr); i++) {
-		pr_debug( "Registering mstpcr '%s'\n", sh7722_mstpcr[i].name);
-		clk_register(&sh7722_mstpcr[i]);
+	clk_put(clk);
+
+	clk_register(&sh7722_r_clock);
+
+	for (i = 0; i < ARRAY_SIZE(sh7722_mstpcr_clocks); i++) {
+		pr_debug( "Registering mstpcr clock '%s'\n",
+			  sh7722_mstpcr_clocks[i].name);
+		clk = clk_get(NULL, (void *) sh7722_mstpcr_clocks[i].ops);
+		sh7722_mstpcr_clocks[i].parent = clk;
+		sh7722_mstpcr_clocks[i].ops = &sh7722_mstpcr_clk_ops;
+		clk_register(&sh7722_mstpcr_clocks[i]);
+		clk_put(clk);
 	}
 
+	clk_recalc_rate(&sh7722_r_clock); /* make sure rate gets propagated */
+
 	return 0;
 }
diff --git a/arch/sh/kernel/cpu/sh4a/setup-sh7343.c b/arch/sh/kernel/cpu/sh4a/setup-sh7343.c
index 78881b4214da..0623e377f488 100644
--- a/arch/sh/kernel/cpu/sh4a/setup-sh7343.c
+++ b/arch/sh/kernel/cpu/sh4a/setup-sh7343.c
@@ -30,6 +30,7 @@ static struct resource iic0_resources[] = {
 
 static struct platform_device iic0_device = {
 	.name           = "i2c-sh_mobile",
+	.id             = 0, /* "i2c0" clock */
 	.num_resources  = ARRAY_SIZE(iic0_resources),
 	.resource       = iic0_resources,
 };
@@ -50,6 +51,7 @@ static struct resource iic1_resources[] = {
 
 static struct platform_device iic1_device = {
 	.name           = "i2c-sh_mobile",
+	.id             = 1, /* "i2c1" clock */
 	.num_resources  = ARRAY_SIZE(iic1_resources),
 	.resource       = iic1_resources,
 };
@@ -115,7 +117,22 @@ static struct plat_sci_port sci_platform_data[] = {
 		.mapbase	= 0xffe00000,
 		.flags		= UPF_BOOT_AUTOCONF,
 		.type		= PORT_SCIF,
-		.irqs		= { 80, 81, 83, 82 },
+		.irqs		= { 80, 80, 80, 80 },
+	}, {
+		.mapbase	= 0xffe10000,
+		.flags		= UPF_BOOT_AUTOCONF,
+		.type		= PORT_SCIF,
+		.irqs		= { 81, 81, 81, 81 },
+	}, {
+		.mapbase	= 0xffe20000,
+		.flags		= UPF_BOOT_AUTOCONF,
+		.type		= PORT_SCIF,
+		.irqs		= { 82, 82, 82, 82 },
+	}, {
+		.mapbase	= 0xffe30000,
+		.flags		= UPF_BOOT_AUTOCONF,
+		.type		= PORT_SCIF,
+		.irqs		= { 83, 83, 83, 83 },
 	}, {
 		.flags = 0,
 	}
@@ -139,18 +156,10 @@ static struct platform_device *sh7343_devices[] __initdata = {
 
 static int __init sh7343_devices_setup(void)
 {
-	clk_always_enable("mstp031"); /* TLB */
-	clk_always_enable("mstp030"); /* IC */
-	clk_always_enable("mstp029"); /* OC */
-	clk_always_enable("mstp028"); /* URAM */
-	clk_always_enable("mstp026"); /* XYMEM */
-	clk_always_enable("mstp023"); /* INTC3 */
-	clk_always_enable("mstp022"); /* INTC */
-	clk_always_enable("mstp020"); /* SuperHyway */
-	clk_always_enable("mstp109"); /* I2C0 */
-	clk_always_enable("mstp108"); /* I2C1 */
-	clk_always_enable("mstp202"); /* VEU */
-	clk_always_enable("mstp201"); /* VPU */
+	clk_always_enable("uram0"); /* URAM */
+	clk_always_enable("xymem0"); /* XYMEM */
+	clk_always_enable("veu0"); /* VEU */
+	clk_always_enable("vpu0"); /* VPU */
 
 	platform_resource_setup_memory(&vpu_device, "vpu", 1 << 20);
 	platform_resource_setup_memory(&veu_device, "veu", 2 << 20);
@@ -171,7 +180,7 @@ enum {
 	MMC_ERR, MMC_TRAN, MMC_FSTAT, MMC_FRDY,
 	DMAC4, DMAC5, DMAC_DADERR,
 	KEYSC,
-	SCIF, SCIF1, SCIF2, SCIF3, SCIF4,
+	SCIF, SCIF1, SCIF2, SCIF3,
 	SIOF0, SIOF1, SIO,
 	FLCTL_FLSTEI, FLCTL_FLENDI, FLCTL_FLTREQ0I, FLCTL_FLTREQ1I,
 	I2C0_ALI, I2C0_TACKI, I2C0_WAITI, I2C0_DTEI,
diff --git a/arch/sh/kernel/cpu/sh4a/setup-sh7366.c b/arch/sh/kernel/cpu/sh4a/setup-sh7366.c
index e17db39b97aa..839ae97a7fd2 100644
--- a/arch/sh/kernel/cpu/sh4a/setup-sh7366.c
+++ b/arch/sh/kernel/cpu/sh4a/setup-sh7366.c
@@ -32,6 +32,7 @@ static struct resource iic_resources[] = {
 
 static struct platform_device iic_device = {
 	.name           = "i2c-sh_mobile",
+	.id             = 0, /* "i2c0" clock */
 	.num_resources  = ARRAY_SIZE(iic_resources),
 	.resource       = iic_resources,
 };
@@ -176,19 +177,11 @@ static struct platform_device *sh7366_devices[] __initdata = {
 
 static int __init sh7366_devices_setup(void)
 {
-	clk_always_enable("mstp031"); /* TLB */
-	clk_always_enable("mstp030"); /* IC */
-	clk_always_enable("mstp029"); /* OC */
-	clk_always_enable("mstp028"); /* RSMEM */
-	clk_always_enable("mstp026"); /* XYMEM */
-	clk_always_enable("mstp023"); /* INTC3 */
-	clk_always_enable("mstp022"); /* INTC */
-	clk_always_enable("mstp020"); /* SuperHyway */
-	clk_always_enable("mstp109"); /* I2C */
-	clk_always_enable("mstp211"); /* USB */
-	clk_always_enable("mstp207"); /* VEU-2 */
-	clk_always_enable("mstp202"); /* VEU-1 */
-	clk_always_enable("mstp201"); /* VPU */
+	clk_always_enable("rsmem0"); /* RSMEM */
+	clk_always_enable("xymem0"); /* XYMEM */
+	clk_always_enable("veu1"); /* VEU-2 */
+	clk_always_enable("veu0"); /* VEU-1 */
+	clk_always_enable("vpu0"); /* VPU */
 
 	platform_resource_setup_memory(&vpu_device, "vpu", 2 << 20);
 	platform_resource_setup_memory(&veu0_device, "veu0", 2 << 20);
diff --git a/arch/sh/kernel/cpu/sh4a/setup-sh7722.c b/arch/sh/kernel/cpu/sh4a/setup-sh7722.c
index ef77ee1d9f53..9162013ec695 100644
--- a/arch/sh/kernel/cpu/sh4a/setup-sh7722.c
+++ b/arch/sh/kernel/cpu/sh4a/setup-sh7722.c
@@ -62,7 +62,7 @@ static struct resource usbf_resources[] = {
 
 static struct platform_device usbf_device = {
 	.name		= "m66592_udc",
-	.id		= -1,
+	.id             = 0, /* "usbf0" clock */
 	.dev = {
 		.dma_mask		= NULL,
 		.coherent_dma_mask	= 0xffffffff,
@@ -87,6 +87,7 @@ static struct resource iic_resources[] = {
 
 static struct platform_device iic_device = {
 	.name           = "i2c-sh_mobile",
+	.id             = 0, /* "i2c0" clock */
 	.num_resources  = ARRAY_SIZE(iic_resources),
 	.resource       = iic_resources,
 };
@@ -190,17 +191,11 @@ static struct platform_device *sh7722_devices[] __initdata = {
 
 static int __init sh7722_devices_setup(void)
 {
-	clk_always_enable("mstp031"); /* TLB */
-	clk_always_enable("mstp030"); /* IC */
-	clk_always_enable("mstp029"); /* OC */
-	clk_always_enable("mstp028"); /* URAM */
-	clk_always_enable("mstp026"); /* XYMEM */
-	clk_always_enable("mstp022"); /* INTC */
-	clk_always_enable("mstp020"); /* SuperHyway */
-	clk_always_enable("mstp109"); /* I2C */
-	clk_always_enable("mstp211"); /* USB */
-	clk_always_enable("mstp202"); /* VEU */
-	clk_always_enable("mstp201"); /* VPU */
+	clk_always_enable("uram0"); /* URAM */
+	clk_always_enable("xymem0"); /* XYMEM */
+	clk_always_enable("rtc0"); /* RTC */
+	clk_always_enable("veu0"); /* VEU */
+	clk_always_enable("vpu0"); /* VPU */
 
 	platform_resource_setup_memory(&vpu_device, "vpu", 1 << 20);
 	platform_resource_setup_memory(&veu_device, "veu", 2 << 20);
diff --git a/arch/sh/kernel/cpu/sh4a/setup-sh7723.c b/arch/sh/kernel/cpu/sh4a/setup-sh7723.c
index 6d9e6972cfc9..849770d780ae 100644
--- a/arch/sh/kernel/cpu/sh4a/setup-sh7723.c
+++ b/arch/sh/kernel/cpu/sh4a/setup-sh7723.c
@@ -215,6 +215,7 @@ static struct resource iic_resources[] = {
 
 static struct platform_device iic_device = {
 	.name           = "i2c-sh_mobile",
+	.id             = 0, /* "i2c0" clock */
 	.num_resources  = ARRAY_SIZE(iic_resources),
 	.resource       = iic_resources,
 };
@@ -231,19 +232,11 @@ static struct platform_device *sh7723_devices[] __initdata = {
 
 static int __init sh7723_devices_setup(void)
 {
-	clk_always_enable("mstp031"); /* TLB */
-	clk_always_enable("mstp030"); /* IC */
-	clk_always_enable("mstp029"); /* OC */
-	clk_always_enable("mstp024"); /* FPU */
-	clk_always_enable("mstp022"); /* INTC */
-	clk_always_enable("mstp020"); /* SuperHyway */
-	clk_always_enable("mstp000"); /* MERAM */
-	clk_always_enable("mstp109"); /* I2C */
-	clk_always_enable("mstp108"); /* RTC */
-	clk_always_enable("mstp211"); /* USB */
-	clk_always_enable("mstp206"); /* VEU2H1 */
-	clk_always_enable("mstp202"); /* VEU2H0 */
-	clk_always_enable("mstp201"); /* VPU */
+	clk_always_enable("meram0"); /* MERAM */
+	clk_always_enable("rtc0"); /* RTC */
+	clk_always_enable("veu1"); /* VEU2H1 */
+	clk_always_enable("veu0"); /* VEU2H0 */
+	clk_always_enable("vpu0"); /* VPU */
 
 	platform_resource_setup_memory(&vpu_device, "vpu", 2 << 20);
 	platform_resource_setup_memory(&veu0_device, "veu0", 2 << 20);
diff --git a/arch/sh/kernel/disassemble.c b/arch/sh/kernel/disassemble.c
new file mode 100644
index 000000000000..64d5d8dded7c
--- /dev/null
+++ b/arch/sh/kernel/disassemble.c
@@ -0,0 +1,573 @@
+/*
+ * Disassemble SuperH instructions.
+ *
+ * Copyright (C) 1999 kaz Kojima
+ * Copyright (C) 2008 Paul Mundt
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ */
+#include <linux/kernel.h>
+#include <linux/string.h>
+#include <linux/uaccess.h>
+
+/*
+ * Format of an instruction in memory.
+ */
+typedef enum {
+	HEX_0, HEX_1, HEX_2, HEX_3, HEX_4, HEX_5, HEX_6, HEX_7,
+	HEX_8, HEX_9, HEX_A, HEX_B, HEX_C, HEX_D, HEX_E, HEX_F,
+	REG_N, REG_M, REG_NM, REG_B,
+	BRANCH_12, BRANCH_8,
+	DISP_8, DISP_4,
+	IMM_4, IMM_4BY2, IMM_4BY4, PCRELIMM_8BY2, PCRELIMM_8BY4,
+	IMM_8, IMM_8BY2, IMM_8BY4,
+} sh_nibble_type;
+
+typedef enum {
+	A_END, A_BDISP12, A_BDISP8,
+	A_DEC_M, A_DEC_N,
+	A_DISP_GBR, A_DISP_PC, A_DISP_REG_M, A_DISP_REG_N,
+	A_GBR,
+	A_IMM,
+	A_INC_M, A_INC_N,
+	A_IND_M, A_IND_N, A_IND_R0_REG_M, A_IND_R0_REG_N,
+	A_MACH, A_MACL,
+	A_PR, A_R0, A_R0_GBR, A_REG_M, A_REG_N, A_REG_B,
+	A_SR, A_VBR, A_SSR, A_SPC, A_SGR, A_DBR,
+	F_REG_N, F_REG_M, D_REG_N, D_REG_M,
+	X_REG_N, /* Only used for argument parsing */
+	X_REG_M, /* Only used for argument parsing */
+	DX_REG_N, DX_REG_M, V_REG_N, V_REG_M,
+	FD_REG_N,
+	XMTRX_M4,
+	F_FR0,
+	FPUL_N, FPUL_M, FPSCR_N, FPSCR_M,
+} sh_arg_type;
+
+static struct sh_opcode_info {
+	char *name;
+	sh_arg_type arg[7];
+	sh_nibble_type nibbles[4];
+} sh_table[] = {
+	{"add",{A_IMM,A_REG_N},{HEX_7,REG_N,IMM_8}},
+	{"add",{ A_REG_M,A_REG_N},{HEX_3,REG_N,REG_M,HEX_C}},
+	{"addc",{ A_REG_M,A_REG_N},{HEX_3,REG_N,REG_M,HEX_E}},
+	{"addv",{ A_REG_M,A_REG_N},{HEX_3,REG_N,REG_M,HEX_F}},
+	{"and",{A_IMM,A_R0},{HEX_C,HEX_9,IMM_8}},
+	{"and",{ A_REG_M,A_REG_N},{HEX_2,REG_N,REG_M,HEX_9}},
+	{"and.b",{A_IMM,A_R0_GBR},{HEX_C,HEX_D,IMM_8}},
+	{"bra",{A_BDISP12},{HEX_A,BRANCH_12}},
+	{"bsr",{A_BDISP12},{HEX_B,BRANCH_12}},
+	{"bt",{A_BDISP8},{HEX_8,HEX_9,BRANCH_8}},
+	{"bf",{A_BDISP8},{HEX_8,HEX_B,BRANCH_8}},
+	{"bt.s",{A_BDISP8},{HEX_8,HEX_D,BRANCH_8}},
+	{"bt/s",{A_BDISP8},{HEX_8,HEX_D,BRANCH_8}},
+	{"bf.s",{A_BDISP8},{HEX_8,HEX_F,BRANCH_8}},
+	{"bf/s",{A_BDISP8},{HEX_8,HEX_F,BRANCH_8}},
+	{"clrmac",{0},{HEX_0,HEX_0,HEX_2,HEX_8}},
+	{"clrs",{0},{HEX_0,HEX_0,HEX_4,HEX_8}},
+	{"clrt",{0},{HEX_0,HEX_0,HEX_0,HEX_8}},
+	{"cmp/eq",{A_IMM,A_R0},{HEX_8,HEX_8,IMM_8}},
+	{"cmp/eq",{ A_REG_M,A_REG_N},{HEX_3,REG_N,REG_M,HEX_0}},
+	{"cmp/ge",{ A_REG_M,A_REG_N},{HEX_3,REG_N,REG_M,HEX_3}},
+	{"cmp/gt",{ A_REG_M,A_REG_N},{HEX_3,REG_N,REG_M,HEX_7}},
+	{"cmp/hi",{ A_REG_M,A_REG_N},{HEX_3,REG_N,REG_M,HEX_6}},
+	{"cmp/hs",{ A_REG_M,A_REG_N},{HEX_3,REG_N,REG_M,HEX_2}},
+	{"cmp/pl",{A_REG_N},{HEX_4,REG_N,HEX_1,HEX_5}},
+	{"cmp/pz",{A_REG_N},{HEX_4,REG_N,HEX_1,HEX_1}},
+	{"cmp/str",{ A_REG_M,A_REG_N},{HEX_2,REG_N,REG_M,HEX_C}},
+	{"div0s",{ A_REG_M,A_REG_N},{HEX_2,REG_N,REG_M,HEX_7}},
+	{"div0u",{0},{HEX_0,HEX_0,HEX_1,HEX_9}},
+	{"div1",{ A_REG_M,A_REG_N},{HEX_3,REG_N,REG_M,HEX_4}},
+	{"exts.b",{ A_REG_M,A_REG_N},{HEX_6,REG_N,REG_M,HEX_E}},
+	{"exts.w",{ A_REG_M,A_REG_N},{HEX_6,REG_N,REG_M,HEX_F}},
+	{"extu.b",{ A_REG_M,A_REG_N},{HEX_6,REG_N,REG_M,HEX_C}},
+	{"extu.w",{ A_REG_M,A_REG_N},{HEX_6,REG_N,REG_M,HEX_D}},
+	{"jmp",{A_IND_N},{HEX_4,REG_N,HEX_2,HEX_B}},
+	{"jsr",{A_IND_N},{HEX_4,REG_N,HEX_0,HEX_B}},
+	{"ldc",{A_REG_N,A_SR},{HEX_4,REG_N,HEX_0,HEX_E}},
+	{"ldc",{A_REG_N,A_GBR},{HEX_4,REG_N,HEX_1,HEX_E}},
+	{"ldc",{A_REG_N,A_VBR},{HEX_4,REG_N,HEX_2,HEX_E}},
+	{"ldc",{A_REG_N,A_SSR},{HEX_4,REG_N,HEX_3,HEX_E}},
+	{"ldc",{A_REG_N,A_SPC},{HEX_4,REG_N,HEX_4,HEX_E}},
+	{"ldc",{A_REG_N,A_DBR},{HEX_4,REG_N,HEX_7,HEX_E}},
+	{"ldc",{A_REG_N,A_REG_B},{HEX_4,REG_N,REG_B,HEX_E}},
+	{"ldc.l",{A_INC_N,A_SR},{HEX_4,REG_N,HEX_0,HEX_7}},
+	{"ldc.l",{A_INC_N,A_GBR},{HEX_4,REG_N,HEX_1,HEX_7}},
+	{"ldc.l",{A_INC_N,A_VBR},{HEX_4,REG_N,HEX_2,HEX_7}},
+	{"ldc.l",{A_INC_N,A_SSR},{HEX_4,REG_N,HEX_3,HEX_7}},
+	{"ldc.l",{A_INC_N,A_SPC},{HEX_4,REG_N,HEX_4,HEX_7}},
+	{"ldc.l",{A_INC_N,A_DBR},{HEX_4,REG_N,HEX_7,HEX_7}},
+	{"ldc.l",{A_INC_N,A_REG_B},{HEX_4,REG_N,REG_B,HEX_7}},
+	{"lds",{A_REG_N,A_MACH},{HEX_4,REG_N,HEX_0,HEX_A}},
+	{"lds",{A_REG_N,A_MACL},{HEX_4,REG_N,HEX_1,HEX_A}},
+	{"lds",{A_REG_N,A_PR},{HEX_4,REG_N,HEX_2,HEX_A}},
+	{"lds",{A_REG_M,FPUL_N},{HEX_4,REG_M,HEX_5,HEX_A}},
+	{"lds",{A_REG_M,FPSCR_N},{HEX_4,REG_M,HEX_6,HEX_A}},
+	{"lds.l",{A_INC_N,A_MACH},{HEX_4,REG_N,HEX_0,HEX_6}},
+	{"lds.l",{A_INC_N,A_MACL},{HEX_4,REG_N,HEX_1,HEX_6}},
+	{"lds.l",{A_INC_N,A_PR},{HEX_4,REG_N,HEX_2,HEX_6}},
+	{"lds.l",{A_INC_M,FPUL_N},{HEX_4,REG_M,HEX_5,HEX_6}},
+	{"lds.l",{A_INC_M,FPSCR_N},{HEX_4,REG_M,HEX_6,HEX_6}},
+	{"ldtlb",{0},{HEX_0,HEX_0,HEX_3,HEX_8}},
+	{"mac.w",{A_INC_M,A_INC_N},{HEX_4,REG_N,REG_M,HEX_F}},
+	{"mov",{A_IMM,A_REG_N},{HEX_E,REG_N,IMM_8}},
+	{"mov",{ A_REG_M,A_REG_N},{HEX_6,REG_N,REG_M,HEX_3}},
+	{"mov.b",{ A_REG_M,A_IND_R0_REG_N},{HEX_0,REG_N,REG_M,HEX_4}},
+	{"mov.b",{ A_REG_M,A_DEC_N},{HEX_2,REG_N,REG_M,HEX_4}},
+	{"mov.b",{ A_REG_M,A_IND_N},{HEX_2,REG_N,REG_M,HEX_0}},
+	{"mov.b",{A_DISP_REG_M,A_R0},{HEX_8,HEX_4,REG_M,IMM_4}},
+	{"mov.b",{A_DISP_GBR,A_R0},{HEX_C,HEX_4,IMM_8}},
+	{"mov.b",{A_IND_R0_REG_M,A_REG_N},{HEX_0,REG_N,REG_M,HEX_C}},
+	{"mov.b",{A_INC_M,A_REG_N},{HEX_6,REG_N,REG_M,HEX_4}},
+	{"mov.b",{A_IND_M,A_REG_N},{HEX_6,REG_N,REG_M,HEX_0}},
+	{"mov.b",{A_R0,A_DISP_REG_M},{HEX_8,HEX_0,REG_M,IMM_4}},
+	{"mov.b",{A_R0,A_DISP_GBR},{HEX_C,HEX_0,IMM_8}},
+	{"mov.l",{ A_REG_M,A_DISP_REG_N},{HEX_1,REG_N,REG_M,IMM_4BY4}},
+	{"mov.l",{ A_REG_M,A_IND_R0_REG_N},{HEX_0,REG_N,REG_M,HEX_6}},
+	{"mov.l",{ A_REG_M,A_DEC_N},{HEX_2,REG_N,REG_M,HEX_6}},
+	{"mov.l",{ A_REG_M,A_IND_N},{HEX_2,REG_N,REG_M,HEX_2}},
+	{"mov.l",{A_DISP_REG_M,A_REG_N},{HEX_5,REG_N,REG_M,IMM_4BY4}},
+	{"mov.l",{A_DISP_GBR,A_R0},{HEX_C,HEX_6,IMM_8BY4}},
+	{"mov.l",{A_DISP_PC,A_REG_N},{HEX_D,REG_N,PCRELIMM_8BY4}},
+	{"mov.l",{A_IND_R0_REG_M,A_REG_N},{HEX_0,REG_N,REG_M,HEX_E}},
+	{"mov.l",{A_INC_M,A_REG_N},{HEX_6,REG_N,REG_M,HEX_6}},
+	{"mov.l",{A_IND_M,A_REG_N},{HEX_6,REG_N,REG_M,HEX_2}},
+	{"mov.l",{A_R0,A_DISP_GBR},{HEX_C,HEX_2,IMM_8BY4}},
+	{"mov.w",{ A_REG_M,A_IND_R0_REG_N},{HEX_0,REG_N,REG_M,HEX_5}},
+	{"mov.w",{ A_REG_M,A_DEC_N},{HEX_2,REG_N,REG_M,HEX_5}},
+	{"mov.w",{ A_REG_M,A_IND_N},{HEX_2,REG_N,REG_M,HEX_1}},
+	{"mov.w",{A_DISP_REG_M,A_R0},{HEX_8,HEX_5,REG_M,IMM_4BY2}},
+	{"mov.w",{A_DISP_GBR,A_R0},{HEX_C,HEX_5,IMM_8BY2}},
+	{"mov.w",{A_DISP_PC,A_REG_N},{HEX_9,REG_N,PCRELIMM_8BY2}},
+	{"mov.w",{A_IND_R0_REG_M,A_REG_N},{HEX_0,REG_N,REG_M,HEX_D}},
+	{"mov.w",{A_INC_M,A_REG_N},{HEX_6,REG_N,REG_M,HEX_5}},
+	{"mov.w",{A_IND_M,A_REG_N},{HEX_6,REG_N,REG_M,HEX_1}},
+	{"mov.w",{A_R0,A_DISP_REG_M},{HEX_8,HEX_1,REG_M,IMM_4BY2}},
+	{"mov.w",{A_R0,A_DISP_GBR},{HEX_C,HEX_1,IMM_8BY2}},
+	{"mova",{A_DISP_PC,A_R0},{HEX_C,HEX_7,PCRELIMM_8BY4}},
+	{"movca.l",{A_R0,A_IND_N},{HEX_0,REG_N,HEX_C,HEX_3}},
+	{"movt",{A_REG_N},{HEX_0,REG_N,HEX_2,HEX_9}},
+	{"muls",{ A_REG_M,A_REG_N},{HEX_2,REG_N,REG_M,HEX_F}},
+	{"mul.l",{ A_REG_M,A_REG_N},{HEX_0,REG_N,REG_M,HEX_7}},
+	{"mulu",{ A_REG_M,A_REG_N},{HEX_2,REG_N,REG_M,HEX_E}},
+	{"neg",{ A_REG_M,A_REG_N},{HEX_6,REG_N,REG_M,HEX_B}},
+	{"negc",{ A_REG_M,A_REG_N},{HEX_6,REG_N,REG_M,HEX_A}},
+	{"nop",{0},{HEX_0,HEX_0,HEX_0,HEX_9}},
+	{"not",{ A_REG_M,A_REG_N},{HEX_6,REG_N,REG_M,HEX_7}},
+	{"ocbi",{A_IND_N},{HEX_0,REG_N,HEX_9,HEX_3}},
+	{"ocbp",{A_IND_N},{HEX_0,REG_N,HEX_A,HEX_3}},
+	{"ocbwb",{A_IND_N},{HEX_0,REG_N,HEX_B,HEX_3}},
+	{"or",{A_IMM,A_R0},{HEX_C,HEX_B,IMM_8}},
+	{"or",{ A_REG_M,A_REG_N},{HEX_2,REG_N,REG_M,HEX_B}},
+	{"or.b",{A_IMM,A_R0_GBR},{HEX_C,HEX_F,IMM_8}},
+	{"pref",{A_IND_N},{HEX_0,REG_N,HEX_8,HEX_3}},
+	{"rotcl",{A_REG_N},{HEX_4,REG_N,HEX_2,HEX_4}},
+	{"rotcr",{A_REG_N},{HEX_4,REG_N,HEX_2,HEX_5}},
+	{"rotl",{A_REG_N},{HEX_4,REG_N,HEX_0,HEX_4}},
+	{"rotr",{A_REG_N},{HEX_4,REG_N,HEX_0,HEX_5}},
+	{"rte",{0},{HEX_0,HEX_0,HEX_2,HEX_B}},
+	{"rts",{0},{HEX_0,HEX_0,HEX_0,HEX_B}},
+	{"sets",{0},{HEX_0,HEX_0,HEX_5,HEX_8}},
+	{"sett",{0},{HEX_0,HEX_0,HEX_1,HEX_8}},
+	{"shad",{ A_REG_M,A_REG_N},{HEX_4,REG_N,REG_M,HEX_C}},
+	{"shld",{ A_REG_M,A_REG_N},{HEX_4,REG_N,REG_M,HEX_D}},
+	{"shal",{A_REG_N},{HEX_4,REG_N,HEX_2,HEX_0}},
+	{"shar",{A_REG_N},{HEX_4,REG_N,HEX_2,HEX_1}},
+	{"shll",{A_REG_N},{HEX_4,REG_N,HEX_0,HEX_0}},
+	{"shll16",{A_REG_N},{HEX_4,REG_N,HEX_2,HEX_8}},
+	{"shll2",{A_REG_N},{HEX_4,REG_N,HEX_0,HEX_8}},
+	{"shll8",{A_REG_N},{HEX_4,REG_N,HEX_1,HEX_8}},
+	{"shlr",{A_REG_N},{HEX_4,REG_N,HEX_0,HEX_1}},
+	{"shlr16",{A_REG_N},{HEX_4,REG_N,HEX_2,HEX_9}},
+	{"shlr2",{A_REG_N},{HEX_4,REG_N,HEX_0,HEX_9}},
+	{"shlr8",{A_REG_N},{HEX_4,REG_N,HEX_1,HEX_9}},
+	{"sleep",{0},{HEX_0,HEX_0,HEX_1,HEX_B}},
+	{"stc",{A_SR,A_REG_N},{HEX_0,REG_N,HEX_0,HEX_2}},
+	{"stc",{A_GBR,A_REG_N},{HEX_0,REG_N,HEX_1,HEX_2}},
+	{"stc",{A_VBR,A_REG_N},{HEX_0,REG_N,HEX_2,HEX_2}},
+	{"stc",{A_SSR,A_REG_N},{HEX_0,REG_N,HEX_3,HEX_2}},
+	{"stc",{A_SPC,A_REG_N},{HEX_0,REG_N,HEX_4,HEX_2}},
+	{"stc",{A_SGR,A_REG_N},{HEX_0,REG_N,HEX_6,HEX_2}},
+	{"stc",{A_DBR,A_REG_N},{HEX_0,REG_N,HEX_7,HEX_2}},
+	{"stc",{A_REG_B,A_REG_N},{HEX_0,REG_N,REG_B,HEX_2}},
+	{"stc.l",{A_SR,A_DEC_N},{HEX_4,REG_N,HEX_0,HEX_3}},
+	{"stc.l",{A_GBR,A_DEC_N},{HEX_4,REG_N,HEX_1,HEX_3}},
+	{"stc.l",{A_VBR,A_DEC_N},{HEX_4,REG_N,HEX_2,HEX_3}},
+	{"stc.l",{A_SSR,A_DEC_N},{HEX_4,REG_N,HEX_3,HEX_3}},
+	{"stc.l",{A_SPC,A_DEC_N},{HEX_4,REG_N,HEX_4,HEX_3}},
+	{"stc.l",{A_SGR,A_DEC_N},{HEX_4,REG_N,HEX_6,HEX_3}},
+	{"stc.l",{A_DBR,A_DEC_N},{HEX_4,REG_N,HEX_7,HEX_3}},
+	{"stc.l",{A_REG_B,A_DEC_N},{HEX_4,REG_N,REG_B,HEX_3}},
+	{"sts",{A_MACH,A_REG_N},{HEX_0,REG_N,HEX_0,HEX_A}},
+	{"sts",{A_MACL,A_REG_N},{HEX_0,REG_N,HEX_1,HEX_A}},
+	{"sts",{A_PR,A_REG_N},{HEX_0,REG_N,HEX_2,HEX_A}},
+	{"sts",{FPUL_M,A_REG_N},{HEX_0,REG_N,HEX_5,HEX_A}},
+	{"sts",{FPSCR_M,A_REG_N},{HEX_0,REG_N,HEX_6,HEX_A}},
+	{"sts.l",{A_MACH,A_DEC_N},{HEX_4,REG_N,HEX_0,HEX_2}},
+	{"sts.l",{A_MACL,A_DEC_N},{HEX_4,REG_N,HEX_1,HEX_2}},
+	{"sts.l",{A_PR,A_DEC_N},{HEX_4,REG_N,HEX_2,HEX_2}},
+	{"sts.l",{FPUL_M,A_DEC_N},{HEX_4,REG_N,HEX_5,HEX_2}},
+	{"sts.l",{FPSCR_M,A_DEC_N},{HEX_4,REG_N,HEX_6,HEX_2}},
+	{"sub",{ A_REG_M,A_REG_N},{HEX_3,REG_N,REG_M,HEX_8}},
+	{"subc",{ A_REG_M,A_REG_N},{HEX_3,REG_N,REG_M,HEX_A}},
+	{"subv",{ A_REG_M,A_REG_N},{HEX_3,REG_N,REG_M,HEX_B}},
+	{"swap.b",{ A_REG_M,A_REG_N},{HEX_6,REG_N,REG_M,HEX_8}},
+	{"swap.w",{ A_REG_M,A_REG_N},{HEX_6,REG_N,REG_M,HEX_9}},
+	{"tas.b",{A_IND_N},{HEX_4,REG_N,HEX_1,HEX_B}},
+	{"trapa",{A_IMM},{HEX_C,HEX_3,IMM_8}},
+	{"tst",{A_IMM,A_R0},{HEX_C,HEX_8,IMM_8}},
+	{"tst",{ A_REG_M,A_REG_N},{HEX_2,REG_N,REG_M,HEX_8}},
+	{"tst.b",{A_IMM,A_R0_GBR},{HEX_C,HEX_C,IMM_8}},
+	{"xor",{A_IMM,A_R0},{HEX_C,HEX_A,IMM_8}},
+	{"xor",{ A_REG_M,A_REG_N},{HEX_2,REG_N,REG_M,HEX_A}},
+	{"xor.b",{A_IMM,A_R0_GBR},{HEX_C,HEX_E,IMM_8}},
+	{"xtrct",{ A_REG_M,A_REG_N},{HEX_2,REG_N,REG_M,HEX_D}},
+	{"mul.l",{ A_REG_M,A_REG_N},{HEX_0,REG_N,REG_M,HEX_7}},
+	{"dt",{A_REG_N},{HEX_4,REG_N,HEX_1,HEX_0}},
+	{"dmuls.l",{ A_REG_M,A_REG_N},{HEX_3,REG_N,REG_M,HEX_D}},
+	{"dmulu.l",{ A_REG_M,A_REG_N},{HEX_3,REG_N,REG_M,HEX_5}},
+	{"mac.l",{A_INC_M,A_INC_N},{HEX_0,REG_N,REG_M,HEX_F}},
+	{"braf",{A_REG_N},{HEX_0,REG_N,HEX_2,HEX_3}},
+	{"bsrf",{A_REG_N},{HEX_0,REG_N,HEX_0,HEX_3}},
+	{"fabs",{FD_REG_N},{HEX_F,REG_N,HEX_5,HEX_D}},
+	{"fadd",{F_REG_M,F_REG_N},{HEX_F,REG_N,REG_M,HEX_0}},
+	{"fadd",{D_REG_M,D_REG_N},{HEX_F,REG_N,REG_M,HEX_0}},
+	{"fcmp/eq",{F_REG_M,F_REG_N},{HEX_F,REG_N,REG_M,HEX_4}},
+	{"fcmp/eq",{D_REG_M,D_REG_N},{HEX_F,REG_N,REG_M,HEX_4}},
+	{"fcmp/gt",{F_REG_M,F_REG_N},{HEX_F,REG_N,REG_M,HEX_5}},
+	{"fcmp/gt",{D_REG_M,D_REG_N},{HEX_F,REG_N,REG_M,HEX_5}},
+	{"fcnvds",{D_REG_N,FPUL_M},{HEX_F,REG_N,HEX_B,HEX_D}},
+	{"fcnvsd",{FPUL_M,D_REG_N},{HEX_F,REG_N,HEX_A,HEX_D}},
+	{"fdiv",{F_REG_M,F_REG_N},{HEX_F,REG_N,REG_M,HEX_3}},
+	{"fdiv",{D_REG_M,D_REG_N},{HEX_F,REG_N,REG_M,HEX_3}},
+	{"fipr",{V_REG_M,V_REG_N},{HEX_F,REG_NM,HEX_E,HEX_D}},
+	{"fldi0",{F_REG_N},{HEX_F,REG_N,HEX_8,HEX_D}},
+	{"fldi1",{F_REG_N},{HEX_F,REG_N,HEX_9,HEX_D}},
+	{"flds",{F_REG_N,FPUL_M},{HEX_F,REG_N,HEX_1,HEX_D}},
+	{"float",{FPUL_M,FD_REG_N},{HEX_F,REG_N,HEX_2,HEX_D}},
+	{"fmac",{F_FR0,F_REG_M,F_REG_N},{HEX_F,REG_N,REG_M,HEX_E}},
+	{"fmov",{F_REG_M,F_REG_N},{HEX_F,REG_N,REG_M,HEX_C}},
+	{"fmov",{DX_REG_M,DX_REG_N},{HEX_F,REG_N,REG_M,HEX_C}},
+	{"fmov",{A_IND_M,F_REG_N},{HEX_F,REG_N,REG_M,HEX_8}},
+	{"fmov",{A_IND_M,DX_REG_N},{HEX_F,REG_N,REG_M,HEX_8}},
+	{"fmov",{F_REG_M,A_IND_N},{HEX_F,REG_N,REG_M,HEX_A}},
+	{"fmov",{DX_REG_M,A_IND_N},{HEX_F,REG_N,REG_M,HEX_A}},
+	{"fmov",{A_INC_M,F_REG_N},{HEX_F,REG_N,REG_M,HEX_9}},
+	{"fmov",{A_INC_M,DX_REG_N},{HEX_F,REG_N,REG_M,HEX_9}},
+	{"fmov",{F_REG_M,A_DEC_N},{HEX_F,REG_N,REG_M,HEX_B}},
+	{"fmov",{DX_REG_M,A_DEC_N},{HEX_F,REG_N,REG_M,HEX_B}},
+	{"fmov",{A_IND_R0_REG_M,F_REG_N},{HEX_F,REG_N,REG_M,HEX_6}},
+	{"fmov",{A_IND_R0_REG_M,DX_REG_N},{HEX_F,REG_N,REG_M,HEX_6}},
+	{"fmov",{F_REG_M,A_IND_R0_REG_N},{HEX_F,REG_N,REG_M,HEX_7}},
+	{"fmov",{DX_REG_M,A_IND_R0_REG_N},{HEX_F,REG_N,REG_M,HEX_7}},
+	{"fmov.d",{A_IND_M,DX_REG_N},{HEX_F,REG_N,REG_M,HEX_8}},
+	{"fmov.d",{DX_REG_M,A_IND_N},{HEX_F,REG_N,REG_M,HEX_A}},
+	{"fmov.d",{A_INC_M,DX_REG_N},{HEX_F,REG_N,REG_M,HEX_9}},
+	{"fmov.d",{DX_REG_M,A_DEC_N},{HEX_F,REG_N,REG_M,HEX_B}},
+	{"fmov.d",{A_IND_R0_REG_M,DX_REG_N},{HEX_F,REG_N,REG_M,HEX_6}},
+	{"fmov.d",{DX_REG_M,A_IND_R0_REG_N},{HEX_F,REG_N,REG_M,HEX_7}},
+	{"fmov.s",{A_IND_M,F_REG_N},{HEX_F,REG_N,REG_M,HEX_8}},
+	{"fmov.s",{F_REG_M,A_IND_N},{HEX_F,REG_N,REG_M,HEX_A}},
+	{"fmov.s",{A_INC_M,F_REG_N},{HEX_F,REG_N,REG_M,HEX_9}},
+	{"fmov.s",{F_REG_M,A_DEC_N},{HEX_F,REG_N,REG_M,HEX_B}},
+	{"fmov.s",{A_IND_R0_REG_M,F_REG_N},{HEX_F,REG_N,REG_M,HEX_6}},
+	{"fmov.s",{F_REG_M,A_IND_R0_REG_N},{HEX_F,REG_N,REG_M,HEX_7}},
+	{"fmul",{F_REG_M,F_REG_N},{HEX_F,REG_N,REG_M,HEX_2}},
+	{"fmul",{D_REG_M,D_REG_N},{HEX_F,REG_N,REG_M,HEX_2}},
+	{"fneg",{FD_REG_N},{HEX_F,REG_N,HEX_4,HEX_D}},
+	{"frchg",{0},{HEX_F,HEX_B,HEX_F,HEX_D}},
+	{"fschg",{0},{HEX_F,HEX_3,HEX_F,HEX_D}},
+	{"fsqrt",{FD_REG_N},{HEX_F,REG_N,HEX_6,HEX_D}},
+	{"fsts",{FPUL_M,F_REG_N},{HEX_F,REG_N,HEX_0,HEX_D}},
+	{"fsub",{F_REG_M,F_REG_N},{HEX_F,REG_N,REG_M,HEX_1}},
+	{"fsub",{D_REG_M,D_REG_N},{HEX_F,REG_N,REG_M,HEX_1}},
+	{"ftrc",{FD_REG_N,FPUL_M},{HEX_F,REG_N,HEX_3,HEX_D}},
+	{"ftrv",{XMTRX_M4,V_REG_N},{HEX_F,REG_NM,HEX_F,HEX_D}},
+	{ 0 },
+};
+
+static void print_sh_insn(u32 memaddr, u16 insn)
+{
+	int relmask = ~0;
+	int nibs[4] = { (insn >> 12) & 0xf, (insn >> 8) & 0xf, (insn >> 4) & 0xf, insn & 0xf};
+	int lastsp;
+	struct sh_opcode_info *op = sh_table;
+
+	for (; op->name; op++) {
+		int n;
+		int imm = 0;
+		int rn = 0;
+		int rm = 0;
+		int rb = 0;
+		int disp_pc;
+		int disp_pc_addr = 0;
+
+		for (n = 0; n < 4; n++) {
+			int i = op->nibbles[n];
+
+			if (i < 16) {
+				if (nibs[n] == i)
+					continue;
+				goto fail;
+			}
+			switch (i) {
+			case BRANCH_8:
+				imm = (nibs[2] << 4) | (nibs[3]);
+				if (imm & 0x80)
+					imm |= ~0xff;
+				imm = ((char)imm) * 2 + 4 ;
+				goto ok;
+			case BRANCH_12:
+				imm = ((nibs[1]) << 8) | (nibs[2] << 4) | (nibs[3]);
+				if (imm & 0x800)
+					imm |= ~0xfff;
+				imm = imm * 2 + 4;
+				goto ok;
+			case IMM_4:
+				imm = nibs[3];
+				goto ok;
+			case IMM_4BY2:
+				imm = nibs[3] <<1;
+				goto ok;
+			case IMM_4BY4:
+				imm = nibs[3] <<2;
+				goto ok;
+			case IMM_8:
+				imm = (nibs[2] << 4) | nibs[3];
+				goto ok;
+			case PCRELIMM_8BY2:
+				imm = ((nibs[2] << 4) | nibs[3]) <<1;
+				relmask = ~1;
+				goto ok;
+			case PCRELIMM_8BY4:
+				imm = ((nibs[2] << 4) | nibs[3]) <<2;
+				relmask = ~3;
+				goto ok;
+			case IMM_8BY2:
+				imm = ((nibs[2] << 4) | nibs[3]) <<1;
+				goto ok;
+			case IMM_8BY4:
+				imm = ((nibs[2] << 4) | nibs[3]) <<2;
+				goto ok;
+			case DISP_8:
+				imm = (nibs[2] << 4) | (nibs[3]);
+				goto ok;
+			case DISP_4:
+				imm = nibs[3];
+				goto ok;
+			case REG_N:
+				rn = nibs[n];
+				break;
+			case REG_M:
+				rm = nibs[n];
+				break;
+			case REG_NM:
+				rn = (nibs[n] & 0xc) >> 2;
+				rm = (nibs[n] & 0x3);
+				break;
+			case REG_B:
+				rb = nibs[n] & 0x07;
+				break;
+			default:
+				return;
+			}
+		}
+
+	ok:
+		printk("%-8s  ", op->name);
+		lastsp = (op->arg[0] == A_END);
+		disp_pc = 0;
+		for (n = 0; n < 6 && op->arg[n] != A_END; n++) {
+			if (n && op->arg[1] != A_END)
+				printk(", ");
+			switch (op->arg[n]) {
+			case A_IMM:
+				printk("#%d", (char)(imm));
+				break;
+			case A_R0:
+				printk("r0");
+				break;
+			case A_REG_N:
+				printk("r%d", rn);
+				break;
+			case A_INC_N:
+				printk("@r%d+", rn);
+				break;
+			case A_DEC_N:
+				printk("@-r%d", rn);
+				break;
+			case A_IND_N:
+				printk("@r%d", rn);
+				break;
+			case A_DISP_REG_N:
+				printk("@(%d,r%d)", imm, rn);
+				break;
+			case A_REG_M:
+				printk("r%d", rm);
+				break;
+			case A_INC_M:
+				printk("@r%d+", rm);
+				break;
+			case A_DEC_M:
+				printk("@-r%d", rm);
+				break;
+			case A_IND_M:
+				printk("@r%d", rm);
+				break;
+			case A_DISP_REG_M:
+				printk("@(%d,r%d)", imm, rm);
+				break;
+			case A_REG_B:
+				printk("r%d_bank", rb);
+				break;
+			case A_DISP_PC:
+				disp_pc = 1;
+				disp_pc_addr = imm + 4 + (memaddr & relmask);
+				printk("%08x <%pS>", disp_pc_addr,
+				       (void *)disp_pc_addr);
+				break;
+			case A_IND_R0_REG_N:
+				printk("@(r0,r%d)", rn);
+				break;
+			case A_IND_R0_REG_M:
+				printk("@(r0,r%d)", rm);
+				break;
+			case A_DISP_GBR:
+				printk("@(%d,gbr)",imm);
+				break;
+			case A_R0_GBR:
+				printk("@(r0,gbr)");
+				break;
+			case A_BDISP12:
+			case A_BDISP8:
+				printk("%08x", imm + memaddr);
+				break;
+			case A_SR:
+				printk("sr");
+				break;
+			case A_GBR:
+				printk("gbr");
+				break;
+			case A_VBR:
+				printk("vbr");
+				break;
+			case A_SSR:
+				printk("ssr");
+				break;
+			case A_SPC:
+				printk("spc");
+				break;
+			case A_MACH:
+				printk("mach");
+				break;
+			case A_MACL:
+				printk("macl");
+				break;
+			case A_PR:
+				printk("pr");
+				break;
+			case A_SGR:
+				printk("sgr");
+				break;
+			case A_DBR:
+				printk("dbr");
+				break;
+			case FD_REG_N:
+				if (0)
+					goto d_reg_n;
+			case F_REG_N:
+				printk("fr%d", rn);
+				break;
+			case F_REG_M:
+				printk("fr%d", rm);
+				break;
+			case DX_REG_N:
+				if (rn & 1) {
+					printk("xd%d", rn & ~1);
+					break;
+				}
+			d_reg_n:
+			case D_REG_N:
+				printk("dr%d", rn);
+				break;
+			case DX_REG_M:
+				if (rm & 1) {
+					printk("xd%d", rm & ~1);
+					break;
+				}
+			case D_REG_M:
+				printk("dr%d", rm);
+				break;
+			case FPSCR_M:
+			case FPSCR_N:
+				printk("fpscr");
+				break;
+			case FPUL_M:
+			case FPUL_N:
+				printk("fpul");
+				break;
+			case F_FR0:
+				printk("fr0");
+				break;
+			case V_REG_N:
+				printk("fv%d", rn*4);
+				break;
+			case V_REG_M:
+				printk("fv%d", rm*4);
+				break;
+			case XMTRX_M4:
+				printk("xmtrx");
+				break;
+			default:
+				return;
+			}
+		}
+
+		if (disp_pc && strcmp(op->name, "mova") != 0) {
+			u32 val;
+
+			if (relmask == ~1)
+				__get_user(val, (u16 *)disp_pc_addr);
+			else
+				__get_user(val, (u32 *)disp_pc_addr);
+
+			printk("  ! %08x <%pS>", val, (void *)val);
+		}
+
+		return;
+	fail:
+		;
+
+	}
+
+	printk(".word 0x%x%x%x%x", nibs[0], nibs[1], nibs[2], nibs[3]);
+}
+
+void show_code(struct pt_regs *regs)
+{
+	unsigned short *pc = (unsigned short *)regs->pc;
+	long i;
+
+	if (regs->pc & 0x1)
+		return;
+
+	printk("Code:\n");
+
+	for (i = -3 ; i < 6 ; i++) {
+		unsigned short insn;
+
+		if (__get_user(insn, pc + i)) {
+			printk(" (Bad address in pc)\n");
+			break;
+		}
+
+		printk("%s%08lx:  ", (i ? "  ": "->"), (unsigned long)(pc + i));
+		print_sh_insn((unsigned long)(pc + i), insn);
+		printk("\n");
+	}
+
+	printk("\n");
+}
diff --git a/arch/sh/kernel/entry-common.S b/arch/sh/kernel/entry-common.S
index 5b7efc4016fa..efbb4268875e 100644
--- a/arch/sh/kernel/entry-common.S
+++ b/arch/sh/kernel/entry-common.S
@@ -371,47 +371,3 @@ syscall_exit:
 #endif
 7:	.long	do_syscall_trace_enter
 8:	.long	do_syscall_trace_leave
-
-#ifdef CONFIG_FUNCTION_TRACER
-	.align 2
-	.globl	_mcount
-	.type	_mcount,@function
-	.globl	mcount
-	.type	mcount,@function
-_mcount:
-mcount:
-	mov.l	r4, @-r15
-	mov.l	r5, @-r15
-	mov.l	r6, @-r15
-	mov.l	r7, @-r15
-	sts.l	pr, @-r15
-
-	mov.l	@(20,r15),r4
-	sts	pr, r5
-
-	mov.l	1f, r6
-	mov.l	ftrace_stub, r7	
-	cmp/eq	r6, r7
-	bt	skip_trace
-
-	mov.l	@r6, r6
-	jsr	@r6
-	 nop
-
-skip_trace:
-
-	lds.l	@r15+, pr
-	mov.l	@r15+, r7
-	mov.l	@r15+, r6
-	mov.l	@r15+, r5
-	rts
-	 mov.l	@r15+, r4
-
-	.align 2
-1:	.long	ftrace_trace_function
-
-	.globl	ftrace_stub
-ftrace_stub:
-	rts
-	 nop
-#endif /* CONFIG_FUNCTION_TRACER */
diff --git a/arch/sh/kernel/ftrace.c b/arch/sh/kernel/ftrace.c
new file mode 100644
index 000000000000..6c193d56c2e7
--- /dev/null
+++ b/arch/sh/kernel/ftrace.c
@@ -0,0 +1,109 @@
+/*
+ * Copyright (C) 2008 Matt Fleming <mjf@gentoo.org>
+ *
+ * Code for replacing ftrace calls with jumps.
+ *
+ * Copyright (C) 2007-2008 Steven Rostedt <srostedt@redhat.com>
+ *
+ * Thanks goes to Ingo Molnar, for suggesting the idea.
+ * Mathieu Desnoyers, for suggesting postponing the modifications.
+ * Arjan van de Ven, for keeping me straight, and explaining to me
+ * the dangers of modifying code on the run.
+ */
+#include <linux/uaccess.h>
+#include <linux/ftrace.h>
+#include <linux/string.h>
+#include <linux/init.h>
+#include <linux/io.h>
+#include <asm/ftrace.h>
+#include <asm/cacheflush.h>
+
+static unsigned char ftrace_nop[] = {
+	0x09, 0x00,		/* nop */
+	0x09, 0x00,		/* nop */
+};
+
+static unsigned char ftrace_replaced_code[MCOUNT_INSN_SIZE];
+
+unsigned char *ftrace_nop_replace(void)
+{
+	return ftrace_nop;
+}
+
+static int is_sh_nop(unsigned char *ip)
+{
+	return strncmp(ip, ftrace_nop, sizeof(ftrace_nop));
+}
+
+unsigned char *ftrace_call_replace(unsigned long ip, unsigned long addr)
+{
+	/* Place the address in the memory table. */
+	if (addr == CALLER_ADDR)
+		__raw_writel(addr + MCOUNT_INSN_OFFSET, ftrace_replaced_code);
+	else
+		__raw_writel(addr, ftrace_replaced_code);
+
+	/*
+	 * No locking needed, this must be called via kstop_machine
+	 * which in essence is like running on a uniprocessor machine.
+	 */
+	return ftrace_replaced_code;
+}
+
+int ftrace_modify_code(unsigned long ip, unsigned char *old_code,
+		       unsigned char *new_code)
+{
+	unsigned char replaced[MCOUNT_INSN_SIZE];
+
+	/*
+	 * Note: Due to modules and __init, code can
+	 *  disappear and change, we need to protect against faulting
+	 *  as well as code changing. We do this by using the
+	 *  probe_kernel_* functions.
+	 *
+	 * No real locking needed, this code is run through
+	 * kstop_machine, or before SMP starts.
+	 */
+
+	/*
+	 * If we're trying to nop out a call to a function, we instead
+	 * place a call to the address after the memory table.
+	 */
+	if (is_sh_nop(new_code) == 0)
+		__raw_writel(ip + MCOUNT_INSN_SIZE, (unsigned long)new_code);
+
+	/* read the text we want to modify */
+	if (probe_kernel_read(replaced, (void *)ip, MCOUNT_INSN_SIZE))
+		return -EFAULT;
+
+	/* Make sure it is what we expect it to be */
+	if (memcmp(replaced, old_code, MCOUNT_INSN_SIZE) != 0)
+		return -EINVAL;
+
+	/* replace the text with the new text */
+	if (probe_kernel_write((void *)ip, new_code, MCOUNT_INSN_SIZE))
+		return -EPERM;
+
+	flush_icache_range(ip, ip + MCOUNT_INSN_SIZE);
+
+	return 0;
+}
+
+int ftrace_update_ftrace_func(ftrace_func_t func)
+{
+	unsigned long ip = (unsigned long)(&ftrace_call);
+	unsigned char old[MCOUNT_INSN_SIZE], *new;
+
+	memcpy(old, (unsigned char *)(ip + MCOUNT_INSN_OFFSET), MCOUNT_INSN_SIZE);
+	new = ftrace_call_replace(ip, (unsigned long)func);
+
+	return ftrace_modify_code(ip + MCOUNT_INSN_OFFSET, old, new);
+}
+
+int __init ftrace_dyn_arch_init(void *data)
+{
+	/* The return code is retured via data */
+	__raw_writel(0, (unsigned long)data);
+
+	return 0;
+}
diff --git a/arch/sh/kernel/idle.c b/arch/sh/kernel/idle.c
new file mode 100644
index 000000000000..fe59ccfc1152
--- /dev/null
+++ b/arch/sh/kernel/idle.c
@@ -0,0 +1,81 @@
+/*
+ * The idle loop for all SuperH platforms.
+ *
+ *  Copyright (C) 2002 - 2008  Paul Mundt
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ */
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/mm.h>
+#include <linux/pm.h>
+#include <linux/tick.h>
+#include <linux/preempt.h>
+#include <linux/thread_info.h>
+#include <linux/irqflags.h>
+#include <asm/pgalloc.h>
+#include <asm/system.h>
+#include <asm/atomic.h>
+
+static int hlt_counter;
+void (*pm_idle)(void);
+void (*pm_power_off)(void);
+EXPORT_SYMBOL(pm_power_off);
+
+static int __init nohlt_setup(char *__unused)
+{
+	hlt_counter = 1;
+	return 1;
+}
+__setup("nohlt", nohlt_setup);
+
+static int __init hlt_setup(char *__unused)
+{
+	hlt_counter = 0;
+	return 1;
+}
+__setup("hlt", hlt_setup);
+
+static void default_idle(void)
+{
+	if (!hlt_counter) {
+		clear_thread_flag(TIF_POLLING_NRFLAG);
+		smp_mb__after_clear_bit();
+		set_bl_bit();
+		stop_critical_timings();
+
+		while (!need_resched())
+			cpu_sleep();
+
+		start_critical_timings();
+		clear_bl_bit();
+		set_thread_flag(TIF_POLLING_NRFLAG);
+	} else
+		while (!need_resched())
+			cpu_relax();
+}
+
+void cpu_idle(void)
+{
+	set_thread_flag(TIF_POLLING_NRFLAG);
+
+	/* endless idle loop with no priority at all */
+	while (1) {
+		void (*idle)(void) = pm_idle;
+
+		if (!idle)
+			idle = default_idle;
+
+		tick_nohz_stop_sched_tick(1);
+		while (!need_resched())
+			idle();
+		tick_nohz_restart_sched_tick();
+
+		preempt_enable_no_resched();
+		schedule();
+		preempt_disable();
+		check_pgt_cache();
+	}
+}
diff --git a/arch/sh/kernel/pm.c b/arch/sh/kernel/pm.c
deleted file mode 100644
index 10ab62c9aede..000000000000
--- a/arch/sh/kernel/pm.c
+++ /dev/null
@@ -1,88 +0,0 @@
-/*
- * Generic Power Management Routine
- *
- * Copyright (c) 2006 Andriy Skulysh <askulsyh@gmail.com>
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License.
- */
-#include <linux/suspend.h>
-#include <linux/delay.h>
-#include <linux/gfp.h>
-#include <asm/freq.h>
-#include <asm/io.h>
-#include <asm/watchdog.h>
-#include <asm/pm.h>
-
-#define INTR_OFFSET	0x600
-
-#define STBCR		0xffffff82
-#define STBCR2		0xffffff88
-
-#define STBCR_STBY	0x80
-#define STBCR_MSTP2	0x04
-
-#define MCR		0xffffff68
-#define RTCNT		0xffffff70
-
-#define MCR_RMODE	2
-#define MCR_RFSH	4
-
-void pm_enter(void)
-{
-	u8 stbcr, csr;
-	u16 frqcr, mcr;
-	u32 vbr_new, vbr_old;
-
-	set_bl_bit();
-
-	/* set wdt */
-	csr = sh_wdt_read_csr();
-	csr &= ~WTCSR_TME;
-	csr |= WTCSR_CKS_4096;
-	sh_wdt_write_csr(csr);
-	csr = sh_wdt_read_csr();
-	sh_wdt_write_cnt(0);
-
-	/* disable PLL1 */
-	frqcr = ctrl_inw(FRQCR);
-	frqcr &= ~(FRQCR_PLLEN | FRQCR_PSTBY);
-	ctrl_outw(frqcr, FRQCR);
-
-	/* enable standby */
-	stbcr = ctrl_inb(STBCR);
-	ctrl_outb(stbcr | STBCR_STBY | STBCR_MSTP2, STBCR);
-
-	/* set self-refresh */
-	mcr = ctrl_inw(MCR);
-	ctrl_outw(mcr & ~MCR_RFSH, MCR);
-
-	/* set interrupt handler */
-	asm volatile("stc vbr, %0" : "=r" (vbr_old));
-	vbr_new = get_zeroed_page(GFP_ATOMIC);
-	udelay(50);
-	memcpy((void*)(vbr_new + INTR_OFFSET),
-	       &wakeup_start, &wakeup_end - &wakeup_start);
-	asm volatile("ldc %0, vbr" : : "r" (vbr_new));
-
-	ctrl_outw(0, RTCNT);
-	ctrl_outw(mcr | MCR_RFSH | MCR_RMODE, MCR);
-
-	cpu_sleep();
-
-	asm volatile("ldc %0, vbr" : : "r" (vbr_old));
-
-	free_page(vbr_new);
-
-	/* enable PLL1 */
-	frqcr = ctrl_inw(FRQCR);
-	frqcr |= FRQCR_PSTBY;
-	ctrl_outw(frqcr, FRQCR);
-	udelay(50);
-	frqcr |= FRQCR_PLLEN;
-	ctrl_outw(frqcr, FRQCR);
-
-	ctrl_outb(stbcr, STBCR);
-
-	clear_bl_bit();
-}
diff --git a/arch/sh/kernel/process_32.c b/arch/sh/kernel/process_32.c
index b965f0282c7d..130817affa64 100644
--- a/arch/sh/kernel/process_32.c
+++ b/arch/sh/kernel/process_32.c
@@ -32,65 +32,8 @@
 #include <asm/fpu.h>
 #include <asm/syscalls.h>
 
-static int hlt_counter;
 int ubc_usercnt = 0;
 
-void (*pm_idle)(void);
-void (*pm_power_off)(void);
-EXPORT_SYMBOL(pm_power_off);
-
-static int __init nohlt_setup(char *__unused)
-{
-	hlt_counter = 1;
-	return 1;
-}
-__setup("nohlt", nohlt_setup);
-
-static int __init hlt_setup(char *__unused)
-{
-	hlt_counter = 0;
-	return 1;
-}
-__setup("hlt", hlt_setup);
-
-static void default_idle(void)
-{
-	if (!hlt_counter) {
-		clear_thread_flag(TIF_POLLING_NRFLAG);
-		smp_mb__after_clear_bit();
-		set_bl_bit();
-		while (!need_resched())
-			cpu_sleep();
-		clear_bl_bit();
-		set_thread_flag(TIF_POLLING_NRFLAG);
-	} else
-		while (!need_resched())
-			cpu_relax();
-}
-
-void cpu_idle(void)
-{
-	set_thread_flag(TIF_POLLING_NRFLAG);
-
-	/* endless idle loop with no priority at all */
-	while (1) {
-		void (*idle)(void) = pm_idle;
-
-		if (!idle)
-			idle = default_idle;
-
-		tick_nohz_stop_sched_tick(1);
-		while (!need_resched())
-			idle();
-		tick_nohz_restart_sched_tick();
-
-		preempt_enable_no_resched();
-		schedule();
-		preempt_disable();
-		check_pgt_cache();
-	}
-}
-
 void machine_restart(char * __unused)
 {
 	/* SR.BL=1 and invoke address error to let CPU reset (manual reset) */
@@ -115,8 +58,8 @@ void machine_power_off(void)
 void show_regs(struct pt_regs * regs)
 {
 	printk("\n");
-	printk("Pid : %d, Comm: %20s\n", task_pid_nr(current), current->comm);
-	printk("CPU : %d    %s  (%s %.*s)\n",
+	printk("Pid : %d, Comm: \t\t%s\n", task_pid_nr(current), current->comm);
+	printk("CPU : %d        \t\t%s  (%s %.*s)\n\n",
 	       smp_processor_id(), print_tainted(), init_utsname()->release,
 	       (int)strcspn(init_utsname()->version, " "),
 	       init_utsname()->version);
@@ -148,6 +91,7 @@ void show_regs(struct pt_regs * regs)
 	       regs->mach, regs->macl, regs->gbr, regs->pr);
 
 	show_trace(NULL, (unsigned long *)regs->regs[15], regs);
+	show_code(regs);
 }
 
 /*
diff --git a/arch/sh/kernel/process_64.c b/arch/sh/kernel/process_64.c
index b7aa09235b51..597cf02db3fc 100644
--- a/arch/sh/kernel/process_64.c
+++ b/arch/sh/kernel/process_64.c
@@ -33,56 +33,6 @@
 
 struct task_struct *last_task_used_math = NULL;
 
-static int hlt_counter = 1;
-
-#define HARD_IDLE_TIMEOUT (HZ / 3)
-
-static int __init nohlt_setup(char *__unused)
-{
-	hlt_counter = 1;
-	return 1;
-}
-
-static int __init hlt_setup(char *__unused)
-{
-	hlt_counter = 0;
-	return 1;
-}
-
-__setup("nohlt", nohlt_setup);
-__setup("hlt", hlt_setup);
-
-static inline void hlt(void)
-{
-	__asm__ __volatile__ ("sleep" : : : "memory");
-}
-
-/*
- * The idle loop on a uniprocessor SH..
- */
-void cpu_idle(void)
-{
-	/* endless idle loop with no priority at all */
-	while (1) {
-		if (hlt_counter) {
-			while (!need_resched())
-				cpu_relax();
-		} else {
-			local_irq_disable();
-			while (!need_resched()) {
-				local_irq_enable();
-				hlt();
-				local_irq_disable();
-			}
-			local_irq_enable();
-		}
-		preempt_enable_no_resched();
-		schedule();
-		preempt_disable();
-	}
-
-}
-
 void machine_restart(char * __unused)
 {
 	extern void phys_stext(void);
@@ -97,13 +47,6 @@ void machine_halt(void)
 
 void machine_power_off(void)
 {
-#if 0
-	/* Disable watchdog timer */
-	ctrl_outl(0xa5000000, WTCSR);
-	/* Configure deep standby on sleep */
-	ctrl_outl(0x03, STBCR);
-#endif
-
 	__asm__ __volatile__ (
 		"sleep\n\t"
 		"synci\n\t"
@@ -113,9 +56,6 @@ void machine_power_off(void)
 	panic("Unexpected wakeup!\n");
 }
 
-void (*pm_power_off)(void) = machine_power_off;
-EXPORT_SYMBOL(pm_power_off);
-
 void show_regs(struct pt_regs * regs)
 {
 	unsigned long long ah, al, bh, bl, ch, cl;
diff --git a/arch/sh/kernel/setup.c b/arch/sh/kernel/setup.c
index e7152cc6930e..534247508572 100644
--- a/arch/sh/kernel/setup.c
+++ b/arch/sh/kernel/setup.c
@@ -417,6 +417,7 @@ void __init setup_arch(char **cmdline_p)
 }
 
 static const char *cpu_name[] = {
+	[CPU_SH7201]	= "SH7201",
 	[CPU_SH7203]	= "SH7203",	[CPU_SH7263]	= "SH7263",
 	[CPU_SH7206]	= "SH7206",	[CPU_SH7619]	= "SH7619",
 	[CPU_SH7705]	= "SH7705",	[CPU_SH7706]	= "SH7706",
diff --git a/arch/sh/kernel/sh_ksyms_32.c b/arch/sh/kernel/sh_ksyms_32.c
index 92ae5e6c099e..528de2955c81 100644
--- a/arch/sh/kernel/sh_ksyms_32.c
+++ b/arch/sh/kernel/sh_ksyms_32.c
@@ -52,16 +52,12 @@ EXPORT_SYMBOL(__const_udelay);
 
 #define DECLARE_EXPORT(name)		\
 	extern void name(void);EXPORT_SYMBOL(name)
-#define MAYBE_DECLARE_EXPORT(name)	\
-	extern void name(void) __weak;EXPORT_SYMBOL(name)
 
-/* These symbols are generated by the compiler itself */
 DECLARE_EXPORT(__udivsi3);
 DECLARE_EXPORT(__sdivsi3);
+DECLARE_EXPORT(__lshrsi3);
 DECLARE_EXPORT(__ashrsi3);
 DECLARE_EXPORT(__ashlsi3);
-DECLARE_EXPORT(__ashrdi3);
-DECLARE_EXPORT(__ashldi3);
 DECLARE_EXPORT(__ashiftrt_r4_6);
 DECLARE_EXPORT(__ashiftrt_r4_7);
 DECLARE_EXPORT(__ashiftrt_r4_8);
@@ -79,8 +75,7 @@ DECLARE_EXPORT(__ashiftrt_r4_23);
 DECLARE_EXPORT(__ashiftrt_r4_24);
 DECLARE_EXPORT(__ashiftrt_r4_27);
 DECLARE_EXPORT(__ashiftrt_r4_30);
-DECLARE_EXPORT(__lshrsi3);
-DECLARE_EXPORT(__lshrdi3);
+DECLARE_EXPORT(__movstr);
 DECLARE_EXPORT(__movstrSI8);
 DECLARE_EXPORT(__movstrSI12);
 DECLARE_EXPORT(__movstrSI16);
@@ -95,31 +90,17 @@ DECLARE_EXPORT(__movstrSI48);
 DECLARE_EXPORT(__movstrSI52);
 DECLARE_EXPORT(__movstrSI56);
 DECLARE_EXPORT(__movstrSI60);
-#if __GNUC__ == 4
-DECLARE_EXPORT(__movmem);
-#else
-DECLARE_EXPORT(__movstr);
-#endif
-
-#if __GNUC__ == 4
+DECLARE_EXPORT(__movstr_i4_even);
+DECLARE_EXPORT(__movstr_i4_odd);
+DECLARE_EXPORT(__movstrSI12_i4);
 DECLARE_EXPORT(__movmem_i4_even);
 DECLARE_EXPORT(__movmem_i4_odd);
 DECLARE_EXPORT(__movmemSI12_i4);
-
-#if (__GNUC_MINOR__ >= 2 || defined(__GNUC_STM_RELEASE__))
-/*
- * GCC >= 4.2 emits these for division, as do GCC 4.1.x versions of the ST
- * compiler which include backported patches.
- */
 DECLARE_EXPORT(__udiv_qrnnd_16);
-MAYBE_DECLARE_EXPORT(__sdivsi3_i4i);
-MAYBE_DECLARE_EXPORT(__udivsi3_i4i);
-#endif
-#else /* GCC 3.x */
-DECLARE_EXPORT(__movstr_i4_even);
-DECLARE_EXPORT(__movstr_i4_odd);
-DECLARE_EXPORT(__movstrSI12_i4);
-#endif /* __GNUC__ == 4 */
+DECLARE_EXPORT(__sdivsi3_i4);
+DECLARE_EXPORT(__udivsi3_i4);
+DECLARE_EXPORT(__sdivsi3_i4i);
+DECLARE_EXPORT(__udivsi3_i4i);
 
 #if !defined(CONFIG_CACHE_OFF) && (defined(CONFIG_CPU_SH4) || \
 	defined(CONFIG_SH7705_CACHE_32KB))
diff --git a/arch/sh/kernel/sys_sh.c b/arch/sh/kernel/sys_sh.c
index 38f098c9c72d..58dfc02c7af1 100644
--- a/arch/sh/kernel/sys_sh.c
+++ b/arch/sh/kernel/sys_sh.c
@@ -22,102 +22,10 @@
 #include <linux/module.h>
 #include <linux/fs.h>
 #include <linux/ipc.h>
-#include <asm/cacheflush.h>
 #include <asm/syscalls.h>
 #include <asm/uaccess.h>
 #include <asm/unistd.h>
 
-unsigned long shm_align_mask = PAGE_SIZE - 1;	/* Sane caches */
-EXPORT_SYMBOL(shm_align_mask);
-
-#ifdef CONFIG_MMU
-/*
- * To avoid cache aliases, we map the shared page with same color.
- */
-#define COLOUR_ALIGN(addr, pgoff)				\
-	((((addr) + shm_align_mask) & ~shm_align_mask) +	\
-	 (((pgoff) << PAGE_SHIFT) & shm_align_mask))
-
-unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr,
-	unsigned long len, unsigned long pgoff, unsigned long flags)
-{
-	struct mm_struct *mm = current->mm;
-	struct vm_area_struct *vma;
-	unsigned long start_addr;
-	int do_colour_align;
-
-	if (flags & MAP_FIXED) {
-		/* We do not accept a shared mapping if it would violate
-		 * cache aliasing constraints.
-		 */
-		if ((flags & MAP_SHARED) && (addr & shm_align_mask))
-			return -EINVAL;
-		return addr;
-	}
-
-	if (unlikely(len > TASK_SIZE))
-		return -ENOMEM;
-
-	do_colour_align = 0;
-	if (filp || (flags & MAP_SHARED))
-		do_colour_align = 1;
-
-	if (addr) {
-		if (do_colour_align)
-			addr = COLOUR_ALIGN(addr, pgoff);
-		else
-			addr = PAGE_ALIGN(addr);
-
-		vma = find_vma(mm, addr);
-		if (TASK_SIZE - len >= addr &&
-		    (!vma || addr + len <= vma->vm_start))
-			return addr;
-	}
-
-	if (len > mm->cached_hole_size) {
-		start_addr = addr = mm->free_area_cache;
-	} else {
-	        mm->cached_hole_size = 0;
-		start_addr = addr = TASK_UNMAPPED_BASE;
-	}
-
-full_search:
-	if (do_colour_align)
-		addr = COLOUR_ALIGN(addr, pgoff);
-	else
-		addr = PAGE_ALIGN(mm->free_area_cache);
-
-	for (vma = find_vma(mm, addr); ; vma = vma->vm_next) {
-		/* At this point:  (!vma || addr < vma->vm_end). */
-		if (unlikely(TASK_SIZE - len < addr)) {
-			/*
-			 * Start a new search - just in case we missed
-			 * some holes.
-			 */
-			if (start_addr != TASK_UNMAPPED_BASE) {
-				start_addr = addr = TASK_UNMAPPED_BASE;
-				mm->cached_hole_size = 0;
-				goto full_search;
-			}
-			return -ENOMEM;
-		}
-		if (likely(!vma || addr + len <= vma->vm_start)) {
-			/*
-			 * Remember the place where we stopped the search:
-			 */
-			mm->free_area_cache = addr + len;
-			return addr;
-		}
-		if (addr + mm->cached_hole_size < vma->vm_start)
-		        mm->cached_hole_size = vma->vm_start - addr;
-
-		addr = vma->vm_end;
-		if (do_colour_align)
-			addr = COLOUR_ALIGN(addr, pgoff);
-	}
-}
-#endif /* CONFIG_MMU */
-
 static inline long
 do_mmap2(unsigned long addr, unsigned long len, unsigned long prot,
 	 unsigned long flags, int fd, unsigned long pgoff)
diff --git a/arch/sh/kernel/timers/timer-mtu2.c b/arch/sh/kernel/timers/timer-mtu2.c
index fe453c01f9c9..c3d237e1d566 100644
--- a/arch/sh/kernel/timers/timer-mtu2.c
+++ b/arch/sh/kernel/timers/timer-mtu2.c
@@ -34,7 +34,12 @@
 #define MTU2_TIER_1	0xfffe4384
 #define MTU2_TSR_1	0xfffe4385
 #define MTU2_TCNT_1	0xfffe4386	/* 16-bit counter */
+
+#if defined(CONFIG_CPU_SUBTYPE_SH7201)
+#define MTU2_TGRA_1	0xfffe4388
+#else
 #define MTU2_TGRA_1	0xfffe438a
+#endif
 
 #define STBCR3		0xfffe0408
 
diff --git a/arch/sh/kernel/traps_32.c b/arch/sh/kernel/traps_32.c
index 1e5c74efbacc..6094fc13beea 100644
--- a/arch/sh/kernel/traps_32.c
+++ b/arch/sh/kernel/traps_32.c
@@ -689,7 +689,7 @@ asmlinkage void do_reserved_inst(unsigned long r4, unsigned long r5,
 }
 
 #ifdef CONFIG_SH_FPU_EMU
-static int emulate_branch(unsigned short inst, struct pt_regs* regs)
+static int emulate_branch(unsigned short inst, struct pt_regs *regs)
 {
 	/*
 	 * bfs: 8fxx: PC+=d*2+4;
@@ -702,27 +702,32 @@ static int emulate_branch(unsigned short inst, struct pt_regs* regs)
 	 * jsr: 4x0b: PC=Rn      after PR=PC+4;
 	 * rts: 000b: PC=PR;
 	 */
-	if ((inst & 0xfd00) == 0x8d00) {
+	if (((inst & 0xf000) == 0xb000)  ||	/* bsr */
+	    ((inst & 0xf0ff) == 0x0003)  ||	/* bsrf */
+	    ((inst & 0xf0ff) == 0x400b))	/* jsr */
+		regs->pr = regs->pc + 4;
+
+	if ((inst & 0xfd00) == 0x8d00) {	/* bfs, bts */
 		regs->pc += SH_PC_8BIT_OFFSET(inst);
 		return 0;
 	}
 
-	if ((inst & 0xe000) == 0xa000) {
+	if ((inst & 0xe000) == 0xa000) {	/* bra, bsr */
 		regs->pc += SH_PC_12BIT_OFFSET(inst);
 		return 0;
 	}
 
-	if ((inst & 0xf0df) == 0x0003) {
+	if ((inst & 0xf0df) == 0x0003) {	/* braf, bsrf */
 		regs->pc += regs->regs[(inst & 0x0f00) >> 8] + 4;
 		return 0;
 	}
 
-	if ((inst & 0xf0df) == 0x400b) {
+	if ((inst & 0xf0df) == 0x400b) {	/* jmp, jsr */
 		regs->pc = regs->regs[(inst & 0x0f00) >> 8];
 		return 0;
 	}
 
-	if ((inst & 0xffff) == 0x000b) {
+	if ((inst & 0xffff) == 0x000b) {	/* rts */
 		regs->pc = regs->pr;
 		return 0;
 	}
@@ -868,10 +873,7 @@ void show_trace(struct task_struct *tsk, unsigned long *sp,
 	if (regs && user_mode(regs))
 		return;
 
-	printk("\nCall trace: ");
-#ifdef CONFIG_KALLSYMS
-	printk("\n");
-#endif
+	printk("\nCall trace:\n");
 
 	while (!kstack_end(sp)) {
 		addr = *sp++;
diff --git a/arch/sh/kernel/vsyscall/vsyscall.c b/arch/sh/kernel/vsyscall/vsyscall.c
index 95f4de0800ec..3f7e415be86a 100644
--- a/arch/sh/kernel/vsyscall/vsyscall.c
+++ b/arch/sh/kernel/vsyscall/vsyscall.c
@@ -59,8 +59,7 @@ int __init vsyscall_init(void)
 }
 
 /* Setup a VMA at program startup for the vsyscall page */
-int arch_setup_additional_pages(struct linux_binprm *bprm,
-				int executable_stack)
+int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
 {
 	struct mm_struct *mm = current->mm;
 	unsigned long addr;
diff --git a/arch/sh/lib/Makefile b/arch/sh/lib/Makefile
index 8596cc78e18d..a30acb8342d9 100644
--- a/arch/sh/lib/Makefile
+++ b/arch/sh/lib/Makefile
@@ -5,12 +5,25 @@
 lib-y  = delay.o memset.o memmove.o memchr.o \
 	 checksum.o strlen.o div64.o div64-generic.o
 
+# Extracted from libgcc
+lib-y += movmem.o ashldi3.o ashrdi3.o lshrdi3.o \
+	 ashlsi3.o ashrsi3.o ashiftrt.o lshrsi3.o \
+	 udiv_qrnnd.o
+
+udivsi3-y			:= udivsi3-Os.o
+
+ifneq ($(CONFIG_CC_OPTIMIZE_FOR_SIZE),y)
+udivsi3-$(CONFIG_CPU_SH3)	:= udivsi3.o
+udivsi3-$(CONFIG_CPU_SH4)	:= udivsi3.o
+endif
+
 obj-y				+= io.o
 
 memcpy-y			:= memcpy.o
 memcpy-$(CONFIG_CPU_SH4)	:= memcpy-sh4.o
 
 lib-$(CONFIG_MMU)		+= copy_page.o clear_page.o
-lib-y				+= $(memcpy-y)
+lib-$(CONFIG_FUNCTION_TRACER)	+= mcount.o
+lib-y				+= $(memcpy-y) $(udivsi3-y)
 
 EXTRA_CFLAGS += -Werror
diff --git a/arch/sh/lib/ashiftrt.S b/arch/sh/lib/ashiftrt.S
new file mode 100644
index 000000000000..45ce86558f46
--- /dev/null
+++ b/arch/sh/lib/ashiftrt.S
@@ -0,0 +1,149 @@
+/* Copyright (C) 1994, 1995, 1997, 1998, 1999, 2000, 2001, 2002, 2003,
+   2004, 2005, 2006
+   Free Software Foundation, Inc.
+
+This file is free software; you can redistribute it and/or modify it
+under the terms of the GNU General Public License as published by the
+Free Software Foundation; either version 2, or (at your option) any
+later version.
+
+In addition to the permissions in the GNU General Public License, the
+Free Software Foundation gives you unlimited permission to link the
+compiled version of this file into combinations with other programs,
+and to distribute those combinations without any restriction coming
+from the use of this file.  (The General Public License restrictions
+do apply in other respects; for example, they cover modification of
+the file, and distribution when not linked into a combine
+executable.)
+
+This file is distributed in the hope that it will be useful, but
+WITHOUT ANY WARRANTY; without even the implied warranty of
+MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+General Public License for more details.
+
+You should have received a copy of the GNU General Public License
+along with this program; see the file COPYING.  If not, write to
+the Free Software Foundation, 51 Franklin Street, Fifth Floor,
+Boston, MA 02110-1301, USA.  */
+
+!! libgcc routines for the Renesas / SuperH SH CPUs.
+!! Contributed by Steve Chamberlain.
+!! sac@cygnus.com
+
+!! ashiftrt_r4_x, ___ashrsi3, ___ashlsi3, ___lshrsi3 routines
+!! recoded in assembly by Toshiyasu Morita
+!! tm@netcom.com
+
+/* SH2 optimizations for ___ashrsi3, ___ashlsi3, ___lshrsi3 and
+   ELF local label prefixes by J"orn Rennecke
+   amylaar@cygnus.com  */
+
+	.global	__ashiftrt_r4_0
+	.global	__ashiftrt_r4_1
+	.global	__ashiftrt_r4_2
+	.global	__ashiftrt_r4_3
+	.global	__ashiftrt_r4_4
+	.global	__ashiftrt_r4_5
+	.global	__ashiftrt_r4_6
+	.global	__ashiftrt_r4_7
+	.global	__ashiftrt_r4_8
+	.global	__ashiftrt_r4_9
+	.global	__ashiftrt_r4_10
+	.global	__ashiftrt_r4_11
+	.global	__ashiftrt_r4_12
+	.global	__ashiftrt_r4_13
+	.global	__ashiftrt_r4_14
+	.global	__ashiftrt_r4_15
+	.global	__ashiftrt_r4_16
+	.global	__ashiftrt_r4_17
+	.global	__ashiftrt_r4_18
+	.global	__ashiftrt_r4_19
+	.global	__ashiftrt_r4_20
+	.global	__ashiftrt_r4_21
+	.global	__ashiftrt_r4_22
+	.global	__ashiftrt_r4_23
+	.global	__ashiftrt_r4_24
+	.global	__ashiftrt_r4_25
+	.global	__ashiftrt_r4_26
+	.global	__ashiftrt_r4_27
+	.global	__ashiftrt_r4_28
+	.global	__ashiftrt_r4_29
+	.global	__ashiftrt_r4_30
+	.global	__ashiftrt_r4_31
+	.global	__ashiftrt_r4_32
+
+	.align	1
+__ashiftrt_r4_32:
+__ashiftrt_r4_31:
+	rotcl	r4
+	rts
+	subc	r4,r4
+__ashiftrt_r4_30:
+	shar	r4
+__ashiftrt_r4_29:
+	shar	r4
+__ashiftrt_r4_28:
+	shar	r4
+__ashiftrt_r4_27:
+	shar	r4
+__ashiftrt_r4_26:
+	shar	r4
+__ashiftrt_r4_25:
+	shar	r4
+__ashiftrt_r4_24:
+	shlr16	r4
+	shlr8	r4
+	rts
+	exts.b	r4,r4
+__ashiftrt_r4_23:
+	shar	r4
+__ashiftrt_r4_22:
+	shar	r4
+__ashiftrt_r4_21:
+	shar	r4
+__ashiftrt_r4_20:
+	shar	r4
+__ashiftrt_r4_19:
+	shar	r4
+__ashiftrt_r4_18:
+	shar	r4
+__ashiftrt_r4_17:
+	shar	r4
+__ashiftrt_r4_16:
+	shlr16	r4
+	rts
+	exts.w	r4,r4
+__ashiftrt_r4_15:
+	shar	r4
+__ashiftrt_r4_14:
+	shar	r4
+__ashiftrt_r4_13:
+	shar	r4
+__ashiftrt_r4_12:
+	shar	r4
+__ashiftrt_r4_11:
+	shar	r4
+__ashiftrt_r4_10:
+	shar	r4
+__ashiftrt_r4_9:
+	shar	r4
+__ashiftrt_r4_8:
+	shar	r4
+__ashiftrt_r4_7:
+	shar	r4
+__ashiftrt_r4_6:
+	shar	r4
+__ashiftrt_r4_5:
+	shar	r4
+__ashiftrt_r4_4:
+	shar	r4
+__ashiftrt_r4_3:
+	shar	r4
+__ashiftrt_r4_2:
+	shar	r4
+__ashiftrt_r4_1:
+	rts
+	shar	r4
+__ashiftrt_r4_0:
+	rts
+	nop
diff --git a/arch/sh/lib/ashldi3.c b/arch/sh/lib/ashldi3.c
new file mode 100644
index 000000000000..beb80f316095
--- /dev/null
+++ b/arch/sh/lib/ashldi3.c
@@ -0,0 +1,29 @@
+#include <linux/module.h>
+
+#include "libgcc.h"
+
+long long __ashldi3(long long u, word_type b)
+{
+	DWunion uu, w;
+	word_type bm;
+
+	if (b == 0)
+		return u;
+
+	uu.ll = u;
+	bm = 32 - b;
+
+	if (bm <= 0) {
+		w.s.low = 0;
+		w.s.high = (unsigned int) uu.s.low << -bm;
+	} else {
+		const unsigned int carries = (unsigned int) uu.s.low >> bm;
+
+		w.s.low = (unsigned int) uu.s.low << b;
+		w.s.high = ((unsigned int) uu.s.high << b) | carries;
+	}
+
+	return w.ll;
+}
+
+EXPORT_SYMBOL(__ashldi3);
diff --git a/arch/sh/lib/ashlsi3.S b/arch/sh/lib/ashlsi3.S
new file mode 100644
index 000000000000..bd47e9b403a5
--- /dev/null
+++ b/arch/sh/lib/ashlsi3.S
@@ -0,0 +1,193 @@
+/* Copyright (C) 1994, 1995, 1997, 1998, 1999, 2000, 2001, 2002, 2003,
+   2004, 2005, 2006
+   Free Software Foundation, Inc.
+
+This file is free software; you can redistribute it and/or modify it
+under the terms of the GNU General Public License as published by the
+Free Software Foundation; either version 2, or (at your option) any
+later version.
+
+In addition to the permissions in the GNU General Public License, the
+Free Software Foundation gives you unlimited permission to link the
+compiled version of this file into combinations with other programs,
+and to distribute those combinations without any restriction coming
+from the use of this file.  (The General Public License restrictions
+do apply in other respects; for example, they cover modification of
+the file, and distribution when not linked into a combine
+executable.)
+
+This file is distributed in the hope that it will be useful, but
+WITHOUT ANY WARRANTY; without even the implied warranty of
+MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+General Public License for more details.
+
+You should have received a copy of the GNU General Public License
+along with this program; see the file COPYING.  If not, write to
+the Free Software Foundation, 51 Franklin Street, Fifth Floor,
+Boston, MA 02110-1301, USA.  */
+
+!! libgcc routines for the Renesas / SuperH SH CPUs.
+!! Contributed by Steve Chamberlain.
+!! sac@cygnus.com
+
+!! ashiftrt_r4_x, ___ashrsi3, ___ashlsi3, ___lshrsi3 routines
+!! recoded in assembly by Toshiyasu Morita
+!! tm@netcom.com
+
+/* SH2 optimizations for ___ashrsi3, ___ashlsi3, ___lshrsi3 and
+   ELF local label prefixes by J"orn Rennecke
+   amylaar@cygnus.com  */
+
+!
+! __ashlsi3
+!
+! Entry:
+!
+! r4: Value to shift
+! r5: Shifts
+!
+! Exit:
+!
+! r0: Result
+!
+! Destroys:
+!
+! (none)
+!
+	.global	__ashlsi3
+	
+	.align	2
+__ashlsi3:
+	mov	#31,r0
+	and	r0,r5
+	mova	ashlsi3_table,r0
+	mov.b	@(r0,r5),r5
+#ifdef __sh1__
+	add	r5,r0
+	jmp	@r0
+#else
+	braf	r5
+#endif
+	mov	r4,r0
+
+	.align	2
+ashlsi3_table:
+	.byte		ashlsi3_0-ashlsi3_table
+	.byte		ashlsi3_1-ashlsi3_table
+	.byte		ashlsi3_2-ashlsi3_table
+	.byte		ashlsi3_3-ashlsi3_table
+	.byte		ashlsi3_4-ashlsi3_table
+	.byte		ashlsi3_5-ashlsi3_table
+	.byte		ashlsi3_6-ashlsi3_table
+	.byte		ashlsi3_7-ashlsi3_table
+	.byte		ashlsi3_8-ashlsi3_table
+	.byte		ashlsi3_9-ashlsi3_table
+	.byte		ashlsi3_10-ashlsi3_table
+	.byte		ashlsi3_11-ashlsi3_table
+	.byte		ashlsi3_12-ashlsi3_table
+	.byte		ashlsi3_13-ashlsi3_table
+	.byte		ashlsi3_14-ashlsi3_table
+	.byte		ashlsi3_15-ashlsi3_table
+	.byte		ashlsi3_16-ashlsi3_table
+	.byte		ashlsi3_17-ashlsi3_table
+	.byte		ashlsi3_18-ashlsi3_table
+	.byte		ashlsi3_19-ashlsi3_table
+	.byte		ashlsi3_20-ashlsi3_table
+	.byte		ashlsi3_21-ashlsi3_table
+	.byte		ashlsi3_22-ashlsi3_table
+	.byte		ashlsi3_23-ashlsi3_table
+	.byte		ashlsi3_24-ashlsi3_table
+	.byte		ashlsi3_25-ashlsi3_table
+	.byte		ashlsi3_26-ashlsi3_table
+	.byte		ashlsi3_27-ashlsi3_table
+	.byte		ashlsi3_28-ashlsi3_table
+	.byte		ashlsi3_29-ashlsi3_table
+	.byte		ashlsi3_30-ashlsi3_table
+	.byte		ashlsi3_31-ashlsi3_table
+
+ashlsi3_6:
+	shll2	r0
+ashlsi3_4:
+	shll2	r0
+ashlsi3_2:
+	rts
+	shll2	r0
+
+ashlsi3_7:
+	shll2	r0
+ashlsi3_5:
+	shll2	r0
+ashlsi3_3:
+	shll2	r0
+ashlsi3_1:
+	rts
+	shll	r0
+
+ashlsi3_14:
+	shll2	r0
+ashlsi3_12:
+	shll2	r0
+ashlsi3_10:
+	shll2	r0
+ashlsi3_8:
+	rts
+	shll8	r0
+
+ashlsi3_15:
+	shll2	r0
+ashlsi3_13:
+	shll2	r0
+ashlsi3_11:
+	shll2	r0
+ashlsi3_9:
+	shll8	r0
+	rts
+	shll	r0
+
+ashlsi3_22:
+	shll2	r0
+ashlsi3_20:
+	shll2	r0
+ashlsi3_18:
+	shll2	r0
+ashlsi3_16:
+	rts
+	shll16	r0
+
+ashlsi3_23:
+	shll2	r0
+ashlsi3_21:
+	shll2	r0
+ashlsi3_19:
+	shll2	r0
+ashlsi3_17:
+	shll16	r0
+	rts
+	shll	r0
+
+ashlsi3_30:
+	shll2	r0
+ashlsi3_28:
+	shll2	r0
+ashlsi3_26:
+	shll2	r0
+ashlsi3_24:
+	shll16	r0
+	rts
+	shll8	r0
+
+ashlsi3_31:
+	shll2	r0
+ashlsi3_29:
+	shll2	r0
+ashlsi3_27:
+	shll2	r0
+ashlsi3_25:
+	shll16	r0
+	shll8	r0
+	rts
+	shll	r0
+
+ashlsi3_0:
+	rts
+	nop
diff --git a/arch/sh/lib/ashrdi3.c b/arch/sh/lib/ashrdi3.c
new file mode 100644
index 000000000000..c884a912b660
--- /dev/null
+++ b/arch/sh/lib/ashrdi3.c
@@ -0,0 +1,31 @@
+#include <linux/module.h>
+
+#include "libgcc.h"
+
+long long __ashrdi3(long long u, word_type b)
+{
+	DWunion uu, w;
+	word_type bm;
+
+	if (b == 0)
+		return u;
+
+	uu.ll = u;
+	bm = 32 - b;
+
+	if (bm <= 0) {
+		/* w.s.high = 1..1 or 0..0 */
+		w.s.high =
+		    uu.s.high >> 31;
+		w.s.low = uu.s.high >> -bm;
+	} else {
+		const unsigned int carries = (unsigned int) uu.s.high << bm;
+
+		w.s.high = uu.s.high >> b;
+		w.s.low = ((unsigned int) uu.s.low >> b) | carries;
+	}
+
+	return w.ll;
+}
+
+EXPORT_SYMBOL(__ashrdi3);
diff --git a/arch/sh/lib/ashrsi3.S b/arch/sh/lib/ashrsi3.S
new file mode 100644
index 000000000000..6f3cf46b77c2
--- /dev/null
+++ b/arch/sh/lib/ashrsi3.S
@@ -0,0 +1,185 @@
+/* Copyright (C) 1994, 1995, 1997, 1998, 1999, 2000, 2001, 2002, 2003,
+   2004, 2005, 2006
+   Free Software Foundation, Inc.
+
+This file is free software; you can redistribute it and/or modify it
+under the terms of the GNU General Public License as published by the
+Free Software Foundation; either version 2, or (at your option) any
+later version.
+
+In addition to the permissions in the GNU General Public License, the
+Free Software Foundation gives you unlimited permission to link the
+compiled version of this file into combinations with other programs,
+and to distribute those combinations without any restriction coming
+from the use of this file.  (The General Public License restrictions
+do apply in other respects; for example, they cover modification of
+the file, and distribution when not linked into a combine
+executable.)
+
+This file is distributed in the hope that it will be useful, but
+WITHOUT ANY WARRANTY; without even the implied warranty of
+MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+General Public License for more details.
+
+You should have received a copy of the GNU General Public License
+along with this program; see the file COPYING.  If not, write to
+the Free Software Foundation, 51 Franklin Street, Fifth Floor,
+Boston, MA 02110-1301, USA.  */
+
+!! libgcc routines for the Renesas / SuperH SH CPUs.
+!! Contributed by Steve Chamberlain.
+!! sac@cygnus.com
+
+!! ashiftrt_r4_x, ___ashrsi3, ___ashlsi3, ___lshrsi3 routines
+!! recoded in assembly by Toshiyasu Morita
+!! tm@netcom.com
+
+/* SH2 optimizations for ___ashrsi3, ___ashlsi3, ___lshrsi3 and
+   ELF local label prefixes by J"orn Rennecke
+   amylaar@cygnus.com  */
+
+!
+! __ashrsi3
+!
+! Entry:
+!
+! r4: Value to shift
+! r5: Shifts
+!
+! Exit:
+!
+! r0: Result
+!
+! Destroys:
+!
+! (none)
+!
+
+	.global	__ashrsi3
+	
+	.align	2
+__ashrsi3:
+	mov	#31,r0
+	and	r0,r5
+	mova	ashrsi3_table,r0
+	mov.b	@(r0,r5),r5
+#ifdef __sh1__
+	add	r5,r0
+	jmp	@r0
+#else
+	braf	r5
+#endif
+	mov	r4,r0
+
+	.align	2
+ashrsi3_table:
+	.byte		ashrsi3_0-ashrsi3_table
+	.byte		ashrsi3_1-ashrsi3_table
+	.byte		ashrsi3_2-ashrsi3_table
+	.byte		ashrsi3_3-ashrsi3_table
+	.byte		ashrsi3_4-ashrsi3_table
+	.byte		ashrsi3_5-ashrsi3_table
+	.byte		ashrsi3_6-ashrsi3_table
+	.byte		ashrsi3_7-ashrsi3_table
+	.byte		ashrsi3_8-ashrsi3_table
+	.byte		ashrsi3_9-ashrsi3_table
+	.byte		ashrsi3_10-ashrsi3_table
+	.byte		ashrsi3_11-ashrsi3_table
+	.byte		ashrsi3_12-ashrsi3_table
+	.byte		ashrsi3_13-ashrsi3_table
+	.byte		ashrsi3_14-ashrsi3_table
+	.byte		ashrsi3_15-ashrsi3_table
+	.byte		ashrsi3_16-ashrsi3_table
+	.byte		ashrsi3_17-ashrsi3_table
+	.byte		ashrsi3_18-ashrsi3_table
+	.byte		ashrsi3_19-ashrsi3_table
+	.byte		ashrsi3_20-ashrsi3_table
+	.byte		ashrsi3_21-ashrsi3_table
+	.byte		ashrsi3_22-ashrsi3_table
+	.byte		ashrsi3_23-ashrsi3_table
+	.byte		ashrsi3_24-ashrsi3_table
+	.byte		ashrsi3_25-ashrsi3_table
+	.byte		ashrsi3_26-ashrsi3_table
+	.byte		ashrsi3_27-ashrsi3_table
+	.byte		ashrsi3_28-ashrsi3_table
+	.byte		ashrsi3_29-ashrsi3_table
+	.byte		ashrsi3_30-ashrsi3_table
+	.byte		ashrsi3_31-ashrsi3_table
+
+ashrsi3_31:
+	rotcl	r0
+	rts
+	subc	r0,r0
+
+ashrsi3_30:
+	shar	r0
+ashrsi3_29:
+	shar	r0
+ashrsi3_28:
+	shar	r0
+ashrsi3_27:
+	shar	r0
+ashrsi3_26:
+	shar	r0
+ashrsi3_25:
+	shar	r0
+ashrsi3_24:
+	shlr16	r0
+	shlr8	r0
+	rts
+	exts.b	r0,r0
+
+ashrsi3_23:
+	shar	r0
+ashrsi3_22:
+	shar	r0
+ashrsi3_21:
+	shar	r0
+ashrsi3_20:
+	shar	r0
+ashrsi3_19:
+	shar	r0
+ashrsi3_18:
+	shar	r0
+ashrsi3_17:
+	shar	r0
+ashrsi3_16:
+	shlr16	r0
+	rts
+	exts.w	r0,r0
+
+ashrsi3_15:
+	shar	r0
+ashrsi3_14:
+	shar	r0
+ashrsi3_13:
+	shar	r0
+ashrsi3_12:
+	shar	r0
+ashrsi3_11:
+	shar	r0
+ashrsi3_10:
+	shar	r0
+ashrsi3_9:
+	shar	r0
+ashrsi3_8:
+	shar	r0
+ashrsi3_7:
+	shar	r0
+ashrsi3_6:
+	shar	r0
+ashrsi3_5:
+	shar	r0
+ashrsi3_4:
+	shar	r0
+ashrsi3_3:
+	shar	r0
+ashrsi3_2:
+	shar	r0
+ashrsi3_1:
+	rts
+	shar	r0
+
+ashrsi3_0:
+	rts
+	nop
diff --git a/arch/sh/lib/libgcc.h b/arch/sh/lib/libgcc.h
new file mode 100644
index 000000000000..3f19d1c5d942
--- /dev/null
+++ b/arch/sh/lib/libgcc.h
@@ -0,0 +1,26 @@
+#ifndef __ASM_LIBGCC_H
+#define __ASM_LIBGCC_H
+
+#include <asm/byteorder.h>
+
+typedef int word_type __attribute__ ((mode (__word__)));
+
+#ifdef __BIG_ENDIAN
+struct DWstruct {
+	int high, low;
+};
+#elif defined(__LITTLE_ENDIAN)
+struct DWstruct {
+	int low, high;
+};
+#else
+#error I feel sick.
+#endif
+
+typedef union
+{
+	struct DWstruct s;
+	long long ll;
+} DWunion;
+
+#endif /* __ASM_LIBGCC_H */
diff --git a/arch/sh/lib/lshrdi3.c b/arch/sh/lib/lshrdi3.c
new file mode 100644
index 000000000000..dcf8d6810b7c
--- /dev/null
+++ b/arch/sh/lib/lshrdi3.c
@@ -0,0 +1,29 @@
+#include <linux/module.h>
+
+#include "libgcc.h"
+
+long long __lshrdi3(long long u, word_type b)
+{
+	DWunion uu, w;
+	word_type bm;
+
+	if (b == 0)
+		return u;
+
+	uu.ll = u;
+	bm = 32 - b;
+
+	if (bm <= 0) {
+		w.s.high = 0;
+		w.s.low = (unsigned int) uu.s.high >> -bm;
+	} else {
+		const unsigned int carries = (unsigned int) uu.s.high << bm;
+
+		w.s.high = (unsigned int) uu.s.high >> b;
+		w.s.low = ((unsigned int) uu.s.low >> b) | carries;
+	}
+
+	return w.ll;
+}
+
+EXPORT_SYMBOL(__lshrdi3);
diff --git a/arch/sh/lib/lshrsi3.S b/arch/sh/lib/lshrsi3.S
new file mode 100644
index 000000000000..1e7aaa557130
--- /dev/null
+++ b/arch/sh/lib/lshrsi3.S
@@ -0,0 +1,193 @@
+/* Copyright (C) 1994, 1995, 1997, 1998, 1999, 2000, 2001, 2002, 2003,
+   2004, 2005, 2006
+   Free Software Foundation, Inc.
+
+This file is free software; you can redistribute it and/or modify it
+under the terms of the GNU General Public License as published by the
+Free Software Foundation; either version 2, or (at your option) any
+later version.
+
+In addition to the permissions in the GNU General Public License, the
+Free Software Foundation gives you unlimited permission to link the
+compiled version of this file into combinations with other programs,
+and to distribute those combinations without any restriction coming
+from the use of this file.  (The General Public License restrictions
+do apply in other respects; for example, they cover modification of
+the file, and distribution when not linked into a combine
+executable.)
+
+This file is distributed in the hope that it will be useful, but
+WITHOUT ANY WARRANTY; without even the implied warranty of
+MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+General Public License for more details.
+
+You should have received a copy of the GNU General Public License
+along with this program; see the file COPYING.  If not, write to
+the Free Software Foundation, 51 Franklin Street, Fifth Floor,
+Boston, MA 02110-1301, USA.  */
+
+!! libgcc routines for the Renesas / SuperH SH CPUs.
+!! Contributed by Steve Chamberlain.
+!! sac@cygnus.com
+
+!! ashiftrt_r4_x, ___ashrsi3, ___ashlsi3, ___lshrsi3 routines
+!! recoded in assembly by Toshiyasu Morita
+!! tm@netcom.com
+
+/* SH2 optimizations for ___ashrsi3, ___ashlsi3, ___lshrsi3 and
+   ELF local label prefixes by J"orn Rennecke
+   amylaar@cygnus.com  */
+
+!
+! __lshrsi3
+!
+! Entry:
+!
+! r4: Value to shift
+! r5: Shifts
+!
+! Exit:
+!
+! r0: Result
+!
+! Destroys:
+!
+! (none)
+!
+	.global	__lshrsi3
+	
+	.align	2
+__lshrsi3:
+	mov	#31,r0
+	and	r0,r5
+	mova	lshrsi3_table,r0
+	mov.b	@(r0,r5),r5
+#ifdef __sh1__
+	add	r5,r0
+	jmp	@r0
+#else
+	braf	r5
+#endif
+	mov	r4,r0
+
+	.align	2
+lshrsi3_table:
+	.byte		lshrsi3_0-lshrsi3_table
+	.byte		lshrsi3_1-lshrsi3_table
+	.byte		lshrsi3_2-lshrsi3_table
+	.byte		lshrsi3_3-lshrsi3_table
+	.byte		lshrsi3_4-lshrsi3_table
+	.byte		lshrsi3_5-lshrsi3_table
+	.byte		lshrsi3_6-lshrsi3_table
+	.byte		lshrsi3_7-lshrsi3_table
+	.byte		lshrsi3_8-lshrsi3_table
+	.byte		lshrsi3_9-lshrsi3_table
+	.byte		lshrsi3_10-lshrsi3_table
+	.byte		lshrsi3_11-lshrsi3_table
+	.byte		lshrsi3_12-lshrsi3_table
+	.byte		lshrsi3_13-lshrsi3_table
+	.byte		lshrsi3_14-lshrsi3_table
+	.byte		lshrsi3_15-lshrsi3_table
+	.byte		lshrsi3_16-lshrsi3_table
+	.byte		lshrsi3_17-lshrsi3_table
+	.byte		lshrsi3_18-lshrsi3_table
+	.byte		lshrsi3_19-lshrsi3_table
+	.byte		lshrsi3_20-lshrsi3_table
+	.byte		lshrsi3_21-lshrsi3_table
+	.byte		lshrsi3_22-lshrsi3_table
+	.byte		lshrsi3_23-lshrsi3_table
+	.byte		lshrsi3_24-lshrsi3_table
+	.byte		lshrsi3_25-lshrsi3_table
+	.byte		lshrsi3_26-lshrsi3_table
+	.byte		lshrsi3_27-lshrsi3_table
+	.byte		lshrsi3_28-lshrsi3_table
+	.byte		lshrsi3_29-lshrsi3_table
+	.byte		lshrsi3_30-lshrsi3_table
+	.byte		lshrsi3_31-lshrsi3_table
+
+lshrsi3_6:
+	shlr2	r0
+lshrsi3_4:
+	shlr2	r0
+lshrsi3_2:
+	rts
+	shlr2	r0
+
+lshrsi3_7:
+	shlr2	r0
+lshrsi3_5:
+	shlr2	r0
+lshrsi3_3:
+	shlr2	r0
+lshrsi3_1:
+	rts
+	shlr	r0
+
+lshrsi3_14:
+	shlr2	r0
+lshrsi3_12:
+	shlr2	r0
+lshrsi3_10:
+	shlr2	r0
+lshrsi3_8:
+	rts
+	shlr8	r0
+
+lshrsi3_15:
+	shlr2	r0
+lshrsi3_13:
+	shlr2	r0
+lshrsi3_11:
+	shlr2	r0
+lshrsi3_9:
+	shlr8	r0
+	rts
+	shlr	r0
+
+lshrsi3_22:
+	shlr2	r0
+lshrsi3_20:
+	shlr2	r0
+lshrsi3_18:
+	shlr2	r0
+lshrsi3_16:
+	rts
+	shlr16	r0
+
+lshrsi3_23:
+	shlr2	r0
+lshrsi3_21:
+	shlr2	r0
+lshrsi3_19:
+	shlr2	r0
+lshrsi3_17:
+	shlr16	r0
+	rts
+	shlr	r0
+
+lshrsi3_30:
+	shlr2	r0
+lshrsi3_28:
+	shlr2	r0
+lshrsi3_26:
+	shlr2	r0
+lshrsi3_24:
+	shlr16	r0
+	rts
+	shlr8	r0
+
+lshrsi3_31:
+	shlr2	r0
+lshrsi3_29:
+	shlr2	r0
+lshrsi3_27:
+	shlr2	r0
+lshrsi3_25:
+	shlr16	r0
+	shlr8	r0
+	rts
+	shlr	r0
+
+lshrsi3_0:
+	rts
+	nop
diff --git a/arch/sh/lib/mcount.S b/arch/sh/lib/mcount.S
new file mode 100644
index 000000000000..110fbfe1831f
--- /dev/null
+++ b/arch/sh/lib/mcount.S
@@ -0,0 +1,90 @@
+/*
+ * arch/sh/lib/mcount.S
+ *
+ *  Copyright (C) 2008  Paul Mundt
+ *  Copyright (C) 2008  Matt Fleming
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ */
+#include <asm/ftrace.h>
+
+#define MCOUNT_ENTER()		\
+	mov.l	r4, @-r15;	\
+	mov.l	r5, @-r15;	\
+	mov.l	r6, @-r15;	\
+	mov.l	r7, @-r15;	\
+	sts.l	pr, @-r15;	\
+				\
+	mov.l	@(20,r15),r4;	\
+	sts	pr, r5
+
+#define MCOUNT_LEAVE()		\
+	lds.l	@r15+, pr;	\
+	mov.l	@r15+, r7;	\
+	mov.l	@r15+, r6;	\
+	mov.l	@r15+, r5;	\
+	rts;			\
+	 mov.l	@r15+, r4
+
+	.align 2
+	.globl	_mcount
+	.type	_mcount,@function
+	.globl	mcount
+	.type	mcount,@function
+_mcount:
+mcount:
+	MCOUNT_ENTER()
+
+#ifdef CONFIG_DYNAMIC_FTRACE
+	.globl	mcount_call
+mcount_call:
+	mov.l	.Lftrace_stub, r6
+#else
+	mov.l	.Lftrace_trace_function, r6
+	mov.l	ftrace_stub, r7
+	cmp/eq	r6, r7
+	bt	skip_trace
+	mov.l	@r6, r6
+#endif
+
+	jsr	@r6
+	 nop
+
+skip_trace:
+	MCOUNT_LEAVE()
+
+	.align 2
+.Lftrace_trace_function:
+	.long	ftrace_trace_function
+
+#ifdef CONFIG_DYNAMIC_FTRACE
+	.globl ftrace_caller
+ftrace_caller:
+	MCOUNT_ENTER()
+
+	.globl ftrace_call
+ftrace_call:
+	mov.l	.Lftrace_stub, r6
+	jsr	@r6
+	 nop
+
+	MCOUNT_LEAVE()
+#endif /* CONFIG_DYNAMIC_FTRACE */
+
+/*
+ * NOTE: From here on the locations of the .Lftrace_stub label and
+ * ftrace_stub itself are fixed. Adding additional data here will skew
+ * the displacement for the memory table and break the block replacement.
+ * Place new labels either after the ftrace_stub body, or before
+ * ftrace_caller. You have been warned.
+ */
+	.align 2
+.Lftrace_stub:
+	.long	ftrace_stub
+
+	.globl	ftrace_stub
+ftrace_stub:
+	rts
+	 nop
diff --git a/arch/sh/lib/movmem.S b/arch/sh/lib/movmem.S
new file mode 100644
index 000000000000..62075f6bc67c
--- /dev/null
+++ b/arch/sh/lib/movmem.S
@@ -0,0 +1,238 @@
+/* Copyright (C) 1994, 1995, 1997, 1998, 1999, 2000, 2001, 2002, 2003,
+   2004, 2005, 2006
+   Free Software Foundation, Inc.
+
+This file is free software; you can redistribute it and/or modify it
+under the terms of the GNU General Public License as published by the
+Free Software Foundation; either version 2, or (at your option) any
+later version.
+
+In addition to the permissions in the GNU General Public License, the
+Free Software Foundation gives you unlimited permission to link the
+compiled version of this file into combinations with other programs,
+and to distribute those combinations without any restriction coming
+from the use of this file.  (The General Public License restrictions
+do apply in other respects; for example, they cover modification of
+the file, and distribution when not linked into a combine
+executable.)
+
+This file is distributed in the hope that it will be useful, but
+WITHOUT ANY WARRANTY; without even the implied warranty of
+MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+General Public License for more details.
+
+You should have received a copy of the GNU General Public License
+along with this program; see the file COPYING.  If not, write to
+the Free Software Foundation, 51 Franklin Street, Fifth Floor,
+Boston, MA 02110-1301, USA.  */
+
+!! libgcc routines for the Renesas / SuperH SH CPUs.
+!! Contributed by Steve Chamberlain.
+!! sac@cygnus.com
+
+!! ashiftrt_r4_x, ___ashrsi3, ___ashlsi3, ___lshrsi3 routines
+!! recoded in assembly by Toshiyasu Morita
+!! tm@netcom.com
+
+/* SH2 optimizations for ___ashrsi3, ___ashlsi3, ___lshrsi3 and
+   ELF local label prefixes by J"orn Rennecke
+   amylaar@cygnus.com  */
+
+	.text
+	.balign	4
+	.global	__movmem
+	.global __movstr
+	.set __movstr, __movmem	
+	/* This would be a lot simpler if r6 contained the byte count
+	   minus 64, and we wouldn't be called here for a byte count of 64.  */
+__movmem:
+	sts.l	pr,@-r15
+	shll2	r6
+	bsr	__movmemSI52+2
+	mov.l	@(48,r5),r0
+	.balign	4
+movmem_loop: /* Reached with rts */
+	mov.l	@(60,r5),r0
+	add	#-64,r6
+	mov.l	r0,@(60,r4)
+	tst	r6,r6
+	mov.l	@(56,r5),r0
+	bt	movmem_done
+	mov.l	r0,@(56,r4)
+	cmp/pl	r6
+	mov.l	@(52,r5),r0
+	add	#64,r5
+	mov.l	r0,@(52,r4)
+	add	#64,r4
+	bt	__movmemSI52
+! done all the large groups, do the remainder
+! jump to movmem+
+	mova	__movmemSI4+4,r0
+	add	r6,r0
+	jmp	@r0
+movmem_done: ! share slot insn, works out aligned.
+	lds.l	@r15+,pr
+	mov.l	r0,@(56,r4)
+	mov.l	@(52,r5),r0
+	rts
+	mov.l	r0,@(52,r4)
+	.balign	4
+
+	.global	__movmemSI64
+	.global __movstrSI64
+	.set	__movstrSI64, __movmemSI64
+__movmemSI64:
+	mov.l	@(60,r5),r0
+	mov.l	r0,@(60,r4)
+	.global	__movmemSI60
+	.global __movstrSI60
+	.set	__movstrSI60, __movmemSI60
+__movmemSI60:
+	mov.l	@(56,r5),r0
+	mov.l	r0,@(56,r4)
+	.global	__movmemSI56
+	.global __movstrSI56
+	.set	__movstrSI56, __movmemSI56
+__movmemSI56:
+	mov.l	@(52,r5),r0
+	mov.l	r0,@(52,r4)
+	.global	__movmemSI52
+	.global __movstrSI52
+	.set	__movstrSI52, __movmemSI52
+__movmemSI52:
+	mov.l	@(48,r5),r0
+	mov.l	r0,@(48,r4)
+	.global	__movmemSI48
+	.global	__movstrSI48
+	.set	__movstrSI48, __movmemSI48
+__movmemSI48:
+	mov.l	@(44,r5),r0
+	mov.l	r0,@(44,r4)
+	.global	__movmemSI44
+	.global	__movstrSI44
+	.set	__movstrSI44, __movmemSI44
+__movmemSI44:
+	mov.l	@(40,r5),r0
+	mov.l	r0,@(40,r4)
+	.global	__movmemSI40
+	.global __movstrSI40
+	.set	__movstrSI40, __movmemSI40
+__movmemSI40:
+	mov.l	@(36,r5),r0
+	mov.l	r0,@(36,r4)
+	.global	__movmemSI36
+	.global	__movstrSI36
+	.set	__movstrSI36, __movmemSI36
+__movmemSI36:
+	mov.l	@(32,r5),r0
+	mov.l	r0,@(32,r4)
+	.global	__movmemSI32
+	.global	__movstrSI32
+	.set	__movstrSI32, __movmemSI32
+__movmemSI32:
+	mov.l	@(28,r5),r0
+	mov.l	r0,@(28,r4)
+	.global	__movmemSI28
+	.global	__movstrSI28
+	.set	__movstrSI28, __movmemSI28
+__movmemSI28:
+	mov.l	@(24,r5),r0
+	mov.l	r0,@(24,r4)
+	.global	__movmemSI24
+	.global	__movstrSI24
+	.set	__movstrSI24, __movmemSI24
+__movmemSI24:
+	mov.l	@(20,r5),r0
+	mov.l	r0,@(20,r4)
+	.global	__movmemSI20
+	.global	__movstrSI20
+	.set	__movstrSI20, __movmemSI20
+__movmemSI20:
+	mov.l	@(16,r5),r0
+	mov.l	r0,@(16,r4)
+	.global	__movmemSI16
+	.global	__movstrSI16
+	.set	__movstrSI16, __movmemSI16
+__movmemSI16:
+	mov.l	@(12,r5),r0
+	mov.l	r0,@(12,r4)
+	.global	__movmemSI12
+	.global	__movstrSI12
+	.set	__movstrSI12, __movmemSI12
+__movmemSI12:
+	mov.l	@(8,r5),r0
+	mov.l	r0,@(8,r4)
+	.global	__movmemSI8
+	.global	__movstrSI8
+	.set	__movstrSI8, __movmemSI8
+__movmemSI8:
+	mov.l	@(4,r5),r0
+	mov.l	r0,@(4,r4)
+	.global	__movmemSI4
+	.global	__movstrSI4
+	.set	__movstrSI4, __movmemSI4
+__movmemSI4:
+	mov.l	@(0,r5),r0
+	rts
+	mov.l	r0,@(0,r4)
+
+	.global	__movmem_i4_even
+	.global	__movstr_i4_even
+	.set	__movstr_i4_even, __movmem_i4_even
+
+	.global	__movmem_i4_odd
+	.global	__movstr_i4_odd
+	.set	__movstr_i4_odd, __movmem_i4_odd
+
+	.global	__movmemSI12_i4
+	.global	__movstrSI12_i4
+	.set	__movstrSI12_i4, __movmemSI12_i4
+
+	.p2align	5
+L_movmem_2mod4_end:
+	mov.l	r0,@(16,r4)
+	rts
+	mov.l	r1,@(20,r4)
+
+	.p2align	2
+
+__movmem_i4_even:
+	mov.l	@r5+,r0
+	bra	L_movmem_start_even
+	mov.l	@r5+,r1
+
+__movmem_i4_odd:
+	mov.l	@r5+,r1
+	add	#-4,r4
+	mov.l	@r5+,r2
+	mov.l	@r5+,r3
+	mov.l	r1,@(4,r4)
+	mov.l	r2,@(8,r4)
+
+L_movmem_loop:
+	mov.l	r3,@(12,r4)
+	dt	r6
+	mov.l	@r5+,r0
+	bt/s	L_movmem_2mod4_end
+	mov.l	@r5+,r1
+	add	#16,r4
+L_movmem_start_even:
+	mov.l	@r5+,r2
+	mov.l	@r5+,r3
+	mov.l	r0,@r4
+	dt	r6
+	mov.l	r1,@(4,r4)
+	bf/s	L_movmem_loop
+	mov.l	r2,@(8,r4)
+	rts
+	mov.l	r3,@(12,r4)
+
+	.p2align	4
+__movmemSI12_i4:
+	mov.l	@r5,r0
+	mov.l	@(4,r5),r1
+	mov.l	@(8,r5),r2
+	mov.l	r0,@r4
+	mov.l	r1,@(4,r4)
+	rts
+	mov.l	r2,@(8,r4)
diff --git a/arch/sh/lib/udiv_qrnnd.S b/arch/sh/lib/udiv_qrnnd.S
new file mode 100644
index 000000000000..32b9a36de943
--- /dev/null
+++ b/arch/sh/lib/udiv_qrnnd.S
@@ -0,0 +1,81 @@
+/* Copyright (C) 1994, 1995, 1997, 1998, 1999, 2000, 2001, 2002, 2003,
+   2004, 2005, 2006
+   Free Software Foundation, Inc.
+
+This file is free software; you can redistribute it and/or modify it
+under the terms of the GNU General Public License as published by the
+Free Software Foundation; either version 2, or (at your option) any
+later version.
+
+In addition to the permissions in the GNU General Public License, the
+Free Software Foundation gives you unlimited permission to link the
+compiled version of this file into combinations with other programs,
+and to distribute those combinations without any restriction coming
+from the use of this file.  (The General Public License restrictions
+do apply in other respects; for example, they cover modification of
+the file, and distribution when not linked into a combine
+executable.)
+
+This file is distributed in the hope that it will be useful, but
+WITHOUT ANY WARRANTY; without even the implied warranty of
+MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+General Public License for more details.
+
+You should have received a copy of the GNU General Public License
+along with this program; see the file COPYING.  If not, write to
+the Free Software Foundation, 51 Franklin Street, Fifth Floor,
+Boston, MA 02110-1301, USA.  */
+
+!! libgcc routines for the Renesas / SuperH SH CPUs.
+!! Contributed by Steve Chamberlain.
+!! sac@cygnus.com
+
+!! ashiftrt_r4_x, ___ashrsi3, ___ashlsi3, ___lshrsi3 routines
+!! recoded in assembly by Toshiyasu Morita
+!! tm@netcom.com
+
+/* SH2 optimizations for ___ashrsi3, ___ashlsi3, ___lshrsi3 and
+   ELF local label prefixes by J"orn Rennecke
+   amylaar@cygnus.com  */
+
+	/* r0: rn r1: qn */ /* r0: n1 r4: n0 r5: d r6: d1 */ /* r2: __m */
+	/* n1 < d, but n1 might be larger than d1.  */
+	.global __udiv_qrnnd_16
+	.balign 8
+__udiv_qrnnd_16:
+	div0u
+	cmp/hi r6,r0
+	bt .Lots
+	.rept 16
+	div1 r6,r0 
+	.endr
+	extu.w r0,r1
+	bt 0f
+	add r6,r0
+0:	rotcl r1
+	mulu.w r1,r5
+	xtrct r4,r0
+	swap.w r0,r0
+	sts macl,r2
+	cmp/hs r2,r0
+	sub r2,r0
+	bt 0f
+	addc r5,r0
+	add #-1,r1
+	bt 0f
+1:	add #-1,r1
+	rts
+	add r5,r0
+	.balign 8
+.Lots:
+	sub r5,r0
+	swap.w r4,r1
+	xtrct r0,r1
+	clrt
+	mov r1,r0
+	addc r5,r0
+	mov #-1,r1
+	bf/s 1b
+	 shlr16 r1
+0:	rts
+	 nop
diff --git a/arch/sh/lib/udivsi3-Os.S b/arch/sh/lib/udivsi3-Os.S
new file mode 100644
index 000000000000..110c5ea769e0
--- /dev/null
+++ b/arch/sh/lib/udivsi3-Os.S
@@ -0,0 +1,151 @@
+/* Copyright (C) 2006 Free Software Foundation, Inc.
+
+This file is free software; you can redistribute it and/or modify it
+under the terms of the GNU General Public License as published by the
+Free Software Foundation; either version 2, or (at your option) any
+later version.
+
+In addition to the permissions in the GNU General Public License, the
+Free Software Foundation gives you unlimited permission to link the
+compiled version of this file into combinations with other programs,
+and to distribute those combinations without any restriction coming
+from the use of this file.  (The General Public License restrictions
+do apply in other respects; for example, they cover modification of
+the file, and distribution when not linked into a combine
+executable.)
+
+This file is distributed in the hope that it will be useful, but
+WITHOUT ANY WARRANTY; without even the implied warranty of
+MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+General Public License for more details.
+
+You should have received a copy of the GNU General Public License
+along with this program; see the file COPYING.  If not, write to
+the Free Software Foundation, 51 Franklin Street, Fifth Floor,
+Boston, MA 02110-1301, USA.  */
+
+/* Moderately Space-optimized libgcc routines for the Renesas SH /
+   STMicroelectronics ST40 CPUs.
+   Contributed by J"orn Rennecke joern.rennecke@st.com.  */
+
+/* Size: 186 bytes jointly for udivsi3_i4i and sdivsi3_i4i
+   sh4-200 run times:
+   udiv small divisor: 55 cycles
+   udiv large divisor: 52 cycles
+   sdiv small divisor, positive result: 59 cycles
+   sdiv large divisor, positive result: 56 cycles
+   sdiv small divisor, negative result: 65 cycles (*)
+   sdiv large divisor, negative result: 62 cycles (*)
+   (*): r2 is restored in the rts delay slot and has a lingering latency
+        of two more cycles.  */
+	.balign 4
+	.global	__udivsi3_i4i
+	.global	__udivsi3_i4
+	.global __udivsi3
+	.set	__udivsi3_i4, __udivsi3_i4i
+	.set	__udivsi3, __udivsi3_i4i
+	.type	__udivsi3_i4i, @function
+	.type	__sdivsi3_i4i, @function
+__udivsi3_i4i:
+	sts pr,r1
+	mov.l r4,@-r15
+	extu.w r5,r0
+	cmp/eq r5,r0
+	swap.w r4,r0
+	shlr16 r4
+	bf/s large_divisor
+	div0u
+	mov.l r5,@-r15
+	shll16 r5
+sdiv_small_divisor:
+	div1 r5,r4
+	bsr div6
+	div1 r5,r4
+	div1 r5,r4
+	bsr div6
+	div1 r5,r4
+	xtrct r4,r0
+	xtrct r0,r4
+	bsr div7
+	swap.w r4,r4
+	div1 r5,r4
+	bsr div7
+	div1 r5,r4
+	xtrct r4,r0
+	mov.l @r15+,r5
+	swap.w r0,r0
+	mov.l @r15+,r4
+	jmp @r1
+	rotcl r0
+div7:
+	div1 r5,r4
+div6:
+	            div1 r5,r4; div1 r5,r4; div1 r5,r4
+	div1 r5,r4; div1 r5,r4; rts;        div1 r5,r4
+
+divx3:
+	rotcl r0
+	div1 r5,r4
+	rotcl r0
+	div1 r5,r4
+	rotcl r0
+	rts
+	div1 r5,r4
+
+large_divisor:
+	mov.l r5,@-r15
+sdiv_large_divisor:
+	xor r4,r0
+	.rept 4
+	rotcl r0
+	bsr divx3
+	div1 r5,r4
+	.endr
+	mov.l @r15+,r5
+	mov.l @r15+,r4
+	jmp @r1
+	rotcl r0
+
+	.global	__sdivsi3_i4i
+	.global __sdivsi3_i4
+	.global __sdivsi3
+	.set	__sdivsi3_i4, __sdivsi3_i4i
+	.set	__sdivsi3, __sdivsi3_i4i
+__sdivsi3_i4i:
+	mov.l r4,@-r15
+	cmp/pz r5
+	mov.l r5,@-r15
+	bt/s pos_divisor
+	cmp/pz r4
+	neg r5,r5
+	extu.w r5,r0
+	bt/s neg_result
+	cmp/eq r5,r0
+	neg r4,r4
+pos_result:
+	swap.w r4,r0
+	bra sdiv_check_divisor
+	sts pr,r1
+pos_divisor:
+	extu.w r5,r0
+	bt/s pos_result
+	cmp/eq r5,r0
+	neg r4,r4
+neg_result:
+	mova negate_result,r0
+	;
+	mov r0,r1
+	swap.w r4,r0
+	lds r2,macl
+	sts pr,r2
+sdiv_check_divisor:
+	shlr16 r4
+	bf/s sdiv_large_divisor
+	div0u
+	bra sdiv_small_divisor
+	shll16 r5
+	.balign 4
+negate_result:
+	neg r0,r0
+	jmp @r2
+	sts macl,r2
diff --git a/arch/sh/lib/udivsi3.S b/arch/sh/lib/udivsi3.S
new file mode 100644
index 000000000000..388e15d75193
--- /dev/null
+++ b/arch/sh/lib/udivsi3.S
@@ -0,0 +1,668 @@
+/* Copyright (C) 1994, 1995, 1997, 1998, 1999, 2000, 2001, 2002, 2003,
+   2004, 2005, 2006
+   Free Software Foundation, Inc.
+
+This file is free software; you can redistribute it and/or modify it
+under the terms of the GNU General Public License as published by the
+Free Software Foundation; either version 2, or (at your option) any
+later version.
+
+In addition to the permissions in the GNU General Public License, the
+Free Software Foundation gives you unlimited permission to link the
+compiled version of this file into combinations with other programs,
+and to distribute those combinations without any restriction coming
+from the use of this file.  (The General Public License restrictions
+do apply in other respects; for example, they cover modification of
+the file, and distribution when not linked into a combine
+executable.)
+
+This file is distributed in the hope that it will be useful, but
+WITHOUT ANY WARRANTY; without even the implied warranty of
+MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+General Public License for more details.
+
+You should have received a copy of the GNU General Public License
+along with this program; see the file COPYING.  If not, write to
+the Free Software Foundation, 51 Franklin Street, Fifth Floor,
+Boston, MA 02110-1301, USA.  */
+
+!! libgcc routines for the Renesas / SuperH SH CPUs.
+!! Contributed by Steve Chamberlain.
+!! sac@cygnus.com
+
+!! ashiftrt_r4_x, ___ashrsi3, ___ashlsi3, ___lshrsi3 routines
+!! recoded in assembly by Toshiyasu Morita
+!! tm@netcom.com
+
+/* SH2 optimizations for ___ashrsi3, ___ashlsi3, ___lshrsi3 and
+   ELF local label prefixes by J"orn Rennecke
+   amylaar@cygnus.com  */
+
+/* This code used shld, thus is not suitable for SH1 / SH2.  */
+
+/* Signed / unsigned division without use of FPU, optimized for SH4.
+   Uses a lookup table for divisors in the range -128 .. +128, and
+   div1 with case distinction for larger divisors in three more ranges.
+   The code is lumped together with the table to allow the use of mova.  */
+#ifdef CONFIG_CPU_LITTLE_ENDIAN
+#define L_LSB 0
+#define L_LSWMSB 1
+#define L_MSWLSB 2
+#else
+#define L_LSB 3
+#define L_LSWMSB 2
+#define L_MSWLSB 1
+#endif
+
+	.balign 4
+	.global	__udivsi3_i4i
+	.global	__udivsi3_i4
+	.global	__udivsi3
+	.set	__udivsi3_i4, __udivsi3_i4i
+	.set	__udivsi3, __udivsi3_i4i
+	.type	__udivsi3_i4i, @function
+__udivsi3_i4i:
+	mov.w c128_w, r1
+	div0u
+	mov r4,r0
+	shlr8 r0
+	cmp/hi r1,r5
+	extu.w r5,r1
+	bf udiv_le128
+	cmp/eq r5,r1
+	bf udiv_ge64k
+	shlr r0
+	mov r5,r1
+	shll16 r5
+	mov.l r4,@-r15
+	div1 r5,r0
+	mov.l r1,@-r15
+	div1 r5,r0
+	div1 r5,r0
+	bra udiv_25
+	div1 r5,r0
+
+div_le128:
+	mova div_table_ix,r0
+	bra div_le128_2
+	mov.b @(r0,r5),r1
+udiv_le128:
+	mov.l r4,@-r15
+	mova div_table_ix,r0
+	mov.b @(r0,r5),r1
+	mov.l r5,@-r15
+div_le128_2:
+	mova div_table_inv,r0
+	mov.l @(r0,r1),r1
+	mov r5,r0
+	tst #0xfe,r0
+	mova div_table_clz,r0
+	dmulu.l r1,r4
+	mov.b @(r0,r5),r1
+	bt/s div_by_1
+	mov r4,r0
+	mov.l @r15+,r5
+	sts mach,r0
+	/* clrt */
+	addc r4,r0
+	mov.l @r15+,r4
+	rotcr r0
+	rts
+	shld r1,r0
+
+div_by_1_neg:
+	neg r4,r0
+div_by_1:
+	mov.l @r15+,r5
+	rts
+	mov.l @r15+,r4
+
+div_ge64k:
+	bt/s div_r8
+	div0u
+	shll8 r5
+	bra div_ge64k_2
+	div1 r5,r0
+udiv_ge64k:
+	cmp/hi r0,r5
+	mov r5,r1
+	bt udiv_r8
+	shll8 r5
+	mov.l r4,@-r15
+	div1 r5,r0
+	mov.l r1,@-r15
+div_ge64k_2:
+	div1 r5,r0
+	mov.l zero_l,r1
+	.rept 4
+	div1 r5,r0
+	.endr
+	mov.l r1,@-r15
+	div1 r5,r0
+	mov.w m256_w,r1
+	div1 r5,r0
+	mov.b r0,@(L_LSWMSB,r15)
+	xor r4,r0
+	and r1,r0
+	bra div_ge64k_end
+	xor r4,r0
+	
+div_r8:
+	shll16 r4
+	bra div_r8_2
+	shll8 r4
+udiv_r8:
+	mov.l r4,@-r15
+	shll16 r4
+	clrt
+	shll8 r4
+	mov.l r5,@-r15
+div_r8_2:
+	rotcl r4
+	mov r0,r1
+	div1 r5,r1
+	mov r4,r0
+	rotcl r0
+	mov r5,r4
+	div1 r5,r1
+	.rept 5
+	rotcl r0; div1 r5,r1
+	.endr
+	rotcl r0
+	mov.l @r15+,r5
+	div1 r4,r1
+	mov.l @r15+,r4
+	rts
+	rotcl r0
+
+	.global	__sdivsi3_i4i
+	.global __sdivsi3_i4
+	.global	__sdivsi3
+	.set	__sdivsi3_i4, __sdivsi3_i4i
+	.set	__sdivsi3, __sdivsi3_i4i
+	.type	__sdivsi3_i4i, @function
+	/* This is link-compatible with a __sdivsi3 call,
+	   but we effectively clobber only r1.  */
+__sdivsi3_i4i:
+	mov.l r4,@-r15
+	cmp/pz r5
+	mov.w c128_w, r1
+	bt/s pos_divisor
+	cmp/pz r4
+	mov.l r5,@-r15
+	neg r5,r5
+	bt/s neg_result
+	cmp/hi r1,r5
+	neg r4,r4
+pos_result:
+	extu.w r5,r0
+	bf div_le128
+	cmp/eq r5,r0
+	mov r4,r0
+	shlr8 r0
+	bf/s div_ge64k
+	cmp/hi r0,r5
+	div0u
+	shll16 r5
+	div1 r5,r0
+	div1 r5,r0
+	div1 r5,r0
+udiv_25:
+	mov.l zero_l,r1
+	div1 r5,r0
+	div1 r5,r0
+	mov.l r1,@-r15
+	.rept 3
+	div1 r5,r0
+	.endr
+	mov.b r0,@(L_MSWLSB,r15)
+	xtrct r4,r0
+	swap.w r0,r0
+	.rept 8
+	div1 r5,r0
+	.endr
+	mov.b r0,@(L_LSWMSB,r15)
+div_ge64k_end:
+	.rept 8
+	div1 r5,r0
+	.endr
+	mov.l @r15+,r4 ! zero-extension and swap using LS unit.
+	extu.b r0,r0
+	mov.l @r15+,r5
+	or r4,r0
+	mov.l @r15+,r4
+	rts
+	rotcl r0
+
+div_le128_neg:
+	tst #0xfe,r0
+	mova div_table_ix,r0
+	mov.b @(r0,r5),r1
+	mova div_table_inv,r0
+	bt/s div_by_1_neg
+	mov.l @(r0,r1),r1
+	mova div_table_clz,r0
+	dmulu.l r1,r4
+	mov.b @(r0,r5),r1
+	mov.l @r15+,r5
+	sts mach,r0
+	/* clrt */
+	addc r4,r0
+	mov.l @r15+,r4
+	rotcr r0
+	shld r1,r0
+	rts
+	neg r0,r0
+
+pos_divisor:
+	mov.l r5,@-r15
+	bt/s pos_result
+	cmp/hi r1,r5
+	neg r4,r4
+neg_result:
+	extu.w r5,r0
+	bf div_le128_neg
+	cmp/eq r5,r0
+	mov r4,r0
+	shlr8 r0
+	bf/s div_ge64k_neg
+	cmp/hi r0,r5
+	div0u
+	mov.l zero_l,r1
+	shll16 r5
+	div1 r5,r0
+	mov.l r1,@-r15
+	.rept 7
+	div1 r5,r0
+	.endr
+	mov.b r0,@(L_MSWLSB,r15)
+	xtrct r4,r0
+	swap.w r0,r0
+	.rept 8
+	div1 r5,r0
+	.endr
+	mov.b r0,@(L_LSWMSB,r15)
+div_ge64k_neg_end:
+	.rept 8
+	div1 r5,r0
+	.endr
+	mov.l @r15+,r4 ! zero-extension and swap using LS unit.
+	extu.b r0,r1
+	mov.l @r15+,r5
+	or r4,r1
+div_r8_neg_end:
+	mov.l @r15+,r4
+	rotcl r1
+	rts
+	neg r1,r0
+
+div_ge64k_neg:
+	bt/s div_r8_neg
+	div0u
+	shll8 r5
+	mov.l zero_l,r1
+	.rept 6
+	div1 r5,r0
+	.endr
+	mov.l r1,@-r15
+	div1 r5,r0
+	mov.w m256_w,r1
+	div1 r5,r0
+	mov.b r0,@(L_LSWMSB,r15)
+	xor r4,r0
+	and r1,r0
+	bra div_ge64k_neg_end
+	xor r4,r0
+
+c128_w:
+	.word 128
+
+div_r8_neg:
+	clrt
+	shll16 r4
+	mov r4,r1
+	shll8 r1
+	mov r5,r4
+	.rept 7
+	rotcl r1; div1 r5,r0
+	.endr
+	mov.l @r15+,r5
+	rotcl r1
+	bra div_r8_neg_end
+	div1 r4,r0
+
+m256_w:
+	.word 0xff00
+/* This table has been generated by divtab-sh4.c.  */
+	.balign 4
+div_table_clz:
+	.byte	0
+	.byte	1
+	.byte	0
+	.byte	-1
+	.byte	-1
+	.byte	-2
+	.byte	-2
+	.byte	-2
+	.byte	-2
+	.byte	-3
+	.byte	-3
+	.byte	-3
+	.byte	-3
+	.byte	-3
+	.byte	-3
+	.byte	-3
+	.byte	-3
+	.byte	-4
+	.byte	-4
+	.byte	-4
+	.byte	-4
+	.byte	-4
+	.byte	-4
+	.byte	-4
+	.byte	-4
+	.byte	-4
+	.byte	-4
+	.byte	-4
+	.byte	-4
+	.byte	-4
+	.byte	-4
+	.byte	-4
+	.byte	-4
+	.byte	-5
+	.byte	-5
+	.byte	-5
+	.byte	-5
+	.byte	-5
+	.byte	-5
+	.byte	-5
+	.byte	-5
+	.byte	-5
+	.byte	-5
+	.byte	-5
+	.byte	-5
+	.byte	-5
+	.byte	-5
+	.byte	-5
+	.byte	-5
+	.byte	-5
+	.byte	-5
+	.byte	-5
+	.byte	-5
+	.byte	-5
+	.byte	-5
+	.byte	-5
+	.byte	-5
+	.byte	-5
+	.byte	-5
+	.byte	-5
+	.byte	-5
+	.byte	-5
+	.byte	-5
+	.byte	-5
+	.byte	-5
+	.byte	-6
+	.byte	-6
+	.byte	-6
+	.byte	-6
+	.byte	-6
+	.byte	-6
+	.byte	-6
+	.byte	-6
+	.byte	-6
+	.byte	-6
+	.byte	-6
+	.byte	-6
+	.byte	-6
+	.byte	-6
+	.byte	-6
+	.byte	-6
+	.byte	-6
+	.byte	-6
+	.byte	-6
+	.byte	-6
+	.byte	-6
+	.byte	-6
+	.byte	-6
+	.byte	-6
+	.byte	-6
+	.byte	-6
+	.byte	-6
+	.byte	-6
+	.byte	-6
+	.byte	-6
+	.byte	-6
+	.byte	-6
+	.byte	-6
+	.byte	-6
+	.byte	-6
+	.byte	-6
+	.byte	-6
+	.byte	-6
+	.byte	-6
+	.byte	-6
+	.byte	-6
+	.byte	-6
+	.byte	-6
+	.byte	-6
+	.byte	-6
+	.byte	-6
+	.byte	-6
+	.byte	-6
+	.byte	-6
+	.byte	-6
+	.byte	-6
+	.byte	-6
+	.byte	-6
+	.byte	-6
+	.byte	-6
+	.byte	-6
+	.byte	-6
+	.byte	-6
+	.byte	-6
+	.byte	-6
+	.byte	-6
+	.byte	-6
+	.byte	-6
+/* Lookup table translating positive divisor to index into table of
+   normalized inverse.  N.B. the '0' entry is also the last entry of the
+ previous table, and causes an unaligned access for division by zero.  */
+div_table_ix:
+	.byte	-6
+	.byte	-128
+	.byte	-128
+	.byte	0
+	.byte	-128
+	.byte	-64
+	.byte	0
+	.byte	64
+	.byte	-128
+	.byte	-96
+	.byte	-64
+	.byte	-32
+	.byte	0
+	.byte	32
+	.byte	64
+	.byte	96
+	.byte	-128
+	.byte	-112
+	.byte	-96
+	.byte	-80
+	.byte	-64
+	.byte	-48
+	.byte	-32
+	.byte	-16
+	.byte	0
+	.byte	16
+	.byte	32
+	.byte	48
+	.byte	64
+	.byte	80
+	.byte	96
+	.byte	112
+	.byte	-128
+	.byte	-120
+	.byte	-112
+	.byte	-104
+	.byte	-96
+	.byte	-88
+	.byte	-80
+	.byte	-72
+	.byte	-64
+	.byte	-56
+	.byte	-48
+	.byte	-40
+	.byte	-32
+	.byte	-24
+	.byte	-16
+	.byte	-8
+	.byte	0
+	.byte	8
+	.byte	16
+	.byte	24
+	.byte	32
+	.byte	40
+	.byte	48
+	.byte	56
+	.byte	64
+	.byte	72
+	.byte	80
+	.byte	88
+	.byte	96
+	.byte	104
+	.byte	112
+	.byte	120
+	.byte	-128
+	.byte	-124
+	.byte	-120
+	.byte	-116
+	.byte	-112
+	.byte	-108
+	.byte	-104
+	.byte	-100
+	.byte	-96
+	.byte	-92
+	.byte	-88
+	.byte	-84
+	.byte	-80
+	.byte	-76
+	.byte	-72
+	.byte	-68
+	.byte	-64
+	.byte	-60
+	.byte	-56
+	.byte	-52
+	.byte	-48
+	.byte	-44
+	.byte	-40
+	.byte	-36
+	.byte	-32
+	.byte	-28
+	.byte	-24
+	.byte	-20
+	.byte	-16
+	.byte	-12
+	.byte	-8
+	.byte	-4
+	.byte	0
+	.byte	4
+	.byte	8
+	.byte	12
+	.byte	16
+	.byte	20
+	.byte	24
+	.byte	28
+	.byte	32
+	.byte	36
+	.byte	40
+	.byte	44
+	.byte	48
+	.byte	52
+	.byte	56
+	.byte	60
+	.byte	64
+	.byte	68
+	.byte	72
+	.byte	76
+	.byte	80
+	.byte	84
+	.byte	88
+	.byte	92
+	.byte	96
+	.byte	100
+	.byte	104
+	.byte	108
+	.byte	112
+	.byte	116
+	.byte	120
+	.byte	124
+	.byte	-128
+/* 1/64 .. 1/127, normalized.  There is an implicit leading 1 in bit 32.  */
+	.balign 4
+zero_l:
+	.long	0x0
+	.long	0xF81F81F9
+	.long	0xF07C1F08
+	.long	0xE9131AC0
+	.long	0xE1E1E1E2
+	.long	0xDAE6076C
+	.long	0xD41D41D5
+	.long	0xCD856891
+	.long	0xC71C71C8
+	.long	0xC0E07039
+	.long	0xBACF914D
+	.long	0xB4E81B4F
+	.long	0xAF286BCB
+	.long	0xA98EF607
+	.long	0xA41A41A5
+	.long	0x9EC8E952
+	.long	0x9999999A
+	.long	0x948B0FCE
+	.long	0x8F9C18FA
+	.long	0x8ACB90F7
+	.long	0x86186187
+	.long	0x81818182
+	.long	0x7D05F418
+	.long	0x78A4C818
+	.long	0x745D1746
+	.long	0x702E05C1
+	.long	0x6C16C16D
+	.long	0x68168169
+	.long	0x642C8591
+	.long	0x60581606
+	.long	0x5C9882BA
+	.long	0x58ED2309
+div_table_inv:
+	.long	0x55555556
+	.long	0x51D07EAF
+	.long	0x4E5E0A73
+	.long	0x4AFD6A06
+	.long	0x47AE147B
+	.long	0x446F8657
+	.long	0x41414142
+	.long	0x3E22CBCF
+	.long	0x3B13B13C
+	.long	0x38138139
+	.long	0x3521CFB3
+	.long	0x323E34A3
+	.long	0x2F684BDB
+	.long	0x2C9FB4D9
+	.long	0x29E4129F
+	.long	0x27350B89
+	.long	0x24924925
+	.long	0x21FB7813
+	.long	0x1F7047DD
+	.long	0x1CF06ADB
+	.long	0x1A7B9612
+	.long	0x18118119
+	.long	0x15B1E5F8
+	.long	0x135C8114
+	.long	0x11111112
+	.long	0xECF56BF
+	.long	0xC9714FC
+	.long	0xA6810A7
+	.long	0x8421085
+	.long	0x624DD30
+	.long	0x4104105
+	.long	0x2040811
+	/* maximum error: 0.987342 scaled: 0.921875*/
diff --git a/arch/sh/mm/fault_32.c b/arch/sh/mm/fault_32.c
index 898d477e47c1..e58726892b5f 100644
--- a/arch/sh/mm/fault_32.c
+++ b/arch/sh/mm/fault_32.c
@@ -265,17 +265,6 @@ static inline int notify_page_fault(struct pt_regs *regs, int trap)
 	return ret;
 }
 
-#ifdef CONFIG_SH_STORE_QUEUES
-/*
- * This is a special case for the SH-4 store queues, as pages for this
- * space still need to be faulted in before it's possible to flush the
- * store queue cache for writeout to the remapped region.
- */
-#define P3_ADDR_MAX		(P4SEG_STORE_QUE + 0x04000000)
-#else
-#define P3_ADDR_MAX		P4SEG
-#endif
-
 /*
  * Called with interrupts disabled.
  */
diff --git a/arch/sh/mm/ioremap_32.c b/arch/sh/mm/ioremap_32.c
index 882a32ebc6b7..32946fba123e 100644
--- a/arch/sh/mm/ioremap_32.c
+++ b/arch/sh/mm/ioremap_32.c
@@ -116,9 +116,10 @@ EXPORT_SYMBOL(__ioremap);
 void __iounmap(void __iomem *addr)
 {
 	unsigned long vaddr = (unsigned long __force)addr;
+	unsigned long seg = PXSEG(vaddr);
 	struct vm_struct *p;
 
-	if (PXSEG(vaddr) < P3SEG || is_pci_memaddr(vaddr))
+	if (seg < P3SEG || seg >= P3_ADDR_MAX || is_pci_memaddr(vaddr))
 		return;
 
 #ifdef CONFIG_32BIT
diff --git a/arch/sh/mm/mmap.c b/arch/sh/mm/mmap.c
index 8837d511710a..931f4d003fa0 100644
--- a/arch/sh/mm/mmap.c
+++ b/arch/sh/mm/mmap.c
@@ -9,7 +9,101 @@
  */
 #include <linux/io.h>
 #include <linux/mm.h>
+#include <linux/mman.h>
+#include <linux/module.h>
 #include <asm/page.h>
+#include <asm/processor.h>
+
+#ifdef CONFIG_MMU
+unsigned long shm_align_mask = PAGE_SIZE - 1;	/* Sane caches */
+EXPORT_SYMBOL(shm_align_mask);
+
+/*
+ * To avoid cache aliases, we map the shared page with same color.
+ */
+#define COLOUR_ALIGN(addr, pgoff)				\
+	((((addr) + shm_align_mask) & ~shm_align_mask) +	\
+	 (((pgoff) << PAGE_SHIFT) & shm_align_mask))
+
+unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr,
+	unsigned long len, unsigned long pgoff, unsigned long flags)
+{
+	struct mm_struct *mm = current->mm;
+	struct vm_area_struct *vma;
+	unsigned long start_addr;
+	int do_colour_align;
+
+	if (flags & MAP_FIXED) {
+		/* We do not accept a shared mapping if it would violate
+		 * cache aliasing constraints.
+		 */
+		if ((flags & MAP_SHARED) && (addr & shm_align_mask))
+			return -EINVAL;
+		return addr;
+	}
+
+	if (unlikely(len > TASK_SIZE))
+		return -ENOMEM;
+
+	do_colour_align = 0;
+	if (filp || (flags & MAP_SHARED))
+		do_colour_align = 1;
+
+	if (addr) {
+		if (do_colour_align)
+			addr = COLOUR_ALIGN(addr, pgoff);
+		else
+			addr = PAGE_ALIGN(addr);
+
+		vma = find_vma(mm, addr);
+		if (TASK_SIZE - len >= addr &&
+		    (!vma || addr + len <= vma->vm_start))
+			return addr;
+	}
+
+	if (len > mm->cached_hole_size) {
+		start_addr = addr = mm->free_area_cache;
+	} else {
+	        mm->cached_hole_size = 0;
+		start_addr = addr = TASK_UNMAPPED_BASE;
+	}
+
+full_search:
+	if (do_colour_align)
+		addr = COLOUR_ALIGN(addr, pgoff);
+	else
+		addr = PAGE_ALIGN(mm->free_area_cache);
+
+	for (vma = find_vma(mm, addr); ; vma = vma->vm_next) {
+		/* At this point:  (!vma || addr < vma->vm_end). */
+		if (unlikely(TASK_SIZE - len < addr)) {
+			/*
+			 * Start a new search - just in case we missed
+			 * some holes.
+			 */
+			if (start_addr != TASK_UNMAPPED_BASE) {
+				start_addr = addr = TASK_UNMAPPED_BASE;
+				mm->cached_hole_size = 0;
+				goto full_search;
+			}
+			return -ENOMEM;
+		}
+		if (likely(!vma || addr + len <= vma->vm_start)) {
+			/*
+			 * Remember the place where we stopped the search:
+			 */
+			mm->free_area_cache = addr + len;
+			return addr;
+		}
+		if (addr + mm->cached_hole_size < vma->vm_start)
+		        mm->cached_hole_size = vma->vm_start - addr;
+
+		addr = vma->vm_end;
+		if (do_colour_align)
+			addr = COLOUR_ALIGN(addr, pgoff);
+	}
+}
+#endif /* CONFIG_MMU */
 
 /*
  * You really shouldn't be using read() or write() on /dev/mem.  This
diff --git a/arch/sh/tools/mach-types b/arch/sh/tools/mach-types
index d0c2928d1066..69a9aeedf6e3 100644
--- a/arch/sh/tools/mach-types
+++ b/arch/sh/tools/mach-types
@@ -46,6 +46,7 @@ R2D_1			RTS7751R2D_1
 CAYMAN			SH_CAYMAN
 SDK7780			SH_SDK7780
 MIGOR			SH_MIGOR
+RSK7201			SH_RSK7201
 RSK7203			SH_RSK7203
 AP325RXA		SH_AP325RXA
 SH7763RDP		SH_SH7763RDP
diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig
index e594559c8dba..c8c7738f2a32 100644
--- a/arch/sparc/Kconfig
+++ b/arch/sparc/Kconfig
@@ -4,21 +4,111 @@
 
 mainmenu "Linux/SPARC Kernel Configuration"
 
+config SPARC
+	bool
+	default y
+	select HAVE_IDE
+	select HAVE_OPROFILE
+	select HAVE_ARCH_KGDB if !SMP || SPARC64
+	select HAVE_ARCH_TRACEHOOK
+	select ARCH_WANT_OPTIONAL_GPIOLIB
+	select RTC_CLASS
+	select RTC_DRV_M48T59
+
+# Identify this as a Sparc32 build
+config SPARC32
+	bool
+	default y if ARCH = "sparc"
+	help
+	  SPARC is a family of RISC microprocessors designed and marketed by
+	  Sun Microsystems, incorporated.  They are very widely found in Sun
+	  workstations and clones. This port covers the original 32-bit SPARC;
+	  it is old and stable and usually considered one of the "big three"
+	  along with the Intel and Alpha ports.  The UltraLinux project
+	  maintains both the SPARC32 and SPARC64 ports; its web page is
+	  available at <http://www.ultralinux.org/>.
+
+config SPARC64
+	bool
+	default y if ARCH = "sparc64"
+	select HAVE_FUNCTION_TRACER
+	select HAVE_KRETPROBES
+	select HAVE_KPROBES
+	select HAVE_LMB
+	select USE_GENERIC_SMP_HELPERS if SMP
+	select RTC_DRV_CMOS
+	select RTC_DRV_BQ4802
+	select RTC_DRV_SUN4V
+	select RTC_DRV_STARFIRE
+
+config ARCH_DEFCONFIG
+	string
+	default "arch/sparc/configs/sparc32_defconfig" if SPARC32
+	default "arch/sparc/configs/sparc64_defconfig" if SPARC64
+
+
+
+config 64BIT
+	def_bool y if SPARC64
+
+config GENERIC_TIME
+	bool
+	default y if SPARC64
+
+config GENERIC_CMOS_UPDATE
+	bool
+	default y if SPARC64
+
+config GENERIC_CLOCKEVENTS
+	bool
+	default y if SPARC64
+
+config IOMMU_HELPER
+	bool
+	default y if SPARC64
+
+config QUICKLIST
+	bool
+	default y if SPARC64
+
+config STACKTRACE_SUPPORT
+	bool
+	default y if SPARC64
+
+config LOCKDEP_SUPPORT
+	bool
+	default y if SPARC64
+
+config HAVE_LATENCYTOP_SUPPORT
+	bool
+	default y if SPARC64
+
+config AUDIT_ARCH
+	bool
+	default y
+
+config HAVE_SETUP_PER_CPU_AREA
+	def_bool y if SPARC64
+
+config GENERIC_HARDIRQS_NO__DO_IRQ
+	bool
+	def_bool y if SPARC64
+
 config MMU
 	bool
 	default y
 
 config HIGHMEM
 	bool
-	default y
+	default y if SPARC32
 
 config ZONE_DMA
 	bool
-	default y
+	default y if SPARC32
 
 config GENERIC_ISA_DMA
 	bool
-	default y
+	default y if SPARC32
 
 config GENERIC_GPIO
 	bool
@@ -31,15 +121,11 @@ config ARCH_NO_VIRT_TO_BUS
 config OF
 	def_bool y
 
-config HZ
-	int
-	default 100
-
 source "init/Kconfig"
 
 source "kernel/Kconfig.freezer"
 
-menu "General machine setup"
+menu "Processor type and features"
 
 config SMP
 	bool "Symmetric multi-processing support (does not work on sun4/sun4c)"
@@ -64,82 +150,269 @@ config SMP
 	  If you don't know what to do here, say N.
 
 config NR_CPUS
-	int "Maximum number of CPUs (2-32)"
-	range 2 32
+	int "Maximum number of CPUs"
 	depends on SMP
-	default "32"
+	range 2 32 if SPARC32
+	range 2 1024 if SPARC64
+	default 32 if SPARC32
+	default 64 if SPARC64
 
-config SPARC
+source kernel/Kconfig.hz
+
+config RWSEM_GENERIC_SPINLOCK
+	bool
+	default y if SPARC32
+
+config RWSEM_XCHGADD_ALGORITHM
+	bool
+	default y if SPARC64
+
+config GENERIC_FIND_NEXT_BIT
 	bool
 	default y
-	select HAVE_IDE
-	select HAVE_OPROFILE
-	select HAVE_ARCH_KGDB if !SMP
-	select HAVE_ARCH_TRACEHOOK
-	select ARCH_WANT_OPTIONAL_GPIOLIB
-	select RTC_CLASS
-	select RTC_DRV_M48T59
 
-# Identify this as a Sparc32 build
-config SPARC32
+config GENERIC_HWEIGHT
+	bool
+	default y if !ULTRA_HAS_POPULATION_COUNT
+
+config GENERIC_CALIBRATE_DELAY
 	bool
 	default y
-	help
-	  SPARC is a family of RISC microprocessors designed and marketed by
-	  Sun Microsystems, incorporated.  They are very widely found in Sun
-	  workstations and clones. This port covers the original 32-bit SPARC;
-	  it is old and stable and usually considered one of the "big three"
-	  along with the Intel and Alpha ports.  The UltraLinux project
-	  maintains both the SPARC32 and SPARC64 ports; its web page is
-	  available at <http://www.ultralinux.org/>.
 
-# Global things across all Sun machines.
-config ISA
+config ARCH_MAY_HAVE_PC_FDC
 	bool
-	help
-	  ISA is found on Espresso only and is not supported currently.
-	  Say N
+	default y
 
-config EISA
+config ARCH_HAS_ILOG2_U32
+	bool
+	default n
+
+config ARCH_HAS_ILOG2_U64
+	bool
+	default n
+
+config EMULATED_CMPXCHG
 	bool
+	default y if SPARC32
 	help
-	  EISA is not supported.
-	  Say N
+	  Sparc32 does not have a CAS instruction like sparc64. cmpxchg()
+	  is emulated, and therefore it is not completely atomic.
 
-config MCA
+# Makefile helpers
+config SPARC32_SMP
+	bool
+	default y
+	depends on SPARC32 && SMP
+
+config SPARC64_SMP
 	bool
+	default y
+	depends on SPARC64 && SMP
+
+choice
+	prompt "Kernel page size" if SPARC64
+	default SPARC64_PAGE_SIZE_8KB
+
+config SPARC64_PAGE_SIZE_8KB
+	bool "8KB"
 	help
-	  MCA is not supported.
-	  Say N
+	  This lets you select the page size of the kernel.
 
-config PCMCIA
-	tristate
-	---help---
-	  Say Y here if you want to attach PCMCIA- or PC-cards to your Linux
-	  computer.  These are credit-card size devices such as network cards,
-	  modems or hard drives often used with laptops computers.  There are
-	  actually two varieties of these cards: the older 16 bit PCMCIA cards
-	  and the newer 32 bit CardBus cards.  If you want to use CardBus
-	  cards, you need to say Y here and also to "CardBus support" below.
+	  8KB and 64KB work quite well, since SPARC ELF sections
+	  provide for up to 64KB alignment.
 
-	  To use your PC-cards, you will need supporting software from David
-	  Hinds' pcmcia-cs package (see the file <file:Documentation/Changes>
-	  for location).  Please also read the PCMCIA-HOWTO, available from
-	  <http://www.tldp.org/docs.html#howto>.
+	  If you don't know what to do, choose 8KB.
 
-	  To compile this driver as modules, choose M here: the
-	  modules will be called pcmcia_core and ds.
+config SPARC64_PAGE_SIZE_64KB
+	bool "64KB"
 
-config SBUS
+endchoice
+
+config SECCOMP
+	bool "Enable seccomp to safely compute untrusted bytecode"
+	depends on SPARC64 && PROC_FS
+	default y
+	help
+	  This kernel feature is useful for number crunching applications
+	  that may need to compute untrusted bytecode during their
+	  execution. By using pipes or other transports made available to
+	  the process as file descriptors supporting the read/write
+	  syscalls, it's possible to isolate those applications in
+	  their own address space using seccomp. Once seccomp is
+	  enabled via /proc/<pid>/seccomp, it cannot be disabled
+	  and the task is only allowed to execute a few safe syscalls
+	  defined by each seccomp mode.
+
+	  If unsure, say Y. Only embedded should say N here.
+
+config HOTPLUG_CPU
+	bool "Support for hot-pluggable CPUs"
+	depends on SPARC64 && SMP
+	select HOTPLUG
+	help
+	  Say Y here to experiment with turning CPUs off and on.  CPUs
+	  can be controlled through /sys/devices/system/cpu/cpu#.
+	  Say N if you want to disable CPU hotplug.
+
+config GENERIC_HARDIRQS
 	bool
+	default y if SPARC64
+
+source "kernel/time/Kconfig"
+
+if SPARC64
+source "drivers/cpufreq/Kconfig"
+
+config US3_FREQ
+	tristate "UltraSPARC-III CPU Frequency driver"
+	depends on CPU_FREQ
+	select CPU_FREQ_TABLE
+	help
+	  This adds the CPUFreq driver for UltraSPARC-III processors.
+
+	  For details, take a look at <file:Documentation/cpu-freq>.
+
+	  If in doubt, say N.
+
+config US2E_FREQ
+	tristate "UltraSPARC-IIe CPU Frequency driver"
+	depends on CPU_FREQ
+	select CPU_FREQ_TABLE
+	help
+	  This adds the CPUFreq driver for UltraSPARC-IIe processors.
+
+	  For details, take a look at <file:Documentation/cpu-freq>.
+
+	  If in doubt, say N.
+
+endif
+
+config US3_MC
+	tristate "UltraSPARC-III Memory Controller driver"
+	depends on SPARC64
 	default y
+	help
+	  This adds a driver for the UltraSPARC-III memory controller.
+	  Loading this driver allows exact mnemonic strings to be
+	  printed in the event of a memory error, so that the faulty DIMM
+	  on the motherboard can be matched to the error.
 
-config SBUSCHAR
+	  If in doubt, say Y, as this information can be very useful.
+
+# Global things across all Sun machines.
+config GENERIC_LOCKBREAK
 	bool
 	default y
+	depends on SPARC64 && SMP && PREEMPT
+
+choice
+	prompt "SPARC64 Huge TLB Page Size"
+	depends on SPARC64 && HUGETLB_PAGE
+	default HUGETLB_PAGE_SIZE_4MB
+
+config HUGETLB_PAGE_SIZE_4MB
+	bool "4MB"
+
+config HUGETLB_PAGE_SIZE_512K
+	bool "512K"
+
+config HUGETLB_PAGE_SIZE_64K
+	depends on !SPARC64_PAGE_SIZE_64KB
+	bool "64K"
+
+endchoice
+
+config NUMA
+	bool "NUMA support"
+	depends on SPARC64 && SMP
+
+config NODES_SHIFT
+	int
+	default "4"
+	depends on NEED_MULTIPLE_NODES
+
+# Some NUMA nodes have memory ranges that span
+# other nodes.  Even though a pfn is valid and
+# between a node's start and end pfns, it may not
+# reside on that node.  See memmap_init_zone()
+# for details.
+config NODES_SPAN_OTHER_NODES
+	def_bool y
+	depends on NEED_MULTIPLE_NODES
+
+config ARCH_POPULATES_NODE_MAP
+	def_bool y if SPARC64
+
+config ARCH_SELECT_MEMORY_MODEL
+	def_bool y if SPARC64
+
+config ARCH_SPARSEMEM_ENABLE
+	def_bool y if SPARC64
+	select SPARSEMEM_VMEMMAP_ENABLE
+
+config ARCH_SPARSEMEM_DEFAULT
+	def_bool y if SPARC64
+
+source "mm/Kconfig"
+
+config SCHED_SMT
+	bool "SMT (Hyperthreading) scheduler support"
+	depends on SPARC64 && SMP
+	default y
+	help
+	  SMT scheduler support improves the CPU scheduler's decision making
+	  when dealing with SPARC cpus at a cost of slightly increased overhead
+	  in some places. If unsure say N here.
+
+config SCHED_MC
+	bool "Multi-core scheduler support"
+	depends on SPARC64 && SMP
+	default y
+	help
+	  Multi-core scheduler support improves the CPU scheduler's decision
+	  making when dealing with multi-core CPU chips at a cost of slightly
+	  increased overhead in some places. If unsure say N here.
+
+if SPARC64
+source "kernel/Kconfig.preempt"
+endif
+
+config CMDLINE_BOOL
+	bool "Default bootloader kernel arguments"
+	depends on SPARC64
+
+config CMDLINE
+	string "Initial kernel command string"
+	depends on CMDLINE_BOOL
+	default "console=ttyS0,9600 root=/dev/sda1"
+	help
+	  Say Y here if you want to be able to pass default arguments to
+	  the kernel. This will be overridden by the bootloader, if you
+	  use one (such as SILO). This is most useful if you want to boot
+	  a kernel from TFTP, and want default options to be available
+	  with having them passed on the command line.
+
+	  NOTE: This option WILL override the PROM bootargs setting!
+
+config SUN_PM
+	bool
+	default y if SPARC32
+	help
+	  Enable power management and CPU standby features on supported
+	  SPARC platforms.
+
+config SPARC_LED
+	tristate "Sun4m LED driver"
+	depends on SPARC32
+	help
+	  This driver toggles the front-panel LED on sun4m systems
+	  in a user-specifiable manner.  Its state can be probed
+	  by reading /proc/led and its blinking mode can be changed
+	  via writes to /proc/led
 
 config SERIAL_CONSOLE
 	bool
+	depends on SPARC32
 	default y
 	---help---
 	  If you say Y here, it will be possible to use a serial port as the
@@ -161,71 +434,71 @@ config SERIAL_CONSOLE
 
 	  If unsure, say N.
 
-config SUN_AUXIO
-	bool
-	default y
-
-config SUN_IO
-	bool
-	default y
+endmenu
 
-config RWSEM_GENERIC_SPINLOCK
+menu "Bus options (PCI etc.)"
+config ISA
 	bool
-	default y
+	help
+	  ISA is found on Espresso only and is not supported currently.
 
-config RWSEM_XCHGADD_ALGORITHM
+config ISAPNP
 	bool
+	help
+	  ISAPNP is not supported
 
-config GENERIC_FIND_NEXT_BIT
+config EISA
 	bool
-	default y
+	help
+	  EISA is not supported.
 
-config GENERIC_HWEIGHT
+config MCA
 	bool
-	default y
+	help
+	  MCA is not supported.
 
-config GENERIC_CALIBRATE_DELAY
+config SBUS
 	bool
 	default y
 
-config ARCH_MAY_HAVE_PC_FDC
+config SBUSCHAR
 	bool
 	default y
 
-config ARCH_HAS_ILOG2_U32
-	bool
-	default n
-
-config ARCH_HAS_ILOG2_U64
-	bool
-	default n
-
-config EMULATED_CMPXCHG
+config SUN_IO
 	bool
 	default y
-	help
-	  Sparc32 does not have a CAS instruction like sparc64. cmpxchg()
-	  is emulated, and therefore it is not completely atomic.
 
-config SUN_PM
-	bool
-	default y
+config SUN_LDOMS
+	bool "Sun Logical Domains support"
+	depends on SPARC64
 	help
-	  Enable power management and CPU standby features on supported
-	  SPARC platforms.
+	  Say Y here is you want to support virtual devices via
+	  Logical Domains.
 
 config PCI
 	bool "Support for PCI and PS/2 keyboard/mouse"
+	select ARCH_SUPPORTS_MSI if SPARC64
 	help
+	  Find out whether your system includes a PCI bus. PCI is the name of
+	  a bus system, i.e. the way the CPU talks to the other stuff inside
+	  your box.  If you say Y here, the kernel will include drivers and
+	  infrastructure code to support PCI bus devices.
+
 	  CONFIG_PCI is needed for all JavaStation's (including MrCoffee),
 	  CP-1200, JavaEngine-1, Corona, Red October, and Serengeti SGSC.
 	  All of these platforms are extremely obscure, so say N if unsure.
 
+config PCI_DOMAINS
+	def_bool PCI if SPARC64
+
 config PCI_SYSCALL
 	def_bool PCI
 
 source "drivers/pci/Kconfig"
 
+source "drivers/pcmcia/Kconfig"
+
 config SUN_OPENPROMFS
 	tristate "Openprom tree appears in /proc/openprom"
 	help
@@ -239,17 +512,33 @@ config SUN_OPENPROMFS
 	  Only choose N if you know in advance that you will not need to modify
 	  OpenPROM settings on the running system.
 
-config SPARC_LED
-	tristate "Sun4m LED driver"
-	help
-	  This driver toggles the front-panel LED on sun4m systems
-	  in a user-specifiable manner.  Its state can be probed
-	  by reading /proc/led and its blinking mode can be changed
-	  via writes to /proc/led
+# Makefile helpers
+config SPARC32_PCI
+	bool
+	default y
+	depends on SPARC32 && PCI
+
+config SPARC64_PCI
+	bool
+	default y
+	depends on SPARC64 && PCI
+
+endmenu
+
+menu "Executable file formats"
 
 source "fs/Kconfig.binfmt"
 
-source "mm/Kconfig"
+config COMPAT
+	bool
+	depends on SPARC64
+	default y
+	select COMPAT_BINFMT_ELF
+
+config SYSVIPC_COMPAT
+	bool
+	depends on COMPAT && SYSVIPC
+	default y
 
 endmenu
 
@@ -259,40 +548,6 @@ source "drivers/Kconfig"
 
 source "drivers/sbus/char/Kconfig"
 
-# This one must be before the filesystem configs. -DaveM
-
-menu "Unix98 PTY support"
-
-config UNIX98_PTYS
-	bool "Unix98 PTY support"
-	---help---
-	  A pseudo terminal (PTY) is a software device consisting of two
-	  halves: a master and a slave. The slave device behaves identical to
-	  a physical terminal; the master device is used by a process to
-	  read data from and write data to the slave, thereby emulating a
-	  terminal. Typical programs for the master side are telnet servers
-	  and xterms.
-
-	  Linux has traditionally used the BSD-like names /dev/ptyxx for
-	  masters and /dev/ttyxx for slaves of pseudo terminals. This scheme
-	  has a number of problems. The GNU C library glibc 2.1 and later,
-	  however, supports the Unix98 naming standard: in order to acquire a
-	  pseudo terminal, a process opens /dev/ptmx; the number of the pseudo
-	  terminal is then made available to the process and the pseudo
-	  terminal slave can be accessed as /dev/pts/<number>. What was
-	  traditionally /dev/ttyp2 will then be /dev/pts/2, for example.
-
-	  The entries in /dev/pts/ are created on the fly by a virtual
-	  file system; therefore, if you say Y here you should say Y to
-	  "/dev/pts file system for Unix98 PTYs" as well.
-
-	  If you want to say Y here, you need to have the C library glibc 2.1
-	  or later (equal to libc-6.1, check with "ls -l /lib/libc.so.*").
-	  Read the instructions in <file:Documentation/Changes> pertaining to
-	  pseudo terminals. It's safe to say N.
-
-endmenu
-
 source "fs/Kconfig"
 
 source "arch/sparc/Kconfig.debug"
diff --git a/arch/sparc/Kconfig.debug b/arch/sparc/Kconfig.debug
index 87dd496f15eb..b8a15e271bfa 100644
--- a/arch/sparc/Kconfig.debug
+++ b/arch/sparc/Kconfig.debug
@@ -15,4 +15,30 @@ config DEBUG_STACK_USAGE
 
 	  This option will slow down process creation somewhat.
 
+config DEBUG_DCFLUSH
+	bool "D-cache flush debugging"
+	depends on SPARC64 && DEBUG_KERNEL
+
+config STACK_DEBUG
+	bool "Stack Overflow Detection Support"
+
+config DEBUG_PAGEALLOC
+	bool "Debug page memory allocations"
+	depends on SPARC64 && DEBUG_KERNEL && !HIBERNATION
+	help
+	  Unmap pages from the kernel linear mapping after free_pages().
+	  This results in a large slowdown, but helps to find certain types
+	  of memory corruptions.
+
+config MCOUNT
+	bool
+	depends on SPARC64
+	depends on STACK_DEBUG || FUNCTION_TRACER
+	default y
+
+config FRAME_POINTER
+	bool
+	depends on MCOUNT
+	default y
+
 endmenu
diff --git a/arch/sparc/Makefile b/arch/sparc/Makefile
index 9592889a6fd0..2003ded054c2 100644
--- a/arch/sparc/Makefile
+++ b/arch/sparc/Makefile
@@ -2,18 +2,31 @@
 # sparc/Makefile
 #
 # Makefile for the architecture dependent flags and dependencies on the
-# Sparc.
+# Sparc and sparc64.
 #
-# Copyright (C) 1994 David S. Miller (davem@caip.rutgers.edu)
+# Copyright (C) 1994,1996,1998 David S. Miller (davem@caip.rutgers.edu)
+# Copyright (C) 1998 Jakub Jelinek (jj@ultra.linux.cz)
+
+# We are not yet configured - so test on arch
+ifeq ($(ARCH),sparc)
+        KBUILD_DEFCONFIG := sparc32_defconfig
+else
+        KBUILD_DEFCONFIG := sparc64_defconfig
+endif
+
+ifeq ($(CONFIG_SPARC32),y)
+#####
+# sparc32
 #
 
 #
 # Uncomment the first KBUILD_CFLAGS if you are doing kgdb source level
 # debugging of the kernel to get the proper debugging information.
 
-AS              := $(AS) -32
-LDFLAGS		:= -m elf32_sparc
-CHECKFLAGS	+= -D__sparc__
+AS             := $(AS) -32
+LDFLAGS        := -m elf32_sparc
+CHECKFLAGS     += -D__sparc__
+export BITS    := 32
 
 #KBUILD_CFLAGS += -g -pipe -fcall-used-g5 -fcall-used-g7
 KBUILD_CFLAGS += -m32 -pipe -mno-fpu -fcall-used-g5 -fcall-used-g7
@@ -25,38 +38,60 @@ CPPFLAGS_vmlinux.lds += -m32
 #  Actual linking is done with "make image".
 LDFLAGS_vmlinux = -r
 
-head-y := arch/sparc/kernel/head.o arch/sparc/kernel/init_task.o
-HEAD_Y := $(head-y)
+# Default target
+all: zImage
+
+
+else
+#####
+# sparc64
+#
 
-core-y += arch/sparc/kernel/ arch/sparc/mm/ arch/sparc/math-emu/
-libs-y += arch/sparc/prom/ arch/sparc/lib/
+CHECKFLAGS      += -D__sparc__ -D__sparc_v9__ -D__arch64__ -m64
+
+# Undefine sparc when processing vmlinux.lds - it is used
+# And teach CPP we are doing 64 bit builds (for this case)
+CPPFLAGS_vmlinux.lds += -m64 -Usparc
+LDFLAGS              := -m elf64_sparc
+export BITS          := 64
+
+KBUILD_CFLAGS += -m64 -pipe -mno-fpu -mcpu=ultrasparc -mcmodel=medlow   \
+                 -ffixed-g4 -ffixed-g5 -fcall-used-g7 -Wno-sign-compare \
+                 -Wa,--undeclared-regs
+KBUILD_CFLAGS += $(call cc-option,-mtune=ultrasparc3)
+KBUILD_AFLAGS += -m64 -mcpu=ultrasparc -Wa,--undeclared-regs
+
+ifeq ($(CONFIG_MCOUNT),y)
+  KBUILD_CFLAGS += -pg
+endif
+
+endif
+
+head-y                 := arch/sparc/kernel/head_$(BITS).o
+head-y                 += arch/sparc/kernel/init_task.o
+
+core-y                 += arch/sparc/kernel/
+core-y                 += arch/sparc/mm/ arch/sparc/math-emu/
+
+libs-y                 += arch/sparc/prom/
+libs-y                 += arch/sparc/lib/
 
 drivers-$(CONFIG_OPROFILE)	+= arch/sparc/oprofile/
 
 # Export what is needed by arch/sparc/boot/Makefile
-# Renaming is done to avoid confusing pattern matching rules in 2.5.45 (multy-)
-INIT_Y		:= $(patsubst %/, %/built-in.o, $(init-y))
-CORE_Y		:= $(core-y)
-CORE_Y		+= kernel/ mm/ fs/ ipc/ security/ crypto/ block/
-CORE_Y		:= $(patsubst %/, %/built-in.o, $(CORE_Y))
-DRIVERS_Y	:= $(patsubst %/, %/built-in.o, $(drivers-y))
-NET_Y		:= $(patsubst %/, %/built-in.o, $(net-y))
-LIBS_Y1		:= $(patsubst %/, %/lib.a, $(libs-y))
-LIBS_Y2		:= $(patsubst %/, %/built-in.o, $(libs-y))
-LIBS_Y		:= $(LIBS_Y1) $(LIBS_Y2)
+export VMLINUX_INIT VMLINUX_MAIN
+VMLINUX_INIT := $(head-y) $(init-y)
+VMLINUX_MAIN := $(core-y) kernel/ mm/ fs/ ipc/ security/ crypto/ block/
+VMLINUX_MAIN += $(patsubst %/, %/lib.a, $(libs-y)) $(libs-y)
+VMLINUX_MAIN += $(drivers-y) $(net-y)
 
 ifdef CONFIG_KALLSYMS
-kallsyms.o := .tmp_kallsyms2.o
+export kallsyms.o := .tmp_kallsyms2.o
 endif
 
-export INIT_Y CORE_Y DRIVERS_Y NET_Y LIBS_Y HEAD_Y kallsyms.o
-
-# Default target
-all: zImage
-
 boot := arch/sparc/boot
 
-image zImage tftpboot.img: vmlinux
+image zImage tftpboot.img vmlinux.aout: vmlinux
 	$(Q)$(MAKE) $(build)=$(boot) $(boot)/$@
 
 archclean:
@@ -65,11 +100,17 @@ archclean:
 # This is the image used for packaging
 KBUILD_IMAGE := $(boot)/zImage
 
-CLEAN_FILES += arch/$(ARCH)/boot/System.map
-
 # Don't use tabs in echo arguments.
+ifeq ($(ARCH),sparc)
 define archhelp
   echo  '* image        - kernel image ($(boot)/image)'
   echo  '* zImage       - stripped kernel image ($(boot)/zImage)'
   echo  '  tftpboot.img - image prepared for tftp'
 endef
+else
+define archhelp
+  echo  '* vmlinux       - Standard sparc64 kernel'
+  echo  '  vmlinux.aout  - a.out kernel for sparc64'
+  echo  '  tftpboot.img - image prepared for tftp'
+endef
+endif
diff --git a/arch/sparc64/boot/.gitignore b/arch/sparc/boot/.gitignore
index 36356f9d498e..fc6f3986c76c 100644
--- a/arch/sparc64/boot/.gitignore
+++ b/arch/sparc/boot/.gitignore
@@ -1,4 +1,8 @@
+btfix.S
+btfixupprep
 image
+zImage
 tftpboot.img
 vmlinux.aout
 piggyback
+
diff --git a/arch/sparc/boot/Makefile b/arch/sparc/boot/Makefile
index 3e77a9f52248..96041a8d39e8 100644
--- a/arch/sparc/boot/Makefile
+++ b/arch/sparc/boot/Makefile
@@ -6,13 +6,16 @@
 ROOT_IMG	:= /usr/src/root.img
 ELFTOAOUT	:= elftoaout
 
-hostprogs-y	:= piggyback btfixupprep
-targets		:= tftpboot.img btfix.o btfix.S image
+hostprogs-y	:= piggyback_32 piggyback_64 btfixupprep
+targets		:= tftpboot.img btfix.o btfix.S image zImage vmlinux.aout
+clean-files	:= System.map
 
 quiet_cmd_elftoaout	= ELFTOAOUT $@
       cmd_elftoaout	= $(ELFTOAOUT) $(obj)/image -o $@
+
+ifeq ($(CONFIG_SPARC32),y)
 quiet_cmd_piggy		= PIGGY   $@
-      cmd_piggy		= $(obj)/piggyback $@ $(obj)/System.map $(ROOT_IMG)
+      cmd_piggy		= $(obj)/piggyback_32 $@ $(obj)/System.map $(ROOT_IMG)
 quiet_cmd_btfix		= BTFIX   $@
       cmd_btfix		= $(OBJDUMP) -x vmlinux | $(obj)/btfixupprep > $@
 quiet_cmd_sysmap        = SYSMAP  $(obj)/System.map
@@ -37,8 +40,8 @@ define rule_image
 	echo 'cmd_$@ := $(cmd_image)' > $(@D)/.$(@F).cmd
 endef
 
-BTOBJS := $(HEAD_Y) $(INIT_Y)
-BTLIBS := $(CORE_Y) $(LIBS_Y) $(DRIVERS_Y) $(NET_Y)
+BTOBJS := $(patsubst %/, %/built-in.o, $(VMLINUX_INIT))
+BTLIBS := $(patsubst %/, %/built-in.o, $(VMLINUX_MAIN))
 LDFLAGS_image := -T arch/sparc/kernel/vmlinux.lds $(BTOBJS) \
                   --start-group $(BTLIBS) --end-group \
                   $(kallsyms.o) $(obj)/btfix.o
@@ -61,3 +64,28 @@ $(obj)/tftpboot.img: $(obj)/piggyback $(obj)/System.map $(obj)/image FORCE
 
 $(obj)/btfix.S: $(obj)/btfixupprep vmlinux FORCE
 	$(call if_changed,btfix)
+
+endif
+
+ifeq ($(CONFIG_SPARC64),y)
+quiet_cmd_piggy     = PIGGY   $@
+      cmd_piggy     = $(obj)/piggyback_64 $@ System.map $(ROOT_IMG)
+quiet_cmd_strip     = STRIP   $@
+      cmd_strip     = $(STRIP) -R .comment -R .note -K sun4u_init -K _end -K _start vmlinux -o $@
+
+
+# Actual linking
+$(obj)/image: vmlinux FORCE
+	$(call if_changed,strip)
+	@echo '  kernel: $@ is ready'
+
+$(obj)/tftpboot.img: vmlinux $(obj)/piggyback_64 System.map $(ROOT_IMG) FORCE
+	$(call if_changed,elftoaout)
+	$(call if_changed,piggy)
+	@echo '  kernel: $@ is ready'
+
+$(obj)/vmlinux.aout: vmlinux FORCE
+	$(call if_changed,elftoaout)
+	@echo '  kernel: $@ is ready'
+endif
+
diff --git a/arch/sparc/boot/piggyback.c b/arch/sparc/boot/piggyback_32.c
index c9f500c1a8b2..c9f500c1a8b2 100644
--- a/arch/sparc/boot/piggyback.c
+++ b/arch/sparc/boot/piggyback_32.c
diff --git a/arch/sparc64/boot/piggyback.c b/arch/sparc/boot/piggyback_64.c
index de364bfed0bb..de364bfed0bb 100644
--- a/arch/sparc64/boot/piggyback.c
+++ b/arch/sparc/boot/piggyback_64.c
diff --git a/arch/sparc/defconfig b/arch/sparc/configs/sparc32_defconfig
index 2e3a149ea0e7..2e3a149ea0e7 100644
--- a/arch/sparc/defconfig
+++ b/arch/sparc/configs/sparc32_defconfig
diff --git a/arch/sparc64/defconfig b/arch/sparc/configs/sparc64_defconfig
index 05d19a3e590f..05d19a3e590f 100644
--- a/arch/sparc64/defconfig
+++ b/arch/sparc/configs/sparc64_defconfig
diff --git a/arch/sparc/include/asm/Kbuild b/arch/sparc/include/asm/Kbuild
index 2d2769d766ec..89c260aab45c 100644
--- a/arch/sparc/include/asm/Kbuild
+++ b/arch/sparc/include/asm/Kbuild
@@ -15,8 +15,6 @@ header-y += signal_32.h
 header-y += signal_64.h
 header-y += stat_32.h
 header-y += stat_64.h
-header-y += unistd_32.h
-header-y += unistd_64.h
 
 header-y += apc.h
 header-y += asi.h
diff --git a/arch/sparc/include/asm/atomic_64.h b/arch/sparc/include/asm/atomic_64.h
index 2c71ec4a3b18..5982c5ae7f07 100644
--- a/arch/sparc/include/asm/atomic_64.h
+++ b/arch/sparc/include/asm/atomic_64.h
@@ -112,17 +112,10 @@ static inline int atomic64_add_unless(atomic64_t *v, long a, long u)
 #define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1, 0)
 
 /* Atomic operations are already serializing */
-#ifdef CONFIG_SMP
-#define smp_mb__before_atomic_dec()	membar_storeload_loadload();
-#define smp_mb__after_atomic_dec()	membar_storeload_storestore();
-#define smp_mb__before_atomic_inc()	membar_storeload_loadload();
-#define smp_mb__after_atomic_inc()	membar_storeload_storestore();
-#else
 #define smp_mb__before_atomic_dec()	barrier()
 #define smp_mb__after_atomic_dec()	barrier()
 #define smp_mb__before_atomic_inc()	barrier()
 #define smp_mb__after_atomic_inc()	barrier()
-#endif
 
 #include <asm-generic/atomic.h>
 #endif /* !(__ARCH_SPARC64_ATOMIC__) */
diff --git a/arch/sparc/include/asm/bitops_32.h b/arch/sparc/include/asm/bitops_32.h
index 68b98a7e6454..9cf4ae0cd7ba 100644
--- a/arch/sparc/include/asm/bitops_32.h
+++ b/arch/sparc/include/asm/bitops_32.h
@@ -98,6 +98,7 @@ static inline void change_bit(unsigned long nr, volatile unsigned long *addr)
 #include <asm-generic/bitops/sched.h>
 #include <asm-generic/bitops/ffs.h>
 #include <asm-generic/bitops/fls.h>
+#include <asm-generic/bitops/__fls.h>
 #include <asm-generic/bitops/fls64.h>
 #include <asm-generic/bitops/hweight.h>
 #include <asm-generic/bitops/lock.h>
diff --git a/arch/sparc/include/asm/bitops_64.h b/arch/sparc/include/asm/bitops_64.h
index bb87b8080220..e72ac9cdfb98 100644
--- a/arch/sparc/include/asm/bitops_64.h
+++ b/arch/sparc/include/asm/bitops_64.h
@@ -23,13 +23,8 @@ extern void change_bit(unsigned long nr, volatile unsigned long *addr);
 
 #include <asm-generic/bitops/non-atomic.h>
 
-#ifdef CONFIG_SMP
-#define smp_mb__before_clear_bit()	membar_storeload_loadload()
-#define smp_mb__after_clear_bit()	membar_storeload_storestore()
-#else
 #define smp_mb__before_clear_bit()	barrier()
 #define smp_mb__after_clear_bit()	barrier()
-#endif
 
 #include <asm-generic/bitops/ffz.h>
 #include <asm-generic/bitops/__ffs.h>
diff --git a/arch/sparc/include/asm/device.h b/arch/sparc/include/asm/device.h
index 19790eb99cc6..3702e087df2c 100644
--- a/arch/sparc/include/asm/device.h
+++ b/arch/sparc/include/asm/device.h
@@ -20,4 +20,16 @@ struct dev_archdata {
 	int			numa_node;
 };
 
+static inline void dev_archdata_set_node(struct dev_archdata *ad,
+					 struct device_node *np)
+{
+	ad->prom_node = np;
+}
+
+static inline struct device_node *
+dev_archdata_get_node(const struct dev_archdata *ad)
+{
+	return ad->prom_node;
+}
+
 #endif /* _ASM_SPARC_DEVICE_H */
diff --git a/arch/sparc/include/asm/hypervisor.h b/arch/sparc/include/asm/hypervisor.h
index 109ae24ba242..bafe5a631b6d 100644
--- a/arch/sparc/include/asm/hypervisor.h
+++ b/arch/sparc/include/asm/hypervisor.h
@@ -2713,6 +2713,30 @@ extern unsigned long sun4v_ldc_revoke(unsigned long channel,
  */
 #define HV_FAST_SET_PERFREG		0x101
 
+#define HV_N2_PERF_SPARC_CTL		0x0
+#define HV_N2_PERF_DRAM_CTL0		0x1
+#define HV_N2_PERF_DRAM_CNT0		0x2
+#define HV_N2_PERF_DRAM_CTL1		0x3
+#define HV_N2_PERF_DRAM_CNT1		0x4
+#define HV_N2_PERF_DRAM_CTL2		0x5
+#define HV_N2_PERF_DRAM_CNT2		0x6
+#define HV_N2_PERF_DRAM_CTL3		0x7
+#define HV_N2_PERF_DRAM_CNT3		0x8
+
+#define HV_FAST_N2_GET_PERFREG		0x104
+#define HV_FAST_N2_SET_PERFREG		0x105
+
+#ifndef __ASSEMBLY__
+extern unsigned long sun4v_niagara_getperf(unsigned long reg,
+					   unsigned long *val);
+extern unsigned long sun4v_niagara_setperf(unsigned long reg,
+					   unsigned long val);
+extern unsigned long sun4v_niagara2_getperf(unsigned long reg,
+					    unsigned long *val);
+extern unsigned long sun4v_niagara2_setperf(unsigned long reg,
+					    unsigned long val);
+#endif
+
 /* MMU statistics services.
  *
  * The hypervisor maintains MMU statistics and privileged code provides
diff --git a/arch/sparc/include/asm/irq_64.h b/arch/sparc/include/asm/irq_64.h
index 71673eca3660..d47d4a1955a9 100644
--- a/arch/sparc/include/asm/irq_64.h
+++ b/arch/sparc/include/asm/irq_64.h
@@ -66,6 +66,9 @@ extern void virt_irq_free(unsigned int virt_irq);
 extern void __init init_IRQ(void);
 extern void fixup_irqs(void);
 
+extern int register_perfctr_intr(void (*handler)(struct pt_regs *));
+extern void release_perfctr_intr(void (*handler)(struct pt_regs *));
+
 static inline void set_softint(unsigned long bits)
 {
 	__asm__ __volatile__("wr	%0, 0x0, %%set_softint"
diff --git a/arch/sparc/include/asm/irqflags_64.h b/arch/sparc/include/asm/irqflags_64.h
index bb42e59162aa..8b49bf920df3 100644
--- a/arch/sparc/include/asm/irqflags_64.h
+++ b/arch/sparc/include/asm/irqflags_64.h
@@ -10,6 +10,8 @@
 #ifndef _ASM_IRQFLAGS_H
 #define _ASM_IRQFLAGS_H
 
+#include <asm/pil.h>
+
 #ifndef __ASSEMBLY__
 
 static inline unsigned long __raw_local_save_flags(void)
@@ -40,9 +42,9 @@ static inline void raw_local_irq_restore(unsigned long flags)
 static inline void raw_local_irq_disable(void)
 {
 	__asm__ __volatile__(
-		"wrpr	15, %%pil"
+		"wrpr	%0, %%pil"
 		: /* no outputs */
-		: /* no inputs */
+		: "i" (PIL_NORMAL_MAX)
 		: "memory"
 	);
 }
diff --git a/arch/sparc/include/asm/openprom_32.h b/arch/sparc/include/asm/openprom_32.h
index 8b1649f29ed9..875da3552d80 100644
--- a/arch/sparc/include/asm/openprom_32.h
+++ b/arch/sparc/include/asm/openprom_32.h
@@ -170,9 +170,9 @@ struct linux_romvec {
 struct linux_nodeops {
 	int (*no_nextnode)(int node);
 	int (*no_child)(int node);
-	int (*no_proplen)(int node, char *name);
-	int (*no_getprop)(int node, char *name, char *val);
-	int (*no_setprop)(int node, char *name, char *val, int len);
+	int (*no_proplen)(int node, const char *name);
+	int (*no_getprop)(int node, const char *name, char *val);
+	int (*no_setprop)(int node, const char *name, char *val, int len);
 	char * (*no_nextprop)(int node, char *name);
 };
 
diff --git a/arch/sparc/include/asm/oplib_32.h b/arch/sparc/include/asm/oplib_32.h
index 699da05235c8..3bdf56f46883 100644
--- a/arch/sparc/include/asm/oplib_32.h
+++ b/arch/sparc/include/asm/oplib_32.h
@@ -199,12 +199,12 @@ extern int prom_getsibling(int node);
 /* Get the length, at the passed node, of the given property type.
  * Returns -1 on error (ie. no such property at this node).
  */
-extern int prom_getproplen(int thisnode, char *property);
+extern int prom_getproplen(int thisnode, const char *property);
 
 /* Fetch the requested property using the given buffer.  Returns
  * the number of bytes the prom put into your buffer or -1 on error.
  */
-extern int __must_check prom_getproperty(int thisnode, char *property,
+extern int __must_check prom_getproperty(int thisnode, const char *property,
 					 char *prop_buffer, int propbuf_size);
 
 /* Acquire an integer property. */
@@ -246,7 +246,7 @@ extern int prom_node_has_property(int node, char *property);
 /* Set the indicated property at the given node with the passed value.
  * Returns the number of bytes of your value that the prom took.
  */
-extern int prom_setprop(int node, char *prop_name, char *prop_value,
+extern int prom_setprop(int node, const char *prop_name, char *prop_value,
 			int value_size);
 
 extern int prom_pathtoinode(char *path);
diff --git a/arch/sparc/include/asm/pil.h b/arch/sparc/include/asm/pil.h
index 71819bb943fc..d573820c0ff4 100644
--- a/arch/sparc/include/asm/pil.h
+++ b/arch/sparc/include/asm/pil.h
@@ -10,7 +10,12 @@
  *
  * In fact any XCALL which has to etrap/rtrap has a problem because
  * it is difficult to prevent rtrap from running BH's, and that would
- * need to be done if the XCALL arrived while %pil==15.
+ * need to be done if the XCALL arrived while %pil==PIL_NORMAL_MAX.
+ *
+ * Finally, in order to handle profiling events even when a
+ * local_irq_disable() is in progress, we only disable up to level 14
+ * interrupts.  Profile counter overflow interrupts arrive at level
+ * 15.
  */
 #define PIL_SMP_CALL_FUNC	1
 #define PIL_SMP_RECEIVE_SIGNAL	2
@@ -18,5 +23,7 @@
 #define PIL_SMP_CTX_NEW_VERSION	4
 #define PIL_DEVICE_IRQ		5
 #define PIL_SMP_CALL_FUNC_SNGL	6
+#define PIL_NORMAL_MAX		14
+#define PIL_NMI			15
 
 #endif /* !(_SPARC64_PIL_H) */
diff --git a/arch/sparc/include/asm/spinlock_64.h b/arch/sparc/include/asm/spinlock_64.h
index 120cfe4577c7..c4d274d330e9 100644
--- a/arch/sparc/include/asm/spinlock_64.h
+++ b/arch/sparc/include/asm/spinlock_64.h
@@ -13,17 +13,12 @@
  * and rebuild your kernel.
  */
 
-/* All of these locking primitives are expected to work properly
- * even in an RMO memory model, which currently is what the kernel
- * runs in.
- *
- * There is another issue.  Because we play games to save cycles
- * in the non-contention case, we need to be extra careful about
- * branch targets into the "spinning" code.  They live in their
- * own section, but the newer V9 branches have a shorter range
- * than the traditional 32-bit sparc branch variants.  The rule
- * is that the branches that go into and out of the spinner sections
- * must be pre-V9 branches.
+/* Because we play games to save cycles in the non-contention case, we
+ * need to be extra careful about branch targets into the "spinning"
+ * code.  They live in their own section, but the newer V9 branches
+ * have a shorter range than the traditional 32-bit sparc branch
+ * variants.  The rule is that the branches that go into and out of
+ * the spinner sections must be pre-V9 branches.
  */
 
 #define __raw_spin_is_locked(lp)	((lp)->lock != 0)
@@ -38,12 +33,10 @@ static inline void __raw_spin_lock(raw_spinlock_t *lock)
 
 	__asm__ __volatile__(
 "1:	ldstub		[%1], %0\n"
-"	membar		#StoreLoad | #StoreStore\n"
 "	brnz,pn		%0, 2f\n"
 "	 nop\n"
 "	.subsection	2\n"
 "2:	ldub		[%1], %0\n"
-"	membar		#LoadLoad\n"
 "	brnz,pt		%0, 2b\n"
 "	 nop\n"
 "	ba,a,pt		%%xcc, 1b\n"
@@ -59,7 +52,6 @@ static inline int __raw_spin_trylock(raw_spinlock_t *lock)
 
 	__asm__ __volatile__(
 "	ldstub		[%1], %0\n"
-"	membar		#StoreLoad | #StoreStore"
 	: "=r" (result)
 	: "r" (lock)
 	: "memory");
@@ -70,7 +62,6 @@ static inline int __raw_spin_trylock(raw_spinlock_t *lock)
 static inline void __raw_spin_unlock(raw_spinlock_t *lock)
 {
 	__asm__ __volatile__(
-"	membar		#StoreStore | #LoadStore\n"
 "	stb		%%g0, [%0]"
 	: /* No outputs */
 	: "r" (lock)
@@ -83,14 +74,12 @@ static inline void __raw_spin_lock_flags(raw_spinlock_t *lock, unsigned long fla
 
 	__asm__ __volatile__(
 "1:	ldstub		[%2], %0\n"
-"	membar		#StoreLoad | #StoreStore\n"
 "	brnz,pn		%0, 2f\n"
 "	 nop\n"
 "	.subsection	2\n"
 "2:	rdpr		%%pil, %1\n"
 "	wrpr		%3, %%pil\n"
 "3:	ldub		[%2], %0\n"
-"	membar		#LoadLoad\n"
 "	brnz,pt		%0, 3b\n"
 "	 nop\n"
 "	ba,pt		%%xcc, 1b\n"
@@ -113,12 +102,10 @@ static void inline __read_lock(raw_rwlock_t *lock)
 "4:	 add		%0, 1, %1\n"
 "	cas		[%2], %0, %1\n"
 "	cmp		%0, %1\n"
-"	membar		#StoreLoad | #StoreStore\n"
 "	bne,pn		%%icc, 1b\n"
 "	 nop\n"
 "	.subsection	2\n"
 "2:	ldsw		[%2], %0\n"
-"	membar		#LoadLoad\n"
 "	brlz,pt		%0, 2b\n"
 "	 nop\n"
 "	ba,a,pt		%%xcc, 4b\n"
@@ -139,7 +126,6 @@ static int inline __read_trylock(raw_rwlock_t *lock)
 "	add		%0, 1, %1\n"
 "	cas		[%2], %0, %1\n"
 "	cmp		%0, %1\n"
-"	membar		#StoreLoad | #StoreStore\n"
 "	bne,pn		%%icc, 1b\n"
 "	 mov		1, %0\n"
 "2:"
@@ -155,7 +141,6 @@ static void inline __read_unlock(raw_rwlock_t *lock)
 	unsigned long tmp1, tmp2;
 
 	__asm__ __volatile__(
-"	membar	#StoreLoad | #LoadLoad\n"
 "1:	lduw	[%2], %0\n"
 "	sub	%0, 1, %1\n"
 "	cas	[%2], %0, %1\n"
@@ -179,12 +164,10 @@ static void inline __write_lock(raw_rwlock_t *lock)
 "4:	 or		%0, %3, %1\n"
 "	cas		[%2], %0, %1\n"
 "	cmp		%0, %1\n"
-"	membar		#StoreLoad | #StoreStore\n"
 "	bne,pn		%%icc, 1b\n"
 "	 nop\n"
 "	.subsection	2\n"
 "2:	lduw		[%2], %0\n"
-"	membar		#LoadLoad\n"
 "	brnz,pt		%0, 2b\n"
 "	 nop\n"
 "	ba,a,pt		%%xcc, 4b\n"
@@ -197,7 +180,6 @@ static void inline __write_lock(raw_rwlock_t *lock)
 static void inline __write_unlock(raw_rwlock_t *lock)
 {
 	__asm__ __volatile__(
-"	membar		#LoadStore | #StoreStore\n"
 "	stw		%%g0, [%0]"
 	: /* no outputs */
 	: "r" (lock)
@@ -217,7 +199,6 @@ static int inline __write_trylock(raw_rwlock_t *lock)
 "	 or		%0, %4, %1\n"
 "	cas		[%3], %0, %1\n"
 "	cmp		%0, %1\n"
-"	membar		#StoreLoad | #StoreStore\n"
 "	bne,pn		%%icc, 1b\n"
 "	 nop\n"
 "	mov		1, %2\n"
diff --git a/arch/sparc/include/asm/spitfire.h b/arch/sparc/include/asm/spitfire.h
index 985ea7e31992..f0d0c40c44da 100644
--- a/arch/sparc/include/asm/spitfire.h
+++ b/arch/sparc/include/asm/spitfire.h
@@ -6,6 +6,8 @@
 #ifndef _SPARC64_SPITFIRE_H
 #define _SPARC64_SPITFIRE_H
 
+#ifdef CONFIG_SPARC64
+
 #include <asm/asi.h>
 
 /* The following register addresses are accessible via ASI_DMMU
@@ -338,5 +340,5 @@ static inline void cheetah_put_itlb_data(int entry, unsigned long data)
 }
 
 #endif /* !(__ASSEMBLY__) */
-
+#endif /* CONFIG_SPARC64 */
 #endif /* !(_SPARC64_SPITFIRE_H) */
diff --git a/arch/sparc/include/asm/system_32.h b/arch/sparc/include/asm/system_32.h
index 8623fc48fe24..79c1ae2b42a3 100644
--- a/arch/sparc/include/asm/system_32.h
+++ b/arch/sparc/include/asm/system_32.h
@@ -15,6 +15,11 @@
 
 #include <linux/irqflags.h>
 
+static inline unsigned int probe_irq_mask(unsigned long val)
+{
+	return 0;
+}
+
 /*
  * Sparc (general) CPU types
  */
diff --git a/arch/sparc/include/asm/system_64.h b/arch/sparc/include/asm/system_64.h
index 8759f2a1b837..6c077816ab28 100644
--- a/arch/sparc/include/asm/system_64.h
+++ b/arch/sparc/include/asm/system_64.h
@@ -59,20 +59,9 @@ do {	__asm__ __volatile__("ba,pt	%%xcc, 1f\n\t" \
 			     : : : "memory"); \
 } while (0)
 
-#define mb()	\
-	membar_safe("#LoadLoad | #LoadStore | #StoreStore | #StoreLoad")
-#define rmb()	\
-	membar_safe("#LoadLoad")
-#define wmb()	\
-	membar_safe("#StoreStore")
-#define membar_storeload() \
-	membar_safe("#StoreLoad")
-#define membar_storeload_storestore() \
-	membar_safe("#StoreLoad | #StoreStore")
-#define membar_storeload_loadload() \
-	membar_safe("#StoreLoad | #LoadLoad")
-#define membar_storestore_loadstore() \
-	membar_safe("#StoreStore | #LoadStore")
+#define mb()	membar_safe("#StoreLoad")
+#define rmb()	__asm__ __volatile__("":::"memory")
+#define wmb()	__asm__ __volatile__("":::"memory")
 
 #endif
 
@@ -80,20 +69,20 @@ do {	__asm__ __volatile__("ba,pt	%%xcc, 1f\n\t" \
 
 #define read_barrier_depends()		do { } while(0)
 #define set_mb(__var, __value) \
-	do { __var = __value; membar_storeload_storestore(); } while(0)
+	do { __var = __value; membar_safe("#StoreLoad"); } while(0)
 
 #ifdef CONFIG_SMP
 #define smp_mb()	mb()
 #define smp_rmb()	rmb()
 #define smp_wmb()	wmb()
-#define smp_read_barrier_depends()	read_barrier_depends()
 #else
 #define smp_mb()	__asm__ __volatile__("":::"memory")
 #define smp_rmb()	__asm__ __volatile__("":::"memory")
 #define smp_wmb()	__asm__ __volatile__("":::"memory")
-#define smp_read_barrier_depends()	do { } while(0)
 #endif
 
+#define smp_read_barrier_depends()	do { } while(0)
+
 #define flushi(addr)	__asm__ __volatile__ ("flush %0" : : "r" (addr) : "memory")
 
 #define flushw_all()	__asm__ __volatile__("flushw")
@@ -107,11 +96,12 @@ do {	__asm__ __volatile__("ba,pt	%%xcc, 1f\n\t" \
  * arch/sparc64/kernel/smp.c:smp_percpu_timer_interrupt()
  * for more information.
  */
-#define reset_pic()    						\
-	__asm__ __volatile__("ba,pt	%xcc, 99f\n\t"		\
+#define write_pic(__p)  					\
+	__asm__ __volatile__("ba,pt	%%xcc, 99f\n\t"		\
 			     ".align	64\n"			\
-			  "99:wr	%g0, 0x0, %pic\n\t"	\
-			     "rd	%pic, %g0")
+			  "99:wr	%0, 0x0, %%pic\n\t"	\
+			     "rd	%%pic, %%g0" : : "r" (__p))
+#define reset_pic()	write_pic(0)
 
 #ifndef __ASSEMBLY__
 
@@ -170,6 +160,7 @@ do {	if (test_thread_flag(TIF_PERFCTR)) {				\
 	"stb	%%o5, [%%g6 + %5]\n\t"					\
 	"rdpr	%%cwp, %%o5\n\t"					\
 	"stb	%%o5, [%%g6 + %8]\n\t"					\
+	"wrpr	%%g0, 15, %%pil\n\t"					\
 	"mov	%4, %%g6\n\t"						\
 	"ldub	[%4 + %8], %%g1\n\t"					\
 	"wrpr	%%g1, %%cwp\n\t"					\
@@ -180,6 +171,7 @@ do {	if (test_thread_flag(TIF_PERFCTR)) {				\
 	"ldx	[%%sp + 2047 + 0x70], %%i6\n\t"				\
 	"ldx	[%%sp + 2047 + 0x78], %%i7\n\t"				\
 	"ldx	[%%g6 + %9], %%g4\n\t"					\
+	"wrpr	%%g0, 14, %%pil\n\t"					\
 	"brz,pt %%o7, switch_to_pc\n\t"					\
 	" mov	%%g7, %0\n\t"						\
 	"sethi	%%hi(ret_from_syscall), %%g1\n\t"			\
@@ -209,14 +201,12 @@ static inline unsigned long xchg32(__volatile__ unsigned int *m, unsigned int va
 	unsigned long tmp1, tmp2;
 
 	__asm__ __volatile__(
-"	membar		#StoreLoad | #LoadLoad\n"
 "	mov		%0, %1\n"
 "1:	lduw		[%4], %2\n"
 "	cas		[%4], %2, %0\n"
 "	cmp		%2, %0\n"
 "	bne,a,pn	%%icc, 1b\n"
 "	 mov		%1, %0\n"
-"	membar		#StoreLoad | #StoreStore\n"
 	: "=&r" (val), "=&r" (tmp1), "=&r" (tmp2)
 	: "0" (val), "r" (m)
 	: "cc", "memory");
@@ -228,14 +218,12 @@ static inline unsigned long xchg64(__volatile__ unsigned long *m, unsigned long
 	unsigned long tmp1, tmp2;
 
 	__asm__ __volatile__(
-"	membar		#StoreLoad | #LoadLoad\n"
 "	mov		%0, %1\n"
 "1:	ldx		[%4], %2\n"
 "	casx		[%4], %2, %0\n"
 "	cmp		%2, %0\n"
 "	bne,a,pn	%%xcc, 1b\n"
 "	 mov		%1, %0\n"
-"	membar		#StoreLoad | #StoreStore\n"
 	: "=&r" (val), "=&r" (tmp1), "=&r" (tmp2)
 	: "0" (val), "r" (m)
 	: "cc", "memory");
@@ -272,9 +260,7 @@ extern void die_if_kernel(char *str, struct pt_regs *regs) __attribute__ ((noret
 static inline unsigned long
 __cmpxchg_u32(volatile int *m, int old, int new)
 {
-	__asm__ __volatile__("membar #StoreLoad | #LoadLoad\n"
-			     "cas [%2], %3, %0\n\t"
-			     "membar #StoreLoad | #StoreStore"
+	__asm__ __volatile__("cas [%2], %3, %0"
 			     : "=&r" (new)
 			     : "0" (new), "r" (m), "r" (old)
 			     : "memory");
@@ -285,9 +271,7 @@ __cmpxchg_u32(volatile int *m, int old, int new)
 static inline unsigned long
 __cmpxchg_u64(volatile long *m, unsigned long old, unsigned long new)
 {
-	__asm__ __volatile__("membar #StoreLoad | #LoadLoad\n"
-			     "casx [%2], %3, %0\n\t"
-			     "membar #StoreLoad | #StoreStore"
+	__asm__ __volatile__("casx [%2], %3, %0"
 			     : "=&r" (new)
 			     : "0" (new), "r" (m), "r" (old)
 			     : "memory");
diff --git a/arch/sparc/include/asm/tsb.h b/arch/sparc/include/asm/tsb.h
index 76e4299dd9bc..83c571d8c8a7 100644
--- a/arch/sparc/include/asm/tsb.h
+++ b/arch/sparc/include/asm/tsb.h
@@ -50,8 +50,6 @@
 #define TSB_TAG_INVALID_BIT	46
 #define TSB_TAG_INVALID_HIGH	(1 << (TSB_TAG_INVALID_BIT - 32))
 
-#define TSB_MEMBAR	membar	#StoreStore
-
 /* Some cpus support physical address quad loads.  We want to use
  * those if possible so we don't need to hard-lock the TSB mapping
  * into the TLB.  We encode some instruction patching in order to
@@ -128,13 +126,11 @@ extern struct tsb_phys_patch_entry __tsb_phys_patch, __tsb_phys_patch_end;
 	cmp	REG1, REG2;		\
 	bne,pn	%icc, 99b;		\
 	 nop;				\
-	TSB_MEMBAR
 
 #define TSB_WRITE(TSB, TTE, TAG) \
 	add	TSB, 0x8, TSB;   \
 	TSB_STORE(TSB, TTE);     \
 	sub	TSB, 0x8, TSB;   \
-	TSB_MEMBAR;              \
 	TSB_STORE(TSB, TAG);
 
 #define KTSB_LOAD_QUAD(TSB, REG) \
@@ -153,13 +149,11 @@ extern struct tsb_phys_patch_entry __tsb_phys_patch, __tsb_phys_patch_end;
 	cmp	REG1, REG2;		\
 	bne,pn	%icc, 99b;		\
 	 nop;				\
-	TSB_MEMBAR
 
 #define KTSB_WRITE(TSB, TTE, TAG) \
 	add	TSB, 0x8, TSB;   \
 	stxa	TTE, [TSB] ASI_N;     \
 	sub	TSB, 0x8, TSB;   \
-	TSB_MEMBAR;              \
 	stxa	TAG, [TSB] ASI_N;
 
 	/* Do a kernel page table walk.  Leaves physical PTE pointer in
diff --git a/arch/sparc/include/asm/ttable.h b/arch/sparc/include/asm/ttable.h
index 5708ba2719fb..48f2807d3265 100644
--- a/arch/sparc/include/asm/ttable.h
+++ b/arch/sparc/include/asm/ttable.h
@@ -2,6 +2,7 @@
 #define _SPARC64_TTABLE_H
 
 #include <asm/utrap.h>
+#include <asm/pil.h>
 
 #ifdef __ASSEMBLY__
 #include <asm/thread_info.h>
@@ -123,7 +124,7 @@
 
 #define TRAP_IRQ(routine, level)			\
 	rdpr	%pil, %g2;				\
-	wrpr	%g0, 15, %pil;				\
+	wrpr	%g0, PIL_NORMAL_MAX, %pil;		\
 	sethi	%hi(1f-4), %g7;				\
 	ba,pt	%xcc, etrap_irq;			\
 	 or	%g7, %lo(1f-4), %g7;			\
@@ -143,7 +144,7 @@
 
 #define TRAP_IRQ(routine, level)			\
 	rdpr	%pil, %g2;				\
-	wrpr	%g0, 15, %pil;				\
+	wrpr	%g0, PIL_NORMAL_MAX, %pil;		\
 	ba,pt	%xcc, etrap_irq;			\
 	 rd	%pc, %g7;				\
 	mov	level, %o0;				\
@@ -153,6 +154,16 @@
 
 #endif
 
+#define TRAP_NMI_IRQ(routine, level)			\
+	rdpr	%pil, %g2;				\
+	wrpr	%g0, PIL_NMI, %pil;			\
+	ba,pt	%xcc, etrap_irq;			\
+	 rd	%pc, %g7;				\
+	mov	level, %o0;				\
+	call	routine;				\
+	 add	%sp, PTREGS_OFF, %o1;			\
+	ba,a,pt	%xcc, rtrap_nmi;
+
 #define TRAP_IVEC TRAP_NOSAVE(do_ivec)
 
 #define BTRAP(lvl) TRAP_ARG(bad_trap, lvl)
diff --git a/arch/sparc/include/asm/unistd.h b/arch/sparc/include/asm/unistd.h
index 4207fb362da0..031f038b19f7 100644
--- a/arch/sparc/include/asm/unistd.h
+++ b/arch/sparc/include/asm/unistd.h
@@ -1,8 +1,444 @@
-#ifndef ___ASM_SPARC_UNISTD_H
-#define ___ASM_SPARC_UNISTD_H
-#if defined(__sparc__) && defined(__arch64__)
-#include <asm/unistd_64.h>
+#ifndef _SPARC_UNISTD_H
+#define _SPARC_UNISTD_H
+
+/*
+ * System calls under the Sparc.
+ *
+ * Don't be scared by the ugly clobbers, it is the only way I can
+ * think of right now to force the arguments into fixed registers
+ * before the trap into the system call with gcc 'asm' statements.
+ *
+ * Copyright (C) 1995, 2007 David S. Miller (davem@davemloft.net)
+ *
+ * SunOS compatibility based upon preliminary work which is:
+ *
+ * Copyright (C) 1995 Adrian M. Rodriguez (adrian@remus.rutgers.edu)
+ */
+#ifndef __32bit_syscall_numbers__
+#ifndef __arch64__
+#define __32bit_syscall_numbers__
+#endif
+#endif
+
+#define __NR_restart_syscall      0 /* Linux Specific				   */
+#define __NR_exit                 1 /* Common                                      */
+#define __NR_fork                 2 /* Common                                      */
+#define __NR_read                 3 /* Common                                      */
+#define __NR_write                4 /* Common                                      */
+#define __NR_open                 5 /* Common                                      */
+#define __NR_close                6 /* Common                                      */
+#define __NR_wait4                7 /* Common                                      */
+#define __NR_creat                8 /* Common                                      */
+#define __NR_link                 9 /* Common                                      */
+#define __NR_unlink              10 /* Common                                      */
+#define __NR_execv               11 /* SunOS Specific                              */
+#define __NR_chdir               12 /* Common                                      */
+#define __NR_chown		 13 /* Common					   */
+#define __NR_mknod               14 /* Common                                      */
+#define __NR_chmod               15 /* Common                                      */
+#define __NR_lchown              16 /* Common                                      */
+#define __NR_brk                 17 /* Common                                      */
+#define __NR_perfctr             18 /* Performance counter operations              */
+#define __NR_lseek               19 /* Common                                      */
+#define __NR_getpid              20 /* Common                                      */
+#define __NR_capget		 21 /* Linux Specific				   */
+#define __NR_capset		 22 /* Linux Specific				   */
+#define __NR_setuid              23 /* Implemented via setreuid in SunOS           */
+#define __NR_getuid              24 /* Common                                      */
+#define __NR_vmsplice	         25 /* ENOSYS under SunOS			   */
+#define __NR_ptrace              26 /* Common                                      */
+#define __NR_alarm               27 /* Implemented via setitimer in SunOS          */
+#define __NR_sigaltstack	 28 /* Common					   */
+#define __NR_pause               29 /* Is sigblock(0)->sigpause() in SunOS         */
+#define __NR_utime               30 /* Implemented via utimes() under SunOS        */
+#ifdef __32bit_syscall_numbers__
+#define __NR_lchown32            31 /* Linux sparc32 specific                      */
+#define __NR_fchown32            32 /* Linux sparc32 specific                      */
+#endif
+#define __NR_access              33 /* Common                                      */
+#define __NR_nice                34 /* Implemented via get/setpriority() in SunOS  */
+#ifdef __32bit_syscall_numbers__
+#define __NR_chown32             35 /* Linux sparc32 specific                      */
+#endif
+#define __NR_sync                36 /* Common                                      */
+#define __NR_kill                37 /* Common                                      */
+#define __NR_stat                38 /* Common                                      */
+#define __NR_sendfile		 39 /* Linux Specific				   */
+#define __NR_lstat               40 /* Common                                      */
+#define __NR_dup                 41 /* Common                                      */
+#define __NR_pipe                42 /* Common                                      */
+#define __NR_times               43 /* Implemented via getrusage() in SunOS        */
+#ifdef __32bit_syscall_numbers__
+#define __NR_getuid32            44 /* Linux sparc32 specific                      */
+#endif
+#define __NR_umount2             45 /* Linux Specific                              */
+#define __NR_setgid              46 /* Implemented via setregid() in SunOS         */
+#define __NR_getgid              47 /* Common                                      */
+#define __NR_signal              48 /* Implemented via sigvec() in SunOS           */
+#define __NR_geteuid             49 /* SunOS calls getuid()                        */
+#define __NR_getegid             50 /* SunOS calls getgid()                        */
+#define __NR_acct                51 /* Common                                      */
+#ifdef __32bit_syscall_numbers__
+#define __NR_getgid32            53 /* Linux sparc32 specific                      */
+#else
+#define __NR_memory_ordering	 52 /* Linux Specific				   */
+#endif
+#define __NR_ioctl               54 /* Common                                      */
+#define __NR_reboot              55 /* Common                                      */
+#ifdef __32bit_syscall_numbers__
+#define __NR_mmap2		 56 /* Linux sparc32 Specific			   */
+#endif
+#define __NR_symlink             57 /* Common                                      */
+#define __NR_readlink            58 /* Common                                      */
+#define __NR_execve              59 /* Common                                      */
+#define __NR_umask               60 /* Common                                      */
+#define __NR_chroot              61 /* Common                                      */
+#define __NR_fstat               62 /* Common                                      */
+#define __NR_fstat64		 63 /* Linux Specific			           */
+#define __NR_getpagesize         64 /* Common                                      */
+#define __NR_msync               65 /* Common in newer 1.3.x revs...               */
+#define __NR_vfork               66 /* Common                                      */
+#define __NR_pread64             67 /* Linux Specific                              */
+#define __NR_pwrite64            68 /* Linux Specific                              */
+#ifdef __32bit_syscall_numbers__
+#define __NR_geteuid32           69 /* Linux sparc32, sbrk under SunOS             */
+#define __NR_getegid32           70 /* Linux sparc32, sstk under SunOS             */
+#endif
+#define __NR_mmap                71 /* Common                                      */
+#ifdef __32bit_syscall_numbers__
+#define __NR_setreuid32          72 /* Linux sparc32, vadvise under SunOS          */
+#endif
+#define __NR_munmap              73 /* Common                                      */
+#define __NR_mprotect            74 /* Common                                      */
+#define __NR_madvise             75 /* Common                                      */
+#define __NR_vhangup             76 /* Common                                      */
+#ifdef __32bit_syscall_numbers__
+#define __NR_truncate64		 77 /* Linux sparc32 Specific			   */
+#endif
+#define __NR_mincore             78 /* Common                                      */
+#define __NR_getgroups           79 /* Common                                      */
+#define __NR_setgroups           80 /* Common                                      */
+#define __NR_getpgrp             81 /* Common                                      */
+#ifdef __32bit_syscall_numbers__
+#define __NR_setgroups32         82 /* Linux sparc32, setpgrp under SunOS          */
+#endif
+#define __NR_setitimer           83 /* Common                                      */
+#ifdef __32bit_syscall_numbers__
+#define __NR_ftruncate64	 84 /* Linux sparc32 Specific			   */
+#endif
+#define __NR_swapon              85 /* Common                                      */
+#define __NR_getitimer           86 /* Common                                      */
+#ifdef __32bit_syscall_numbers__
+#define __NR_setuid32            87 /* Linux sparc32, gethostname under SunOS      */
+#endif
+#define __NR_sethostname         88 /* Common                                      */
+#ifdef __32bit_syscall_numbers__
+#define __NR_setgid32            89 /* Linux sparc32, getdtablesize under SunOS    */
+#endif
+#define __NR_dup2                90 /* Common                                      */
+#ifdef __32bit_syscall_numbers__
+#define __NR_setfsuid32          91 /* Linux sparc32, getdopt under SunOS          */
+#endif
+#define __NR_fcntl               92 /* Common                                      */
+#define __NR_select              93 /* Common                                      */
+#ifdef __32bit_syscall_numbers__
+#define __NR_setfsgid32          94 /* Linux sparc32, setdopt under SunOS          */
+#endif
+#define __NR_fsync               95 /* Common                                      */
+#define __NR_setpriority         96 /* Common                                      */
+#define __NR_socket              97 /* Common                                      */
+#define __NR_connect             98 /* Common                                      */
+#define __NR_accept              99 /* Common                                      */
+#define __NR_getpriority        100 /* Common                                      */
+#define __NR_rt_sigreturn       101 /* Linux Specific                              */
+#define __NR_rt_sigaction       102 /* Linux Specific                              */
+#define __NR_rt_sigprocmask     103 /* Linux Specific                              */
+#define __NR_rt_sigpending      104 /* Linux Specific                              */
+#define __NR_rt_sigtimedwait    105 /* Linux Specific                              */
+#define __NR_rt_sigqueueinfo    106 /* Linux Specific                              */
+#define __NR_rt_sigsuspend      107 /* Linux Specific                              */
+#ifdef __32bit_syscall_numbers__
+#define __NR_setresuid32        108 /* Linux Specific, sigvec under SunOS	   */
+#define __NR_getresuid32        109 /* Linux Specific, sigblock under SunOS	   */
+#define __NR_setresgid32        110 /* Linux Specific, sigsetmask under SunOS	   */
+#define __NR_getresgid32        111 /* Linux Specific, sigpause under SunOS	   */
+#define __NR_setregid32         112 /* Linux sparc32, sigstack under SunOS         */
+#else
+#define __NR_setresuid          108 /* Linux Specific, sigvec under SunOS	   */
+#define __NR_getresuid          109 /* Linux Specific, sigblock under SunOS	   */
+#define __NR_setresgid          110 /* Linux Specific, sigsetmask under SunOS	   */
+#define __NR_getresgid          111 /* Linux Specific, sigpause under SunOS	   */
+#endif
+#define __NR_recvmsg            113 /* Common                                      */
+#define __NR_sendmsg            114 /* Common                                      */
+#ifdef __32bit_syscall_numbers__
+#define __NR_getgroups32        115 /* Linux sparc32, vtrace under SunOS           */
+#endif
+#define __NR_gettimeofday       116 /* Common                                      */
+#define __NR_getrusage          117 /* Common                                      */
+#define __NR_getsockopt         118 /* Common                                      */
+#define __NR_getcwd		119 /* Linux Specific				   */
+#define __NR_readv              120 /* Common                                      */
+#define __NR_writev             121 /* Common                                      */
+#define __NR_settimeofday       122 /* Common                                      */
+#define __NR_fchown             123 /* Common                                      */
+#define __NR_fchmod             124 /* Common                                      */
+#define __NR_recvfrom           125 /* Common                                      */
+#define __NR_setreuid           126 /* Common                                      */
+#define __NR_setregid           127 /* Common                                      */
+#define __NR_rename             128 /* Common                                      */
+#define __NR_truncate           129 /* Common                                      */
+#define __NR_ftruncate          130 /* Common                                      */
+#define __NR_flock              131 /* Common                                      */
+#define __NR_lstat64		132 /* Linux Specific			           */
+#define __NR_sendto             133 /* Common                                      */
+#define __NR_shutdown           134 /* Common                                      */
+#define __NR_socketpair         135 /* Common                                      */
+#define __NR_mkdir              136 /* Common                                      */
+#define __NR_rmdir              137 /* Common                                      */
+#define __NR_utimes             138 /* SunOS Specific                              */
+#define __NR_stat64		139 /* Linux Specific			           */
+#define __NR_sendfile64         140 /* adjtime under SunOS                         */
+#define __NR_getpeername        141 /* Common                                      */
+#define __NR_futex              142 /* gethostid under SunOS                       */
+#define __NR_gettid             143 /* ENOSYS under SunOS                          */
+#define __NR_getrlimit		144 /* Common                                      */
+#define __NR_setrlimit          145 /* Common                                      */
+#define __NR_pivot_root		146 /* Linux Specific, killpg under SunOS          */
+#define __NR_prctl		147 /* ENOSYS under SunOS                          */
+#define __NR_pciconfig_read	148 /* ENOSYS under SunOS                          */
+#define __NR_pciconfig_write	149 /* ENOSYS under SunOS                          */
+#define __NR_getsockname        150 /* Common                                      */
+#define __NR_inotify_init       151 /* Linux specific                              */
+#define __NR_inotify_add_watch  152 /* Linux specific                              */
+#define __NR_poll               153 /* Common                                      */
+#define __NR_getdents64		154 /* Linux specific				   */
+#ifdef __32bit_syscall_numbers__
+#define __NR_fcntl64		155 /* Linux sparc32 Specific                      */
+#endif
+#define __NR_inotify_rm_watch   156 /* Linux specific				   */
+#define __NR_statfs             157 /* Common                                      */
+#define __NR_fstatfs            158 /* Common                                      */
+#define __NR_umount             159 /* Common                                      */
+#define __NR_sched_set_affinity 160 /* Linux specific, async_daemon under SunOS    */
+#define __NR_sched_get_affinity 161 /* Linux specific, getfh under SunOS           */
+#define __NR_getdomainname      162 /* SunOS Specific                              */
+#define __NR_setdomainname      163 /* Common                                      */
+#ifndef __32bit_syscall_numbers__
+#define __NR_utrap_install	164 /* SYSV ABI/v9 required			   */
+#endif
+#define __NR_quotactl           165 /* Common                                      */
+#define __NR_set_tid_address    166 /* Linux specific, exportfs under SunOS        */
+#define __NR_mount              167 /* Common                                      */
+#define __NR_ustat              168 /* Common                                      */
+#define __NR_setxattr           169 /* SunOS: semsys                               */
+#define __NR_lsetxattr          170 /* SunOS: msgsys                               */
+#define __NR_fsetxattr          171 /* SunOS: shmsys                               */
+#define __NR_getxattr           172 /* SunOS: auditsys                             */
+#define __NR_lgetxattr          173 /* SunOS: rfssys                               */
+#define __NR_getdents           174 /* Common                                      */
+#define __NR_setsid             175 /* Common                                      */
+#define __NR_fchdir             176 /* Common                                      */
+#define __NR_fgetxattr          177 /* SunOS: fchroot                              */
+#define __NR_listxattr          178 /* SunOS: vpixsys                              */
+#define __NR_llistxattr         179 /* SunOS: aioread                              */
+#define __NR_flistxattr         180 /* SunOS: aiowrite                             */
+#define __NR_removexattr        181 /* SunOS: aiowait                              */
+#define __NR_lremovexattr       182 /* SunOS: aiocancel                            */
+#define __NR_sigpending         183 /* Common                                      */
+#define __NR_query_module	184 /* Linux Specific				   */
+#define __NR_setpgid            185 /* Common                                      */
+#define __NR_fremovexattr       186 /* SunOS: pathconf                             */
+#define __NR_tkill              187 /* SunOS: fpathconf                            */
+#define __NR_exit_group		188 /* Linux specific, sysconf undef SunOS         */
+#define __NR_uname              189 /* Linux Specific                              */
+#define __NR_init_module        190 /* Linux Specific                              */
+#define __NR_personality        191 /* Linux Specific                              */
+#define __NR_remap_file_pages   192 /* Linux Specific                              */
+#define __NR_epoll_create       193 /* Linux Specific                              */
+#define __NR_epoll_ctl          194 /* Linux Specific                              */
+#define __NR_epoll_wait         195 /* Linux Specific                              */
+#define __NR_ioprio_set         196 /* Linux Specific                              */
+#define __NR_getppid            197 /* Linux Specific                              */
+#define __NR_sigaction          198 /* Linux Specific                              */
+#define __NR_sgetmask           199 /* Linux Specific                              */
+#define __NR_ssetmask           200 /* Linux Specific                              */
+#define __NR_sigsuspend         201 /* Linux Specific                              */
+#define __NR_oldlstat           202 /* Linux Specific                              */
+#define __NR_uselib             203 /* Linux Specific                              */
+#define __NR_readdir            204 /* Linux Specific                              */
+#define __NR_readahead          205 /* Linux Specific                              */
+#define __NR_socketcall         206 /* Linux Specific                              */
+#define __NR_syslog             207 /* Linux Specific                              */
+#define __NR_lookup_dcookie     208 /* Linux Specific                              */
+#define __NR_fadvise64          209 /* Linux Specific                              */
+#define __NR_fadvise64_64       210 /* Linux Specific                              */
+#define __NR_tgkill             211 /* Linux Specific                              */
+#define __NR_waitpid            212 /* Linux Specific                              */
+#define __NR_swapoff            213 /* Linux Specific                              */
+#define __NR_sysinfo            214 /* Linux Specific                              */
+#define __NR_ipc                215 /* Linux Specific                              */
+#define __NR_sigreturn          216 /* Linux Specific                              */
+#define __NR_clone              217 /* Linux Specific                              */
+#define __NR_ioprio_get         218 /* Linux Specific                              */
+#define __NR_adjtimex           219 /* Linux Specific                              */
+#define __NR_sigprocmask        220 /* Linux Specific                              */
+#define __NR_create_module      221 /* Linux Specific                              */
+#define __NR_delete_module      222 /* Linux Specific                              */
+#define __NR_get_kernel_syms    223 /* Linux Specific                              */
+#define __NR_getpgid            224 /* Linux Specific                              */
+#define __NR_bdflush            225 /* Linux Specific                              */
+#define __NR_sysfs              226 /* Linux Specific                              */
+#define __NR_afs_syscall        227 /* Linux Specific                              */
+#define __NR_setfsuid           228 /* Linux Specific                              */
+#define __NR_setfsgid           229 /* Linux Specific                              */
+#define __NR__newselect         230 /* Linux Specific                              */
+#ifdef __32bit_syscall_numbers__
+#define __NR_time               231 /* Linux Specific                              */
 #else
-#include <asm/unistd_32.h>
+#ifdef __KERNEL__
+#define __NR_time		231 /* Linux sparc32                               */
+#endif
+#endif
+#define __NR_splice             232 /* Linux Specific                              */
+#define __NR_stime              233 /* Linux Specific                              */
+#define __NR_statfs64           234 /* Linux Specific                              */
+#define __NR_fstatfs64          235 /* Linux Specific                              */
+#define __NR__llseek            236 /* Linux Specific                              */
+#define __NR_mlock              237
+#define __NR_munlock            238
+#define __NR_mlockall           239
+#define __NR_munlockall         240
+#define __NR_sched_setparam     241
+#define __NR_sched_getparam     242
+#define __NR_sched_setscheduler 243
+#define __NR_sched_getscheduler 244
+#define __NR_sched_yield        245
+#define __NR_sched_get_priority_max 246
+#define __NR_sched_get_priority_min 247
+#define __NR_sched_rr_get_interval  248
+#define __NR_nanosleep          249
+#define __NR_mremap             250
+#define __NR__sysctl            251
+#define __NR_getsid             252
+#define __NR_fdatasync          253
+#define __NR_nfsservctl         254
+#define __NR_sync_file_range	255
+#define __NR_clock_settime	256
+#define __NR_clock_gettime	257
+#define __NR_clock_getres	258
+#define __NR_clock_nanosleep	259
+#define __NR_sched_getaffinity	260
+#define __NR_sched_setaffinity	261
+#define __NR_timer_settime	262
+#define __NR_timer_gettime	263
+#define __NR_timer_getoverrun	264
+#define __NR_timer_delete	265
+#define __NR_timer_create	266
+/* #define __NR_vserver		267 Reserved for VSERVER */
+#define __NR_io_setup		268
+#define __NR_io_destroy		269
+#define __NR_io_submit		270
+#define __NR_io_cancel		271
+#define __NR_io_getevents	272
+#define __NR_mq_open		273
+#define __NR_mq_unlink		274
+#define __NR_mq_timedsend	275
+#define __NR_mq_timedreceive	276
+#define __NR_mq_notify		277
+#define __NR_mq_getsetattr	278
+#define __NR_waitid		279
+#define __NR_tee		280
+#define __NR_add_key		281
+#define __NR_request_key	282
+#define __NR_keyctl		283
+#define __NR_openat		284
+#define __NR_mkdirat		285
+#define __NR_mknodat		286
+#define __NR_fchownat		287
+#define __NR_futimesat		288
+#define __NR_fstatat64		289
+#define __NR_unlinkat		290
+#define __NR_renameat		291
+#define __NR_linkat		292
+#define __NR_symlinkat		293
+#define __NR_readlinkat		294
+#define __NR_fchmodat		295
+#define __NR_faccessat		296
+#define __NR_pselect6		297
+#define __NR_ppoll		298
+#define __NR_unshare		299
+#define __NR_set_robust_list	300
+#define __NR_get_robust_list	301
+#define __NR_migrate_pages	302
+#define __NR_mbind		303
+#define __NR_get_mempolicy	304
+#define __NR_set_mempolicy	305
+#define __NR_kexec_load		306
+#define __NR_move_pages		307
+#define __NR_getcpu		308
+#define __NR_epoll_pwait	309
+#define __NR_utimensat		310
+#define __NR_signalfd		311
+#define __NR_timerfd_create	312
+#define __NR_eventfd		313
+#define __NR_fallocate		314
+#define __NR_timerfd_settime	315
+#define __NR_timerfd_gettime	316
+#define __NR_signalfd4		317
+#define __NR_eventfd2		318
+#define __NR_epoll_create1	319
+#define __NR_dup3		320
+#define __NR_pipe2		321
+#define __NR_inotify_init1	322
+#define __NR_accept4		323
+
+#define NR_SYSCALLS		324
+
+#ifdef __32bit_syscall_numbers__
+/* Sparc 32-bit only has the "setresuid32", "getresuid32" variants,
+ * it never had the plain ones and there is no value to adding those
+ * old versions into the syscall table.
+ */
+#define __IGNORE_setresuid
+#define __IGNORE_getresuid
+#define __IGNORE_setresgid
+#define __IGNORE_getresgid
 #endif
+
+#ifdef __KERNEL__
+#define __ARCH_WANT_IPC_PARSE_VERSION
+#define __ARCH_WANT_OLD_READDIR
+#define __ARCH_WANT_STAT64
+#define __ARCH_WANT_SYS_ALARM
+#define __ARCH_WANT_SYS_GETHOSTNAME
+#define __ARCH_WANT_SYS_PAUSE
+#define __ARCH_WANT_SYS_SGETMASK
+#define __ARCH_WANT_SYS_SIGNAL
+#define __ARCH_WANT_SYS_TIME
+#define __ARCH_WANT_SYS_UTIME
+#define __ARCH_WANT_SYS_WAITPID
+#define __ARCH_WANT_SYS_SOCKETCALL
+#define __ARCH_WANT_SYS_FADVISE64
+#define __ARCH_WANT_SYS_GETPGRP
+#define __ARCH_WANT_SYS_LLSEEK
+#define __ARCH_WANT_SYS_NICE
+#define __ARCH_WANT_SYS_OLDUMOUNT
+#define __ARCH_WANT_SYS_SIGPENDING
+#define __ARCH_WANT_SYS_SIGPROCMASK
+#define __ARCH_WANT_SYS_RT_SIGSUSPEND
+#ifndef __32bit_syscall_numbers__
+#define __ARCH_WANT_COMPAT_SYS_TIME
+#define __ARCH_WANT_COMPAT_SYS_RT_SIGSUSPEND
 #endif
+
+/*
+ * "Conditional" syscalls
+ *
+ * What we want is __attribute__((weak,alias("sys_ni_syscall"))),
+ * but it doesn't work on all toolchains, so we just do it by hand
+ */
+#define cond_syscall(x) asm(".weak\t" #x "\n\t.set\t" #x ",sys_ni_syscall")
+
+#endif /* __KERNEL__ */
+#endif /* _SPARC_UNISTD_H */
diff --git a/arch/sparc/include/asm/unistd_32.h b/arch/sparc/include/asm/unistd_32.h
deleted file mode 100644
index 0d13d2a4c76f..000000000000
--- a/arch/sparc/include/asm/unistd_32.h
+++ /dev/null
@@ -1,385 +0,0 @@
-#ifndef _SPARC_UNISTD_H
-#define _SPARC_UNISTD_H
-
-/*
- * System calls under the Sparc.
- *
- * Don't be scared by the ugly clobbers, it is the only way I can
- * think of right now to force the arguments into fixed registers
- * before the trap into the system call with gcc 'asm' statements.
- *
- * Copyright (C) 1995, 2007 David S. Miller (davem@davemloft.net)
- *
- * SunOS compatibility based upon preliminary work which is:
- *
- * Copyright (C) 1995 Adrian M. Rodriguez (adrian@remus.rutgers.edu)
- */
-
-#define __NR_restart_syscall      0 /* Linux Specific				   */
-#define __NR_exit                 1 /* Common                                      */
-#define __NR_fork                 2 /* Common                                      */
-#define __NR_read                 3 /* Common                                      */
-#define __NR_write                4 /* Common                                      */
-#define __NR_open                 5 /* Common                                      */
-#define __NR_close                6 /* Common                                      */
-#define __NR_wait4                7 /* Common                                      */
-#define __NR_creat                8 /* Common                                      */
-#define __NR_link                 9 /* Common                                      */
-#define __NR_unlink              10 /* Common                                      */
-#define __NR_execv               11 /* SunOS Specific                              */
-#define __NR_chdir               12 /* Common                                      */
-#define __NR_chown		 13 /* Common					   */
-#define __NR_mknod               14 /* Common                                      */
-#define __NR_chmod               15 /* Common                                      */
-#define __NR_lchown              16 /* Common                                      */
-#define __NR_brk                 17 /* Common                                      */
-#define __NR_perfctr             18 /* Performance counter operations              */
-#define __NR_lseek               19 /* Common                                      */
-#define __NR_getpid              20 /* Common                                      */
-#define __NR_capget		 21 /* Linux Specific				   */
-#define __NR_capset		 22 /* Linux Specific				   */
-#define __NR_setuid              23 /* Implemented via setreuid in SunOS           */
-#define __NR_getuid              24 /* Common                                      */
-#define __NR_vmsplice	         25 /* ENOSYS under SunOS			   */
-#define __NR_ptrace              26 /* Common                                      */
-#define __NR_alarm               27 /* Implemented via setitimer in SunOS          */
-#define __NR_sigaltstack	 28 /* Common					   */
-#define __NR_pause               29 /* Is sigblock(0)->sigpause() in SunOS         */
-#define __NR_utime               30 /* Implemented via utimes() under SunOS        */
-#define __NR_lchown32            31 /* Linux sparc32 specific                      */
-#define __NR_fchown32            32 /* Linux sparc32 specific                      */
-#define __NR_access              33 /* Common                                      */
-#define __NR_nice                34 /* Implemented via get/setpriority() in SunOS  */
-#define __NR_chown32             35 /* Linux sparc32 specific                      */
-#define __NR_sync                36 /* Common                                      */
-#define __NR_kill                37 /* Common                                      */
-#define __NR_stat                38 /* Common                                      */
-#define __NR_sendfile		 39 /* Linux Specific				   */
-#define __NR_lstat               40 /* Common                                      */
-#define __NR_dup                 41 /* Common                                      */
-#define __NR_pipe                42 /* Common                                      */
-#define __NR_times               43 /* Implemented via getrusage() in SunOS        */
-#define __NR_getuid32            44 /* Linux sparc32 specific                      */
-#define __NR_umount2             45 /* Linux Specific                              */
-#define __NR_setgid              46 /* Implemented via setregid() in SunOS         */
-#define __NR_getgid              47 /* Common                                      */
-#define __NR_signal              48 /* Implemented via sigvec() in SunOS           */
-#define __NR_geteuid             49 /* SunOS calls getuid()                        */
-#define __NR_getegid             50 /* SunOS calls getgid()                        */
-#define __NR_acct                51 /* Common                                      */
-/* #define __NR_memory_ordering  52    Linux sparc64 specific			   */
-#define __NR_getgid32            53 /* Linux sparc32 specific                      */
-#define __NR_ioctl               54 /* Common                                      */
-#define __NR_reboot              55 /* Common                                      */
-#define __NR_mmap2		 56 /* Linux sparc32 Specific			   */
-#define __NR_symlink             57 /* Common                                      */
-#define __NR_readlink            58 /* Common                                      */
-#define __NR_execve              59 /* Common                                      */
-#define __NR_umask               60 /* Common                                      */
-#define __NR_chroot              61 /* Common                                      */
-#define __NR_fstat               62 /* Common                                      */
-#define __NR_fstat64		 63 /* Linux Specific			           */
-#define __NR_getpagesize         64 /* Common                                      */
-#define __NR_msync               65 /* Common in newer 1.3.x revs...               */
-#define __NR_vfork               66 /* Common                                      */
-#define __NR_pread64             67 /* Linux Specific                              */
-#define __NR_pwrite64            68 /* Linux Specific                              */
-#define __NR_geteuid32           69 /* Linux sparc32, sbrk under SunOS             */
-#define __NR_getegid32           70 /* Linux sparc32, sstk under SunOS             */
-#define __NR_mmap                71 /* Common                                      */
-#define __NR_setreuid32          72 /* Linux sparc32, vadvise under SunOS          */
-#define __NR_munmap              73 /* Common                                      */
-#define __NR_mprotect            74 /* Common                                      */
-#define __NR_madvise             75 /* Common                                      */
-#define __NR_vhangup             76 /* Common                                      */
-#define __NR_truncate64		 77 /* Linux sparc32 Specific			   */
-#define __NR_mincore             78 /* Common                                      */
-#define __NR_getgroups           79 /* Common                                      */
-#define __NR_setgroups           80 /* Common                                      */
-#define __NR_getpgrp             81 /* Common                                      */
-#define __NR_setgroups32         82 /* Linux sparc32, setpgrp under SunOS          */
-#define __NR_setitimer           83 /* Common                                      */
-#define __NR_ftruncate64	 84 /* Linux sparc32 Specific			   */
-#define __NR_swapon              85 /* Common                                      */
-#define __NR_getitimer           86 /* Common                                      */
-#define __NR_setuid32            87 /* Linux sparc32, gethostname under SunOS      */
-#define __NR_sethostname         88 /* Common                                      */
-#define __NR_setgid32            89 /* Linux sparc32, getdtablesize under SunOS    */
-#define __NR_dup2                90 /* Common                                      */
-#define __NR_setfsuid32          91 /* Linux sparc32, getdopt under SunOS          */
-#define __NR_fcntl               92 /* Common                                      */
-#define __NR_select              93 /* Common                                      */
-#define __NR_setfsgid32          94 /* Linux sparc32, setdopt under SunOS          */
-#define __NR_fsync               95 /* Common                                      */
-#define __NR_setpriority         96 /* Common                                      */
-#define __NR_socket              97 /* Common                                      */
-#define __NR_connect             98 /* Common                                      */
-#define __NR_accept              99 /* Common                                      */
-#define __NR_getpriority        100 /* Common                                      */
-#define __NR_rt_sigreturn       101 /* Linux Specific                              */
-#define __NR_rt_sigaction       102 /* Linux Specific                              */
-#define __NR_rt_sigprocmask     103 /* Linux Specific                              */
-#define __NR_rt_sigpending      104 /* Linux Specific                              */
-#define __NR_rt_sigtimedwait    105 /* Linux Specific                              */
-#define __NR_rt_sigqueueinfo    106 /* Linux Specific                              */
-#define __NR_rt_sigsuspend      107 /* Linux Specific                              */
-#define __NR_setresuid32        108 /* Linux Specific, sigvec under SunOS	   */
-#define __NR_getresuid32        109 /* Linux Specific, sigblock under SunOS	   */
-#define __NR_setresgid32        110 /* Linux Specific, sigsetmask under SunOS	   */
-#define __NR_getresgid32        111 /* Linux Specific, sigpause under SunOS	   */
-#define __NR_setregid32         112 /* Linux sparc32, sigstack under SunOS         */
-#define __NR_recvmsg            113 /* Common                                      */
-#define __NR_sendmsg            114 /* Common                                      */
-#define __NR_getgroups32        115 /* Linux sparc32, vtrace under SunOS           */
-#define __NR_gettimeofday       116 /* Common                                      */
-#define __NR_getrusage          117 /* Common                                      */
-#define __NR_getsockopt         118 /* Common                                      */
-#define __NR_getcwd		119 /* Linux Specific				   */
-#define __NR_readv              120 /* Common                                      */
-#define __NR_writev             121 /* Common                                      */
-#define __NR_settimeofday       122 /* Common                                      */
-#define __NR_fchown             123 /* Common                                      */
-#define __NR_fchmod             124 /* Common                                      */
-#define __NR_recvfrom           125 /* Common                                      */
-#define __NR_setreuid           126 /* Common                                      */
-#define __NR_setregid           127 /* Common                                      */
-#define __NR_rename             128 /* Common                                      */
-#define __NR_truncate           129 /* Common                                      */
-#define __NR_ftruncate          130 /* Common                                      */
-#define __NR_flock              131 /* Common                                      */
-#define __NR_lstat64		132 /* Linux Specific			           */
-#define __NR_sendto             133 /* Common                                      */
-#define __NR_shutdown           134 /* Common                                      */
-#define __NR_socketpair         135 /* Common                                      */
-#define __NR_mkdir              136 /* Common                                      */
-#define __NR_rmdir              137 /* Common                                      */
-#define __NR_utimes             138 /* SunOS Specific                              */
-#define __NR_stat64		139 /* Linux Specific			           */
-#define __NR_sendfile64         140 /* adjtime under SunOS                         */
-#define __NR_getpeername        141 /* Common                                      */
-#define __NR_futex              142 /* gethostid under SunOS                       */
-#define __NR_gettid             143 /* ENOSYS under SunOS                          */
-#define __NR_getrlimit          144 /* Common                                      */
-#define __NR_setrlimit          145 /* Common                                      */
-#define __NR_pivot_root		146 /* Linux Specific, killpg under SunOS          */
-#define __NR_prctl		147 /* ENOSYS under SunOS                          */
-#define __NR_pciconfig_read	148 /* ENOSYS under SunOS                          */
-#define __NR_pciconfig_write	149 /* ENOSYS under SunOS                          */
-#define __NR_getsockname        150 /* Common                                      */
-#define __NR_inotify_init       151 /* Linux specific                              */
-#define __NR_inotify_add_watch  152 /* Linux specific                              */
-#define __NR_poll               153 /* Common                                      */
-#define __NR_getdents64		154 /* Linux specific				   */
-#define __NR_fcntl64		155 /* Linux sparc32 Specific                      */
-#define __NR_inotify_rm_watch   156 /* Linux specific				   */
-#define __NR_statfs             157 /* Common                                      */
-#define __NR_fstatfs            158 /* Common                                      */
-#define __NR_umount             159 /* Common                                      */
-#define __NR_sched_set_affinity 160 /* Linux specific, async_daemon under SunOS    */
-#define __NR_sched_get_affinity 161 /* Linux specific, getfh under SunOS           */
-#define __NR_getdomainname      162 /* SunOS Specific                              */
-#define __NR_setdomainname      163 /* Common                                      */
-/* #define __NR_utrap_install   164    Linux sparc64 specific			   */
-#define __NR_quotactl           165 /* Common                                      */
-#define __NR_set_tid_address    166 /* Linux specific, exportfs under SunOS        */
-#define __NR_mount              167 /* Common                                      */
-#define __NR_ustat              168 /* Common                                      */
-#define __NR_setxattr           169 /* SunOS: semsys                               */
-#define __NR_lsetxattr          170 /* SunOS: msgsys                               */
-#define __NR_fsetxattr          171 /* SunOS: shmsys                               */
-#define __NR_getxattr           172 /* SunOS: auditsys                             */
-#define __NR_lgetxattr          173 /* SunOS: rfssys                               */
-#define __NR_getdents           174 /* Common                                      */
-#define __NR_setsid             175 /* Common                                      */
-#define __NR_fchdir             176 /* Common                                      */
-#define __NR_fgetxattr          177 /* SunOS: fchroot                              */
-#define __NR_listxattr          178 /* SunOS: vpixsys                              */
-#define __NR_llistxattr         179 /* SunOS: aioread                              */
-#define __NR_flistxattr         180 /* SunOS: aiowrite                             */
-#define __NR_removexattr        181 /* SunOS: aiowait                              */
-#define __NR_lremovexattr       182 /* SunOS: aiocancel                            */
-#define __NR_sigpending         183 /* Common                                      */
-#define __NR_query_module	184 /* Linux Specific				   */
-#define __NR_setpgid            185 /* Common                                      */
-#define __NR_fremovexattr       186 /* SunOS: pathconf                             */
-#define __NR_tkill              187 /* SunOS: fpathconf                            */
-#define __NR_exit_group		188 /* Linux specific, sysconf undef SunOS         */
-#define __NR_uname              189 /* Linux Specific                              */
-#define __NR_init_module        190 /* Linux Specific                              */
-#define __NR_personality        191 /* Linux Specific                              */
-#define __NR_remap_file_pages   192 /* Linux Specific                              */
-#define __NR_epoll_create       193 /* Linux Specific                              */
-#define __NR_epoll_ctl          194 /* Linux Specific                              */
-#define __NR_epoll_wait         195 /* Linux Specific                              */
-#define __NR_ioprio_set         196 /* Linux Specific                              */
-#define __NR_getppid            197 /* Linux Specific                              */
-#define __NR_sigaction          198 /* Linux Specific                              */
-#define __NR_sgetmask           199 /* Linux Specific                              */
-#define __NR_ssetmask           200 /* Linux Specific                              */
-#define __NR_sigsuspend         201 /* Linux Specific                              */
-#define __NR_oldlstat           202 /* Linux Specific                              */
-#define __NR_uselib             203 /* Linux Specific                              */
-#define __NR_readdir            204 /* Linux Specific                              */
-#define __NR_readahead          205 /* Linux Specific                              */
-#define __NR_socketcall         206 /* Linux Specific                              */
-#define __NR_syslog             207 /* Linux Specific                              */
-#define __NR_lookup_dcookie     208 /* Linux Specific                              */
-#define __NR_fadvise64          209 /* Linux Specific                              */
-#define __NR_fadvise64_64       210 /* Linux Specific                              */
-#define __NR_tgkill             211 /* Linux Specific                              */
-#define __NR_waitpid            212 /* Linux Specific                              */
-#define __NR_swapoff            213 /* Linux Specific                              */
-#define __NR_sysinfo            214 /* Linux Specific                              */
-#define __NR_ipc                215 /* Linux Specific                              */
-#define __NR_sigreturn          216 /* Linux Specific                              */
-#define __NR_clone              217 /* Linux Specific                              */
-#define __NR_ioprio_get         218 /* Linux Specific                              */
-#define __NR_adjtimex           219 /* Linux Specific                              */
-#define __NR_sigprocmask        220 /* Linux Specific                              */
-#define __NR_create_module      221 /* Linux Specific                              */
-#define __NR_delete_module      222 /* Linux Specific                              */
-#define __NR_get_kernel_syms    223 /* Linux Specific                              */
-#define __NR_getpgid            224 /* Linux Specific                              */
-#define __NR_bdflush            225 /* Linux Specific                              */
-#define __NR_sysfs              226 /* Linux Specific                              */
-#define __NR_afs_syscall        227 /* Linux Specific                              */
-#define __NR_setfsuid           228 /* Linux Specific                              */
-#define __NR_setfsgid           229 /* Linux Specific                              */
-#define __NR__newselect         230 /* Linux Specific                              */
-#define __NR_time               231 /* Linux Specific                              */
-#define __NR_splice             232 /* Linux Specific                              */
-#define __NR_stime              233 /* Linux Specific                              */
-#define __NR_statfs64           234 /* Linux Specific                              */
-#define __NR_fstatfs64          235 /* Linux Specific                              */
-#define __NR__llseek            236 /* Linux Specific                              */
-#define __NR_mlock              237
-#define __NR_munlock            238
-#define __NR_mlockall           239
-#define __NR_munlockall         240
-#define __NR_sched_setparam     241
-#define __NR_sched_getparam     242
-#define __NR_sched_setscheduler 243
-#define __NR_sched_getscheduler 244
-#define __NR_sched_yield        245
-#define __NR_sched_get_priority_max 246
-#define __NR_sched_get_priority_min 247
-#define __NR_sched_rr_get_interval  248
-#define __NR_nanosleep          249
-#define __NR_mremap             250
-#define __NR__sysctl            251
-#define __NR_getsid             252
-#define __NR_fdatasync          253
-#define __NR_nfsservctl         254
-#define __NR_sync_file_range	255
-#define __NR_clock_settime	256
-#define __NR_clock_gettime	257
-#define __NR_clock_getres	258
-#define __NR_clock_nanosleep	259
-#define __NR_sched_getaffinity	260
-#define __NR_sched_setaffinity	261
-#define __NR_timer_settime	262
-#define __NR_timer_gettime	263
-#define __NR_timer_getoverrun	264
-#define __NR_timer_delete	265
-#define __NR_timer_create	266
-/* #define __NR_vserver		267 Reserved for VSERVER */
-#define __NR_io_setup		268
-#define __NR_io_destroy		269
-#define __NR_io_submit		270
-#define __NR_io_cancel		271
-#define __NR_io_getevents	272
-#define __NR_mq_open		273
-#define __NR_mq_unlink		274
-#define __NR_mq_timedsend	275
-#define __NR_mq_timedreceive	276
-#define __NR_mq_notify		277
-#define __NR_mq_getsetattr	278
-#define __NR_waitid		279
-#define __NR_tee		280
-#define __NR_add_key		281
-#define __NR_request_key	282
-#define __NR_keyctl		283
-#define __NR_openat		284
-#define __NR_mkdirat		285
-#define __NR_mknodat		286
-#define __NR_fchownat		287
-#define __NR_futimesat		288
-#define __NR_fstatat64		289
-#define __NR_unlinkat		290
-#define __NR_renameat		291
-#define __NR_linkat		292
-#define __NR_symlinkat		293
-#define __NR_readlinkat		294
-#define __NR_fchmodat		295
-#define __NR_faccessat		296
-#define __NR_pselect6		297
-#define __NR_ppoll		298
-#define __NR_unshare		299
-#define __NR_set_robust_list	300
-#define __NR_get_robust_list	301
-#define __NR_migrate_pages	302
-#define __NR_mbind		303
-#define __NR_get_mempolicy	304
-#define __NR_set_mempolicy	305
-#define __NR_kexec_load		306
-#define __NR_move_pages		307
-#define __NR_getcpu		308
-#define __NR_epoll_pwait	309
-#define __NR_utimensat		310
-#define __NR_signalfd		311
-#define __NR_timerfd_create	312
-#define __NR_eventfd		313
-#define __NR_fallocate		314
-#define __NR_timerfd_settime	315
-#define __NR_timerfd_gettime	316
-#define __NR_signalfd4		317
-#define __NR_eventfd2		318
-#define __NR_epoll_create1	319
-#define __NR_dup3		320
-#define __NR_pipe2		321
-#define __NR_inotify_init1	322
-#define __NR_accept4		323
-
-#define NR_SYSCALLS		324
-
-/* Sparc 32-bit only has the "setresuid32", "getresuid32" variants,
- * it never had the plain ones and there is no value to adding those
- * old versions into the syscall table.
- */
-#define __IGNORE_setresuid
-#define __IGNORE_getresuid
-#define __IGNORE_setresgid
-#define __IGNORE_getresgid
-
-#ifdef __KERNEL__
-#define __ARCH_WANT_IPC_PARSE_VERSION
-#define __ARCH_WANT_OLD_READDIR
-#define __ARCH_WANT_STAT64
-#define __ARCH_WANT_SYS_ALARM
-#define __ARCH_WANT_SYS_GETHOSTNAME
-#define __ARCH_WANT_SYS_PAUSE
-#define __ARCH_WANT_SYS_SGETMASK
-#define __ARCH_WANT_SYS_SIGNAL
-#define __ARCH_WANT_SYS_TIME
-#define __ARCH_WANT_SYS_UTIME
-#define __ARCH_WANT_SYS_WAITPID
-#define __ARCH_WANT_SYS_SOCKETCALL
-#define __ARCH_WANT_SYS_FADVISE64
-#define __ARCH_WANT_SYS_GETPGRP
-#define __ARCH_WANT_SYS_LLSEEK
-#define __ARCH_WANT_SYS_NICE
-#define __ARCH_WANT_SYS_OLDUMOUNT
-#define __ARCH_WANT_SYS_SIGPENDING
-#define __ARCH_WANT_SYS_SIGPROCMASK
-#define __ARCH_WANT_SYS_RT_SIGSUSPEND
-
-/*
- * "Conditional" syscalls
- *
- * What we want is __attribute__((weak,alias("sys_ni_syscall"))),
- * but it doesn't work on all toolchains, so we just do it by hand
- */
-#define cond_syscall(x) asm(".weak\t" #x "\n\t.set\t" #x ",sys_ni_syscall")
-
-#endif /* __KERNEL__ */
-#endif /* _SPARC_UNISTD_H */
diff --git a/arch/sparc/include/asm/unistd_64.h b/arch/sparc/include/asm/unistd_64.h
deleted file mode 100644
index fa5d3c0343c7..000000000000
--- a/arch/sparc/include/asm/unistd_64.h
+++ /dev/null
@@ -1,380 +0,0 @@
-#ifndef _SPARC64_UNISTD_H
-#define _SPARC64_UNISTD_H
-
-/*
- * System calls under the Sparc.
- *
- * Don't be scared by the ugly clobbers, it is the only way I can
- * think of right now to force the arguments into fixed registers
- * before the trap into the system call with gcc 'asm' statements.
- *
- * Copyright (C) 1995, 2007 David S. Miller (davem@davemloft.net)
- *
- * SunOS compatibility based upon preliminary work which is:
- *
- * Copyright (C) 1995 Adrian M. Rodriguez (adrian@remus.rutgers.edu)
- */
-
-#define __NR_restart_syscall      0 /* Linux Specific				   */
-#define __NR_exit                 1 /* Common                                      */
-#define __NR_fork                 2 /* Common                                      */
-#define __NR_read                 3 /* Common                                      */
-#define __NR_write                4 /* Common                                      */
-#define __NR_open                 5 /* Common                                      */
-#define __NR_close                6 /* Common                                      */
-#define __NR_wait4                7 /* Common                                      */
-#define __NR_creat                8 /* Common                                      */
-#define __NR_link                 9 /* Common                                      */
-#define __NR_unlink              10 /* Common                                      */
-#define __NR_execv               11 /* SunOS Specific                              */
-#define __NR_chdir               12 /* Common                                      */
-#define __NR_chown		 13 /* Common					   */
-#define __NR_mknod               14 /* Common                                      */
-#define __NR_chmod               15 /* Common                                      */
-#define __NR_lchown              16 /* Common                                      */
-#define __NR_brk                 17 /* Common                                      */
-#define __NR_perfctr             18 /* Performance counter operations              */
-#define __NR_lseek               19 /* Common                                      */
-#define __NR_getpid              20 /* Common                                      */
-#define __NR_capget		 21 /* Linux Specific				   */
-#define __NR_capset		 22 /* Linux Specific				   */
-#define __NR_setuid              23 /* Implemented via setreuid in SunOS           */
-#define __NR_getuid              24 /* Common                                      */
-#define __NR_vmsplice	         25 /* ENOSYS under SunOS			   */
-#define __NR_ptrace              26 /* Common                                      */
-#define __NR_alarm               27 /* Implemented via setitimer in SunOS          */
-#define __NR_sigaltstack	 28 /* Common					   */
-#define __NR_pause               29 /* Is sigblock(0)->sigpause() in SunOS         */
-#define __NR_utime               30 /* Implemented via utimes() under SunOS        */
-/* #define __NR_lchown32         31    Linux sparc32 specific                      */
-/* #define __NR_fchown32         32    Linux sparc32 specific                      */
-#define __NR_access              33 /* Common                                      */
-#define __NR_nice                34 /* Implemented via get/setpriority() in SunOS  */
-/* #define __NR_chown32          35    Linux sparc32 specific                      */
-#define __NR_sync                36 /* Common                                      */
-#define __NR_kill                37 /* Common                                      */
-#define __NR_stat                38 /* Common                                      */
-#define __NR_sendfile		 39 /* Linux Specific				   */
-#define __NR_lstat               40 /* Common                                      */
-#define __NR_dup                 41 /* Common                                      */
-#define __NR_pipe                42 /* Common                                      */
-#define __NR_times               43 /* Implemented via getrusage() in SunOS        */
-/* #define __NR_getuid32         44    Linux sparc32 specific                      */
-#define __NR_umount2             45 /* Linux Specific                              */
-#define __NR_setgid              46 /* Implemented via setregid() in SunOS         */
-#define __NR_getgid              47 /* Common                                      */
-#define __NR_signal              48 /* Implemented via sigvec() in SunOS           */
-#define __NR_geteuid             49 /* SunOS calls getuid()                        */
-#define __NR_getegid             50 /* SunOS calls getgid()                        */
-#define __NR_acct                51 /* Common                                      */
-#define __NR_memory_ordering	 52 /* Linux Specific				   */
-/* #define __NR_getgid32         53    Linux sparc32 specific                      */
-#define __NR_ioctl               54 /* Common                                      */
-#define __NR_reboot              55 /* Common                                      */
-/* #define __NR_mmap2		 56    Linux sparc32 Specific                      */
-#define __NR_symlink             57 /* Common                                      */
-#define __NR_readlink            58 /* Common                                      */
-#define __NR_execve              59 /* Common                                      */
-#define __NR_umask               60 /* Common                                      */
-#define __NR_chroot              61 /* Common                                      */
-#define __NR_fstat               62 /* Common                                      */
-#define __NR_fstat64             63 /* Linux Specific                              */
-#define __NR_getpagesize         64 /* Common                                      */
-#define __NR_msync               65 /* Common in newer 1.3.x revs...               */
-#define __NR_vfork               66 /* Common                                      */
-#define __NR_pread64             67 /* Linux Specific                              */
-#define __NR_pwrite64            68 /* Linux Specific                              */
-/* #define __NR_geteuid32        69    Linux sparc32, sbrk under SunOS             */
-/* #define __NR_getegid32        70    Linux sparc32, sstk under SunOS             */
-#define __NR_mmap                71 /* Common                                      */
-/* #define __NR_setreuid32       72    Linux sparc32, vadvise under SunOS          */
-#define __NR_munmap              73 /* Common                                      */
-#define __NR_mprotect            74 /* Common                                      */
-#define __NR_madvise             75 /* Common                                      */
-#define __NR_vhangup             76 /* Common                                      */
-/* #define __NR_truncate64       77    Linux sparc32 Specific			   */
-#define __NR_mincore             78 /* Common                                      */
-#define __NR_getgroups           79 /* Common                                      */
-#define __NR_setgroups           80 /* Common                                      */
-#define __NR_getpgrp             81 /* Common                                      */
-/* #define __NR_setgroups32      82    Linux sparc32, setpgrp under SunOS          */
-#define __NR_setitimer           83 /* Common                                      */
-/* #define __NR_ftruncate64      84    Linux sparc32 Specific			   */
-#define __NR_swapon              85 /* Common                                      */
-#define __NR_getitimer           86 /* Common                                      */
-/* #define __NR_setuid32         87    Linux sparc32, gethostname under SunOS      */
-#define __NR_sethostname         88 /* Common                                      */
-/* #define __NR_setgid32         89    Linux sparc32, getdtablesize under SunOS    */
-#define __NR_dup2                90 /* Common                                      */
-/* #define __NR_setfsuid32       91    Linux sparc32, getdopt under SunOS          */
-#define __NR_fcntl               92 /* Common                                      */
-#define __NR_select              93 /* Common                                      */
-/* #define __NR_setfsgid32       94    Linux sparc32, setdopt under SunOS          */
-#define __NR_fsync               95 /* Common                                      */
-#define __NR_setpriority         96 /* Common                                      */
-#define __NR_socket              97 /* Common                                      */
-#define __NR_connect             98 /* Common                                      */
-#define __NR_accept              99 /* Common                                      */
-#define __NR_getpriority        100 /* Common                                      */
-#define __NR_rt_sigreturn       101 /* Linux Specific                              */
-#define __NR_rt_sigaction       102 /* Linux Specific                              */
-#define __NR_rt_sigprocmask     103 /* Linux Specific                              */
-#define __NR_rt_sigpending      104 /* Linux Specific                              */
-#define __NR_rt_sigtimedwait    105 /* Linux Specific                              */
-#define __NR_rt_sigqueueinfo    106 /* Linux Specific                              */
-#define __NR_rt_sigsuspend      107 /* Linux Specific                              */
-#define __NR_setresuid          108 /* Linux Specific, sigvec under SunOS	   */
-#define __NR_getresuid          109 /* Linux Specific, sigblock under SunOS	   */
-#define __NR_setresgid          110 /* Linux Specific, sigsetmask under SunOS	   */
-#define __NR_getresgid          111 /* Linux Specific, sigpause under SunOS	   */
-/* #define __NR_setregid32       75    Linux sparc32, sigstack under SunOS         */
-#define __NR_recvmsg            113 /* Common                                      */
-#define __NR_sendmsg            114 /* Common                                      */
-/* #define __NR_getgroups32     115    Linux sparc32, vtrace under SunOS           */
-#define __NR_gettimeofday       116 /* Common                                      */
-#define __NR_getrusage          117 /* Common                                      */
-#define __NR_getsockopt         118 /* Common                                      */
-#define __NR_getcwd		119 /* Linux Specific				   */
-#define __NR_readv              120 /* Common                                      */
-#define __NR_writev             121 /* Common                                      */
-#define __NR_settimeofday       122 /* Common                                      */
-#define __NR_fchown             123 /* Common                                      */
-#define __NR_fchmod             124 /* Common                                      */
-#define __NR_recvfrom           125 /* Common                                      */
-#define __NR_setreuid           126 /* Common                                      */
-#define __NR_setregid           127 /* Common                                      */
-#define __NR_rename             128 /* Common                                      */
-#define __NR_truncate           129 /* Common                                      */
-#define __NR_ftruncate          130 /* Common                                      */
-#define __NR_flock              131 /* Common                                      */
-#define __NR_lstat64		132 /* Linux Specific                              */
-#define __NR_sendto             133 /* Common                                      */
-#define __NR_shutdown           134 /* Common                                      */
-#define __NR_socketpair         135 /* Common                                      */
-#define __NR_mkdir              136 /* Common                                      */
-#define __NR_rmdir              137 /* Common                                      */
-#define __NR_utimes             138 /* SunOS Specific                              */
-#define __NR_stat64		139 /* Linux Specific			           */
-#define __NR_sendfile64         140 /* adjtime under SunOS                         */
-#define __NR_getpeername        141 /* Common                                      */
-#define __NR_futex              142 /* gethostid under SunOS                       */
-#define __NR_gettid             143 /* ENOSYS under SunOS                          */
-#define __NR_getrlimit		144 /* Common                                      */
-#define __NR_setrlimit          145 /* Common                                      */
-#define __NR_pivot_root		146 /* Linux Specific, killpg under SunOS          */
-#define __NR_prctl		147 /* ENOSYS under SunOS                          */
-#define __NR_pciconfig_read	148 /* ENOSYS under SunOS                          */
-#define __NR_pciconfig_write	149 /* ENOSYS under SunOS                          */
-#define __NR_getsockname        150 /* Common                                      */
-#define __NR_inotify_init       151 /* Linux specific                              */
-#define __NR_inotify_add_watch  152 /* Linux specific                              */
-#define __NR_poll               153 /* Common                                      */
-#define __NR_getdents64		154 /* Linux specific				   */
-/* #define __NR_fcntl64         155    Linux sparc32 Specific                      */
-#define __NR_inotify_rm_watch   156 /* Linux specific				   */
-#define __NR_statfs             157 /* Common                                      */
-#define __NR_fstatfs            158 /* Common                                      */
-#define __NR_umount             159 /* Common                                      */
-#define __NR_sched_set_affinity 160 /* Linux specific, async_daemon under SunOS    */
-#define __NR_sched_get_affinity 161 /* Linux specific, getfh under SunOS           */
-#define __NR_getdomainname      162 /* SunOS Specific                              */
-#define __NR_setdomainname      163 /* Common                                      */
-#define __NR_utrap_install	164 /* SYSV ABI/v9 required			   */
-#define __NR_quotactl           165 /* Common                                      */
-#define __NR_set_tid_address    166 /* Linux specific, exportfs under SunOS        */
-#define __NR_mount              167 /* Common                                      */
-#define __NR_ustat              168 /* Common                                      */
-#define __NR_setxattr           169 /* SunOS: semsys                               */
-#define __NR_lsetxattr          170 /* SunOS: msgsys                               */
-#define __NR_fsetxattr          171 /* SunOS: shmsys                               */
-#define __NR_getxattr           172 /* SunOS: auditsys                             */
-#define __NR_lgetxattr          173 /* SunOS: rfssys                               */
-#define __NR_getdents           174 /* Common                                      */
-#define __NR_setsid             175 /* Common                                      */
-#define __NR_fchdir             176 /* Common                                      */
-#define __NR_fgetxattr          177 /* SunOS: fchroot                              */
-#define __NR_listxattr          178 /* SunOS: vpixsys                              */
-#define __NR_llistxattr         179 /* SunOS: aioread                              */
-#define __NR_flistxattr         180 /* SunOS: aiowrite                             */
-#define __NR_removexattr        181 /* SunOS: aiowait                              */
-#define __NR_lremovexattr       182 /* SunOS: aiocancel                            */
-#define __NR_sigpending         183 /* Common                                      */
-#define __NR_query_module	184 /* Linux Specific				   */
-#define __NR_setpgid            185 /* Common                                      */
-#define __NR_fremovexattr       186 /* SunOS: pathconf                             */
-#define __NR_tkill              187 /* SunOS: fpathconf                            */
-#define __NR_exit_group		188 /* Linux specific, sysconf undef SunOS         */
-#define __NR_uname              189 /* Linux Specific                              */
-#define __NR_init_module        190 /* Linux Specific                              */
-#define __NR_personality        191 /* Linux Specific                              */
-#define __NR_remap_file_pages   192 /* Linux Specific                              */
-#define __NR_epoll_create       193 /* Linux Specific                              */
-#define __NR_epoll_ctl          194 /* Linux Specific                              */
-#define __NR_epoll_wait         195 /* Linux Specific                              */
-#define __NR_ioprio_set         196 /* Linux Specific                              */
-#define __NR_getppid            197 /* Linux Specific                              */
-#define __NR_sigaction          198 /* Linux Specific                              */
-#define __NR_sgetmask           199 /* Linux Specific                              */
-#define __NR_ssetmask           200 /* Linux Specific                              */
-#define __NR_sigsuspend         201 /* Linux Specific                              */
-#define __NR_oldlstat           202 /* Linux Specific                              */
-#define __NR_uselib             203 /* Linux Specific                              */
-#define __NR_readdir            204 /* Linux Specific                              */
-#define __NR_readahead          205 /* Linux Specific                              */
-#define __NR_socketcall         206 /* Linux Specific                              */
-#define __NR_syslog             207 /* Linux Specific                              */
-#define __NR_lookup_dcookie     208 /* Linux Specific                              */
-#define __NR_fadvise64          209 /* Linux Specific                              */
-#define __NR_fadvise64_64       210 /* Linux Specific                              */
-#define __NR_tgkill             211 /* Linux Specific                              */
-#define __NR_waitpid            212 /* Linux Specific                              */
-#define __NR_swapoff            213 /* Linux Specific                              */
-#define __NR_sysinfo            214 /* Linux Specific                              */
-#define __NR_ipc                215 /* Linux Specific                              */
-#define __NR_sigreturn          216 /* Linux Specific                              */
-#define __NR_clone              217 /* Linux Specific                              */
-#define __NR_ioprio_get         218 /* Linux Specific                              */
-#define __NR_adjtimex           219 /* Linux Specific                              */
-#define __NR_sigprocmask        220 /* Linux Specific                              */
-#define __NR_create_module      221 /* Linux Specific                              */
-#define __NR_delete_module      222 /* Linux Specific                              */
-#define __NR_get_kernel_syms    223 /* Linux Specific                              */
-#define __NR_getpgid            224 /* Linux Specific                              */
-#define __NR_bdflush            225 /* Linux Specific                              */
-#define __NR_sysfs              226 /* Linux Specific                              */
-#define __NR_afs_syscall        227 /* Linux Specific                              */
-#define __NR_setfsuid           228 /* Linux Specific                              */
-#define __NR_setfsgid           229 /* Linux Specific                              */
-#define __NR__newselect         230 /* Linux Specific                              */
-#ifdef __KERNEL__
-#define __NR_time		231 /* Linux sparc32                               */
-#endif
-#define __NR_splice             232 /* Linux Specific                              */
-#define __NR_stime              233 /* Linux Specific                              */
-#define __NR_statfs64           234 /* Linux Specific                              */
-#define __NR_fstatfs64          235 /* Linux Specific                              */
-#define __NR__llseek            236 /* Linux Specific                              */
-#define __NR_mlock              237
-#define __NR_munlock            238
-#define __NR_mlockall           239
-#define __NR_munlockall         240
-#define __NR_sched_setparam     241
-#define __NR_sched_getparam     242
-#define __NR_sched_setscheduler 243
-#define __NR_sched_getscheduler 244
-#define __NR_sched_yield        245
-#define __NR_sched_get_priority_max 246
-#define __NR_sched_get_priority_min 247
-#define __NR_sched_rr_get_interval  248
-#define __NR_nanosleep          249
-#define __NR_mremap             250
-#define __NR__sysctl            251
-#define __NR_getsid             252
-#define __NR_fdatasync          253
-#define __NR_nfsservctl         254
-#define __NR_sync_file_range	255
-#define __NR_clock_settime	256
-#define __NR_clock_gettime	257
-#define __NR_clock_getres	258
-#define __NR_clock_nanosleep	259
-#define __NR_sched_getaffinity	260
-#define __NR_sched_setaffinity	261
-#define __NR_timer_settime	262
-#define __NR_timer_gettime	263
-#define __NR_timer_getoverrun	264
-#define __NR_timer_delete	265
-#define __NR_timer_create	266
-/* #define __NR_vserver		267 Reserved for VSERVER */
-#define __NR_io_setup		268
-#define __NR_io_destroy		269
-#define __NR_io_submit		270
-#define __NR_io_cancel		271
-#define __NR_io_getevents	272
-#define __NR_mq_open		273
-#define __NR_mq_unlink		274
-#define __NR_mq_timedsend	275
-#define __NR_mq_timedreceive	276
-#define __NR_mq_notify		277
-#define __NR_mq_getsetattr	278
-#define __NR_waitid		279
-#define __NR_tee		280
-#define __NR_add_key		281
-#define __NR_request_key	282
-#define __NR_keyctl		283
-#define __NR_openat		284
-#define __NR_mkdirat		285
-#define __NR_mknodat		286
-#define __NR_fchownat		287
-#define __NR_futimesat		288
-#define __NR_fstatat64		289
-#define __NR_unlinkat		290
-#define __NR_renameat		291
-#define __NR_linkat		292
-#define __NR_symlinkat		293
-#define __NR_readlinkat		294
-#define __NR_fchmodat		295
-#define __NR_faccessat		296
-#define __NR_pselect6		297
-#define __NR_ppoll		298
-#define __NR_unshare		299
-#define __NR_set_robust_list	300
-#define __NR_get_robust_list	301
-#define __NR_migrate_pages	302
-#define __NR_mbind		303
-#define __NR_get_mempolicy	304
-#define __NR_set_mempolicy	305
-#define __NR_kexec_load		306
-#define __NR_move_pages		307
-#define __NR_getcpu		308
-#define __NR_epoll_pwait	309
-#define __NR_utimensat		310
-#define __NR_signalfd		311
-#define __NR_timerfd_create	312
-#define __NR_eventfd		313
-#define __NR_fallocate		314
-#define __NR_timerfd_settime	315
-#define __NR_timerfd_gettime	316
-#define __NR_signalfd4		317
-#define __NR_eventfd2		318
-#define __NR_epoll_create1	319
-#define __NR_dup3		320
-#define __NR_pipe2		321
-#define __NR_inotify_init1	322
-#define __NR_accept4		323
-
-#define NR_SYSCALLS		324
-
-#ifdef __KERNEL__
-#define __ARCH_WANT_IPC_PARSE_VERSION
-#define __ARCH_WANT_OLD_READDIR
-#define __ARCH_WANT_STAT64
-#define __ARCH_WANT_SYS_ALARM
-#define __ARCH_WANT_SYS_GETHOSTNAME
-#define __ARCH_WANT_SYS_PAUSE
-#define __ARCH_WANT_SYS_SGETMASK
-#define __ARCH_WANT_SYS_SIGNAL
-#define __ARCH_WANT_SYS_TIME
-#define __ARCH_WANT_COMPAT_SYS_TIME
-#define __ARCH_WANT_SYS_UTIME
-#define __ARCH_WANT_SYS_WAITPID
-#define __ARCH_WANT_SYS_SOCKETCALL
-#define __ARCH_WANT_SYS_FADVISE64
-#define __ARCH_WANT_SYS_GETPGRP
-#define __ARCH_WANT_SYS_LLSEEK
-#define __ARCH_WANT_SYS_NICE
-#define __ARCH_WANT_SYS_OLDUMOUNT
-#define __ARCH_WANT_SYS_SIGPENDING
-#define __ARCH_WANT_SYS_SIGPROCMASK
-#define __ARCH_WANT_SYS_RT_SIGSUSPEND
-#define __ARCH_WANT_COMPAT_SYS_RT_SIGSUSPEND
-
-/*
- * "Conditional" syscalls
- *
- * What we want is __attribute__((weak,alias("sys_ni_syscall"))),
- * but it doesn't work on all toolchains, so we just do it by hand
- */
-#define cond_syscall(x) asm(".weak\t" #x "\n\t.set\t" #x ",sys_ni_syscall")
-
-#endif /* __KERNEL__ */
-#endif /* _SPARC64_UNISTD_H */
diff --git a/arch/sparc/kernel/.gitignore b/arch/sparc/kernel/.gitignore
new file mode 100644
index 000000000000..c5f676c3c224
--- /dev/null
+++ b/arch/sparc/kernel/.gitignore
@@ -0,0 +1 @@
+vmlinux.lds
diff --git a/arch/sparc/kernel/Makefile b/arch/sparc/kernel/Makefile
index 2d6582095099..59aab6a81e89 100644
--- a/arch/sparc/kernel/Makefile
+++ b/arch/sparc/kernel/Makefile
@@ -2,25 +2,98 @@
 # Makefile for the linux kernel.
 #
 
-extra-y		:= head.o init_task.o vmlinux.lds
-
-EXTRA_AFLAGS	:= -ansi
-
-IRQ_OBJS := irq.o sun4m_irq.o sun4c_irq.o sun4d_irq.o
-obj-y    := entry.o wof.o wuf.o etrap.o rtrap.o traps.o $(IRQ_OBJS) \
-	    process.o signal.o ioport.o setup.o idprom.o \
-	    sys_sparc.o systbls.o \
-	    time.o windows.o cpu.o devices.o \
-	    tadpole.o tick14.o ptrace.o \
-	    unaligned.o una_asm.o muldiv.o \
-	    prom.o of_device.o devres.o dma.o
-
-devres-y = ../../../kernel/irq/devres.o
-
-obj-$(CONFIG_PCI) += pcic.o
-obj-$(CONFIG_SMP) += trampoline.o smp.o sun4m_smp.o sun4d_smp.o
-obj-$(CONFIG_SUN_AUXIO) += auxio.o
-obj-$(CONFIG_SUN_PM) += apc.o pmc.o
-obj-$(CONFIG_MODULES) += module.o sparc_ksyms.o
-obj-$(CONFIG_SPARC_LED) += led.o
-obj-$(CONFIG_KGDB) += kgdb.o
+asflags-y := -ansi
+ccflags-y := -Werror
+
+extra-y     := head_$(BITS).o
+extra-y     += init_task.o
+extra-y     += vmlinux.lds
+
+obj-$(CONFIG_SPARC32)   += entry.o wof.o wuf.o
+obj-$(CONFIG_SPARC32)   += etrap_32.o
+obj-$(CONFIG_SPARC32)   += rtrap_32.o
+obj-y                   += traps_$(BITS).o
+
+# IRQ
+obj-y                   += irq_$(BITS).o
+obj-$(CONFIG_SPARC32)   += sun4m_irq.o sun4c_irq.o sun4d_irq.o
+
+obj-y                   += process_$(BITS).o
+obj-y                   += signal_$(BITS).o
+obj-$(CONFIG_SPARC32)   += ioport.o
+obj-y                   += setup_$(BITS).o
+obj-y                   += idprom.o
+obj-y                   += sys_sparc_$(BITS).o
+obj-$(CONFIG_SPARC32)   += systbls_32.o
+obj-y                   += time_$(BITS).o
+obj-$(CONFIG_SPARC32)   += windows.o
+obj-y                   += cpu.o
+obj-$(CONFIG_SPARC32)   += devices.o
+obj-$(CONFIG_SPARC32)   += tadpole.o
+obj-$(CONFIG_SPARC32)   += tick14.o
+obj-y                   += ptrace_$(BITS).o
+obj-y                   += unaligned_$(BITS).o
+obj-y                   += una_asm_$(BITS).o
+obj-$(CONFIG_SPARC32)   += muldiv.o
+obj-y                   += prom_common.o
+obj-y                   += prom_$(BITS).o
+obj-y                   += of_device_$(BITS).o
+obj-$(CONFIG_SPARC64)   += prom_irqtrans.o
+
+obj-$(CONFIG_SPARC64)   += reboot.o
+obj-$(CONFIG_SPARC64)   += sysfs.o
+obj-$(CONFIG_SPARC64)   += iommu.o
+obj-$(CONFIG_SPARC64)   += central.o
+obj-$(CONFIG_SPARC64)   += starfire.o
+obj-$(CONFIG_SPARC64)   += power.o
+obj-$(CONFIG_SPARC64)   += sbus.o
+obj-$(CONFIG_SPARC64)   += ebus.o
+obj-$(CONFIG_SPARC64)   += visemul.o
+obj-$(CONFIG_SPARC64)   += hvapi.o
+obj-$(CONFIG_SPARC64)   += sstate.o
+obj-$(CONFIG_SPARC64)   += mdesc.o
+
+# sparc32 do not use GENERIC_HARDIRQS but uses the generic devres implementation
+obj-$(CONFIG_SPARC32)     += devres.o
+devres-y                  := ../../../kernel/irq/devres.o
+
+obj-$(CONFIG_SPARC32)     += dma.o
+
+obj-$(CONFIG_SPARC32_PCI) += pcic.o
+
+obj-$(CONFIG_SMP)         += trampoline_$(BITS).o smp_$(BITS).o
+obj-$(CONFIG_SPARC32_SMP) += sun4m_smp.o sun4d_smp.o
+obj-$(CONFIG_SPARC64_SMP) += hvtramp.o
+
+obj-y                     += auxio_$(BITS).o
+obj-$(CONFIG_SUN_PM)      += apc.o pmc.o
+
+obj-$(CONFIG_MODULES)     += module_$(BITS).o
+obj-$(CONFIG_MODULES)     += sparc_ksyms_$(BITS).o
+obj-$(CONFIG_SPARC_LED)   += led.o
+obj-$(CONFIG_KGDB)        += kgdb_$(BITS).o
+
+
+obj-$(CONFIG_DYNAMIC_FTRACE) += ftrace.o
+CFLAGS_REMOVE_ftrace.o := -pg
+
+obj-$(CONFIG_STACKTRACE)     += stacktrace.o
+# sparc64 PCI
+obj-$(CONFIG_SPARC64_PCI)    += pci.o pci_common.o psycho_common.o
+obj-$(CONFIG_SPARC64_PCI)    += pci_psycho.o pci_sabre.o pci_schizo.o
+obj-$(CONFIG_SPARC64_PCI)    += pci_sun4v.o pci_sun4v_asm.o pci_fire.o
+obj-$(CONFIG_PCI_MSI)        += pci_msi.o
+
+obj-$(CONFIG_COMPAT)         += sys32.o sys_sparc32.o signal32.o
+
+# sparc64 cpufreq
+obj-$(CONFIG_US3_FREQ)  += us3_cpufreq.o
+obj-$(CONFIG_US2E_FREQ) += us2e_cpufreq.o
+obj-$(CONFIG_US3_MC)    += chmc.o
+
+obj-$(CONFIG_KPROBES)   += kprobes.o
+obj-$(CONFIG_SUN_LDOMS) += ldc.o vio.o viohs.o ds.o
+
+obj-$(CONFIG_AUDIT)     += audit.o
+audit--$(CONFIG_AUDIT)  := compat_audit.o
+obj-$(CONFIG_COMPAT)    += $(audit--y)
diff --git a/arch/sparc/kernel/asm-offsets.c b/arch/sparc/kernel/asm-offsets.c
index b5bb99ed892c..68f7e1118e9b 100644
--- a/arch/sparc/kernel/asm-offsets.c
+++ b/arch/sparc/kernel/asm-offsets.c
@@ -14,15 +14,28 @@
 // #include <linux/mm.h>
 #include <linux/kbuild.h>
 
-int foo(void)
+#ifdef CONFIG_SPARC32
+int sparc32_foo(void)
 {
-	DEFINE(AOFF_task_thread, offsetof(struct task_struct, thread));
-	BLANK();
 	DEFINE(AOFF_thread_fork_kpsr,
 			offsetof(struct thread_struct, fork_kpsr));
+	return 0;
+}
+#else
+int sparc64_foo(void)
+{
+	return 0;
+}
+#endif
+
+int foo(void)
+{
+	BLANK();
+	DEFINE(AOFF_task_thread, offsetof(struct task_struct, thread));
 	BLANK();
 	DEFINE(AOFF_mm_context, offsetof(struct mm_struct, context));
 
 	/* DEFINE(NUM_USER_SEGMENTS, TASK_SIZE>>28); */
 	return 0;
 }
+
diff --git a/arch/sparc64/kernel/audit.c b/arch/sparc/kernel/audit.c
index 8fff0ac63d56..8fff0ac63d56 100644
--- a/arch/sparc64/kernel/audit.c
+++ b/arch/sparc/kernel/audit.c
diff --git a/arch/sparc/kernel/auxio.c b/arch/sparc/kernel/auxio_32.c
index 09c857215a52..09c857215a52 100644
--- a/arch/sparc/kernel/auxio.c
+++ b/arch/sparc/kernel/auxio_32.c
diff --git a/arch/sparc64/kernel/auxio.c b/arch/sparc/kernel/auxio_64.c
index 858beda86524..8b67347d4221 100644
--- a/arch/sparc64/kernel/auxio.c
+++ b/arch/sparc/kernel/auxio_64.c
@@ -27,73 +27,55 @@ enum auxio_type {
 static enum auxio_type auxio_devtype = AUXIO_TYPE_NODEV;
 static DEFINE_SPINLOCK(auxio_lock);
 
-static void __auxio_sbus_set(u8 bits_on, u8 bits_off)
+static void __auxio_rmw(u8 bits_on, u8 bits_off, int ebus)
 {
 	if (auxio_register) {
-		unsigned char regval;
 		unsigned long flags;
-		unsigned char newval;
+		u8 regval, newval;
 
 		spin_lock_irqsave(&auxio_lock, flags);
 
-		regval =  sbus_readb(auxio_register);
+		regval = (ebus ?
+			  (u8) readl(auxio_register) :
+			  sbus_readb(auxio_register));
 		newval =  regval | bits_on;
 		newval &= ~bits_off;
-		newval &= ~AUXIO_AUX1_MASK;
-		sbus_writeb(newval, auxio_register);
+		if (!ebus)
+			newval &= ~AUXIO_AUX1_MASK;
+		if (ebus)
+			writel((u32) newval, auxio_register);
+		else
+			sbus_writeb(newval, auxio_register);
 		
 		spin_unlock_irqrestore(&auxio_lock, flags);
 	}
 }
 
-static void __auxio_ebus_set(u8 bits_on, u8 bits_off)
+static void __auxio_set_bit(u8 bit, int on, int ebus)
 {
-	if (auxio_register) {
-		unsigned char regval;
-		unsigned long flags;
-		unsigned char newval;
-
-		spin_lock_irqsave(&auxio_lock, flags);
-
-		regval =  (u8)readl(auxio_register);
-		newval =  regval | bits_on;
-		newval &= ~bits_off;
-		writel((u32)newval, auxio_register);
+	u8 bits_on = (ebus ? AUXIO_PCIO_LED : AUXIO_AUX1_LED);
+	u8 bits_off = 0;
 
-		spin_unlock_irqrestore(&auxio_lock, flags);
+	if (!on) {
+		u8 tmp = bits_off;
+		bits_off = bits_on;
+		bits_on = tmp;
 	}
-}
-
-static inline void __auxio_ebus_set_led(int on)
-{
-	(on) ? __auxio_ebus_set(AUXIO_PCIO_LED, 0) :
-		__auxio_ebus_set(0, AUXIO_PCIO_LED) ;
-}
-
-static inline void __auxio_sbus_set_led(int on)
-{
-	(on) ? __auxio_sbus_set(AUXIO_AUX1_LED, 0) :
-		__auxio_sbus_set(0, AUXIO_AUX1_LED) ;
+	__auxio_rmw(bits_on, bits_off, ebus);
 }
 
 void auxio_set_led(int on)
 {
-	switch(auxio_devtype) {
-	case AUXIO_TYPE_SBUS:
-		__auxio_sbus_set_led(on);
-		break;
-	case AUXIO_TYPE_EBUS:
-		__auxio_ebus_set_led(on);
-		break;
-	default:
-		break;
-	}
+	int ebus = auxio_devtype == AUXIO_TYPE_EBUS;
+	u8 bit;
+
+	bit = (ebus ? AUXIO_PCIO_LED : AUXIO_AUX1_LED);
+	__auxio_set_bit(bit, on, ebus);
 }
 
-static inline void __auxio_sbus_set_lte(int on)
+static void __auxio_sbus_set_lte(int on)
 {
-	(on) ? __auxio_sbus_set(AUXIO_AUX1_LTE, 0) : 
-		__auxio_sbus_set(0, AUXIO_AUX1_LTE) ;
+	__auxio_set_bit(AUXIO_AUX1_LTE, on, 0);
 }
 
 void auxio_set_lte(int on)
diff --git a/arch/sparc64/kernel/central.c b/arch/sparc/kernel/central.c
index 05f1c916db06..05f1c916db06 100644
--- a/arch/sparc64/kernel/central.c
+++ b/arch/sparc/kernel/central.c
diff --git a/arch/sparc64/kernel/cherrs.S b/arch/sparc/kernel/cherrs.S
index 89afebd7eca0..4ee1ad420862 100644
--- a/arch/sparc64/kernel/cherrs.S
+++ b/arch/sparc/kernel/cherrs.S
@@ -102,7 +102,7 @@ cheetah_plus_dcpe_trap_vector:
 	.type		do_cheetah_plus_data_parity,#function
 do_cheetah_plus_data_parity:
 	rdpr		%pil, %g2
-	wrpr		%g0, 15, %pil
+	wrpr		%g0, PIL_NORMAL_MAX, %pil
 	ba,pt		%xcc, etrap_irq
 	 rd		%pc, %g7
 #ifdef CONFIG_TRACE_IRQFLAGS
@@ -144,7 +144,7 @@ cheetah_plus_icpe_trap_vector:
 	.type		do_cheetah_plus_insn_parity,#function
 do_cheetah_plus_insn_parity:
 	rdpr		%pil, %g2
-	wrpr		%g0, 15, %pil
+	wrpr		%g0, PIL_NORMAL_MAX, %pil
 	ba,pt		%xcc, etrap_irq
 	 rd		%pc, %g7
 #ifdef CONFIG_TRACE_IRQFLAGS
@@ -492,7 +492,7 @@ cheetah_fast_ecc:
 	.type		c_fast_ecc,#function
 c_fast_ecc:
 	rdpr		%pil, %g2
-	wrpr		%g0, 15, %pil
+	wrpr		%g0, PIL_NORMAL_MAX, %pil
 	ba,pt		%xcc, etrap_irq
 	 rd		%pc, %g7
 #ifdef CONFIG_TRACE_IRQFLAGS
@@ -528,7 +528,7 @@ cheetah_cee:
 	.type		c_cee,#function
 c_cee:
 	rdpr		%pil, %g2
-	wrpr		%g0, 15, %pil
+	wrpr		%g0, PIL_NORMAL_MAX, %pil
 	ba,pt		%xcc, etrap_irq
 	 rd		%pc, %g7
 #ifdef CONFIG_TRACE_IRQFLAGS
@@ -564,7 +564,7 @@ cheetah_deferred_trap:
 	.type		c_deferred,#function
 c_deferred:
 	rdpr		%pil, %g2
-	wrpr		%g0, 15, %pil
+	wrpr		%g0, PIL_NORMAL_MAX, %pil
 	ba,pt		%xcc, etrap_irq
 	 rd		%pc, %g7
 #ifdef CONFIG_TRACE_IRQFLAGS
diff --git a/arch/sparc64/kernel/chmc.c b/arch/sparc/kernel/chmc.c
index 3b9f4d6e14a9..3b9f4d6e14a9 100644
--- a/arch/sparc64/kernel/chmc.c
+++ b/arch/sparc/kernel/chmc.c
diff --git a/arch/sparc64/kernel/compat_audit.c b/arch/sparc/kernel/compat_audit.c
index c831b0a4e660..d865575b25bf 100644
--- a/arch/sparc64/kernel/compat_audit.c
+++ b/arch/sparc/kernel/compat_audit.c
@@ -1,4 +1,5 @@
-#include <asm/unistd_32.h>
+#define __32bit_syscall_numbers__
+#include <asm/unistd.h>
 
 unsigned sparc32_dir_class[] = {
 #include <asm-generic/audit_dir_write.h>
diff --git a/arch/sparc/kernel/cpu.c b/arch/sparc/kernel/cpu.c
index 1fc17f59c6bf..6c2da2420f76 100644
--- a/arch/sparc/kernel/cpu.c
+++ b/arch/sparc/kernel/cpu.c
@@ -8,6 +8,8 @@
 #include <linux/init.h>
 #include <linux/smp.h>
 #include <linux/threads.h>
+
+#include <asm/spitfire.h>
 #include <asm/oplib.h>
 #include <asm/page.h>
 #include <asm/head.h>
@@ -15,153 +17,322 @@
 #include <asm/mbus.h>
 #include <asm/cpudata.h>
 
+#include "kernel.h"
+
 DEFINE_PER_CPU(cpuinfo_sparc, __cpu_data) = { 0 };
 
-struct cpu_iu_info {
-  int psr_impl;
-  int psr_vers;
-  char* cpu_name;   /* should be enough I hope... */
+struct cpu_info {
+	int psr_vers;
+	const char *name;
+};
+
+struct fpu_info {
+	int fp_vers;
+	const char *name;
 };
 
-struct cpu_fp_info {
-  int psr_impl;
-  int fp_vers;
-  char* fp_name;
+#define NOCPU 8
+#define NOFPU 8
+
+struct manufacturer_info {
+	int psr_impl;
+	struct cpu_info cpu_info[NOCPU];
+	struct fpu_info fpu_info[NOFPU];
 };
 
+#define CPU(ver, _name) \
+{ .psr_vers = ver, .name = _name }
+
+#define FPU(ver, _name) \
+{ .fp_vers = ver, .name = _name }
+
+static const struct manufacturer_info __initconst manufacturer_info[] = {
+{
+	0,
+	/* Sun4/100, 4/200, SLC */
+	.cpu_info = {
+		CPU(0, "Fujitsu  MB86900/1A or LSI L64831 SparcKIT-40"),
+		/* borned STP1012PGA */
+		CPU(4,  "Fujitsu  MB86904"),
+		CPU(5, "Fujitsu TurboSparc MB86907"),
+		CPU(-1, NULL)
+	},
+	.fpu_info = {
+		FPU(0, "Fujitsu MB86910 or Weitek WTL1164/5"),
+		FPU(1, "Fujitsu MB86911 or Weitek WTL1164/5 or LSI L64831"),
+		FPU(2, "LSI Logic L64802 or Texas Instruments ACT8847"),
+		/* SparcStation SLC, SparcStation1 */
+		FPU(3, "Weitek WTL3170/2"),
+		/* SPARCstation-5 */
+		FPU(4, "Lsi Logic/Meiko L64804 or compatible"),
+		FPU(-1, NULL)
+	}
+},{
+	1,
+	.cpu_info = {
+		/* SparcStation2, SparcServer 490 & 690 */
+		CPU(0, "LSI Logic Corporation - L64811"),
+		/* SparcStation2 */
+		CPU(1, "Cypress/ROSS CY7C601"),
+		/* Embedded controller */
+		CPU(3, "Cypress/ROSS CY7C611"),
+		/* Ross Technologies HyperSparc */
+		CPU(0xf, "ROSS HyperSparc RT620"),
+		CPU(0xe, "ROSS HyperSparc RT625 or RT626"),
+		CPU(-1, NULL)
+	},
+	.fpu_info = {
+		FPU(0, "ROSS HyperSparc combined IU/FPU"),
+		FPU(1, "Lsi Logic L64814"),
+		FPU(2, "Texas Instruments TMS390-C602A"),
+		FPU(3, "Cypress CY7C602 FPU"),
+		FPU(-1, NULL)
+	}
+},{
+	2,
+	.cpu_info = {
+		/* ECL Implementation, CRAY S-MP Supercomputer... AIEEE! */
+		/* Someone please write the code to support this beast! ;) */
+		CPU(0, "Bipolar Integrated Technology - B5010"),
+		CPU(-1, NULL)
+	},
+	.fpu_info = {
+		FPU(-1, NULL)
+	}
+},{
+	3,
+	.cpu_info = {
+		CPU(0, "LSI Logic Corporation - unknown-type"),
+		CPU(-1, NULL)
+	},
+	.fpu_info = {
+		FPU(-1, NULL)
+	}
+},{
+	4,
+	.cpu_info = {
+		CPU(0, "Texas Instruments, Inc. - SuperSparc-(II)"),
+		/* SparcClassic  --  borned STP1010TAB-50*/
+		CPU(1, "Texas Instruments, Inc. - MicroSparc"),
+		CPU(2, "Texas Instruments, Inc. - MicroSparc II"),
+		CPU(3, "Texas Instruments, Inc. - SuperSparc 51"),
+		CPU(4, "Texas Instruments, Inc. - SuperSparc 61"),
+		CPU(5, "Texas Instruments, Inc. - unknown"),
+		CPU(-1, NULL)
+	},
+	.fpu_info = {
+		/* SuperSparc 50 module */
+		FPU(0, "SuperSparc on-chip FPU"),
+		/* SparcClassic */
+		FPU(4, "TI MicroSparc on chip FPU"),
+		FPU(-1, NULL)
+	}
+},{
+	5,
+	.cpu_info = {
+		CPU(0, "Matsushita - MN10501"),
+		CPU(-1, NULL)
+	},
+	.fpu_info = {
+		FPU(0, "Matsushita MN10501"),
+		FPU(-1, NULL)
+	}
+},{
+	6,
+	.cpu_info = {
+		CPU(0, "Philips Corporation - unknown"),
+		CPU(-1, NULL)
+	},
+	.fpu_info = {
+		FPU(-1, NULL)
+	}
+},{
+	7,
+	.cpu_info = {
+		CPU(0, "Harvest VLSI Design Center, Inc. - unknown"),
+		CPU(-1, NULL)
+	},
+	.fpu_info = {
+		FPU(-1, NULL)
+	}
+},{
+	8,
+	.cpu_info = {
+		CPU(0, "Systems and Processes Engineering Corporation (SPEC)"),
+		CPU(-1, NULL)
+	},
+	.fpu_info = {
+		FPU(-1, NULL)
+	}
+},{
+	9,
+	.cpu_info = {
+		/* Gallium arsenide 200MHz, BOOOOGOOOOMIPS!!! */
+		CPU(0, "Fujitsu or Weitek Power-UP"),
+		CPU(1, "Fujitsu or Weitek Power-UP"),
+		CPU(2, "Fujitsu or Weitek Power-UP"),
+		CPU(3, "Fujitsu or Weitek Power-UP"),
+		CPU(-1, NULL)
+	},
+	.fpu_info = {
+		FPU(3, "Fujitsu or Weitek on-chip FPU"),
+		FPU(-1, NULL)
+	}
+},{
+	0x17,
+	.cpu_info = {
+		CPU(0x10, "TI UltraSparc I   (SpitFire)"),
+		CPU(0x11, "TI UltraSparc II  (BlackBird)"),
+		CPU(0x12, "TI UltraSparc IIi (Sabre)"),
+		CPU(0x13, "TI UltraSparc IIe (Hummingbird)"),
+		CPU(-1, NULL)
+	},
+	.fpu_info = {
+		FPU(0x10, "UltraSparc I integrated FPU"),
+		FPU(0x11, "UltraSparc II integrated FPU"),
+		FPU(0x12, "UltraSparc IIi integrated FPU"),
+		FPU(0x13, "UltraSparc IIe integrated FPU"),
+		FPU(-1, NULL)
+	}
+},{
+	0x22,
+	.cpu_info = {
+		CPU(0x10, "TI UltraSparc I   (SpitFire)"),
+		CPU(-1, NULL)
+	},
+	.fpu_info = {
+		FPU(0x10, "UltraSparc I integrated FPU"),
+		FPU(-1, NULL)
+	}
+},{
+	0x3e,
+	.cpu_info = {
+		CPU(0x14, "TI UltraSparc III (Cheetah)"),
+		CPU(0x15, "TI UltraSparc III+ (Cheetah+)"),
+		CPU(0x16, "TI UltraSparc IIIi (Jalapeno)"),
+		CPU(0x18, "TI UltraSparc IV (Jaguar)"),
+		CPU(0x19, "TI UltraSparc IV+ (Panther)"),
+		CPU(0x22, "TI UltraSparc IIIi+ (Serrano)"),
+		CPU(-1, NULL)
+	},
+	.fpu_info = {
+		FPU(0x14, "UltraSparc III integrated FPU"),
+		FPU(0x15, "UltraSparc III+ integrated FPU"),
+		FPU(0x16, "UltraSparc IIIi integrated FPU"),
+		FPU(0x18, "UltraSparc IV integrated FPU"),
+		FPU(0x19, "UltraSparc IV+ integrated FPU"),
+		FPU(0x22, "UltraSparc IIIi+ integrated FPU"),
+		FPU(-1, NULL)
+	}
+}};
+
 /* In order to get the fpu type correct, you need to take the IDPROM's
  * machine type value into consideration too.  I will fix this.
  */
-static struct cpu_fp_info linux_sparc_fpu[] = {
-  { 0, 0, "Fujitsu MB86910 or Weitek WTL1164/5"},
-  { 0, 1, "Fujitsu MB86911 or Weitek WTL1164/5 or LSI L64831"},
-  { 0, 2, "LSI Logic L64802 or Texas Instruments ACT8847"},
-  /* SparcStation SLC, SparcStation1 */
-  { 0, 3, "Weitek WTL3170/2"},
-  /* SPARCstation-5 */
-  { 0, 4, "Lsi Logic/Meiko L64804 or compatible"},
-  { 0, 5, "reserved"},
-  { 0, 6, "reserved"},
-  { 0, 7, "No FPU"},
-  { 1, 0, "ROSS HyperSparc combined IU/FPU"},
-  { 1, 1, "Lsi Logic L64814"},
-  { 1, 2, "Texas Instruments TMS390-C602A"},
-  { 1, 3, "Cypress CY7C602 FPU"},
-  { 1, 4, "reserved"},
-  { 1, 5, "reserved"},
-  { 1, 6, "reserved"},
-  { 1, 7, "No FPU"},
-  { 2, 0, "BIT B5010 or B5110/20 or B5210"},
-  { 2, 1, "reserved"},
-  { 2, 2, "reserved"},
-  { 2, 3, "reserved"},
-  { 2, 4, "reserved"},
-  { 2, 5, "reserved"},
-  { 2, 6, "reserved"},
-  { 2, 7, "No FPU"},
-  /* SuperSparc 50 module */
-  { 4, 0, "SuperSparc on-chip FPU"},
-  /* SparcClassic */
-  { 4, 4, "TI MicroSparc on chip FPU"},
-  { 5, 0, "Matsushita MN10501"},
-  { 5, 1, "reserved"},
-  { 5, 2, "reserved"},
-  { 5, 3, "reserved"},
-  { 5, 4, "reserved"},
-  { 5, 5, "reserved"},
-  { 5, 6, "reserved"},
-  { 5, 7, "No FPU"},
-  { 9, 3, "Fujitsu or Weitek on-chip FPU"},
-};
 
-#define NSPARCFPU  ARRAY_SIZE(linux_sparc_fpu)
-
-static struct cpu_iu_info linux_sparc_chips[] = {
-  /* Sun4/100, 4/200, SLC */
-  { 0, 0, "Fujitsu  MB86900/1A or LSI L64831 SparcKIT-40"},
-  /* borned STP1012PGA */
-  { 0, 4, "Fujitsu  MB86904"},
-  { 0, 5, "Fujitsu TurboSparc MB86907"},
-  /* SparcStation2, SparcServer 490 & 690 */
-  { 1, 0, "LSI Logic Corporation - L64811"},
-  /* SparcStation2 */
-  { 1, 1, "Cypress/ROSS CY7C601"},
-  /* Embedded controller */
-  { 1, 3, "Cypress/ROSS CY7C611"},
-  /* Ross Technologies HyperSparc */
-  { 1, 0xf, "ROSS HyperSparc RT620"},
-  { 1, 0xe, "ROSS HyperSparc RT625 or RT626"},
-  /* ECL Implementation, CRAY S-MP Supercomputer... AIEEE! */
-  /* Someone please write the code to support this beast! ;) */
-  { 2, 0, "Bipolar Integrated Technology - B5010"},
-  { 3, 0, "LSI Logic Corporation - unknown-type"},
-  { 4, 0, "Texas Instruments, Inc. - SuperSparc-(II)"},
-  /* SparcClassic  --  borned STP1010TAB-50*/
-  { 4, 1, "Texas Instruments, Inc. - MicroSparc"},
-  { 4, 2, "Texas Instruments, Inc. - MicroSparc II"},
-  { 4, 3, "Texas Instruments, Inc. - SuperSparc 51"},
-  { 4, 4, "Texas Instruments, Inc. - SuperSparc 61"},
-  { 4, 5, "Texas Instruments, Inc. - unknown"},
-  { 5, 0, "Matsushita - MN10501"},
-  { 6, 0, "Philips Corporation - unknown"},
-  { 7, 0, "Harvest VLSI Design Center, Inc. - unknown"},
-  /* Gallium arsenide 200MHz, BOOOOGOOOOMIPS!!! */
-  { 8, 0, "Systems and Processes Engineering Corporation (SPEC)"},
-  { 9, 0, "Fujitsu or Weitek Power-UP"},
-  { 9, 1, "Fujitsu or Weitek Power-UP"},
-  { 9, 2, "Fujitsu or Weitek Power-UP"},
-  { 9, 3, "Fujitsu or Weitek Power-UP"},
-  { 0xa, 0, "UNKNOWN CPU-VENDOR/TYPE"},
-  { 0xb, 0, "UNKNOWN CPU-VENDOR/TYPE"},
-  { 0xc, 0, "UNKNOWN CPU-VENDOR/TYPE"},
-  { 0xd, 0, "UNKNOWN CPU-VENDOR/TYPE"},
-  { 0xe, 0, "UNKNOWN CPU-VENDOR/TYPE"},
-  { 0xf, 0, "UNKNOWN CPU-VENDOR/TYPE"},
-};
+const char *sparc_cpu_type;
+const char *sparc_fpu_type;
 
-#define NSPARCCHIPS  ARRAY_SIZE(linux_sparc_chips)
+unsigned int fsr_storage;
 
-char *sparc_cpu_type;
-char *sparc_fpu_type;
+static void set_cpu_and_fpu(int psr_impl, int psr_vers, int fpu_vers)
+{
+	sparc_cpu_type = NULL;
+	sparc_fpu_type = NULL;
+	if (psr_impl < ARRAY_SIZE(manufacturer_info))
+	{
+		const struct cpu_info *cpu;
+		const struct fpu_info *fpu;
 
-unsigned int fsr_storage;
+		cpu = &manufacturer_info[psr_impl].cpu_info[0];
+		while (cpu->psr_vers != -1)
+		{
+			if (cpu->psr_vers == psr_vers) {
+				sparc_cpu_type = cpu->name;
+				sparc_fpu_type = "No FPU";
+				break;
+			}
+			cpu++;
+		}
+		fpu =  &manufacturer_info[psr_impl].fpu_info[0];
+		while (fpu->fp_vers != -1)
+		{
+			if (fpu->fp_vers == fpu_vers) {
+				sparc_fpu_type = fpu->name;
+				break;
+			}
+			fpu++;
+		}
+	}
+	if (sparc_cpu_type == NULL)
+	{
+		printk(KERN_ERR "CPU: Unknown chip, impl[0x%x] vers[0x%x]\n",
+		       psr_impl, psr_vers);
+		sparc_cpu_type = "Unknown CPU";
+	}
+	if (sparc_fpu_type == NULL)
+	{
+		printk(KERN_ERR "FPU: Unknown chip, impl[0x%x] vers[0x%x]\n",
+		       psr_impl, fpu_vers);
+		sparc_fpu_type = "Unknown FPU";
+	}
+}
 
+#ifdef CONFIG_SPARC32
 void __cpuinit cpu_probe(void)
 {
 	int psr_impl, psr_vers, fpu_vers;
-	int i, psr;
+	int psr;
 
-	psr_impl = ((get_psr()>>28)&0xf);
-	psr_vers = ((get_psr()>>24)&0xf);
+	psr_impl = ((get_psr() >> 28) & 0xf);
+	psr_vers = ((get_psr() >> 24) & 0xf);
 
 	psr = get_psr();
 	put_psr(psr | PSR_EF);
-	fpu_vers = ((get_fsr()>>17)&0x7);
+	fpu_vers = ((get_fsr() >> 17) & 0x7);
 	put_psr(psr);
 
-	for(i = 0; i<NSPARCCHIPS; i++) {
-		if(linux_sparc_chips[i].psr_impl == psr_impl)
-			if(linux_sparc_chips[i].psr_vers == psr_vers) {
-				sparc_cpu_type = linux_sparc_chips[i].cpu_name;
-				break;
-			}
-	}
+	set_cpu_and_fpu(psr_impl, psr_vers, fpu_vers);
+}
+#else
+static void __init sun4v_cpu_probe(void)
+{
+	switch (sun4v_chip_type) {
+	case SUN4V_CHIP_NIAGARA1:
+		sparc_cpu_type = "UltraSparc T1 (Niagara)";
+		sparc_fpu_type = "UltraSparc T1 integrated FPU";
+		break;
 
-	if(i==NSPARCCHIPS)
-		printk("DEBUG: psr.impl = 0x%x   psr.vers = 0x%x\n", psr_impl, 
-			    psr_vers);
+	case SUN4V_CHIP_NIAGARA2:
+		sparc_cpu_type = "UltraSparc T2 (Niagara2)";
+		sparc_fpu_type = "UltraSparc T2 integrated FPU";
+		break;
 
-	for(i = 0; i<NSPARCFPU; i++) {
-		if(linux_sparc_fpu[i].psr_impl == psr_impl)
-			if(linux_sparc_fpu[i].fp_vers == fpu_vers) {
-				sparc_fpu_type = linux_sparc_fpu[i].fp_name;
-				break;
-			}
+	default:
+		printk(KERN_WARNING "CPU: Unknown sun4v cpu type [%s]\n",
+		       prom_cpu_compatible);
+		sparc_cpu_type = "Unknown SUN4V CPU";
+		sparc_fpu_type = "Unknown SUN4V FPU";
+		break;
 	}
+}
+
+static int __init cpu_type_probe(void)
+{
+	if (tlb_type == hypervisor) {
+		sun4v_cpu_probe();
+	} else {
+		unsigned long ver;
+		int manuf, impl;
 
-	if(i == NSPARCFPU) {
-		printk("DEBUG: psr.impl = 0x%x  fsr.vers = 0x%x\n", psr_impl,
-			    fpu_vers);
-		sparc_fpu_type = linux_sparc_fpu[31].fp_name;
+		__asm__ __volatile__("rdpr %%ver, %0" : "=r" (ver));
+
+		manuf = ((ver >> 48) & 0xffff);
+		impl = ((ver >> 32) & 0xffff);
+		set_cpu_and_fpu(manuf, impl, impl);
 	}
+	return 0;
 }
+
+arch_initcall(cpu_type_probe);
+#endif
diff --git a/arch/sparc/kernel/devices.c b/arch/sparc/kernel/devices.c
index ad656b044b8c..b171ae8de90d 100644
--- a/arch/sparc/kernel/devices.c
+++ b/arch/sparc/kernel/devices.c
@@ -133,14 +133,12 @@ void __init device_scan(void)
 #endif /* !CONFIG_SMP */
 
 	cpu_probe();
-#ifdef CONFIG_SUN_AUXIO
 	{
 		extern void auxio_probe(void);
 		extern void auxio_power_probe(void);
 		auxio_probe();
 		auxio_power_probe();
 	}
-#endif
 	clock_stop_probe();
 
 	if (ARCH_SUN4C)
diff --git a/arch/sparc64/kernel/ds.c b/arch/sparc/kernel/ds.c
index f52e0534d91d..f52e0534d91d 100644
--- a/arch/sparc64/kernel/ds.c
+++ b/arch/sparc/kernel/ds.c
diff --git a/arch/sparc64/kernel/dtlb_miss.S b/arch/sparc/kernel/dtlb_miss.S
index 09a6a15a7105..09a6a15a7105 100644
--- a/arch/sparc64/kernel/dtlb_miss.S
+++ b/arch/sparc/kernel/dtlb_miss.S
diff --git a/arch/sparc64/kernel/dtlb_prot.S b/arch/sparc/kernel/dtlb_prot.S
index b2c2c5be281c..b2c2c5be281c 100644
--- a/arch/sparc64/kernel/dtlb_prot.S
+++ b/arch/sparc/kernel/dtlb_prot.S
diff --git a/arch/sparc64/kernel/ebus.c b/arch/sparc/kernel/ebus.c
index 77dbf6d45faf..77dbf6d45faf 100644
--- a/arch/sparc64/kernel/ebus.c
+++ b/arch/sparc/kernel/ebus.c
diff --git a/arch/sparc64/kernel/entry.h b/arch/sparc/kernel/entry.h
index 34d7ab5e10d2..a9ab19aa0411 100644
--- a/arch/sparc64/kernel/entry.h
+++ b/arch/sparc/kernel/entry.h
@@ -5,9 +5,6 @@
 #include <linux/types.h>
 #include <linux/init.h>
 
-extern const char *sparc_cpu_type;
-extern const char *sparc_fpu_type;
-
 extern void __init per_cpu_patch(void);
 extern void __init sun4v_patch(void);
 extern void __init boot_cpu_id_too_large(int cpu);
diff --git a/arch/sparc/kernel/etrap.S b/arch/sparc/kernel/etrap_32.S
index e806fcdc46db..e806fcdc46db 100644
--- a/arch/sparc/kernel/etrap.S
+++ b/arch/sparc/kernel/etrap_32.S
diff --git a/arch/sparc64/kernel/etrap.S b/arch/sparc/kernel/etrap_64.S
index 29ce489bc188..786b185e6e3f 100644
--- a/arch/sparc64/kernel/etrap.S
+++ b/arch/sparc/kernel/etrap_64.S
@@ -16,9 +16,9 @@
 #include <asm/mmu.h>
 
 #define		TASK_REGOFF		(THREAD_SIZE-TRACEREG_SZ-STACKFRAME_SZ)
-#define		ETRAP_PSTATE1		(PSTATE_RMO | PSTATE_PRIV)
+#define		ETRAP_PSTATE1		(PSTATE_TSO | PSTATE_PRIV)
 #define		ETRAP_PSTATE2		\
-		(PSTATE_RMO | PSTATE_PEF | PSTATE_PRIV | PSTATE_IE)
+		(PSTATE_TSO | PSTATE_PEF | PSTATE_PRIV | PSTATE_IE)
 
 /*
  * On entry, %g7 is return address - 0x4.
@@ -130,7 +130,7 @@ etrap_save:	save	%g2, -STACK_BIAS, %sp
 		stx	%g6, [%sp + PTREGS_OFF + PT_V9_G6]
 		stx	%g7, [%sp + PTREGS_OFF + PT_V9_G7]
 		or	%l7, %l0, %l7
-		sethi	%hi(TSTATE_RMO | TSTATE_PEF), %l0
+		sethi	%hi(TSTATE_TSO | TSTATE_PEF), %l0
 		or	%l7, %l0, %l7
 		wrpr	%l2, %tnpc
 		wrpr	%l7, (TSTATE_PRIV | TSTATE_IE), %tstate
diff --git a/arch/sparc64/kernel/fpu_traps.S b/arch/sparc/kernel/fpu_traps.S
index a6864826a4bd..a6864826a4bd 100644
--- a/arch/sparc64/kernel/fpu_traps.S
+++ b/arch/sparc/kernel/fpu_traps.S
diff --git a/arch/sparc64/kernel/ftrace.c b/arch/sparc/kernel/ftrace.c
index d0218e73f982..d0218e73f982 100644
--- a/arch/sparc64/kernel/ftrace.c
+++ b/arch/sparc/kernel/ftrace.c
diff --git a/arch/sparc64/kernel/getsetcc.S b/arch/sparc/kernel/getsetcc.S
index a14d272d2061..a14d272d2061 100644
--- a/arch/sparc64/kernel/getsetcc.S
+++ b/arch/sparc/kernel/getsetcc.S
diff --git a/arch/sparc/kernel/head.S b/arch/sparc/kernel/head_32.S
index 51b40426f9c6..51b40426f9c6 100644
--- a/arch/sparc/kernel/head.S
+++ b/arch/sparc/kernel/head_32.S
diff --git a/arch/sparc64/kernel/head.S b/arch/sparc/kernel/head_64.S
index 353226fa0239..8ffee714f932 100644
--- a/arch/sparc64/kernel/head.S
+++ b/arch/sparc/kernel/head_64.S
@@ -706,7 +706,7 @@ setup_trap_table:
 	andn	%l0, PSTATE_IE, %o1
 	wrpr	%o1, 0x0, %pstate
 	rdpr	%pil, %l1
-	wrpr	%g0, 15, %pil
+	wrpr	%g0, PIL_NORMAL_MAX, %pil
 
 	/* Make the firmware call to jump over to the Linux trap table.  */
 	sethi	%hi(is_sun4v), %o0
@@ -825,8 +825,8 @@ setup_tba:
 	 restore
 sparc64_boot_end:
 
-#include "etrap.S"
-#include "rtrap.S"
+#include "etrap_64.S"
+#include "rtrap_64.S"
 #include "winfixup.S"
 #include "fpu_traps.S"
 #include "ivec.S"
@@ -882,7 +882,7 @@ swapper_4m_tsb:
 
 ! 0x0000000000428000
 
-#include "systbls.S"
+#include "systbls_64.S"
 
 	.data
 	.align	8
diff --git a/arch/sparc64/kernel/helpers.S b/arch/sparc/kernel/helpers.S
index 314dd0c9fc5b..314dd0c9fc5b 100644
--- a/arch/sparc64/kernel/helpers.S
+++ b/arch/sparc/kernel/helpers.S
diff --git a/arch/sparc64/kernel/hvapi.c b/arch/sparc/kernel/hvapi.c
index 1d272c3b5740..1d272c3b5740 100644
--- a/arch/sparc64/kernel/hvapi.c
+++ b/arch/sparc/kernel/hvapi.c
diff --git a/arch/sparc64/kernel/hvcalls.S b/arch/sparc/kernel/hvcalls.S
index e066269d1594..8a5f35ffb15e 100644
--- a/arch/sparc64/kernel/hvcalls.S
+++ b/arch/sparc/kernel/hvcalls.S
@@ -766,3 +766,35 @@ ENTRY(sun4v_mmu_demap_all)
 	retl
 	 nop
 ENDPROC(sun4v_mmu_demap_all)
+
+ENTRY(sun4v_niagara_getperf)
+	mov	%o0, %o4
+	mov	HV_FAST_GET_PERFREG, %o5
+	ta	HV_FAST_TRAP
+	stx	%o1, [%o4]
+	retl
+	 nop
+ENDPROC(sun4v_niagara_getperf)
+
+ENTRY(sun4v_niagara_setperf)
+	mov	HV_FAST_SET_PERFREG, %o5
+	ta	HV_FAST_TRAP
+	retl
+	 nop
+ENDPROC(sun4v_niagara_setperf)
+
+ENTRY(sun4v_niagara2_getperf)
+	mov	%o0, %o4
+	mov	HV_FAST_N2_GET_PERFREG, %o5
+	ta	HV_FAST_TRAP
+	stx	%o1, [%o4]
+	retl
+	 nop
+ENDPROC(sun4v_niagara2_getperf)
+
+ENTRY(sun4v_niagara2_setperf)
+	mov	HV_FAST_N2_SET_PERFREG, %o5
+	ta	HV_FAST_TRAP
+	retl
+	 nop
+ENDPROC(sun4v_niagara2_setperf)
diff --git a/arch/sparc64/kernel/hvtramp.S b/arch/sparc/kernel/hvtramp.S
index 0236c43772fa..9365432904d6 100644
--- a/arch/sparc64/kernel/hvtramp.S
+++ b/arch/sparc/kernel/hvtramp.S
@@ -1,6 +1,6 @@
 /* hvtramp.S: Hypervisor start-cpu trampoline code.
  *
- * Copyright (C) 2007 David S. Miller <davem@davemloft.net>
+ * Copyright (C) 2007, 2008 David S. Miller <davem@davemloft.net>
  */
 
 #include <linux/init.h>
@@ -14,6 +14,7 @@
 #include <asm/ptrace.h>
 #include <asm/head.h>
 #include <asm/asi.h>
+#include <asm/pil.h>
 
 	__CPUINIT
 	.align		8
@@ -32,7 +33,7 @@
 	 */
 hv_cpu_startup:
 	SET_GL(0)
-	wrpr		%g0, 15, %pil
+	wrpr		%g0, PIL_NORMAL_MAX, %pil
 	wrpr		%g0, 0, %canrestore
 	wrpr		%g0, 0, %otherwin
 	wrpr		%g0, 6, %cansave
diff --git a/arch/sparc/kernel/idprom.c b/arch/sparc/kernel/idprom.c
index 223a6582e1e2..1b0bd9120c1c 100644
--- a/arch/sparc/kernel/idprom.c
+++ b/arch/sparc/kernel/idprom.c
@@ -11,35 +11,37 @@
 
 #include <asm/oplib.h>
 #include <asm/idprom.h>
-#include <asm/machines.h>  /* Fun with Sun released architectures. */
 
 struct idprom *idprom;
 static struct idprom idprom_buffer;
 
+#ifdef CONFIG_SPARC32
+#include <asm/machines.h>  /* Fun with Sun released architectures. */
+
 /* Here is the master table of Sun machines which use some implementation
  * of the Sparc CPU and have a meaningful IDPROM machtype value that we
  * know about.  See asm-sparc/machines.h for empirical constants.
  */
 static struct Sun_Machine_Models Sun_Machines[NUM_SUN_MACHINES] = {
 /* First, Sun4's */
-{ "Sun 4/100 Series", (SM_SUN4 | SM_4_110) },
-{ "Sun 4/200 Series", (SM_SUN4 | SM_4_260) },
-{ "Sun 4/300 Series", (SM_SUN4 | SM_4_330) },
-{ "Sun 4/400 Series", (SM_SUN4 | SM_4_470) },
+{ .name = "Sun 4/100 Series",        .id_machtype = (SM_SUN4 | SM_4_110) },
+{ .name = "Sun 4/200 Series",        .id_machtype = (SM_SUN4 | SM_4_260) },
+{ .name = "Sun 4/300 Series",        .id_machtype = (SM_SUN4 | SM_4_330) },
+{ .name = "Sun 4/400 Series",        .id_machtype = (SM_SUN4 | SM_4_470) },
 /* Now, Sun4c's */
-{ "Sun4c SparcStation 1", (SM_SUN4C | SM_4C_SS1) },
-{ "Sun4c SparcStation IPC", (SM_SUN4C | SM_4C_IPC) },
-{ "Sun4c SparcStation 1+", (SM_SUN4C | SM_4C_SS1PLUS) },
-{ "Sun4c SparcStation SLC", (SM_SUN4C | SM_4C_SLC) },
-{ "Sun4c SparcStation 2", (SM_SUN4C | SM_4C_SS2) },
-{ "Sun4c SparcStation ELC", (SM_SUN4C | SM_4C_ELC) },
-{ "Sun4c SparcStation IPX", (SM_SUN4C | SM_4C_IPX) },
+{ .name = "Sun4c SparcStation 1",    .id_machtype = (SM_SUN4C | SM_4C_SS1) },
+{ .name = "Sun4c SparcStation IPC",  .id_machtype = (SM_SUN4C | SM_4C_IPC) },
+{ .name = "Sun4c SparcStation 1+",   .id_machtype = (SM_SUN4C | SM_4C_SS1PLUS) },
+{ .name = "Sun4c SparcStation SLC",  .id_machtype = (SM_SUN4C | SM_4C_SLC) },
+{ .name = "Sun4c SparcStation 2",    .id_machtype = (SM_SUN4C | SM_4C_SS2) },
+{ .name = "Sun4c SparcStation ELC",  .id_machtype = (SM_SUN4C | SM_4C_ELC) },
+{ .name = "Sun4c SparcStation IPX",  .id_machtype = (SM_SUN4C | SM_4C_IPX) },
 /* Finally, early Sun4m's */
-{ "Sun4m SparcSystem600", (SM_SUN4M | SM_4M_SS60) },
-{ "Sun4m SparcStation10/20", (SM_SUN4M | SM_4M_SS50) },
-{ "Sun4m SparcStation5", (SM_SUN4M | SM_4M_SS40) },
+{ .name = "Sun4m SparcSystem600",    .id_machtype = (SM_SUN4M | SM_4M_SS60) },
+{ .name = "Sun4m SparcStation10/20", .id_machtype = (SM_SUN4M | SM_4M_SS50) },
+{ .name = "Sun4m SparcStation5",     .id_machtype = (SM_SUN4M | SM_4M_SS40) },
 /* One entry for the OBP arch's which are sun4d, sun4e, and newer sun4m's */
-{ "Sun4M OBP based system", (SM_SUN4M_OBP | 0x0) } };
+{ .name = "Sun4M OBP based system",  .id_machtype = (SM_SUN4M_OBP | 0x0) } };
 
 static void __init display_system_type(unsigned char machtype)
 {
@@ -47,21 +49,25 @@ static void __init display_system_type(unsigned char machtype)
 	register int i;
 
 	for (i = 0; i < NUM_SUN_MACHINES; i++) {
-		if(Sun_Machines[i].id_machtype == machtype) {
+		if (Sun_Machines[i].id_machtype == machtype) {
 			if (machtype != (SM_SUN4M_OBP | 0x00) ||
 			    prom_getproperty(prom_root_node, "banner-name",
 					     sysname, sizeof(sysname)) <= 0)
-				printk("TYPE: %s\n", Sun_Machines[i].name);
+				printk(KERN_WARNING "TYPE: %s\n",
+				       Sun_Machines[i].name);
 			else
-				printk("TYPE: %s\n", sysname);
+				printk(KERN_WARNING "TYPE: %s\n", sysname);
 			return;
 		}
 	}
 
-	prom_printf("IDPROM: Bogus id_machtype value, 0x%x\n", machtype);
-	prom_halt();
+	prom_printf("IDPROM: Warning, bogus id_machtype value, 0x%x\n", machtype);
 }
-
+#else
+static void __init display_system_type(unsigned char machtype)
+{
+}
+#endif
 /* Calculate the IDPROM checksum (xor of the data bytes). */
 static unsigned char __init calc_idprom_cksum(struct idprom *idprom)
 {
@@ -80,20 +86,16 @@ void __init idprom_init(void)
 
 	idprom = &idprom_buffer;
 
-	if (idprom->id_format != 0x01)  {
-		prom_printf("IDPROM: Unknown format type!\n");
-		prom_halt();
-	}
+	if (idprom->id_format != 0x01)
+		prom_printf("IDPROM: Warning, unknown format type!\n");
 
-	if (idprom->id_cksum != calc_idprom_cksum(idprom)) {
-		prom_printf("IDPROM: Checksum failure (nvram=%x, calc=%x)!\n",
+	if (idprom->id_cksum != calc_idprom_cksum(idprom))
+		prom_printf("IDPROM: Warning, checksum failure (nvram=%x, calc=%x)!\n",
 			    idprom->id_cksum, calc_idprom_cksum(idprom));
-		prom_halt();
-	}
 
 	display_system_type(idprom->id_machtype);
 
-	printk("Ethernet address: %x:%x:%x:%x:%x:%x\n",
+	printk(KERN_WARNING "Ethernet address: %02x:%02x:%02x:%02x:%02x:%02x\n",
 		    idprom->id_ethaddr[0], idprom->id_ethaddr[1],
 		    idprom->id_ethaddr[2], idprom->id_ethaddr[3],
 		    idprom->id_ethaddr[4], idprom->id_ethaddr[5]);
diff --git a/arch/sparc64/kernel/iommu.c b/arch/sparc/kernel/iommu.c
index 1cc1995531e2..1cc1995531e2 100644
--- a/arch/sparc64/kernel/iommu.c
+++ b/arch/sparc/kernel/iommu.c
diff --git a/arch/sparc64/kernel/iommu_common.h b/arch/sparc/kernel/iommu_common.h
index 591f5879039c..591f5879039c 100644
--- a/arch/sparc64/kernel/iommu_common.h
+++ b/arch/sparc/kernel/iommu_common.h
diff --git a/arch/sparc/kernel/irq.c b/arch/sparc/kernel/irq_32.c
index 93e1d1c65290..93e1d1c65290 100644
--- a/arch/sparc/kernel/irq.c
+++ b/arch/sparc/kernel/irq_32.c
diff --git a/arch/sparc64/kernel/irq.c b/arch/sparc/kernel/irq_64.c
index 52fc836f464d..a3ea2bcb95de 100644
--- a/arch/sparc64/kernel/irq.c
+++ b/arch/sparc/kernel/irq_64.c
@@ -775,6 +775,69 @@ void do_softirq(void)
 	local_irq_restore(flags);
 }
 
+static void unhandled_perf_irq(struct pt_regs *regs)
+{
+	unsigned long pcr, pic;
+
+	read_pcr(pcr);
+	read_pic(pic);
+
+	write_pcr(0);
+
+	printk(KERN_EMERG "CPU %d: Got unexpected perf counter IRQ.\n",
+	       smp_processor_id());
+	printk(KERN_EMERG "CPU %d: PCR[%016lx] PIC[%016lx]\n",
+	       smp_processor_id(), pcr, pic);
+}
+
+/* Almost a direct copy of the powerpc PMC code.  */
+static DEFINE_SPINLOCK(perf_irq_lock);
+static void *perf_irq_owner_caller; /* mostly for debugging */
+static void (*perf_irq)(struct pt_regs *regs) = unhandled_perf_irq;
+
+/* Invoked from level 15 PIL handler in trap table.  */
+void perfctr_irq(int irq, struct pt_regs *regs)
+{
+	clear_softint(1 << irq);
+	perf_irq(regs);
+}
+
+int register_perfctr_intr(void (*handler)(struct pt_regs *))
+{
+	int ret;
+
+	if (!handler)
+		return -EINVAL;
+
+	spin_lock(&perf_irq_lock);
+	if (perf_irq != unhandled_perf_irq) {
+		printk(KERN_WARNING "register_perfctr_intr: "
+		       "perf IRQ busy (reserved by caller %p)\n",
+		       perf_irq_owner_caller);
+		ret = -EBUSY;
+		goto out;
+	}
+
+	perf_irq_owner_caller = __builtin_return_address(0);
+	perf_irq = handler;
+
+	ret = 0;
+out:
+	spin_unlock(&perf_irq_lock);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(register_perfctr_intr);
+
+void release_perfctr_intr(void (*handler)(struct pt_regs *))
+{
+	spin_lock(&perf_irq_lock);
+	perf_irq_owner_caller = NULL;
+	perf_irq = unhandled_perf_irq;
+	spin_unlock(&perf_irq_lock);
+}
+EXPORT_SYMBOL_GPL(release_perfctr_intr);
+
 #ifdef CONFIG_HOTPLUG_CPU
 void fixup_irqs(void)
 {
diff --git a/arch/sparc64/kernel/itlb_miss.S b/arch/sparc/kernel/itlb_miss.S
index 5a8377b54955..5a8377b54955 100644
--- a/arch/sparc64/kernel/itlb_miss.S
+++ b/arch/sparc/kernel/itlb_miss.S
diff --git a/arch/sparc64/kernel/ivec.S b/arch/sparc/kernel/ivec.S
index d29f92ebca5e..d29f92ebca5e 100644
--- a/arch/sparc64/kernel/ivec.S
+++ b/arch/sparc/kernel/ivec.S
diff --git a/arch/sparc/kernel/kernel.h b/arch/sparc/kernel/kernel.h
new file mode 100644
index 000000000000..7f02aad2e1ab
--- /dev/null
+++ b/arch/sparc/kernel/kernel.h
@@ -0,0 +1,8 @@
+/* cpu.c */
+extern const char *sparc_cpu_type;
+extern const char *sparc_fpu_type;
+
+extern unsigned int fsr_storage;
+
+extern void cpu_probe(void);
+
diff --git a/arch/sparc/kernel/kgdb.c b/arch/sparc/kernel/kgdb_32.c
index 757805ce02ee..757805ce02ee 100644
--- a/arch/sparc/kernel/kgdb.c
+++ b/arch/sparc/kernel/kgdb_32.c
diff --git a/arch/sparc64/kernel/kgdb.c b/arch/sparc/kernel/kgdb_64.c
index fefbe6dc51be..fefbe6dc51be 100644
--- a/arch/sparc64/kernel/kgdb.c
+++ b/arch/sparc/kernel/kgdb_64.c
diff --git a/arch/sparc64/kernel/kprobes.c b/arch/sparc/kernel/kprobes.c
index 201a6e547e4a..201a6e547e4a 100644
--- a/arch/sparc64/kernel/kprobes.c
+++ b/arch/sparc/kernel/kprobes.c
diff --git a/arch/sparc64/kernel/kstack.h b/arch/sparc/kernel/kstack.h
index 4248d969272f..4248d969272f 100644
--- a/arch/sparc64/kernel/kstack.h
+++ b/arch/sparc/kernel/kstack.h
diff --git a/arch/sparc64/kernel/ktlb.S b/arch/sparc/kernel/ktlb.S
index cef8defcd7a9..cef8defcd7a9 100644
--- a/arch/sparc64/kernel/ktlb.S
+++ b/arch/sparc/kernel/ktlb.S
diff --git a/arch/sparc64/kernel/ldc.c b/arch/sparc/kernel/ldc.c
index d68982330f66..d68982330f66 100644
--- a/arch/sparc64/kernel/ldc.c
+++ b/arch/sparc/kernel/ldc.c
diff --git a/arch/sparc64/kernel/mdesc.c b/arch/sparc/kernel/mdesc.c
index dde52bcf5c64..dde52bcf5c64 100644
--- a/arch/sparc64/kernel/mdesc.c
+++ b/arch/sparc/kernel/mdesc.c
diff --git a/arch/sparc64/kernel/misctrap.S b/arch/sparc/kernel/misctrap.S
index 753b4f031bfb..753b4f031bfb 100644
--- a/arch/sparc64/kernel/misctrap.S
+++ b/arch/sparc/kernel/misctrap.S
diff --git a/arch/sparc/kernel/module.c b/arch/sparc/kernel/module_32.c
index 598682f31ebf..598682f31ebf 100644
--- a/arch/sparc/kernel/module.c
+++ b/arch/sparc/kernel/module_32.c
diff --git a/arch/sparc64/kernel/module.c b/arch/sparc/kernel/module_64.c
index 158484bf5999..158484bf5999 100644
--- a/arch/sparc64/kernel/module.c
+++ b/arch/sparc/kernel/module_64.c
diff --git a/arch/sparc/kernel/of_device.c b/arch/sparc/kernel/of_device_32.c
index 0a83bd737654..0a83bd737654 100644
--- a/arch/sparc/kernel/of_device.c
+++ b/arch/sparc/kernel/of_device_32.c
diff --git a/arch/sparc64/kernel/of_device.c b/arch/sparc/kernel/of_device_64.c
index 0f616ae3246c..0f616ae3246c 100644
--- a/arch/sparc64/kernel/of_device.c
+++ b/arch/sparc/kernel/of_device_64.c
diff --git a/arch/sparc64/kernel/pci.c b/arch/sparc/kernel/pci.c
index bdb7c0a6d83d..bdb7c0a6d83d 100644
--- a/arch/sparc64/kernel/pci.c
+++ b/arch/sparc/kernel/pci.c
diff --git a/arch/sparc64/kernel/pci_common.c b/arch/sparc/kernel/pci_common.c
index 23b88082d0b2..23b88082d0b2 100644
--- a/arch/sparc64/kernel/pci_common.c
+++ b/arch/sparc/kernel/pci_common.c
diff --git a/arch/sparc64/kernel/pci_fire.c b/arch/sparc/kernel/pci_fire.c
index 9462b68f4894..9462b68f4894 100644
--- a/arch/sparc64/kernel/pci_fire.c
+++ b/arch/sparc/kernel/pci_fire.c
diff --git a/arch/sparc64/kernel/pci_impl.h b/arch/sparc/kernel/pci_impl.h
index 03186824327e..03186824327e 100644
--- a/arch/sparc64/kernel/pci_impl.h
+++ b/arch/sparc/kernel/pci_impl.h
diff --git a/arch/sparc64/kernel/pci_msi.c b/arch/sparc/kernel/pci_msi.c
index 2e680f34f727..2e680f34f727 100644
--- a/arch/sparc64/kernel/pci_msi.c
+++ b/arch/sparc/kernel/pci_msi.c
diff --git a/arch/sparc64/kernel/pci_psycho.c b/arch/sparc/kernel/pci_psycho.c
index dfb3ec892987..dfb3ec892987 100644
--- a/arch/sparc64/kernel/pci_psycho.c
+++ b/arch/sparc/kernel/pci_psycho.c
diff --git a/arch/sparc64/kernel/pci_sabre.c b/arch/sparc/kernel/pci_sabre.c
index 713257b6963c..713257b6963c 100644
--- a/arch/sparc64/kernel/pci_sabre.c
+++ b/arch/sparc/kernel/pci_sabre.c
diff --git a/arch/sparc64/kernel/pci_schizo.c b/arch/sparc/kernel/pci_schizo.c
index 45d9dba1ba11..45d9dba1ba11 100644
--- a/arch/sparc64/kernel/pci_schizo.c
+++ b/arch/sparc/kernel/pci_schizo.c
diff --git a/arch/sparc64/kernel/pci_sun4v.c b/arch/sparc/kernel/pci_sun4v.c
index 34a1fded3941..34a1fded3941 100644
--- a/arch/sparc64/kernel/pci_sun4v.c
+++ b/arch/sparc/kernel/pci_sun4v.c
diff --git a/arch/sparc64/kernel/pci_sun4v.h b/arch/sparc/kernel/pci_sun4v.h
index 8e9fc3a5b4f5..8e9fc3a5b4f5 100644
--- a/arch/sparc64/kernel/pci_sun4v.h
+++ b/arch/sparc/kernel/pci_sun4v.h
diff --git a/arch/sparc64/kernel/pci_sun4v_asm.S b/arch/sparc/kernel/pci_sun4v_asm.S
index e606d46c6815..e606d46c6815 100644
--- a/arch/sparc64/kernel/pci_sun4v_asm.S
+++ b/arch/sparc/kernel/pci_sun4v_asm.S
diff --git a/arch/sparc/kernel/pcic.c b/arch/sparc/kernel/pcic.c
index 462584e55fba..75ed98be3edf 100644
--- a/arch/sparc/kernel/pcic.c
+++ b/arch/sparc/kernel/pcic.c
@@ -436,7 +436,7 @@ int pcic_present(void)
 	return pcic0_up;
 }
 
-static int __init pdev_to_pnode(struct linux_pbm_info *pbm, 
+static int __devinit pdev_to_pnode(struct linux_pbm_info *pbm,
 				    struct pci_dev *pdev)
 {
 	struct linux_prom_pci_registers regs[PROMREG_MAX];
diff --git a/arch/sparc64/kernel/power.c b/arch/sparc/kernel/power.c
index 076cad7f9757..076cad7f9757 100644
--- a/arch/sparc64/kernel/power.c
+++ b/arch/sparc/kernel/power.c
diff --git a/arch/sparc/kernel/process.c b/arch/sparc/kernel/process_32.c
index e8c43ffe317e..69d9315f4a93 100644
--- a/arch/sparc/kernel/process.c
+++ b/arch/sparc/kernel/process_32.c
@@ -168,11 +168,9 @@ void machine_restart(char * cmd)
 
 void machine_power_off(void)
 {
-#ifdef CONFIG_SUN_AUXIO
 	if (auxio_power_register &&
 	    (strcmp(of_console_device->type, "serial") || scons_pwroff))
 		*auxio_power_register |= AUXIO_POWER_OFF;
-#endif
 	machine_halt();
 }
 
diff --git a/arch/sparc64/kernel/process.c b/arch/sparc/kernel/process_64.c
index d5e2acef9877..d5e2acef9877 100644
--- a/arch/sparc64/kernel/process.c
+++ b/arch/sparc/kernel/process_64.c
diff --git a/arch/sparc/kernel/prom.h b/arch/sparc/kernel/prom.h
new file mode 100644
index 000000000000..bb0f0fda6cab
--- /dev/null
+++ b/arch/sparc/kernel/prom.h
@@ -0,0 +1,29 @@
+#ifndef __PROM_H
+#define __PROM_H
+
+#include <linux/spinlock.h>
+#include <asm/prom.h>
+
+extern struct device_node *allnodes;	/* temporary while merging */
+extern rwlock_t devtree_lock;	/* temporary while merging */
+
+extern void * prom_early_alloc(unsigned long size);
+extern void irq_trans_init(struct device_node *dp);
+
+extern unsigned int prom_unique_id;
+
+static inline int is_root_node(const struct device_node *dp)
+{
+	if (!dp)
+		return 0;
+
+	return (dp->parent == NULL);
+}
+
+extern char *build_path_component(struct device_node *dp);
+extern void of_console_init(void);
+extern void of_fill_in_cpu_data(void);
+
+extern unsigned int prom_early_allocated;
+
+#endif /* __PROM_H */
diff --git a/arch/sparc/kernel/prom.c b/arch/sparc/kernel/prom_32.c
index eee5efcfe50e..fe43e80772db 100644
--- a/arch/sparc/kernel/prom.c
+++ b/arch/sparc/kernel/prom_32.c
@@ -25,107 +25,9 @@
 #include <asm/prom.h>
 #include <asm/oplib.h>
 
-extern struct device_node *allnodes;	/* temporary while merging */
+#include "prom.h"
 
-extern rwlock_t devtree_lock;	/* temporary while merging */
-
-struct device_node *of_find_node_by_phandle(phandle handle)
-{
-	struct device_node *np;
-
-	for (np = allnodes; np != 0; np = np->allnext)
-		if (np->node == handle)
-			break;
-
-	return np;
-}
-EXPORT_SYMBOL(of_find_node_by_phandle);
-
-int of_getintprop_default(struct device_node *np, const char *name, int def)
-{
-	struct property *prop;
-	int len;
-
-	prop = of_find_property(np, name, &len);
-	if (!prop || len != 4)
-		return def;
-
-	return *(int *) prop->value;
-}
-EXPORT_SYMBOL(of_getintprop_default);
-
-DEFINE_MUTEX(of_set_property_mutex);
-EXPORT_SYMBOL(of_set_property_mutex);
-
-int of_set_property(struct device_node *dp, const char *name, void *val, int len)
-{
-	struct property **prevp;
-	void *new_val;
-	int err;
-
-	new_val = kmalloc(len, GFP_KERNEL);
-	if (!new_val)
-		return -ENOMEM;
-
-	memcpy(new_val, val, len);
-
-	err = -ENODEV;
-
-	write_lock(&devtree_lock);
-	prevp = &dp->properties;
-	while (*prevp) {
-		struct property *prop = *prevp;
-
-		if (!strcasecmp(prop->name, name)) {
-			void *old_val = prop->value;
-			int ret;
-
-			mutex_lock(&of_set_property_mutex);
-			ret = prom_setprop(dp->node, (char *) name, val, len);
-			mutex_unlock(&of_set_property_mutex);
-
-			err = -EINVAL;
-			if (ret >= 0) {
-				prop->value = new_val;
-				prop->length = len;
-
-				if (OF_IS_DYNAMIC(prop))
-					kfree(old_val);
-
-				OF_MARK_DYNAMIC(prop);
-
-				err = 0;
-			}
-			break;
-		}
-		prevp = &(*prevp)->next;
-	}
-	write_unlock(&devtree_lock);
-
-	/* XXX Upate procfs if necessary... */
-
-	return err;
-}
-EXPORT_SYMBOL(of_set_property);
-
-int of_find_in_proplist(const char *list, const char *match, int len)
-{
-	while (len > 0) {
-		int l;
-
-		if (!strcmp(list, match))
-			return 1;
-		l = strlen(list) + 1;
-		list += l;
-		len -= l;
-	}
-	return 0;
-}
-EXPORT_SYMBOL(of_find_in_proplist);
-
-static unsigned int prom_early_allocated;
-
-static void * __init prom_early_alloc(unsigned long size)
+void * __init prom_early_alloc(unsigned long size)
 {
 	void *ret;
 
@@ -138,14 +40,6 @@ static void * __init prom_early_alloc(unsigned long size)
 	return ret;
 }
 
-static int is_root_node(const struct device_node *dp)
-{
-	if (!dp)
-		return 0;
-
-	return (dp->parent == NULL);
-}
-
 /* The following routines deal with the black magic of fully naming a
  * node.
  *
@@ -257,7 +151,7 @@ static void __init __build_path_component(struct device_node *dp, char *tmp_buf)
 	return sparc32_path_component(dp, tmp_buf);
 }
 
-static char * __init build_path_component(struct device_node *dp)
+char * __init build_path_component(struct device_node *dp)
 {
 	char tmp_buf[64], *n;
 
@@ -272,164 +166,9 @@ static char * __init build_path_component(struct device_node *dp)
 	return n;
 }
 
-static char * __init build_full_name(struct device_node *dp)
-{
-	int len, ourlen, plen;
-	char *n;
-
-	plen = strlen(dp->parent->full_name);
-	ourlen = strlen(dp->path_component_name);
-	len = ourlen + plen + 2;
-
-	n = prom_early_alloc(len);
-	strcpy(n, dp->parent->full_name);
-	if (!is_root_node(dp->parent)) {
-		strcpy(n + plen, "/");
-		plen++;
-	}
-	strcpy(n + plen, dp->path_component_name);
-
-	return n;
-}
-
-static unsigned int unique_id;
-
-static struct property * __init build_one_prop(phandle node, char *prev, char *special_name, void *special_val, int special_len)
-{
-	static struct property *tmp = NULL;
-	struct property *p;
-	int len;
-	const char *name;
-
-	if (tmp) {
-		p = tmp;
-		memset(p, 0, sizeof(*p) + 32);
-		tmp = NULL;
-	} else {
-		p = prom_early_alloc(sizeof(struct property) + 32);
-		p->unique_id = unique_id++;
-	}
-
-	p->name = (char *) (p + 1);
-	if (special_name) {
-		strcpy(p->name, special_name);
-		p->length = special_len;
-		p->value = prom_early_alloc(special_len);
-		memcpy(p->value, special_val, special_len);
-	} else {
-		if (prev == NULL) {
-			name = prom_firstprop(node, NULL);
-		} else {
-			name = prom_nextprop(node, prev, NULL);
-		}
-		if (strlen(name) == 0) {
-			tmp = p;
-			return NULL;
-		}
-		strcpy(p->name, name);
-		p->length = prom_getproplen(node, p->name);
-		if (p->length <= 0) {
-			p->length = 0;
-		} else {
-			p->value = prom_early_alloc(p->length + 1);
-			len = prom_getproperty(node, p->name, p->value,
-					       p->length);
-			if (len <= 0)
-				p->length = 0;
-			((unsigned char *)p->value)[p->length] = '\0';
-		}
-	}
-	return p;
-}
-
-static struct property * __init build_prop_list(phandle node)
-{
-	struct property *head, *tail;
-
-	head = tail = build_one_prop(node, NULL,
-				     ".node", &node, sizeof(node));
-
-	tail->next = build_one_prop(node, NULL, NULL, NULL, 0);
-	tail = tail->next;
-	while(tail) {
-		tail->next = build_one_prop(node, tail->name,
-					    NULL, NULL, 0);
-		tail = tail->next;
-	}
-
-	return head;
-}
-
-static char * __init get_one_property(phandle node, char *name)
-{
-	char *buf = "<NULL>";
-	int len;
-
-	len = prom_getproplen(node, name);
-	if (len > 0) {
-		buf = prom_early_alloc(len);
-		len = prom_getproperty(node, name, buf, len);
-	}
-
-	return buf;
-}
-
-static struct device_node * __init create_node(phandle node)
-{
-	struct device_node *dp;
-
-	if (!node)
-		return NULL;
-
-	dp = prom_early_alloc(sizeof(*dp));
-	dp->unique_id = unique_id++;
-
-	kref_init(&dp->kref);
-
-	dp->name = get_one_property(node, "name");
-	dp->type = get_one_property(node, "device_type");
-	dp->node = node;
-
-	/* Build interrupts later... */
-
-	dp->properties = build_prop_list(node);
-
-	return dp;
-}
-
-static struct device_node * __init build_tree(struct device_node *parent, phandle node, struct device_node ***nextp)
-{
-	struct device_node *dp;
-
-	dp = create_node(node);
-	if (dp) {
-		*(*nextp) = dp;
-		*nextp = &dp->allnext;
-
-		dp->parent = parent;
-		dp->path_component_name = build_path_component(dp);
-		dp->full_name = build_full_name(dp);
-
-		dp->child = build_tree(dp, prom_getchild(node), nextp);
-
-		dp->sibling = build_tree(parent, prom_getsibling(node), nextp);
-	}
-
-	return dp;
-}
-
-struct device_node *of_console_device;
-EXPORT_SYMBOL(of_console_device);
-
-char *of_console_path;
-EXPORT_SYMBOL(of_console_path);
-
-char *of_console_options;
-EXPORT_SYMBOL(of_console_options);
-
 extern void restore_current(void);
 
-static void __init of_console_init(void)
+void __init of_console_init(void)
 {
 	char *msg = "OF stdout device is: %s\n";
 	struct device_node *dp;
@@ -547,20 +286,10 @@ static void __init of_console_init(void)
 	printk(msg, of_console_path);
 }
 
-void __init prom_build_devicetree(void)
+void __init of_fill_in_cpu_data(void)
 {
-	struct device_node **nextp;
-
-	allnodes = create_node(prom_root_node);
-	allnodes->path_component_name = "";
-	allnodes->full_name = "/";
-
-	nextp = &allnodes->allnext;
-	allnodes->child = build_tree(allnodes,
-				     prom_getchild(allnodes->node),
-				     &nextp);
-	of_console_init();
+}
 
-	printk("PROM: Built device tree with %u bytes of memory.\n",
-	       prom_early_allocated);
+void __init irq_trans_init(struct device_node *dp)
+{
 }
diff --git a/arch/sparc/kernel/prom_64.c b/arch/sparc/kernel/prom_64.c
new file mode 100644
index 000000000000..edecca7b8116
--- /dev/null
+++ b/arch/sparc/kernel/prom_64.c
@@ -0,0 +1,571 @@
+/*
+ * Procedures for creating, accessing and interpreting the device tree.
+ *
+ * Paul Mackerras	August 1996.
+ * Copyright (C) 1996-2005 Paul Mackerras.
+ * 
+ *  Adapted for 64bit PowerPC by Dave Engebretsen and Peter Bergner.
+ *    {engebret|bergner}@us.ibm.com 
+ *
+ *  Adapted for sparc64 by David S. Miller davem@davemloft.net
+ *
+ *      This program is free software; you can redistribute it and/or
+ *      modify it under the terms of the GNU General Public License
+ *      as published by the Free Software Foundation; either version
+ *      2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/string.h>
+#include <linux/mm.h>
+#include <linux/module.h>
+#include <linux/lmb.h>
+#include <linux/of_device.h>
+
+#include <asm/prom.h>
+#include <asm/oplib.h>
+#include <asm/irq.h>
+#include <asm/asi.h>
+#include <asm/upa.h>
+#include <asm/smp.h>
+
+#include "prom.h"
+
+void * __init prom_early_alloc(unsigned long size)
+{
+	unsigned long paddr = lmb_alloc(size, SMP_CACHE_BYTES);
+	void *ret;
+
+	if (!paddr) {
+		prom_printf("prom_early_alloc(%lu) failed\n");
+		prom_halt();
+	}
+
+	ret = __va(paddr);
+	memset(ret, 0, size);
+	prom_early_allocated += size;
+
+	return ret;
+}
+
+/* The following routines deal with the black magic of fully naming a
+ * node.
+ *
+ * Certain well known named nodes are just the simple name string.
+ *
+ * Actual devices have an address specifier appended to the base name
+ * string, like this "foo@addr".  The "addr" can be in any number of
+ * formats, and the platform plus the type of the node determine the
+ * format and how it is constructed.
+ *
+ * For children of the ROOT node, the naming convention is fixed and
+ * determined by whether this is a sun4u or sun4v system.
+ *
+ * For children of other nodes, it is bus type specific.  So
+ * we walk up the tree until we discover a "device_type" property
+ * we recognize and we go from there.
+ *
+ * As an example, the boot device on my workstation has a full path:
+ *
+ *	/pci@1e,600000/ide@d/disk@0,0:c
+ */
+static void __init sun4v_path_component(struct device_node *dp, char *tmp_buf)
+{
+	struct linux_prom64_registers *regs;
+	struct property *rprop;
+	u32 high_bits, low_bits, type;
+
+	rprop = of_find_property(dp, "reg", NULL);
+	if (!rprop)
+		return;
+
+	regs = rprop->value;
+	if (!is_root_node(dp->parent)) {
+		sprintf(tmp_buf, "%s@%x,%x",
+			dp->name,
+			(unsigned int) (regs->phys_addr >> 32UL),
+			(unsigned int) (regs->phys_addr & 0xffffffffUL));
+		return;
+	}
+
+	type = regs->phys_addr >> 60UL;
+	high_bits = (regs->phys_addr >> 32UL) & 0x0fffffffUL;
+	low_bits = (regs->phys_addr & 0xffffffffUL);
+
+	if (type == 0 || type == 8) {
+		const char *prefix = (type == 0) ? "m" : "i";
+
+		if (low_bits)
+			sprintf(tmp_buf, "%s@%s%x,%x",
+				dp->name, prefix,
+				high_bits, low_bits);
+		else
+			sprintf(tmp_buf, "%s@%s%x",
+				dp->name,
+				prefix,
+				high_bits);
+	} else if (type == 12) {
+		sprintf(tmp_buf, "%s@%x",
+			dp->name, high_bits);
+	}
+}
+
+static void __init sun4u_path_component(struct device_node *dp, char *tmp_buf)
+{
+	struct linux_prom64_registers *regs;
+	struct property *prop;
+
+	prop = of_find_property(dp, "reg", NULL);
+	if (!prop)
+		return;
+
+	regs = prop->value;
+	if (!is_root_node(dp->parent)) {
+		sprintf(tmp_buf, "%s@%x,%x",
+			dp->name,
+			(unsigned int) (regs->phys_addr >> 32UL),
+			(unsigned int) (regs->phys_addr & 0xffffffffUL));
+		return;
+	}
+
+	prop = of_find_property(dp, "upa-portid", NULL);
+	if (!prop)
+		prop = of_find_property(dp, "portid", NULL);
+	if (prop) {
+		unsigned long mask = 0xffffffffUL;
+
+		if (tlb_type >= cheetah)
+			mask = 0x7fffff;
+
+		sprintf(tmp_buf, "%s@%x,%x",
+			dp->name,
+			*(u32 *)prop->value,
+			(unsigned int) (regs->phys_addr & mask));
+	}
+}
+
+/* "name@slot,offset"  */
+static void __init sbus_path_component(struct device_node *dp, char *tmp_buf)
+{
+	struct linux_prom_registers *regs;
+	struct property *prop;
+
+	prop = of_find_property(dp, "reg", NULL);
+	if (!prop)
+		return;
+
+	regs = prop->value;
+	sprintf(tmp_buf, "%s@%x,%x",
+		dp->name,
+		regs->which_io,
+		regs->phys_addr);
+}
+
+/* "name@devnum[,func]" */
+static void __init pci_path_component(struct device_node *dp, char *tmp_buf)
+{
+	struct linux_prom_pci_registers *regs;
+	struct property *prop;
+	unsigned int devfn;
+
+	prop = of_find_property(dp, "reg", NULL);
+	if (!prop)
+		return;
+
+	regs = prop->value;
+	devfn = (regs->phys_hi >> 8) & 0xff;
+	if (devfn & 0x07) {
+		sprintf(tmp_buf, "%s@%x,%x",
+			dp->name,
+			devfn >> 3,
+			devfn & 0x07);
+	} else {
+		sprintf(tmp_buf, "%s@%x",
+			dp->name,
+			devfn >> 3);
+	}
+}
+
+/* "name@UPA_PORTID,offset" */
+static void __init upa_path_component(struct device_node *dp, char *tmp_buf)
+{
+	struct linux_prom64_registers *regs;
+	struct property *prop;
+
+	prop = of_find_property(dp, "reg", NULL);
+	if (!prop)
+		return;
+
+	regs = prop->value;
+
+	prop = of_find_property(dp, "upa-portid", NULL);
+	if (!prop)
+		return;
+
+	sprintf(tmp_buf, "%s@%x,%x",
+		dp->name,
+		*(u32 *) prop->value,
+		(unsigned int) (regs->phys_addr & 0xffffffffUL));
+}
+
+/* "name@reg" */
+static void __init vdev_path_component(struct device_node *dp, char *tmp_buf)
+{
+	struct property *prop;
+	u32 *regs;
+
+	prop = of_find_property(dp, "reg", NULL);
+	if (!prop)
+		return;
+
+	regs = prop->value;
+
+	sprintf(tmp_buf, "%s@%x", dp->name, *regs);
+}
+
+/* "name@addrhi,addrlo" */
+static void __init ebus_path_component(struct device_node *dp, char *tmp_buf)
+{
+	struct linux_prom64_registers *regs;
+	struct property *prop;
+
+	prop = of_find_property(dp, "reg", NULL);
+	if (!prop)
+		return;
+
+	regs = prop->value;
+
+	sprintf(tmp_buf, "%s@%x,%x",
+		dp->name,
+		(unsigned int) (regs->phys_addr >> 32UL),
+		(unsigned int) (regs->phys_addr & 0xffffffffUL));
+}
+
+/* "name@bus,addr" */
+static void __init i2c_path_component(struct device_node *dp, char *tmp_buf)
+{
+	struct property *prop;
+	u32 *regs;
+
+	prop = of_find_property(dp, "reg", NULL);
+	if (!prop)
+		return;
+
+	regs = prop->value;
+
+	/* This actually isn't right... should look at the #address-cells
+	 * property of the i2c bus node etc. etc.
+	 */
+	sprintf(tmp_buf, "%s@%x,%x",
+		dp->name, regs[0], regs[1]);
+}
+
+/* "name@reg0[,reg1]" */
+static void __init usb_path_component(struct device_node *dp, char *tmp_buf)
+{
+	struct property *prop;
+	u32 *regs;
+
+	prop = of_find_property(dp, "reg", NULL);
+	if (!prop)
+		return;
+
+	regs = prop->value;
+
+	if (prop->length == sizeof(u32) || regs[1] == 1) {
+		sprintf(tmp_buf, "%s@%x",
+			dp->name, regs[0]);
+	} else {
+		sprintf(tmp_buf, "%s@%x,%x",
+			dp->name, regs[0], regs[1]);
+	}
+}
+
+/* "name@reg0reg1[,reg2reg3]" */
+static void __init ieee1394_path_component(struct device_node *dp, char *tmp_buf)
+{
+	struct property *prop;
+	u32 *regs;
+
+	prop = of_find_property(dp, "reg", NULL);
+	if (!prop)
+		return;
+
+	regs = prop->value;
+
+	if (regs[2] || regs[3]) {
+		sprintf(tmp_buf, "%s@%08x%08x,%04x%08x",
+			dp->name, regs[0], regs[1], regs[2], regs[3]);
+	} else {
+		sprintf(tmp_buf, "%s@%08x%08x",
+			dp->name, regs[0], regs[1]);
+	}
+}
+
+static void __init __build_path_component(struct device_node *dp, char *tmp_buf)
+{
+	struct device_node *parent = dp->parent;
+
+	if (parent != NULL) {
+		if (!strcmp(parent->type, "pci") ||
+		    !strcmp(parent->type, "pciex")) {
+			pci_path_component(dp, tmp_buf);
+			return;
+		}
+		if (!strcmp(parent->type, "sbus")) {
+			sbus_path_component(dp, tmp_buf);
+			return;
+		}
+		if (!strcmp(parent->type, "upa")) {
+			upa_path_component(dp, tmp_buf);
+			return;
+		}
+		if (!strcmp(parent->type, "ebus")) {
+			ebus_path_component(dp, tmp_buf);
+			return;
+		}
+		if (!strcmp(parent->name, "usb") ||
+		    !strcmp(parent->name, "hub")) {
+			usb_path_component(dp, tmp_buf);
+			return;
+		}
+		if (!strcmp(parent->type, "i2c")) {
+			i2c_path_component(dp, tmp_buf);
+			return;
+		}
+		if (!strcmp(parent->type, "firewire")) {
+			ieee1394_path_component(dp, tmp_buf);
+			return;
+		}
+		if (!strcmp(parent->type, "virtual-devices")) {
+			vdev_path_component(dp, tmp_buf);
+			return;
+		}
+		/* "isa" is handled with platform naming */
+	}
+
+	/* Use platform naming convention.  */
+	if (tlb_type == hypervisor) {
+		sun4v_path_component(dp, tmp_buf);
+		return;
+	} else {
+		sun4u_path_component(dp, tmp_buf);
+	}
+}
+
+char * __init build_path_component(struct device_node *dp)
+{
+	char tmp_buf[64], *n;
+
+	tmp_buf[0] = '\0';
+	__build_path_component(dp, tmp_buf);
+	if (tmp_buf[0] == '\0')
+		strcpy(tmp_buf, dp->name);
+
+	n = prom_early_alloc(strlen(tmp_buf) + 1);
+	strcpy(n, tmp_buf);
+
+	return n;
+}
+
+static const char *get_mid_prop(void)
+{
+	return (tlb_type == spitfire ? "upa-portid" : "portid");
+}
+
+struct device_node *of_find_node_by_cpuid(int cpuid)
+{
+	struct device_node *dp;
+	const char *mid_prop = get_mid_prop();
+
+	for_each_node_by_type(dp, "cpu") {
+		int id = of_getintprop_default(dp, mid_prop, -1);
+		const char *this_mid_prop = mid_prop;
+
+		if (id < 0) {
+			this_mid_prop = "cpuid";
+			id = of_getintprop_default(dp, this_mid_prop, -1);
+		}
+
+		if (id < 0) {
+			prom_printf("OF: Serious problem, cpu lacks "
+				    "%s property", this_mid_prop);
+			prom_halt();
+		}
+		if (cpuid == id)
+			return dp;
+	}
+	return NULL;
+}
+
+void __init of_fill_in_cpu_data(void)
+{
+	struct device_node *dp;
+	const char *mid_prop;
+
+	if (tlb_type == hypervisor)
+		return;
+
+	mid_prop = get_mid_prop();
+	ncpus_probed = 0;
+	for_each_node_by_type(dp, "cpu") {
+		int cpuid = of_getintprop_default(dp, mid_prop, -1);
+		const char *this_mid_prop = mid_prop;
+		struct device_node *portid_parent;
+		int portid = -1;
+
+		portid_parent = NULL;
+		if (cpuid < 0) {
+			this_mid_prop = "cpuid";
+			cpuid = of_getintprop_default(dp, this_mid_prop, -1);
+			if (cpuid >= 0) {
+				int limit = 2;
+
+				portid_parent = dp;
+				while (limit--) {
+					portid_parent = portid_parent->parent;
+					if (!portid_parent)
+						break;
+					portid = of_getintprop_default(portid_parent,
+								       "portid", -1);
+					if (portid >= 0)
+						break;
+				}
+			}
+		}
+
+		if (cpuid < 0) {
+			prom_printf("OF: Serious problem, cpu lacks "
+				    "%s property", this_mid_prop);
+			prom_halt();
+		}
+
+		ncpus_probed++;
+
+#ifdef CONFIG_SMP
+		if (cpuid >= NR_CPUS) {
+			printk(KERN_WARNING "Ignoring CPU %d which is "
+			       ">= NR_CPUS (%d)\n",
+			       cpuid, NR_CPUS);
+			continue;
+		}
+#else
+		/* On uniprocessor we only want the values for the
+		 * real physical cpu the kernel booted onto, however
+		 * cpu_data() only has one entry at index 0.
+		 */
+		if (cpuid != real_hard_smp_processor_id())
+			continue;
+		cpuid = 0;
+#endif
+
+		cpu_data(cpuid).clock_tick =
+			of_getintprop_default(dp, "clock-frequency", 0);
+
+		if (portid_parent) {
+			cpu_data(cpuid).dcache_size =
+				of_getintprop_default(dp, "l1-dcache-size",
+						      16 * 1024);
+			cpu_data(cpuid).dcache_line_size =
+				of_getintprop_default(dp, "l1-dcache-line-size",
+						      32);
+			cpu_data(cpuid).icache_size =
+				of_getintprop_default(dp, "l1-icache-size",
+						      8 * 1024);
+			cpu_data(cpuid).icache_line_size =
+				of_getintprop_default(dp, "l1-icache-line-size",
+						      32);
+			cpu_data(cpuid).ecache_size =
+				of_getintprop_default(dp, "l2-cache-size", 0);
+			cpu_data(cpuid).ecache_line_size =
+				of_getintprop_default(dp, "l2-cache-line-size", 0);
+			if (!cpu_data(cpuid).ecache_size ||
+			    !cpu_data(cpuid).ecache_line_size) {
+				cpu_data(cpuid).ecache_size =
+					of_getintprop_default(portid_parent,
+							      "l2-cache-size",
+							      (4 * 1024 * 1024));
+				cpu_data(cpuid).ecache_line_size =
+					of_getintprop_default(portid_parent,
+							      "l2-cache-line-size", 64);
+			}
+
+			cpu_data(cpuid).core_id = portid + 1;
+			cpu_data(cpuid).proc_id = portid;
+#ifdef CONFIG_SMP
+			sparc64_multi_core = 1;
+#endif
+		} else {
+			cpu_data(cpuid).dcache_size =
+				of_getintprop_default(dp, "dcache-size", 16 * 1024);
+			cpu_data(cpuid).dcache_line_size =
+				of_getintprop_default(dp, "dcache-line-size", 32);
+
+			cpu_data(cpuid).icache_size =
+				of_getintprop_default(dp, "icache-size", 16 * 1024);
+			cpu_data(cpuid).icache_line_size =
+				of_getintprop_default(dp, "icache-line-size", 32);
+
+			cpu_data(cpuid).ecache_size =
+				of_getintprop_default(dp, "ecache-size",
+						      (4 * 1024 * 1024));
+			cpu_data(cpuid).ecache_line_size =
+				of_getintprop_default(dp, "ecache-line-size", 64);
+
+			cpu_data(cpuid).core_id = 0;
+			cpu_data(cpuid).proc_id = -1;
+		}
+
+#ifdef CONFIG_SMP
+		cpu_set(cpuid, cpu_present_map);
+		cpu_set(cpuid, cpu_possible_map);
+#endif
+	}
+
+	smp_fill_in_sib_core_maps();
+}
+
+void __init of_console_init(void)
+{
+	char *msg = "OF stdout device is: %s\n";
+	struct device_node *dp;
+	const char *type;
+	phandle node;
+
+	of_console_path = prom_early_alloc(256);
+	if (prom_ihandle2path(prom_stdout, of_console_path, 256) < 0) {
+		prom_printf("Cannot obtain path of stdout.\n");
+		prom_halt();
+	}
+	of_console_options = strrchr(of_console_path, ':');
+	if (of_console_options) {
+		of_console_options++;
+		if (*of_console_options == '\0')
+			of_console_options = NULL;
+	}
+
+	node = prom_inst2pkg(prom_stdout);
+	if (!node) {
+		prom_printf("Cannot resolve stdout node from "
+			    "instance %08x.\n", prom_stdout);
+		prom_halt();
+	}
+
+	dp = of_find_node_by_phandle(node);
+	type = of_get_property(dp, "device_type", NULL);
+	if (!type) {
+		prom_printf("Console stdout lacks device_type property.\n");
+		prom_halt();
+	}
+
+	if (strcmp(type, "display") && strcmp(type, "serial")) {
+		prom_printf("Console device_type is neither display "
+			    "nor serial.\n");
+		prom_halt();
+	}
+
+	of_console_device = dp;
+
+	printk(msg, of_console_path);
+}
diff --git a/arch/sparc/kernel/prom_common.c b/arch/sparc/kernel/prom_common.c
new file mode 100644
index 000000000000..4e9af593db49
--- /dev/null
+++ b/arch/sparc/kernel/prom_common.c
@@ -0,0 +1,326 @@
+/* prom_common.c: OF device tree support common code.
+ *
+ * Paul Mackerras	August 1996.
+ * Copyright (C) 1996-2005 Paul Mackerras.
+ *
+ *  Adapted for 64bit PowerPC by Dave Engebretsen and Peter Bergner.
+ *    {engebret|bergner}@us.ibm.com
+ *
+ *  Adapted for sparc by David S. Miller davem@davemloft.net
+ *
+ *      This program is free software; you can redistribute it and/or
+ *      modify it under the terms of the GNU General Public License
+ *      as published by the Free Software Foundation; either version
+ *      2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/errno.h>
+#include <linux/mutex.h>
+#include <linux/slab.h>
+#include <linux/of.h>
+#include <asm/prom.h>
+#include <asm/oplib.h>
+
+#include "prom.h"
+
+struct device_node *of_console_device;
+EXPORT_SYMBOL(of_console_device);
+
+char *of_console_path;
+EXPORT_SYMBOL(of_console_path);
+
+char *of_console_options;
+EXPORT_SYMBOL(of_console_options);
+
+struct device_node *of_find_node_by_phandle(phandle handle)
+{
+	struct device_node *np;
+
+	for (np = allnodes; np; np = np->allnext)
+		if (np->node == handle)
+			break;
+
+	return np;
+}
+EXPORT_SYMBOL(of_find_node_by_phandle);
+
+int of_getintprop_default(struct device_node *np, const char *name, int def)
+{
+	struct property *prop;
+	int len;
+
+	prop = of_find_property(np, name, &len);
+	if (!prop || len != 4)
+		return def;
+
+	return *(int *) prop->value;
+}
+EXPORT_SYMBOL(of_getintprop_default);
+
+DEFINE_MUTEX(of_set_property_mutex);
+EXPORT_SYMBOL(of_set_property_mutex);
+
+int of_set_property(struct device_node *dp, const char *name, void *val, int len)
+{
+	struct property **prevp;
+	void *new_val;
+	int err;
+
+	new_val = kmalloc(len, GFP_KERNEL);
+	if (!new_val)
+		return -ENOMEM;
+
+	memcpy(new_val, val, len);
+
+	err = -ENODEV;
+
+	write_lock(&devtree_lock);
+	prevp = &dp->properties;
+	while (*prevp) {
+		struct property *prop = *prevp;
+
+		if (!strcasecmp(prop->name, name)) {
+			void *old_val = prop->value;
+			int ret;
+
+			mutex_lock(&of_set_property_mutex);
+			ret = prom_setprop(dp->node, name, val, len);
+			mutex_unlock(&of_set_property_mutex);
+
+			err = -EINVAL;
+			if (ret >= 0) {
+				prop->value = new_val;
+				prop->length = len;
+
+				if (OF_IS_DYNAMIC(prop))
+					kfree(old_val);
+
+				OF_MARK_DYNAMIC(prop);
+
+				err = 0;
+			}
+			break;
+		}
+		prevp = &(*prevp)->next;
+	}
+	write_unlock(&devtree_lock);
+
+	/* XXX Upate procfs if necessary... */
+
+	return err;
+}
+EXPORT_SYMBOL(of_set_property);
+
+int of_find_in_proplist(const char *list, const char *match, int len)
+{
+	while (len > 0) {
+		int l;
+
+		if (!strcmp(list, match))
+			return 1;
+		l = strlen(list) + 1;
+		list += l;
+		len -= l;
+	}
+	return 0;
+}
+EXPORT_SYMBOL(of_find_in_proplist);
+
+unsigned int prom_unique_id;
+
+static struct property * __init build_one_prop(phandle node, char *prev,
+					       char *special_name,
+					       void *special_val,
+					       int special_len)
+{
+	static struct property *tmp = NULL;
+	struct property *p;
+	const char *name;
+
+	if (tmp) {
+		p = tmp;
+		memset(p, 0, sizeof(*p) + 32);
+		tmp = NULL;
+	} else {
+		p = prom_early_alloc(sizeof(struct property) + 32);
+		p->unique_id = prom_unique_id++;
+	}
+
+	p->name = (char *) (p + 1);
+	if (special_name) {
+		strcpy(p->name, special_name);
+		p->length = special_len;
+		p->value = prom_early_alloc(special_len);
+		memcpy(p->value, special_val, special_len);
+	} else {
+#ifdef CONFIG_SPARC32
+		if (prev == NULL) {
+			name = prom_firstprop(node, NULL);
+		} else {
+			name = prom_nextprop(node, prev, NULL);
+		}
+#else
+		if (prev == NULL) {
+			prom_firstprop(node, p->name);
+		} else {
+			prom_nextprop(node, prev, p->name);
+		}
+		name = p->name;
+#endif
+		if (strlen(name) == 0) {
+			tmp = p;
+			return NULL;
+		}
+#ifdef CONFIG_SPARC32
+		strcpy(p->name, name);
+#endif
+		p->length = prom_getproplen(node, p->name);
+		if (p->length <= 0) {
+			p->length = 0;
+		} else {
+			int len;
+
+			p->value = prom_early_alloc(p->length + 1);
+			len = prom_getproperty(node, p->name, p->value,
+					       p->length);
+			if (len <= 0)
+				p->length = 0;
+			((unsigned char *)p->value)[p->length] = '\0';
+		}
+	}
+	return p;
+}
+
+static struct property * __init build_prop_list(phandle node)
+{
+	struct property *head, *tail;
+
+	head = tail = build_one_prop(node, NULL,
+				     ".node", &node, sizeof(node));
+
+	tail->next = build_one_prop(node, NULL, NULL, NULL, 0);
+	tail = tail->next;
+	while(tail) {
+		tail->next = build_one_prop(node, tail->name,
+					    NULL, NULL, 0);
+		tail = tail->next;
+	}
+
+	return head;
+}
+
+static char * __init get_one_property(phandle node, const char *name)
+{
+	char *buf = "<NULL>";
+	int len;
+
+	len = prom_getproplen(node, name);
+	if (len > 0) {
+		buf = prom_early_alloc(len);
+		len = prom_getproperty(node, name, buf, len);
+	}
+
+	return buf;
+}
+
+static struct device_node * __init prom_create_node(phandle node,
+						    struct device_node *parent)
+{
+	struct device_node *dp;
+
+	if (!node)
+		return NULL;
+
+	dp = prom_early_alloc(sizeof(*dp));
+	dp->unique_id = prom_unique_id++;
+	dp->parent = parent;
+
+	kref_init(&dp->kref);
+
+	dp->name = get_one_property(node, "name");
+	dp->type = get_one_property(node, "device_type");
+	dp->node = node;
+
+	dp->properties = build_prop_list(node);
+
+	irq_trans_init(dp);
+
+	return dp;
+}
+
+static char * __init build_full_name(struct device_node *dp)
+{
+	int len, ourlen, plen;
+	char *n;
+
+	plen = strlen(dp->parent->full_name);
+	ourlen = strlen(dp->path_component_name);
+	len = ourlen + plen + 2;
+
+	n = prom_early_alloc(len);
+	strcpy(n, dp->parent->full_name);
+	if (!is_root_node(dp->parent)) {
+		strcpy(n + plen, "/");
+		plen++;
+	}
+	strcpy(n + plen, dp->path_component_name);
+
+	return n;
+}
+
+static struct device_node * __init prom_build_tree(struct device_node *parent,
+						   phandle node,
+						   struct device_node ***nextp)
+{
+	struct device_node *ret = NULL, *prev_sibling = NULL;
+	struct device_node *dp;
+
+	while (1) {
+		dp = prom_create_node(node, parent);
+		if (!dp)
+			break;
+
+		if (prev_sibling)
+			prev_sibling->sibling = dp;
+
+		if (!ret)
+			ret = dp;
+		prev_sibling = dp;
+
+		*(*nextp) = dp;
+		*nextp = &dp->allnext;
+
+		dp->path_component_name = build_path_component(dp);
+		dp->full_name = build_full_name(dp);
+
+		dp->child = prom_build_tree(dp, prom_getchild(node), nextp);
+
+		node = prom_getsibling(node);
+	}
+
+	return ret;
+}
+
+unsigned int prom_early_allocated __initdata;
+
+void __init prom_build_devicetree(void)
+{
+	struct device_node **nextp;
+
+	allnodes = prom_create_node(prom_root_node, NULL);
+	allnodes->path_component_name = "";
+	allnodes->full_name = "/";
+
+	nextp = &allnodes->allnext;
+	allnodes->child = prom_build_tree(allnodes,
+					  prom_getchild(allnodes->node),
+					  &nextp);
+	of_console_init();
+
+	printk("PROM: Built device tree with %u bytes of memory.\n",
+	       prom_early_allocated);
+
+	of_fill_in_cpu_data();
+}
diff --git a/arch/sparc64/kernel/prom.c b/arch/sparc/kernel/prom_irqtrans.c
index dbba82f9b142..96958c4dce8e 100644
--- a/arch/sparc64/kernel/prom.c
+++ b/arch/sparc/kernel/prom_irqtrans.c
@@ -1,151 +1,15 @@
-/*
- * Procedures for creating, accessing and interpreting the device tree.
- *
- * Paul Mackerras	August 1996.
- * Copyright (C) 1996-2005 Paul Mackerras.
- * 
- *  Adapted for 64bit PowerPC by Dave Engebretsen and Peter Bergner.
- *    {engebret|bergner}@us.ibm.com 
- *
- *  Adapted for sparc64 by David S. Miller davem@davemloft.net
- *
- *      This program is free software; you can redistribute it and/or
- *      modify it under the terms of the GNU General Public License
- *      as published by the Free Software Foundation; either version
- *      2 of the License, or (at your option) any later version.
- */
-
 #include <linux/kernel.h>
-#include <linux/types.h>
 #include <linux/string.h>
-#include <linux/mm.h>
-#include <linux/module.h>
-#include <linux/lmb.h>
-#include <linux/of_device.h>
+#include <linux/init.h>
+#include <linux/of.h>
+#include <linux/of_platform.h>
 
-#include <asm/prom.h>
 #include <asm/oplib.h>
+#include <asm/prom.h>
 #include <asm/irq.h>
-#include <asm/asi.h>
 #include <asm/upa.h>
-#include <asm/smp.h>
-
-extern struct device_node *allnodes;	/* temporary while merging */
-
-extern rwlock_t devtree_lock;	/* temporary while merging */
-
-struct device_node *of_find_node_by_phandle(phandle handle)
-{
-	struct device_node *np;
-
-	for (np = allnodes; np; np = np->allnext)
-		if (np->node == handle)
-			break;
-
-	return np;
-}
-EXPORT_SYMBOL(of_find_node_by_phandle);
-
-int of_getintprop_default(struct device_node *np, const char *name, int def)
-{
-	struct property *prop;
-	int len;
-
-	prop = of_find_property(np, name, &len);
-	if (!prop || len != 4)
-		return def;
-
-	return *(int *) prop->value;
-}
-EXPORT_SYMBOL(of_getintprop_default);
-
-DEFINE_MUTEX(of_set_property_mutex);
-EXPORT_SYMBOL(of_set_property_mutex);
-
-int of_set_property(struct device_node *dp, const char *name, void *val, int len)
-{
-	struct property **prevp;
-	void *new_val;
-	int err;
-
-	new_val = kmalloc(len, GFP_KERNEL);
-	if (!new_val)
-		return -ENOMEM;
-
-	memcpy(new_val, val, len);
-
-	err = -ENODEV;
-
-	write_lock(&devtree_lock);
-	prevp = &dp->properties;
-	while (*prevp) {
-		struct property *prop = *prevp;
-
-		if (!strcasecmp(prop->name, name)) {
-			void *old_val = prop->value;
-			int ret;
-
-			mutex_lock(&of_set_property_mutex);
-			ret = prom_setprop(dp->node, name, val, len);
-			mutex_unlock(&of_set_property_mutex);
-
-			err = -EINVAL;
-			if (ret >= 0) {
-				prop->value = new_val;
-				prop->length = len;
-
-				if (OF_IS_DYNAMIC(prop))
-					kfree(old_val);
-
-				OF_MARK_DYNAMIC(prop);
-
-				err = 0;
-			}
-			break;
-		}
-		prevp = &(*prevp)->next;
-	}
-	write_unlock(&devtree_lock);
-
-	/* XXX Upate procfs if necessary... */
 
-	return err;
-}
-EXPORT_SYMBOL(of_set_property);
-
-int of_find_in_proplist(const char *list, const char *match, int len)
-{
-	while (len > 0) {
-		int l;
-
-		if (!strcmp(list, match))
-			return 1;
-		l = strlen(list) + 1;
-		list += l;
-		len -= l;
-	}
-	return 0;
-}
-EXPORT_SYMBOL(of_find_in_proplist);
-
-static unsigned int prom_early_allocated __initdata;
-
-static void * __init prom_early_alloc(unsigned long size)
-{
-	unsigned long paddr = lmb_alloc(size, SMP_CACHE_BYTES);
-	void *ret;
-
-	if (!paddr) {
-		prom_printf("prom_early_alloc(%lu) failed\n");
-		prom_halt();
-	}
-
-	ret = __va(paddr);
-	memset(ret, 0, size);
-	prom_early_allocated += size;
-
-	return ret;
-}
+#include "prom.h"
 
 #ifdef CONFIG_PCI
 /* PSYCHO interrupt mapping support. */
@@ -936,7 +800,7 @@ static void __init sun4v_vdev_irq_trans_init(struct device_node *dp)
 		((regs->phys_addr >> 32UL) & 0x0fffffff);
 }
 
-static void __init irq_trans_init(struct device_node *dp)
+void __init irq_trans_init(struct device_node *dp)
 {
 #ifdef CONFIG_PCI
 	const char *model;
@@ -976,709 +840,3 @@ static void __init irq_trans_init(struct device_node *dp)
 		return;
 	}
 }
-
-static int is_root_node(const struct device_node *dp)
-{
-	if (!dp)
-		return 0;
-
-	return (dp->parent == NULL);
-}
-
-/* The following routines deal with the black magic of fully naming a
- * node.
- *
- * Certain well known named nodes are just the simple name string.
- *
- * Actual devices have an address specifier appended to the base name
- * string, like this "foo@addr".  The "addr" can be in any number of
- * formats, and the platform plus the type of the node determine the
- * format and how it is constructed.
- *
- * For children of the ROOT node, the naming convention is fixed and
- * determined by whether this is a sun4u or sun4v system.
- *
- * For children of other nodes, it is bus type specific.  So
- * we walk up the tree until we discover a "device_type" property
- * we recognize and we go from there.
- *
- * As an example, the boot device on my workstation has a full path:
- *
- *	/pci@1e,600000/ide@d/disk@0,0:c
- */
-static void __init sun4v_path_component(struct device_node *dp, char *tmp_buf)
-{
-	struct linux_prom64_registers *regs;
-	struct property *rprop;
-	u32 high_bits, low_bits, type;
-
-	rprop = of_find_property(dp, "reg", NULL);
-	if (!rprop)
-		return;
-
-	regs = rprop->value;
-	if (!is_root_node(dp->parent)) {
-		sprintf(tmp_buf, "%s@%x,%x",
-			dp->name,
-			(unsigned int) (regs->phys_addr >> 32UL),
-			(unsigned int) (regs->phys_addr & 0xffffffffUL));
-		return;
-	}
-
-	type = regs->phys_addr >> 60UL;
-	high_bits = (regs->phys_addr >> 32UL) & 0x0fffffffUL;
-	low_bits = (regs->phys_addr & 0xffffffffUL);
-
-	if (type == 0 || type == 8) {
-		const char *prefix = (type == 0) ? "m" : "i";
-
-		if (low_bits)
-			sprintf(tmp_buf, "%s@%s%x,%x",
-				dp->name, prefix,
-				high_bits, low_bits);
-		else
-			sprintf(tmp_buf, "%s@%s%x",
-				dp->name,
-				prefix,
-				high_bits);
-	} else if (type == 12) {
-		sprintf(tmp_buf, "%s@%x",
-			dp->name, high_bits);
-	}
-}
-
-static void __init sun4u_path_component(struct device_node *dp, char *tmp_buf)
-{
-	struct linux_prom64_registers *regs;
-	struct property *prop;
-
-	prop = of_find_property(dp, "reg", NULL);
-	if (!prop)
-		return;
-
-	regs = prop->value;
-	if (!is_root_node(dp->parent)) {
-		sprintf(tmp_buf, "%s@%x,%x",
-			dp->name,
-			(unsigned int) (regs->phys_addr >> 32UL),
-			(unsigned int) (regs->phys_addr & 0xffffffffUL));
-		return;
-	}
-
-	prop = of_find_property(dp, "upa-portid", NULL);
-	if (!prop)
-		prop = of_find_property(dp, "portid", NULL);
-	if (prop) {
-		unsigned long mask = 0xffffffffUL;
-
-		if (tlb_type >= cheetah)
-			mask = 0x7fffff;
-
-		sprintf(tmp_buf, "%s@%x,%x",
-			dp->name,
-			*(u32 *)prop->value,
-			(unsigned int) (regs->phys_addr & mask));
-	}
-}
-
-/* "name@slot,offset"  */
-static void __init sbus_path_component(struct device_node *dp, char *tmp_buf)
-{
-	struct linux_prom_registers *regs;
-	struct property *prop;
-
-	prop = of_find_property(dp, "reg", NULL);
-	if (!prop)
-		return;
-
-	regs = prop->value;
-	sprintf(tmp_buf, "%s@%x,%x",
-		dp->name,
-		regs->which_io,
-		regs->phys_addr);
-}
-
-/* "name@devnum[,func]" */
-static void __init pci_path_component(struct device_node *dp, char *tmp_buf)
-{
-	struct linux_prom_pci_registers *regs;
-	struct property *prop;
-	unsigned int devfn;
-
-	prop = of_find_property(dp, "reg", NULL);
-	if (!prop)
-		return;
-
-	regs = prop->value;
-	devfn = (regs->phys_hi >> 8) & 0xff;
-	if (devfn & 0x07) {
-		sprintf(tmp_buf, "%s@%x,%x",
-			dp->name,
-			devfn >> 3,
-			devfn & 0x07);
-	} else {
-		sprintf(tmp_buf, "%s@%x",
-			dp->name,
-			devfn >> 3);
-	}
-}
-
-/* "name@UPA_PORTID,offset" */
-static void __init upa_path_component(struct device_node *dp, char *tmp_buf)
-{
-	struct linux_prom64_registers *regs;
-	struct property *prop;
-
-	prop = of_find_property(dp, "reg", NULL);
-	if (!prop)
-		return;
-
-	regs = prop->value;
-
-	prop = of_find_property(dp, "upa-portid", NULL);
-	if (!prop)
-		return;
-
-	sprintf(tmp_buf, "%s@%x,%x",
-		dp->name,
-		*(u32 *) prop->value,
-		(unsigned int) (regs->phys_addr & 0xffffffffUL));
-}
-
-/* "name@reg" */
-static void __init vdev_path_component(struct device_node *dp, char *tmp_buf)
-{
-	struct property *prop;
-	u32 *regs;
-
-	prop = of_find_property(dp, "reg", NULL);
-	if (!prop)
-		return;
-
-	regs = prop->value;
-
-	sprintf(tmp_buf, "%s@%x", dp->name, *regs);
-}
-
-/* "name@addrhi,addrlo" */
-static void __init ebus_path_component(struct device_node *dp, char *tmp_buf)
-{
-	struct linux_prom64_registers *regs;
-	struct property *prop;
-
-	prop = of_find_property(dp, "reg", NULL);
-	if (!prop)
-		return;
-
-	regs = prop->value;
-
-	sprintf(tmp_buf, "%s@%x,%x",
-		dp->name,
-		(unsigned int) (regs->phys_addr >> 32UL),
-		(unsigned int) (regs->phys_addr & 0xffffffffUL));
-}
-
-/* "name@bus,addr" */
-static void __init i2c_path_component(struct device_node *dp, char *tmp_buf)
-{
-	struct property *prop;
-	u32 *regs;
-
-	prop = of_find_property(dp, "reg", NULL);
-	if (!prop)
-		return;
-
-	regs = prop->value;
-
-	/* This actually isn't right... should look at the #address-cells
-	 * property of the i2c bus node etc. etc.
-	 */
-	sprintf(tmp_buf, "%s@%x,%x",
-		dp->name, regs[0], regs[1]);
-}
-
-/* "name@reg0[,reg1]" */
-static void __init usb_path_component(struct device_node *dp, char *tmp_buf)
-{
-	struct property *prop;
-	u32 *regs;
-
-	prop = of_find_property(dp, "reg", NULL);
-	if (!prop)
-		return;
-
-	regs = prop->value;
-
-	if (prop->length == sizeof(u32) || regs[1] == 1) {
-		sprintf(tmp_buf, "%s@%x",
-			dp->name, regs[0]);
-	} else {
-		sprintf(tmp_buf, "%s@%x,%x",
-			dp->name, regs[0], regs[1]);
-	}
-}
-
-/* "name@reg0reg1[,reg2reg3]" */
-static void __init ieee1394_path_component(struct device_node *dp, char *tmp_buf)
-{
-	struct property *prop;
-	u32 *regs;
-
-	prop = of_find_property(dp, "reg", NULL);
-	if (!prop)
-		return;
-
-	regs = prop->value;
-
-	if (regs[2] || regs[3]) {
-		sprintf(tmp_buf, "%s@%08x%08x,%04x%08x",
-			dp->name, regs[0], regs[1], regs[2], regs[3]);
-	} else {
-		sprintf(tmp_buf, "%s@%08x%08x",
-			dp->name, regs[0], regs[1]);
-	}
-}
-
-static void __init __build_path_component(struct device_node *dp, char *tmp_buf)
-{
-	struct device_node *parent = dp->parent;
-
-	if (parent != NULL) {
-		if (!strcmp(parent->type, "pci") ||
-		    !strcmp(parent->type, "pciex")) {
-			pci_path_component(dp, tmp_buf);
-			return;
-		}
-		if (!strcmp(parent->type, "sbus")) {
-			sbus_path_component(dp, tmp_buf);
-			return;
-		}
-		if (!strcmp(parent->type, "upa")) {
-			upa_path_component(dp, tmp_buf);
-			return;
-		}
-		if (!strcmp(parent->type, "ebus")) {
-			ebus_path_component(dp, tmp_buf);
-			return;
-		}
-		if (!strcmp(parent->name, "usb") ||
-		    !strcmp(parent->name, "hub")) {
-			usb_path_component(dp, tmp_buf);
-			return;
-		}
-		if (!strcmp(parent->type, "i2c")) {
-			i2c_path_component(dp, tmp_buf);
-			return;
-		}
-		if (!strcmp(parent->type, "firewire")) {
-			ieee1394_path_component(dp, tmp_buf);
-			return;
-		}
-		if (!strcmp(parent->type, "virtual-devices")) {
-			vdev_path_component(dp, tmp_buf);
-			return;
-		}
-		/* "isa" is handled with platform naming */
-	}
-
-	/* Use platform naming convention.  */
-	if (tlb_type == hypervisor) {
-		sun4v_path_component(dp, tmp_buf);
-		return;
-	} else {
-		sun4u_path_component(dp, tmp_buf);
-	}
-}
-
-static char * __init build_path_component(struct device_node *dp)
-{
-	char tmp_buf[64], *n;
-
-	tmp_buf[0] = '\0';
-	__build_path_component(dp, tmp_buf);
-	if (tmp_buf[0] == '\0')
-		strcpy(tmp_buf, dp->name);
-
-	n = prom_early_alloc(strlen(tmp_buf) + 1);
-	strcpy(n, tmp_buf);
-
-	return n;
-}
-
-static char * __init build_full_name(struct device_node *dp)
-{
-	int len, ourlen, plen;
-	char *n;
-
-	plen = strlen(dp->parent->full_name);
-	ourlen = strlen(dp->path_component_name);
-	len = ourlen + plen + 2;
-
-	n = prom_early_alloc(len);
-	strcpy(n, dp->parent->full_name);
-	if (!is_root_node(dp->parent)) {
-		strcpy(n + plen, "/");
-		plen++;
-	}
-	strcpy(n + plen, dp->path_component_name);
-
-	return n;
-}
-
-static unsigned int unique_id;
-
-static struct property * __init build_one_prop(phandle node, char *prev, char *special_name, void *special_val, int special_len)
-{
-	static struct property *tmp = NULL;
-	struct property *p;
-
-	if (tmp) {
-		p = tmp;
-		memset(p, 0, sizeof(*p) + 32);
-		tmp = NULL;
-	} else {
-		p = prom_early_alloc(sizeof(struct property) + 32);
-		p->unique_id = unique_id++;
-	}
-
-	p->name = (char *) (p + 1);
-	if (special_name) {
-		strcpy(p->name, special_name);
-		p->length = special_len;
-		p->value = prom_early_alloc(special_len);
-		memcpy(p->value, special_val, special_len);
-	} else {
-		if (prev == NULL) {
-			prom_firstprop(node, p->name);
-		} else {
-			prom_nextprop(node, prev, p->name);
-		}
-		if (strlen(p->name) == 0) {
-			tmp = p;
-			return NULL;
-		}
-		p->length = prom_getproplen(node, p->name);
-		if (p->length <= 0) {
-			p->length = 0;
-		} else {
-			p->value = prom_early_alloc(p->length + 1);
-			prom_getproperty(node, p->name, p->value, p->length);
-			((unsigned char *)p->value)[p->length] = '\0';
-		}
-	}
-	return p;
-}
-
-static struct property * __init build_prop_list(phandle node)
-{
-	struct property *head, *tail;
-
-	head = tail = build_one_prop(node, NULL,
-				     ".node", &node, sizeof(node));
-
-	tail->next = build_one_prop(node, NULL, NULL, NULL, 0);
-	tail = tail->next;
-	while(tail) {
-		tail->next = build_one_prop(node, tail->name,
-					    NULL, NULL, 0);
-		tail = tail->next;
-	}
-
-	return head;
-}
-
-static char * __init get_one_property(phandle node, const char *name)
-{
-	char *buf = "<NULL>";
-	int len;
-
-	len = prom_getproplen(node, name);
-	if (len > 0) {
-		buf = prom_early_alloc(len);
-		prom_getproperty(node, name, buf, len);
-	}
-
-	return buf;
-}
-
-static struct device_node * __init create_node(phandle node, struct device_node *parent)
-{
-	struct device_node *dp;
-
-	if (!node)
-		return NULL;
-
-	dp = prom_early_alloc(sizeof(*dp));
-	dp->unique_id = unique_id++;
-	dp->parent = parent;
-
-	kref_init(&dp->kref);
-
-	dp->name = get_one_property(node, "name");
-	dp->type = get_one_property(node, "device_type");
-	dp->node = node;
-
-	dp->properties = build_prop_list(node);
-
-	irq_trans_init(dp);
-
-	return dp;
-}
-
-static struct device_node * __init build_tree(struct device_node *parent, phandle node, struct device_node ***nextp)
-{
-	struct device_node *ret = NULL, *prev_sibling = NULL;
-	struct device_node *dp;
-
-	while (1) {
-		dp = create_node(node, parent);
-		if (!dp)
-			break;
-
-		if (prev_sibling)
-			prev_sibling->sibling = dp;
-
-		if (!ret)
-			ret = dp;
-		prev_sibling = dp;
-
-		*(*nextp) = dp;
-		*nextp = &dp->allnext;
-
-		dp->path_component_name = build_path_component(dp);
-		dp->full_name = build_full_name(dp);
-
-		dp->child = build_tree(dp, prom_getchild(node), nextp);
-
-		node = prom_getsibling(node);
-	}
-
-	return ret;
-}
-
-static const char *get_mid_prop(void)
-{
-	return (tlb_type == spitfire ? "upa-portid" : "portid");
-}
-
-struct device_node *of_find_node_by_cpuid(int cpuid)
-{
-	struct device_node *dp;
-	const char *mid_prop = get_mid_prop();
-
-	for_each_node_by_type(dp, "cpu") {
-		int id = of_getintprop_default(dp, mid_prop, -1);
-		const char *this_mid_prop = mid_prop;
-
-		if (id < 0) {
-			this_mid_prop = "cpuid";
-			id = of_getintprop_default(dp, this_mid_prop, -1);
-		}
-
-		if (id < 0) {
-			prom_printf("OF: Serious problem, cpu lacks "
-				    "%s property", this_mid_prop);
-			prom_halt();
-		}
-		if (cpuid == id)
-			return dp;
-	}
-	return NULL;
-}
-
-static void __init of_fill_in_cpu_data(void)
-{
-	struct device_node *dp;
-	const char *mid_prop = get_mid_prop();
-
-	ncpus_probed = 0;
-	for_each_node_by_type(dp, "cpu") {
-		int cpuid = of_getintprop_default(dp, mid_prop, -1);
-		const char *this_mid_prop = mid_prop;
-		struct device_node *portid_parent;
-		int portid = -1;
-
-		portid_parent = NULL;
-		if (cpuid < 0) {
-			this_mid_prop = "cpuid";
-			cpuid = of_getintprop_default(dp, this_mid_prop, -1);
-			if (cpuid >= 0) {
-				int limit = 2;
-
-				portid_parent = dp;
-				while (limit--) {
-					portid_parent = portid_parent->parent;
-					if (!portid_parent)
-						break;
-					portid = of_getintprop_default(portid_parent,
-								       "portid", -1);
-					if (portid >= 0)
-						break;
-				}
-			}
-		}
-
-		if (cpuid < 0) {
-			prom_printf("OF: Serious problem, cpu lacks "
-				    "%s property", this_mid_prop);
-			prom_halt();
-		}
-
-		ncpus_probed++;
-
-#ifdef CONFIG_SMP
-		if (cpuid >= NR_CPUS) {
-			printk(KERN_WARNING "Ignoring CPU %d which is "
-			       ">= NR_CPUS (%d)\n",
-			       cpuid, NR_CPUS);
-			continue;
-		}
-#else
-		/* On uniprocessor we only want the values for the
-		 * real physical cpu the kernel booted onto, however
-		 * cpu_data() only has one entry at index 0.
-		 */
-		if (cpuid != real_hard_smp_processor_id())
-			continue;
-		cpuid = 0;
-#endif
-
-		cpu_data(cpuid).clock_tick =
-			of_getintprop_default(dp, "clock-frequency", 0);
-
-		if (portid_parent) {
-			cpu_data(cpuid).dcache_size =
-				of_getintprop_default(dp, "l1-dcache-size",
-						      16 * 1024);
-			cpu_data(cpuid).dcache_line_size =
-				of_getintprop_default(dp, "l1-dcache-line-size",
-						      32);
-			cpu_data(cpuid).icache_size =
-				of_getintprop_default(dp, "l1-icache-size",
-						      8 * 1024);
-			cpu_data(cpuid).icache_line_size =
-				of_getintprop_default(dp, "l1-icache-line-size",
-						      32);
-			cpu_data(cpuid).ecache_size =
-				of_getintprop_default(dp, "l2-cache-size", 0);
-			cpu_data(cpuid).ecache_line_size =
-				of_getintprop_default(dp, "l2-cache-line-size", 0);
-			if (!cpu_data(cpuid).ecache_size ||
-			    !cpu_data(cpuid).ecache_line_size) {
-				cpu_data(cpuid).ecache_size =
-					of_getintprop_default(portid_parent,
-							      "l2-cache-size",
-							      (4 * 1024 * 1024));
-				cpu_data(cpuid).ecache_line_size =
-					of_getintprop_default(portid_parent,
-							      "l2-cache-line-size", 64);
-			}
-
-			cpu_data(cpuid).core_id = portid + 1;
-			cpu_data(cpuid).proc_id = portid;
-#ifdef CONFIG_SMP
-			sparc64_multi_core = 1;
-#endif
-		} else {
-			cpu_data(cpuid).dcache_size =
-				of_getintprop_default(dp, "dcache-size", 16 * 1024);
-			cpu_data(cpuid).dcache_line_size =
-				of_getintprop_default(dp, "dcache-line-size", 32);
-
-			cpu_data(cpuid).icache_size =
-				of_getintprop_default(dp, "icache-size", 16 * 1024);
-			cpu_data(cpuid).icache_line_size =
-				of_getintprop_default(dp, "icache-line-size", 32);
-
-			cpu_data(cpuid).ecache_size =
-				of_getintprop_default(dp, "ecache-size",
-						      (4 * 1024 * 1024));
-			cpu_data(cpuid).ecache_line_size =
-				of_getintprop_default(dp, "ecache-line-size", 64);
-
-			cpu_data(cpuid).core_id = 0;
-			cpu_data(cpuid).proc_id = -1;
-		}
-
-#ifdef CONFIG_SMP
-		cpu_set(cpuid, cpu_present_map);
-		cpu_set(cpuid, cpu_possible_map);
-#endif
-	}
-
-	smp_fill_in_sib_core_maps();
-}
-
-struct device_node *of_console_device;
-EXPORT_SYMBOL(of_console_device);
-
-char *of_console_path;
-EXPORT_SYMBOL(of_console_path);
-
-char *of_console_options;
-EXPORT_SYMBOL(of_console_options);
-
-static void __init of_console_init(void)
-{
-	char *msg = "OF stdout device is: %s\n";
-	struct device_node *dp;
-	const char *type;
-	phandle node;
-
-	of_console_path = prom_early_alloc(256);
-	if (prom_ihandle2path(prom_stdout, of_console_path, 256) < 0) {
-		prom_printf("Cannot obtain path of stdout.\n");
-		prom_halt();
-	}
-	of_console_options = strrchr(of_console_path, ':');
-	if (of_console_options) {
-		of_console_options++;
-		if (*of_console_options == '\0')
-			of_console_options = NULL;
-	}
-
-	node = prom_inst2pkg(prom_stdout);
-	if (!node) {
-		prom_printf("Cannot resolve stdout node from "
-			    "instance %08x.\n", prom_stdout);
-		prom_halt();
-	}
-
-	dp = of_find_node_by_phandle(node);
-	type = of_get_property(dp, "device_type", NULL);
-	if (!type) {
-		prom_printf("Console stdout lacks device_type property.\n");
-		prom_halt();
-	}
-
-	if (strcmp(type, "display") && strcmp(type, "serial")) {
-		prom_printf("Console device_type is neither display "
-			    "nor serial.\n");
-		prom_halt();
-	}
-
-	of_console_device = dp;
-
-	printk(msg, of_console_path);
-}
-
-void __init prom_build_devicetree(void)
-{
-	struct device_node **nextp;
-
-	allnodes = create_node(prom_root_node, NULL);
-	allnodes->path_component_name = "";
-	allnodes->full_name = "/";
-
-	nextp = &allnodes->allnext;
-	allnodes->child = build_tree(allnodes,
-				     prom_getchild(allnodes->node),
-				     &nextp);
-	of_console_init();
-
-	printk("PROM: Built device tree with %u bytes of memory.\n",
-	       prom_early_allocated);
-
-	if (tlb_type != hypervisor)
-		of_fill_in_cpu_data();
-}
diff --git a/arch/sparc64/kernel/psycho_common.c b/arch/sparc/kernel/psycho_common.c
index 790996428c14..790996428c14 100644
--- a/arch/sparc64/kernel/psycho_common.c
+++ b/arch/sparc/kernel/psycho_common.c
diff --git a/arch/sparc64/kernel/psycho_common.h b/arch/sparc/kernel/psycho_common.h
index 092c278ef28d..092c278ef28d 100644
--- a/arch/sparc64/kernel/psycho_common.h
+++ b/arch/sparc/kernel/psycho_common.h
diff --git a/arch/sparc/kernel/ptrace.c b/arch/sparc/kernel/ptrace_32.c
index 8ce6285a06d5..8ce6285a06d5 100644
--- a/arch/sparc/kernel/ptrace.c
+++ b/arch/sparc/kernel/ptrace_32.c
diff --git a/arch/sparc64/kernel/ptrace.c b/arch/sparc/kernel/ptrace_64.c
index f43adbc773ca..a941c610e7ce 100644
--- a/arch/sparc64/kernel/ptrace.c
+++ b/arch/sparc/kernel/ptrace_64.c
@@ -1014,7 +1014,7 @@ long arch_ptrace(struct task_struct *child, long request, long addr, long data)
 		break;
 
 	case PTRACE_SETFPREGS64:
-		ret = copy_regset_to_user(child, view, REGSET_FP,
+		ret = copy_regset_from_user(child, view, REGSET_FP,
 					  0 * sizeof(u64),
 					  33 * sizeof(u64),
 					  fps);
diff --git a/arch/sparc64/kernel/reboot.c b/arch/sparc/kernel/reboot.c
index ef89d3d69748..ef89d3d69748 100644
--- a/arch/sparc64/kernel/reboot.c
+++ b/arch/sparc/kernel/reboot.c
diff --git a/arch/sparc/kernel/rtrap.S b/arch/sparc/kernel/rtrap_32.S
index 4da2e1f66290..4da2e1f66290 100644
--- a/arch/sparc/kernel/rtrap.S
+++ b/arch/sparc/kernel/rtrap_32.S
diff --git a/arch/sparc64/kernel/rtrap.S b/arch/sparc/kernel/rtrap_64.S
index 97a993c1f7f3..fd3cee4d117c 100644
--- a/arch/sparc64/kernel/rtrap.S
+++ b/arch/sparc/kernel/rtrap_64.S
@@ -14,9 +14,9 @@
 #include <asm/visasm.h>
 #include <asm/processor.h>
 
-#define		RTRAP_PSTATE		(PSTATE_RMO|PSTATE_PEF|PSTATE_PRIV|PSTATE_IE)
-#define		RTRAP_PSTATE_IRQOFF	(PSTATE_RMO|PSTATE_PEF|PSTATE_PRIV)
-#define		RTRAP_PSTATE_AG_IRQOFF	(PSTATE_RMO|PSTATE_PEF|PSTATE_PRIV|PSTATE_AG)
+#define		RTRAP_PSTATE		(PSTATE_TSO|PSTATE_PEF|PSTATE_PRIV|PSTATE_IE)
+#define		RTRAP_PSTATE_IRQOFF	(PSTATE_TSO|PSTATE_PEF|PSTATE_PRIV)
+#define		RTRAP_PSTATE_AG_IRQOFF	(PSTATE_TSO|PSTATE_PEF|PSTATE_PRIV|PSTATE_AG)
 
 		.text
 		.align			32
@@ -132,6 +132,18 @@ __handle_signal:
 		ba,pt			%xcc, __handle_signal_continue
 		 andn			%l1, %l4, %l1
 
+		/* When returning from a NMI (%pil==15) interrupt we want to
+		 * avoid running softirqs, doing IRQ tracing, preempting, etc.
+		 */
+		.globl			rtrap_nmi
+rtrap_nmi:	ldx			[%sp + PTREGS_OFF + PT_V9_TSTATE], %l1
+		sethi			%hi(0xf << 20), %l4
+		and			%l1, %l4, %l4
+		andn			%l1, %l4, %l1
+		srl			%l4, 20, %l4
+		ba,pt			%xcc, rtrap_no_irq_enable
+		 wrpr			%l4, %pil
+
 		.align			64
 		.globl			rtrap_irq, rtrap, irqsz_patchme, rtrap_xcall
 rtrap_irq:
@@ -161,8 +173,8 @@ rtrap_xcall:
 		call			trace_hardirqs_on
 		 nop
 		wrpr			%l4, %pil
-rtrap_no_irq_enable:
 #endif
+rtrap_no_irq_enable:
 		andcc			%l1, TSTATE_PRIV, %l3
 		bne,pn			%icc, to_kernel
 		 nop
diff --git a/arch/sparc64/kernel/sbus.c b/arch/sparc/kernel/sbus.c
index 2ead310066d1..2ead310066d1 100644
--- a/arch/sparc64/kernel/sbus.c
+++ b/arch/sparc/kernel/sbus.c
diff --git a/arch/sparc/kernel/setup.c b/arch/sparc/kernel/setup_32.c
index 24fe3078bd4b..c96c65d1b58b 100644
--- a/arch/sparc/kernel/setup.c
+++ b/arch/sparc/kernel/setup_32.c
@@ -46,6 +46,8 @@
 #include <asm/cpudata.h>
 #include <asm/setup.h>
 
+#include "kernel.h"
+
 struct screen_info screen_info = {
 	0, 0,			/* orig-x, orig-y */
 	0,			/* unused */
@@ -308,9 +310,6 @@ void __init setup_arch(char **cmdline_p)
 	smp_setup_cpu_possible_map();
 }
 
-extern char *sparc_cpu_type;
-extern char *sparc_fpu_type;
-
 static int ncpus_probed;
 
 static int show_cpuinfo(struct seq_file *m, void *__unused)
@@ -328,8 +327,8 @@ static int show_cpuinfo(struct seq_file *m, void *__unused)
 		   "CPU0ClkTck\t: %ld\n"
 #endif
 		   ,
-		   sparc_cpu_type ? sparc_cpu_type : "undetermined",
-		   sparc_fpu_type ? sparc_fpu_type : "undetermined",
+		   sparc_cpu_type,
+		   sparc_fpu_type ,
 		   romvec->pv_romvers,
 		   prom_rev,
 		   romvec->pv_printrev >> 16,
diff --git a/arch/sparc64/kernel/setup.c b/arch/sparc/kernel/setup_64.c
index c8b03a4f68bf..555db7452ebe 100644
--- a/arch/sparc64/kernel/setup.c
+++ b/arch/sparc/kernel/setup_64.c
@@ -52,6 +52,7 @@
 #endif
 
 #include "entry.h"
+#include "kernel.h"
 
 /* Used to synchronize accesses to NatSemi SUPER I/O chip configure
  * operations in asm/ns87303.h
diff --git a/arch/sparc64/kernel/signal32.c b/arch/sparc/kernel/signal32.c
index ba5b09ad6666..ba5b09ad6666 100644
--- a/arch/sparc64/kernel/signal32.c
+++ b/arch/sparc/kernel/signal32.c
diff --git a/arch/sparc/kernel/signal.c b/arch/sparc/kernel/signal_32.c
index c94f91c8b6e0..c94f91c8b6e0 100644
--- a/arch/sparc/kernel/signal.c
+++ b/arch/sparc/kernel/signal_32.c
diff --git a/arch/sparc64/kernel/signal.c b/arch/sparc/kernel/signal_64.c
index ec82d76dc6f2..ec82d76dc6f2 100644
--- a/arch/sparc64/kernel/signal.c
+++ b/arch/sparc/kernel/signal_64.c
diff --git a/arch/sparc/kernel/smp.c b/arch/sparc/kernel/smp_32.c
index e396c1f17a92..e396c1f17a92 100644
--- a/arch/sparc/kernel/smp.c
+++ b/arch/sparc/kernel/smp_32.c
diff --git a/arch/sparc64/kernel/smp.c b/arch/sparc/kernel/smp_64.c
index f500b0618bb0..b5225c81556c 100644
--- a/arch/sparc64/kernel/smp.c
+++ b/arch/sparc/kernel/smp_64.c
@@ -163,7 +163,7 @@ static inline long get_delta (long *rt, long *master)
 	for (i = 0; i < NUM_ITERS; i++) {
 		t0 = tick_ops->get_tick();
 		go[MASTER] = 1;
-		membar_storeload();
+		membar_safe("#StoreLoad");
 		while (!(tm = go[SLAVE]))
 			rmb();
 		go[SLAVE] = 0;
@@ -257,7 +257,7 @@ static void smp_synchronize_one_tick(int cpu)
 
 	/* now let the client proceed into his loop */
 	go[MASTER] = 0;
-	membar_storeload();
+	membar_safe("#StoreLoad");
 
 	spin_lock_irqsave(&itc_sync_lock, flags);
 	{
@@ -267,7 +267,7 @@ static void smp_synchronize_one_tick(int cpu)
 			go[MASTER] = 0;
 			wmb();
 			go[SLAVE] = tick_ops->get_tick();
-			membar_storeload();
+			membar_safe("#StoreLoad");
 		}
 	}
 	spin_unlock_irqrestore(&itc_sync_lock, flags);
@@ -1122,7 +1122,6 @@ void smp_capture(void)
 		       smp_processor_id());
 #endif
 		penguins_are_doing_time = 1;
-		membar_storestore_loadstore();
 		atomic_inc(&smp_capture_registry);
 		smp_cross_call(&xcall_capture, 0, 0, 0);
 		while (atomic_read(&smp_capture_registry) != ncpus)
@@ -1142,13 +1141,13 @@ void smp_release(void)
 		       smp_processor_id());
 #endif
 		penguins_are_doing_time = 0;
-		membar_storeload_storestore();
+		membar_safe("#StoreLoad");
 		atomic_dec(&smp_capture_registry);
 	}
 }
 
-/* Imprisoned penguins run with %pil == 15, but PSTATE_IE set, so they
- * can service tlb flush xcalls...
+/* Imprisoned penguins run with %pil == PIL_NORMAL_MAX, but PSTATE_IE
+ * set, so they can service tlb flush xcalls...
  */
 extern void prom_world(int);
 
@@ -1161,7 +1160,7 @@ void smp_penguin_jailcell(int irq, struct pt_regs *regs)
 	__asm__ __volatile__("flushw");
 	prom_world(1);
 	atomic_inc(&smp_capture_registry);
-	membar_storeload_storestore();
+	membar_safe("#StoreLoad");
 	while (penguins_are_doing_time)
 		rmb();
 	atomic_dec(&smp_capture_registry);
diff --git a/arch/sparc/kernel/sparc_ksyms.c b/arch/sparc/kernel/sparc_ksyms_32.c
index b0dfff848653..3c80562faa8a 100644
--- a/arch/sparc/kernel/sparc_ksyms.c
+++ b/arch/sparc/kernel/sparc_ksyms_32.c
@@ -122,10 +122,8 @@ EXPORT_SYMBOL(phys_cpu_present_map);
 EXPORT_SYMBOL(__udelay);
 EXPORT_SYMBOL(__ndelay);
 EXPORT_SYMBOL(rtc_lock);
-#ifdef CONFIG_SUN_AUXIO
 EXPORT_SYMBOL(set_auxio);
 EXPORT_SYMBOL(get_auxio);
-#endif
 EXPORT_SYMBOL(io_remap_pfn_range);
 
 #ifndef CONFIG_SMP
diff --git a/arch/sparc64/kernel/sparc64_ksyms.c b/arch/sparc/kernel/sparc_ksyms_64.c
index 30bba8b0a3b0..e6d2bb86a46f 100644
--- a/arch/sparc64/kernel/sparc64_ksyms.c
+++ b/arch/sparc/kernel/sparc_ksyms_64.c
@@ -49,6 +49,7 @@
 #include <asm/timer.h>
 #include <asm/cpudata.h>
 #include <asm/ftrace.h>
+#include <asm/hypervisor.h>
 
 struct poll {
 	int fd;
@@ -148,10 +149,13 @@ EXPORT_SYMBOL(flush_dcache_page);
 EXPORT_SYMBOL(__flush_dcache_range);
 #endif
 
-#ifdef CONFIG_SUN_AUXIO
+EXPORT_SYMBOL(sun4v_niagara_getperf);
+EXPORT_SYMBOL(sun4v_niagara_setperf);
+EXPORT_SYMBOL(sun4v_niagara2_getperf);
+EXPORT_SYMBOL(sun4v_niagara2_setperf);
+
 EXPORT_SYMBOL(auxio_set_led);
 EXPORT_SYMBOL(auxio_set_lte);
-#endif
 #ifdef CONFIG_SBUS
 EXPORT_SYMBOL(sbus_set_sbus64);
 #endif
diff --git a/arch/sparc64/kernel/spiterrs.S b/arch/sparc/kernel/spiterrs.S
index ef902c6f8e3c..c357e40ffd01 100644
--- a/arch/sparc64/kernel/spiterrs.S
+++ b/arch/sparc/kernel/spiterrs.S
@@ -80,7 +80,7 @@ __spitfire_cee_trap_continue:
 	cmp		%g2, 1
 	rdpr		%pil, %g2
 	bleu,pt		%xcc, 1f
-	 wrpr		%g0, 15, %pil
+	 wrpr		%g0, PIL_NORMAL_MAX, %pil
 
 	ba,pt		%xcc, etraptl1
 	 rd		%pc, %g7
diff --git a/arch/sparc64/kernel/sstate.c b/arch/sparc/kernel/sstate.c
index 8cdbe5946b43..8cdbe5946b43 100644
--- a/arch/sparc64/kernel/sstate.c
+++ b/arch/sparc/kernel/sstate.c
diff --git a/arch/sparc64/kernel/stacktrace.c b/arch/sparc/kernel/stacktrace.c
index 4e21d4a57d3b..acb12f673757 100644
--- a/arch/sparc64/kernel/stacktrace.c
+++ b/arch/sparc/kernel/stacktrace.c
@@ -7,17 +7,18 @@
 
 #include "kstack.h"
 
-void save_stack_trace(struct stack_trace *trace)
+static void __save_stack_trace(struct thread_info *tp,
+			       struct stack_trace *trace,
+			       bool skip_sched)
 {
-	struct thread_info *tp = task_thread_info(current);
 	unsigned long ksp, fp;
 
-	stack_trace_flush();
-
-	__asm__ __volatile__(
-		"mov	%%fp, %0"
-		: "=r" (ksp)
-	);
+	if (tp == current_thread_info()) {
+		stack_trace_flush();
+		__asm__ __volatile__("mov %%fp, %0" : "=r" (ksp));
+	} else {
+		ksp = tp->ksp;
+	}
 
 	fp = ksp + STACK_BIAS;
 	do {
@@ -43,8 +44,21 @@ void save_stack_trace(struct stack_trace *trace)
 
 		if (trace->skip > 0)
 			trace->skip--;
-		else
+		else if (!skip_sched || !in_sched_functions(pc))
 			trace->entries[trace->nr_entries++] = pc;
 	} while (trace->nr_entries < trace->max_entries);
 }
+
+void save_stack_trace(struct stack_trace *trace)
+{
+	__save_stack_trace(current_thread_info(), trace, false);
+}
 EXPORT_SYMBOL_GPL(save_stack_trace);
+
+void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
+{
+	struct thread_info *tp = task_thread_info(tsk);
+
+	__save_stack_trace(tp, trace, true);
+}
+EXPORT_SYMBOL_GPL(save_stack_trace_tsk);
diff --git a/arch/sparc64/kernel/starfire.c b/arch/sparc/kernel/starfire.c
index 060d0f3a6151..060d0f3a6151 100644
--- a/arch/sparc64/kernel/starfire.c
+++ b/arch/sparc/kernel/starfire.c
diff --git a/arch/sparc/kernel/sun4c_irq.c b/arch/sparc/kernel/sun4c_irq.c
index 5dc8a5769489..bc3adbf79c6a 100644
--- a/arch/sparc/kernel/sun4c_irq.c
+++ b/arch/sparc/kernel/sun4c_irq.c
@@ -160,6 +160,7 @@ static void __init sun4c_init_timers(irq_handler_t counter_fn)
 	sun4c_timers = (void __iomem *) (unsigned long) addr[0];
 
 	irq = of_get_property(dp, "intr", NULL);
+	of_node_put(dp);
 	if (!irq) {
 		prom_printf("sun4c_init_timers: No intr property\n");
 		prom_halt();
@@ -200,6 +201,7 @@ void __init sun4c_init_IRQ(void)
 	}
 
 	addr = of_get_property(dp, "address", NULL);
+	of_node_put(dp);
 	if (!addr) {
 		prom_printf("sun4c_init_IRQ: No address property\n");
 		prom_halt();
diff --git a/arch/sparc/kernel/sun4d_irq.c b/arch/sparc/kernel/sun4d_irq.c
index d3cb76ce418b..1c98821e1a64 100644
--- a/arch/sparc/kernel/sun4d_irq.c
+++ b/arch/sparc/kernel/sun4d_irq.c
@@ -508,6 +508,7 @@ static void __init sun4d_init_timers(irq_handler_t counter_fn)
 	 * bootbus.
 	 */
 	reg = of_get_property(dp, "reg", NULL);
+	of_node_put(dp);
 	if (!reg) {
 		prom_printf("sun4d_init_timers: No reg property\n");
 		prom_halt();
diff --git a/arch/sparc/kernel/sun4m_irq.c b/arch/sparc/kernel/sun4m_irq.c
index f10317179ee6..301892e2d718 100644
--- a/arch/sparc/kernel/sun4m_irq.c
+++ b/arch/sparc/kernel/sun4m_irq.c
@@ -374,6 +374,7 @@ static void __init sun4m_init_timers(irq_handler_t counter_fn)
 	}
 
 	addr = of_get_property(dp, "address", &len);
+	of_node_put(dp);
 	if (!addr) {
 		printk(KERN_ERR "sun4m_init_timers: No 'address' prop.\n");
 		return;
@@ -437,6 +438,7 @@ void __init sun4m_init_IRQ(void)
 	}
 
 	addr = of_get_property(dp, "address", &len);
+	of_node_put(dp);
 	if (!addr) {
 		printk(KERN_ERR "sun4m_init_IRQ: No 'address' prop.\n");
 		return;
diff --git a/arch/sparc64/kernel/sun4v_ivec.S b/arch/sparc/kernel/sun4v_ivec.S
index e2f8e1b4882a..559bc5e9c199 100644
--- a/arch/sparc64/kernel/sun4v_ivec.S
+++ b/arch/sparc/kernel/sun4v_ivec.S
@@ -186,7 +186,7 @@ sun4v_res_mondo:
 	 * when it's done.
 	 */
 	rdpr	%pil, %g2
-	wrpr	%g0, 15, %pil
+	wrpr	%g0, PIL_NORMAL_MAX, %pil
 	mov	%g1, %g4
 	ba,pt	%xcc, etrap_irq
 	 rd	%pc, %g7
@@ -216,7 +216,7 @@ sun4v_res_mondo_queue_full:
 	membar	#Sync
 
 	rdpr	%pil, %g2
-	wrpr	%g0, 15, %pil
+	wrpr	%g0, PIL_NORMAL_MAX, %pil
 	ba,pt	%xcc, etrap_irq
 	 rd	%pc, %g7
 #ifdef CONFIG_TRACE_IRQFLAGS
@@ -297,7 +297,7 @@ sun4v_nonres_mondo:
 	 * when it's done.
 	 */
 	rdpr	%pil, %g2
-	wrpr	%g0, 15, %pil
+	wrpr	%g0, PIL_NORMAL_MAX, %pil
 	mov	%g1, %g4
 	ba,pt	%xcc, etrap_irq
 	 rd	%pc, %g7
@@ -327,7 +327,7 @@ sun4v_nonres_mondo_queue_full:
 	membar	#Sync
 
 	rdpr	%pil, %g2
-	wrpr	%g0, 15, %pil
+	wrpr	%g0, PIL_NORMAL_MAX, %pil
 	ba,pt	%xcc, etrap_irq
 	 rd	%pc, %g7
 #ifdef CONFIG_TRACE_IRQFLAGS
diff --git a/arch/sparc64/kernel/sun4v_tlb_miss.S b/arch/sparc/kernel/sun4v_tlb_miss.S
index e1fbf8c75787..e1fbf8c75787 100644
--- a/arch/sparc64/kernel/sun4v_tlb_miss.S
+++ b/arch/sparc/kernel/sun4v_tlb_miss.S
diff --git a/arch/sparc64/kernel/sys32.S b/arch/sparc/kernel/sys32.S
index f061c4dda9ef..f061c4dda9ef 100644
--- a/arch/sparc64/kernel/sys32.S
+++ b/arch/sparc/kernel/sys32.S
diff --git a/arch/sparc64/kernel/sys_sparc32.c b/arch/sparc/kernel/sys_sparc32.c
index e800503879e4..e800503879e4 100644
--- a/arch/sparc64/kernel/sys_sparc32.c
+++ b/arch/sparc/kernel/sys_sparc32.c
diff --git a/arch/sparc/kernel/sys_sparc.c b/arch/sparc/kernel/sys_sparc_32.c
index 03035c852a43..03035c852a43 100644
--- a/arch/sparc/kernel/sys_sparc.c
+++ b/arch/sparc/kernel/sys_sparc_32.c
diff --git a/arch/sparc64/kernel/sys_sparc.c b/arch/sparc/kernel/sys_sparc_64.c
index 39749e32dc7e..39749e32dc7e 100644
--- a/arch/sparc64/kernel/sys_sparc.c
+++ b/arch/sparc/kernel/sys_sparc_64.c
diff --git a/arch/sparc64/kernel/syscalls.S b/arch/sparc/kernel/syscalls.S
index 7a6786a71363..7a6786a71363 100644
--- a/arch/sparc64/kernel/syscalls.S
+++ b/arch/sparc/kernel/syscalls.S
diff --git a/arch/sparc64/kernel/sysfs.c b/arch/sparc/kernel/sysfs.c
index 84e5ce146713..84e5ce146713 100644
--- a/arch/sparc64/kernel/sysfs.c
+++ b/arch/sparc/kernel/sysfs.c
diff --git a/arch/sparc64/kernel/systbls.h b/arch/sparc/kernel/systbls.h
index bc9f5dac4069..bc9f5dac4069 100644
--- a/arch/sparc64/kernel/systbls.h
+++ b/arch/sparc/kernel/systbls.h
diff --git a/arch/sparc/kernel/systbls.S b/arch/sparc/kernel/systbls_32.S
index 7d0807586442..7d0807586442 100644
--- a/arch/sparc/kernel/systbls.S
+++ b/arch/sparc/kernel/systbls_32.S
diff --git a/arch/sparc64/kernel/systbls.S b/arch/sparc/kernel/systbls_64.S
index 9fc78cf354bd..9fc78cf354bd 100644
--- a/arch/sparc64/kernel/systbls.S
+++ b/arch/sparc/kernel/systbls_64.S
diff --git a/arch/sparc/kernel/time.c b/arch/sparc/kernel/time_32.c
index 00f7383c7657..00f7383c7657 100644
--- a/arch/sparc/kernel/time.c
+++ b/arch/sparc/kernel/time_32.c
diff --git a/arch/sparc64/kernel/time.c b/arch/sparc/kernel/time_64.c
index 141da3759091..141da3759091 100644
--- a/arch/sparc64/kernel/time.c
+++ b/arch/sparc/kernel/time_64.c
diff --git a/arch/sparc/kernel/trampoline.S b/arch/sparc/kernel/trampoline_32.S
index 5e235c52d667..5e235c52d667 100644
--- a/arch/sparc/kernel/trampoline.S
+++ b/arch/sparc/kernel/trampoline_32.S
diff --git a/arch/sparc64/kernel/trampoline.S b/arch/sparc/kernel/trampoline_64.S
index 83abd5ae88a4..da1b781b5e65 100644
--- a/arch/sparc64/kernel/trampoline.S
+++ b/arch/sparc/kernel/trampoline_64.S
@@ -109,7 +109,6 @@ startup_continue:
 	 */
 	sethi		%hi(prom_entry_lock), %g2
 1:	ldstub		[%g2 + %lo(prom_entry_lock)], %g1
-	membar		#StoreLoad | #StoreStore
 	brnz,pn		%g1, 1b
 	 nop
 
@@ -214,7 +213,6 @@ startup_continue:
 
 	sethi		%hi(prom_entry_lock), %g2
 	stb		%g0, [%g2 + %lo(prom_entry_lock)]
-	membar		#StoreStore | #StoreLoad
 
 	ba,pt		%xcc, after_lock_tlb
 	 nop
@@ -330,7 +328,6 @@ after_lock_tlb:
 
 	sethi		%hi(prom_entry_lock), %g2
 1:	ldstub		[%g2 + %lo(prom_entry_lock)], %g1
-	membar		#StoreLoad | #StoreStore
 	brnz,pn		%g1, 1b
 	 nop
 
@@ -394,7 +391,6 @@ after_lock_tlb:
 
 3:	sethi		%hi(prom_entry_lock), %g2
 	stb		%g0, [%g2 + %lo(prom_entry_lock)]
-	membar		#StoreStore | #StoreLoad
 
 	ldx		[%l0], %g6
 	ldx		[%g6 + TI_TASK], %g4
diff --git a/arch/sparc/kernel/traps.c b/arch/sparc/kernel/traps_32.c
index 2b7d50659036..2b7d50659036 100644
--- a/arch/sparc/kernel/traps.c
+++ b/arch/sparc/kernel/traps_32.c
diff --git a/arch/sparc64/kernel/traps.c b/arch/sparc/kernel/traps_64.c
index 81ccd22e78d4..4638af2f55a0 100644
--- a/arch/sparc64/kernel/traps.c
+++ b/arch/sparc/kernel/traps_64.c
@@ -1371,7 +1371,6 @@ static int cheetah_fix_ce(unsigned long physaddr)
 	__asm__ __volatile__("ldxa	[%0] %3, %%g0\n\t"
 			     "ldxa	[%1] %3, %%g0\n\t"
 			     "casxa	[%2] %3, %%g0, %%g0\n\t"
-			     "membar	#StoreLoad | #StoreStore\n\t"
 			     "ldxa	[%0] %3, %%g0\n\t"
 			     "ldxa	[%1] %3, %%g0\n\t"
 			     "membar	#Sync"
@@ -1833,7 +1832,7 @@ static void sun4v_log_error(struct pt_regs *regs, struct sun4v_error_entry *ent,
 	}
 }
 
-/* We run with %pil set to 15 and PSTATE_IE enabled in %pstate.
+/* We run with %pil set to PIL_NORMAL_MAX and PSTATE_IE enabled in %pstate.
  * Log the event and clear the first word of the entry.
  */
 void sun4v_resum_error(struct pt_regs *regs, unsigned long offset)
@@ -1881,7 +1880,7 @@ void sun4v_resum_overflow(struct pt_regs *regs)
 	atomic_inc(&sun4v_resum_oflow_cnt);
 }
 
-/* We run with %pil set to 15 and PSTATE_IE enabled in %pstate.
+/* We run with %pil set to PIL_NORMAL_MAX and PSTATE_IE enabled in %pstate.
  * Log the event, clear the first word of the entry, and die.
  */
 void sun4v_nonresum_error(struct pt_regs *regs, unsigned long offset)
diff --git a/arch/sparc64/kernel/tsb.S b/arch/sparc/kernel/tsb.S
index c499214b501d..8c91d9b29a2f 100644
--- a/arch/sparc64/kernel/tsb.S
+++ b/arch/sparc/kernel/tsb.S
@@ -317,7 +317,7 @@ tsb_flush:
 	srlx	%g1, 32, %o3
 	andcc	%o3, %g2, %g0
 	bne,pn	%icc, 1b
-	 membar	#LoadLoad
+	 nop
 	cmp	%g1, %o1
 	mov	1, %o3
 	bne,pt	%xcc, 2f
@@ -327,7 +327,7 @@ tsb_flush:
 	bne,pn	%xcc, 1b
 	 nop
 2:	retl
-	 TSB_MEMBAR
+	 nop
 	.size	tsb_flush, .-tsb_flush
 
 	/* Reload MMU related context switch state at
@@ -478,7 +478,7 @@ copy_tsb:		/* %o0=old_tsb_base, %o1=old_tsb_size
 	 nop
 
 	retl
-	 TSB_MEMBAR
+	 nop
 	.size		copy_tsb, .-copy_tsb
 
 	/* Set the invalid bit in all TSB entries.  */
diff --git a/arch/sparc64/kernel/ttable.S b/arch/sparc/kernel/ttable.S
index 1ade3d6fb7fc..ea925503b42e 100644
--- a/arch/sparc64/kernel/ttable.S
+++ b/arch/sparc/kernel/ttable.S
@@ -66,7 +66,7 @@ tl0_irq6:	BTRAP(0x46)
 tl0_irq7:	BTRAP(0x47) BTRAP(0x48) BTRAP(0x49)
 tl0_irq10:	BTRAP(0x4a) BTRAP(0x4b) BTRAP(0x4c) BTRAP(0x4d)
 tl0_irq14:	TRAP_IRQ(timer_interrupt, 14)
-tl0_irq15:	TRAP_IRQ(handler_irq, 15)
+tl0_irq15:	TRAP_NMI_IRQ(perfctr_irq, 15)
 tl0_resv050:	BTRAP(0x50) BTRAP(0x51) BTRAP(0x52) BTRAP(0x53) BTRAP(0x54) BTRAP(0x55)
 tl0_resv056:	BTRAP(0x56) BTRAP(0x57) BTRAP(0x58) BTRAP(0x59) BTRAP(0x5a) BTRAP(0x5b)
 tl0_resv05c:	BTRAP(0x5c) BTRAP(0x5d) BTRAP(0x5e) BTRAP(0x5f)
diff --git a/arch/sparc/kernel/una_asm.S b/arch/sparc/kernel/una_asm_32.S
index 8cc03458eb7e..8cc03458eb7e 100644
--- a/arch/sparc/kernel/una_asm.S
+++ b/arch/sparc/kernel/una_asm_32.S
diff --git a/arch/sparc64/kernel/una_asm.S b/arch/sparc/kernel/una_asm_64.S
index be183fe41443..be183fe41443 100644
--- a/arch/sparc64/kernel/una_asm.S
+++ b/arch/sparc/kernel/una_asm_64.S
diff --git a/arch/sparc/kernel/unaligned.c b/arch/sparc/kernel/unaligned_32.c
index c2a28c5ad650..c2a28c5ad650 100644
--- a/arch/sparc/kernel/unaligned.c
+++ b/arch/sparc/kernel/unaligned_32.c
diff --git a/arch/sparc64/kernel/unaligned.c b/arch/sparc/kernel/unaligned_64.c
index 203ddfad9f27..203ddfad9f27 100644
--- a/arch/sparc64/kernel/unaligned.c
+++ b/arch/sparc/kernel/unaligned_64.c
diff --git a/arch/sparc64/kernel/us2e_cpufreq.c b/arch/sparc/kernel/us2e_cpufreq.c
index 791c15138f3a..791c15138f3a 100644
--- a/arch/sparc64/kernel/us2e_cpufreq.c
+++ b/arch/sparc/kernel/us2e_cpufreq.c
diff --git a/arch/sparc64/kernel/us3_cpufreq.c b/arch/sparc/kernel/us3_cpufreq.c
index 365b6464e2ce..365b6464e2ce 100644
--- a/arch/sparc64/kernel/us3_cpufreq.c
+++ b/arch/sparc/kernel/us3_cpufreq.c
diff --git a/arch/sparc64/kernel/utrap.S b/arch/sparc/kernel/utrap.S
index b7f0f3f3a909..b7f0f3f3a909 100644
--- a/arch/sparc64/kernel/utrap.S
+++ b/arch/sparc/kernel/utrap.S
diff --git a/arch/sparc64/kernel/vio.c b/arch/sparc/kernel/vio.c
index 92b1f8ec01de..92b1f8ec01de 100644
--- a/arch/sparc64/kernel/vio.c
+++ b/arch/sparc/kernel/vio.c
diff --git a/arch/sparc64/kernel/viohs.c b/arch/sparc/kernel/viohs.c
index 708fa1705fbe..708fa1705fbe 100644
--- a/arch/sparc64/kernel/viohs.c
+++ b/arch/sparc/kernel/viohs.c
diff --git a/arch/sparc64/kernel/visemul.c b/arch/sparc/kernel/visemul.c
index 9e05cb5cb855..b956fd71c131 100644
--- a/arch/sparc64/kernel/visemul.c
+++ b/arch/sparc/kernel/visemul.c
@@ -131,7 +131,7 @@
 #define VIS_OPF_SHIFT	5
 #define VIS_OPF_MASK	(0x1ff << VIS_OPF_SHIFT)
 
-#define RS1(INSN)	(((INSN) >> 24) & 0x1f)
+#define RS1(INSN)	(((INSN) >> 14) & 0x1f)
 #define RS2(INSN)	(((INSN) >>  0) & 0x1f)
 #define RD(INSN)	(((INSN) >> 25) & 0x1f)
 
@@ -445,7 +445,7 @@ static void pdist(struct pt_regs *regs, unsigned int insn)
 	unsigned long i;
 
 	rs1 = fpd_regval(f, RS1(insn));
-	rs2 = fpd_regval(f, RS1(insn));
+	rs2 = fpd_regval(f, RS2(insn));
 	rd = fpd_regaddr(f, RD(insn));
 
 	rd_val = *rd;
@@ -807,6 +807,8 @@ int vis_emul(struct pt_regs *regs, unsigned int insn)
 	if (get_user(insn, (u32 __user *) pc))
 		return -EFAULT;
 
+	save_and_clear_fpu();
+
 	opf = (insn & VIS_OPF_MASK) >> VIS_OPF_SHIFT;
 	switch (opf) {
 	default:
diff --git a/arch/sparc/kernel/vmlinux.lds.S b/arch/sparc/kernel/vmlinux.lds.S
index 5b7e69a8c32f..4bfbeffb7320 100644
--- a/arch/sparc/kernel/vmlinux.lds.S
+++ b/arch/sparc/kernel/vmlinux.lds.S
@@ -1,27 +1,55 @@
-/* ld script to make SparcLinux kernel */
+/* ld script for sparc32/sparc64 kernel */
 
 #include <asm-generic/vmlinux.lds.h>
 #include <asm/page.h>
 
+#ifdef CONFIG_SPARC32
+#define INITIAL_ADDRESS  0x10000 + SIZEOF_HEADERS
+#define TEXTSTART	0xf0004000
+
+#define SMP_CACHE_BYTES_SHIFT 5
+
+#else
+#define SMP_CACHE_BYTES_SHIFT 6
+#define INITIAL_ADDRESS 0x4000
+#define TEXTSTART      0x0000000000404000
+
+#endif
+
+#define SMP_CACHE_BYTES (1 << SMP_CACHE_BYTES_SHIFT)
+
+#ifdef CONFIG_SPARC32
 OUTPUT_FORMAT("elf32-sparc", "elf32-sparc", "elf32-sparc")
 OUTPUT_ARCH(sparc)
 ENTRY(_start)
 jiffies = jiffies_64 + 4;
+#else
+/* sparc64 */
+OUTPUT_FORMAT("elf64-sparc", "elf64-sparc", "elf64-sparc")
+OUTPUT_ARCH(sparc:v9a)
+ENTRY(_start)
+jiffies = jiffies_64;
+#endif
+
 SECTIONS
 {
-	. = 0x10000 + SIZEOF_HEADERS;
-	.text 0xf0004000 :
+	/* swapper_low_pmd_dir is sparc64 only */
+	swapper_low_pmd_dir = 0x0000000000402000;
+	. = INITIAL_ADDRESS;
+	.text TEXTSTART :
 	{
 		_text = .;
 		*(.text.head)
 		TEXT_TEXT
 		SCHED_TEXT
 		LOCK_TEXT
+		KPROBES_TEXT
 		*(.gnu.warning)
 	} = 0
 	_etext = .;
 	PROVIDE (etext = .);
-	RODATA
+
+	RO_DATA(PAGE_SIZE)
 	.data :	{
 		DATA_DATA
 		CONSTRUCTORS
@@ -29,25 +57,32 @@ SECTIONS
 	.data1 : {
 		*(.data1)
 	}
+	. = ALIGN(SMP_CACHE_BYTES);
+	.data.cacheline_aligned : {
+		*(.data.cacheline_aligned)
+	}
+	. = ALIGN(SMP_CACHE_BYTES);
+	.data.read_mostly : {
+		*(.data.read_mostly)
+	}
 	_edata = .;
 	PROVIDE (edata = .);
-
 	.fixup : {
 		__start___fixup = .;
 		*(.fixup)
 		__stop___fixup = .;
 	}
+	. = ALIGN(16);
 	__ex_table : {
 		__start___ex_table = .;
 		*(__ex_table)
 		__stop___ex_table = .;
 	}
-
 	NOTES
 
 	. = ALIGN(PAGE_SIZE);
-	__init_begin = .;
 	.init.text : {
+		__init_begin = .;
 		_sinittext = .;
 		INIT_TEXT
 		_einittext = .;
@@ -65,7 +100,7 @@ SECTIONS
 	.initcall.init : {
 		__initcall_start = .;
 		INITCALLS
-	__initcall_end = .;
+		__initcall_end = .;
 	}
 	.con_initcall.init : {
 		__con_initcall_start = .;
@@ -74,31 +109,54 @@ SECTIONS
 	}
 	SECURITY_INIT
 
+	. = ALIGN(4);
+	.tsb_ldquad_phys_patch : {
+		__tsb_ldquad_phys_patch = .;
+		*(.tsb_ldquad_phys_patch)
+		__tsb_ldquad_phys_patch_end = .;
+	}
+
+	.tsb_phys_patch : {
+		__tsb_phys_patch = .;
+		*(.tsb_phys_patch)
+		__tsb_phys_patch_end = .;
+	}
+
+	.cpuid_patch : {
+		__cpuid_patch = .;
+		*(.cpuid_patch)
+		__cpuid_patch_end = .;
+	}
+
+	.sun4v_1insn_patch : {
+		__sun4v_1insn_patch = .;
+		*(.sun4v_1insn_patch)
+		__sun4v_1insn_patch_end = .;
+	}
+	.sun4v_2insn_patch : {
+		__sun4v_2insn_patch = .;
+		*(.sun4v_2insn_patch)
+		__sun4v_2insn_patch_end = .;
+	}
+
 #ifdef CONFIG_BLK_DEV_INITRD
 	. = ALIGN(PAGE_SIZE);
 	.init.ramfs : {
-	__initramfs_start = .;
+		__initramfs_start = .;
 		*(.init.ramfs)
-	__initramfs_end = .;
+		__initramfs_end = .;
 	}
 #endif
 
 	PERCPU(PAGE_SIZE)
+
 	. = ALIGN(PAGE_SIZE);
 	__init_end = .;
-	. = ALIGN(32);
-	.data.cacheline_aligned : {
-		*(.data.cacheline_aligned)
-	}
-	. = ALIGN(32);
-	.data.read_mostly : {
-		*(.data.read_mostly)
-	}
-
 	__bss_start = .;
 	.sbss : {
 		*(.sbss)
-		*(.scommon) }
+		*(.scommon)
+	}
 	.bss : {
 		*(.dynbss)
 		*(.bss)
@@ -106,6 +164,7 @@ SECTIONS
 	}
 	_end = . ;
 	PROVIDE (end = .);
+
 	/DISCARD/ : {
 		EXIT_TEXT
 		EXIT_DATA
diff --git a/arch/sparc64/kernel/winfixup.S b/arch/sparc/kernel/winfixup.S
index a6b0863c27df..a6b0863c27df 100644
--- a/arch/sparc64/kernel/winfixup.S
+++ b/arch/sparc/kernel/winfixup.S
diff --git a/arch/sparc64/lib/GENbzero.S b/arch/sparc/lib/GENbzero.S
index 6a4f956a2f7a..6a4f956a2f7a 100644
--- a/arch/sparc64/lib/GENbzero.S
+++ b/arch/sparc/lib/GENbzero.S
diff --git a/arch/sparc64/lib/GENcopy_from_user.S b/arch/sparc/lib/GENcopy_from_user.S
index 2b9df99e87f9..2b9df99e87f9 100644
--- a/arch/sparc64/lib/GENcopy_from_user.S
+++ b/arch/sparc/lib/GENcopy_from_user.S
diff --git a/arch/sparc64/lib/GENcopy_to_user.S b/arch/sparc/lib/GENcopy_to_user.S
index bb3f7084daf9..bb3f7084daf9 100644
--- a/arch/sparc64/lib/GENcopy_to_user.S
+++ b/arch/sparc/lib/GENcopy_to_user.S
diff --git a/arch/sparc64/lib/GENmemcpy.S b/arch/sparc/lib/GENmemcpy.S
index 89358ee94851..89358ee94851 100644
--- a/arch/sparc64/lib/GENmemcpy.S
+++ b/arch/sparc/lib/GENmemcpy.S
diff --git a/arch/sparc64/lib/GENpage.S b/arch/sparc/lib/GENpage.S
index 2ef9d05f21bc..2ef9d05f21bc 100644
--- a/arch/sparc64/lib/GENpage.S
+++ b/arch/sparc/lib/GENpage.S
diff --git a/arch/sparc64/lib/GENpatch.S b/arch/sparc/lib/GENpatch.S
index fab9e89f16bd..fab9e89f16bd 100644
--- a/arch/sparc64/lib/GENpatch.S
+++ b/arch/sparc/lib/GENpatch.S
diff --git a/arch/sparc/lib/Makefile b/arch/sparc/lib/Makefile
index 6e303e10c3b9..05ae5c945e35 100644
--- a/arch/sparc/lib/Makefile
+++ b/arch/sparc/lib/Makefile
@@ -1,13 +1,44 @@
 # Makefile for Sparc library files..
 #
 
-EXTRA_AFLAGS := -ansi -DST_DIV0=0x02
+asflags-y := -ansi -DST_DIV0=0x02
+ccflags-y := -Werror
 
-lib-y := mul.o rem.o sdiv.o udiv.o umul.o urem.o ashrdi3.o memcpy.o memset.o \
-         strlen.o checksum.o blockops.o memscan.o memcmp.o strncmp.o \
-	 strncpy_from_user.o divdi3.o udivdi3.o strlen_user.o \
-	 copy_user.o locks.o atomic.o \
-	 lshrdi3.o ashldi3.o rwsem.o muldi3.o bitext.o \
-	 cmpdi2.o
+lib-$(CONFIG_SPARC32) += mul.o rem.o sdiv.o udiv.o umul.o urem.o ashrdi3.o
+lib-$(CONFIG_SPARC32) += memcpy.o memset.o
+lib-y                 += strlen_$(BITS).o
+lib-y                 += checksum_$(BITS).o
+lib-$(CONFIG_SPARC32) += blockops.o
+lib-y                 += memscan_$(BITS).o memcmp_$(BITS).o strncmp_$(BITS).o
+lib-y                 += strncpy_from_user_$(BITS).o strlen_user_$(BITS).o
+lib-$(CONFIG_SPARC32) += divdi3.o udivdi3.o
+lib-$(CONFIG_SPARC32) += copy_user.o locks.o
+lib-y                 += atomic_$(BITS).o
+lib-$(CONFIG_SPARC32) += lshrdi3.o ashldi3.o
+lib-y                 += rwsem_$(BITS).o
+lib-$(CONFIG_SPARC32) += muldi3.o bitext.o cmpdi2.o
 
-obj-y += iomap.o atomic32.o
+lib-$(CONFIG_SPARC64) += PeeCeeI.o copy_page.o clear_page.o bzero.o
+lib-$(CONFIG_SPARC64) += csum_copy.o csum_copy_from_user.o csum_copy_to_user.o
+lib-$(CONFIG_SPARC64) += VISsave.o
+lib-$(CONFIG_SPARC64) += bitops.o
+
+lib-$(CONFIG_SPARC64) += U1memcpy.o U1copy_from_user.o U1copy_to_user.o
+
+lib-$(CONFIG_SPARC64) += U3memcpy.o U3copy_from_user.o U3copy_to_user.o
+lib-$(CONFIG_SPARC64) += U3patch.o
+
+lib-$(CONFIG_SPARC64) += NGmemcpy.o NGcopy_from_user.o NGcopy_to_user.o
+lib-$(CONFIG_SPARC64) += NGpatch.o NGpage.o NGbzero.o
+
+lib-$(CONFIG_SPARC64) += NG2memcpy.o NG2copy_from_user.o NG2copy_to_user.o
+lib-$(CONFIG_SPARC64) +=  NG2patch.o NG2page.o
+
+lib-$(CONFIG_SPARC64) += GENmemcpy.o GENcopy_from_user.o GENcopy_to_user.o
+lib-$(CONFIG_SPARC64) += GENpatch.o GENpage.o GENbzero.o
+
+lib-$(CONFIG_SPARC64) += copy_in_user.o user_fixup.o memmove.o
+lib-$(CONFIG_SPARC64) += mcount.o ipcsum.o xor.o
+
+obj-y                 += iomap.o
+obj-$(CONFIG_SPARC32) += atomic32.o
diff --git a/arch/sparc64/lib/NG2copy_from_user.S b/arch/sparc/lib/NG2copy_from_user.S
index c77ef5f22102..c77ef5f22102 100644
--- a/arch/sparc64/lib/NG2copy_from_user.S
+++ b/arch/sparc/lib/NG2copy_from_user.S
diff --git a/arch/sparc64/lib/NG2copy_to_user.S b/arch/sparc/lib/NG2copy_to_user.S
index 4bd4093acbbd..4bd4093acbbd 100644
--- a/arch/sparc64/lib/NG2copy_to_user.S
+++ b/arch/sparc/lib/NG2copy_to_user.S
diff --git a/arch/sparc64/lib/NG2memcpy.S b/arch/sparc/lib/NG2memcpy.S
index 0aed75653b50..0aed75653b50 100644
--- a/arch/sparc64/lib/NG2memcpy.S
+++ b/arch/sparc/lib/NG2memcpy.S
diff --git a/arch/sparc64/lib/NG2page.S b/arch/sparc/lib/NG2page.S
index 73b6b7c72cbf..73b6b7c72cbf 100644
--- a/arch/sparc64/lib/NG2page.S
+++ b/arch/sparc/lib/NG2page.S
diff --git a/arch/sparc64/lib/NG2patch.S b/arch/sparc/lib/NG2patch.S
index 28c36f06a6d1..28c36f06a6d1 100644
--- a/arch/sparc64/lib/NG2patch.S
+++ b/arch/sparc/lib/NG2patch.S
diff --git a/arch/sparc64/lib/NGbzero.S b/arch/sparc/lib/NGbzero.S
index 814d5f7a45e1..814d5f7a45e1 100644
--- a/arch/sparc64/lib/NGbzero.S
+++ b/arch/sparc/lib/NGbzero.S
diff --git a/arch/sparc64/lib/NGcopy_from_user.S b/arch/sparc/lib/NGcopy_from_user.S
index e7f433f71b42..e7f433f71b42 100644
--- a/arch/sparc64/lib/NGcopy_from_user.S
+++ b/arch/sparc/lib/NGcopy_from_user.S
diff --git a/arch/sparc64/lib/NGcopy_to_user.S b/arch/sparc/lib/NGcopy_to_user.S
index 6ea01c5532a0..6ea01c5532a0 100644
--- a/arch/sparc64/lib/NGcopy_to_user.S
+++ b/arch/sparc/lib/NGcopy_to_user.S
diff --git a/arch/sparc64/lib/NGmemcpy.S b/arch/sparc/lib/NGmemcpy.S
index 96a14caf6966..96a14caf6966 100644
--- a/arch/sparc64/lib/NGmemcpy.S
+++ b/arch/sparc/lib/NGmemcpy.S
diff --git a/arch/sparc64/lib/NGpage.S b/arch/sparc/lib/NGpage.S
index 428920de05ba..428920de05ba 100644
--- a/arch/sparc64/lib/NGpage.S
+++ b/arch/sparc/lib/NGpage.S
diff --git a/arch/sparc64/lib/NGpatch.S b/arch/sparc/lib/NGpatch.S
index 3b0674fc3366..3b0674fc3366 100644
--- a/arch/sparc64/lib/NGpatch.S
+++ b/arch/sparc/lib/NGpatch.S
diff --git a/arch/sparc64/lib/PeeCeeI.c b/arch/sparc/lib/PeeCeeI.c
index 46053e6ddd7b..46053e6ddd7b 100644
--- a/arch/sparc64/lib/PeeCeeI.c
+++ b/arch/sparc/lib/PeeCeeI.c
diff --git a/arch/sparc64/lib/U1copy_from_user.S b/arch/sparc/lib/U1copy_from_user.S
index 3192b0bf4fab..3192b0bf4fab 100644
--- a/arch/sparc64/lib/U1copy_from_user.S
+++ b/arch/sparc/lib/U1copy_from_user.S
diff --git a/arch/sparc64/lib/U1copy_to_user.S b/arch/sparc/lib/U1copy_to_user.S
index d1210ffb0b82..d1210ffb0b82 100644
--- a/arch/sparc64/lib/U1copy_to_user.S
+++ b/arch/sparc/lib/U1copy_to_user.S
diff --git a/arch/sparc64/lib/U1memcpy.S b/arch/sparc/lib/U1memcpy.S
index bafd2fc07acb..bafd2fc07acb 100644
--- a/arch/sparc64/lib/U1memcpy.S
+++ b/arch/sparc/lib/U1memcpy.S
diff --git a/arch/sparc64/lib/U3copy_from_user.S b/arch/sparc/lib/U3copy_from_user.S
index f5bfc8d9d216..f5bfc8d9d216 100644
--- a/arch/sparc64/lib/U3copy_from_user.S
+++ b/arch/sparc/lib/U3copy_from_user.S
diff --git a/arch/sparc64/lib/U3copy_to_user.S b/arch/sparc/lib/U3copy_to_user.S
index 2334f111bb0c..2334f111bb0c 100644
--- a/arch/sparc64/lib/U3copy_to_user.S
+++ b/arch/sparc/lib/U3copy_to_user.S
diff --git a/arch/sparc64/lib/U3memcpy.S b/arch/sparc/lib/U3memcpy.S
index 7cae9cc6a204..7cae9cc6a204 100644
--- a/arch/sparc64/lib/U3memcpy.S
+++ b/arch/sparc/lib/U3memcpy.S
diff --git a/arch/sparc64/lib/U3patch.S b/arch/sparc/lib/U3patch.S
index ecc302619a6e..ecc302619a6e 100644
--- a/arch/sparc64/lib/U3patch.S
+++ b/arch/sparc/lib/U3patch.S
diff --git a/arch/sparc64/lib/VISsave.S b/arch/sparc/lib/VISsave.S
index b320ae9e2e2e..b320ae9e2e2e 100644
--- a/arch/sparc64/lib/VISsave.S
+++ b/arch/sparc/lib/VISsave.S
diff --git a/arch/sparc/lib/atomic.S b/arch/sparc/lib/atomic_32.S
index 178cbb8ae1b9..178cbb8ae1b9 100644
--- a/arch/sparc/lib/atomic.S
+++ b/arch/sparc/lib/atomic_32.S
diff --git a/arch/sparc64/lib/atomic.S b/arch/sparc/lib/atomic_64.S
index 70ac4186f62b..0268210ca168 100644
--- a/arch/sparc64/lib/atomic.S
+++ b/arch/sparc/lib/atomic_64.S
@@ -43,29 +43,10 @@ atomic_sub: /* %o0 = decrement, %o1 = atomic_ptr */
 2:	BACKOFF_SPIN(%o2, %o3, 1b)
 	.size	atomic_sub, .-atomic_sub
 
-	/* On SMP we need to use memory barriers to ensure
-	 * correct memory operation ordering, nop these out
-	 * for uniprocessor.
-	 */
-#ifdef CONFIG_SMP
-
-#define ATOMIC_PRE_BARRIER	membar #StoreLoad | #LoadLoad;
-#define ATOMIC_POST_BARRIER	\
-	ba,pt %xcc, 80b;	\
-	membar #StoreLoad | #StoreStore
-
-80:	retl
-	 nop
-#else
-#define ATOMIC_PRE_BARRIER
-#define ATOMIC_POST_BARRIER
-#endif
-
 	.globl	atomic_add_ret
 	.type	atomic_add_ret,#function
 atomic_add_ret: /* %o0 = increment, %o1 = atomic_ptr */
 	BACKOFF_SETUP(%o2)
-	ATOMIC_PRE_BARRIER
 1:	lduw	[%o1], %g1
 	add	%g1, %o0, %g7
 	cas	[%o1], %g1, %g7
@@ -73,7 +54,6 @@ atomic_add_ret: /* %o0 = increment, %o1 = atomic_ptr */
 	bne,pn	%icc, 2f
 	 add	%g7, %o0, %g7
 	sra	%g7, 0, %o0
-	ATOMIC_POST_BARRIER
 	retl
 	 nop
 2:	BACKOFF_SPIN(%o2, %o3, 1b)
@@ -83,7 +63,6 @@ atomic_add_ret: /* %o0 = increment, %o1 = atomic_ptr */
 	.type	atomic_sub_ret,#function
 atomic_sub_ret: /* %o0 = decrement, %o1 = atomic_ptr */
 	BACKOFF_SETUP(%o2)
-	ATOMIC_PRE_BARRIER
 1:	lduw	[%o1], %g1
 	sub	%g1, %o0, %g7
 	cas	[%o1], %g1, %g7
@@ -91,7 +70,6 @@ atomic_sub_ret: /* %o0 = decrement, %o1 = atomic_ptr */
 	bne,pn	%icc, 2f
 	 sub	%g7, %o0, %g7
 	sra	%g7, 0, %o0
-	ATOMIC_POST_BARRIER
 	retl
 	 nop
 2:	BACKOFF_SPIN(%o2, %o3, 1b)
@@ -131,7 +109,6 @@ atomic64_sub: /* %o0 = decrement, %o1 = atomic_ptr */
 	.type	atomic64_add_ret,#function
 atomic64_add_ret: /* %o0 = increment, %o1 = atomic_ptr */
 	BACKOFF_SETUP(%o2)
-	ATOMIC_PRE_BARRIER
 1:	ldx	[%o1], %g1
 	add	%g1, %o0, %g7
 	casx	[%o1], %g1, %g7
@@ -139,7 +116,6 @@ atomic64_add_ret: /* %o0 = increment, %o1 = atomic_ptr */
 	bne,pn	%xcc, 2f
 	 add	%g7, %o0, %g7
 	mov	%g7, %o0
-	ATOMIC_POST_BARRIER
 	retl
 	 nop
 2:	BACKOFF_SPIN(%o2, %o3, 1b)
@@ -149,7 +125,6 @@ atomic64_add_ret: /* %o0 = increment, %o1 = atomic_ptr */
 	.type	atomic64_sub_ret,#function
 atomic64_sub_ret: /* %o0 = decrement, %o1 = atomic_ptr */
 	BACKOFF_SETUP(%o2)
-	ATOMIC_PRE_BARRIER
 1:	ldx	[%o1], %g1
 	sub	%g1, %o0, %g7
 	casx	[%o1], %g1, %g7
@@ -157,7 +132,6 @@ atomic64_sub_ret: /* %o0 = decrement, %o1 = atomic_ptr */
 	bne,pn	%xcc, 2f
 	 sub	%g7, %o0, %g7
 	mov	%g7, %o0
-	ATOMIC_POST_BARRIER
 	retl
 	 nop
 2:	BACKOFF_SPIN(%o2, %o3, 1b)
diff --git a/arch/sparc64/lib/bitops.S b/arch/sparc/lib/bitops.S
index 6b015a6eefb5..2b7228cb8c22 100644
--- a/arch/sparc64/lib/bitops.S
+++ b/arch/sparc/lib/bitops.S
@@ -8,29 +8,10 @@
 
 	.text
 
-	/* On SMP we need to use memory barriers to ensure
-	 * correct memory operation ordering, nop these out
-	 * for uniprocessor.
-	 */
-
-#ifdef CONFIG_SMP
-#define BITOP_PRE_BARRIER	membar #StoreLoad | #LoadLoad
-#define BITOP_POST_BARRIER	\
-	ba,pt	%xcc, 80b;	\
-	membar #StoreLoad | #StoreStore
-
-80:	retl
-	 nop
-#else
-#define BITOP_PRE_BARRIER
-#define BITOP_POST_BARRIER
-#endif
-
 	.globl	test_and_set_bit
 	.type	test_and_set_bit,#function
 test_and_set_bit:	/* %o0=nr, %o1=addr */
 	BACKOFF_SETUP(%o3)
-	BITOP_PRE_BARRIER
 	srlx	%o0, 6, %g1
 	mov	1, %o2
 	sllx	%g1, 3, %g3
@@ -45,7 +26,6 @@ test_and_set_bit:	/* %o0=nr, %o1=addr */
 	 and	%g7, %o2, %g2
 	clr	%o0
 	movrne	%g2, 1, %o0
-	BITOP_POST_BARRIER
 	retl
 	 nop
 2:	BACKOFF_SPIN(%o3, %o4, 1b)
@@ -55,7 +35,6 @@ test_and_set_bit:	/* %o0=nr, %o1=addr */
 	.type	test_and_clear_bit,#function
 test_and_clear_bit:	/* %o0=nr, %o1=addr */
 	BACKOFF_SETUP(%o3)
-	BITOP_PRE_BARRIER
 	srlx	%o0, 6, %g1
 	mov	1, %o2
 	sllx	%g1, 3, %g3
@@ -70,7 +49,6 @@ test_and_clear_bit:	/* %o0=nr, %o1=addr */
 	 and	%g7, %o2, %g2
 	clr	%o0
 	movrne	%g2, 1, %o0
-	BITOP_POST_BARRIER
 	retl
 	 nop
 2:	BACKOFF_SPIN(%o3, %o4, 1b)
@@ -80,7 +58,6 @@ test_and_clear_bit:	/* %o0=nr, %o1=addr */
 	.type	test_and_change_bit,#function
 test_and_change_bit:	/* %o0=nr, %o1=addr */
 	BACKOFF_SETUP(%o3)
-	BITOP_PRE_BARRIER
 	srlx	%o0, 6, %g1
 	mov	1, %o2
 	sllx	%g1, 3, %g3
@@ -95,7 +72,6 @@ test_and_change_bit:	/* %o0=nr, %o1=addr */
 	 and	%g7, %o2, %g2
 	clr	%o0
 	movrne	%g2, 1, %o0
-	BITOP_POST_BARRIER
 	retl
 	 nop
 2:	BACKOFF_SPIN(%o3, %o4, 1b)
diff --git a/arch/sparc64/lib/bzero.S b/arch/sparc/lib/bzero.S
index c7bbae8c590f..c7bbae8c590f 100644
--- a/arch/sparc64/lib/bzero.S
+++ b/arch/sparc/lib/bzero.S
diff --git a/arch/sparc/lib/checksum.S b/arch/sparc/lib/checksum_32.S
index 77f228533d47..77f228533d47 100644
--- a/arch/sparc/lib/checksum.S
+++ b/arch/sparc/lib/checksum_32.S
diff --git a/arch/sparc64/lib/checksum.S b/arch/sparc/lib/checksum_64.S
index 1d230f693dc4..1d230f693dc4 100644
--- a/arch/sparc64/lib/checksum.S
+++ b/arch/sparc/lib/checksum_64.S
diff --git a/arch/sparc64/lib/clear_page.S b/arch/sparc/lib/clear_page.S
index 77e531f6c2a7..77e531f6c2a7 100644
--- a/arch/sparc64/lib/clear_page.S
+++ b/arch/sparc/lib/clear_page.S
diff --git a/arch/sparc64/lib/copy_in_user.S b/arch/sparc/lib/copy_in_user.S
index 650af3f21f78..650af3f21f78 100644
--- a/arch/sparc64/lib/copy_in_user.S
+++ b/arch/sparc/lib/copy_in_user.S
diff --git a/arch/sparc64/lib/copy_page.S b/arch/sparc/lib/copy_page.S
index b243d3b606ba..b243d3b606ba 100644
--- a/arch/sparc64/lib/copy_page.S
+++ b/arch/sparc/lib/copy_page.S
diff --git a/arch/sparc64/lib/csum_copy.S b/arch/sparc/lib/csum_copy.S
index e566c770a0f6..e566c770a0f6 100644
--- a/arch/sparc64/lib/csum_copy.S
+++ b/arch/sparc/lib/csum_copy.S
diff --git a/arch/sparc64/lib/csum_copy_from_user.S b/arch/sparc/lib/csum_copy_from_user.S
index a22eddbe5dba..a22eddbe5dba 100644
--- a/arch/sparc64/lib/csum_copy_from_user.S
+++ b/arch/sparc/lib/csum_copy_from_user.S
diff --git a/arch/sparc64/lib/csum_copy_to_user.S b/arch/sparc/lib/csum_copy_to_user.S
index d5b12f441f02..d5b12f441f02 100644
--- a/arch/sparc64/lib/csum_copy_to_user.S
+++ b/arch/sparc/lib/csum_copy_to_user.S
diff --git a/arch/sparc64/lib/ipcsum.S b/arch/sparc/lib/ipcsum.S
index 58ca5b9a8778..58ca5b9a8778 100644
--- a/arch/sparc64/lib/ipcsum.S
+++ b/arch/sparc/lib/ipcsum.S
diff --git a/arch/sparc64/lib/mcount.S b/arch/sparc/lib/mcount.S
index 7ce9c65f3592..7ce9c65f3592 100644
--- a/arch/sparc64/lib/mcount.S
+++ b/arch/sparc/lib/mcount.S
diff --git a/arch/sparc/lib/memcmp.S b/arch/sparc/lib/memcmp_32.S
index cb4bdb0cc2af..cb4bdb0cc2af 100644
--- a/arch/sparc/lib/memcmp.S
+++ b/arch/sparc/lib/memcmp_32.S
diff --git a/arch/sparc64/lib/memcmp.S b/arch/sparc/lib/memcmp_64.S
index d3fdaa898566..d3fdaa898566 100644
--- a/arch/sparc64/lib/memcmp.S
+++ b/arch/sparc/lib/memcmp_64.S
diff --git a/arch/sparc64/lib/memmove.S b/arch/sparc/lib/memmove.S
index 97395802c23c..97395802c23c 100644
--- a/arch/sparc64/lib/memmove.S
+++ b/arch/sparc/lib/memmove.S
diff --git a/arch/sparc/lib/memscan.S b/arch/sparc/lib/memscan_32.S
index 4ff1657dfc24..4ff1657dfc24 100644
--- a/arch/sparc/lib/memscan.S
+++ b/arch/sparc/lib/memscan_32.S
diff --git a/arch/sparc64/lib/memscan.S b/arch/sparc/lib/memscan_64.S
index 5686dfa5dc15..5686dfa5dc15 100644
--- a/arch/sparc64/lib/memscan.S
+++ b/arch/sparc/lib/memscan_64.S
diff --git a/arch/sparc/lib/rwsem.S b/arch/sparc/lib/rwsem_32.S
index 9675268e7fde..9675268e7fde 100644
--- a/arch/sparc/lib/rwsem.S
+++ b/arch/sparc/lib/rwsem_32.S
diff --git a/arch/sparc64/lib/rwsem.S b/arch/sparc/lib/rwsem_64.S
index 1a4cc5654de4..91a7d29a79d5 100644
--- a/arch/sparc64/lib/rwsem.S
+++ b/arch/sparc/lib/rwsem_64.S
@@ -17,7 +17,6 @@ __down_read:
 	bne,pn		%icc, 1b
 	 add		%g7, 1, %g7
 	cmp		%g7, 0
-	membar		#StoreLoad | #StoreStore
 	bl,pn		%icc, 3f
 	 nop
 2:
@@ -42,7 +41,6 @@ __down_read_trylock:
 	cmp		%g1, %g7
 	bne,pn		%icc, 1b
 	 mov		1, %o1
-	membar		#StoreLoad | #StoreStore
 2:	retl
 	 mov		%o1, %o0
 	.size		__down_read_trylock, .-__down_read_trylock
@@ -58,7 +56,6 @@ __down_write:
 	cmp		%g3, %g7
 	bne,pn		%icc, 1b
 	 cmp		%g7, 0
-	membar		#StoreLoad | #StoreStore
 	bne,pn		%icc, 3f
 	 nop
 2:	retl
@@ -85,7 +82,6 @@ __down_write_trylock:
 	cmp		%g3, %g7
 	bne,pn		%icc, 1b
 	 mov		1, %o1
-	membar		#StoreLoad | #StoreStore
 2:	retl
 	 mov		%o1, %o0
 	.size		__down_write_trylock, .-__down_write_trylock
@@ -99,7 +95,6 @@ __up_read:
 	cmp		%g1, %g7
 	bne,pn		%icc, 1b
 	 cmp		%g7, 0
-	membar		#StoreLoad | #StoreStore
 	bl,pn		%icc, 3f
 	 nop
 2:	retl
@@ -129,7 +124,6 @@ __up_write:
 	bne,pn		%icc, 1b
 	 sub		%g7, %g1, %g7
 	cmp		%g7, 0
-	membar		#StoreLoad | #StoreStore
 	bl,pn		%icc, 3f
 	 nop
 2:
@@ -155,7 +149,6 @@ __downgrade_write:
 	bne,pn		%icc, 1b
 	 sub		%g7, %g1, %g7
 	cmp		%g7, 0
-	membar		#StoreLoad | #StoreStore
 	bl,pn		%icc, 3f
 	 nop
 2:
diff --git a/arch/sparc/lib/strlen.S b/arch/sparc/lib/strlen_32.S
index ed9a763368cd..ed9a763368cd 100644
--- a/arch/sparc/lib/strlen.S
+++ b/arch/sparc/lib/strlen_32.S
diff --git a/arch/sparc64/lib/strlen.S b/arch/sparc/lib/strlen_64.S
index e9ba1920d818..e9ba1920d818 100644
--- a/arch/sparc64/lib/strlen.S
+++ b/arch/sparc/lib/strlen_64.S
diff --git a/arch/sparc/lib/strlen_user.S b/arch/sparc/lib/strlen_user_32.S
index 8c8a371df3c9..8c8a371df3c9 100644
--- a/arch/sparc/lib/strlen_user.S
+++ b/arch/sparc/lib/strlen_user_32.S
diff --git a/arch/sparc64/lib/strlen_user.S b/arch/sparc/lib/strlen_user_64.S
index 114ed111e251..114ed111e251 100644
--- a/arch/sparc64/lib/strlen_user.S
+++ b/arch/sparc/lib/strlen_user_64.S
diff --git a/arch/sparc/lib/strncmp.S b/arch/sparc/lib/strncmp_32.S
index 494ec664537a..494ec664537a 100644
--- a/arch/sparc/lib/strncmp.S
+++ b/arch/sparc/lib/strncmp_32.S
diff --git a/arch/sparc64/lib/strncmp.S b/arch/sparc/lib/strncmp_64.S
index 980e83751556..980e83751556 100644
--- a/arch/sparc64/lib/strncmp.S
+++ b/arch/sparc/lib/strncmp_64.S
diff --git a/arch/sparc/lib/strncpy_from_user.S b/arch/sparc/lib/strncpy_from_user_32.S
index d77198976a66..d77198976a66 100644
--- a/arch/sparc/lib/strncpy_from_user.S
+++ b/arch/sparc/lib/strncpy_from_user_32.S
diff --git a/arch/sparc64/lib/strncpy_from_user.S b/arch/sparc/lib/strncpy_from_user_64.S
index 511c8f136f95..511c8f136f95 100644
--- a/arch/sparc64/lib/strncpy_from_user.S
+++ b/arch/sparc/lib/strncpy_from_user_64.S
diff --git a/arch/sparc64/lib/user_fixup.c b/arch/sparc/lib/user_fixup.c
index 05a361b0a1a4..05a361b0a1a4 100644
--- a/arch/sparc64/lib/user_fixup.c
+++ b/arch/sparc/lib/user_fixup.c
diff --git a/arch/sparc64/lib/xor.S b/arch/sparc/lib/xor.S
index f44f58f40234..f44f58f40234 100644
--- a/arch/sparc64/lib/xor.S
+++ b/arch/sparc/lib/xor.S
diff --git a/arch/sparc/math-emu/Makefile b/arch/sparc/math-emu/Makefile
index 8136987977f4..b9085ecbb27b 100644
--- a/arch/sparc/math-emu/Makefile
+++ b/arch/sparc/math-emu/Makefile
@@ -2,7 +2,7 @@
 # Makefile for the FPU instruction emulation.
 #
 
-obj-y    := math.o
+# supress all warnings - as math.c produces a lot!
+ccflags-y := -w
 
-EXTRA_AFLAGS := -ansi
-EXTRA_CFLAGS = -I. -Iinclude/math-emu -w
+obj-y    := math_$(BITS).o
diff --git a/arch/sparc/math-emu/ashldi3.S b/arch/sparc/math-emu/ashldi3.S
deleted file mode 100644
index 7230ff5c7aa1..000000000000
--- a/arch/sparc/math-emu/ashldi3.S
+++ /dev/null
@@ -1,36 +0,0 @@
-/*
- * ashldi3.S:	Math-emu code creates all kinds of references to
- *              this little routine on the sparc with gcc.
- *
- * Copyright (C) 1998 Jakub Jelinek(jj@ultra.linux.cz)
- */
-
-#include <asm/cprefix.h>
-
-	.globl C_LABEL(__ashldi3)
-C_LABEL(__ashldi3):
-	tst	%o2
-	be	3f
-	 mov	32, %g2
-
-	sub	%g2, %o2, %g2
-
-	tst	%g2
-	bg	1f
-	 srl	%o1, %g2, %g3
-
-	clr	%o5
-	neg	%g2
-	ba	2f
-	 sll	%o1, %g2, %o4
-
-1:
-	sll	%o1, %o2, %o5
-	srl	%o0, %o2, %g2
-	or	%g2, %g3, %o4
-2:
-	mov	%o4, %o0
-	mov	%o5, %o1
-3:
-	jmpl	%o7 + 8, %g0
-	 nop
diff --git a/arch/sparc/math-emu/math.c b/arch/sparc/math-emu/math_32.c
index 8613b3eb877c..e13f65da17df 100644
--- a/arch/sparc/math-emu/math.c
+++ b/arch/sparc/math-emu/math_32.c
@@ -69,7 +69,7 @@
 #include <linux/mm.h>
 #include <asm/uaccess.h>
 
-#include "sfp-util.h"
+#include "sfp-util_32.h"
 #include <math-emu/soft-fp.h>
 #include <math-emu/single.h>
 #include <math-emu/double.h>
diff --git a/arch/sparc64/math-emu/math.c b/arch/sparc/math-emu/math_64.c
index add053e0f3b3..6863c9bde25c 100644
--- a/arch/sparc64/math-emu/math.c
+++ b/arch/sparc/math-emu/math_64.c
@@ -16,7 +16,7 @@
 #include <asm/ptrace.h>
 #include <asm/uaccess.h>
 
-#include "sfp-util.h"
+#include "sfp-util_64.h"
 #include <math-emu/soft-fp.h>
 #include <math-emu/single.h>
 #include <math-emu/double.h>
diff --git a/arch/sparc/math-emu/sfp-util.h b/arch/sparc/math-emu/sfp-util_32.h
index d1b2aff3c259..d1b2aff3c259 100644
--- a/arch/sparc/math-emu/sfp-util.h
+++ b/arch/sparc/math-emu/sfp-util_32.h
diff --git a/arch/sparc64/math-emu/sfp-util.h b/arch/sparc/math-emu/sfp-util_64.h
index 425d3cf01af4..425d3cf01af4 100644
--- a/arch/sparc64/math-emu/sfp-util.h
+++ b/arch/sparc/math-emu/sfp-util_64.h
diff --git a/arch/sparc/mm/Makefile b/arch/sparc/mm/Makefile
index ea88955d97ff..681abe0a4594 100644
--- a/arch/sparc/mm/Makefile
+++ b/arch/sparc/mm/Makefile
@@ -1,17 +1,25 @@
 # Makefile for the linux Sparc-specific parts of the memory manager.
 #
 
-EXTRA_AFLAGS := -ansi
+asflags-y := -ansi
+ccflags-y := -Werror
 
-obj-y	:= fault.o init.o loadmmu.o generic.o extable.o btfixup.o \
-	    srmmu.o iommu.o io-unit.o hypersparc.o viking.o tsunami.o swift.o
+obj-$(CONFIG_SPARC64)   += ultra.o tlb.o tsb.o
+obj-y                   += fault_$(BITS).o
+obj-y                   += init_$(BITS).o
+obj-$(CONFIG_SPARC32)   += loadmmu.o
+obj-y                   += generic_$(BITS).o
+obj-$(CONFIG_SPARC32)   += extable.o btfixup.o srmmu.o iommu.o io-unit.o
+obj-$(CONFIG_SPARC32)   += hypersparc.o viking.o tsunami.o swift.o
 
-ifdef CONFIG_HIGHMEM
-obj-y	+= highmem.o
-endif
+# Only used by sparc64
+obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o
+
+# Only used by sparc32
+obj-$(CONFIG_HIGHMEM)   += highmem.o
 
 ifdef CONFIG_SMP
-obj-y   += nosun4c.o
+obj-$(CONFIG_SPARC32) += nosun4c.o
 else
-obj-y   += sun4c.o
+obj-$(CONFIG_SPARC32) += sun4c.o
 endif
diff --git a/arch/sparc/mm/fault.c b/arch/sparc/mm/fault_32.c
index a507e1174662..a507e1174662 100644
--- a/arch/sparc/mm/fault.c
+++ b/arch/sparc/mm/fault_32.c
diff --git a/arch/sparc64/mm/fault.c b/arch/sparc/mm/fault_64.c
index a9e474bf6385..a9e474bf6385 100644
--- a/arch/sparc64/mm/fault.c
+++ b/arch/sparc/mm/fault_64.c
diff --git a/arch/sparc/mm/generic.c b/arch/sparc/mm/generic_32.c
index a289261da9fd..a289261da9fd 100644
--- a/arch/sparc/mm/generic.c
+++ b/arch/sparc/mm/generic_32.c
diff --git a/arch/sparc64/mm/generic.c b/arch/sparc/mm/generic_64.c
index f362c2037013..f362c2037013 100644
--- a/arch/sparc64/mm/generic.c
+++ b/arch/sparc/mm/generic_64.c
diff --git a/arch/sparc64/mm/hugetlbpage.c b/arch/sparc/mm/hugetlbpage.c
index f27d10369e0c..f27d10369e0c 100644
--- a/arch/sparc64/mm/hugetlbpage.c
+++ b/arch/sparc/mm/hugetlbpage.c
diff --git a/arch/sparc/mm/init.c b/arch/sparc/mm/init_32.c
index 677c1e187a23..677c1e187a23 100644
--- a/arch/sparc/mm/init.c
+++ b/arch/sparc/mm/init_32.c
diff --git a/arch/sparc64/mm/init.c b/arch/sparc/mm/init_64.c
index 185f34679110..6ea73da29312 100644
--- a/arch/sparc64/mm/init.c
+++ b/arch/sparc/mm/init_64.c
@@ -50,7 +50,7 @@
 #include <asm/cpudata.h>
 #include <asm/irq.h>
 
-#include "init.h"
+#include "init_64.h"
 
 unsigned long kern_linear_pte_xor[2] __read_mostly;
 
@@ -214,7 +214,6 @@ static inline void set_dcache_dirty(struct page *page, int this_cpu)
 			     "or	%%g1, %0, %%g1\n\t"
 			     "casx	[%2], %%g7, %%g1\n\t"
 			     "cmp	%%g7, %%g1\n\t"
-			     "membar	#StoreLoad | #StoreStore\n\t"
 			     "bne,pn	%%xcc, 1b\n\t"
 			     " nop"
 			     : /* no outputs */
@@ -236,7 +235,6 @@ static inline void clear_dcache_dirty_cpu(struct page *page, unsigned long cpu)
 			     " andn	%%g7, %1, %%g1\n\t"
 			     "casx	[%2], %%g7, %%g1\n\t"
 			     "cmp	%%g7, %%g1\n\t"
-			     "membar	#StoreLoad | #StoreStore\n\t"
 			     "bne,pn	%%xcc, 1b\n\t"
 			     " nop\n"
 			     "2:"
@@ -956,7 +954,7 @@ int of_node_to_nid(struct device_node *dp)
 	return nid;
 }
 
-static void __init add_node_ranges(void)
+static void add_node_ranges(void)
 {
 	int i;
 
diff --git a/arch/sparc64/mm/init.h b/arch/sparc/mm/init_64.h
index 16063870a489..16063870a489 100644
--- a/arch/sparc64/mm/init.h
+++ b/arch/sparc/mm/init_64.h
diff --git a/arch/sparc/mm/srmmu.c b/arch/sparc/mm/srmmu.c
index dd8aa36f366c..56df59903eaa 100644
--- a/arch/sparc/mm/srmmu.c
+++ b/arch/sparc/mm/srmmu.c
@@ -1916,18 +1916,6 @@ static void __cpuinit poke_viking(void)
 	mreg |= VIKING_SBENABLE;
 	mreg &= ~(VIKING_ACENABLE);
 	srmmu_set_mmureg(mreg);
-
-#ifdef CONFIG_SMP
-	/* Avoid unnecessary cross calls. */
-	BTFIXUPCOPY_CALL(flush_cache_all, local_flush_cache_all);
-	BTFIXUPCOPY_CALL(flush_cache_mm, local_flush_cache_mm);
-	BTFIXUPCOPY_CALL(flush_cache_range, local_flush_cache_range);
-	BTFIXUPCOPY_CALL(flush_cache_page, local_flush_cache_page);
-	BTFIXUPCOPY_CALL(__flush_page_to_ram, local_flush_page_to_ram);
-	BTFIXUPCOPY_CALL(flush_sig_insns, local_flush_sig_insns);
-	BTFIXUPCOPY_CALL(flush_page_for_dma, local_flush_page_for_dma);
-	btfixup();
-#endif
 }
 
 static void __init init_viking(void)
@@ -2272,6 +2260,17 @@ void __init ld_mmu_srmmu(void)
 	BTFIXUPSET_CALL(__flush_page_to_ram, smp_flush_page_to_ram, BTFIXUPCALL_NORM);
 	BTFIXUPSET_CALL(flush_sig_insns, smp_flush_sig_insns, BTFIXUPCALL_NORM);
 	BTFIXUPSET_CALL(flush_page_for_dma, smp_flush_page_for_dma, BTFIXUPCALL_NORM);
+
+	if (poke_srmmu == poke_viking) {
+		/* Avoid unnecessary cross calls. */
+		BTFIXUPCOPY_CALL(flush_cache_all, local_flush_cache_all);
+		BTFIXUPCOPY_CALL(flush_cache_mm, local_flush_cache_mm);
+		BTFIXUPCOPY_CALL(flush_cache_range, local_flush_cache_range);
+		BTFIXUPCOPY_CALL(flush_cache_page, local_flush_cache_page);
+		BTFIXUPCOPY_CALL(__flush_page_to_ram, local_flush_page_to_ram);
+		BTFIXUPCOPY_CALL(flush_sig_insns, local_flush_sig_insns);
+		BTFIXUPCOPY_CALL(flush_page_for_dma, local_flush_page_for_dma);
+	}
 #endif
 
 	if (sparc_cpu_model == sun4d)
diff --git a/arch/sparc/mm/sun4c.c b/arch/sparc/mm/sun4c.c
index fe65aeeb3947..6b0c49004ba6 100644
--- a/arch/sparc/mm/sun4c.c
+++ b/arch/sparc/mm/sun4c.c
@@ -240,9 +240,7 @@ void sun4c_complete_all_stores(void)
 
 	_unused = sun4c_get_context();
 	sun4c_set_context(_unused);
-#ifdef CONFIG_SUN_AUXIO
 	_unused = get_auxio();
-#endif
 }
 
 /* Bootup utility functions. */
diff --git a/arch/sparc64/mm/tlb.c b/arch/sparc/mm/tlb.c
index d8f21e24a82f..d8f21e24a82f 100644
--- a/arch/sparc64/mm/tlb.c
+++ b/arch/sparc/mm/tlb.c
diff --git a/arch/sparc64/mm/tsb.c b/arch/sparc/mm/tsb.c
index 587f8efb2e05..36a0813f9517 100644
--- a/arch/sparc64/mm/tsb.c
+++ b/arch/sparc/mm/tsb.c
@@ -41,10 +41,8 @@ void flush_tsb_kernel_range(unsigned long start, unsigned long end)
 					      KERNEL_TSB_NENTRIES);
 		struct tsb *ent = &swapper_tsb[hash];
 
-		if (tag_compare(ent->tag, v)) {
+		if (tag_compare(ent->tag, v))
 			ent->tag = (1UL << TSB_TAG_INVALID_BIT);
-			membar_storeload_storestore();
-		}
 	}
 }
 
@@ -267,6 +265,18 @@ void __init pgtable_cache_init(void)
 	}
 }
 
+int sysctl_tsb_ratio = -2;
+
+static unsigned long tsb_size_to_rss_limit(unsigned long new_size)
+{
+	unsigned long num_ents = (new_size / sizeof(struct tsb));
+
+	if (sysctl_tsb_ratio < 0)
+		return num_ents - (num_ents >> -sysctl_tsb_ratio);
+	else
+		return num_ents + (num_ents >> sysctl_tsb_ratio);
+}
+
 /* When the RSS of an address space exceeds tsb_rss_limit for a TSB,
  * do_sparc64_fault() invokes this routine to try and grow it.
  *
@@ -297,19 +307,14 @@ void tsb_grow(struct mm_struct *mm, unsigned long tsb_index, unsigned long rss)
 
 	new_cache_index = 0;
 	for (new_size = 8192; new_size < max_tsb_size; new_size <<= 1UL) {
-		unsigned long n_entries = new_size / sizeof(struct tsb);
-
-		n_entries = (n_entries * 3) / 4;
-		if (n_entries > rss)
+		new_rss_limit = tsb_size_to_rss_limit(new_size);
+		if (new_rss_limit > rss)
 			break;
-
 		new_cache_index++;
 	}
 
 	if (new_size == max_tsb_size)
 		new_rss_limit = ~0UL;
-	else
-		new_rss_limit = ((new_size / sizeof(struct tsb)) * 3) / 4;
 
 retry_tsb_alloc:
 	gfp_flags = GFP_KERNEL;
diff --git a/arch/sparc64/mm/ultra.S b/arch/sparc/mm/ultra.S
index 86773e89dc1b..80c788ec7c32 100644
--- a/arch/sparc64/mm/ultra.S
+++ b/arch/sparc/mm/ultra.S
@@ -125,7 +125,6 @@ __spitfire_flush_tlb_mm_slow:
 	.align		32
 	.globl		__flush_icache_page
 __flush_icache_page:	/* %o0 = phys_page */
-	membar		#StoreStore
 	srlx		%o0, PAGE_SHIFT, %o0
 	sethi		%uhi(PAGE_OFFSET), %g1
 	sllx		%o0, PAGE_SHIFT, %o0
@@ -467,7 +466,7 @@ xcall_sync_tick:
 	.previous
 
 	rdpr		%pil, %g2
-	wrpr		%g0, 15, %pil
+	wrpr		%g0, PIL_NORMAL_MAX, %pil
 	sethi		%hi(109f), %g7
 	b,pt		%xcc, etrap_irq
 109:	 or		%g7, %lo(109b), %g7
@@ -507,7 +506,6 @@ xcall_fetch_glob_regs:
 	sllx		%g2, TRAP_BLOCK_SZ_SHIFT, %g2
 	add		%g7, %g2, %g7
 	ldx		[%g7 + TRAP_PER_CPU_THREAD], %g3
-	membar		#StoreStore
 	stx		%g3, [%g1 + GR_SNAP_THREAD]
 	retry
 
@@ -690,7 +688,7 @@ xcall_kgdb_capture:
 	.previous
 
 	rdpr		%pil, %g2
-	wrpr		%g0, 15, %pil
+	wrpr		%g0, PIL_NORMAL_MAX, %pil
 	sethi		%hi(109f), %g7
 	ba,pt		%xcc, etrap_irq
 109:	 or		%g7, %lo(109b), %g7
diff --git a/arch/sparc/oprofile/init.c b/arch/sparc/oprofile/init.c
index 17bb6035069b..d6e170c074fc 100644
--- a/arch/sparc/oprofile/init.c
+++ b/arch/sparc/oprofile/init.c
@@ -12,12 +12,239 @@
 #include <linux/errno.h>
 #include <linux/init.h>
  
+#ifdef CONFIG_SPARC64
+#include <asm/hypervisor.h>
+#include <asm/spitfire.h>
+#include <asm/cpudata.h>
+#include <asm/irq.h>
+
+static int nmi_enabled;
+
+struct pcr_ops {
+	u64 (*read)(void);
+	void (*write)(u64);
+};
+static const struct pcr_ops *pcr_ops;
+
+static u64 direct_pcr_read(void)
+{
+	u64 val;
+
+	read_pcr(val);
+	return val;
+}
+
+static void direct_pcr_write(u64 val)
+{
+	write_pcr(val);
+}
+
+static const struct pcr_ops direct_pcr_ops = {
+	.read	= direct_pcr_read,
+	.write	= direct_pcr_write,
+};
+
+static void n2_pcr_write(u64 val)
+{
+	unsigned long ret;
+
+	ret = sun4v_niagara2_setperf(HV_N2_PERF_SPARC_CTL, val);
+	if (val != HV_EOK)
+		write_pcr(val);
+}
+
+static const struct pcr_ops n2_pcr_ops = {
+	.read	= direct_pcr_read,
+	.write	= n2_pcr_write,
+};
+
+/* In order to commonize as much of the implementation as
+ * possible, we use PICH as our counter.  Mostly this is
+ * to accomodate Niagara-1 which can only count insn cycles
+ * in PICH.
+ */
+static u64 picl_value(void)
+{
+	u32 delta = local_cpu_data().clock_tick / HZ;
+
+	return ((u64)((0 - delta) & 0xffffffff)) << 32;
+}
+
+#define PCR_PIC_PRIV		0x00000001 /* PIC access is privileged */
+#define PCR_STRACE		0x00000002 /* Trace supervisor events  */
+#define PCR_UTRACE		0x00000004 /* Trace user events        */
+#define PCR_N2_HTRACE		0x00000008 /* Trace hypervisor events  */
+#define PCR_N2_TOE_OV0		0x00000010 /* Trap if PIC 0 overflows  */
+#define PCR_N2_TOE_OV1		0x00000020 /* Trap if PIC 1 overflows  */
+#define PCR_N2_MASK0		0x00003fc0
+#define PCR_N2_MASK0_SHIFT	6
+#define PCR_N2_SL0		0x0003c000
+#define PCR_N2_SL0_SHIFT	14
+#define PCR_N2_OV0		0x00040000
+#define PCR_N2_MASK1		0x07f80000
+#define PCR_N2_MASK1_SHIFT	19
+#define PCR_N2_SL1		0x78000000
+#define PCR_N2_SL1_SHIFT	27
+#define PCR_N2_OV1		0x80000000
+
+#define PCR_SUN4U_ENABLE	(PCR_PIC_PRIV | PCR_STRACE | PCR_UTRACE)
+#define PCR_N2_ENABLE		(PCR_PIC_PRIV | PCR_STRACE | PCR_UTRACE | \
+				 PCR_N2_TOE_OV1 | \
+				 (2 << PCR_N2_SL1_SHIFT) | \
+				 (0xff << PCR_N2_MASK1_SHIFT))
+
+static u64 pcr_enable = PCR_SUN4U_ENABLE;
+
+static void nmi_handler(struct pt_regs *regs)
+{
+	pcr_ops->write(PCR_PIC_PRIV);
+
+	if (nmi_enabled) {
+		oprofile_add_sample(regs, 0);
+
+		write_pic(picl_value());
+		pcr_ops->write(pcr_enable);
+	}
+}
+
+/* We count "clock cycle" events in the lower 32-bit PIC.
+ * Then configure it such that it overflows every HZ, and thus
+ * generates a level 15 interrupt at that frequency.
+ */
+static void cpu_nmi_start(void *_unused)
+{
+	pcr_ops->write(PCR_PIC_PRIV);
+	write_pic(picl_value());
+
+	pcr_ops->write(pcr_enable);
+}
+
+static void cpu_nmi_stop(void *_unused)
+{
+	pcr_ops->write(PCR_PIC_PRIV);
+}
+
+static int nmi_start(void)
+{
+	int err = register_perfctr_intr(nmi_handler);
+
+	if (!err) {
+		nmi_enabled = 1;
+		wmb();
+		err = on_each_cpu(cpu_nmi_start, NULL, 1);
+		if (err) {
+			nmi_enabled = 0;
+			wmb();
+			on_each_cpu(cpu_nmi_stop, NULL, 1);
+			release_perfctr_intr(nmi_handler);
+		}
+	}
+
+	return err;
+}
+
+static void nmi_stop(void)
+{
+	nmi_enabled = 0;
+	wmb();
+
+	on_each_cpu(cpu_nmi_stop, NULL, 1);
+	release_perfctr_intr(nmi_handler);
+	synchronize_sched();
+}
+
+static unsigned long perf_hsvc_group;
+static unsigned long perf_hsvc_major;
+static unsigned long perf_hsvc_minor;
+
+static int __init register_perf_hsvc(void)
+{
+	if (tlb_type == hypervisor) {
+		switch (sun4v_chip_type) {
+		case SUN4V_CHIP_NIAGARA1:
+			perf_hsvc_group = HV_GRP_NIAG_PERF;
+			break;
+
+		case SUN4V_CHIP_NIAGARA2:
+			perf_hsvc_group = HV_GRP_N2_CPU;
+			break;
+
+		default:
+			return -ENODEV;
+		}
+
+
+		perf_hsvc_major = 1;
+		perf_hsvc_minor = 0;
+		if (sun4v_hvapi_register(perf_hsvc_group,
+					 perf_hsvc_major,
+					 &perf_hsvc_minor)) {
+			printk("perfmon: Could not register N2 hvapi.\n");
+			return -ENODEV;
+		}
+	}
+	return 0;
+}
+
+static void unregister_perf_hsvc(void)
+{
+	if (tlb_type != hypervisor)
+		return;
+	sun4v_hvapi_unregister(perf_hsvc_group);
+}
+
+static int oprofile_nmi_init(struct oprofile_operations *ops)
+{
+	int err = register_perf_hsvc();
+
+	if (err)
+		return err;
+
+	switch (tlb_type) {
+	case hypervisor:
+		pcr_ops = &n2_pcr_ops;
+		pcr_enable = PCR_N2_ENABLE;
+		break;
+
+	case cheetah:
+	case cheetah_plus:
+		pcr_ops = &direct_pcr_ops;
+		break;
+
+	default:
+		return -ENODEV;
+	}
+
+	ops->create_files = NULL;
+	ops->setup = NULL;
+	ops->shutdown = NULL;
+	ops->start = nmi_start;
+	ops->stop = nmi_stop;
+	ops->cpu_type = "timer";
+
+	printk(KERN_INFO "oprofile: Using perfctr based NMI timer interrupt.\n");
+
+	return 0;
+}
+#endif
+
 int __init oprofile_arch_init(struct oprofile_operations *ops)
 {
-	return -ENODEV;
+	int ret = -ENODEV;
+
+#ifdef CONFIG_SPARC64
+	ret = oprofile_nmi_init(ops);
+	if (!ret)
+		return ret;
+#endif
+
+	return ret;
 }
 
 
 void oprofile_arch_exit(void)
 {
+#ifdef CONFIG_SPARC64
+	unregister_perf_hsvc();
+#endif
 }
diff --git a/arch/sparc/prom/Makefile b/arch/sparc/prom/Makefile
index 8f7e18546c97..f8e0278b8b4f 100644
--- a/arch/sparc/prom/Makefile
+++ b/arch/sparc/prom/Makefile
@@ -1,6 +1,21 @@
 # Makefile for the Sun Boot PROM interface library under
 # Linux.
 #
+asflags := -ansi
+ccflags := -Werror
 
-lib-y := bootstr.o devmap.o devops.o init.o memory.o misc.o mp.o \
-	 palloc.o ranges.o segment.o console.o printf.o tree.o
+lib-y                 := bootstr_$(BITS).o
+lib-$(CONFIG_SPARC32) += devmap.o
+lib-y                 += devops_$(BITS).o
+lib-y                 += init_$(BITS).o
+lib-$(CONFIG_SPARC32) += memory.o
+lib-y                 += misc_$(BITS).o
+lib-$(CONFIG_SPARC32) += mp.o
+lib-$(CONFIG_SPARC32) += palloc.o
+lib-$(CONFIG_SPARC32) += ranges.o
+lib-$(CONFIG_SPARC32) += segment.o
+lib-y                 += console_$(BITS).o
+lib-y                 += printf_$(BITS).o
+lib-y                 += tree_$(BITS).o
+lib-$(CONFIG_SPARC64) += p1275.o
+lib-$(CONFIG_SPARC64) += cif.o
diff --git a/arch/sparc/prom/bootstr.c b/arch/sparc/prom/bootstr_32.c
index 916831da7e67..916831da7e67 100644
--- a/arch/sparc/prom/bootstr.c
+++ b/arch/sparc/prom/bootstr_32.c
diff --git a/arch/sparc64/prom/bootstr.c b/arch/sparc/prom/bootstr_64.c
index ab9ccc63b388..ab9ccc63b388 100644
--- a/arch/sparc64/prom/bootstr.c
+++ b/arch/sparc/prom/bootstr_64.c
diff --git a/arch/sparc64/prom/cif.S b/arch/sparc/prom/cif.S
index 5f27ad779c0c..5f27ad779c0c 100644
--- a/arch/sparc64/prom/cif.S
+++ b/arch/sparc/prom/cif.S
diff --git a/arch/sparc/prom/console.c b/arch/sparc/prom/console_32.c
index b3075d73fc19..b3075d73fc19 100644
--- a/arch/sparc/prom/console.c
+++ b/arch/sparc/prom/console_32.c
diff --git a/arch/sparc64/prom/console.c b/arch/sparc/prom/console_64.c
index e1c3fc87484d..e1c3fc87484d 100644
--- a/arch/sparc64/prom/console.c
+++ b/arch/sparc/prom/console_64.c
diff --git a/arch/sparc/prom/devops.c b/arch/sparc/prom/devops_32.c
index 9f1a95c91ad1..9f1a95c91ad1 100644
--- a/arch/sparc/prom/devops.c
+++ b/arch/sparc/prom/devops_32.c
diff --git a/arch/sparc64/prom/devops.c b/arch/sparc/prom/devops_64.c
index 9dbd803e46e1..9dbd803e46e1 100644
--- a/arch/sparc64/prom/devops.c
+++ b/arch/sparc/prom/devops_64.c
diff --git a/arch/sparc/prom/init.c b/arch/sparc/prom/init_32.c
index 873217c6d823..873217c6d823 100644
--- a/arch/sparc/prom/init.c
+++ b/arch/sparc/prom/init_32.c
diff --git a/arch/sparc64/prom/init.c b/arch/sparc/prom/init_64.c
index 7b00f89490a4..7b00f89490a4 100644
--- a/arch/sparc64/prom/init.c
+++ b/arch/sparc/prom/init_64.c
diff --git a/arch/sparc/prom/misc.c b/arch/sparc/prom/misc_32.c
index 49b5057b9601..cf6c3f6d36c3 100644
--- a/arch/sparc/prom/misc.c
+++ b/arch/sparc/prom/misc_32.c
@@ -61,9 +61,7 @@ prom_cmdline(void)
 	restore_current();
 	install_linux_ticker();
 	spin_unlock_irqrestore(&prom_lock, flags);
-#ifdef CONFIG_SUN_AUXIO
 	set_auxio(AUXIO_LED, 0);
-#endif
 }
 
 /* Drop into the prom, but completely terminate the program.
diff --git a/arch/sparc64/prom/misc.c b/arch/sparc/prom/misc_64.c
index 9b0c0760901e..9b0c0760901e 100644
--- a/arch/sparc64/prom/misc.c
+++ b/arch/sparc/prom/misc_64.c
diff --git a/arch/sparc64/prom/p1275.c b/arch/sparc/prom/p1275.c
index 4b7c937bba61..4b7c937bba61 100644
--- a/arch/sparc64/prom/p1275.c
+++ b/arch/sparc/prom/p1275.c
diff --git a/arch/sparc/prom/printf.c b/arch/sparc/prom/printf_32.c
index a36ab9c5ee08..a36ab9c5ee08 100644
--- a/arch/sparc/prom/printf.c
+++ b/arch/sparc/prom/printf_32.c
diff --git a/arch/sparc64/prom/printf.c b/arch/sparc/prom/printf_64.c
index 660943ee4c2a..660943ee4c2a 100644
--- a/arch/sparc64/prom/printf.c
+++ b/arch/sparc/prom/printf_64.c
diff --git a/arch/sparc/prom/tree.c b/arch/sparc/prom/tree_32.c
index f228fe057b24..6d8187357331 100644
--- a/arch/sparc/prom/tree.c
+++ b/arch/sparc/prom/tree_32.c
@@ -85,7 +85,7 @@ int prom_getsibling(int node)
 /* Return the length in bytes of property 'prop' at node 'node'.
  * Return -1 on error.
  */
-int prom_getproplen(int node, char *prop)
+int prom_getproplen(int node, const char *prop)
 {
 	int ret;
 	unsigned long flags;
@@ -104,7 +104,7 @@ int prom_getproplen(int node, char *prop)
  * 'buffer' which has a size of 'bufsize'.  If the acquisition
  * was successful the length will be returned, else -1 is returned.
  */
-int prom_getproperty(int node, char *prop, char *buffer, int bufsize)
+int prom_getproperty(int node, const char *prop, char *buffer, int bufsize)
 {
 	int plen, ret;
 	unsigned long flags;
@@ -303,7 +303,7 @@ int prom_node_has_property(int node, char *prop)
 /* Set property 'pname' at node 'node' to value 'value' which has a length
  * of 'size' bytes.  Return the number of bytes the prom accepted.
  */
-int prom_setprop(int node, char *pname, char *value, int size)
+int prom_setprop(int node, const char *pname, char *value, int size)
 {
 	unsigned long flags;
 	int ret;
diff --git a/arch/sparc64/prom/tree.c b/arch/sparc/prom/tree_64.c
index 281aea44790b..281aea44790b 100644
--- a/arch/sparc64/prom/tree.c
+++ b/arch/sparc/prom/tree_64.c
diff --git a/arch/sparc64/Kconfig b/arch/sparc64/Kconfig
deleted file mode 100644
index 3b96e70b4670..000000000000
--- a/arch/sparc64/Kconfig
+++ /dev/null
@@ -1,433 +0,0 @@
-# sparc64 configuration
-mainmenu "Linux Kernel Configuration for 64-bit SPARC"
-
-config SPARC
-	bool
-	default y
-	select HAVE_OPROFILE
-	select HAVE_KPROBES
-	select HAVE_KRETPROBES
-
-config SPARC64
-	bool
-	default y
-	select HAVE_FUNCTION_TRACER
-	select HAVE_IDE
-	select HAVE_LMB
-	select HAVE_ARCH_KGDB
-	select USE_GENERIC_SMP_HELPERS if SMP
-	select HAVE_ARCH_TRACEHOOK
-	select ARCH_WANT_OPTIONAL_GPIOLIB
-	select RTC_CLASS
-	select RTC_DRV_M48T59
-	select RTC_DRV_CMOS
-	select RTC_DRV_BQ4802
-	select RTC_DRV_SUN4V
-	select RTC_DRV_STARFIRE
-
-config GENERIC_TIME
-	bool
-	default y
-
-config GENERIC_CMOS_UPDATE
-	bool
-	default y
-
-config GENERIC_CLOCKEVENTS
-	bool
-	default y
-
-config GENERIC_GPIO
-	bool
-	help
-	  Generic GPIO API support
-
-config 64BIT
-	def_bool y
-
-config MMU
-	bool
-	default y
-
-config IOMMU_HELPER
-	bool
-	default y
-
-config QUICKLIST
-	bool
-	default y
-
-config STACKTRACE_SUPPORT
-	bool
-	default y
-
-config LOCKDEP_SUPPORT
-	bool
-	default y
-
-config ARCH_MAY_HAVE_PC_FDC
-	bool
-	default y
-
-config ARCH_HAS_ILOG2_U32
-	bool
-	default n
-
-config ARCH_HAS_ILOG2_U64
-	bool
-	default n
-
-config AUDIT_ARCH
-	bool
-	default y
-
-config HAVE_SETUP_PER_CPU_AREA
-	def_bool y
-
-config ARCH_NO_VIRT_TO_BUS
-	def_bool y
-
-config OF
-	def_bool y
-
-config GENERIC_HARDIRQS_NO__DO_IRQ
-	bool
-	def_bool y
-
-source "init/Kconfig"
-source "kernel/Kconfig.freezer"
-
-menu "Processor type and features"
-
-choice
-	prompt "Kernel page size"
-	default SPARC64_PAGE_SIZE_8KB
-
-config SPARC64_PAGE_SIZE_8KB
-	bool "8KB"
-	help
-	  This lets you select the page size of the kernel.
-
-	  8KB and 64KB work quite well, since SPARC ELF sections
-	  provide for up to 64KB alignment.
-
-	  If you don't know what to do, choose 8KB.
-
-config SPARC64_PAGE_SIZE_64KB
-	bool "64KB"
-
-endchoice
-
-config SECCOMP
-	bool "Enable seccomp to safely compute untrusted bytecode"
-	depends on PROC_FS
-	default y
-	help
-	  This kernel feature is useful for number crunching applications
-	  that may need to compute untrusted bytecode during their
-	  execution. By using pipes or other transports made available to
-	  the process as file descriptors supporting the read/write
-	  syscalls, it's possible to isolate those applications in
-	  their own address space using seccomp. Once seccomp is
-	  enabled via /proc/<pid>/seccomp, it cannot be disabled
-	  and the task is only allowed to execute a few safe syscalls
-	  defined by each seccomp mode.
-
-	  If unsure, say Y. Only embedded should say N here.
-
-source kernel/Kconfig.hz
-
-config HOTPLUG_CPU
-	bool "Support for hot-pluggable CPUs"
-	depends on SMP
-	select HOTPLUG
-	help
-	  Say Y here to experiment with turning CPUs off and on.  CPUs
-	  can be controlled through /sys/devices/system/cpu/cpu#.
-	  Say N if you want to disable CPU hotplug.
-
-config GENERIC_HARDIRQS
-	bool
-	default y
-
-source "kernel/time/Kconfig"
-
-config SMP
-	bool "Symmetric multi-processing support"
-	help
-	  This enables support for systems with more than one CPU. If you have
-	  a system with only one CPU, say N. If you have a system with more than
-	  one CPU, say Y.
-
-	  If you say N here, the kernel will run on single and multiprocessor
-	  machines, but will use only one CPU of a multiprocessor machine. If
-	  you say Y here, the kernel will run on single-processor machines.
-	  On a single-processor machine, the kernel will run faster if you say
-	  N here.
-
-	  If you don't know what to do here, say N.
-
-config NR_CPUS
-	int "Maximum number of CPUs (2-1024)"
-	range 2 1024
-	depends on SMP
-	default "64"
-
-source "drivers/cpufreq/Kconfig"
-
-config US3_FREQ
-	tristate "UltraSPARC-III CPU Frequency driver"
-	depends on CPU_FREQ
-	select CPU_FREQ_TABLE
-	help
-	  This adds the CPUFreq driver for UltraSPARC-III processors.
-
-	  For details, take a look at <file:Documentation/cpu-freq>.
-
-	  If in doubt, say N.
-
-config US2E_FREQ
-	tristate "UltraSPARC-IIe CPU Frequency driver"
-	depends on CPU_FREQ
-	select CPU_FREQ_TABLE
-	help
-	  This adds the CPUFreq driver for UltraSPARC-IIe processors.
-
-	  For details, take a look at <file:Documentation/cpu-freq>.
-
-	  If in doubt, say N.
-
-config US3_MC
-	tristate "UltraSPARC-III Memory Controller driver"
-	default y
-	help
-	  This adds a driver for the UltraSPARC-III memory controller.
-	  Loading this driver allows exact mnemonic strings to be
-	  printed in the event of a memory error, so that the faulty DIMM
-	  on the motherboard can be matched to the error.
-
-	  If in doubt, say Y, as this information can be very useful.
-
-# Global things across all Sun machines.
-config GENERIC_LOCKBREAK
-	bool
-	default y
-	depends on SMP && PREEMPT
-
-config RWSEM_GENERIC_SPINLOCK
-	bool
-
-config RWSEM_XCHGADD_ALGORITHM
-	bool
-	default y
-
-config GENERIC_FIND_NEXT_BIT
-	bool
-	default y
-
-config GENERIC_HWEIGHT
-	bool
-	default y if !ULTRA_HAS_POPULATION_COUNT
-
-config GENERIC_CALIBRATE_DELAY
-	bool
-	default y
-
-choice
-	prompt "SPARC64 Huge TLB Page Size"
-	depends on HUGETLB_PAGE
-	default HUGETLB_PAGE_SIZE_4MB
-
-config HUGETLB_PAGE_SIZE_4MB
-	bool "4MB"
-
-config HUGETLB_PAGE_SIZE_512K
-	bool "512K"
-
-config HUGETLB_PAGE_SIZE_64K
-	depends on !SPARC64_PAGE_SIZE_64KB
-	bool "64K"
-
-endchoice
-
-endmenu
-
-config NUMA
-	bool "NUMA support"
-	depends on SMP
-
-config NODES_SHIFT
-	int
-	default "4"
-	depends on NEED_MULTIPLE_NODES
-
-# Some NUMA nodes have memory ranges that span
-# other nodes.  Even though a pfn is valid and
-# between a node's start and end pfns, it may not
-# reside on that node.  See memmap_init_zone()
-# for details.
-config NODES_SPAN_OTHER_NODES
-	def_bool y
-	depends on NEED_MULTIPLE_NODES
-
-config ARCH_POPULATES_NODE_MAP
-	def_bool y
-
-config ARCH_SELECT_MEMORY_MODEL
-	def_bool y
-
-config ARCH_SPARSEMEM_ENABLE
-	def_bool y
-	select SPARSEMEM_VMEMMAP_ENABLE
-
-config ARCH_SPARSEMEM_DEFAULT
-	def_bool y
-
-source "mm/Kconfig"
-
-config ISA
-	bool
-
-config ISAPNP
-	bool
-
-config EISA
-	bool
-
-config MCA
-	bool
-
-config PCMCIA
-	tristate
-	help
-	  Say Y here if you want to attach PCMCIA- or PC-cards to your Linux
-	  computer.  These are credit-card size devices such as network cards,
-	  modems or hard drives often used with laptops computers.  There are
-	  actually two varieties of these cards: the older 16 bit PCMCIA cards
-	  and the newer 32 bit CardBus cards.  If you want to use CardBus
-	  cards, you need to say Y here and also to "CardBus support" below.
-
-	  To use your PC-cards, you will need supporting software from David
-	  Hinds' pcmcia-cs package (see the file <file:Documentation/Changes>
-	  for location).  Please also read the PCMCIA-HOWTO, available from
-	  <http://www.tldp.org/docs.html#howto>.
-
-	  To compile this driver as modules, choose M here: the
-	  modules will be called pcmcia_core and ds.
-
-config SBUS
-	bool
-	default y
-
-config SBUSCHAR
-	bool
-	default y
-
-config SUN_AUXIO
-	bool
-	default y
-
-config SUN_IO
-	bool
-	default y
-
-config SUN_LDOMS
-	bool "Sun Logical Domains support"
-	help
-	  Say Y here is you want to support virtual devices via
-	  Logical Domains.
-
-config PCI
-	bool "PCI support"
-	select ARCH_SUPPORTS_MSI
-	help
-	  Find out whether your system includes a PCI bus. PCI is the name of
-	  a bus system, i.e. the way the CPU talks to the other stuff inside
-	  your box.  If you say Y here, the kernel will include drivers and
-	  infrastructure code to support PCI bus devices.
-
-config PCI_DOMAINS
-	def_bool PCI
-
-config PCI_SYSCALL
-	def_bool PCI
-
-source "drivers/pci/Kconfig"
-
-config SUN_OPENPROMFS
-	tristate "Openprom tree appears in /proc/openprom"
-	help
-	  If you say Y, the OpenPROM device tree will be available as a
-	  virtual file system, which you can mount to /proc/openprom by "mount
-	  -t openpromfs none /proc/openprom".
-
-	  To compile the /proc/openprom support as a module, choose M here: the
-	  module will be called openpromfs.  If unsure, choose M.
-
-menu "Executable file formats"
-
-source "fs/Kconfig.binfmt"
-
-config COMPAT
-	bool
-	default y
-	select COMPAT_BINFMT_ELF
-
-config SYSVIPC_COMPAT
-	bool
-	depends on COMPAT && SYSVIPC
-	default y
-
-endmenu
-
-config SCHED_SMT
-	bool "SMT (Hyperthreading) scheduler support"
-	depends on SMP
-	default y
-	help
-	  SMT scheduler support improves the CPU scheduler's decision making
-	  when dealing with SPARC cpus at a cost of slightly increased overhead
-	  in some places. If unsure say N here.
-
-config SCHED_MC
-	bool "Multi-core scheduler support"
-	depends on SMP
-	default y
-	help
-	  Multi-core scheduler support improves the CPU scheduler's decision
-	  making when dealing with multi-core CPU chips at a cost of slightly
-	  increased overhead in some places. If unsure say N here.
-
-source "kernel/Kconfig.preempt"
-
-config CMDLINE_BOOL
-	bool "Default bootloader kernel arguments"
-
-config CMDLINE
-	string "Initial kernel command string"
-	depends on CMDLINE_BOOL
-	default "console=ttyS0,9600 root=/dev/sda1"
-	help
-	  Say Y here if you want to be able to pass default arguments to
-	  the kernel. This will be overridden by the bootloader, if you
-	  use one (such as SILO). This is most useful if you want to boot
-	  a kernel from TFTP, and want default options to be available
-	  with having them passed on the command line.
-
-	  NOTE: This option WILL override the PROM bootargs setting!
-
-source "net/Kconfig"
-
-source "drivers/Kconfig"
-
-source "drivers/sbus/char/Kconfig"
-
-source "fs/Kconfig"
-
-source "arch/sparc64/Kconfig.debug"
-
-source "security/Kconfig"
-
-source "crypto/Kconfig"
-
-source "lib/Kconfig"
diff --git a/arch/sparc64/Kconfig.debug b/arch/sparc64/Kconfig.debug
deleted file mode 100644
index c40515c06690..000000000000
--- a/arch/sparc64/Kconfig.debug
+++ /dev/null
@@ -1,44 +0,0 @@
-menu "Kernel hacking"
-
-config TRACE_IRQFLAGS_SUPPORT
-	bool
-	default y
-
-source "lib/Kconfig.debug"
-
-config DEBUG_STACK_USAGE
-	bool "Enable stack utilization instrumentation"
-	depends on DEBUG_KERNEL
-	help
-	  Enables the display of the minimum amount of free stack which each
-	  task has ever had available in the sysrq-T and sysrq-P debug output.
-
-	  This option will slow down process creation somewhat.
-
-config DEBUG_DCFLUSH
-	bool "D-cache flush debugging"
-	depends on DEBUG_KERNEL
-
-config STACK_DEBUG
-	depends on DEBUG_KERNEL
-	bool "Stack Overflow Detection Support"
-
-config DEBUG_PAGEALLOC
-	bool "Debug page memory allocations"
-	depends on DEBUG_KERNEL && !HIBERNATION
-	help
-	  Unmap pages from the kernel linear mapping after free_pages().
-	  This results in a large slowdown, but helps to find certain types
-	  of memory corruptions.
-
-config MCOUNT
-	bool
-	depends on STACK_DEBUG || FUNCTION_TRACER
-	default y
-
-config FRAME_POINTER
-	bool
-	depends on MCOUNT
-	default y
-
-endmenu
diff --git a/arch/sparc64/Makefile b/arch/sparc64/Makefile
deleted file mode 100644
index c7214abc0d84..000000000000
--- a/arch/sparc64/Makefile
+++ /dev/null
@@ -1,48 +0,0 @@
-# sparc64/Makefile
-#
-# Makefile for the architecture dependent flags and dependencies on the
-# 64-bit Sparc.
-#
-# Copyright (C) 1996,1998 David S. Miller (davem@caip.rutgers.edu)
-# Copyright (C) 1998 Jakub Jelinek (jj@ultra.linux.cz)
-#
-
-CHECKFLAGS	+= -D__sparc__ -D__sparc_v9__ -D__arch64__ -m64
-
-# Undefine sparc when processing vmlinux.lds - it is used
-# And teach CPP we are doing 64 bit builds (for this case)
-CPPFLAGS_vmlinux.lds += -m64 -Usparc
-
-LDFLAGS		:= -m elf64_sparc
-
-KBUILD_CFLAGS += -m64 -pipe -mno-fpu -mcpu=ultrasparc -mcmodel=medlow \
-	-ffixed-g4 -ffixed-g5 -fcall-used-g7 -Wno-sign-compare \
-	-Wa,--undeclared-regs
-KBUILD_CFLAGS += $(call cc-option,-mtune=ultrasparc3)
-KBUILD_AFLAGS += -m64 -mcpu=ultrasparc -Wa,--undeclared-regs
-
-ifeq ($(CONFIG_MCOUNT),y)
-  KBUILD_CFLAGS += -pg
-endif
-
-head-y := arch/sparc64/kernel/head.o arch/sparc64/kernel/init_task.o
-
-core-y				+= arch/sparc64/kernel/ arch/sparc64/mm/
-core-y				+= arch/sparc64/math-emu/
-libs-y				+= arch/sparc64/prom/ arch/sparc64/lib/
-drivers-$(CONFIG_OPROFILE)	+= arch/sparc64/oprofile/
-
-boot := arch/sparc64/boot
-
-image tftpboot.img vmlinux.aout: vmlinux
-	$(Q)$(MAKE) $(build)=$(boot) $(boot)/$@
-
-archclean:
-	$(Q)$(MAKE) $(clean)=$(boot)
-
-define archhelp
-  echo  '* vmlinux       - Standard sparc64 kernel'
-  echo  '  vmlinux.aout  - a.out kernel for sparc64'
-  echo  '  tftpboot.img  - Image prepared for tftp'
-endef
-
diff --git a/arch/sparc64/boot/Makefile b/arch/sparc64/boot/Makefile
deleted file mode 100644
index 0458b5244f09..000000000000
--- a/arch/sparc64/boot/Makefile
+++ /dev/null
@@ -1,33 +0,0 @@
-# Makefile for the Sparc64 boot stuff.
-#
-# Copyright (C) 1995 David S. Miller (davem@caip.rutgers.edu)
-# Copyright (C) 1997 Jakub Jelinek (jj@sunsite.mff.cuni.cz)
-
-ROOT_IMG	:= /usr/src/root.img
-ELFTOAOUT	:= elftoaout
-
-hostprogs-y	:= piggyback
-targets		:= image tftpboot.img vmlinux.aout
-
-quiet_cmd_elftoaout = ELF2AOUT $@
-      cmd_elftoaout = $(ELFTOAOUT) vmlinux -o $@
-quiet_cmd_piggy     = PIGGY   $@
-      cmd_piggy     = $(obj)/piggyback $@ System.map $(ROOT_IMG)
-quiet_cmd_strip     = STRIP   $@
-      cmd_strip     = $(STRIP) -R .comment -R .note -K sun4u_init -K _end -K _start vmlinux -o $@
-
-
-# Actual linking
-$(obj)/image: vmlinux FORCE
-	$(call if_changed,strip)
-	@echo '  kernel: $@ is ready'
-
-$(obj)/tftpboot.img: vmlinux $(obj)/piggyback System.map $(ROOT_IMG) FORCE
-	$(call if_changed,elftoaout)
-	$(call if_changed,piggy)
-	@echo '  kernel: $@ is ready'
-
-$(obj)/vmlinux.aout: vmlinux FORCE
-	$(call if_changed,elftoaout)
-	@echo '  kernel: $@ is ready'
-
diff --git a/arch/sparc64/kernel/Makefile b/arch/sparc64/kernel/Makefile
deleted file mode 100644
index b3e0b986bef8..000000000000
--- a/arch/sparc64/kernel/Makefile
+++ /dev/null
@@ -1,36 +0,0 @@
-#
-# Makefile for the linux kernel.
-#
-
-EXTRA_AFLAGS := -ansi
-EXTRA_CFLAGS := -Werror
-
-CFLAGS_REMOVE_ftrace.o = -pg
-
-extra-y		:= head.o init_task.o vmlinux.lds
-
-obj-y		:= process.o setup.o cpu.o idprom.o reboot.o \
-		   traps.o auxio.o una_asm.o sysfs.o iommu.o \
-		   irq.o ptrace.o time.o sys_sparc.o signal.o \
-		   unaligned.o central.o starfire.o \
-		   power.o sbus.o sparc64_ksyms.o ebus.o \
-		   visemul.o prom.o of_device.o hvapi.o sstate.o mdesc.o
-
-obj-$(CONFIG_DYNAMIC_FTRACE) += ftrace.o
-obj-$(CONFIG_STACKTRACE) += stacktrace.o
-obj-$(CONFIG_PCI)	 += pci.o pci_common.o psycho_common.o \
-			    pci_psycho.o pci_sabre.o pci_schizo.o \
-			    pci_sun4v.o pci_sun4v_asm.o pci_fire.o
-obj-$(CONFIG_PCI_MSI)	+= pci_msi.o
-obj-$(CONFIG_SMP)	 += smp.o trampoline.o hvtramp.o
-obj-$(CONFIG_COMPAT) += sys32.o sys_sparc32.o signal32.o
-obj-$(CONFIG_MODULES) += module.o
-obj-$(CONFIG_US3_FREQ) += us3_cpufreq.o
-obj-$(CONFIG_US2E_FREQ) += us2e_cpufreq.o
-obj-$(CONFIG_US3_MC) += chmc.o
-obj-$(CONFIG_KPROBES) += kprobes.o
-obj-$(CONFIG_SUN_LDOMS) += ldc.o vio.o viohs.o ds.o
-obj-$(CONFIG_AUDIT) += audit.o
-obj-$(CONFIG_AUDIT)$(CONFIG_COMPAT) += compat_audit.o
-obj-y += $(obj-yy)
-obj-$(CONFIG_KGDB) += kgdb.o
diff --git a/arch/sparc64/kernel/asm-offsets.c b/arch/sparc64/kernel/asm-offsets.c
deleted file mode 100644
index 9e263112a6e2..000000000000
--- a/arch/sparc64/kernel/asm-offsets.c
+++ /dev/null
@@ -1 +0,0 @@
-/* Dummy asm-offsets.c file. Required by kbuild and ready to be used - hint! */
diff --git a/arch/sparc64/kernel/cpu.c b/arch/sparc64/kernel/cpu.c
deleted file mode 100644
index 0c9ac83ed0a8..000000000000
--- a/arch/sparc64/kernel/cpu.c
+++ /dev/null
@@ -1,166 +0,0 @@
-/* cpu.c: Dinky routines to look for the kind of Sparc cpu
- *        we are on.
- *
- * Copyright (C) 1996, 2007, 2008 David S. Miller (davem@davemloft.net)
- */
-
-#include <linux/kernel.h>
-#include <linux/init.h>
-#include <linux/sched.h>
-#include <linux/smp.h>
-#include <asm/asi.h>
-#include <asm/system.h>
-#include <asm/fpumacro.h>
-#include <asm/cpudata.h>
-#include <asm/spitfire.h>
-#include <asm/oplib.h>
-
-#include "entry.h"
-
-DEFINE_PER_CPU(cpuinfo_sparc, __cpu_data) = { 0 };
-
-struct cpu_chip_info {
-	unsigned short	manuf;
-	unsigned short	impl;
-	const char	*cpu_name;
-	const char	*fp_name;
-};
-
-static const struct cpu_chip_info cpu_chips[] = {
-	{
-		.manuf		= 0x17,
-		.impl		= 0x10,
-		.cpu_name	= "TI UltraSparc I   (SpitFire)",
-		.fp_name	= "UltraSparc I integrated FPU",
-	},
-	{
-		.manuf		= 0x22,
-		.impl		= 0x10,
-		.cpu_name	= "TI UltraSparc I   (SpitFire)",
-		.fp_name	= "UltraSparc I integrated FPU",
-	},
-	{
-		.manuf		= 0x17,
-		.impl		= 0x11,
-		.cpu_name	= "TI UltraSparc II  (BlackBird)",
-		.fp_name	= "UltraSparc II integrated FPU",
-	},
-	{
-		.manuf		= 0x17,
-		.impl		= 0x12,
-		.cpu_name	= "TI UltraSparc IIi (Sabre)",
-		.fp_name	= "UltraSparc IIi integrated FPU",
-	},
-	{
-		.manuf		= 0x17,
-		.impl		= 0x13,
-		.cpu_name	= "TI UltraSparc IIe (Hummingbird)",
-		.fp_name	= "UltraSparc IIe integrated FPU",
-	},
-	{
-		.manuf		= 0x3e,
-		.impl		= 0x14,
-		.cpu_name	= "TI UltraSparc III (Cheetah)",
-		.fp_name	= "UltraSparc III integrated FPU",
-	},
-	{
-		.manuf		= 0x3e,
-		.impl		= 0x15,
-		.cpu_name	= "TI UltraSparc III+ (Cheetah+)",
-		.fp_name	= "UltraSparc III+ integrated FPU",
-	},
-	{
-		.manuf		= 0x3e,
-		.impl		= 0x16,
-		.cpu_name	= "TI UltraSparc IIIi (Jalapeno)",
-		.fp_name	= "UltraSparc IIIi integrated FPU",
-	},
-	{
-		.manuf		= 0x3e,
-		.impl		= 0x18,
-		.cpu_name	= "TI UltraSparc IV (Jaguar)",
-		.fp_name	= "UltraSparc IV integrated FPU",
-	},
-	{
-		.manuf		= 0x3e,
-		.impl		= 0x19,
-		.cpu_name	= "TI UltraSparc IV+ (Panther)",
-		.fp_name	= "UltraSparc IV+ integrated FPU",
-	},
-	{
-		.manuf		= 0x3e,
-		.impl		= 0x22,
-		.cpu_name	= "TI UltraSparc IIIi+ (Serrano)",
-		.fp_name	= "UltraSparc IIIi+ integrated FPU",
-	},
-};
-
-#define NSPARCCHIPS ARRAY_SIZE(linux_sparc_chips)
-
-const char *sparc_cpu_type;
-const char *sparc_fpu_type;
-
-static void __init sun4v_cpu_probe(void)
-{
-	switch (sun4v_chip_type) {
-	case SUN4V_CHIP_NIAGARA1:
-		sparc_cpu_type = "UltraSparc T1 (Niagara)";
-		sparc_fpu_type = "UltraSparc T1 integrated FPU";
-		break;
-
-	case SUN4V_CHIP_NIAGARA2:
-		sparc_cpu_type = "UltraSparc T2 (Niagara2)";
-		sparc_fpu_type = "UltraSparc T2 integrated FPU";
-		break;
-
-	default:
-		printk(KERN_WARNING "CPU: Unknown sun4v cpu type [%s]\n",
-		       prom_cpu_compatible);
-		sparc_cpu_type = "Unknown SUN4V CPU";
-		sparc_fpu_type = "Unknown SUN4V FPU";
-		break;
-	}
-}
-
-static const struct cpu_chip_info * __init find_cpu_chip(unsigned short manuf,
-							 unsigned short impl)
-{
-	int i;
-
-	for (i = 0; i < ARRAY_SIZE(cpu_chips); i++) {
-		const struct cpu_chip_info *p = &cpu_chips[i];
-
-		if (p->manuf == manuf && p->impl == impl)
-			return p;
-	}
-	return NULL;
-}
-
-static int __init cpu_type_probe(void)
-{
-	if (tlb_type == hypervisor) {
-		sun4v_cpu_probe();
-	} else {
-		unsigned long ver, manuf, impl;
-		const struct cpu_chip_info *p;
-	
-		__asm__ __volatile__("rdpr %%ver, %0" : "=r" (ver));
-	
-		manuf = ((ver >> 48) & 0xffff);
-		impl = ((ver >> 32) & 0xffff);
-
-		p = find_cpu_chip(manuf, impl);
-		if (p) {
-			sparc_cpu_type = p->cpu_name;
-			sparc_fpu_type = p->fp_name;
-		} else {
-			printk(KERN_ERR "CPU: Unknown chip, manuf[%lx] impl[%lx]\n",
-			       manuf, impl);
-			sparc_cpu_type = "Unknown CPU";
-			sparc_fpu_type = "Unknown FPU";
-		}
-	}
-	return 0;
-}
-
-arch_initcall(cpu_type_probe);
diff --git a/arch/sparc64/kernel/idprom.c b/arch/sparc64/kernel/idprom.c
deleted file mode 100644
index 5b45a808c621..000000000000
--- a/arch/sparc64/kernel/idprom.c
+++ /dev/null
@@ -1,49 +0,0 @@
-/*
- * idprom.c: Routines to load the idprom into kernel addresses and
- *           interpret the data contained within.
- *
- * Copyright (C) 1995 David S. Miller (davem@caip.rutgers.edu)
- */
-
-#include <linux/kernel.h>
-#include <linux/types.h>
-#include <linux/init.h>
-
-#include <asm/oplib.h>
-#include <asm/idprom.h>
-
-struct idprom *idprom;
-static struct idprom idprom_buffer;
-
-/* Calculate the IDPROM checksum (xor of the data bytes). */
-static unsigned char __init calc_idprom_cksum(struct idprom *idprom)
-{
-	unsigned char cksum, i, *ptr = (unsigned char *)idprom;
-
-	for (i = cksum = 0; i <= 0x0E; i++)
-		cksum ^= *ptr++;
-
-	return cksum;
-}
-
-/* Create a local IDPROM copy and verify integrity. */
-void __init idprom_init(void)
-{
-	prom_get_idprom((char *) &idprom_buffer, sizeof(idprom_buffer));
-
-	idprom = &idprom_buffer;
-
-	if (idprom->id_format != 0x01)  {
-		prom_printf("IDPROM: Warning, unknown format type!\n");
-	}
-
-	if (idprom->id_cksum != calc_idprom_cksum(idprom)) {
-		prom_printf("IDPROM: Warning, checksum failure (nvram=%x, calc=%x)!\n",
-			    idprom->id_cksum, calc_idprom_cksum(idprom));
-	}
-
-	printk("Ethernet address: %02x:%02x:%02x:%02x:%02x:%02x\n",
-	       idprom->id_ethaddr[0], idprom->id_ethaddr[1],
-	       idprom->id_ethaddr[2], idprom->id_ethaddr[3],
-	       idprom->id_ethaddr[4], idprom->id_ethaddr[5]);
-}
diff --git a/arch/sparc64/kernel/init_task.c b/arch/sparc64/kernel/init_task.c
deleted file mode 100644
index d2b312381c19..000000000000
--- a/arch/sparc64/kernel/init_task.c
+++ /dev/null
@@ -1,35 +0,0 @@
-#include <linux/mm.h>
-#include <linux/fs.h>
-#include <linux/module.h>
-#include <linux/sched.h>
-#include <linux/init_task.h>
-#include <linux/mqueue.h>
-
-#include <asm/pgtable.h>
-#include <asm/uaccess.h>
-#include <asm/processor.h>
-
-static struct fs_struct init_fs = INIT_FS;
-static struct signal_struct init_signals = INIT_SIGNALS(init_signals);
-static struct sighand_struct init_sighand = INIT_SIGHAND(init_sighand);
-struct mm_struct init_mm = INIT_MM(init_mm);
-
-EXPORT_SYMBOL(init_mm);
-
-/* .text section in head.S is aligned at 2 page boundary and this gets linked
- * right after that so that the init_thread_union is aligned properly as well.
- * We really don't need this special alignment like the Intel does, but
- * I do it anyways for completeness.
- */
-__asm__ (".text");
-union thread_union init_thread_union = { INIT_THREAD_INFO(init_task) };
-
-/*
- * Initial task structure.
- *
- * All other task structs will be allocated on slabs in fork.c
- */
-EXPORT_SYMBOL(init_task);
-
-__asm__(".data");
-struct task_struct init_task = INIT_TASK(init_task);
diff --git a/arch/sparc64/kernel/vmlinux.lds.S b/arch/sparc64/kernel/vmlinux.lds.S
deleted file mode 100644
index 01f809617e5e..000000000000
--- a/arch/sparc64/kernel/vmlinux.lds.S
+++ /dev/null
@@ -1,147 +0,0 @@
-/* ld script to make UltraLinux kernel */
-
-#include <asm/page.h>
-#include <asm-generic/vmlinux.lds.h>
-
-OUTPUT_FORMAT("elf64-sparc", "elf64-sparc", "elf64-sparc")
-OUTPUT_ARCH(sparc:v9a)
-ENTRY(_start)
-
-jiffies = jiffies_64;
-SECTIONS
-{
-	swapper_low_pmd_dir = 0x0000000000402000;
-	. = 0x4000;
-	.text 0x0000000000404000 : {
-		_text = .;
-		TEXT_TEXT
-		SCHED_TEXT
-		LOCK_TEXT
-		KPROBES_TEXT
-		*(.gnu.warning)
-	} = 0
-	_etext = .;
-	PROVIDE (etext = .);
-
-	RO_DATA(PAGE_SIZE)
-	.data : {
-		DATA_DATA
-		CONSTRUCTORS
-	}
-	.data1 : {
-		*(.data1)
-	}
-	. = ALIGN(64);
-	.data.cacheline_aligned : {
-		*(.data.cacheline_aligned)
-	}
-	. = ALIGN(64);
-	.data.read_mostly : {
-		*(.data.read_mostly)
-	}
-	_edata = .;
-	PROVIDE (edata = .);
-	.fixup : {
-		*(.fixup)
-	}
-	. = ALIGN(16);
-	__ex_table : {
-		__start___ex_table = .;
-		*(__ex_table)
-		__stop___ex_table = .;
-	}
-	NOTES
-
-	. = ALIGN(PAGE_SIZE);
-	.init.text : {
-		__init_begin = .;
-		_sinittext = .;
-		INIT_TEXT
-		_einittext = .;
-	}
-	.init.data : {
-		INIT_DATA
-	}
-	. = ALIGN(16);
-	.init.setup : {
-		__setup_start = .;
-		*(.init.setup)
-		__setup_end = .;
-	}
-	.initcall.init : {
-		__initcall_start = .;
-		INITCALLS
-		__initcall_end = .;
-	}
-	.con_initcall.init : {
-		__con_initcall_start = .;
-		*(.con_initcall.init)
-		__con_initcall_end = .;
-	}
-	SECURITY_INIT
-
-	. = ALIGN(4);
-	.tsb_ldquad_phys_patch : {
-		__tsb_ldquad_phys_patch = .;
-		*(.tsb_ldquad_phys_patch)
-		__tsb_ldquad_phys_patch_end = .;
-	}
-
-	.tsb_phys_patch : {
-		__tsb_phys_patch = .;
-		*(.tsb_phys_patch)
-		__tsb_phys_patch_end = .;
-	}
-
-	.cpuid_patch : {
-		__cpuid_patch = .;
-		*(.cpuid_patch)
-		__cpuid_patch_end = .;
-	}
-
-	.sun4v_1insn_patch : {
-		__sun4v_1insn_patch = .;
-		*(.sun4v_1insn_patch)
-		__sun4v_1insn_patch_end = .;
-	}
-	.sun4v_2insn_patch : {
-		__sun4v_2insn_patch = .;
-		*(.sun4v_2insn_patch)
-		__sun4v_2insn_patch_end = .;
-	}
-
-#ifdef CONFIG_BLK_DEV_INITRD
-	. = ALIGN(PAGE_SIZE);
-	.init.ramfs : {
-		__initramfs_start = .;
-		*(.init.ramfs)
-		__initramfs_end = .;
-	}
-#endif
-
-	PERCPU(PAGE_SIZE)
-
-	. = ALIGN(PAGE_SIZE);
-	__init_end = .;
-	__bss_start = .;
-	.sbss : {
-		*(.sbss)
-		*(.scommon)
-	}
-	.bss : {
-		*(.dynbss)
-		*(.bss)
-		*(COMMON)
-	}
-	_end = . ;
-	PROVIDE (end = .);
-
-	/DISCARD/ : {
-		EXIT_TEXT
-		EXIT_DATA
-		*(.exitcall.exit)
-	}
-
-	STABS_DEBUG
-	DWARF_DEBUG
-}
diff --git a/arch/sparc64/lib/Makefile b/arch/sparc64/lib/Makefile
deleted file mode 100644
index f095e13910bc..000000000000
--- a/arch/sparc64/lib/Makefile
+++ /dev/null
@@ -1,23 +0,0 @@
-#
-# Makefile for Sparc64 library files..
-#
-
-EXTRA_AFLAGS := -ansi
-EXTRA_CFLAGS := -Werror
-
-lib-y := PeeCeeI.o copy_page.o clear_page.o strlen.o strncmp.o \
-	 memscan.o strncpy_from_user.o strlen_user.o memcmp.o checksum.o \
-	 bzero.o csum_copy.o csum_copy_from_user.o csum_copy_to_user.o \
-	 VISsave.o atomic.o bitops.o \
-	 U1memcpy.o U1copy_from_user.o U1copy_to_user.o \
-	 U3memcpy.o U3copy_from_user.o U3copy_to_user.o U3patch.o \
-	 NGmemcpy.o NGcopy_from_user.o NGcopy_to_user.o NGpatch.o \
-	 NGpage.o NGbzero.o \
-	 NG2memcpy.o NG2copy_from_user.o NG2copy_to_user.o NG2patch.o \
-	 NG2page.o \
-	 GENmemcpy.o GENcopy_from_user.o GENcopy_to_user.o GENpatch.o \
-	 GENpage.o GENbzero.o \
-	 copy_in_user.o user_fixup.o memmove.o \
-	 mcount.o ipcsum.o rwsem.o xor.o
-
-obj-y += iomap.o
diff --git a/arch/sparc64/lib/iomap.c b/arch/sparc64/lib/iomap.c
deleted file mode 100644
index 7120ebbd4d03..000000000000
--- a/arch/sparc64/lib/iomap.c
+++ /dev/null
@@ -1,48 +0,0 @@
-/*
- * Implement the sparc64 iomap interfaces
- */
-#include <linux/pci.h>
-#include <linux/module.h>
-#include <asm/io.h>
-
-/* Create a virtual mapping cookie for an IO port range */
-void __iomem *ioport_map(unsigned long port, unsigned int nr)
-{
-	return (void __iomem *) (unsigned long) port;
-}
-
-void ioport_unmap(void __iomem *addr)
-{
-	/* Nothing to do */
-}
-EXPORT_SYMBOL(ioport_map);
-EXPORT_SYMBOL(ioport_unmap);
-
-/* Create a virtual mapping cookie for a PCI BAR (memory or IO) */
-void __iomem *pci_iomap(struct pci_dev *dev, int bar, unsigned long maxlen)
-{
-	resource_size_t start = pci_resource_start(dev, bar);
-	resource_size_t len = pci_resource_len(dev, bar);
-	unsigned long flags = pci_resource_flags(dev, bar);
-
-	if (!len || !start)
-		return NULL;
-	if (maxlen && len > maxlen)
-		len = maxlen;
-	if (flags & IORESOURCE_IO)
-		return ioport_map(start, len);
-	if (flags & IORESOURCE_MEM) {
-		if (flags & IORESOURCE_CACHEABLE)
-			return ioremap(start, len);
-		return ioremap_nocache(start, len);
-	}
-	/* What? */
-	return NULL;
-}
-
-void pci_iounmap(struct pci_dev *dev, void __iomem * addr)
-{
-	/* nothing to do */
-}
-EXPORT_SYMBOL(pci_iomap);
-EXPORT_SYMBOL(pci_iounmap);
diff --git a/arch/sparc64/math-emu/Makefile b/arch/sparc64/math-emu/Makefile
deleted file mode 100644
index cc5cb9baf6aa..000000000000
--- a/arch/sparc64/math-emu/Makefile
+++ /dev/null
@@ -1,7 +0,0 @@
-#
-# Makefile for the FPU instruction emulation.
-#
-
-obj-y    := math.o
-
-EXTRA_CFLAGS = -Iinclude/math-emu -w
diff --git a/arch/sparc64/mm/Makefile b/arch/sparc64/mm/Makefile
deleted file mode 100644
index 68d04c0370f4..000000000000
--- a/arch/sparc64/mm/Makefile
+++ /dev/null
@@ -1,9 +0,0 @@
-# Makefile for the linux Sparc64-specific parts of the memory manager.
-#
-
-EXTRA_AFLAGS := -ansi
-EXTRA_CFLAGS := -Werror
-
-obj-y    := ultra.o tlb.o tsb.o fault.o init.o generic.o
-
-obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o
diff --git a/arch/sparc64/oprofile/Makefile b/arch/sparc64/oprofile/Makefile
deleted file mode 100644
index e9feca1ca28b..000000000000
--- a/arch/sparc64/oprofile/Makefile
+++ /dev/null
@@ -1,9 +0,0 @@
-obj-$(CONFIG_OPROFILE) += oprofile.o
-
-DRIVER_OBJS = $(addprefix ../../../drivers/oprofile/, \
-		oprof.o cpu_buffer.o buffer_sync.o \
-		event_buffer.o oprofile_files.o \
-		oprofilefs.o oprofile_stats.o \
-		timer_int.o )
-
-oprofile-y				:= $(DRIVER_OBJS) init.o
diff --git a/arch/sparc64/oprofile/init.c b/arch/sparc64/oprofile/init.c
deleted file mode 100644
index 17bb6035069b..000000000000
--- a/arch/sparc64/oprofile/init.c
+++ /dev/null
@@ -1,23 +0,0 @@
-/**
- * @file init.c
- *
- * @remark Copyright 2002 OProfile authors
- * @remark Read the file COPYING
- *
- * @author John Levon <levon@movementarian.org>
- */
-
-#include <linux/kernel.h>
-#include <linux/oprofile.h>
-#include <linux/errno.h>
-#include <linux/init.h>
- 
-int __init oprofile_arch_init(struct oprofile_operations *ops)
-{
-	return -ENODEV;
-}
-
-
-void oprofile_arch_exit(void)
-{
-}
diff --git a/arch/sparc64/prom/Makefile b/arch/sparc64/prom/Makefile
deleted file mode 100644
index 8c94483ca54d..000000000000
--- a/arch/sparc64/prom/Makefile
+++ /dev/null
@@ -1,9 +0,0 @@
-# Makefile for the Sun Boot PROM interface library under
-# Linux.
-#
-
-EXTRA_AFLAGS := -ansi
-EXTRA_CFLAGS := -Werror
-
-lib-y   := bootstr.o devops.o init.o misc.o \
-	   tree.o console.o printf.o p1275.o cif.o
diff --git a/arch/um/include/asm/system.h b/arch/um/include/asm/system.h
index 753346e2cdfd..ae5f94d6317d 100644
--- a/arch/um/include/asm/system.h
+++ b/arch/um/include/asm/system.h
@@ -11,21 +11,21 @@ extern int get_signals(void);
 extern void block_signals(void);
 extern void unblock_signals(void);
 
-#define local_save_flags(flags) do { typecheck(unsigned long, flags); \
+#define raw_local_save_flags(flags) do { typecheck(unsigned long, flags); \
 				     (flags) = get_signals(); } while(0)
-#define local_irq_restore(flags) do { typecheck(unsigned long, flags); \
+#define raw_local_irq_restore(flags) do { typecheck(unsigned long, flags); \
 				      set_signals(flags); } while(0)
 
-#define local_irq_save(flags) do { local_save_flags(flags); \
-                                   local_irq_disable(); } while(0)
+#define raw_local_irq_save(flags) do { raw_local_save_flags(flags); \
+                                   raw_local_irq_disable(); } while(0)
 
-#define local_irq_enable() unblock_signals()
-#define local_irq_disable() block_signals()
+#define raw_local_irq_enable() unblock_signals()
+#define raw_local_irq_disable() block_signals()
 
 #define irqs_disabled()                 \
 ({                                      \
         unsigned long flags;            \
-        local_save_flags(flags);        \
+        raw_local_save_flags(flags);        \
         (flags == 0);                   \
 })
 
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index ac22bb7719f7..a9051b3223d8 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -19,6 +19,8 @@ config X86_64
 config X86
 	def_bool y
 	select HAVE_AOUT if X86_32
+	select HAVE_READQ
+	select HAVE_WRITEQ
 	select HAVE_UNSTABLE_SCHED_CLOCK
 	select HAVE_IDE
 	select HAVE_OPROFILE
@@ -29,11 +31,14 @@ config X86
 	select HAVE_FTRACE_MCOUNT_RECORD
 	select HAVE_DYNAMIC_FTRACE
 	select HAVE_FUNCTION_TRACER
+	select HAVE_FUNCTION_RET_TRACER if X86_32
+	select HAVE_FUNCTION_TRACE_MCOUNT_TEST
 	select HAVE_KVM if ((X86_32 && !X86_VOYAGER && !X86_VISWS && !X86_NUMAQ) || X86_64)
 	select HAVE_ARCH_KGDB if !X86_VOYAGER
 	select HAVE_ARCH_TRACEHOOK
 	select HAVE_GENERIC_DMA_COHERENT if X86_32
 	select HAVE_EFFICIENT_UNALIGNED_ACCESS
+	select USER_STACKTRACE_SUPPORT
 
 config ARCH_DEFCONFIG
 	string
@@ -242,21 +247,13 @@ config X86_FIND_SMP_CONFIG
 	def_bool y
 	depends on X86_MPPARSE || X86_VOYAGER
 
-if ACPI
 config X86_MPPARSE
-	def_bool y
-	bool "Enable MPS table"
+	bool "Enable MPS table" if ACPI
+	default y
 	depends on X86_LOCAL_APIC
 	help
 	  For old smp systems that do not have proper acpi support. Newer systems
 	  (esp with 64bit cpus) with acpi support, MADT and DSDT will override it
-endif
-
-if !ACPI
-config X86_MPPARSE
-	def_bool y
-	depends on X86_LOCAL_APIC
-endif
 
 choice
 	prompt "Subarchitecture Type"
@@ -367,10 +364,10 @@ config X86_RDC321X
 	  as R-8610-(G).
 	  If you don't have one of these chips, you should say N here.
 
-config SCHED_NO_NO_OMIT_FRAME_POINTER
+config SCHED_OMIT_FRAME_POINTER
 	def_bool y
 	prompt "Single-depth WCHAN output"
-	depends on X86_32
+	depends on X86
 	help
 	  Calculate simpler /proc/<PID>/wchan values. If this option
 	  is disabled then wchan values will recurse back to the
@@ -465,10 +462,6 @@ config X86_CYCLONE_TIMER
 	def_bool y
 	depends on X86_GENERICARCH
 
-config ES7000_CLUSTERED_APIC
-	def_bool y
-	depends on SMP && X86_ES7000 && MPENTIUMIII
-
 source "arch/x86/Kconfig.cpu"
 
 config HPET_TIMER
@@ -569,7 +562,7 @@ config AMD_IOMMU
 
 # need this always selected by IOMMU for the VIA workaround
 config SWIOTLB
-	bool
+	def_bool y if X86_64
 	help
 	  Support for software bounce buffers used on x86-64 systems
 	  which don't have a hardware IOMMU (e.g. the current generation
@@ -660,6 +653,30 @@ config X86_VISWS_APIC
 	def_bool y
 	depends on X86_32 && X86_VISWS
 
+config X86_REROUTE_FOR_BROKEN_BOOT_IRQS
+	bool "Reroute for broken boot IRQs"
+	default n
+	depends on X86_IO_APIC
+	help
+	  This option enables a workaround that fixes a source of
+	  spurious interrupts. This is recommended when threaded
+	  interrupt handling is used on systems where the generation of
+	  superfluous "boot interrupts" cannot be disabled.
+
+	  Some chipsets generate a legacy INTx "boot IRQ" when the IRQ
+	  entry in the chipset's IO-APIC is masked (as, e.g. the RT
+	  kernel does during interrupt handling). On chipsets where this
+	  boot IRQ generation cannot be disabled, this workaround keeps
+	  the original IRQ line masked so that only the equivalent "boot
+	  IRQ" is delivered to the CPUs. The workaround also tells the
+	  kernel to set up the IRQ handler on the boot IRQ line. In this
+	  way only one interrupt is delivered to the kernel. Otherwise
+	  the spurious second interrupt may cause the kernel to bring
+	  down (vital) interrupt lines.
+
+	  Only affects "broken" chipsets. Interrupt sharing may be
+	  increased on these systems.
+
 config X86_MCE
 	bool "Machine Check Exception"
 	depends on !X86_VOYAGER
@@ -956,24 +973,37 @@ config X86_PAE
 config ARCH_PHYS_ADDR_T_64BIT
        def_bool X86_64 || X86_PAE
 
+config DIRECT_GBPAGES
+	bool "Enable 1GB pages for kernel pagetables" if EMBEDDED
+	default y
+	depends on X86_64
+	help
+	  Allow the kernel linear mapping to use 1GB pages on CPUs that
+	  support it. This can improve the kernel's performance a tiny bit by
+	  reducing TLB pressure. If in doubt, say "Y".
+
 # Common NUMA Features
 config NUMA
-	bool "Numa Memory Allocation and Scheduler Support (EXPERIMENTAL)"
+	bool "Numa Memory Allocation and Scheduler Support"
 	depends on SMP
 	depends on X86_64 || (X86_32 && HIGHMEM64G && (X86_NUMAQ || X86_BIGSMP || X86_SUMMIT && ACPI) && EXPERIMENTAL)
 	default n if X86_PC
 	default y if (X86_NUMAQ || X86_SUMMIT || X86_BIGSMP)
 	help
 	  Enable NUMA (Non Uniform Memory Access) support.
+
 	  The kernel will try to allocate memory used by a CPU on the
 	  local memory controller of the CPU and add some more
 	  NUMA awareness to the kernel.
 
-	  For 32-bit this is currently highly experimental and should be only
-	  used for kernel development. It might also cause boot failures.
-	  For 64-bit this is recommended on all multiprocessor Opteron systems.
-	  If the system is EM64T, you should say N unless your system is
-	  EM64T NUMA.
+	  For 64-bit this is recommended if the system is Intel Core i7
+	  (or later), AMD Opteron, or EM64T NUMA.
+
+	  For 32-bit this is only needed on (rare) 32-bit-only platforms
+	  that support NUMA topologies, such as NUMAQ / Summit, or if you
+	  boot a 32-bit kernel on a 64-bit NUMA platform.
+
+	  Otherwise, you should say N.
 
 comment "NUMA (Summit) requires SMP, 64GB highmem support, ACPI"
 	depends on X86_32 && X86_SUMMIT && (!HIGHMEM64G || !ACPI)
@@ -1072,6 +1102,11 @@ config ARCH_MEMORY_PROBE
 	def_bool X86_64
 	depends on MEMORY_HOTPLUG
 
+config ILLEGAL_POINTER_VALUE
+       hex
+       default 0 if X86_32
+       default 0xdead000000000000 if X86_64
+
 source "mm/Kconfig"
 
 config HIGHPTE
@@ -1269,13 +1304,17 @@ config SECCOMP
 
 	  If unsure, say Y. Only embedded should say N here.
 
+config CC_STACKPROTECTOR_ALL
+	bool
+
 config CC_STACKPROTECTOR
 	bool "Enable -fstack-protector buffer overflow detection (EXPERIMENTAL)"
-	depends on X86_64 && EXPERIMENTAL && BROKEN
+	depends on X86_64
+	select CC_STACKPROTECTOR_ALL
 	help
-         This option turns on the -fstack-protector GCC feature. This
-	  feature puts, at the beginning of critical functions, a canary
-	  value on the stack just before the return address, and validates
+          This option turns on the -fstack-protector GCC feature. This
+	  feature puts, at the beginning of functions, a canary value on
+	  the stack just before the return address, and validates
 	  the value just before actually returning.  Stack based buffer
 	  overflows (that need to overwrite this return address) now also
 	  overwrite the canary, which gets detected and the attack is then
@@ -1283,15 +1322,8 @@ config CC_STACKPROTECTOR
 
 	  This feature requires gcc version 4.2 or above, or a distribution
 	  gcc with the feature backported. Older versions are automatically
-	  detected and for those versions, this configuration option is ignored.
-
-config CC_STACKPROTECTOR_ALL
-	bool "Use stack-protector for all functions"
-	depends on CC_STACKPROTECTOR
-	help
-	  Normally, GCC only inserts the canary value protection for
-	  functions that use large-ish on-stack buffers. By enabling
-	  this option, GCC will be asked to do this for ALL functions.
+	  detected and for those versions, this configuration option is
+	  ignored. (and a warning is printed during bootup)
 
 source kernel/Kconfig.hz
 
@@ -1493,6 +1525,10 @@ config ARCH_ENABLE_MEMORY_HOTPLUG
 	def_bool y
 	depends on X86_64 || (X86_32 && HIGHMEM)
 
+config ARCH_ENABLE_MEMORY_HOTREMOVE
+	def_bool y
+	depends on MEMORY_HOTPLUG
+
 config HAVE_ARCH_EARLY_PFN_TO_NID
 	def_bool X86_64
 	depends on NUMA
@@ -1632,13 +1668,6 @@ config APM_ALLOW_INTS
 	  many of the newer IBM Thinkpads.  If you experience hangs when you
 	  suspend, try setting this to Y.  Otherwise, say N.
 
-config APM_REAL_MODE_POWER_OFF
-	bool "Use real mode APM BIOS call to power off"
-	help
-	  Use real mode APM BIOS calls to switch off the computer. This is
-	  a work-around for a number of buggy BIOSes. Switch this option on if
-	  your computer crashes instead of powering off properly.
-
 endif # APM
 
 source "arch/x86/kernel/cpu/cpufreq/Kconfig"
diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug
index 2a3dfbd5e677..28f111461ca8 100644
--- a/arch/x86/Kconfig.debug
+++ b/arch/x86/Kconfig.debug
@@ -114,21 +114,10 @@ config DEBUG_RODATA
 	  data. This is recommended so that we can catch kernel bugs sooner.
 	  If in doubt, say "Y".
 
-config DIRECT_GBPAGES
-	bool "Enable gbpages-mapped kernel pagetables"
-	depends on DEBUG_KERNEL && EXPERIMENTAL && X86_64
-	help
-	  Enable gigabyte pages support (if the CPU supports it). This can
-	  improve the kernel's performance a tiny bit by reducing TLB
-	  pressure.
-
-	  This is experimental code.
-
-	  If in doubt, say "N".
-
 config DEBUG_RODATA_TEST
 	bool "Testcase for the DEBUG_RODATA feature"
 	depends on DEBUG_RODATA
+	default y
 	help
 	  This option enables a testcase for the DEBUG_RODATA
 	  feature as well as for the change_page_attr() infrastructure.
@@ -186,14 +175,10 @@ config IOMMU_LEAK
 	  Add a simple leak tracer to the IOMMU code. This is useful when you
 	  are debugging a buggy device driver that leaks IOMMU mappings.
 
-config MMIOTRACE_HOOKS
-	bool
-
 config MMIOTRACE
 	bool "Memory mapped IO tracing"
 	depends on DEBUG_KERNEL && PCI
 	select TRACING
-	select MMIOTRACE_HOOKS
 	help
 	  Mmiotrace traces Memory Mapped I/O access and is meant for
 	  debugging and reverse engineering. It is called from the ioremap
@@ -307,10 +292,10 @@ config OPTIMIZE_INLINING
 	  developers have marked 'inline'. Doing so takes away freedom from gcc to
 	  do what it thinks is best, which is desirable for the gcc 3.x series of
 	  compilers. The gcc 4.x series have a rewritten inlining algorithm and
-	  disabling this option will generate a smaller kernel there. Hopefully
-	  this algorithm is so good that allowing gcc4 to make the decision can
-	  become the default in the future, until then this option is there to
-	  test gcc for this.
+	  enabling this option will generate a smaller kernel there. Hopefully
+	  this algorithm is so good that allowing gcc 4.x and above to make the
+	  decision will become the default in the future. Until then this option
+	  is there to test gcc for this.
 
 	  If unsure, say N.
 
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index d1a47adb5aec..cacee981d166 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -73,7 +73,7 @@ else
 
         stackp := $(CONFIG_SHELL) $(srctree)/scripts/gcc-x86_64-has-stack-protector.sh
         stackp-$(CONFIG_CC_STACKPROTECTOR) := $(shell $(stackp) \
-                "$(CC)" -fstack-protector )
+                "$(CC)" "-fstack-protector -DGCC_HAS_SP" )
         stackp-$(CONFIG_CC_STACKPROTECTOR_ALL) += $(shell $(stackp) \
                 "$(CC)" -fstack-protector-all )
 
diff --git a/arch/x86/boot/video-vga.c b/arch/x86/boot/video-vga.c
index b939cb476dec..5d4742ed4aa2 100644
--- a/arch/x86/boot/video-vga.c
+++ b/arch/x86/boot/video-vga.c
@@ -34,7 +34,7 @@ static struct mode_info cga_modes[] = {
 	{ VIDEO_80x25,  80, 25, 0 },
 };
 
-__videocard video_vga;
+static __videocard video_vga;
 
 /* Set basic 80x25 mode */
 static u8 vga_set_basic_mode(void)
@@ -259,7 +259,7 @@ static int vga_probe(void)
 	return mode_count[adapter];
 }
 
-__videocard video_vga = {
+static __videocard video_vga = {
 	.card_name	= "VGA",
 	.probe		= vga_probe,
 	.set_mode	= vga_set_mode,
diff --git a/arch/x86/boot/video.c b/arch/x86/boot/video.c
index 83598b23093a..3bef2c1febe9 100644
--- a/arch/x86/boot/video.c
+++ b/arch/x86/boot/video.c
@@ -226,7 +226,7 @@ static unsigned int mode_menu(void)
 
 #ifdef CONFIG_VIDEO_RETAIN
 /* Save screen content to the heap */
-struct saved_screen {
+static struct saved_screen {
 	int x, y;
 	int curx, cury;
 	u16 *data;
diff --git a/arch/x86/configs/i386_defconfig b/arch/x86/configs/i386_defconfig
index 13b8c86ae985..71fc39c70782 100644
--- a/arch/x86/configs/i386_defconfig
+++ b/arch/x86/configs/i386_defconfig
@@ -77,7 +77,7 @@ CONFIG_AUDIT=y
 CONFIG_AUDITSYSCALL=y
 CONFIG_AUDIT_TREE=y
 # CONFIG_IKCONFIG is not set
-CONFIG_LOG_BUF_SHIFT=17
+CONFIG_LOG_BUF_SHIFT=18
 CONFIG_CGROUPS=y
 # CONFIG_CGROUP_DEBUG is not set
 CONFIG_CGROUP_NS=y
diff --git a/arch/x86/configs/x86_64_defconfig b/arch/x86/configs/x86_64_defconfig
index f0a03d7a7d63..b38bbabc1706 100644
--- a/arch/x86/configs/x86_64_defconfig
+++ b/arch/x86/configs/x86_64_defconfig
@@ -77,7 +77,7 @@ CONFIG_AUDIT=y
 CONFIG_AUDITSYSCALL=y
 CONFIG_AUDIT_TREE=y
 # CONFIG_IKCONFIG is not set
-CONFIG_LOG_BUF_SHIFT=17
+CONFIG_LOG_BUF_SHIFT=18
 CONFIG_CGROUPS=y
 # CONFIG_CGROUP_DEBUG is not set
 CONFIG_CGROUP_NS=y
diff --git a/arch/x86/ia32/ia32_signal.c b/arch/x86/ia32/ia32_signal.c
index 4bc02b23674b..9ddf2fa0129d 100644
--- a/arch/x86/ia32/ia32_signal.c
+++ b/arch/x86/ia32/ia32_signal.c
@@ -197,23 +197,28 @@ struct rt_sigframe
 	/* fp state follows here */
 };
 
-#define COPY(x)		{ 		\
-	unsigned int reg;		\
-	err |= __get_user(reg, &sc->x);	\
-	regs->x = reg;			\
+#define COPY(x)			{		\
+	err |= __get_user(regs->x, &sc->x);	\
 }
 
-#define RELOAD_SEG(seg,mask)						\
-	{ unsigned int cur;						\
-	  unsigned short pre;						\
-	  err |= __get_user(pre, &sc->seg);				\
-	  savesegment(seg, cur);					\
-	  pre |= mask;							\
-	  if (pre != cur) loadsegment(seg, pre); }
+#define COPY_SEG_CPL3(seg)	{			\
+		unsigned short tmp;			\
+		err |= __get_user(tmp, &sc->seg);	\
+		regs->seg = tmp | 3;			\
+}
+
+#define RELOAD_SEG(seg)		{		\
+	unsigned int cur, pre;			\
+	err |= __get_user(pre, &sc->seg);	\
+	savesegment(seg, cur);			\
+	pre |= 3;				\
+	if (pre != cur)				\
+		loadsegment(seg, pre);		\
+}
 
 static int ia32_restore_sigcontext(struct pt_regs *regs,
 				   struct sigcontext_ia32 __user *sc,
-				   unsigned int *peax)
+				   unsigned int *pax)
 {
 	unsigned int tmpflags, gs, oldgs, err = 0;
 	void __user *buf;
@@ -240,18 +245,16 @@ static int ia32_restore_sigcontext(struct pt_regs *regs,
 	if (gs != oldgs)
 		load_gs_index(gs);
 
-	RELOAD_SEG(fs, 3);
-	RELOAD_SEG(ds, 3);
-	RELOAD_SEG(es, 3);
+	RELOAD_SEG(fs);
+	RELOAD_SEG(ds);
+	RELOAD_SEG(es);
 
 	COPY(di); COPY(si); COPY(bp); COPY(sp); COPY(bx);
 	COPY(dx); COPY(cx); COPY(ip);
 	/* Don't touch extended registers */
 
-	err |= __get_user(regs->cs, &sc->cs);
-	regs->cs |= 3;
-	err |= __get_user(regs->ss, &sc->ss);
-	regs->ss |= 3;
+	COPY_SEG_CPL3(cs);
+	COPY_SEG_CPL3(ss);
 
 	err |= __get_user(tmpflags, &sc->flags);
 	regs->flags = (regs->flags & ~FIX_EFLAGS) | (tmpflags & FIX_EFLAGS);
@@ -262,9 +265,7 @@ static int ia32_restore_sigcontext(struct pt_regs *regs,
 	buf = compat_ptr(tmp);
 	err |= restore_i387_xstate_ia32(buf);
 
-	err |= __get_user(tmp, &sc->ax);
-	*peax = tmp;
-
+	err |= __get_user(*pax, &sc->ax);
 	return err;
 }
 
@@ -359,20 +360,15 @@ static int ia32_setup_sigcontext(struct sigcontext_ia32 __user *sc,
 	err |= __put_user(regs->dx, &sc->dx);
 	err |= __put_user(regs->cx, &sc->cx);
 	err |= __put_user(regs->ax, &sc->ax);
-	err |= __put_user(regs->cs, &sc->cs);
-	err |= __put_user(regs->ss, &sc->ss);
 	err |= __put_user(current->thread.trap_no, &sc->trapno);
 	err |= __put_user(current->thread.error_code, &sc->err);
 	err |= __put_user(regs->ip, &sc->ip);
+	err |= __put_user(regs->cs, (unsigned int __user *)&sc->cs);
 	err |= __put_user(regs->flags, &sc->flags);
 	err |= __put_user(regs->sp, &sc->sp_at_signal);
+	err |= __put_user(regs->ss, (unsigned int __user *)&sc->ss);
 
-	tmp = save_i387_xstate_ia32(fpstate);
-	if (tmp < 0)
-		err = -EFAULT;
-	else
-		err |= __put_user(ptr_to_compat(tmp ? fpstate : NULL),
-					&sc->fpstate);
+	err |= __put_user(ptr_to_compat(fpstate), &sc->fpstate);
 
 	/* non-iBCS2 extensions.. */
 	err |= __put_user(mask, &sc->oldmask);
@@ -408,6 +404,8 @@ static void __user *get_sigframe(struct k_sigaction *ka, struct pt_regs *regs,
 	if (used_math()) {
 		sp = sp - sig_xstate_ia32_size;
 		*fpstate = (struct _fpstate_ia32 *) sp;
+		if (save_i387_xstate_ia32(*fpstate) < 0)
+			return (void __user *) -1L;
 	}
 
 	sp -= frame_size;
@@ -430,12 +428,10 @@ int ia32_setup_frame(int sig, struct k_sigaction *ka,
 		u16 poplmovl;
 		u32 val;
 		u16 int80;
-		u16 pad;
 	} __attribute__((packed)) code = {
 		0xb858,		 /* popl %eax ; movl $...,%eax */
 		__NR_ia32_sigreturn,
 		0x80cd,		/* int $0x80 */
-		0,
 	};
 
 	frame = get_sigframe(ka, regs, sizeof(*frame), &fpstate);
@@ -511,8 +507,7 @@ int ia32_setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
 		u8 movl;
 		u32 val;
 		u16 int80;
-		u16 pad;
-		u8  pad2;
+		u8  pad;
 	} __attribute__((packed)) code = {
 		0xb8,
 		__NR_ia32_rt_sigreturn,
@@ -572,11 +567,6 @@ int ia32_setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
 	regs->dx = (unsigned long) &frame->info;
 	regs->cx = (unsigned long) &frame->uc;
 
-	/* Make -mregparm=3 work */
-	regs->ax = sig;
-	regs->dx = (unsigned long) &frame->info;
-	regs->cx = (unsigned long) &frame->uc;
-
 	loadsegment(ds, __USER32_DS);
 	loadsegment(es, __USER32_DS);
 
diff --git a/arch/x86/include/asm/amd_iommu_types.h b/arch/x86/include/asm/amd_iommu_types.h
index 1a30c0440c6b..ac302a2fa339 100644
--- a/arch/x86/include/asm/amd_iommu_types.h
+++ b/arch/x86/include/asm/amd_iommu_types.h
@@ -251,13 +251,6 @@ struct amd_iommu {
 	/* Pointer to PCI device of this IOMMU */
 	struct pci_dev *dev;
 
-	/*
-	 * Capability pointer. There could be more than one IOMMU per PCI
-	 * device function if there are more than one AMD IOMMU capability
-	 * pointers.
-	 */
-	u16 cap_ptr;
-
 	/* physical address of MMIO space */
 	u64 mmio_phys;
 	/* virtual address of MMIO space */
@@ -266,6 +259,13 @@ struct amd_iommu {
 	/* capabilities of that IOMMU read from ACPI */
 	u32 cap;
 
+	/*
+	 * Capability pointer. There could be more than one IOMMU per PCI
+	 * device function if there are more than one AMD IOMMU capability
+	 * pointers.
+	 */
+	u16 cap_ptr;
+
 	/* pci domain of this IOMMU */
 	u16 pci_seg;
 
@@ -284,19 +284,19 @@ struct amd_iommu {
 	/* size of command buffer */
 	u32 cmd_buf_size;
 
-	/* event buffer virtual address */
-	u8 *evt_buf;
 	/* size of event buffer */
 	u32 evt_buf_size;
+	/* event buffer virtual address */
+	u8 *evt_buf;
 	/* MSI number for event interrupt */
 	u16 evt_msi_num;
 
-	/* if one, we need to send a completion wait command */
-	int need_sync;
-
 	/* true if interrupts for this IOMMU are already enabled */
 	bool int_enabled;
 
+	/* if one, we need to send a completion wait command */
+	int need_sync;
+
 	/* default dma_ops domain for that IOMMU */
 	struct dma_ops_domain *default_dom;
 };
diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index 3b1510b4fc57..25caa0738af5 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -193,6 +193,7 @@ extern u8 setup_APIC_eilvt_ibs(u8 vector, u8 msg_type, u8 mask);
 static inline void lapic_shutdown(void) { }
 #define local_apic_timer_c2_ok		1
 static inline void init_apic_mappings(void) { }
+static inline void disable_local_APIC(void) { }
 
 #endif /* !CONFIG_X86_LOCAL_APIC */
 
diff --git a/arch/x86/include/asm/bigsmp/apic.h b/arch/x86/include/asm/bigsmp/apic.h
index 1d9543b9d358..ce547f24a1cd 100644
--- a/arch/x86/include/asm/bigsmp/apic.h
+++ b/arch/x86/include/asm/bigsmp/apic.h
@@ -24,8 +24,6 @@ static inline cpumask_t target_cpus(void)
 #define INT_DELIVERY_MODE	(dest_Fixed)
 #define INT_DEST_MODE		(0)    /* phys delivery to target proc */
 #define NO_BALANCE_IRQ		(0)
-#define WAKE_SECONDARY_VIA_INIT
-
 
 static inline unsigned long check_apicid_used(physid_mask_t bitmap, int apicid)
 {
diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h
index 360010322711..9fa9dcdf344b 100644
--- a/arch/x86/include/asm/bitops.h
+++ b/arch/x86/include/asm/bitops.h
@@ -168,7 +168,15 @@ static inline void __change_bit(int nr, volatile unsigned long *addr)
  */
 static inline void change_bit(int nr, volatile unsigned long *addr)
 {
-	asm volatile(LOCK_PREFIX "btc %1,%0" : ADDR : "Ir" (nr));
+	if (IS_IMMEDIATE(nr)) {
+		asm volatile(LOCK_PREFIX "xorb %1,%0"
+			: CONST_MASK_ADDR(nr, addr)
+			: "iq" ((u8)CONST_MASK(nr)));
+	} else {
+		asm volatile(LOCK_PREFIX "btc %1,%0"
+			: BITOP_ADDR(addr)
+			: "Ir" (nr));
+	}
 }
 
 /**
diff --git a/arch/x86/include/asm/byteorder.h b/arch/x86/include/asm/byteorder.h
index e02ae2d89acf..f110ad417df3 100644
--- a/arch/x86/include/asm/byteorder.h
+++ b/arch/x86/include/asm/byteorder.h
@@ -4,26 +4,33 @@
 #include <asm/types.h>
 #include <linux/compiler.h>
 
-#ifdef __GNUC__
+#define __LITTLE_ENDIAN
 
-#ifdef __i386__
-
-static inline __attribute_const__ __u32 ___arch__swab32(__u32 x)
+static inline __attribute_const__ __u32 __arch_swab32(__u32 val)
 {
-#ifdef CONFIG_X86_BSWAP
-	asm("bswap %0" : "=r" (x) : "0" (x));
-#else
+#ifdef __i386__
+# ifdef CONFIG_X86_BSWAP
+	asm("bswap %0" : "=r" (val) : "0" (val));
+# else
 	asm("xchgb %b0,%h0\n\t"	/* swap lower bytes	*/
 	    "rorl $16,%0\n\t"	/* swap words		*/
 	    "xchgb %b0,%h0"	/* swap higher bytes	*/
-	    : "=q" (x)
-	    : "0" (x));
+	    : "=q" (val)
+	    : "0" (val));
+# endif
+
+#else /* __i386__ */
+	asm("bswapl %0"
+	    : "=r" (val)
+	    : "0" (val));
 #endif
-	return x;
+	return val;
 }
+#define __arch_swab32 __arch_swab32
 
-static inline __attribute_const__ __u64 ___arch__swab64(__u64 val)
+static inline __attribute_const__ __u64 __arch_swab64(__u64 val)
 {
+#ifdef __i386__
 	union {
 		struct {
 			__u32 a;
@@ -32,50 +39,27 @@ static inline __attribute_const__ __u64 ___arch__swab64(__u64 val)
 		__u64 u;
 	} v;
 	v.u = val;
-#ifdef CONFIG_X86_BSWAP
+# ifdef CONFIG_X86_BSWAP
 	asm("bswapl %0 ; bswapl %1 ; xchgl %0,%1"
 	    : "=r" (v.s.a), "=r" (v.s.b)
 	    : "0" (v.s.a), "1" (v.s.b));
-#else
-	v.s.a = ___arch__swab32(v.s.a);
-	v.s.b = ___arch__swab32(v.s.b);
+# else
+	v.s.a = __arch_swab32(v.s.a);
+	v.s.b = __arch_swab32(v.s.b);
 	asm("xchgl %0,%1"
 	    : "=r" (v.s.a), "=r" (v.s.b)
 	    : "0" (v.s.a), "1" (v.s.b));
-#endif
+# endif
 	return v.u;
-}
-
 #else /* __i386__ */
-
-static inline __attribute_const__ __u64 ___arch__swab64(__u64 x)
-{
 	asm("bswapq %0"
-	    : "=r" (x)
-	    : "0" (x));
-	return x;
-}
-
-static inline __attribute_const__ __u32 ___arch__swab32(__u32 x)
-{
-	asm("bswapl %0"
-	    : "=r" (x)
-	    : "0" (x));
-	return x;
-}
-
+	    : "=r" (val)
+	    : "0" (val));
+	return val;
 #endif
+}
+#define __arch_swab64 __arch_swab64
 
-/* Do not define swab16.  Gcc is smart enough to recognize "C" version and
-   convert it into rotation or exhange.  */
-
-#define __arch__swab64(x) ___arch__swab64(x)
-#define __arch__swab32(x) ___arch__swab32(x)
-
-#define __BYTEORDER_HAS_U64__
-
-#endif /* __GNUC__ */
-
-#include <linux/byteorder/little_endian.h>
+#include <linux/byteorder.h>
 
 #endif /* _ASM_X86_BYTEORDER_H */
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index cfdf8c2c5c31..5bce8ed02b44 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -80,7 +80,6 @@
 #define X86_FEATURE_UP		(3*32+ 9) /* smp kernel running on up */
 #define X86_FEATURE_FXSAVE_LEAK (3*32+10) /* "" FXSAVE leaks FOP/FIP/FOP */
 #define X86_FEATURE_ARCH_PERFMON (3*32+11) /* Intel Architectural PerfMon */
-#define X86_FEATURE_NOPL	(3*32+20) /* The NOPL (0F 1F) instructions */
 #define X86_FEATURE_PEBS	(3*32+12) /* Precise-Event Based Sampling */
 #define X86_FEATURE_BTS		(3*32+13) /* Branch Trace Store */
 #define X86_FEATURE_SYSCALL32	(3*32+14) /* "" syscall in ia32 userspace */
@@ -92,6 +91,7 @@
 #define X86_FEATURE_NOPL	(3*32+20) /* The NOPL (0F 1F) instructions */
 #define X86_FEATURE_AMDC1E	(3*32+21) /* AMD C1E detected */
 #define X86_FEATURE_XTOPOLOGY	(3*32+22) /* cpu topology enum extensions */
+#define X86_FEATURE_TSC_RELIABLE (3*32+23) /* TSC is known to be reliable */
 
 /* Intel-defined CPU features, CPUID level 0x00000001 (ecx), word 4 */
 #define X86_FEATURE_XMM3	(4*32+ 0) /* "pni" SSE-3 */
@@ -117,6 +117,7 @@
 #define X86_FEATURE_XSAVE	(4*32+26) /* XSAVE/XRSTOR/XSETBV/XGETBV */
 #define X86_FEATURE_OSXSAVE	(4*32+27) /* "" XSAVE enabled in the OS */
 #define X86_FEATURE_AVX		(4*32+28) /* Advanced Vector Extensions */
+#define X86_FEATURE_HYPERVISOR	(4*32+31) /* Running on a hypervisor */
 
 /* VIA/Cyrix/Centaur-defined CPU features, CPUID level 0xC0000001, word 5 */
 #define X86_FEATURE_XSTORE	(5*32+ 2) /* "rng" RNG present (xstore) */
@@ -237,6 +238,7 @@ extern const char * const x86_power_flags[32];
 #define cpu_has_xmm4_2		boot_cpu_has(X86_FEATURE_XMM4_2)
 #define cpu_has_x2apic		boot_cpu_has(X86_FEATURE_X2APIC)
 #define cpu_has_xsave		boot_cpu_has(X86_FEATURE_XSAVE)
+#define cpu_has_hypervisor	boot_cpu_has(X86_FEATURE_HYPERVISOR)
 
 #if defined(CONFIG_X86_INVLPG) || defined(CONFIG_X86_64)
 # define cpu_has_invlpg		1
diff --git a/arch/x86/include/asm/dma-mapping.h b/arch/x86/include/asm/dma-mapping.h
index 7f225a4b2a26..dc22c0733282 100644
--- a/arch/x86/include/asm/dma-mapping.h
+++ b/arch/x86/include/asm/dma-mapping.h
@@ -71,15 +71,11 @@ static inline struct dma_mapping_ops *get_dma_ops(struct device *dev)
 /* Make sure we keep the same behaviour */
 static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
 {
-#ifdef CONFIG_X86_32
-	return 0;
-#else
 	struct dma_mapping_ops *ops = get_dma_ops(dev);
 	if (ops->mapping_error)
 		return ops->mapping_error(dev, dma_addr);
 
 	return (dma_addr == bad_dma_address);
-#endif
 }
 
 #define dma_alloc_noncoherent(d, s, h, f) dma_alloc_coherent(d, s, h, f)
diff --git a/arch/x86/include/asm/dwarf2.h b/arch/x86/include/asm/dwarf2.h
index 804b6e6be929..3afc5e87cfdd 100644
--- a/arch/x86/include/asm/dwarf2.h
+++ b/arch/x86/include/asm/dwarf2.h
@@ -6,56 +6,91 @@
 #endif
 
 /*
-   Macros for dwarf2 CFI unwind table entries.
-   See "as.info" for details on these pseudo ops. Unfortunately
-   they are only supported in very new binutils, so define them
-   away for older version.
+ * Macros for dwarf2 CFI unwind table entries.
+ * See "as.info" for details on these pseudo ops. Unfortunately
+ * they are only supported in very new binutils, so define them
+ * away for older version.
  */
 
 #ifdef CONFIG_AS_CFI
 
-#define CFI_STARTPROC .cfi_startproc
-#define CFI_ENDPROC .cfi_endproc
-#define CFI_DEF_CFA .cfi_def_cfa
-#define CFI_DEF_CFA_REGISTER .cfi_def_cfa_register
-#define CFI_DEF_CFA_OFFSET .cfi_def_cfa_offset
-#define CFI_ADJUST_CFA_OFFSET .cfi_adjust_cfa_offset
-#define CFI_OFFSET .cfi_offset
-#define CFI_REL_OFFSET .cfi_rel_offset
-#define CFI_REGISTER .cfi_register
-#define CFI_RESTORE .cfi_restore
-#define CFI_REMEMBER_STATE .cfi_remember_state
-#define CFI_RESTORE_STATE .cfi_restore_state
-#define CFI_UNDEFINED .cfi_undefined
+#define CFI_STARTPROC		.cfi_startproc
+#define CFI_ENDPROC		.cfi_endproc
+#define CFI_DEF_CFA		.cfi_def_cfa
+#define CFI_DEF_CFA_REGISTER	.cfi_def_cfa_register
+#define CFI_DEF_CFA_OFFSET	.cfi_def_cfa_offset
+#define CFI_ADJUST_CFA_OFFSET	.cfi_adjust_cfa_offset
+#define CFI_OFFSET		.cfi_offset
+#define CFI_REL_OFFSET		.cfi_rel_offset
+#define CFI_REGISTER		.cfi_register
+#define CFI_RESTORE		.cfi_restore
+#define CFI_REMEMBER_STATE	.cfi_remember_state
+#define CFI_RESTORE_STATE	.cfi_restore_state
+#define CFI_UNDEFINED		.cfi_undefined
 
 #ifdef CONFIG_AS_CFI_SIGNAL_FRAME
-#define CFI_SIGNAL_FRAME .cfi_signal_frame
+#define CFI_SIGNAL_FRAME	.cfi_signal_frame
 #else
 #define CFI_SIGNAL_FRAME
 #endif
 
 #else
 
-/* Due to the structure of pre-exisiting code, don't use assembler line
-   comment character # to ignore the arguments. Instead, use a dummy macro. */
+/*
+ * Due to the structure of pre-exisiting code, don't use assembler line
+ * comment character # to ignore the arguments. Instead, use a dummy macro.
+ */
 .macro cfi_ignore a=0, b=0, c=0, d=0
 .endm
 
-#define CFI_STARTPROC	cfi_ignore
-#define CFI_ENDPROC	cfi_ignore
-#define CFI_DEF_CFA	cfi_ignore
+#define CFI_STARTPROC		cfi_ignore
+#define CFI_ENDPROC		cfi_ignore
+#define CFI_DEF_CFA		cfi_ignore
 #define CFI_DEF_CFA_REGISTER	cfi_ignore
 #define CFI_DEF_CFA_OFFSET	cfi_ignore
 #define CFI_ADJUST_CFA_OFFSET	cfi_ignore
-#define CFI_OFFSET	cfi_ignore
-#define CFI_REL_OFFSET	cfi_ignore
-#define CFI_REGISTER	cfi_ignore
-#define CFI_RESTORE	cfi_ignore
-#define CFI_REMEMBER_STATE cfi_ignore
-#define CFI_RESTORE_STATE cfi_ignore
-#define CFI_UNDEFINED cfi_ignore
-#define CFI_SIGNAL_FRAME cfi_ignore
+#define CFI_OFFSET		cfi_ignore
+#define CFI_REL_OFFSET		cfi_ignore
+#define CFI_REGISTER		cfi_ignore
+#define CFI_RESTORE		cfi_ignore
+#define CFI_REMEMBER_STATE	cfi_ignore
+#define CFI_RESTORE_STATE	cfi_ignore
+#define CFI_UNDEFINED		cfi_ignore
+#define CFI_SIGNAL_FRAME	cfi_ignore
 
 #endif
 
+/*
+ * An attempt to make CFI annotations more or less
+ * correct and shorter. It is implied that you know
+ * what you're doing if you use them.
+ */
+#ifdef __ASSEMBLY__
+#ifdef CONFIG_X86_64
+	.macro pushq_cfi reg
+	pushq \reg
+	CFI_ADJUST_CFA_OFFSET 8
+	.endm
+
+	.macro popq_cfi reg
+	popq \reg
+	CFI_ADJUST_CFA_OFFSET -8
+	.endm
+
+	.macro movq_cfi reg offset=0
+	movq %\reg, \offset(%rsp)
+	CFI_REL_OFFSET \reg, \offset
+	.endm
+
+	.macro movq_cfi_restore offset reg
+	movq \offset(%rsp), %\reg
+	CFI_RESTORE \reg
+	.endm
+#else /*!CONFIG_X86_64*/
+
+	/* 32bit defenitions are missed yet */
+
+#endif /*!CONFIG_X86_64*/
+#endif /*__ASSEMBLY__*/
+
 #endif /* _ASM_X86_DWARF2_H */
diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h
index 40ca1bea7916..f51a3ddde01a 100644
--- a/arch/x86/include/asm/elf.h
+++ b/arch/x86/include/asm/elf.h
@@ -325,7 +325,7 @@ struct linux_binprm;
 
 #define ARCH_HAS_SETUP_ADDITIONAL_PAGES 1
 extern int arch_setup_additional_pages(struct linux_binprm *bprm,
-				       int executable_stack);
+				       int uses_interp);
 
 extern int syscall32_setup_pages(struct linux_binprm *, int exstack);
 #define compat_arch_setup_additional_pages	syscall32_setup_pages
diff --git a/arch/x86/include/asm/emergency-restart.h b/arch/x86/include/asm/emergency-restart.h
index 94826cf87455..cc70c1c78ca4 100644
--- a/arch/x86/include/asm/emergency-restart.h
+++ b/arch/x86/include/asm/emergency-restart.h
@@ -8,7 +8,9 @@ enum reboot_type {
 	BOOT_BIOS = 'b',
 #endif
 	BOOT_ACPI = 'a',
-	BOOT_EFI = 'e'
+	BOOT_EFI = 'e',
+	BOOT_CF9 = 'p',
+	BOOT_CF9_COND = 'q',
 };
 
 extern enum reboot_type reboot_type;
diff --git a/arch/x86/include/asm/es7000/apic.h b/arch/x86/include/asm/es7000/apic.h
index 380f0b4f17ed..e24ef876915f 100644
--- a/arch/x86/include/asm/es7000/apic.h
+++ b/arch/x86/include/asm/es7000/apic.h
@@ -9,31 +9,27 @@ static inline int apic_id_registered(void)
 	        return (1);
 }
 
-static inline cpumask_t target_cpus(void)
+static inline cpumask_t target_cpus_cluster(void)
 {
-#if defined CONFIG_ES7000_CLUSTERED_APIC
 	return CPU_MASK_ALL;
-#else
+}
+
+static inline cpumask_t target_cpus(void)
+{
 	return cpumask_of_cpu(smp_processor_id());
-#endif
 }
 
-#if defined CONFIG_ES7000_CLUSTERED_APIC
-#define APIC_DFR_VALUE		(APIC_DFR_CLUSTER)
-#define INT_DELIVERY_MODE	(dest_LowestPrio)
-#define INT_DEST_MODE		(1)    /* logical delivery broadcast to all procs */
-#define NO_BALANCE_IRQ		(1)
-#undef  WAKE_SECONDARY_VIA_INIT
-#define WAKE_SECONDARY_VIA_MIP
-#else
+#define APIC_DFR_VALUE_CLUSTER		(APIC_DFR_CLUSTER)
+#define INT_DELIVERY_MODE_CLUSTER	(dest_LowestPrio)
+#define INT_DEST_MODE_CLUSTER		(1) /* logical delivery broadcast to all procs */
+#define NO_BALANCE_IRQ_CLUSTER		(1)
+
 #define APIC_DFR_VALUE		(APIC_DFR_FLAT)
 #define INT_DELIVERY_MODE	(dest_Fixed)
 #define INT_DEST_MODE		(0)    /* phys delivery to target procs */
 #define NO_BALANCE_IRQ		(0)
 #undef  APIC_DEST_LOGICAL
 #define APIC_DEST_LOGICAL	0x0
-#define WAKE_SECONDARY_VIA_INIT
-#endif
 
 static inline unsigned long check_apicid_used(physid_mask_t bitmap, int apicid)
 {
@@ -60,6 +56,16 @@ static inline unsigned long calculate_ldr(int cpu)
  * an APIC.  See e.g. "AP-388 82489DX User's Manual" (Intel
  * document number 292116).  So here it goes...
  */
+static inline void init_apic_ldr_cluster(void)
+{
+	unsigned long val;
+	int cpu = smp_processor_id();
+
+	apic_write(APIC_DFR, APIC_DFR_VALUE_CLUSTER);
+	val = calculate_ldr(cpu);
+	apic_write(APIC_LDR, val);
+}
+
 static inline void init_apic_ldr(void)
 {
 	unsigned long val;
@@ -70,10 +76,6 @@ static inline void init_apic_ldr(void)
 	apic_write(APIC_LDR, val);
 }
 
-#ifndef CONFIG_X86_GENERICARCH
-extern void enable_apic_mode(void);
-#endif
-
 extern int apic_version [MAX_APICS];
 static inline void setup_apic_routing(void)
 {
@@ -144,7 +146,7 @@ static inline int check_phys_apicid_present(int cpu_physical_apicid)
 	return (1);
 }
 
-static inline unsigned int cpu_mask_to_apicid(cpumask_t cpumask)
+static inline unsigned int cpu_mask_to_apicid_cluster(cpumask_t cpumask)
 {
 	int num_bits_set;
 	int cpus_found = 0;
@@ -154,11 +156,7 @@ static inline unsigned int cpu_mask_to_apicid(cpumask_t cpumask)
 	num_bits_set = cpus_weight(cpumask);
 	/* Return id to all */
 	if (num_bits_set == NR_CPUS)
-#if defined CONFIG_ES7000_CLUSTERED_APIC
 		return 0xFF;
-#else
-		return cpu_to_logical_apicid(0);
-#endif
 	/*
 	 * The cpus in the mask must all be on the apic cluster.  If are not
 	 * on the same apicid cluster return default value of TARGET_CPUS.
@@ -171,11 +169,40 @@ static inline unsigned int cpu_mask_to_apicid(cpumask_t cpumask)
 			if (apicid_cluster(apicid) !=
 					apicid_cluster(new_apicid)){
 				printk ("%s: Not a valid mask!\n", __func__);
-#if defined CONFIG_ES7000_CLUSTERED_APIC
 				return 0xFF;
-#else
+			}
+			apicid = new_apicid;
+			cpus_found++;
+		}
+		cpu++;
+	}
+	return apicid;
+}
+
+static inline unsigned int cpu_mask_to_apicid(cpumask_t cpumask)
+{
+	int num_bits_set;
+	int cpus_found = 0;
+	int cpu;
+	int apicid;
+
+	num_bits_set = cpus_weight(cpumask);
+	/* Return id to all */
+	if (num_bits_set == NR_CPUS)
+		return cpu_to_logical_apicid(0);
+	/*
+	 * The cpus in the mask must all be on the apic cluster.  If are not
+	 * on the same apicid cluster return default value of TARGET_CPUS.
+	 */
+	cpu = first_cpu(cpumask);
+	apicid = cpu_to_logical_apicid(cpu);
+	while (cpus_found < num_bits_set) {
+		if (cpu_isset(cpu, cpumask)) {
+			int new_apicid = cpu_to_logical_apicid(cpu);
+			if (apicid_cluster(apicid) !=
+					apicid_cluster(new_apicid)){
+				printk ("%s: Not a valid mask!\n", __func__);
 				return cpu_to_logical_apicid(0);
-#endif
 			}
 			apicid = new_apicid;
 			cpus_found++;
diff --git a/arch/x86/include/asm/es7000/wakecpu.h b/arch/x86/include/asm/es7000/wakecpu.h
index 398493461913..78f0daaee436 100644
--- a/arch/x86/include/asm/es7000/wakecpu.h
+++ b/arch/x86/include/asm/es7000/wakecpu.h
@@ -1,36 +1,12 @@
 #ifndef __ASM_ES7000_WAKECPU_H
 #define __ASM_ES7000_WAKECPU_H
 
-/*
- * This file copes with machines that wakeup secondary CPUs by the
- * INIT, INIT, STARTUP sequence.
- */
-
-#ifdef CONFIG_ES7000_CLUSTERED_APIC
-#define WAKE_SECONDARY_VIA_MIP
-#else
-#define WAKE_SECONDARY_VIA_INIT
-#endif
-
-#ifdef WAKE_SECONDARY_VIA_MIP
-extern int es7000_start_cpu(int cpu, unsigned long eip);
-static inline int
-wakeup_secondary_cpu(int phys_apicid, unsigned long start_eip)
-{
-	int boot_error = 0;
-	boot_error = es7000_start_cpu(phys_apicid, start_eip);
-	return boot_error;
-}
-#endif
-
-#define TRAMPOLINE_LOW phys_to_virt(0x467)
-#define TRAMPOLINE_HIGH phys_to_virt(0x469)
-
-#define boot_cpu_apicid boot_cpu_physical_apicid
+#define TRAMPOLINE_PHYS_LOW	0x467
+#define TRAMPOLINE_PHYS_HIGH	0x469
 
 static inline void wait_for_init_deassert(atomic_t *deassert)
 {
-#ifdef WAKE_SECONDARY_VIA_INIT
+#ifndef CONFIG_ES7000_CLUSTERED_APIC
 	while (!atomic_read(deassert))
 		cpu_relax();
 #endif
@@ -50,9 +26,12 @@ static inline void restore_NMI_vector(unsigned short *high, unsigned short *low)
 {
 }
 
-#define inquire_remote_apic(apicid) do {		\
-		if (apic_verbosity >= APIC_DEBUG)	\
-			__inquire_remote_apic(apicid);	\
-	} while (0)
+extern void __inquire_remote_apic(int apicid);
+
+static inline void inquire_remote_apic(int apicid)
+{
+	if (apic_verbosity >= APIC_DEBUG)
+		__inquire_remote_apic(apicid);
+}
 
 #endif /* __ASM_MACH_WAKECPU_H */
diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h
index 9e8bc29b8b17..754a3e082f94 100644
--- a/arch/x86/include/asm/ftrace.h
+++ b/arch/x86/include/asm/ftrace.h
@@ -17,8 +17,40 @@ static inline unsigned long ftrace_call_adjust(unsigned long addr)
 	 */
 	return addr - 1;
 }
-#endif
 
+#ifdef CONFIG_DYNAMIC_FTRACE
+
+struct dyn_arch_ftrace {
+	/* No extra data needed for x86 */
+};
+
+#endif /*  CONFIG_DYNAMIC_FTRACE */
+#endif /* __ASSEMBLY__ */
 #endif /* CONFIG_FUNCTION_TRACER */
 
+#ifdef CONFIG_FUNCTION_RET_TRACER
+
+#ifndef __ASSEMBLY__
+
+/*
+ * Stack of return addresses for functions
+ * of a thread.
+ * Used in struct thread_info
+ */
+struct ftrace_ret_stack {
+	unsigned long ret;
+	unsigned long func;
+	unsigned long long calltime;
+};
+
+/*
+ * Primary handler of a function return.
+ * It relays on ftrace_return_to_handler.
+ * Defined in entry32.S
+ */
+extern void return_to_handler(void);
+
+#endif /* __ASSEMBLY__ */
+#endif /* CONFIG_FUNCTION_RET_TRACER */
+
 #endif /* _ASM_X86_FTRACE_H */
diff --git a/arch/x86/include/asm/gart.h b/arch/x86/include/asm/gart.h
index 74252264433d..6cfdafa409d8 100644
--- a/arch/x86/include/asm/gart.h
+++ b/arch/x86/include/asm/gart.h
@@ -29,6 +29,39 @@ extern int fix_aperture;
 #define AMD64_GARTCACHECTL	0x9c
 #define AMD64_GARTEN		(1<<0)
 
+#ifdef CONFIG_GART_IOMMU
+extern int gart_iommu_aperture;
+extern int gart_iommu_aperture_allowed;
+extern int gart_iommu_aperture_disabled;
+
+extern void early_gart_iommu_check(void);
+extern void gart_iommu_init(void);
+extern void gart_iommu_shutdown(void);
+extern void __init gart_parse_options(char *);
+extern void gart_iommu_hole_init(void);
+
+#else
+#define gart_iommu_aperture            0
+#define gart_iommu_aperture_allowed    0
+#define gart_iommu_aperture_disabled   1
+
+static inline void early_gart_iommu_check(void)
+{
+}
+static inline void gart_iommu_init(void)
+{
+}
+static inline void gart_iommu_shutdown(void)
+{
+}
+static inline void gart_parse_options(char *options)
+{
+}
+static inline void gart_iommu_hole_init(void)
+{
+}
+#endif
+
 extern int agp_amd64_init(void);
 
 static inline void enable_gart_translation(struct pci_dev *dev, u64 addr)
diff --git a/arch/x86/include/asm/genapic_32.h b/arch/x86/include/asm/genapic_32.h
index 5cbd4fcc06fd..0ac17d33a8c7 100644
--- a/arch/x86/include/asm/genapic_32.h
+++ b/arch/x86/include/asm/genapic_32.h
@@ -2,6 +2,7 @@
 #define _ASM_X86_GENAPIC_32_H
 
 #include <asm/mpspec.h>
+#include <asm/atomic.h>
 
 /*
  * Generic APIC driver interface.
@@ -65,6 +66,14 @@ struct genapic {
 	void (*send_IPI_allbutself)(int vector);
 	void (*send_IPI_all)(int vector);
 #endif
+	int (*wakeup_cpu)(int apicid, unsigned long start_eip);
+	int trampoline_phys_low;
+	int trampoline_phys_high;
+	void (*wait_for_init_deassert)(atomic_t *deassert);
+	void (*smp_callin_clear_local_apic)(void);
+	void (*store_NMI_vector)(unsigned short *high, unsigned short *low);
+	void (*restore_NMI_vector)(unsigned short *high, unsigned short *low);
+	void (*inquire_remote_apic)(int apicid);
 };
 
 #define APICFUNC(x) .x = x,
@@ -105,16 +114,24 @@ struct genapic {
 	APICFUNC(get_apic_id)				\
 	.apic_id_mask = APIC_ID_MASK,			\
 	APICFUNC(cpu_mask_to_apicid)			\
-	APICFUNC(vector_allocation_domain)			\
+	APICFUNC(vector_allocation_domain)		\
 	APICFUNC(acpi_madt_oem_check)			\
 	IPIFUNC(send_IPI_mask)				\
 	IPIFUNC(send_IPI_allbutself)			\
 	IPIFUNC(send_IPI_all)				\
 	APICFUNC(enable_apic_mode)			\
 	APICFUNC(phys_pkg_id)				\
+	.trampoline_phys_low = TRAMPOLINE_PHYS_LOW,		\
+	.trampoline_phys_high = TRAMPOLINE_PHYS_HIGH,		\
+	APICFUNC(wait_for_init_deassert)		\
+	APICFUNC(smp_callin_clear_local_apic)		\
+	APICFUNC(store_NMI_vector)			\
+	APICFUNC(restore_NMI_vector)			\
+	APICFUNC(inquire_remote_apic)			\
 }
 
 extern struct genapic *genapic;
+extern void es7000_update_genapic_to_cluster(void);
 
 enum uv_system_type {UV_NONE, UV_LEGACY_APIC, UV_X2APIC, UV_NON_UNIQUE_APIC};
 #define get_uv_system_type()		UV_NONE
diff --git a/arch/x86/include/asm/genapic_64.h b/arch/x86/include/asm/genapic_64.h
index 13c4e96199ea..2cae011668b7 100644
--- a/arch/x86/include/asm/genapic_64.h
+++ b/arch/x86/include/asm/genapic_64.h
@@ -32,6 +32,8 @@ struct genapic {
 	unsigned int (*get_apic_id)(unsigned long x);
 	unsigned long (*set_apic_id)(unsigned int id);
 	unsigned long apic_id_mask;
+	/* wakeup_secondary_cpu */
+	int (*wakeup_cpu)(int apicid, unsigned long start_eip);
 };
 
 extern struct genapic *genapic;
diff --git a/arch/x86/include/asm/hw_irq.h b/arch/x86/include/asm/hw_irq.h
index b97aecb0b61d..8de644b6b959 100644
--- a/arch/x86/include/asm/hw_irq.h
+++ b/arch/x86/include/asm/hw_irq.h
@@ -109,9 +109,7 @@ extern asmlinkage void smp_invalidate_interrupt(struct pt_regs *);
 #endif
 #endif
 
-#ifdef CONFIG_X86_32
-extern void (*const interrupt[NR_VECTORS])(void);
-#endif
+extern void (*__initconst interrupt[NR_VECTORS-FIRST_EXTERNAL_VECTOR])(void);
 
 typedef int vector_irq_t[NR_VECTORS];
 DECLARE_PER_CPU(vector_irq_t, vector_irq);
diff --git a/arch/x86/include/asm/hypervisor.h b/arch/x86/include/asm/hypervisor.h
new file mode 100644
index 000000000000..369f5c5d09a1
--- /dev/null
+++ b/arch/x86/include/asm/hypervisor.h
@@ -0,0 +1,26 @@
+/*
+ * Copyright (C) 2008, VMware, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
+ * NON INFRINGEMENT.  See the GNU General Public License for more
+ * details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
+ *
+ */
+#ifndef ASM_X86__HYPERVISOR_H
+#define ASM_X86__HYPERVISOR_H
+
+extern unsigned long get_hypervisor_tsc_freq(void);
+extern void init_hypervisor(struct cpuinfo_x86 *c);
+
+#endif
diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h
index ac2abc88cd95..05cfed4485fa 100644
--- a/arch/x86/include/asm/io.h
+++ b/arch/x86/include/asm/io.h
@@ -4,6 +4,7 @@
 #define ARCH_HAS_IOREMAP_WC
 
 #include <linux/compiler.h>
+#include <asm-generic/int-ll64.h>
 
 #define build_mmio_read(name, size, type, reg, barrier) \
 static inline type name(const volatile void __iomem *addr) \
@@ -45,21 +46,39 @@ build_mmio_write(__writel, "l", unsigned int, "r", )
 #define mmiowb() barrier()
 
 #ifdef CONFIG_X86_64
+
 build_mmio_read(readq, "q", unsigned long, "=r", :"memory")
-build_mmio_read(__readq, "q", unsigned long, "=r", )
 build_mmio_write(writeq, "q", unsigned long, "r", :"memory")
-build_mmio_write(__writeq, "q", unsigned long, "r", )
 
-#define readq_relaxed(a) __readq(a)
-#define __raw_readq __readq
-#define __raw_writeq writeq
+#else
+
+static inline __u64 readq(const volatile void __iomem *addr)
+{
+	const volatile u32 __iomem *p = addr;
+	u32 low, high;
+
+	low = readl(p);
+	high = readl(p + 1);
+
+	return low + ((u64)high << 32);
+}
+
+static inline void writeq(__u64 val, volatile void __iomem *addr)
+{
+	writel(val, addr);
+	writel(val >> 32, addr+4);
+}
 
-/* Let people know we have them */
-#define readq readq
-#define writeq writeq
 #endif
 
-extern int iommu_bio_merge;
+#define readq_relaxed(a)	readq(a)
+
+#define __raw_readq(a)		readq(a)
+#define __raw_writeq(val, addr)	writeq(val, addr)
+
+/* Let people know that we have them */
+#define readq			readq
+#define writeq			writeq
 
 #ifdef CONFIG_X86_32
 # include "io_32.h"
diff --git a/arch/x86/include/asm/io_64.h b/arch/x86/include/asm/io_64.h
index fea325a1122f..563c16270ba6 100644
--- a/arch/x86/include/asm/io_64.h
+++ b/arch/x86/include/asm/io_64.h
@@ -232,8 +232,6 @@ void memset_io(volatile void __iomem *a, int b, size_t c);
 
 #define flush_write_buffers()
 
-#define BIO_VMERGE_BOUNDARY iommu_bio_merge
-
 /*
  * Convert a virtual cached pointer to an uncached pointer
  */
diff --git a/arch/x86/include/asm/io_apic.h b/arch/x86/include/asm/io_apic.h
index 6afd9933a7dd..e475e009ae5d 100644
--- a/arch/x86/include/asm/io_apic.h
+++ b/arch/x86/include/asm/io_apic.h
@@ -156,11 +156,21 @@ extern int sis_apic_bug;
 /* 1 if "noapic" boot option passed */
 extern int skip_ioapic_setup;
 
+/* 1 if "noapic" boot option passed */
+extern int noioapicquirk;
+
+/* -1 if "noapic" boot option passed */
+extern int noioapicreroute;
+
 /* 1 if the timer IRQ uses the '8259A Virtual Wire' mode */
 extern int timer_through_8259;
 
 static inline void disable_ioapic_setup(void)
 {
+#ifdef CONFIG_PCI
+	noioapicquirk = 1;
+	noioapicreroute = -1;
+#endif
 	skip_ioapic_setup = 1;
 }
 
diff --git a/arch/x86/include/asm/iommu.h b/arch/x86/include/asm/iommu.h
index 0b500c5b6446..295b13193f4d 100644
--- a/arch/x86/include/asm/iommu.h
+++ b/arch/x86/include/asm/iommu.h
@@ -12,37 +12,4 @@ extern unsigned long iommu_nr_pages(unsigned long addr, unsigned long len);
 /* 10 seconds */
 #define DMAR_OPERATION_TIMEOUT ((cycles_t) tsc_khz*10*1000)
 
-#ifdef CONFIG_GART_IOMMU
-extern int gart_iommu_aperture;
-extern int gart_iommu_aperture_allowed;
-extern int gart_iommu_aperture_disabled;
-
-extern void early_gart_iommu_check(void);
-extern void gart_iommu_init(void);
-extern void gart_iommu_shutdown(void);
-extern void __init gart_parse_options(char *);
-extern void gart_iommu_hole_init(void);
-
-#else
-#define gart_iommu_aperture            0
-#define gart_iommu_aperture_allowed    0
-#define gart_iommu_aperture_disabled   1
-
-static inline void early_gart_iommu_check(void)
-{
-}
-static inline void gart_iommu_init(void)
-{
-}
-static inline void gart_iommu_shutdown(void)
-{
-}
-static inline void gart_parse_options(char *options)
-{
-}
-static inline void gart_iommu_hole_init(void)
-{
-}
-#endif
-
 #endif /* _ASM_X86_IOMMU_H */
diff --git a/arch/x86/include/asm/irq.h b/arch/x86/include/asm/irq.h
index bae0eda95486..28e409fc73f3 100644
--- a/arch/x86/include/asm/irq.h
+++ b/arch/x86/include/asm/irq.h
@@ -31,10 +31,6 @@ static inline int irq_canonicalize(int irq)
 # endif
 #endif
 
-#ifdef CONFIG_IRQBALANCE
-extern int irqbalance_disable(char *str);
-#endif
-
 #ifdef CONFIG_HOTPLUG_CPU
 #include <linux/cpumask.h>
 extern void fixup_irqs(cpumask_t map);
diff --git a/arch/x86/include/asm/irq_regs_32.h b/arch/x86/include/asm/irq_regs_32.h
index af2f02d27fc7..86afd7473457 100644
--- a/arch/x86/include/asm/irq_regs_32.h
+++ b/arch/x86/include/asm/irq_regs_32.h
@@ -9,6 +9,8 @@
 
 #include <asm/percpu.h>
 
+#define ARCH_HAS_OWN_IRQ_REGS
+
 DECLARE_PER_CPU(struct pt_regs *, irq_regs);
 
 static inline struct pt_regs *get_irq_regs(void)
diff --git a/arch/x86/include/asm/kexec.h b/arch/x86/include/asm/kexec.h
index a1f22771a15a..c61d8b2ab8b9 100644
--- a/arch/x86/include/asm/kexec.h
+++ b/arch/x86/include/asm/kexec.h
@@ -5,21 +5,8 @@
 # define PA_CONTROL_PAGE	0
 # define VA_CONTROL_PAGE	1
 # define PA_PGD			2
-# define VA_PGD			3
-# define PA_PTE_0		4
-# define VA_PTE_0		5
-# define PA_PTE_1		6
-# define VA_PTE_1		7
-# define PA_SWAP_PAGE		8
-# ifdef CONFIG_X86_PAE
-#  define PA_PMD_0		9
-#  define VA_PMD_0		10
-#  define PA_PMD_1		11
-#  define VA_PMD_1		12
-#  define PAGES_NR		13
-# else
-#  define PAGES_NR		9
-# endif
+# define PA_SWAP_PAGE		3
+# define PAGES_NR		4
 #else
 # define PA_CONTROL_PAGE	0
 # define VA_CONTROL_PAGE	1
@@ -170,6 +157,20 @@ relocate_kernel(unsigned long indirection_page,
 		unsigned long start_address) ATTRIB_NORET;
 #endif
 
+#ifdef CONFIG_X86_32
+#define ARCH_HAS_KIMAGE_ARCH
+
+struct kimage_arch {
+	pgd_t *pgd;
+#ifdef CONFIG_X86_PAE
+	pmd_t *pmd0;
+	pmd_t *pmd1;
+#endif
+	pte_t *pte0;
+	pte_t *pte1;
+};
+#endif
+
 #endif /* __ASSEMBLY__ */
 
 #endif /* _ASM_X86_KEXEC_H */
diff --git a/arch/x86/include/asm/linkage.h b/arch/x86/include/asm/linkage.h
index f61ee8f937e4..5d98d0b68ffc 100644
--- a/arch/x86/include/asm/linkage.h
+++ b/arch/x86/include/asm/linkage.h
@@ -57,5 +57,65 @@
 #define __ALIGN_STR ".align 16,0x90"
 #endif
 
+/*
+ * to check ENTRY_X86/END_X86 and
+ * KPROBE_ENTRY_X86/KPROBE_END_X86
+ * unbalanced-missed-mixed appearance
+ */
+#define __set_entry_x86		.set ENTRY_X86_IN, 0
+#define __unset_entry_x86	.set ENTRY_X86_IN, 1
+#define __set_kprobe_x86	.set KPROBE_X86_IN, 0
+#define __unset_kprobe_x86	.set KPROBE_X86_IN, 1
+
+#define __macro_err_x86 .error "ENTRY_X86/KPROBE_X86 unbalanced,missed,mixed"
+
+#define __check_entry_x86	\
+	.ifdef ENTRY_X86_IN;	\
+	.ifeq ENTRY_X86_IN;	\
+	__macro_err_x86;	\
+	.abort;			\
+	.endif;			\
+	.endif
+
+#define __check_kprobe_x86	\
+	.ifdef KPROBE_X86_IN;	\
+	.ifeq KPROBE_X86_IN;	\
+	__macro_err_x86;	\
+	.abort;			\
+	.endif;			\
+	.endif
+
+#define __check_entry_kprobe_x86	\
+	__check_entry_x86;		\
+	__check_kprobe_x86
+
+#define ENTRY_KPROBE_FINAL_X86 __check_entry_kprobe_x86
+
+#define ENTRY_X86(name)			\
+	__check_entry_kprobe_x86;	\
+	__set_entry_x86;		\
+	.globl name;			\
+	__ALIGN;			\
+	name:
+
+#define END_X86(name)			\
+	__unset_entry_x86;		\
+	__check_entry_kprobe_x86;	\
+	.size name, .-name
+
+#define KPROBE_ENTRY_X86(name)		\
+	__check_entry_kprobe_x86;	\
+	__set_kprobe_x86;		\
+	.pushsection .kprobes.text, "ax"; \
+	.globl name;			\
+	__ALIGN;			\
+	name:
+
+#define KPROBE_END_X86(name)		\
+	__unset_kprobe_x86;		\
+	__check_entry_kprobe_x86;	\
+	.size name, .-name;		\
+	.popsection
+
 #endif /* _ASM_X86_LINKAGE_H */
 
diff --git a/arch/x86/include/asm/mach-default/mach_apic.h b/arch/x86/include/asm/mach-default/mach_apic.h
index ff3a6c236c00..6cb3a467e067 100644
--- a/arch/x86/include/asm/mach-default/mach_apic.h
+++ b/arch/x86/include/asm/mach-default/mach_apic.h
@@ -32,11 +32,13 @@ static inline cpumask_t target_cpus(void)
 #define vector_allocation_domain    (genapic->vector_allocation_domain)
 #define read_apic_id()  (GET_APIC_ID(apic_read(APIC_ID)))
 #define send_IPI_self (genapic->send_IPI_self)
+#define wakeup_secondary_cpu (genapic->wakeup_cpu)
 extern void setup_apic_routing(void);
 #else
 #define INT_DELIVERY_MODE dest_LowestPrio
 #define INT_DEST_MODE 1     /* logical delivery broadcast to all procs */
 #define TARGET_CPUS (target_cpus())
+#define wakeup_secondary_cpu wakeup_secondary_cpu_via_init
 /*
  * Set up the logical destination ID.
  *
diff --git a/arch/x86/include/asm/mach-default/mach_wakecpu.h b/arch/x86/include/asm/mach-default/mach_wakecpu.h
index 9d80db91e992..ceb013660146 100644
--- a/arch/x86/include/asm/mach-default/mach_wakecpu.h
+++ b/arch/x86/include/asm/mach-default/mach_wakecpu.h
@@ -1,17 +1,8 @@
 #ifndef _ASM_X86_MACH_DEFAULT_MACH_WAKECPU_H
 #define _ASM_X86_MACH_DEFAULT_MACH_WAKECPU_H
 
-/* 
- * This file copes with machines that wakeup secondary CPUs by the
- * INIT, INIT, STARTUP sequence.
- */
-
-#define WAKE_SECONDARY_VIA_INIT
-
-#define TRAMPOLINE_LOW phys_to_virt(0x467)
-#define TRAMPOLINE_HIGH phys_to_virt(0x469)
-
-#define boot_cpu_apicid boot_cpu_physical_apicid
+#define TRAMPOLINE_PHYS_LOW (0x467)
+#define TRAMPOLINE_PHYS_HIGH (0x469)
 
 static inline void wait_for_init_deassert(atomic_t *deassert)
 {
@@ -33,9 +24,12 @@ static inline void restore_NMI_vector(unsigned short *high, unsigned short *low)
 {
 }
 
-#define inquire_remote_apic(apicid) do {		\
-		if (apic_verbosity >= APIC_DEBUG)	\
-			__inquire_remote_apic(apicid);	\
-	} while (0)
+extern void __inquire_remote_apic(int apicid);
+
+static inline void inquire_remote_apic(int apicid)
+{
+	if (apic_verbosity >= APIC_DEBUG)
+		__inquire_remote_apic(apicid);
+}
 
 #endif /* _ASM_X86_MACH_DEFAULT_MACH_WAKECPU_H */
diff --git a/arch/x86/include/asm/mach-default/smpboot_hooks.h b/arch/x86/include/asm/mach-default/smpboot_hooks.h
index dbab36d64d48..23bf52103b89 100644
--- a/arch/x86/include/asm/mach-default/smpboot_hooks.h
+++ b/arch/x86/include/asm/mach-default/smpboot_hooks.h
@@ -13,9 +13,11 @@ static inline void smpboot_setup_warm_reset_vector(unsigned long start_eip)
 	CMOS_WRITE(0xa, 0xf);
 	local_flush_tlb();
 	pr_debug("1.\n");
-	*((volatile unsigned short *) TRAMPOLINE_HIGH) = start_eip >> 4;
+	*((volatile unsigned short *)phys_to_virt(TRAMPOLINE_PHYS_HIGH)) =
+								 start_eip >> 4;
 	pr_debug("2.\n");
-	*((volatile unsigned short *) TRAMPOLINE_LOW) = start_eip & 0xf;
+	*((volatile unsigned short *)phys_to_virt(TRAMPOLINE_PHYS_LOW)) =
+							 start_eip & 0xf;
 	pr_debug("3.\n");
 }
 
@@ -32,7 +34,7 @@ static inline void smpboot_restore_warm_reset_vector(void)
 	 */
 	CMOS_WRITE(0, 0xf);
 
-	*((volatile long *) phys_to_virt(0x467)) = 0;
+	*((volatile long *)phys_to_virt(TRAMPOLINE_PHYS_LOW)) = 0;
 }
 
 static inline void __init smpboot_setup_io_apic(void)
diff --git a/arch/x86/include/asm/mach-generic/mach_apic.h b/arch/x86/include/asm/mach-generic/mach_apic.h
index 5180bd7478fb..e430f47df667 100644
--- a/arch/x86/include/asm/mach-generic/mach_apic.h
+++ b/arch/x86/include/asm/mach-generic/mach_apic.h
@@ -27,6 +27,7 @@
 #define vector_allocation_domain (genapic->vector_allocation_domain)
 #define enable_apic_mode (genapic->enable_apic_mode)
 #define phys_pkg_id (genapic->phys_pkg_id)
+#define wakeup_secondary_cpu (genapic->wakeup_cpu)
 
 extern void generic_bigsmp_probe(void);
 
diff --git a/arch/x86/include/asm/mach-generic/mach_wakecpu.h b/arch/x86/include/asm/mach-generic/mach_wakecpu.h
new file mode 100644
index 000000000000..1ab16b168c8a
--- /dev/null
+++ b/arch/x86/include/asm/mach-generic/mach_wakecpu.h
@@ -0,0 +1,12 @@
+#ifndef _ASM_X86_MACH_GENERIC_MACH_WAKECPU_H
+#define _ASM_X86_MACH_GENERIC_MACH_WAKECPU_H
+
+#define TRAMPOLINE_PHYS_LOW (genapic->trampoline_phys_low)
+#define TRAMPOLINE_PHYS_HIGH (genapic->trampoline_phys_high)
+#define wait_for_init_deassert (genapic->wait_for_init_deassert)
+#define smp_callin_clear_local_apic (genapic->smp_callin_clear_local_apic)
+#define store_NMI_vector (genapic->store_NMI_vector)
+#define restore_NMI_vector (genapic->restore_NMI_vector)
+#define inquire_remote_apic (genapic->inquire_remote_apic)
+
+#endif /* _ASM_X86_MACH_GENERIC_MACH_APIC_H */
diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h
index c2a812ebde89..397efa375581 100644
--- a/arch/x86/include/asm/msr.h
+++ b/arch/x86/include/asm/msr.h
@@ -22,10 +22,10 @@ static inline unsigned long long native_read_tscp(unsigned int *aux)
 }
 
 /*
- * i386 calling convention returns 64-bit value in edx:eax, while
- * x86_64 returns at rax. Also, the "A" constraint does not really
- * mean rdx:rax in x86_64, so we need specialized behaviour for each
- * architecture
+ * both i386 and x86_64 returns 64-bit value in edx:eax, but gcc's "A"
+ * constraint has different meanings. For i386, "A" means exactly
+ * edx:eax, while for x86_64 it doesn't mean rdx:rax or edx:eax. Instead,
+ * it means rax *or* rdx.
  */
 #ifdef CONFIG_X86_64
 #define DECLARE_ARGS(val, low, high)	unsigned low, high
diff --git a/arch/x86/include/asm/numaq/wakecpu.h b/arch/x86/include/asm/numaq/wakecpu.h
index c577bda5b1c5..6f499df8eddb 100644
--- a/arch/x86/include/asm/numaq/wakecpu.h
+++ b/arch/x86/include/asm/numaq/wakecpu.h
@@ -3,12 +3,8 @@
 
 /* This file copes with machines that wakeup secondary CPUs by NMIs */
 
-#define WAKE_SECONDARY_VIA_NMI
-
-#define TRAMPOLINE_LOW phys_to_virt(0x8)
-#define TRAMPOLINE_HIGH phys_to_virt(0xa)
-
-#define boot_cpu_apicid boot_cpu_logical_apicid
+#define TRAMPOLINE_PHYS_LOW (0x8)
+#define TRAMPOLINE_PHYS_HIGH (0xa)
 
 /* We don't do anything here because we use NMI's to boot instead */
 static inline void wait_for_init_deassert(atomic_t *deassert)
@@ -27,17 +23,23 @@ static inline void smp_callin_clear_local_apic(void)
 static inline void store_NMI_vector(unsigned short *high, unsigned short *low)
 {
 	printk("Storing NMI vector\n");
-	*high = *((volatile unsigned short *) TRAMPOLINE_HIGH);
-	*low = *((volatile unsigned short *) TRAMPOLINE_LOW);
+	*high =
+	  *((volatile unsigned short *)phys_to_virt(TRAMPOLINE_PHYS_HIGH));
+	*low =
+	  *((volatile unsigned short *)phys_to_virt(TRAMPOLINE_PHYS_LOW));
 }
 
 static inline void restore_NMI_vector(unsigned short *high, unsigned short *low)
 {
 	printk("Restoring NMI vector\n");
-	*((volatile unsigned short *) TRAMPOLINE_HIGH) = *high;
-	*((volatile unsigned short *) TRAMPOLINE_LOW) = *low;
+	*((volatile unsigned short *)phys_to_virt(TRAMPOLINE_PHYS_HIGH)) =
+								 *high;
+	*((volatile unsigned short *)phys_to_virt(TRAMPOLINE_PHYS_LOW)) =
+								 *low;
 }
 
-#define inquire_remote_apic(apicid) {}
+static inline void inquire_remote_apic(int apicid)
+{
+}
 
 #endif /* __ASM_NUMAQ_WAKECPU_H */
diff --git a/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h
index 875b38edf193..647781298e7e 100644
--- a/arch/x86/include/asm/pci.h
+++ b/arch/x86/include/asm/pci.h
@@ -19,6 +19,8 @@ struct pci_sysdata {
 };
 
 extern int pci_routeirq;
+extern int noioapicquirk;
+extern int noioapicreroute;
 
 /* scan a bus after allocating a pci_sysdata for it */
 extern struct pci_bus *pci_scan_bus_on_node(int busno, struct pci_ops *ops,
diff --git a/arch/x86/include/asm/pda.h b/arch/x86/include/asm/pda.h
index 2fbfff88df37..3fea2fdb3302 100644
--- a/arch/x86/include/asm/pda.h
+++ b/arch/x86/include/asm/pda.h
@@ -16,11 +16,9 @@ struct x8664_pda {
 	unsigned long oldrsp;		/* 24 user rsp for system call */
 	int irqcount;			/* 32 Irq nesting counter. Starts -1 */
 	unsigned int cpunumber;		/* 36 Logical CPU number */
-#ifdef CONFIG_CC_STACKPROTECTOR
 	unsigned long stack_canary;	/* 40 stack canary value */
 					/* gcc-ABI: this canary MUST be at
 					   offset 40!!! */
-#endif
 	char *irqstackptr;
 	short nodenumber;		/* number of current node (32k max) */
 	short in_bootmem;		/* pda lives in bootmem */
@@ -134,4 +132,6 @@ do {									\
 
 #define PDA_STACKOFFSET (5*8)
 
+#define refresh_stack_canary() write_pda(stack_canary, current->stack_canary)
+
 #endif /* _ASM_X86_PDA_H */
diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index ece72053ba63..313b3d692595 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -134,6 +134,11 @@ do {							\
 		    : "+m" (var)			\
 		    : "ri" ((T__)val));			\
 		break;					\
+	case 8:						\
+		asm(op "q %1,"__percpu_seg"%0"		\
+		    : "+m" (var)			\
+		    : "ri" ((T__)val));			\
+		break;					\
 	default: __bad_percpu_size();			\
 	}						\
 } while (0)
@@ -157,16 +162,84 @@ do {							\
 		    : "=r" (ret__)			\
 		    : "m" (var));			\
 		break;					\
+	case 8:						\
+		asm(op "q "__percpu_seg"%1,%0"		\
+		    : "=r" (ret__)			\
+		    : "m" (var));			\
+		break;					\
 	default: __bad_percpu_size();			\
 	}						\
 	ret__;						\
 })
 
-#define x86_read_percpu(var) percpu_from_op("mov", per_cpu__##var)
-#define x86_write_percpu(var, val) percpu_to_op("mov", per_cpu__##var, val)
-#define x86_add_percpu(var, val) percpu_to_op("add", per_cpu__##var, val)
-#define x86_sub_percpu(var, val) percpu_to_op("sub", per_cpu__##var, val)
-#define x86_or_percpu(var, val) percpu_to_op("or", per_cpu__##var, val)
+#define percpu_addr_op(op, var)				\
+({							\
+	switch (sizeof(var)) {				\
+	case 1:						\
+		asm(op "b "__percpu_seg"%0"		\
+				: : "m"(var));		\
+		break;					\
+	case 2:						\
+		asm(op "w "__percpu_seg"%0"		\
+				: : "m"(var));		\
+		break;					\
+	case 4:						\
+		asm(op "l "__percpu_seg"%0"		\
+				: : "m"(var));		\
+		break;					\
+	case 8:						\
+		asm(op "q "__percpu_seg"%0"		\
+				: : "m"(var));		\
+		break;					\
+	default: __bad_percpu_size();			\
+	}						\
+})
+
+#define percpu_cmpxchg_op(var, old, new)				\
+({									\
+	typeof(var) prev;						\
+	switch (sizeof(var)) {						\
+	case 1:								\
+		asm("cmpxchgb %b1, "__percpu_seg"%2"			\
+				     : "=a"(prev)			\
+				     : "q"(new), "m"(var), "0"(old)	\
+				     : "memory");			\
+		break;							\
+	case 2:								\
+		asm("cmpxchgw %w1, "__percpu_seg"%2"			\
+				     : "=a"(prev)			\
+				     : "r"(new), "m"(var), "0"(old)	\
+				     : "memory");			\
+		break;							\
+	case 4:								\
+		asm("cmpxchgl %k1, "__percpu_seg"%2"			\
+				     : "=a"(prev)			\
+				     : "r"(new), "m"(var), "0"(old)	\
+				     : "memory");			\
+		break;							\
+	case 8:								\
+		asm("cmpxchgq %1, "__percpu_seg"%2"			\
+				     : "=a"(prev)			\
+				     : "r"(new), "m"(var), "0"(old)	\
+				     : "memory");			\
+		break;							\
+	default:							\
+		__bad_percpu_size();					\
+	}								\
+	return prev;							\
+})
+
+#define x86_read_percpu(var) percpu_from_op("mov", per_cpu_var(var))
+#define x86_write_percpu(var, val) percpu_to_op("mov", per_cpu_var(var), val)
+#define x86_add_percpu(var, val) percpu_to_op("add", per_cpu_var(var), val)
+#define x86_sub_percpu(var, val) percpu_to_op("sub", per_cpu_var(var), val)
+#define x86_inc_percpu(var) percpu_addr_op("inc", per_cpu_var(var))
+#define x86_dec_percpu(var) percpu_addr_op("dec", per_cpu_var(var))
+#define x86_or_percpu(var, val) percpu_to_op("or", per_cpu_var(var), val)
+#define x86_xchg_percpu(var, val) percpu_to_op("xchg", per_cpu_var(var), val)
+#define x86_cmpxchg_percpu(var, old, new) \
+				percpu_cmpxchg_op(per_cpu_var(var), old, new)
+
 #endif /* !__ASSEMBLY__ */
 #endif /* !CONFIG_X86_64 */
 
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 5ca01e383269..a570eafa4755 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -110,6 +110,7 @@ struct cpuinfo_x86 {
 	/* Index into per_cpu list: */
 	u16			cpu_index;
 #endif
+	unsigned int		x86_hyper_vendor;
 } __attribute__((__aligned__(SMP_CACHE_BYTES)));
 
 #define X86_VENDOR_INTEL	0
@@ -123,6 +124,9 @@ struct cpuinfo_x86 {
 
 #define X86_VENDOR_UNKNOWN	0xff
 
+#define X86_HYPER_VENDOR_NONE  0
+#define X86_HYPER_VENDOR_VMWARE 1
+
 /*
  * capabilities of CPUs
  */
diff --git a/arch/x86/include/asm/reboot.h b/arch/x86/include/asm/reboot.h
index df7710354f85..562d4fd31ba8 100644
--- a/arch/x86/include/asm/reboot.h
+++ b/arch/x86/include/asm/reboot.h
@@ -1,6 +1,8 @@
 #ifndef _ASM_X86_REBOOT_H
 #define _ASM_X86_REBOOT_H
 
+#include <linux/kdebug.h>
+
 struct pt_regs;
 
 struct machine_ops {
@@ -18,4 +20,7 @@ void native_machine_crash_shutdown(struct pt_regs *regs);
 void native_machine_shutdown(void);
 void machine_real_restart(const unsigned char *code, int length);
 
+typedef void (*nmi_shootdown_cb)(int, struct die_args*);
+void nmi_shootdown_cpus(nmi_shootdown_cb callback);
+
 #endif /* _ASM_X86_REBOOT_H */
diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h
index f12d37237465..4fcd53fd5f43 100644
--- a/arch/x86/include/asm/setup.h
+++ b/arch/x86/include/asm/setup.h
@@ -8,6 +8,10 @@
 /* Interrupt control for vSMPowered x86_64 systems */
 void vsmp_init(void);
 
+
+void setup_bios_corruption_check(void);
+
+
 #ifdef CONFIG_X86_VISWS
 extern void visws_early_detect(void);
 extern int is_visws_box(void);
@@ -16,6 +20,8 @@ static inline void visws_early_detect(void) { }
 static inline int is_visws_box(void) { return 0; }
 #endif
 
+extern int wakeup_secondary_cpu_via_nmi(int apicid, unsigned long start_eip);
+extern int wakeup_secondary_cpu_via_init(int apicid, unsigned long start_eip);
 /*
  * Any setup quirks to be performed?
  */
@@ -39,6 +45,7 @@ struct x86_quirks {
 	void (*smp_read_mpc_oem)(struct mp_config_oemtable *oemtable,
                                     unsigned short oemsize);
 	int (*setup_ioapic_ids)(void);
+	int (*update_genapic)(void);
 };
 
 extern struct x86_quirks *x86_quirks;
diff --git a/arch/x86/include/asm/system.h b/arch/x86/include/asm/system.h
index 2ed3f0f44ff7..f2025b0c69d4 100644
--- a/arch/x86/include/asm/system.h
+++ b/arch/x86/include/asm/system.h
@@ -95,6 +95,8 @@ do {									\
 	     ".globl thread_return\n"					  \
 	     "thread_return:\n\t"					  \
 	     "movq %%gs:%P[pda_pcurrent],%%rsi\n\t"			  \
+	     "movq %P[task_canary](%%rsi),%%r8\n\t"			  \
+	     "movq %%r8,%%gs:%P[pda_canary]\n\t"			  \
 	     "movq %P[thread_info](%%rsi),%%r8\n\t"			  \
 	     LOCK_PREFIX "btr  %[tif_fork],%P[ti_flags](%%r8)\n\t"	  \
 	     "movq %%rax,%%rdi\n\t" 					  \
@@ -106,7 +108,9 @@ do {									\
 	       [ti_flags] "i" (offsetof(struct thread_info, flags)),	  \
 	       [tif_fork] "i" (TIF_FORK),			  	  \
 	       [thread_info] "i" (offsetof(struct task_struct, stack)),   \
-	       [pda_pcurrent] "i" (offsetof(struct x8664_pda, pcurrent))  \
+	       [task_canary] "i" (offsetof(struct task_struct, stack_canary)),\
+	       [pda_pcurrent] "i" (offsetof(struct x8664_pda, pcurrent)), \
+	       [pda_canary] "i" (offsetof(struct x8664_pda, stack_canary))\
 	     : "memory", "cc" __EXTRA_CLOBBER)
 #endif
 
@@ -314,6 +318,8 @@ extern void free_init_pages(char *what, unsigned long begin, unsigned long end);
 
 void default_idle(void);
 
+void stop_this_cpu(void *dummy);
+
 /*
  * Force strict CPU ordering.
  * And yes, this is required on UP too when we're talking
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index e44d379faad2..0921b4018c11 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -20,6 +20,8 @@
 struct task_struct;
 struct exec_domain;
 #include <asm/processor.h>
+#include <asm/ftrace.h>
+#include <asm/atomic.h>
 
 struct thread_info {
 	struct task_struct	*task;		/* main task structure */
diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h
index 4850e4b02b61..ff386ff50ed7 100644
--- a/arch/x86/include/asm/topology.h
+++ b/arch/x86/include/asm/topology.h
@@ -239,7 +239,7 @@ struct pci_bus;
 void set_pci_bus_resources_arch_default(struct pci_bus *b);
 
 #ifdef CONFIG_SMP
-#define mc_capable()			(boot_cpu_data.x86_max_cores > 1)
+#define mc_capable()	(cpus_weight(per_cpu(cpu_core_map, 0)) != nr_cpu_ids)
 #define smt_capable()			(smp_num_siblings > 1)
 #endif
 
diff --git a/arch/x86/include/asm/tsc.h b/arch/x86/include/asm/tsc.h
index 9cd83a8e40d5..38ae163cc91b 100644
--- a/arch/x86/include/asm/tsc.h
+++ b/arch/x86/include/asm/tsc.h
@@ -34,8 +34,6 @@ static inline cycles_t get_cycles(void)
 
 static __always_inline cycles_t vget_cycles(void)
 {
-	cycles_t cycles;
-
 	/*
 	 * We only do VDSOs on TSC capable CPUs, so this shouldnt
 	 * access boot_cpu_data (which is not VDSO-safe):
@@ -44,11 +42,7 @@ static __always_inline cycles_t vget_cycles(void)
 	if (!cpu_has_tsc)
 		return 0;
 #endif
-	rdtsc_barrier();
-	cycles = (cycles_t)__native_read_tsc();
-	rdtsc_barrier();
-
-	return cycles;
+	return (cycles_t)__native_read_tsc();
 }
 
 extern void tsc_init(void);
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index 35c54921b2e4..99192bb55a53 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -157,6 +157,7 @@ extern int __get_user_bad(void);
 	int __ret_gu;							\
 	unsigned long __val_gu;						\
 	__chk_user_ptr(ptr);						\
+	might_fault();							\
 	switch (sizeof(*(ptr))) {					\
 	case 1:								\
 		__get_user_x(1, __ret_gu, __val_gu, ptr);		\
@@ -241,6 +242,7 @@ extern void __put_user_8(void);
 	int __ret_pu;						\
 	__typeof__(*(ptr)) __pu_val;				\
 	__chk_user_ptr(ptr);					\
+	might_fault();						\
 	__pu_val = x;						\
 	switch (sizeof(*(ptr))) {				\
 	case 1:							\
diff --git a/arch/x86/include/asm/uaccess_32.h b/arch/x86/include/asm/uaccess_32.h
index d095a3aeea1b..5e06259e90e5 100644
--- a/arch/x86/include/asm/uaccess_32.h
+++ b/arch/x86/include/asm/uaccess_32.h
@@ -82,8 +82,8 @@ __copy_to_user_inatomic(void __user *to, const void *from, unsigned long n)
 static __always_inline unsigned long __must_check
 __copy_to_user(void __user *to, const void *from, unsigned long n)
 {
-       might_sleep();
-       return __copy_to_user_inatomic(to, from, n);
+	might_fault();
+	return __copy_to_user_inatomic(to, from, n);
 }
 
 static __always_inline unsigned long
@@ -137,7 +137,7 @@ __copy_from_user_inatomic(void *to, const void __user *from, unsigned long n)
 static __always_inline unsigned long
 __copy_from_user(void *to, const void __user *from, unsigned long n)
 {
-	might_sleep();
+	might_fault();
 	if (__builtin_constant_p(n)) {
 		unsigned long ret;
 
@@ -159,7 +159,7 @@ __copy_from_user(void *to, const void __user *from, unsigned long n)
 static __always_inline unsigned long __copy_from_user_nocache(void *to,
 				const void __user *from, unsigned long n)
 {
-	might_sleep();
+	might_fault();
 	if (__builtin_constant_p(n)) {
 		unsigned long ret;
 
diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h
index f8cfd00db450..84210c479fca 100644
--- a/arch/x86/include/asm/uaccess_64.h
+++ b/arch/x86/include/asm/uaccess_64.h
@@ -29,6 +29,8 @@ static __always_inline __must_check
 int __copy_from_user(void *dst, const void __user *src, unsigned size)
 {
 	int ret = 0;
+
+	might_fault();
 	if (!__builtin_constant_p(size))
 		return copy_user_generic(dst, (__force void *)src, size);
 	switch (size) {
@@ -71,6 +73,8 @@ static __always_inline __must_check
 int __copy_to_user(void __user *dst, const void *src, unsigned size)
 {
 	int ret = 0;
+
+	might_fault();
 	if (!__builtin_constant_p(size))
 		return copy_user_generic((__force void *)dst, src, size);
 	switch (size) {
@@ -113,6 +117,8 @@ static __always_inline __must_check
 int __copy_in_user(void __user *dst, const void __user *src, unsigned size)
 {
 	int ret = 0;
+
+	might_fault();
 	if (!__builtin_constant_p(size))
 		return copy_user_generic((__force void *)dst,
 					 (__force void *)src, size);
diff --git a/arch/x86/include/asm/uv/bios.h b/arch/x86/include/asm/uv/bios.h
index d931d3b7e6f7..da1c4e8e78fc 100644
--- a/arch/x86/include/asm/uv/bios.h
+++ b/arch/x86/include/asm/uv/bios.h
@@ -32,13 +32,18 @@
 enum uv_bios_cmd {
 	UV_BIOS_COMMON,
 	UV_BIOS_GET_SN_INFO,
-	UV_BIOS_FREQ_BASE
+	UV_BIOS_FREQ_BASE,
+	UV_BIOS_WATCHLIST_ALLOC,
+	UV_BIOS_WATCHLIST_FREE,
+	UV_BIOS_MEMPROTECT,
+	UV_BIOS_GET_PARTITION_ADDR
 };
 
 /*
  * Status values returned from a BIOS call.
  */
 enum {
+	BIOS_STATUS_MORE_PASSES		=  1,
 	BIOS_STATUS_SUCCESS		=  0,
 	BIOS_STATUS_UNIMPLEMENTED	= -ENOSYS,
 	BIOS_STATUS_EINVAL		= -EINVAL,
@@ -71,6 +76,21 @@ union partition_info_u {
 	};
 };
 
+union uv_watchlist_u {
+	u64	val;
+	struct {
+		u64	blade	: 16,
+			size	: 32,
+			filler	: 16;
+	};
+};
+
+enum uv_memprotect {
+	UV_MEMPROT_RESTRICT_ACCESS,
+	UV_MEMPROT_ALLOW_AMO,
+	UV_MEMPROT_ALLOW_RW
+};
+
 /*
  * bios calls have 6 parameters
  */
@@ -80,14 +100,20 @@ extern s64 uv_bios_call_reentrant(enum uv_bios_cmd, u64, u64, u64, u64, u64);
 
 extern s64 uv_bios_get_sn_info(int, int *, long *, long *, long *);
 extern s64 uv_bios_freq_base(u64, u64 *);
+extern int uv_bios_mq_watchlist_alloc(int, void *, unsigned int,
+					unsigned long *);
+extern int uv_bios_mq_watchlist_free(int, int);
+extern s64 uv_bios_change_memprotect(u64, u64, enum uv_memprotect);
+extern s64 uv_bios_reserved_page_pa(u64, u64 *, u64 *, u64 *);
 
 extern void uv_bios_init(void);
 
+extern unsigned long sn_rtc_cycles_per_second;
 extern int uv_type;
 extern long sn_partition_id;
-extern long uv_coherency_id;
-extern long uv_region_size;
-#define partition_coherence_id()	(uv_coherency_id)
+extern long sn_coherency_id;
+extern long sn_region_size;
+#define partition_coherence_id()	(sn_coherency_id)
 
 extern struct kobject *sgi_uv_kobj;	/* /sys/firmware/sgi_uv */
 
diff --git a/arch/x86/include/asm/uv/uv_hub.h b/arch/x86/include/asm/uv/uv_hub.h
index 7a5782610b2b..52aa943c634f 100644
--- a/arch/x86/include/asm/uv/uv_hub.h
+++ b/arch/x86/include/asm/uv/uv_hub.h
@@ -113,25 +113,37 @@
  */
 #define UV_MAX_NASID_VALUE	(UV_MAX_NUMALINK_NODES * 2)
 
+struct uv_scir_s {
+	struct timer_list timer;
+	unsigned long	offset;
+	unsigned long	last;
+	unsigned long	idle_on;
+	unsigned long	idle_off;
+	unsigned char	state;
+	unsigned char	enabled;
+};
+
 /*
  * The following defines attributes of the HUB chip. These attributes are
  * frequently referenced and are kept in the per-cpu data areas of each cpu.
  * They are kept together in a struct to minimize cache misses.
  */
 struct uv_hub_info_s {
-	unsigned long	global_mmr_base;
-	unsigned long	gpa_mask;
-	unsigned long	gnode_upper;
-	unsigned long	lowmem_remap_top;
-	unsigned long	lowmem_remap_base;
-	unsigned short	pnode;
-	unsigned short	pnode_mask;
-	unsigned short	coherency_domain_number;
-	unsigned short	numa_blade_id;
-	unsigned char	blade_processor_id;
-	unsigned char	m_val;
-	unsigned char	n_val;
+	unsigned long		global_mmr_base;
+	unsigned long		gpa_mask;
+	unsigned long		gnode_upper;
+	unsigned long		lowmem_remap_top;
+	unsigned long		lowmem_remap_base;
+	unsigned short		pnode;
+	unsigned short		pnode_mask;
+	unsigned short		coherency_domain_number;
+	unsigned short		numa_blade_id;
+	unsigned char		blade_processor_id;
+	unsigned char		m_val;
+	unsigned char		n_val;
+	struct uv_scir_s	scir;
 };
+
 DECLARE_PER_CPU(struct uv_hub_info_s, __uv_hub_info);
 #define uv_hub_info 		(&__get_cpu_var(__uv_hub_info))
 #define uv_cpu_hub_info(cpu)	(&per_cpu(__uv_hub_info, cpu))
@@ -163,6 +175,30 @@ DECLARE_PER_CPU(struct uv_hub_info_s, __uv_hub_info);
 
 #define UV_APIC_PNODE_SHIFT	6
 
+/* Local Bus from cpu's perspective */
+#define LOCAL_BUS_BASE		0x1c00000
+#define LOCAL_BUS_SIZE		(4 * 1024 * 1024)
+
+/*
+ * System Controller Interface Reg
+ *
+ * Note there are NO leds on a UV system.  This register is only
+ * used by the system controller to monitor system-wide operation.
+ * There are 64 regs per node.  With Nahelem cpus (2 cores per node,
+ * 8 cpus per core, 2 threads per cpu) there are 32 cpu threads on
+ * a node.
+ *
+ * The window is located at top of ACPI MMR space
+ */
+#define SCIR_WINDOW_COUNT	64
+#define SCIR_LOCAL_MMR_BASE	(LOCAL_BUS_BASE + \
+				 LOCAL_BUS_SIZE - \
+				 SCIR_WINDOW_COUNT)
+
+#define SCIR_CPU_HEARTBEAT	0x01	/* timer interrupt */
+#define SCIR_CPU_ACTIVITY	0x02	/* not idle */
+#define SCIR_CPU_HB_INTERVAL	(HZ)	/* once per second */
+
 /*
  * Macros for converting between kernel virtual addresses, socket local physical
  * addresses, and UV global physical addresses.
@@ -277,6 +313,16 @@ static inline void uv_write_local_mmr(unsigned long offset, unsigned long val)
 	*uv_local_mmr_address(offset) = val;
 }
 
+static inline unsigned char uv_read_local_mmr8(unsigned long offset)
+{
+	return *((unsigned char *)uv_local_mmr_address(offset));
+}
+
+static inline void uv_write_local_mmr8(unsigned long offset, unsigned char val)
+{
+	*((unsigned char *)uv_local_mmr_address(offset)) = val;
+}
+
 /*
  * Structures and definitions for converting between cpu, node, pnode, and blade
  * numbers.
@@ -351,5 +397,20 @@ static inline int uv_num_possible_blades(void)
 	return uv_possible_blades;
 }
 
-#endif /* _ASM_X86_UV_UV_HUB_H */
+/* Update SCIR state */
+static inline void uv_set_scir_bits(unsigned char value)
+{
+	if (uv_hub_info->scir.state != value) {
+		uv_hub_info->scir.state = value;
+		uv_write_local_mmr8(uv_hub_info->scir.offset, value);
+	}
+}
+static inline void uv_set_cpu_scir_bits(int cpu, unsigned char value)
+{
+	if (uv_cpu_hub_info(cpu)->scir.state != value) {
+		uv_cpu_hub_info(cpu)->scir.state = value;
+		uv_write_local_mmr8(uv_cpu_hub_info(cpu)->scir.offset, value);
+	}
+}
 
+#endif /* _ASM_X86_UV_UV_HUB_H */
diff --git a/arch/x86/include/asm/vmware.h b/arch/x86/include/asm/vmware.h
new file mode 100644
index 000000000000..c11b7e100d83
--- /dev/null
+++ b/arch/x86/include/asm/vmware.h
@@ -0,0 +1,27 @@
+/*
+ * Copyright (C) 2008, VMware, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
+ * NON INFRINGEMENT.  See the GNU General Public License for more
+ * details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
+ *
+ */
+#ifndef ASM_X86__VMWARE_H
+#define ASM_X86__VMWARE_H
+
+extern unsigned long vmware_get_tsc_khz(void);
+extern int vmware_platform(void);
+extern void vmware_set_feature_bits(struct cpuinfo_x86 *c);
+
+#endif
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index b62a7667828e..d3e7e3aadaab 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -12,6 +12,12 @@ CFLAGS_REMOVE_tsc.o = -pg
 CFLAGS_REMOVE_rtc.o = -pg
 CFLAGS_REMOVE_paravirt-spinlocks.o = -pg
 CFLAGS_REMOVE_ftrace.o = -pg
+CFLAGS_REMOVE_early_printk.o = -pg
+endif
+
+ifdef CONFIG_FUNCTION_RET_TRACER
+# Don't trace __switch_to() but let it for function tracer
+CFLAGS_REMOVE_process_32.o = -pg
 endif
 
 #
@@ -22,10 +28,11 @@ nostackp := $(call cc-option, -fno-stack-protector)
 CFLAGS_vsyscall_64.o	:= $(PROFILING) -g0 $(nostackp)
 CFLAGS_hpet.o		:= $(nostackp)
 CFLAGS_tsc.o		:= $(nostackp)
+CFLAGS_paravirt.o	:= $(nostackp)
 
-obj-y			:= process_$(BITS).o signal_$(BITS).o entry_$(BITS).o
+obj-y			:= process_$(BITS).o signal.o entry_$(BITS).o
 obj-y			+= traps.o irq.o irq_$(BITS).o dumpstack_$(BITS).o
-obj-y			+= time_$(BITS).o ioport.o ldt.o
+obj-y			+= time_$(BITS).o ioport.o ldt.o dumpstack.o
 obj-y			+= setup.o i8259.o irqinit_$(BITS).o setup_percpu.o
 obj-$(CONFIG_X86_VISWS)	+= visws_quirks.o
 obj-$(CONFIG_X86_32)	+= probe_roms_32.o
@@ -65,6 +72,7 @@ obj-$(CONFIG_X86_LOCAL_APIC)	+= apic.o nmi.o
 obj-$(CONFIG_X86_IO_APIC)	+= io_apic.o
 obj-$(CONFIG_X86_REBOOTFIXUPS)	+= reboot_fixups_32.o
 obj-$(CONFIG_DYNAMIC_FTRACE)	+= ftrace.o
+obj-$(CONFIG_FUNCTION_RET_TRACER)	+= ftrace.o
 obj-$(CONFIG_KEXEC)		+= machine_kexec_$(BITS).o
 obj-$(CONFIG_KEXEC)		+= relocate_kernel_$(BITS).o crash.o
 obj-$(CONFIG_CRASH_DUMP)	+= crash_dump_$(BITS).o
@@ -105,6 +113,8 @@ microcode-$(CONFIG_MICROCODE_INTEL)	+= microcode_intel.o
 microcode-$(CONFIG_MICROCODE_AMD)	+= microcode_amd.o
 obj-$(CONFIG_MICROCODE)			+= microcode.o
 
+obj-$(CONFIG_X86_CHECK_BIOS_CORRUPTION) += check.o
+
 ###
 # 64 bit specific files
 ifeq ($(CONFIG_X86_64),y)
diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c
index 806b4e9051b4..707c1f6f95fa 100644
--- a/arch/x86/kernel/acpi/sleep.c
+++ b/arch/x86/kernel/acpi/sleep.c
@@ -159,6 +159,8 @@ static int __init acpi_sleep_setup(char *str)
 #endif
 		if (strncmp(str, "old_ordering", 12) == 0)
 			acpi_old_suspend_ordering();
+		if (strncmp(str, "s4_nonvs", 8) == 0)
+			acpi_s4_no_nvs();
 		str = strchr(str, ',');
 		if (str != NULL)
 			str += strspn(str, ", \t");
diff --git a/arch/x86/kernel/amd_iommu.c b/arch/x86/kernel/amd_iommu.c
index e4899e0e8787..ce948aa1356c 100644
--- a/arch/x86/kernel/amd_iommu.c
+++ b/arch/x86/kernel/amd_iommu.c
@@ -24,6 +24,7 @@
 #include <linux/iommu-helper.h>
 #include <asm/proto.h>
 #include <asm/iommu.h>
+#include <asm/gart.h>
 #include <asm/amd_iommu_types.h>
 #include <asm/amd_iommu.h>
 
@@ -187,6 +188,8 @@ static int iommu_queue_command(struct amd_iommu *iommu, struct iommu_cmd *cmd)
 
 	spin_lock_irqsave(&iommu->lock, flags);
 	ret = __iommu_queue_command(iommu, cmd);
+	if (!ret)
+		iommu->need_sync = 1;
 	spin_unlock_irqrestore(&iommu->lock, flags);
 
 	return ret;
@@ -210,10 +213,13 @@ static int iommu_completion_wait(struct amd_iommu *iommu)
 	cmd.data[0] = CMD_COMPL_WAIT_INT_MASK;
 	CMD_SET_TYPE(&cmd, CMD_COMPL_WAIT);
 
-	iommu->need_sync = 0;
-
 	spin_lock_irqsave(&iommu->lock, flags);
 
+	if (!iommu->need_sync)
+		goto out;
+
+	iommu->need_sync = 0;
+
 	ret = __iommu_queue_command(iommu, &cmd);
 
 	if (ret)
@@ -254,8 +260,6 @@ static int iommu_queue_inv_dev_entry(struct amd_iommu *iommu, u16 devid)
 
 	ret = iommu_queue_command(iommu, &cmd);
 
-	iommu->need_sync = 1;
-
 	return ret;
 }
 
@@ -281,8 +285,6 @@ static int iommu_queue_inv_iommu_pages(struct amd_iommu *iommu,
 
 	ret = iommu_queue_command(iommu, &cmd);
 
-	iommu->need_sync = 1;
-
 	return ret;
 }
 
@@ -762,8 +764,6 @@ static void set_device_domain(struct amd_iommu *iommu,
 	write_unlock_irqrestore(&amd_iommu_devtable_lock, flags);
 
 	iommu_queue_inv_dev_entry(iommu, devid);
-
-	iommu->need_sync = 1;
 }
 
 /*****************************************************************************
@@ -858,6 +858,9 @@ static int get_device_resources(struct device *dev,
 		print_devid(_bdf, 1);
 	}
 
+	if (domain_for_device(_bdf) == NULL)
+		set_device_domain(*iommu, *domain, _bdf);
+
 	return 1;
 }
 
@@ -1031,8 +1034,7 @@ static dma_addr_t map_single(struct device *dev, phys_addr_t paddr,
 	if (addr == bad_dma_address)
 		goto out;
 
-	if (unlikely(iommu->need_sync))
-		iommu_completion_wait(iommu);
+	iommu_completion_wait(iommu);
 
 out:
 	spin_unlock_irqrestore(&domain->lock, flags);
@@ -1060,8 +1062,7 @@ static void unmap_single(struct device *dev, dma_addr_t dma_addr,
 
 	__unmap_single(iommu, domain->priv, dma_addr, size, dir);
 
-	if (unlikely(iommu->need_sync))
-		iommu_completion_wait(iommu);
+	iommu_completion_wait(iommu);
 
 	spin_unlock_irqrestore(&domain->lock, flags);
 }
@@ -1127,8 +1128,7 @@ static int map_sg(struct device *dev, struct scatterlist *sglist,
 			goto unmap;
 	}
 
-	if (unlikely(iommu->need_sync))
-		iommu_completion_wait(iommu);
+	iommu_completion_wait(iommu);
 
 out:
 	spin_unlock_irqrestore(&domain->lock, flags);
@@ -1173,8 +1173,7 @@ static void unmap_sg(struct device *dev, struct scatterlist *sglist,
 		s->dma_address = s->dma_length = 0;
 	}
 
-	if (unlikely(iommu->need_sync))
-		iommu_completion_wait(iommu);
+	iommu_completion_wait(iommu);
 
 	spin_unlock_irqrestore(&domain->lock, flags);
 }
@@ -1225,8 +1224,7 @@ static void *alloc_coherent(struct device *dev, size_t size,
 		goto out;
 	}
 
-	if (unlikely(iommu->need_sync))
-		iommu_completion_wait(iommu);
+	iommu_completion_wait(iommu);
 
 out:
 	spin_unlock_irqrestore(&domain->lock, flags);
@@ -1257,8 +1255,7 @@ static void free_coherent(struct device *dev, size_t size,
 
 	__unmap_single(iommu, domain->priv, dma_addr, size, DMA_BIDIRECTIONAL);
 
-	if (unlikely(iommu->need_sync))
-		iommu_completion_wait(iommu);
+	iommu_completion_wait(iommu);
 
 	spin_unlock_irqrestore(&domain->lock, flags);
 
diff --git a/arch/x86/kernel/amd_iommu_init.c b/arch/x86/kernel/amd_iommu_init.c
index 30ae2701b3df..1188b98e27ea 100644
--- a/arch/x86/kernel/amd_iommu_init.c
+++ b/arch/x86/kernel/amd_iommu_init.c
@@ -28,6 +28,7 @@
 #include <asm/amd_iommu_types.h>
 #include <asm/amd_iommu.h>
 #include <asm/iommu.h>
+#include <asm/gart.h>
 
 /*
  * definitions for the ACPI scanning code
diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c
index 9a32b37ee2ee..676debfc1702 100644
--- a/arch/x86/kernel/aperture_64.c
+++ b/arch/x86/kernel/aperture_64.c
@@ -1,8 +1,9 @@
 /*
  * Firmware replacement code.
  *
- * Work around broken BIOSes that don't set an aperture or only set the
- * aperture in the AGP bridge.
+ * Work around broken BIOSes that don't set an aperture, only set the
+ * aperture in the AGP bridge, or set too small aperture.
+ *
  * If all fails map the aperture over some low memory.  This is cheaper than
  * doing bounce buffering. The memory is lost. This is done at early boot
  * because only the bootmem allocator can allocate 32+MB.
diff --git a/arch/x86/kernel/apic.c b/arch/x86/kernel/apic.c
index 16f94879b525..fc26ff390f14 100644
--- a/arch/x86/kernel/apic.c
+++ b/arch/x86/kernel/apic.c
@@ -441,6 +441,7 @@ static void lapic_timer_setup(enum clock_event_mode mode,
 		v = apic_read(APIC_LVTT);
 		v |= (APIC_LVT_MASKED | LOCAL_TIMER_VECTOR);
 		apic_write(APIC_LVTT, v);
+		apic_write(APIC_TMICT, 0xffffffff);
 		break;
 	case CLOCK_EVT_MODE_RESUME:
 		/* Nothing to do here */
@@ -559,13 +560,13 @@ static int __init calibrate_by_pmtimer(long deltapm, long *delta)
 	} else {
 		res = (((u64)deltapm) *  mult) >> 22;
 		do_div(res, 1000000);
-		printk(KERN_WARNING "APIC calibration not consistent "
+		pr_warning("APIC calibration not consistent "
 			"with PM Timer: %ldms instead of 100ms\n",
 			(long)res);
 		/* Correct the lapic counter value */
 		res = (((u64)(*delta)) * pm_100ms);
 		do_div(res, deltapm);
-		printk(KERN_INFO "APIC delta adjusted to PM-Timer: "
+		pr_info("APIC delta adjusted to PM-Timer: "
 			"%lu (%ld)\n", (unsigned long)res, *delta);
 		*delta = (long)res;
 	}
@@ -645,8 +646,7 @@ static int __init calibrate_APIC_clock(void)
 	 */
 	if (calibration_result < (1000000 / HZ)) {
 		local_irq_enable();
-		printk(KERN_WARNING
-		       "APIC frequency too slow, disabling apic timer\n");
+		pr_warning("APIC frequency too slow, disabling apic timer\n");
 		return -1;
 	}
 
@@ -672,13 +672,9 @@ static int __init calibrate_APIC_clock(void)
 		while (lapic_cal_loops <= LAPIC_CAL_LOOPS)
 			cpu_relax();
 
-		local_irq_disable();
-
 		/* Stop the lapic timer */
 		lapic_timer_setup(CLOCK_EVT_MODE_SHUTDOWN, levt);
 
-		local_irq_enable();
-
 		/* Jiffies delta */
 		deltaj = lapic_cal_j2 - lapic_cal_j1;
 		apic_printk(APIC_VERBOSE, "... jiffies delta = %lu\n", deltaj);
@@ -692,8 +688,7 @@ static int __init calibrate_APIC_clock(void)
 		local_irq_enable();
 
 	if (levt->features & CLOCK_EVT_FEAT_DUMMY) {
-		printk(KERN_WARNING
-		       "APIC timer disabled due to verification failure.\n");
+		pr_warning("APIC timer disabled due to verification failure.\n");
 			return -1;
 	}
 
@@ -714,7 +709,7 @@ void __init setup_boot_APIC_clock(void)
 	 * broadcast mechanism is used. On UP systems simply ignore it.
 	 */
 	if (disable_apic_timer) {
-		printk(KERN_INFO "Disabling APIC timer\n");
+		pr_info("Disabling APIC timer\n");
 		/* No broadcast on UP ! */
 		if (num_possible_cpus() > 1) {
 			lapic_clockevent.mult = 1;
@@ -741,7 +736,7 @@ void __init setup_boot_APIC_clock(void)
 	if (nmi_watchdog != NMI_IO_APIC)
 		lapic_clockevent.features &= ~CLOCK_EVT_FEAT_DUMMY;
 	else
-		printk(KERN_WARNING "APIC timer registered as dummy,"
+		pr_warning("APIC timer registered as dummy,"
 			" due to nmi_watchdog=%d!\n", nmi_watchdog);
 
 	/* Setup the lapic or request the broadcast */
@@ -773,8 +768,7 @@ static void local_apic_timer_interrupt(void)
 	 * spurious.
 	 */
 	if (!evt->event_handler) {
-		printk(KERN_WARNING
-		       "Spurious LAPIC timer interrupt on cpu %d\n", cpu);
+		pr_warning("Spurious LAPIC timer interrupt on cpu %d\n", cpu);
 		/* Switch it off */
 		lapic_timer_setup(CLOCK_EVT_MODE_SHUTDOWN, evt);
 		return;
@@ -1093,7 +1087,7 @@ static void __cpuinit lapic_setup_esr(void)
 	unsigned int oldvalue, value, maxlvt;
 
 	if (!lapic_is_integrated()) {
-		printk(KERN_INFO "No ESR for 82489DX.\n");
+		pr_info("No ESR for 82489DX.\n");
 		return;
 	}
 
@@ -1104,7 +1098,7 @@ static void __cpuinit lapic_setup_esr(void)
 		 * ESR disabled - we can't do anything useful with the
 		 * errors anyway - mbligh
 		 */
-		printk(KERN_INFO "Leaving ESR disabled.\n");
+		pr_info("Leaving ESR disabled.\n");
 		return;
 	}
 
@@ -1298,7 +1292,7 @@ void check_x2apic(void)
 	rdmsr(MSR_IA32_APICBASE, msr, msr2);
 
 	if (msr & X2APIC_ENABLE) {
-		printk("x2apic enabled by BIOS, switching to x2apic ops\n");
+		pr_info("x2apic enabled by BIOS, switching to x2apic ops\n");
 		x2apic_preenabled = x2apic = 1;
 		apic_ops = &x2apic_ops;
 	}
@@ -1310,7 +1304,7 @@ void enable_x2apic(void)
 
 	rdmsr(MSR_IA32_APICBASE, msr, msr2);
 	if (!(msr & X2APIC_ENABLE)) {
-		printk("Enabling x2apic\n");
+		pr_info("Enabling x2apic\n");
 		wrmsr(MSR_IA32_APICBASE, msr | X2APIC_ENABLE, 0);
 	}
 }
@@ -1325,9 +1319,8 @@ void __init enable_IR_x2apic(void)
 		return;
 
 	if (!x2apic_preenabled && disable_x2apic) {
-		printk(KERN_INFO
-		       "Skipped enabling x2apic and Interrupt-remapping "
-		       "because of nox2apic\n");
+		pr_info("Skipped enabling x2apic and Interrupt-remapping "
+			"because of nox2apic\n");
 		return;
 	}
 
@@ -1335,22 +1328,19 @@ void __init enable_IR_x2apic(void)
 		panic("Bios already enabled x2apic, can't enforce nox2apic");
 
 	if (!x2apic_preenabled && skip_ioapic_setup) {
-		printk(KERN_INFO
-		       "Skipped enabling x2apic and Interrupt-remapping "
-		       "because of skipping io-apic setup\n");
+		pr_info("Skipped enabling x2apic and Interrupt-remapping "
+			"because of skipping io-apic setup\n");
 		return;
 	}
 
 	ret = dmar_table_init();
 	if (ret) {
-		printk(KERN_INFO
-		       "dmar_table_init() failed with %d:\n", ret);
+		pr_info("dmar_table_init() failed with %d:\n", ret);
 
 		if (x2apic_preenabled)
 			panic("x2apic enabled by bios. But IR enabling failed");
 		else
-			printk(KERN_INFO
-			       "Not enabling x2apic,Intr-remapping\n");
+			pr_info("Not enabling x2apic,Intr-remapping\n");
 		return;
 	}
 
@@ -1359,7 +1349,7 @@ void __init enable_IR_x2apic(void)
 
 	ret = save_mask_IO_APIC_setup();
 	if (ret) {
-		printk(KERN_INFO "Saving IO-APIC state failed: %d\n", ret);
+		pr_info("Saving IO-APIC state failed: %d\n", ret);
 		goto end;
 	}
 
@@ -1394,14 +1384,11 @@ end:
 
 	if (!ret) {
 		if (!x2apic_preenabled)
-			printk(KERN_INFO
-			       "Enabled x2apic and interrupt-remapping\n");
+			pr_info("Enabled x2apic and interrupt-remapping\n");
 		else
-			printk(KERN_INFO
-			       "Enabled Interrupt-remapping\n");
+			pr_info("Enabled Interrupt-remapping\n");
 	} else
-		printk(KERN_ERR
-		       "Failed to enable Interrupt-remapping and x2apic\n");
+		pr_err("Failed to enable Interrupt-remapping and x2apic\n");
 #else
 	if (!cpu_has_x2apic)
 		return;
@@ -1410,8 +1397,8 @@ end:
 		panic("x2apic enabled prior OS handover,"
 		      " enable CONFIG_INTR_REMAP");
 
-	printk(KERN_INFO "Enable CONFIG_INTR_REMAP for enabling intr-remapping "
-	       " and x2apic\n");
+	pr_info("Enable CONFIG_INTR_REMAP for enabling intr-remapping "
+		" and x2apic\n");
 #endif
 
 	return;
@@ -1428,7 +1415,7 @@ end:
 static int __init detect_init_APIC(void)
 {
 	if (!cpu_has_apic) {
-		printk(KERN_INFO "No local APIC present\n");
+		pr_info("No local APIC present\n");
 		return -1;
 	}
 
@@ -1469,8 +1456,8 @@ static int __init detect_init_APIC(void)
 		 * "lapic" specified.
 		 */
 		if (!force_enable_local_apic) {
-			printk(KERN_INFO "Local APIC disabled by BIOS -- "
-			       "you can enable it with \"lapic\"\n");
+			pr_info("Local APIC disabled by BIOS -- "
+				"you can enable it with \"lapic\"\n");
 			return -1;
 		}
 		/*
@@ -1480,8 +1467,7 @@ static int __init detect_init_APIC(void)
 		 */
 		rdmsr(MSR_IA32_APICBASE, l, h);
 		if (!(l & MSR_IA32_APICBASE_ENABLE)) {
-			printk(KERN_INFO
-			       "Local APIC disabled by BIOS -- reenabling.\n");
+			pr_info("Local APIC disabled by BIOS -- reenabling.\n");
 			l &= ~MSR_IA32_APICBASE_BASE;
 			l |= MSR_IA32_APICBASE_ENABLE | APIC_DEFAULT_PHYS_BASE;
 			wrmsr(MSR_IA32_APICBASE, l, h);
@@ -1494,7 +1480,7 @@ static int __init detect_init_APIC(void)
 	 */
 	features = cpuid_edx(1);
 	if (!(features & (1 << X86_FEATURE_APIC))) {
-		printk(KERN_WARNING "Could not enable APIC!\n");
+		pr_warning("Could not enable APIC!\n");
 		return -1;
 	}
 	set_cpu_cap(&boot_cpu_data, X86_FEATURE_APIC);
@@ -1505,14 +1491,14 @@ static int __init detect_init_APIC(void)
 	if (l & MSR_IA32_APICBASE_ENABLE)
 		mp_lapic_addr = l & MSR_IA32_APICBASE_BASE;
 
-	printk(KERN_INFO "Found and enabled local APIC!\n");
+	pr_info("Found and enabled local APIC!\n");
 
 	apic_pm_activate();
 
 	return 0;
 
 no_apic:
-	printk(KERN_INFO "No local APIC present or hardware disabled\n");
+	pr_info("No local APIC present or hardware disabled\n");
 	return -1;
 }
 #endif
@@ -1588,12 +1574,12 @@ int __init APIC_init_uniprocessor(void)
 {
 #ifdef CONFIG_X86_64
 	if (disable_apic) {
-		printk(KERN_INFO "Apic disabled\n");
+		pr_info("Apic disabled\n");
 		return -1;
 	}
 	if (!cpu_has_apic) {
 		disable_apic = 1;
-		printk(KERN_INFO "Apic disabled by BIOS\n");
+		pr_info("Apic disabled by BIOS\n");
 		return -1;
 	}
 #else
@@ -1605,8 +1591,8 @@ int __init APIC_init_uniprocessor(void)
 	 */
 	if (!cpu_has_apic &&
 	    APIC_INTEGRATED(apic_version[boot_cpu_physical_apicid])) {
-		printk(KERN_ERR "BIOS bug, local APIC 0x%x not detected!...\n",
-		       boot_cpu_physical_apicid);
+		pr_err("BIOS bug, local APIC 0x%x not detected!...\n",
+			boot_cpu_physical_apicid);
 		clear_cpu_cap(&boot_cpu_data, X86_FEATURE_APIC);
 		return -1;
 	}
@@ -1699,8 +1685,8 @@ void smp_spurious_interrupt(struct pt_regs *regs)
 	add_pda(irq_spurious_count, 1);
 #else
 	/* see sw-dev-man vol 3, chapter 7.4.13.5 */
-	printk(KERN_INFO "spurious APIC interrupt on CPU#%d, "
-	       "should never happen.\n", smp_processor_id());
+	pr_info("spurious APIC interrupt on CPU#%d, "
+		"should never happen.\n", smp_processor_id());
 	__get_cpu_var(irq_stat).irq_spurious_count++;
 #endif
 	irq_exit();
@@ -1724,17 +1710,18 @@ void smp_error_interrupt(struct pt_regs *regs)
 	ack_APIC_irq();
 	atomic_inc(&irq_err_count);
 
-	/* Here is what the APIC error bits mean:
-	   0: Send CS error
-	   1: Receive CS error
-	   2: Send accept error
-	   3: Receive accept error
-	   4: Reserved
-	   5: Send illegal vector
-	   6: Received illegal vector
-	   7: Illegal register address
-	*/
-	printk(KERN_DEBUG "APIC error on CPU%d: %02x(%02x)\n",
+	/*
+	 * Here is what the APIC error bits mean:
+	 * 0: Send CS error
+	 * 1: Receive CS error
+	 * 2: Send accept error
+	 * 3: Receive accept error
+	 * 4: Reserved
+	 * 5: Send illegal vector
+	 * 6: Received illegal vector
+	 * 7: Illegal register address
+	 */
+	pr_debug("APIC error on CPU%d: %02x(%02x)\n",
 		smp_processor_id(), v , v1);
 	irq_exit();
 }
@@ -1838,15 +1825,15 @@ void __cpuinit generic_processor_info(int apicid, int version)
 	 * Validate version
 	 */
 	if (version == 0x0) {
-		printk(KERN_WARNING "BIOS bug, APIC version is 0 for CPU#%d! "
-				"fixing up to 0x10. (tell your hw vendor)\n",
-				version);
+		pr_warning("BIOS bug, APIC version is 0 for CPU#%d! "
+			"fixing up to 0x10. (tell your hw vendor)\n",
+			version);
 		version = 0x10;
 	}
 	apic_version[apicid] = version;
 
 	if (num_processors >= NR_CPUS) {
-		printk(KERN_WARNING "WARNING: NR_CPUS limit of %i reached."
+		pr_warning("WARNING: NR_CPUS limit of %i reached."
 			"  Processor ignored.\n", NR_CPUS);
 		return;
 	}
@@ -2209,7 +2196,7 @@ static int __init apic_set_verbosity(char *arg)
 	else if (strcmp("verbose", arg) == 0)
 		apic_verbosity = APIC_VERBOSE;
 	else {
-		printk(KERN_WARNING "APIC Verbosity level %s not recognised"
+		pr_warning("APIC Verbosity level %s not recognised"
 			" use apic=verbose or apic=debug\n", arg);
 		return -EINVAL;
 	}
diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c
index 5145a6e72bbb..3a26525a3f31 100644
--- a/arch/x86/kernel/apm_32.c
+++ b/arch/x86/kernel/apm_32.c
@@ -391,11 +391,7 @@ static int power_off;
 #else
 static int power_off = 1;
 #endif
-#ifdef CONFIG_APM_REAL_MODE_POWER_OFF
-static int realmode_power_off = 1;
-#else
 static int realmode_power_off;
-#endif
 #ifdef CONFIG_APM_ALLOW_INTS
 static int allow_ints = 1;
 #else
diff --git a/arch/x86/kernel/bios_uv.c b/arch/x86/kernel/bios_uv.c
index f0dfe6f17e7e..d22d0f1bbea0 100644
--- a/arch/x86/kernel/bios_uv.c
+++ b/arch/x86/kernel/bios_uv.c
@@ -69,10 +69,10 @@ s64 uv_bios_call_reentrant(enum uv_bios_cmd which, u64 a1, u64 a2, u64 a3,
 
 long sn_partition_id;
 EXPORT_SYMBOL_GPL(sn_partition_id);
-long uv_coherency_id;
-EXPORT_SYMBOL_GPL(uv_coherency_id);
-long uv_region_size;
-EXPORT_SYMBOL_GPL(uv_region_size);
+long sn_coherency_id;
+EXPORT_SYMBOL_GPL(sn_coherency_id);
+long sn_region_size;
+EXPORT_SYMBOL_GPL(sn_region_size);
 int uv_type;
 
 
@@ -100,6 +100,58 @@ s64 uv_bios_get_sn_info(int fc, int *uvtype, long *partid, long *coher,
 	return ret;
 }
 
+int
+uv_bios_mq_watchlist_alloc(int blade, void *mq, unsigned int mq_size,
+			   unsigned long *intr_mmr_offset)
+{
+	union uv_watchlist_u size_blade;
+	unsigned long addr;
+	u64 watchlist;
+	s64 ret;
+
+	addr = (unsigned long)mq;
+	size_blade.size = mq_size;
+	size_blade.blade = blade;
+
+	/*
+	 * bios returns watchlist number or negative error number.
+	 */
+	ret = (int)uv_bios_call_irqsave(UV_BIOS_WATCHLIST_ALLOC, addr,
+			size_blade.val, (u64)intr_mmr_offset,
+			(u64)&watchlist, 0);
+	if (ret < BIOS_STATUS_SUCCESS)
+		return ret;
+
+	return watchlist;
+}
+EXPORT_SYMBOL_GPL(uv_bios_mq_watchlist_alloc);
+
+int
+uv_bios_mq_watchlist_free(int blade, int watchlist_num)
+{
+	return (int)uv_bios_call_irqsave(UV_BIOS_WATCHLIST_FREE,
+				blade, watchlist_num, 0, 0, 0);
+}
+EXPORT_SYMBOL_GPL(uv_bios_mq_watchlist_free);
+
+s64
+uv_bios_change_memprotect(u64 paddr, u64 len, enum uv_memprotect perms)
+{
+	return uv_bios_call_irqsave(UV_BIOS_MEMPROTECT, paddr, len,
+					perms, 0, 0);
+}
+EXPORT_SYMBOL_GPL(uv_bios_change_memprotect);
+
+s64
+uv_bios_reserved_page_pa(u64 buf, u64 *cookie, u64 *addr, u64 *len)
+{
+	s64 ret;
+
+	ret = uv_bios_call_irqsave(UV_BIOS_GET_PARTITION_ADDR, (u64)cookie,
+					(u64)addr, buf, (u64)len, 0);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(uv_bios_reserved_page_pa);
 
 s64 uv_bios_freq_base(u64 clock_type, u64 *ticks_per_second)
 {
diff --git a/arch/x86/kernel/check.c b/arch/x86/kernel/check.c
new file mode 100644
index 000000000000..2ac0ab71412a
--- /dev/null
+++ b/arch/x86/kernel/check.c
@@ -0,0 +1,161 @@
+#include <linux/module.h>
+#include <linux/sched.h>
+#include <linux/kthread.h>
+#include <linux/workqueue.h>
+#include <asm/e820.h>
+#include <asm/proto.h>
+
+/*
+ * Some BIOSes seem to corrupt the low 64k of memory during events
+ * like suspend/resume and unplugging an HDMI cable.  Reserve all
+ * remaining free memory in that area and fill it with a distinct
+ * pattern.
+ */
+#define MAX_SCAN_AREAS	8
+
+static int __read_mostly memory_corruption_check = -1;
+
+static unsigned __read_mostly corruption_check_size = 64*1024;
+static unsigned __read_mostly corruption_check_period = 60; /* seconds */
+
+static struct e820entry scan_areas[MAX_SCAN_AREAS];
+static int num_scan_areas;
+
+
+static __init int set_corruption_check(char *arg)
+{
+	char *end;
+
+	memory_corruption_check = simple_strtol(arg, &end, 10);
+
+	return (*end == 0) ? 0 : -EINVAL;
+}
+early_param("memory_corruption_check", set_corruption_check);
+
+static __init int set_corruption_check_period(char *arg)
+{
+	char *end;
+
+	corruption_check_period = simple_strtoul(arg, &end, 10);
+
+	return (*end == 0) ? 0 : -EINVAL;
+}
+early_param("memory_corruption_check_period", set_corruption_check_period);
+
+static __init int set_corruption_check_size(char *arg)
+{
+	char *end;
+	unsigned size;
+
+	size = memparse(arg, &end);
+
+	if (*end == '\0')
+		corruption_check_size = size;
+
+	return (size == corruption_check_size) ? 0 : -EINVAL;
+}
+early_param("memory_corruption_check_size", set_corruption_check_size);
+
+
+void __init setup_bios_corruption_check(void)
+{
+	u64 addr = PAGE_SIZE;	/* assume first page is reserved anyway */
+
+	if (memory_corruption_check == -1) {
+		memory_corruption_check =
+#ifdef CONFIG_X86_BOOTPARAM_MEMORY_CORRUPTION_CHECK
+			1
+#else
+			0
+#endif
+			;
+	}
+
+	if (corruption_check_size == 0)
+		memory_corruption_check = 0;
+
+	if (!memory_corruption_check)
+		return;
+
+	corruption_check_size = round_up(corruption_check_size, PAGE_SIZE);
+
+	while (addr < corruption_check_size && num_scan_areas < MAX_SCAN_AREAS) {
+		u64 size;
+		addr = find_e820_area_size(addr, &size, PAGE_SIZE);
+
+		if (addr == 0)
+			break;
+
+		if ((addr + size) > corruption_check_size)
+			size = corruption_check_size - addr;
+
+		if (size == 0)
+			break;
+
+		e820_update_range(addr, size, E820_RAM, E820_RESERVED);
+		scan_areas[num_scan_areas].addr = addr;
+		scan_areas[num_scan_areas].size = size;
+		num_scan_areas++;
+
+		/* Assume we've already mapped this early memory */
+		memset(__va(addr), 0, size);
+
+		addr += size;
+	}
+
+	printk(KERN_INFO "Scanning %d areas for low memory corruption\n",
+	       num_scan_areas);
+	update_e820();
+}
+
+
+void check_for_bios_corruption(void)
+{
+	int i;
+	int corruption = 0;
+
+	if (!memory_corruption_check)
+		return;
+
+	for (i = 0; i < num_scan_areas; i++) {
+		unsigned long *addr = __va(scan_areas[i].addr);
+		unsigned long size = scan_areas[i].size;
+
+		for (; size; addr++, size -= sizeof(unsigned long)) {
+			if (!*addr)
+				continue;
+			printk(KERN_ERR "Corrupted low memory at %p (%lx phys) = %08lx\n",
+			       addr, __pa(addr), *addr);
+			corruption = 1;
+			*addr = 0;
+		}
+	}
+
+	WARN_ONCE(corruption, KERN_ERR "Memory corruption detected in low memory\n");
+}
+
+static void check_corruption(struct work_struct *dummy);
+static DECLARE_DELAYED_WORK(bios_check_work, check_corruption);
+
+static void check_corruption(struct work_struct *dummy)
+{
+	check_for_bios_corruption();
+	schedule_delayed_work(&bios_check_work,
+		round_jiffies_relative(corruption_check_period*HZ)); 
+}
+
+static int start_periodic_check_for_corruption(void)
+{
+	if (!memory_corruption_check || corruption_check_period == 0)
+		return 0;
+
+	printk(KERN_INFO "Scanning for low memory corruption every %d seconds\n",
+	       corruption_check_period);
+
+	/* First time we run the checks right away */
+	schedule_delayed_work(&bios_check_work, 0);
+	return 0;
+}
+
+module_init(start_periodic_check_for_corruption);
+
diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile
index 82ec6075c057..a5c04e88777e 100644
--- a/arch/x86/kernel/cpu/Makefile
+++ b/arch/x86/kernel/cpu/Makefile
@@ -4,6 +4,7 @@
 
 obj-y			:= intel_cacheinfo.o addon_cpuid_features.o
 obj-y			+= proc.o capflags.o powerflags.o common.o
+obj-y			+= vmware.o hypervisor.o
 
 obj-$(CONFIG_X86_32)	+= bugs.o cmpxchg.o
 obj-$(CONFIG_X86_64)	+= bugs_64.o
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index b9c9ea0217a9..b88595c36254 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -36,6 +36,7 @@
 #include <asm/proto.h>
 #include <asm/sections.h>
 #include <asm/setup.h>
+#include <asm/hypervisor.h>
 
 #include "cpu.h"
 
@@ -703,6 +704,7 @@ static void __cpuinit identify_cpu(struct cpuinfo_x86 *c)
 	detect_ht(c);
 #endif
 
+	init_hypervisor(c);
 	/*
 	 * On SMP, boot_cpu_data holds the common feature set between
 	 * all CPUs; so make sure that we indicate which features are
diff --git a/arch/x86/kernel/cpu/hypervisor.c b/arch/x86/kernel/cpu/hypervisor.c
new file mode 100644
index 000000000000..fb5b86af0b01
--- /dev/null
+++ b/arch/x86/kernel/cpu/hypervisor.c
@@ -0,0 +1,58 @@
+/*
+ * Common hypervisor code
+ *
+ * Copyright (C) 2008, VMware, Inc.
+ * Author : Alok N Kataria <akataria@vmware.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
+ * NON INFRINGEMENT.  See the GNU General Public License for more
+ * details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
+ *
+ */
+
+#include <asm/processor.h>
+#include <asm/vmware.h>
+#include <asm/hypervisor.h>
+
+static inline void __cpuinit
+detect_hypervisor_vendor(struct cpuinfo_x86 *c)
+{
+	if (vmware_platform()) {
+		c->x86_hyper_vendor = X86_HYPER_VENDOR_VMWARE;
+	} else {
+		c->x86_hyper_vendor = X86_HYPER_VENDOR_NONE;
+	}
+}
+
+unsigned long get_hypervisor_tsc_freq(void)
+{
+	if (boot_cpu_data.x86_hyper_vendor == X86_HYPER_VENDOR_VMWARE)
+		return vmware_get_tsc_khz();
+	return 0;
+}
+
+static inline void __cpuinit
+hypervisor_set_feature_bits(struct cpuinfo_x86 *c)
+{
+	if (boot_cpu_data.x86_hyper_vendor == X86_HYPER_VENDOR_VMWARE) {
+		vmware_set_feature_bits(c);
+		return;
+	}
+}
+
+void __cpuinit init_hypervisor(struct cpuinfo_x86 *c)
+{
+	detect_hypervisor_vendor(c);
+	hypervisor_set_feature_bits(c);
+}
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index cce0b6118d55..816f27f289b1 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -307,12 +307,11 @@ static void __cpuinit init_intel(struct cpuinfo_x86 *c)
 		set_cpu_cap(c, X86_FEATURE_P4);
 	if (c->x86 == 6)
 		set_cpu_cap(c, X86_FEATURE_P3);
+#endif
 
 	if (cpu_has_bts)
 		ptrace_bts_init_intel(c);
 
-#endif
-
 	detect_extended_topology(c);
 	if (!cpu_has(c, X86_FEATURE_XTOPOLOGY)) {
 		/*
diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c
index 3f46afbb1cf1..68b5d8681cbb 100644
--- a/arch/x86/kernel/cpu/intel_cacheinfo.c
+++ b/arch/x86/kernel/cpu/intel_cacheinfo.c
@@ -644,20 +644,17 @@ static inline ssize_t show_shared_cpu_list(struct _cpuid4_info *leaf, char *buf)
 	return show_shared_cpu_map_func(leaf, 1, buf);
 }
 
-static ssize_t show_type(struct _cpuid4_info *this_leaf, char *buf) {
-	switch(this_leaf->eax.split.type) {
-	    case CACHE_TYPE_DATA:
+static ssize_t show_type(struct _cpuid4_info *this_leaf, char *buf)
+{
+	switch (this_leaf->eax.split.type) {
+	case CACHE_TYPE_DATA:
 		return sprintf(buf, "Data\n");
-		break;
-	    case CACHE_TYPE_INST:
+	case CACHE_TYPE_INST:
 		return sprintf(buf, "Instruction\n");
-		break;
-	    case CACHE_TYPE_UNIFIED:
+	case CACHE_TYPE_UNIFIED:
 		return sprintf(buf, "Unified\n");
-		break;
-	    default:
+	default:
 		return sprintf(buf, "Unknown\n");
-		break;
 	}
 }
 
diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c
index c78c04821ea1..1159e269e596 100644
--- a/arch/x86/kernel/cpu/mtrr/main.c
+++ b/arch/x86/kernel/cpu/mtrr/main.c
@@ -803,6 +803,7 @@ x86_get_mtrr_mem_range(struct res_range *range, int nr_range,
 }
 
 static struct res_range __initdata range[RANGE_NUM];
+static int __initdata nr_range;
 
 #ifdef CONFIG_MTRR_SANITIZER
 
@@ -1206,39 +1207,43 @@ struct mtrr_cleanup_result {
 #define PSHIFT		(PAGE_SHIFT - 10)
 
 static struct mtrr_cleanup_result __initdata result[NUM_RESULT];
-static struct res_range __initdata range_new[RANGE_NUM];
 static unsigned long __initdata min_loss_pfn[RANGE_NUM];
 
-static int __init mtrr_cleanup(unsigned address_bits)
+static void __init print_out_mtrr_range_state(void)
 {
-	unsigned long extra_remove_base, extra_remove_size;
-	unsigned long base, size, def, dummy;
-	mtrr_type type;
-	int nr_range, nr_range_new;
-	u64 chunk_size, gran_size;
-	unsigned long range_sums, range_sums_new;
-	int index_good;
-	int num_reg_good;
 	int i;
+	char start_factor = 'K', size_factor = 'K';
+	unsigned long start_base, size_base;
+	mtrr_type type;
 
-	/* extra one for all 0 */
-	int num[MTRR_NUM_TYPES + 1];
+	for (i = 0; i < num_var_ranges; i++) {
 
-	if (!is_cpu(INTEL) || enable_mtrr_cleanup < 1)
-		return 0;
-	rdmsr(MTRRdefType_MSR, def, dummy);
-	def &= 0xff;
-	if (def != MTRR_TYPE_UNCACHABLE)
-		return 0;
+		size_base = range_state[i].size_pfn << (PAGE_SHIFT - 10);
+		if (!size_base)
+			continue;
 
-	/* get it and store it aside */
-	memset(range_state, 0, sizeof(range_state));
-	for (i = 0; i < num_var_ranges; i++) {
-		mtrr_if->get(i, &base, &size, &type);
-		range_state[i].base_pfn = base;
-		range_state[i].size_pfn = size;
-		range_state[i].type = type;
+		size_base = to_size_factor(size_base, &size_factor),
+		start_base = range_state[i].base_pfn << (PAGE_SHIFT - 10);
+		start_base = to_size_factor(start_base, &start_factor),
+		type = range_state[i].type;
+
+		printk(KERN_DEBUG "reg %d, base: %ld%cB, range: %ld%cB, type %s\n",
+			i, start_base, start_factor,
+			size_base, size_factor,
+			(type == MTRR_TYPE_UNCACHABLE) ? "UC" :
+			    ((type == MTRR_TYPE_WRPROT) ? "WP" :
+			     ((type == MTRR_TYPE_WRBACK) ? "WB" : "Other"))
+			);
 	}
+}
+
+static int __init mtrr_need_cleanup(void)
+{
+	int i;
+	mtrr_type type;
+	unsigned long size;
+	/* extra one for all 0 */
+	int num[MTRR_NUM_TYPES + 1];
 
 	/* check entries number */
 	memset(num, 0, sizeof(num));
@@ -1263,29 +1268,133 @@ static int __init mtrr_cleanup(unsigned address_bits)
 		num_var_ranges - num[MTRR_NUM_TYPES])
 		return 0;
 
-	/* print original var MTRRs at first, for debugging: */
-	printk(KERN_DEBUG "original variable MTRRs\n");
-	for (i = 0; i < num_var_ranges; i++) {
-		char start_factor = 'K', size_factor = 'K';
-		unsigned long start_base, size_base;
+	return 1;
+}
 
-		size_base = range_state[i].size_pfn << (PAGE_SHIFT - 10);
-		if (!size_base)
-			continue;
+static unsigned long __initdata range_sums;
+static void __init mtrr_calc_range_state(u64 chunk_size, u64 gran_size,
+					 unsigned long extra_remove_base,
+					 unsigned long extra_remove_size,
+					 int i)
+{
+	int num_reg;
+	static struct res_range range_new[RANGE_NUM];
+	static int nr_range_new;
+	unsigned long range_sums_new;
+
+	/* convert ranges to var ranges state */
+	num_reg = x86_setup_var_mtrrs(range, nr_range,
+						chunk_size, gran_size);
+
+	/* we got new setting in range_state, check it */
+	memset(range_new, 0, sizeof(range_new));
+	nr_range_new = x86_get_mtrr_mem_range(range_new, 0,
+				extra_remove_base, extra_remove_size);
+	range_sums_new = sum_ranges(range_new, nr_range_new);
+
+	result[i].chunk_sizek = chunk_size >> 10;
+	result[i].gran_sizek = gran_size >> 10;
+	result[i].num_reg = num_reg;
+	if (range_sums < range_sums_new) {
+		result[i].lose_cover_sizek =
+			(range_sums_new - range_sums) << PSHIFT;
+		result[i].bad = 1;
+	} else
+		result[i].lose_cover_sizek =
+			(range_sums - range_sums_new) << PSHIFT;
 
-		size_base = to_size_factor(size_base, &size_factor),
-		start_base = range_state[i].base_pfn << (PAGE_SHIFT - 10);
-		start_base = to_size_factor(start_base, &start_factor),
-		type = range_state[i].type;
+	/* double check it */
+	if (!result[i].bad && !result[i].lose_cover_sizek) {
+		if (nr_range_new != nr_range ||
+			memcmp(range, range_new, sizeof(range)))
+				result[i].bad = 1;
+	}
 
-		printk(KERN_DEBUG "reg %d, base: %ld%cB, range: %ld%cB, type %s\n",
-			i, start_base, start_factor,
-			size_base, size_factor,
-			(type == MTRR_TYPE_UNCACHABLE) ? "UC" :
-			    ((type == MTRR_TYPE_WRPROT) ? "WP" :
-			     ((type == MTRR_TYPE_WRBACK) ? "WB" : "Other"))
-			);
+	if (!result[i].bad && (range_sums - range_sums_new <
+				min_loss_pfn[num_reg])) {
+		min_loss_pfn[num_reg] =
+			range_sums - range_sums_new;
 	}
+}
+
+static void __init mtrr_print_out_one_result(int i)
+{
+	char gran_factor, chunk_factor, lose_factor;
+	unsigned long gran_base, chunk_base, lose_base;
+
+	gran_base = to_size_factor(result[i].gran_sizek, &gran_factor),
+	chunk_base = to_size_factor(result[i].chunk_sizek, &chunk_factor),
+	lose_base = to_size_factor(result[i].lose_cover_sizek, &lose_factor),
+	printk(KERN_INFO "%sgran_size: %ld%c \tchunk_size: %ld%c \t",
+			result[i].bad ? "*BAD*" : " ",
+			gran_base, gran_factor, chunk_base, chunk_factor);
+	printk(KERN_CONT "num_reg: %d  \tlose cover RAM: %s%ld%c\n",
+			result[i].num_reg, result[i].bad ? "-" : "",
+			lose_base, lose_factor);
+}
+
+static int __init mtrr_search_optimal_index(void)
+{
+	int i;
+	int num_reg_good;
+	int index_good;
+
+	if (nr_mtrr_spare_reg >= num_var_ranges)
+		nr_mtrr_spare_reg = num_var_ranges - 1;
+	num_reg_good = -1;
+	for (i = num_var_ranges - nr_mtrr_spare_reg; i > 0; i--) {
+		if (!min_loss_pfn[i])
+			num_reg_good = i;
+	}
+
+	index_good = -1;
+	if (num_reg_good != -1) {
+		for (i = 0; i < NUM_RESULT; i++) {
+			if (!result[i].bad &&
+			    result[i].num_reg == num_reg_good &&
+			    !result[i].lose_cover_sizek) {
+				index_good = i;
+				break;
+			}
+		}
+	}
+
+	return index_good;
+}
+
+
+static int __init mtrr_cleanup(unsigned address_bits)
+{
+	unsigned long extra_remove_base, extra_remove_size;
+	unsigned long base, size, def, dummy;
+	mtrr_type type;
+	u64 chunk_size, gran_size;
+	int index_good;
+	int i;
+
+	if (!is_cpu(INTEL) || enable_mtrr_cleanup < 1)
+		return 0;
+	rdmsr(MTRRdefType_MSR, def, dummy);
+	def &= 0xff;
+	if (def != MTRR_TYPE_UNCACHABLE)
+		return 0;
+
+	/* get it and store it aside */
+	memset(range_state, 0, sizeof(range_state));
+	for (i = 0; i < num_var_ranges; i++) {
+		mtrr_if->get(i, &base, &size, &type);
+		range_state[i].base_pfn = base;
+		range_state[i].size_pfn = size;
+		range_state[i].type = type;
+	}
+
+	/* check if we need handle it and can handle it */
+	if (!mtrr_need_cleanup())
+		return 0;
+
+	/* print original var MTRRs at first, for debugging: */
+	printk(KERN_DEBUG "original variable MTRRs\n");
+	print_out_mtrr_range_state();
 
 	memset(range, 0, sizeof(range));
 	extra_remove_size = 0;
@@ -1309,176 +1418,64 @@ static int __init mtrr_cleanup(unsigned address_bits)
 	       range_sums >> (20 - PAGE_SHIFT));
 
 	if (mtrr_chunk_size && mtrr_gran_size) {
-		int num_reg;
-		char gran_factor, chunk_factor, lose_factor;
-		unsigned long gran_base, chunk_base, lose_base;
-
-		debug_print++;
-		/* convert ranges to var ranges state */
-		num_reg = x86_setup_var_mtrrs(range, nr_range, mtrr_chunk_size,
-					      mtrr_gran_size);
+		i = 0;
+		mtrr_calc_range_state(mtrr_chunk_size, mtrr_gran_size,
+				      extra_remove_base, extra_remove_size, i);
 
-		/* we got new setting in range_state, check it */
-		memset(range_new, 0, sizeof(range_new));
-		nr_range_new = x86_get_mtrr_mem_range(range_new, 0,
-						      extra_remove_base,
-						      extra_remove_size);
-		range_sums_new = sum_ranges(range_new, nr_range_new);
+		mtrr_print_out_one_result(i);
 
-		i = 0;
-		result[i].chunk_sizek = mtrr_chunk_size >> 10;
-		result[i].gran_sizek = mtrr_gran_size >> 10;
-		result[i].num_reg = num_reg;
-		if (range_sums < range_sums_new) {
-			result[i].lose_cover_sizek =
-				(range_sums_new - range_sums) << PSHIFT;
-			result[i].bad = 1;
-		} else
-			result[i].lose_cover_sizek =
-				(range_sums - range_sums_new) << PSHIFT;
-
-		gran_base = to_size_factor(result[i].gran_sizek, &gran_factor),
-		chunk_base = to_size_factor(result[i].chunk_sizek, &chunk_factor),
-		lose_base = to_size_factor(result[i].lose_cover_sizek, &lose_factor),
-		printk(KERN_INFO "%sgran_size: %ld%c \tchunk_size: %ld%c \t",
-			 result[i].bad?"*BAD*":" ",
-			 gran_base, gran_factor, chunk_base, chunk_factor);
-		printk(KERN_CONT "num_reg: %d  \tlose cover RAM: %s%ld%c\n",
-			 result[i].num_reg, result[i].bad?"-":"",
-			 lose_base, lose_factor);
 		if (!result[i].bad) {
 			set_var_mtrr_all(address_bits);
 			return 1;
 		}
 		printk(KERN_INFO "invalid mtrr_gran_size or mtrr_chunk_size, "
 		       "will find optimal one\n");
-		debug_print--;
-		memset(result, 0, sizeof(result[0]));
 	}
 
 	i = 0;
 	memset(min_loss_pfn, 0xff, sizeof(min_loss_pfn));
 	memset(result, 0, sizeof(result));
 	for (gran_size = (1ULL<<16); gran_size < (1ULL<<32); gran_size <<= 1) {
-		char gran_factor;
-		unsigned long gran_base;
-
-		if (debug_print)
-			gran_base = to_size_factor(gran_size >> 10, &gran_factor);
 
 		for (chunk_size = gran_size; chunk_size < (1ULL<<32);
 		     chunk_size <<= 1) {
-			int num_reg;
 
-			if (debug_print) {
-				char chunk_factor;
-				unsigned long chunk_base;
-
-				chunk_base = to_size_factor(chunk_size>>10, &chunk_factor),
-				printk(KERN_INFO "\n");
-				printk(KERN_INFO "gran_size: %ld%c   chunk_size: %ld%c \n",
-				       gran_base, gran_factor, chunk_base, chunk_factor);
-			}
 			if (i >= NUM_RESULT)
 				continue;
 
-			/* convert ranges to var ranges state */
-			num_reg = x86_setup_var_mtrrs(range, nr_range,
-							 chunk_size, gran_size);
-
-			/* we got new setting in range_state, check it */
-			memset(range_new, 0, sizeof(range_new));
-			nr_range_new = x86_get_mtrr_mem_range(range_new, 0,
-					 extra_remove_base, extra_remove_size);
-			range_sums_new = sum_ranges(range_new, nr_range_new);
-
-			result[i].chunk_sizek = chunk_size >> 10;
-			result[i].gran_sizek = gran_size >> 10;
-			result[i].num_reg = num_reg;
-			if (range_sums < range_sums_new) {
-				result[i].lose_cover_sizek =
-					(range_sums_new - range_sums) << PSHIFT;
-				result[i].bad = 1;
-			} else
-				result[i].lose_cover_sizek =
-					(range_sums - range_sums_new) << PSHIFT;
-
-			/* double check it */
-			if (!result[i].bad && !result[i].lose_cover_sizek) {
-				if (nr_range_new != nr_range ||
-					memcmp(range, range_new, sizeof(range)))
-						result[i].bad = 1;
+			mtrr_calc_range_state(chunk_size, gran_size,
+				      extra_remove_base, extra_remove_size, i);
+			if (debug_print) {
+				mtrr_print_out_one_result(i);
+				printk(KERN_INFO "\n");
 			}
 
-			if (!result[i].bad && (range_sums - range_sums_new <
-					       min_loss_pfn[num_reg])) {
-				min_loss_pfn[num_reg] =
-					range_sums - range_sums_new;
-			}
 			i++;
 		}
 	}
 
-	/* print out all */
-	for (i = 0; i < NUM_RESULT; i++) {
-		char gran_factor, chunk_factor, lose_factor;
-		unsigned long gran_base, chunk_base, lose_base;
-
-		gran_base = to_size_factor(result[i].gran_sizek, &gran_factor),
-		chunk_base = to_size_factor(result[i].chunk_sizek, &chunk_factor),
-		lose_base = to_size_factor(result[i].lose_cover_sizek, &lose_factor),
-		printk(KERN_INFO "%sgran_size: %ld%c \tchunk_size: %ld%c \t",
-			 result[i].bad?"*BAD*":" ",
-			 gran_base, gran_factor, chunk_base, chunk_factor);
-		printk(KERN_CONT "num_reg: %d  \tlose cover RAM: %s%ld%c\n",
-			 result[i].num_reg, result[i].bad?"-":"",
-			 lose_base, lose_factor);
-	}
-
 	/* try to find the optimal index */
-	if (nr_mtrr_spare_reg >= num_var_ranges)
-		nr_mtrr_spare_reg = num_var_ranges - 1;
-	num_reg_good = -1;
-	for (i = num_var_ranges - nr_mtrr_spare_reg; i > 0; i--) {
-		if (!min_loss_pfn[i])
-			num_reg_good = i;
-	}
-
-	index_good = -1;
-	if (num_reg_good != -1) {
-		for (i = 0; i < NUM_RESULT; i++) {
-			if (!result[i].bad &&
-			    result[i].num_reg == num_reg_good &&
-			    !result[i].lose_cover_sizek) {
-				index_good = i;
-				break;
-			}
-		}
-	}
+	index_good = mtrr_search_optimal_index();
 
 	if (index_good != -1) {
-		char gran_factor, chunk_factor, lose_factor;
-		unsigned long gran_base, chunk_base, lose_base;
-
 		printk(KERN_INFO "Found optimal setting for mtrr clean up\n");
 		i = index_good;
-		gran_base = to_size_factor(result[i].gran_sizek, &gran_factor),
-		chunk_base = to_size_factor(result[i].chunk_sizek, &chunk_factor),
-		lose_base = to_size_factor(result[i].lose_cover_sizek, &lose_factor),
-		printk(KERN_INFO "gran_size: %ld%c \tchunk_size: %ld%c \t",
-			 gran_base, gran_factor, chunk_base, chunk_factor);
-		printk(KERN_CONT "num_reg: %d  \tlose RAM: %ld%c\n",
-			 result[i].num_reg, lose_base, lose_factor);
+		mtrr_print_out_one_result(i);
+
 		/* convert ranges to var ranges state */
 		chunk_size = result[i].chunk_sizek;
 		chunk_size <<= 10;
 		gran_size = result[i].gran_sizek;
 		gran_size <<= 10;
-		debug_print++;
 		x86_setup_var_mtrrs(range, nr_range, chunk_size, gran_size);
-		debug_print--;
 		set_var_mtrr_all(address_bits);
+		printk(KERN_DEBUG "New variable MTRRs\n");
+		print_out_mtrr_range_state();
 		return 1;
+	} else {
+		/* print out all */
+		for (i = 0; i < NUM_RESULT; i++)
+			mtrr_print_out_one_result(i);
 	}
 
 	printk(KERN_INFO "mtrr_cleanup: can not find optimal value\n");
@@ -1562,7 +1559,6 @@ int __init mtrr_trim_uncached_memory(unsigned long end_pfn)
 {
 	unsigned long i, base, size, highest_pfn = 0, def, dummy;
 	mtrr_type type;
-	int nr_range;
 	u64 total_trim_size;
 
 	/* extra one for all 0 */
diff --git a/arch/x86/kernel/cpu/vmware.c b/arch/x86/kernel/cpu/vmware.c
new file mode 100644
index 000000000000..284c399e3234
--- /dev/null
+++ b/arch/x86/kernel/cpu/vmware.c
@@ -0,0 +1,112 @@
+/*
+ * VMware Detection code.
+ *
+ * Copyright (C) 2008, VMware, Inc.
+ * Author : Alok N Kataria <akataria@vmware.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
+ * NON INFRINGEMENT.  See the GNU General Public License for more
+ * details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
+ *
+ */
+
+#include <linux/dmi.h>
+#include <asm/div64.h>
+#include <asm/vmware.h>
+
+#define CPUID_VMWARE_INFO_LEAF	0x40000000
+#define VMWARE_HYPERVISOR_MAGIC	0x564D5868
+#define VMWARE_HYPERVISOR_PORT	0x5658
+
+#define VMWARE_PORT_CMD_GETVERSION	10
+#define VMWARE_PORT_CMD_GETHZ		45
+
+#define VMWARE_PORT(cmd, eax, ebx, ecx, edx)				\
+	__asm__("inl (%%dx)" :						\
+			"=a"(eax), "=c"(ecx), "=d"(edx), "=b"(ebx) :	\
+			"0"(VMWARE_HYPERVISOR_MAGIC),			\
+			"1"(VMWARE_PORT_CMD_##cmd),			\
+			"2"(VMWARE_HYPERVISOR_PORT), "3"(UINT_MAX) :	\
+			"memory");
+
+static inline int __vmware_platform(void)
+{
+	uint32_t eax, ebx, ecx, edx;
+	VMWARE_PORT(GETVERSION, eax, ebx, ecx, edx);
+	return eax != (uint32_t)-1 && ebx == VMWARE_HYPERVISOR_MAGIC;
+}
+
+static unsigned long __vmware_get_tsc_khz(void)
+{
+        uint64_t tsc_hz;
+        uint32_t eax, ebx, ecx, edx;
+
+        VMWARE_PORT(GETHZ, eax, ebx, ecx, edx);
+
+        if (ebx == UINT_MAX)
+                return 0;
+        tsc_hz = eax | (((uint64_t)ebx) << 32);
+        do_div(tsc_hz, 1000);
+        BUG_ON(tsc_hz >> 32);
+        return tsc_hz;
+}
+
+/*
+ * While checking the dmi string infomation, just checking the product
+ * serial key should be enough, as this will always have a VMware
+ * specific string when running under VMware hypervisor.
+ */
+int vmware_platform(void)
+{
+	if (cpu_has_hypervisor) {
+		unsigned int eax, ebx, ecx, edx;
+		char hyper_vendor_id[13];
+
+		cpuid(CPUID_VMWARE_INFO_LEAF, &eax, &ebx, &ecx, &edx);
+		memcpy(hyper_vendor_id + 0, &ebx, 4);
+		memcpy(hyper_vendor_id + 4, &ecx, 4);
+		memcpy(hyper_vendor_id + 8, &edx, 4);
+		hyper_vendor_id[12] = '\0';
+		if (!strcmp(hyper_vendor_id, "VMwareVMware"))
+			return 1;
+	} else if (dmi_available && dmi_name_in_serial("VMware") &&
+		   __vmware_platform())
+		return 1;
+
+	return 0;
+}
+
+unsigned long vmware_get_tsc_khz(void)
+{
+	BUG_ON(!vmware_platform());
+	return __vmware_get_tsc_khz();
+}
+
+/*
+ * VMware hypervisor takes care of exporting a reliable TSC to the guest.
+ * Still, due to timing difference when running on virtual cpus, the TSC can
+ * be marked as unstable in some cases. For example, the TSC sync check at
+ * bootup can fail due to a marginal offset between vcpus' TSCs (though the
+ * TSCs do not drift from each other).  Also, the ACPI PM timer clocksource
+ * is not suitable as a watchdog when running on a hypervisor because the
+ * kernel may miss a wrap of the counter if the vcpu is descheduled for a
+ * long time. To skip these checks at runtime we set these capability bits,
+ * so that the kernel could just trust the hypervisor with providing a
+ * reliable virtual TSC that is suitable for timekeeping.
+ */
+void __cpuinit vmware_set_feature_bits(struct cpuinfo_x86 *c)
+{
+	set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
+	set_cpu_cap(c, X86_FEATURE_TSC_RELIABLE);
+}
diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c
index 268553817909..d84a852e4cd7 100644
--- a/arch/x86/kernel/crash.c
+++ b/arch/x86/kernel/crash.c
@@ -29,34 +29,17 @@
 
 #include <mach_ipi.h>
 
-/* This keeps a track of which one is crashing cpu. */
-static int crashing_cpu;
 
 #if defined(CONFIG_SMP) && defined(CONFIG_X86_LOCAL_APIC)
-static atomic_t waiting_for_crash_ipi;
 
-static int crash_nmi_callback(struct notifier_block *self,
-			unsigned long val, void *data)
+static void kdump_nmi_callback(int cpu, struct die_args *args)
 {
 	struct pt_regs *regs;
 #ifdef CONFIG_X86_32
 	struct pt_regs fixed_regs;
 #endif
-	int cpu;
 
-	if (val != DIE_NMI_IPI)
-		return NOTIFY_OK;
-
-	regs = ((struct die_args *)data)->regs;
-	cpu = raw_smp_processor_id();
-
-	/* Don't do anything if this handler is invoked on crashing cpu.
-	 * Otherwise, system will completely hang. Crashing cpu can get
-	 * an NMI if system was initially booted with nmi_watchdog parameter.
-	 */
-	if (cpu == crashing_cpu)
-		return NOTIFY_STOP;
-	local_irq_disable();
+	regs = args->regs;
 
 #ifdef CONFIG_X86_32
 	if (!user_mode_vm(regs)) {
@@ -65,54 +48,19 @@ static int crash_nmi_callback(struct notifier_block *self,
 	}
 #endif
 	crash_save_cpu(regs, cpu);
-	disable_local_APIC();
-	atomic_dec(&waiting_for_crash_ipi);
-	/* Assume hlt works */
-	halt();
-	for (;;)
-		cpu_relax();
-
-	return 1;
-}
 
-static void smp_send_nmi_allbutself(void)
-{
-	cpumask_t mask = cpu_online_map;
-	cpu_clear(safe_smp_processor_id(), mask);
-	if (!cpus_empty(mask))
-		send_IPI_mask(mask, NMI_VECTOR);
+	disable_local_APIC();
 }
 
-static struct notifier_block crash_nmi_nb = {
-	.notifier_call = crash_nmi_callback,
-};
-
-static void nmi_shootdown_cpus(void)
+static void kdump_nmi_shootdown_cpus(void)
 {
-	unsigned long msecs;
-
-	atomic_set(&waiting_for_crash_ipi, num_online_cpus() - 1);
-	/* Would it be better to replace the trap vector here? */
-	if (register_die_notifier(&crash_nmi_nb))
-		return;		/* return what? */
-	/* Ensure the new callback function is set before sending
-	 * out the NMI
-	 */
-	wmb();
+	nmi_shootdown_cpus(kdump_nmi_callback);
 
-	smp_send_nmi_allbutself();
-
-	msecs = 1000; /* Wait at most a second for the other cpus to stop */
-	while ((atomic_read(&waiting_for_crash_ipi) > 0) && msecs) {
-		mdelay(1);
-		msecs--;
-	}
-
-	/* Leave the nmi callback set */
 	disable_local_APIC();
 }
+
 #else
-static void nmi_shootdown_cpus(void)
+static void kdump_nmi_shootdown_cpus(void)
 {
 	/* There are no cpus to shootdown */
 }
@@ -131,9 +79,7 @@ void native_machine_crash_shutdown(struct pt_regs *regs)
 	/* The kernel is broken so disable interrupts */
 	local_irq_disable();
 
-	/* Make a note of crashing cpu. Will be used in NMI callback.*/
-	crashing_cpu = safe_smp_processor_id();
-	nmi_shootdown_cpus();
+	kdump_nmi_shootdown_cpus();
 	lapic_shutdown();
 #if defined(CONFIG_X86_IO_APIC)
 	disable_IO_APIC();
diff --git a/arch/x86/kernel/ds.c b/arch/x86/kernel/ds.c
index a2d1176c38ee..d6938d9351cf 100644
--- a/arch/x86/kernel/ds.c
+++ b/arch/x86/kernel/ds.c
@@ -847,17 +847,16 @@ void __cpuinit ds_init_intel(struct cpuinfo_x86 *c)
 	switch (c->x86) {
 	case 0x6:
 		switch (c->x86_model) {
+		case 0 ... 0xC:
+			/* sorry, don't know about them */
+			break;
 		case 0xD:
 		case 0xE: /* Pentium M */
 			ds_configure(&ds_cfg_var);
 			break;
-		case 0xF: /* Core2 */
-		case 0x1C: /* Atom */
+		default: /* Core2, Atom, ... */
 			ds_configure(&ds_cfg_64);
 			break;
-		default:
-			/* sorry, don't know about them */
-			break;
 		}
 		break;
 	case 0xF:
diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c
new file mode 100644
index 000000000000..5962176dfabb
--- /dev/null
+++ b/arch/x86/kernel/dumpstack.c
@@ -0,0 +1,319 @@
+/*
+ *  Copyright (C) 1991, 1992  Linus Torvalds
+ *  Copyright (C) 2000, 2001, 2002 Andi Kleen, SuSE Labs
+ */
+#include <linux/kallsyms.h>
+#include <linux/kprobes.h>
+#include <linux/uaccess.h>
+#include <linux/utsname.h>
+#include <linux/hardirq.h>
+#include <linux/kdebug.h>
+#include <linux/module.h>
+#include <linux/ptrace.h>
+#include <linux/kexec.h>
+#include <linux/bug.h>
+#include <linux/nmi.h>
+#include <linux/sysfs.h>
+
+#include <asm/stacktrace.h>
+
+#include "dumpstack.h"
+
+int panic_on_unrecovered_nmi;
+unsigned int code_bytes = 64;
+int kstack_depth_to_print = 3 * STACKSLOTS_PER_LINE;
+static int die_counter;
+
+void printk_address(unsigned long address, int reliable)
+{
+	printk(" [<%p>] %s%pS\n", (void *) address,
+			reliable ? "" : "? ", (void *) address);
+}
+
+/*
+ * x86-64 can have up to three kernel stacks:
+ * process stack
+ * interrupt stack
+ * severe exception (double fault, nmi, stack fault, debug, mce) hardware stack
+ */
+
+static inline int valid_stack_ptr(struct thread_info *tinfo,
+			void *p, unsigned int size, void *end)
+{
+	void *t = tinfo;
+	if (end) {
+		if (p < end && p >= (end-THREAD_SIZE))
+			return 1;
+		else
+			return 0;
+	}
+	return p > t && p < t + THREAD_SIZE - size;
+}
+
+unsigned long
+print_context_stack(struct thread_info *tinfo,
+		unsigned long *stack, unsigned long bp,
+		const struct stacktrace_ops *ops, void *data,
+		unsigned long *end)
+{
+	struct stack_frame *frame = (struct stack_frame *)bp;
+
+	while (valid_stack_ptr(tinfo, stack, sizeof(*stack), end)) {
+		unsigned long addr;
+
+		addr = *stack;
+		if (__kernel_text_address(addr)) {
+			if ((unsigned long) stack == bp + sizeof(long)) {
+				ops->address(data, addr, 1);
+				frame = frame->next_frame;
+				bp = (unsigned long) frame;
+			} else {
+				ops->address(data, addr, bp == 0);
+			}
+		}
+		stack++;
+	}
+	return bp;
+}
+
+
+static void
+print_trace_warning_symbol(void *data, char *msg, unsigned long symbol)
+{
+	printk(data);
+	print_symbol(msg, symbol);
+	printk("\n");
+}
+
+static void print_trace_warning(void *data, char *msg)
+{
+	printk("%s%s\n", (char *)data, msg);
+}
+
+static int print_trace_stack(void *data, char *name)
+{
+	printk("%s <%s> ", (char *)data, name);
+	return 0;
+}
+
+/*
+ * Print one address/symbol entries per line.
+ */
+static void print_trace_address(void *data, unsigned long addr, int reliable)
+{
+	touch_nmi_watchdog();
+	printk(data);
+	printk_address(addr, reliable);
+}
+
+static const struct stacktrace_ops print_trace_ops = {
+	.warning = print_trace_warning,
+	.warning_symbol = print_trace_warning_symbol,
+	.stack = print_trace_stack,
+	.address = print_trace_address,
+};
+
+void
+show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs,
+		unsigned long *stack, unsigned long bp, char *log_lvl)
+{
+	printk("%sCall Trace:\n", log_lvl);
+	dump_trace(task, regs, stack, bp, &print_trace_ops, log_lvl);
+}
+
+void show_trace(struct task_struct *task, struct pt_regs *regs,
+		unsigned long *stack, unsigned long bp)
+{
+	show_trace_log_lvl(task, regs, stack, bp, "");
+}
+
+void show_stack(struct task_struct *task, unsigned long *sp)
+{
+	show_stack_log_lvl(task, NULL, sp, 0, "");
+}
+
+/*
+ * The architecture-independent dump_stack generator
+ */
+void dump_stack(void)
+{
+	unsigned long bp = 0;
+	unsigned long stack;
+
+#ifdef CONFIG_FRAME_POINTER
+	if (!bp)
+		get_bp(bp);
+#endif
+
+	printk("Pid: %d, comm: %.20s %s %s %.*s\n",
+		current->pid, current->comm, print_tainted(),
+		init_utsname()->release,
+		(int)strcspn(init_utsname()->version, " "),
+		init_utsname()->version);
+	show_trace(NULL, NULL, &stack, bp);
+}
+EXPORT_SYMBOL(dump_stack);
+
+static raw_spinlock_t die_lock = __RAW_SPIN_LOCK_UNLOCKED;
+static int die_owner = -1;
+static unsigned int die_nest_count;
+
+unsigned __kprobes long oops_begin(void)
+{
+	int cpu;
+	unsigned long flags;
+
+	oops_enter();
+
+	/* racy, but better than risking deadlock. */
+	raw_local_irq_save(flags);
+	cpu = smp_processor_id();
+	if (!__raw_spin_trylock(&die_lock)) {
+		if (cpu == die_owner)
+			/* nested oops. should stop eventually */;
+		else
+			__raw_spin_lock(&die_lock);
+	}
+	die_nest_count++;
+	die_owner = cpu;
+	console_verbose();
+	bust_spinlocks(1);
+	return flags;
+}
+
+void __kprobes oops_end(unsigned long flags, struct pt_regs *regs, int signr)
+{
+	if (regs && kexec_should_crash(current))
+		crash_kexec(regs);
+
+	bust_spinlocks(0);
+	die_owner = -1;
+	add_taint(TAINT_DIE);
+	die_nest_count--;
+	if (!die_nest_count)
+		/* Nest count reaches zero, release the lock. */
+		__raw_spin_unlock(&die_lock);
+	raw_local_irq_restore(flags);
+	oops_exit();
+
+	if (!signr)
+		return;
+	if (in_interrupt())
+		panic("Fatal exception in interrupt");
+	if (panic_on_oops)
+		panic("Fatal exception");
+	do_exit(signr);
+}
+
+int __kprobes __die(const char *str, struct pt_regs *regs, long err)
+{
+#ifdef CONFIG_X86_32
+	unsigned short ss;
+	unsigned long sp;
+#endif
+	printk(KERN_EMERG "%s: %04lx [#%d] ", str, err & 0xffff, ++die_counter);
+#ifdef CONFIG_PREEMPT
+	printk("PREEMPT ");
+#endif
+#ifdef CONFIG_SMP
+	printk("SMP ");
+#endif
+#ifdef CONFIG_DEBUG_PAGEALLOC
+	printk("DEBUG_PAGEALLOC");
+#endif
+	printk("\n");
+	sysfs_printk_last_file();
+	if (notify_die(DIE_OOPS, str, regs, err,
+			current->thread.trap_no, SIGSEGV) == NOTIFY_STOP)
+		return 1;
+
+	show_registers(regs);
+#ifdef CONFIG_X86_32
+	sp = (unsigned long) (&regs->sp);
+	savesegment(ss, ss);
+	if (user_mode(regs)) {
+		sp = regs->sp;
+		ss = regs->ss & 0xffff;
+	}
+	printk(KERN_EMERG "EIP: [<%08lx>] ", regs->ip);
+	print_symbol("%s", regs->ip);
+	printk(" SS:ESP %04x:%08lx\n", ss, sp);
+#else
+	/* Executive summary in case the oops scrolled away */
+	printk(KERN_ALERT "RIP ");
+	printk_address(regs->ip, 1);
+	printk(" RSP <%016lx>\n", regs->sp);
+#endif
+	return 0;
+}
+
+/*
+ * This is gone through when something in the kernel has done something bad
+ * and is about to be terminated:
+ */
+void die(const char *str, struct pt_regs *regs, long err)
+{
+	unsigned long flags = oops_begin();
+	int sig = SIGSEGV;
+
+	if (!user_mode_vm(regs))
+		report_bug(regs->ip, regs);
+
+	if (__die(str, regs, err))
+		sig = 0;
+	oops_end(flags, regs, sig);
+}
+
+void notrace __kprobes
+die_nmi(char *str, struct pt_regs *regs, int do_panic)
+{
+	unsigned long flags;
+
+	if (notify_die(DIE_NMIWATCHDOG, str, regs, 0, 2, SIGINT) == NOTIFY_STOP)
+		return;
+
+	/*
+	 * We are in trouble anyway, lets at least try
+	 * to get a message out.
+	 */
+	flags = oops_begin();
+	printk(KERN_EMERG "%s", str);
+	printk(" on CPU%d, ip %08lx, registers:\n",
+		smp_processor_id(), regs->ip);
+	show_registers(regs);
+	oops_end(flags, regs, 0);
+	if (do_panic || panic_on_oops)
+		panic("Non maskable interrupt");
+	nmi_exit();
+	local_irq_enable();
+	do_exit(SIGBUS);
+}
+
+static int __init oops_setup(char *s)
+{
+	if (!s)
+		return -EINVAL;
+	if (!strcmp(s, "panic"))
+		panic_on_oops = 1;
+	return 0;
+}
+early_param("oops", oops_setup);
+
+static int __init kstack_setup(char *s)
+{
+	if (!s)
+		return -EINVAL;
+	kstack_depth_to_print = simple_strtoul(s, NULL, 0);
+	return 0;
+}
+early_param("kstack", kstack_setup);
+
+static int __init code_bytes_setup(char *s)
+{
+	code_bytes = simple_strtoul(s, NULL, 0);
+	if (code_bytes > 8192)
+		code_bytes = 8192;
+
+	return 1;
+}
+__setup("code_bytes=", code_bytes_setup);
diff --git a/arch/x86/kernel/dumpstack.h b/arch/x86/kernel/dumpstack.h
new file mode 100644
index 000000000000..3119a801c32b
--- /dev/null
+++ b/arch/x86/kernel/dumpstack.h
@@ -0,0 +1,39 @@
+/*
+ *  Copyright (C) 1991, 1992  Linus Torvalds
+ *  Copyright (C) 2000, 2001, 2002 Andi Kleen, SuSE Labs
+ */
+
+#ifndef DUMPSTACK_H
+#define DUMPSTACK_H
+
+#ifdef CONFIG_X86_32
+#define STACKSLOTS_PER_LINE 8
+#define get_bp(bp) asm("movl %%ebp, %0" : "=r" (bp) :)
+#else
+#define STACKSLOTS_PER_LINE 4
+#define get_bp(bp) asm("movq %%rbp, %0" : "=r" (bp) :)
+#endif
+
+extern unsigned long
+print_context_stack(struct thread_info *tinfo,
+		unsigned long *stack, unsigned long bp,
+		const struct stacktrace_ops *ops, void *data,
+		unsigned long *end);
+
+extern void
+show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs,
+		unsigned long *stack, unsigned long bp, char *log_lvl);
+
+extern void
+show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs,
+		unsigned long *sp, unsigned long bp, char *log_lvl);
+
+extern unsigned int code_bytes;
+extern int kstack_depth_to_print;
+
+/* The form of the top of the frame on the stack */
+struct stack_frame {
+	struct stack_frame *next_frame;
+	unsigned long return_address;
+};
+#endif
diff --git a/arch/x86/kernel/dumpstack_32.c b/arch/x86/kernel/dumpstack_32.c
index b3614752197b..7b031b106ec8 100644
--- a/arch/x86/kernel/dumpstack_32.c
+++ b/arch/x86/kernel/dumpstack_32.c
@@ -17,64 +17,7 @@
 
 #include <asm/stacktrace.h>
 
-#define STACKSLOTS_PER_LINE 8
-#define get_bp(bp) asm("movl %%ebp, %0" : "=r" (bp) :)
-
-int panic_on_unrecovered_nmi;
-int kstack_depth_to_print = 3 * STACKSLOTS_PER_LINE;
-static unsigned int code_bytes = 64;
-static int die_counter;
-
-void printk_address(unsigned long address, int reliable)
-{
-	printk(" [<%p>] %s%pS\n", (void *) address,
-			reliable ? "" : "? ", (void *) address);
-}
-
-static inline int valid_stack_ptr(struct thread_info *tinfo,
-			void *p, unsigned int size, void *end)
-{
-	void *t = tinfo;
-	if (end) {
-		if (p < end && p >= (end-THREAD_SIZE))
-			return 1;
-		else
-			return 0;
-	}
-	return p > t && p < t + THREAD_SIZE - size;
-}
-
-/* The form of the top of the frame on the stack */
-struct stack_frame {
-	struct stack_frame *next_frame;
-	unsigned long return_address;
-};
-
-static inline unsigned long
-print_context_stack(struct thread_info *tinfo,
-		unsigned long *stack, unsigned long bp,
-		const struct stacktrace_ops *ops, void *data,
-		unsigned long *end)
-{
-	struct stack_frame *frame = (struct stack_frame *)bp;
-
-	while (valid_stack_ptr(tinfo, stack, sizeof(*stack), end)) {
-		unsigned long addr;
-
-		addr = *stack;
-		if (__kernel_text_address(addr)) {
-			if ((unsigned long) stack == bp + sizeof(long)) {
-				ops->address(data, addr, 1);
-				frame = frame->next_frame;
-				bp = (unsigned long) frame;
-			} else {
-				ops->address(data, addr, bp == 0);
-			}
-		}
-		stack++;
-	}
-	return bp;
-}
+#include "dumpstack.h"
 
 void dump_trace(struct task_struct *task, struct pt_regs *regs,
 		unsigned long *stack, unsigned long bp,
@@ -119,57 +62,7 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs,
 }
 EXPORT_SYMBOL(dump_trace);
 
-static void
-print_trace_warning_symbol(void *data, char *msg, unsigned long symbol)
-{
-	printk(data);
-	print_symbol(msg, symbol);
-	printk("\n");
-}
-
-static void print_trace_warning(void *data, char *msg)
-{
-	printk("%s%s\n", (char *)data, msg);
-}
-
-static int print_trace_stack(void *data, char *name)
-{
-	printk("%s <%s> ", (char *)data, name);
-	return 0;
-}
-
-/*
- * Print one address/symbol entries per line.
- */
-static void print_trace_address(void *data, unsigned long addr, int reliable)
-{
-	touch_nmi_watchdog();
-	printk(data);
-	printk_address(addr, reliable);
-}
-
-static const struct stacktrace_ops print_trace_ops = {
-	.warning = print_trace_warning,
-	.warning_symbol = print_trace_warning_symbol,
-	.stack = print_trace_stack,
-	.address = print_trace_address,
-};
-
-static void
-show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs,
-		unsigned long *stack, unsigned long bp, char *log_lvl)
-{
-	printk("%sCall Trace:\n", log_lvl);
-	dump_trace(task, regs, stack, bp, &print_trace_ops, log_lvl);
-}
-
-void show_trace(struct task_struct *task, struct pt_regs *regs,
-		unsigned long *stack, unsigned long bp)
-{
-	show_trace_log_lvl(task, regs, stack, bp, "");
-}
-
-static void
+void
 show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs,
 		unsigned long *sp, unsigned long bp, char *log_lvl)
 {
@@ -196,33 +89,6 @@ show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs,
 	show_trace_log_lvl(task, regs, sp, bp, log_lvl);
 }
 
-void show_stack(struct task_struct *task, unsigned long *sp)
-{
-	show_stack_log_lvl(task, NULL, sp, 0, "");
-}
-
-/*
- * The architecture-independent dump_stack generator
- */
-void dump_stack(void)
-{
-	unsigned long bp = 0;
-	unsigned long stack;
-
-#ifdef CONFIG_FRAME_POINTER
-	if (!bp)
-		get_bp(bp);
-#endif
-
-	printk("Pid: %d, comm: %.20s %s %s %.*s\n",
-		current->pid, current->comm, print_tainted(),
-		init_utsname()->release,
-		(int)strcspn(init_utsname()->version, " "),
-		init_utsname()->version);
-	show_trace(NULL, NULL, &stack, bp);
-}
-
-EXPORT_SYMBOL(dump_stack);
 
 void show_registers(struct pt_regs *regs)
 {
@@ -283,167 +149,3 @@ int is_valid_bugaddr(unsigned long ip)
 	return ud2 == 0x0b0f;
 }
 
-static raw_spinlock_t die_lock = __RAW_SPIN_LOCK_UNLOCKED;
-static int die_owner = -1;
-static unsigned int die_nest_count;
-
-unsigned __kprobes long oops_begin(void)
-{
-	unsigned long flags;
-
-	oops_enter();
-
-	if (die_owner != raw_smp_processor_id()) {
-		console_verbose();
-		raw_local_irq_save(flags);
-		__raw_spin_lock(&die_lock);
-		die_owner = smp_processor_id();
-		die_nest_count = 0;
-		bust_spinlocks(1);
-	} else {
-		raw_local_irq_save(flags);
-	}
-	die_nest_count++;
-	return flags;
-}
-
-void __kprobes oops_end(unsigned long flags, struct pt_regs *regs, int signr)
-{
-	bust_spinlocks(0);
-	die_owner = -1;
-	add_taint(TAINT_DIE);
-	__raw_spin_unlock(&die_lock);
-	raw_local_irq_restore(flags);
-
-	if (!regs)
-		return;
-
-	if (kexec_should_crash(current))
-		crash_kexec(regs);
-	if (in_interrupt())
-		panic("Fatal exception in interrupt");
-	if (panic_on_oops)
-		panic("Fatal exception");
-	oops_exit();
-	do_exit(signr);
-}
-
-int __kprobes __die(const char *str, struct pt_regs *regs, long err)
-{
-	unsigned short ss;
-	unsigned long sp;
-
-	printk(KERN_EMERG "%s: %04lx [#%d] ", str, err & 0xffff, ++die_counter);
-#ifdef CONFIG_PREEMPT
-	printk("PREEMPT ");
-#endif
-#ifdef CONFIG_SMP
-	printk("SMP ");
-#endif
-#ifdef CONFIG_DEBUG_PAGEALLOC
-	printk("DEBUG_PAGEALLOC");
-#endif
-	printk("\n");
-	sysfs_printk_last_file();
-	if (notify_die(DIE_OOPS, str, regs, err,
-			current->thread.trap_no, SIGSEGV) == NOTIFY_STOP)
-		return 1;
-
-	show_registers(regs);
-	/* Executive summary in case the oops scrolled away */
-	sp = (unsigned long) (&regs->sp);
-	savesegment(ss, ss);
-	if (user_mode(regs)) {
-		sp = regs->sp;
-		ss = regs->ss & 0xffff;
-	}
-	printk(KERN_EMERG "EIP: [<%08lx>] ", regs->ip);
-	print_symbol("%s", regs->ip);
-	printk(" SS:ESP %04x:%08lx\n", ss, sp);
-	return 0;
-}
-
-/*
- * This is gone through when something in the kernel has done something bad
- * and is about to be terminated:
- */
-void die(const char *str, struct pt_regs *regs, long err)
-{
-	unsigned long flags = oops_begin();
-
-	if (die_nest_count < 3) {
-		report_bug(regs->ip, regs);
-
-		if (__die(str, regs, err))
-			regs = NULL;
-	} else {
-		printk(KERN_EMERG "Recursive die() failure, output suppressed\n");
-	}
-
-	oops_end(flags, regs, SIGSEGV);
-}
-
-static DEFINE_SPINLOCK(nmi_print_lock);
-
-void notrace __kprobes
-die_nmi(char *str, struct pt_regs *regs, int do_panic)
-{
-	if (notify_die(DIE_NMIWATCHDOG, str, regs, 0, 2, SIGINT) == NOTIFY_STOP)
-		return;
-
-	spin_lock(&nmi_print_lock);
-	/*
-	* We are in trouble anyway, lets at least try
-	* to get a message out:
-	*/
-	bust_spinlocks(1);
-	printk(KERN_EMERG "%s", str);
-	printk(" on CPU%d, ip %08lx, registers:\n",
-		smp_processor_id(), regs->ip);
-	show_registers(regs);
-	if (do_panic)
-		panic("Non maskable interrupt");
-	console_silent();
-	spin_unlock(&nmi_print_lock);
-
-	/*
-	 * If we are in kernel we are probably nested up pretty bad
-	 * and might aswell get out now while we still can:
-	 */
-	if (!user_mode_vm(regs)) {
-		current->thread.trap_no = 2;
-		crash_kexec(regs);
-	}
-
-	bust_spinlocks(0);
-	do_exit(SIGSEGV);
-}
-
-static int __init oops_setup(char *s)
-{
-	if (!s)
-		return -EINVAL;
-	if (!strcmp(s, "panic"))
-		panic_on_oops = 1;
-	return 0;
-}
-early_param("oops", oops_setup);
-
-static int __init kstack_setup(char *s)
-{
-	if (!s)
-		return -EINVAL;
-	kstack_depth_to_print = simple_strtoul(s, NULL, 0);
-	return 0;
-}
-early_param("kstack", kstack_setup);
-
-static int __init code_bytes_setup(char *s)
-{
-	code_bytes = simple_strtoul(s, NULL, 0);
-	if (code_bytes > 8192)
-		code_bytes = 8192;
-
-	return 1;
-}
-__setup("code_bytes=", code_bytes_setup);
diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c
index 96a5db7da8a7..33ff10287a5d 100644
--- a/arch/x86/kernel/dumpstack_64.c
+++ b/arch/x86/kernel/dumpstack_64.c
@@ -17,19 +17,7 @@
 
 #include <asm/stacktrace.h>
 
-#define STACKSLOTS_PER_LINE 4
-#define get_bp(bp) asm("movq %%rbp, %0" : "=r" (bp) :)
-
-int panic_on_unrecovered_nmi;
-int kstack_depth_to_print = 3 * STACKSLOTS_PER_LINE;
-static unsigned int code_bytes = 64;
-static int die_counter;
-
-void printk_address(unsigned long address, int reliable)
-{
-	printk(" [<%p>] %s%pS\n", (void *) address,
-			reliable ? "" : "? ", (void *) address);
-}
+#include "dumpstack.h"
 
 static unsigned long *in_exception_stack(unsigned cpu, unsigned long stack,
 					unsigned *usedp, char **idp)
@@ -113,51 +101,6 @@ static unsigned long *in_exception_stack(unsigned cpu, unsigned long stack,
  * severe exception (double fault, nmi, stack fault, debug, mce) hardware stack
  */
 
-static inline int valid_stack_ptr(struct thread_info *tinfo,
-			void *p, unsigned int size, void *end)
-{
-	void *t = tinfo;
-	if (end) {
-		if (p < end && p >= (end-THREAD_SIZE))
-			return 1;
-		else
-			return 0;
-	}
-	return p > t && p < t + THREAD_SIZE - size;
-}
-
-/* The form of the top of the frame on the stack */
-struct stack_frame {
-	struct stack_frame *next_frame;
-	unsigned long return_address;
-};
-
-static inline unsigned long
-print_context_stack(struct thread_info *tinfo,
-		unsigned long *stack, unsigned long bp,
-		const struct stacktrace_ops *ops, void *data,
-		unsigned long *end)
-{
-	struct stack_frame *frame = (struct stack_frame *)bp;
-
-	while (valid_stack_ptr(tinfo, stack, sizeof(*stack), end)) {
-		unsigned long addr;
-
-		addr = *stack;
-		if (__kernel_text_address(addr)) {
-			if ((unsigned long) stack == bp + sizeof(long)) {
-				ops->address(data, addr, 1);
-				frame = frame->next_frame;
-				bp = (unsigned long) frame;
-			} else {
-				ops->address(data, addr, bp == 0);
-			}
-		}
-		stack++;
-	}
-	return bp;
-}
-
 void dump_trace(struct task_struct *task, struct pt_regs *regs,
 		unsigned long *stack, unsigned long bp,
 		const struct stacktrace_ops *ops, void *data)
@@ -248,57 +191,7 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs,
 }
 EXPORT_SYMBOL(dump_trace);
 
-static void
-print_trace_warning_symbol(void *data, char *msg, unsigned long symbol)
-{
-	printk(data);
-	print_symbol(msg, symbol);
-	printk("\n");
-}
-
-static void print_trace_warning(void *data, char *msg)
-{
-	printk("%s%s\n", (char *)data, msg);
-}
-
-static int print_trace_stack(void *data, char *name)
-{
-	printk("%s <%s> ", (char *)data, name);
-	return 0;
-}
-
-/*
- * Print one address/symbol entries per line.
- */
-static void print_trace_address(void *data, unsigned long addr, int reliable)
-{
-	touch_nmi_watchdog();
-	printk(data);
-	printk_address(addr, reliable);
-}
-
-static const struct stacktrace_ops print_trace_ops = {
-	.warning = print_trace_warning,
-	.warning_symbol = print_trace_warning_symbol,
-	.stack = print_trace_stack,
-	.address = print_trace_address,
-};
-
-static void
-show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs,
-		unsigned long *stack, unsigned long bp, char *log_lvl)
-{
-	printk("%sCall Trace:\n", log_lvl);
-	dump_trace(task, regs, stack, bp, &print_trace_ops, log_lvl);
-}
-
-void show_trace(struct task_struct *task, struct pt_regs *regs,
-		unsigned long *stack, unsigned long bp)
-{
-	show_trace_log_lvl(task, regs, stack, bp, "");
-}
-
-static void
+void
 show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs,
 		unsigned long *sp, unsigned long bp, char *log_lvl)
 {
@@ -342,33 +235,6 @@ show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs,
 	show_trace_log_lvl(task, regs, sp, bp, log_lvl);
 }
 
-void show_stack(struct task_struct *task, unsigned long *sp)
-{
-	show_stack_log_lvl(task, NULL, sp, 0, "");
-}
-
-/*
- * The architecture-independent dump_stack generator
- */
-void dump_stack(void)
-{
-	unsigned long bp = 0;
-	unsigned long stack;
-
-#ifdef CONFIG_FRAME_POINTER
-	if (!bp)
-		get_bp(bp);
-#endif
-
-	printk("Pid: %d, comm: %.20s %s %s %.*s\n",
-		current->pid, current->comm, print_tainted(),
-		init_utsname()->release,
-		(int)strcspn(init_utsname()->version, " "),
-		init_utsname()->version);
-	show_trace(NULL, NULL, &stack, bp);
-}
-EXPORT_SYMBOL(dump_stack);
-
 void show_registers(struct pt_regs *regs)
 {
 	int i;
@@ -429,147 +295,3 @@ int is_valid_bugaddr(unsigned long ip)
 	return ud2 == 0x0b0f;
 }
 
-static raw_spinlock_t die_lock = __RAW_SPIN_LOCK_UNLOCKED;
-static int die_owner = -1;
-static unsigned int die_nest_count;
-
-unsigned __kprobes long oops_begin(void)
-{
-	int cpu;
-	unsigned long flags;
-
-	oops_enter();
-
-	/* racy, but better than risking deadlock. */
-	raw_local_irq_save(flags);
-	cpu = smp_processor_id();
-	if (!__raw_spin_trylock(&die_lock)) {
-		if (cpu == die_owner)
-			/* nested oops. should stop eventually */;
-		else
-			__raw_spin_lock(&die_lock);
-	}
-	die_nest_count++;
-	die_owner = cpu;
-	console_verbose();
-	bust_spinlocks(1);
-	return flags;
-}
-
-void __kprobes oops_end(unsigned long flags, struct pt_regs *regs, int signr)
-{
-	die_owner = -1;
-	bust_spinlocks(0);
-	die_nest_count--;
-	if (!die_nest_count)
-		/* Nest count reaches zero, release the lock. */
-		__raw_spin_unlock(&die_lock);
-	raw_local_irq_restore(flags);
-	if (!regs) {
-		oops_exit();
-		return;
-	}
-	if (in_interrupt())
-		panic("Fatal exception in interrupt");
-	if (panic_on_oops)
-		panic("Fatal exception");
-	oops_exit();
-	do_exit(signr);
-}
-
-int __kprobes __die(const char *str, struct pt_regs *regs, long err)
-{
-	printk(KERN_EMERG "%s: %04lx [#%d] ", str, err & 0xffff, ++die_counter);
-#ifdef CONFIG_PREEMPT
-	printk("PREEMPT ");
-#endif
-#ifdef CONFIG_SMP
-	printk("SMP ");
-#endif
-#ifdef CONFIG_DEBUG_PAGEALLOC
-	printk("DEBUG_PAGEALLOC");
-#endif
-	printk("\n");
-	sysfs_printk_last_file();
-	if (notify_die(DIE_OOPS, str, regs, err,
-			current->thread.trap_no, SIGSEGV) == NOTIFY_STOP)
-		return 1;
-
-	show_registers(regs);
-	add_taint(TAINT_DIE);
-	/* Executive summary in case the oops scrolled away */
-	printk(KERN_ALERT "RIP ");
-	printk_address(regs->ip, 1);
-	printk(" RSP <%016lx>\n", regs->sp);
-	if (kexec_should_crash(current))
-		crash_kexec(regs);
-	return 0;
-}
-
-void die(const char *str, struct pt_regs *regs, long err)
-{
-	unsigned long flags = oops_begin();
-
-	if (!user_mode(regs))
-		report_bug(regs->ip, regs);
-
-	if (__die(str, regs, err))
-		regs = NULL;
-	oops_end(flags, regs, SIGSEGV);
-}
-
-notrace __kprobes void
-die_nmi(char *str, struct pt_regs *regs, int do_panic)
-{
-	unsigned long flags;
-
-	if (notify_die(DIE_NMIWATCHDOG, str, regs, 0, 2, SIGINT) == NOTIFY_STOP)
-		return;
-
-	flags = oops_begin();
-	/*
-	 * We are in trouble anyway, lets at least try
-	 * to get a message out.
-	 */
-	printk(KERN_EMERG "%s", str);
-	printk(" on CPU%d, ip %08lx, registers:\n",
-		smp_processor_id(), regs->ip);
-	show_registers(regs);
-	if (kexec_should_crash(current))
-		crash_kexec(regs);
-	if (do_panic || panic_on_oops)
-		panic("Non maskable interrupt");
-	oops_end(flags, NULL, SIGBUS);
-	nmi_exit();
-	local_irq_enable();
-	do_exit(SIGBUS);
-}
-
-static int __init oops_setup(char *s)
-{
-	if (!s)
-		return -EINVAL;
-	if (!strcmp(s, "panic"))
-		panic_on_oops = 1;
-	return 0;
-}
-early_param("oops", oops_setup);
-
-static int __init kstack_setup(char *s)
-{
-	if (!s)
-		return -EINVAL;
-	kstack_depth_to_print = simple_strtoul(s, NULL, 0);
-	return 0;
-}
-early_param("kstack", kstack_setup);
-
-static int __init code_bytes_setup(char *s)
-{
-	code_bytes = simple_strtoul(s, NULL, 0);
-	if (code_bytes > 8192)
-		code_bytes = 8192;
-
-	return 1;
-}
-__setup("code_bytes=", code_bytes_setup);
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index 7aafeb5263ef..74c6a21fdc8c 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -665,6 +665,27 @@ void __init e820_mark_nosave_regions(unsigned long limit_pfn)
 }
 #endif
 
+#ifdef CONFIG_HIBERNATION
+/**
+ * Mark ACPI NVS memory region, so that we can save/restore it during
+ * hibernation and the subsequent resume.
+ */
+static int __init e820_mark_nvs_memory(void)
+{
+	int i;
+
+	for (i = 0; i < e820.nr_map; i++) {
+		struct e820entry *ei = &e820.map[i];
+
+		if (ei->type == E820_NVS)
+			hibernate_nvs_register(ei->addr, ei->size);
+	}
+
+	return 0;
+}
+core_initcall(e820_mark_nvs_memory);
+#endif
+
 /*
  * Early reserved memory areas.
  */
diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c
index 1b894b72c0f5..744aa7fc49d5 100644
--- a/arch/x86/kernel/early-quirks.c
+++ b/arch/x86/kernel/early-quirks.c
@@ -17,6 +17,7 @@
 #include <asm/io_apic.h>
 #include <asm/apic.h>
 #include <asm/iommu.h>
+#include <asm/gart.h>
 
 static void __init fix_hypertransport_config(int num, int slot, int func)
 {
diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S
index 28b597ef9ca1..d517c89673ee 100644
--- a/arch/x86/kernel/entry_32.S
+++ b/arch/x86/kernel/entry_32.S
@@ -619,28 +619,37 @@ END(syscall_badsys)
 27:;
 
 /*
- * Build the entry stubs and pointer table with
- * some assembler magic.
+ * Build the entry stubs and pointer table with some assembler magic.
+ * We pack 7 stubs into a single 32-byte chunk, which will fit in a
+ * single cache line on all modern x86 implementations.
  */
-.section .rodata,"a"
+.section .init.rodata,"a"
 ENTRY(interrupt)
 .text
-
+	.p2align 5
+	.p2align CONFIG_X86_L1_CACHE_SHIFT
 ENTRY(irq_entries_start)
 	RING0_INT_FRAME
-vector=0
-.rept NR_VECTORS
-	ALIGN
- .if vector
+vector=FIRST_EXTERNAL_VECTOR
+.rept (NR_VECTORS-FIRST_EXTERNAL_VECTOR+6)/7
+	.balign 32
+  .rept	7
+    .if vector < NR_VECTORS
+      .if vector <> FIRST_EXTERNAL_VECTOR
 	CFI_ADJUST_CFA_OFFSET -4
- .endif
-1:	pushl $~(vector)
+      .endif
+1:	pushl $(~vector+0x80)	/* Note: always in signed byte range */
 	CFI_ADJUST_CFA_OFFSET 4
-	jmp common_interrupt
- .previous
+      .if ((vector-FIRST_EXTERNAL_VECTOR)%7) <> 6
+	jmp 2f
+      .endif
+      .previous
 	.long 1b
- .text
+      .text
 vector=vector+1
+    .endif
+  .endr
+2:	jmp common_interrupt
 .endr
 END(irq_entries_start)
 
@@ -652,8 +661,9 @@ END(interrupt)
  * the CPU automatically disables interrupts when executing an IRQ vector,
  * so IRQ-flags tracing has to follow that:
  */
-	ALIGN
+	.p2align CONFIG_X86_L1_CACHE_SHIFT
 common_interrupt:
+	addl $-0x80,(%esp)	/* Adjust vector into the [-256,-1] range */
 	SAVE_ALL
 	TRACE_IRQS_OFF
 	movl %esp,%eax
@@ -678,65 +688,6 @@ ENDPROC(name)
 /* The include is where all of the SMP etc. interrupts come from */
 #include "entry_arch.h"
 
-KPROBE_ENTRY(page_fault)
-	RING0_EC_FRAME
-	pushl $do_page_fault
-	CFI_ADJUST_CFA_OFFSET 4
-	ALIGN
-error_code:
-	/* the function address is in %fs's slot on the stack */
-	pushl %es
-	CFI_ADJUST_CFA_OFFSET 4
-	/*CFI_REL_OFFSET es, 0*/
-	pushl %ds
-	CFI_ADJUST_CFA_OFFSET 4
-	/*CFI_REL_OFFSET ds, 0*/
-	pushl %eax
-	CFI_ADJUST_CFA_OFFSET 4
-	CFI_REL_OFFSET eax, 0
-	pushl %ebp
-	CFI_ADJUST_CFA_OFFSET 4
-	CFI_REL_OFFSET ebp, 0
-	pushl %edi
-	CFI_ADJUST_CFA_OFFSET 4
-	CFI_REL_OFFSET edi, 0
-	pushl %esi
-	CFI_ADJUST_CFA_OFFSET 4
-	CFI_REL_OFFSET esi, 0
-	pushl %edx
-	CFI_ADJUST_CFA_OFFSET 4
-	CFI_REL_OFFSET edx, 0
-	pushl %ecx
-	CFI_ADJUST_CFA_OFFSET 4
-	CFI_REL_OFFSET ecx, 0
-	pushl %ebx
-	CFI_ADJUST_CFA_OFFSET 4
-	CFI_REL_OFFSET ebx, 0
-	cld
-	pushl %fs
-	CFI_ADJUST_CFA_OFFSET 4
-	/*CFI_REL_OFFSET fs, 0*/
-	movl $(__KERNEL_PERCPU), %ecx
-	movl %ecx, %fs
-	UNWIND_ESPFIX_STACK
-	popl %ecx
-	CFI_ADJUST_CFA_OFFSET -4
-	/*CFI_REGISTER es, ecx*/
-	movl PT_FS(%esp), %edi		# get the function address
-	movl PT_ORIG_EAX(%esp), %edx	# get the error code
-	movl $-1, PT_ORIG_EAX(%esp)	# no syscall to restart
-	mov  %ecx, PT_FS(%esp)
-	/*CFI_REL_OFFSET fs, ES*/
-	movl $(__USER_DS), %ecx
-	movl %ecx, %ds
-	movl %ecx, %es
-	TRACE_IRQS_OFF
-	movl %esp,%eax			# pt_regs pointer
-	call *%edi
-	jmp ret_from_exception
-	CFI_ENDPROC
-KPROBE_END(page_fault)
-
 ENTRY(coprocessor_error)
 	RING0_INT_FRAME
 	pushl $0
@@ -767,140 +718,6 @@ ENTRY(device_not_available)
 	CFI_ENDPROC
 END(device_not_available)
 
-/*
- * Debug traps and NMI can happen at the one SYSENTER instruction
- * that sets up the real kernel stack. Check here, since we can't
- * allow the wrong stack to be used.
- *
- * "TSS_sysenter_sp0+12" is because the NMI/debug handler will have
- * already pushed 3 words if it hits on the sysenter instruction:
- * eflags, cs and eip.
- *
- * We just load the right stack, and push the three (known) values
- * by hand onto the new stack - while updating the return eip past
- * the instruction that would have done it for sysenter.
- */
-#define FIX_STACK(offset, ok, label)		\
-	cmpw $__KERNEL_CS,4(%esp);		\
-	jne ok;					\
-label:						\
-	movl TSS_sysenter_sp0+offset(%esp),%esp;	\
-	CFI_DEF_CFA esp, 0;			\
-	CFI_UNDEFINED eip;			\
-	pushfl;					\
-	CFI_ADJUST_CFA_OFFSET 4;		\
-	pushl $__KERNEL_CS;			\
-	CFI_ADJUST_CFA_OFFSET 4;		\
-	pushl $sysenter_past_esp;		\
-	CFI_ADJUST_CFA_OFFSET 4;		\
-	CFI_REL_OFFSET eip, 0
-
-KPROBE_ENTRY(debug)
-	RING0_INT_FRAME
-	cmpl $ia32_sysenter_target,(%esp)
-	jne debug_stack_correct
-	FIX_STACK(12, debug_stack_correct, debug_esp_fix_insn)
-debug_stack_correct:
-	pushl $-1			# mark this as an int
-	CFI_ADJUST_CFA_OFFSET 4
-	SAVE_ALL
-	TRACE_IRQS_OFF
-	xorl %edx,%edx			# error code 0
-	movl %esp,%eax			# pt_regs pointer
-	call do_debug
-	jmp ret_from_exception
-	CFI_ENDPROC
-KPROBE_END(debug)
-
-/*
- * NMI is doubly nasty. It can happen _while_ we're handling
- * a debug fault, and the debug fault hasn't yet been able to
- * clear up the stack. So we first check whether we got  an
- * NMI on the sysenter entry path, but after that we need to
- * check whether we got an NMI on the debug path where the debug
- * fault happened on the sysenter path.
- */
-KPROBE_ENTRY(nmi)
-	RING0_INT_FRAME
-	pushl %eax
-	CFI_ADJUST_CFA_OFFSET 4
-	movl %ss, %eax
-	cmpw $__ESPFIX_SS, %ax
-	popl %eax
-	CFI_ADJUST_CFA_OFFSET -4
-	je nmi_espfix_stack
-	cmpl $ia32_sysenter_target,(%esp)
-	je nmi_stack_fixup
-	pushl %eax
-	CFI_ADJUST_CFA_OFFSET 4
-	movl %esp,%eax
-	/* Do not access memory above the end of our stack page,
-	 * it might not exist.
-	 */
-	andl $(THREAD_SIZE-1),%eax
-	cmpl $(THREAD_SIZE-20),%eax
-	popl %eax
-	CFI_ADJUST_CFA_OFFSET -4
-	jae nmi_stack_correct
-	cmpl $ia32_sysenter_target,12(%esp)
-	je nmi_debug_stack_check
-nmi_stack_correct:
-	/* We have a RING0_INT_FRAME here */
-	pushl %eax
-	CFI_ADJUST_CFA_OFFSET 4
-	SAVE_ALL
-	TRACE_IRQS_OFF
-	xorl %edx,%edx		# zero error code
-	movl %esp,%eax		# pt_regs pointer
-	call do_nmi
-	jmp restore_nocheck_notrace
-	CFI_ENDPROC
-
-nmi_stack_fixup:
-	RING0_INT_FRAME
-	FIX_STACK(12,nmi_stack_correct, 1)
-	jmp nmi_stack_correct
-
-nmi_debug_stack_check:
-	/* We have a RING0_INT_FRAME here */
-	cmpw $__KERNEL_CS,16(%esp)
-	jne nmi_stack_correct
-	cmpl $debug,(%esp)
-	jb nmi_stack_correct
-	cmpl $debug_esp_fix_insn,(%esp)
-	ja nmi_stack_correct
-	FIX_STACK(24,nmi_stack_correct, 1)
-	jmp nmi_stack_correct
-
-nmi_espfix_stack:
-	/* We have a RING0_INT_FRAME here.
-	 *
-	 * create the pointer to lss back
-	 */
-	pushl %ss
-	CFI_ADJUST_CFA_OFFSET 4
-	pushl %esp
-	CFI_ADJUST_CFA_OFFSET 4
-	addw $4, (%esp)
-	/* copy the iret frame of 12 bytes */
-	.rept 3
-	pushl 16(%esp)
-	CFI_ADJUST_CFA_OFFSET 4
-	.endr
-	pushl %eax
-	CFI_ADJUST_CFA_OFFSET 4
-	SAVE_ALL
-	TRACE_IRQS_OFF
-	FIXUP_ESPFIX_STACK		# %eax == %esp
-	xorl %edx,%edx			# zero error code
-	call do_nmi
-	RESTORE_REGS
-	lss 12+4(%esp), %esp		# back to espfix stack
-	CFI_ADJUST_CFA_OFFSET -24
-	jmp irq_return
-	CFI_ENDPROC
-KPROBE_END(nmi)
-
 #ifdef CONFIG_PARAVIRT
 ENTRY(native_iret)
 	iret
@@ -916,19 +733,6 @@ ENTRY(native_irq_enable_sysexit)
 END(native_irq_enable_sysexit)
 #endif
 
-KPROBE_ENTRY(int3)
-	RING0_INT_FRAME
-	pushl $-1			# mark this as an int
-	CFI_ADJUST_CFA_OFFSET 4
-	SAVE_ALL
-	TRACE_IRQS_OFF
-	xorl %edx,%edx		# zero error code
-	movl %esp,%eax		# pt_regs pointer
-	call do_int3
-	jmp ret_from_exception
-	CFI_ENDPROC
-KPROBE_END(int3)
-
 ENTRY(overflow)
 	RING0_INT_FRAME
 	pushl $0
@@ -993,14 +797,6 @@ ENTRY(stack_segment)
 	CFI_ENDPROC
 END(stack_segment)
 
-KPROBE_ENTRY(general_protection)
-	RING0_EC_FRAME
-	pushl $do_general_protection
-	CFI_ADJUST_CFA_OFFSET 4
-	jmp error_code
-	CFI_ENDPROC
-KPROBE_END(general_protection)
-
 ENTRY(alignment_check)
 	RING0_EC_FRAME
 	pushl $do_alignment_check
@@ -1051,6 +847,7 @@ ENTRY(kernel_thread_helper)
 	push %eax
 	CFI_ADJUST_CFA_OFFSET 4
 	call do_exit
+	ud2			# padding for call trace
 	CFI_ENDPROC
 ENDPROC(kernel_thread_helper)
 
@@ -1157,6 +954,9 @@ ENTRY(mcount)
 END(mcount)
 
 ENTRY(ftrace_caller)
+	cmpl $0, function_trace_stop
+	jne  ftrace_stub
+
 	pushl %eax
 	pushl %ecx
 	pushl %edx
@@ -1180,8 +980,15 @@ END(ftrace_caller)
 #else /* ! CONFIG_DYNAMIC_FTRACE */
 
 ENTRY(mcount)
+	cmpl $0, function_trace_stop
+	jne  ftrace_stub
+
 	cmpl $ftrace_stub, ftrace_trace_function
 	jnz trace
+#ifdef CONFIG_FUNCTION_RET_TRACER
+	cmpl $ftrace_stub, ftrace_function_return
+	jnz ftrace_return_caller
+#endif
 .globl ftrace_stub
 ftrace_stub:
 	ret
@@ -1200,13 +1007,267 @@ trace:
 	popl %edx
 	popl %ecx
 	popl %eax
-
 	jmp ftrace_stub
 END(mcount)
 #endif /* CONFIG_DYNAMIC_FTRACE */
 #endif /* CONFIG_FUNCTION_TRACER */
 
+#ifdef CONFIG_FUNCTION_RET_TRACER
+ENTRY(ftrace_return_caller)
+	cmpl $0, function_trace_stop
+	jne ftrace_stub
+
+	pushl %eax
+	pushl %ecx
+	pushl %edx
+	movl 0xc(%esp), %edx
+	lea 0x4(%ebp), %eax
+	call prepare_ftrace_return
+	popl %edx
+	popl %ecx
+	popl %eax
+	ret
+END(ftrace_return_caller)
+
+.globl return_to_handler
+return_to_handler:
+	pushl $0
+	pushl %eax
+	pushl %ecx
+	pushl %edx
+	call ftrace_return_to_handler
+	movl %eax, 0xc(%esp)
+	popl %edx
+	popl %ecx
+	popl %eax
+	ret
+#endif
+
 .section .rodata,"a"
 #include "syscall_table_32.S"
 
 syscall_table_size=(.-sys_call_table)
+
+/*
+ * Some functions should be protected against kprobes
+ */
+	.pushsection .kprobes.text, "ax"
+
+ENTRY(page_fault)
+	RING0_EC_FRAME
+	pushl $do_page_fault
+	CFI_ADJUST_CFA_OFFSET 4
+	ALIGN
+error_code:
+	/* the function address is in %fs's slot on the stack */
+	pushl %es
+	CFI_ADJUST_CFA_OFFSET 4
+	/*CFI_REL_OFFSET es, 0*/
+	pushl %ds
+	CFI_ADJUST_CFA_OFFSET 4
+	/*CFI_REL_OFFSET ds, 0*/
+	pushl %eax
+	CFI_ADJUST_CFA_OFFSET 4
+	CFI_REL_OFFSET eax, 0
+	pushl %ebp
+	CFI_ADJUST_CFA_OFFSET 4
+	CFI_REL_OFFSET ebp, 0
+	pushl %edi
+	CFI_ADJUST_CFA_OFFSET 4
+	CFI_REL_OFFSET edi, 0
+	pushl %esi
+	CFI_ADJUST_CFA_OFFSET 4
+	CFI_REL_OFFSET esi, 0
+	pushl %edx
+	CFI_ADJUST_CFA_OFFSET 4
+	CFI_REL_OFFSET edx, 0
+	pushl %ecx
+	CFI_ADJUST_CFA_OFFSET 4
+	CFI_REL_OFFSET ecx, 0
+	pushl %ebx
+	CFI_ADJUST_CFA_OFFSET 4
+	CFI_REL_OFFSET ebx, 0
+	cld
+	pushl %fs
+	CFI_ADJUST_CFA_OFFSET 4
+	/*CFI_REL_OFFSET fs, 0*/
+	movl $(__KERNEL_PERCPU), %ecx
+	movl %ecx, %fs
+	UNWIND_ESPFIX_STACK
+	popl %ecx
+	CFI_ADJUST_CFA_OFFSET -4
+	/*CFI_REGISTER es, ecx*/
+	movl PT_FS(%esp), %edi		# get the function address
+	movl PT_ORIG_EAX(%esp), %edx	# get the error code
+	movl $-1, PT_ORIG_EAX(%esp)	# no syscall to restart
+	mov  %ecx, PT_FS(%esp)
+	/*CFI_REL_OFFSET fs, ES*/
+	movl $(__USER_DS), %ecx
+	movl %ecx, %ds
+	movl %ecx, %es
+	TRACE_IRQS_OFF
+	movl %esp,%eax			# pt_regs pointer
+	call *%edi
+	jmp ret_from_exception
+	CFI_ENDPROC
+END(page_fault)
+
+/*
+ * Debug traps and NMI can happen at the one SYSENTER instruction
+ * that sets up the real kernel stack. Check here, since we can't
+ * allow the wrong stack to be used.
+ *
+ * "TSS_sysenter_sp0+12" is because the NMI/debug handler will have
+ * already pushed 3 words if it hits on the sysenter instruction:
+ * eflags, cs and eip.
+ *
+ * We just load the right stack, and push the three (known) values
+ * by hand onto the new stack - while updating the return eip past
+ * the instruction that would have done it for sysenter.
+ */
+#define FIX_STACK(offset, ok, label)		\
+	cmpw $__KERNEL_CS,4(%esp);		\
+	jne ok;					\
+label:						\
+	movl TSS_sysenter_sp0+offset(%esp),%esp;	\
+	CFI_DEF_CFA esp, 0;			\
+	CFI_UNDEFINED eip;			\
+	pushfl;					\
+	CFI_ADJUST_CFA_OFFSET 4;		\
+	pushl $__KERNEL_CS;			\
+	CFI_ADJUST_CFA_OFFSET 4;		\
+	pushl $sysenter_past_esp;		\
+	CFI_ADJUST_CFA_OFFSET 4;		\
+	CFI_REL_OFFSET eip, 0
+
+ENTRY(debug)
+	RING0_INT_FRAME
+	cmpl $ia32_sysenter_target,(%esp)
+	jne debug_stack_correct
+	FIX_STACK(12, debug_stack_correct, debug_esp_fix_insn)
+debug_stack_correct:
+	pushl $-1			# mark this as an int
+	CFI_ADJUST_CFA_OFFSET 4
+	SAVE_ALL
+	TRACE_IRQS_OFF
+	xorl %edx,%edx			# error code 0
+	movl %esp,%eax			# pt_regs pointer
+	call do_debug
+	jmp ret_from_exception
+	CFI_ENDPROC
+END(debug)
+
+/*
+ * NMI is doubly nasty. It can happen _while_ we're handling
+ * a debug fault, and the debug fault hasn't yet been able to
+ * clear up the stack. So we first check whether we got  an
+ * NMI on the sysenter entry path, but after that we need to
+ * check whether we got an NMI on the debug path where the debug
+ * fault happened on the sysenter path.
+ */
+ENTRY(nmi)
+	RING0_INT_FRAME
+	pushl %eax
+	CFI_ADJUST_CFA_OFFSET 4
+	movl %ss, %eax
+	cmpw $__ESPFIX_SS, %ax
+	popl %eax
+	CFI_ADJUST_CFA_OFFSET -4
+	je nmi_espfix_stack
+	cmpl $ia32_sysenter_target,(%esp)
+	je nmi_stack_fixup
+	pushl %eax
+	CFI_ADJUST_CFA_OFFSET 4
+	movl %esp,%eax
+	/* Do not access memory above the end of our stack page,
+	 * it might not exist.
+	 */
+	andl $(THREAD_SIZE-1),%eax
+	cmpl $(THREAD_SIZE-20),%eax
+	popl %eax
+	CFI_ADJUST_CFA_OFFSET -4
+	jae nmi_stack_correct
+	cmpl $ia32_sysenter_target,12(%esp)
+	je nmi_debug_stack_check
+nmi_stack_correct:
+	/* We have a RING0_INT_FRAME here */
+	pushl %eax
+	CFI_ADJUST_CFA_OFFSET 4
+	SAVE_ALL
+	TRACE_IRQS_OFF
+	xorl %edx,%edx		# zero error code
+	movl %esp,%eax		# pt_regs pointer
+	call do_nmi
+	jmp restore_nocheck_notrace
+	CFI_ENDPROC
+
+nmi_stack_fixup:
+	RING0_INT_FRAME
+	FIX_STACK(12,nmi_stack_correct, 1)
+	jmp nmi_stack_correct
+
+nmi_debug_stack_check:
+	/* We have a RING0_INT_FRAME here */
+	cmpw $__KERNEL_CS,16(%esp)
+	jne nmi_stack_correct
+	cmpl $debug,(%esp)
+	jb nmi_stack_correct
+	cmpl $debug_esp_fix_insn,(%esp)
+	ja nmi_stack_correct
+	FIX_STACK(24,nmi_stack_correct, 1)
+	jmp nmi_stack_correct
+
+nmi_espfix_stack:
+	/* We have a RING0_INT_FRAME here.
+	 *
+	 * create the pointer to lss back
+	 */
+	pushl %ss
+	CFI_ADJUST_CFA_OFFSET 4
+	pushl %esp
+	CFI_ADJUST_CFA_OFFSET 4
+	addw $4, (%esp)
+	/* copy the iret frame of 12 bytes */
+	.rept 3
+	pushl 16(%esp)
+	CFI_ADJUST_CFA_OFFSET 4
+	.endr
+	pushl %eax
+	CFI_ADJUST_CFA_OFFSET 4
+	SAVE_ALL
+	TRACE_IRQS_OFF
+	FIXUP_ESPFIX_STACK		# %eax == %esp
+	xorl %edx,%edx			# zero error code
+	call do_nmi
+	RESTORE_REGS
+	lss 12+4(%esp), %esp		# back to espfix stack
+	CFI_ADJUST_CFA_OFFSET -24
+	jmp irq_return
+	CFI_ENDPROC
+END(nmi)
+
+ENTRY(int3)
+	RING0_INT_FRAME
+	pushl $-1			# mark this as an int
+	CFI_ADJUST_CFA_OFFSET 4
+	SAVE_ALL
+	TRACE_IRQS_OFF
+	xorl %edx,%edx		# zero error code
+	movl %esp,%eax		# pt_regs pointer
+	call do_int3
+	jmp ret_from_exception
+	CFI_ENDPROC
+END(int3)
+
+ENTRY(general_protection)
+	RING0_EC_FRAME
+	pushl $do_general_protection
+	CFI_ADJUST_CFA_OFFSET 4
+	jmp error_code
+	CFI_ENDPROC
+END(general_protection)
+
+/*
+ * End of kprobes section
+ */
+	.popsection
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index b86f332c96a6..5e63b530ba07 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -11,15 +11,15 @@
  *
  * NOTE: This code handles signal-recognition, which happens every time
  * after an interrupt and after each system call.
- * 
- * Normal syscalls and interrupts don't save a full stack frame, this is 
+ *
+ * Normal syscalls and interrupts don't save a full stack frame, this is
  * only done for syscall tracing, signals or fork/exec et.al.
- * 
- * A note on terminology:	 
- * - top of stack: Architecture defined interrupt frame from SS to RIP 
- * at the top of the kernel process stack.	
+ *
+ * A note on terminology:
+ * - top of stack: Architecture defined interrupt frame from SS to RIP
+ * at the top of the kernel process stack.
  * - partial stack frame: partially saved registers upto R11.
- * - full stack frame: Like partial stack frame, but all register saved. 
+ * - full stack frame: Like partial stack frame, but all register saved.
  *
  * Some macro usage:
  * - CFI macros are used to generate dwarf2 unwind information for better
@@ -60,7 +60,6 @@
 #define __AUDIT_ARCH_LE	   0x40000000
 
 	.code64
-
 #ifdef CONFIG_FUNCTION_TRACER
 #ifdef CONFIG_DYNAMIC_FTRACE
 ENTRY(mcount)
@@ -68,6 +67,8 @@ ENTRY(mcount)
 END(mcount)
 
 ENTRY(ftrace_caller)
+	cmpl $0, function_trace_stop
+	jne  ftrace_stub
 
 	/* taken from glibc */
 	subq $0x38, %rsp
@@ -103,6 +104,9 @@ END(ftrace_caller)
 
 #else /* ! CONFIG_DYNAMIC_FTRACE */
 ENTRY(mcount)
+	cmpl $0, function_trace_stop
+	jne  ftrace_stub
+
 	cmpq $ftrace_stub, ftrace_trace_function
 	jnz trace
 .globl ftrace_stub
@@ -142,7 +146,7 @@ END(mcount)
 
 #ifndef CONFIG_PREEMPT
 #define retint_kernel retint_restore_args
-#endif	
+#endif
 
 #ifdef CONFIG_PARAVIRT
 ENTRY(native_usergs_sysret64)
@@ -161,29 +165,29 @@ ENTRY(native_usergs_sysret64)
 .endm
 
 /*
- * C code is not supposed to know about undefined top of stack. Every time 
- * a C function with an pt_regs argument is called from the SYSCALL based 
+ * C code is not supposed to know about undefined top of stack. Every time
+ * a C function with an pt_regs argument is called from the SYSCALL based
  * fast path FIXUP_TOP_OF_STACK is needed.
  * RESTORE_TOP_OF_STACK syncs the syscall state after any possible ptregs
  * manipulation.
- */        	
-		
-	/* %rsp:at FRAMEEND */ 
-	.macro FIXUP_TOP_OF_STACK tmp
-	movq	%gs:pda_oldrsp,\tmp
-	movq  	\tmp,RSP(%rsp)
-	movq    $__USER_DS,SS(%rsp)
-	movq    $__USER_CS,CS(%rsp)
-	movq 	$-1,RCX(%rsp)
-	movq	R11(%rsp),\tmp  /* get eflags */
-	movq	\tmp,EFLAGS(%rsp)
+ */
+
+	/* %rsp:at FRAMEEND */
+	.macro FIXUP_TOP_OF_STACK tmp offset=0
+	movq %gs:pda_oldrsp,\tmp
+	movq \tmp,RSP+\offset(%rsp)
+	movq $__USER_DS,SS+\offset(%rsp)
+	movq $__USER_CS,CS+\offset(%rsp)
+	movq $-1,RCX+\offset(%rsp)
+	movq R11+\offset(%rsp),\tmp  /* get eflags */
+	movq \tmp,EFLAGS+\offset(%rsp)
 	.endm
 
-	.macro RESTORE_TOP_OF_STACK tmp,offset=0
-	movq   RSP-\offset(%rsp),\tmp
-	movq   \tmp,%gs:pda_oldrsp
-	movq   EFLAGS-\offset(%rsp),\tmp
-	movq   \tmp,R11-\offset(%rsp)
+	.macro RESTORE_TOP_OF_STACK tmp offset=0
+	movq RSP+\offset(%rsp),\tmp
+	movq \tmp,%gs:pda_oldrsp
+	movq EFLAGS+\offset(%rsp),\tmp
+	movq \tmp,R11+\offset(%rsp)
 	.endm
 
 	.macro FAKE_STACK_FRAME child_rip
@@ -195,7 +199,7 @@ ENTRY(native_usergs_sysret64)
 	pushq %rax /* rsp */
 	CFI_ADJUST_CFA_OFFSET	8
 	CFI_REL_OFFSET	rsp,0
-	pushq $(1<<9) /* eflags - interrupts on */
+	pushq $X86_EFLAGS_IF /* eflags - interrupts on */
 	CFI_ADJUST_CFA_OFFSET	8
 	/*CFI_REL_OFFSET	rflags,0*/
 	pushq $__KERNEL_CS /* cs */
@@ -213,62 +217,184 @@ ENTRY(native_usergs_sysret64)
 	CFI_ADJUST_CFA_OFFSET	-(6*8)
 	.endm
 
-	.macro	CFI_DEFAULT_STACK start=1
+/*
+ * initial frame state for interrupts (and exceptions without error code)
+ */
+	.macro EMPTY_FRAME start=1 offset=0
 	.if \start
-	CFI_STARTPROC	simple
+	CFI_STARTPROC simple
 	CFI_SIGNAL_FRAME
-	CFI_DEF_CFA	rsp,SS+8
+	CFI_DEF_CFA rsp,8+\offset
 	.else
-	CFI_DEF_CFA_OFFSET SS+8
+	CFI_DEF_CFA_OFFSET 8+\offset
 	.endif
-	CFI_REL_OFFSET	r15,R15
-	CFI_REL_OFFSET	r14,R14
-	CFI_REL_OFFSET	r13,R13
-	CFI_REL_OFFSET	r12,R12
-	CFI_REL_OFFSET	rbp,RBP
-	CFI_REL_OFFSET	rbx,RBX
-	CFI_REL_OFFSET	r11,R11
-	CFI_REL_OFFSET	r10,R10
-	CFI_REL_OFFSET	r9,R9
-	CFI_REL_OFFSET	r8,R8
-	CFI_REL_OFFSET	rax,RAX
-	CFI_REL_OFFSET	rcx,RCX
-	CFI_REL_OFFSET	rdx,RDX
-	CFI_REL_OFFSET	rsi,RSI
-	CFI_REL_OFFSET	rdi,RDI
-	CFI_REL_OFFSET	rip,RIP
-	/*CFI_REL_OFFSET	cs,CS*/
-	/*CFI_REL_OFFSET	rflags,EFLAGS*/
-	CFI_REL_OFFSET	rsp,RSP
-	/*CFI_REL_OFFSET	ss,SS*/
 	.endm
+
+/*
+ * initial frame state for interrupts (and exceptions without error code)
+ */
+	.macro INTR_FRAME start=1 offset=0
+	EMPTY_FRAME \start, SS+8+\offset-RIP
+	/*CFI_REL_OFFSET ss, SS+\offset-RIP*/
+	CFI_REL_OFFSET rsp, RSP+\offset-RIP
+	/*CFI_REL_OFFSET rflags, EFLAGS+\offset-RIP*/
+	/*CFI_REL_OFFSET cs, CS+\offset-RIP*/
+	CFI_REL_OFFSET rip, RIP+\offset-RIP
+	.endm
+
+/*
+ * initial frame state for exceptions with error code (and interrupts
+ * with vector already pushed)
+ */
+	.macro XCPT_FRAME start=1 offset=0
+	INTR_FRAME \start, RIP+\offset-ORIG_RAX
+	/*CFI_REL_OFFSET orig_rax, ORIG_RAX-ORIG_RAX*/
+	.endm
+
+/*
+ * frame that enables calling into C.
+ */
+	.macro PARTIAL_FRAME start=1 offset=0
+	XCPT_FRAME \start, ORIG_RAX+\offset-ARGOFFSET
+	CFI_REL_OFFSET rdi, RDI+\offset-ARGOFFSET
+	CFI_REL_OFFSET rsi, RSI+\offset-ARGOFFSET
+	CFI_REL_OFFSET rdx, RDX+\offset-ARGOFFSET
+	CFI_REL_OFFSET rcx, RCX+\offset-ARGOFFSET
+	CFI_REL_OFFSET rax, RAX+\offset-ARGOFFSET
+	CFI_REL_OFFSET r8, R8+\offset-ARGOFFSET
+	CFI_REL_OFFSET r9, R9+\offset-ARGOFFSET
+	CFI_REL_OFFSET r10, R10+\offset-ARGOFFSET
+	CFI_REL_OFFSET r11, R11+\offset-ARGOFFSET
+	.endm
+
 /*
- * A newly forked process directly context switches into this.
- */ 	
-/* rdi:	prev */	
+ * frame that enables passing a complete pt_regs to a C function.
+ */
+	.macro DEFAULT_FRAME start=1 offset=0
+	PARTIAL_FRAME \start, R11+\offset-R15
+	CFI_REL_OFFSET rbx, RBX+\offset
+	CFI_REL_OFFSET rbp, RBP+\offset
+	CFI_REL_OFFSET r12, R12+\offset
+	CFI_REL_OFFSET r13, R13+\offset
+	CFI_REL_OFFSET r14, R14+\offset
+	CFI_REL_OFFSET r15, R15+\offset
+	.endm
+
+/* save partial stack frame */
+ENTRY(save_args)
+	XCPT_FRAME
+	cld
+	movq_cfi rdi, RDI+16-ARGOFFSET
+	movq_cfi rsi, RSI+16-ARGOFFSET
+	movq_cfi rdx, RDX+16-ARGOFFSET
+	movq_cfi rcx, RCX+16-ARGOFFSET
+	movq_cfi rax, RAX+16-ARGOFFSET
+	movq_cfi  r8,  R8+16-ARGOFFSET
+	movq_cfi  r9,  R9+16-ARGOFFSET
+	movq_cfi r10, R10+16-ARGOFFSET
+	movq_cfi r11, R11+16-ARGOFFSET
+
+	leaq -ARGOFFSET+16(%rsp),%rdi	/* arg1 for handler */
+	movq_cfi rbp, 8		/* push %rbp */
+	leaq 8(%rsp), %rbp		/* mov %rsp, %ebp */
+	testl $3, CS(%rdi)
+	je 1f
+	SWAPGS
+	/*
+	 * irqcount is used to check if a CPU is already on an interrupt stack
+	 * or not. While this is essentially redundant with preempt_count it is
+	 * a little cheaper to use a separate counter in the PDA (short of
+	 * moving irq_enter into assembly, which would be too much work)
+	 */
+1:	incl %gs:pda_irqcount
+	jne 2f
+	popq_cfi %rax			/* move return address... */
+	mov %gs:pda_irqstackptr,%rsp
+	EMPTY_FRAME 0
+	pushq_cfi %rax			/* ... to the new stack */
+	/*
+	 * We entered an interrupt context - irqs are off:
+	 */
+2:	TRACE_IRQS_OFF
+	ret
+	CFI_ENDPROC
+END(save_args)
+
+ENTRY(save_rest)
+	PARTIAL_FRAME 1 REST_SKIP+8
+	movq 5*8+16(%rsp), %r11	/* save return address */
+	movq_cfi rbx, RBX+16
+	movq_cfi rbp, RBP+16
+	movq_cfi r12, R12+16
+	movq_cfi r13, R13+16
+	movq_cfi r14, R14+16
+	movq_cfi r15, R15+16
+	movq %r11, 8(%rsp)	/* return address */
+	FIXUP_TOP_OF_STACK %r11, 16
+	ret
+	CFI_ENDPROC
+END(save_rest)
+
+/* save complete stack frame */
+ENTRY(save_paranoid)
+	XCPT_FRAME 1 RDI+8
+	cld
+	movq_cfi rdi, RDI+8
+	movq_cfi rsi, RSI+8
+	movq_cfi rdx, RDX+8
+	movq_cfi rcx, RCX+8
+	movq_cfi rax, RAX+8
+	movq_cfi r8, R8+8
+	movq_cfi r9, R9+8
+	movq_cfi r10, R10+8
+	movq_cfi r11, R11+8
+	movq_cfi rbx, RBX+8
+	movq_cfi rbp, RBP+8
+	movq_cfi r12, R12+8
+	movq_cfi r13, R13+8
+	movq_cfi r14, R14+8
+	movq_cfi r15, R15+8
+	movl $1,%ebx
+	movl $MSR_GS_BASE,%ecx
+	rdmsr
+	testl %edx,%edx
+	js 1f	/* negative -> in kernel */
+	SWAPGS
+	xorl %ebx,%ebx
+1:	ret
+	CFI_ENDPROC
+END(save_paranoid)
+
+/*
+ * A newly forked process directly context switches into this address.
+ *
+ * rdi: prev task we switched from
+ */
 ENTRY(ret_from_fork)
-	CFI_DEFAULT_STACK
+	DEFAULT_FRAME
+
 	push kernel_eflags(%rip)
 	CFI_ADJUST_CFA_OFFSET 8
-	popf				# reset kernel eflags
+	popf					# reset kernel eflags
 	CFI_ADJUST_CFA_OFFSET -8
-	call schedule_tail
+
+	call schedule_tail			# rdi: 'prev' task parameter
+
 	GET_THREAD_INFO(%rcx)
-	testl $(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT),TI_flags(%rcx)
-	jnz rff_trace
-rff_action:	
+
+	CFI_REMEMBER_STATE
 	RESTORE_REST
-	testl $3,CS-ARGOFFSET(%rsp)	# from kernel_thread?
+
+	testl $3, CS-ARGOFFSET(%rsp)		# from kernel_thread?
 	je   int_ret_from_sys_call
-	testl $_TIF_IA32,TI_flags(%rcx)
+
+	testl $_TIF_IA32, TI_flags(%rcx)	# 32-bit compat task needs IRET
 	jnz  int_ret_from_sys_call
-	RESTORE_TOP_OF_STACK %rdi,ARGOFFSET
-	jmp ret_from_sys_call
-rff_trace:
-	movq %rsp,%rdi
-	call syscall_trace_leave
-	GET_THREAD_INFO(%rcx)	
-	jmp rff_action
+
+	RESTORE_TOP_OF_STACK %rdi, -ARGOFFSET
+	jmp ret_from_sys_call			# go to the SYSRET fastpath
+
+	CFI_RESTORE_STATE
 	CFI_ENDPROC
 END(ret_from_fork)
 
@@ -278,20 +404,20 @@ END(ret_from_fork)
  * SYSCALL does not save anything on the stack and does not change the
  * stack pointer.
  */
-		
+
 /*
- * Register setup:	
+ * Register setup:
  * rax  system call number
  * rdi  arg0
- * rcx  return address for syscall/sysret, C arg3 
+ * rcx  return address for syscall/sysret, C arg3
  * rsi  arg1
- * rdx  arg2	
+ * rdx  arg2
  * r10  arg3 	(--> moved to rcx for C)
  * r8   arg4
  * r9   arg5
  * r11  eflags for syscall/sysret, temporary for C
- * r12-r15,rbp,rbx saved by C code, not touched. 		
- * 
+ * r12-r15,rbp,rbx saved by C code, not touched.
+ *
  * Interrupts are off on entry.
  * Only called from user space.
  *
@@ -301,7 +427,7 @@ END(ret_from_fork)
  * When user can change the frames always force IRET. That is because
  * it deals with uncanonical addresses better. SYSRET has trouble
  * with them due to bugs in both AMD and Intel CPUs.
- */ 			 		
+ */
 
 ENTRY(system_call)
 	CFI_STARTPROC	simple
@@ -317,7 +443,7 @@ ENTRY(system_call)
 	 */
 ENTRY(system_call_after_swapgs)
 
-	movq	%rsp,%gs:pda_oldrsp 
+	movq	%rsp,%gs:pda_oldrsp
 	movq	%gs:pda_kernelstack,%rsp
 	/*
 	 * No need to follow this irqs off/on section - it's straight
@@ -325,7 +451,7 @@ ENTRY(system_call_after_swapgs)
 	 */
 	ENABLE_INTERRUPTS(CLBR_NONE)
 	SAVE_ARGS 8,1
-	movq  %rax,ORIG_RAX-ARGOFFSET(%rsp) 
+	movq  %rax,ORIG_RAX-ARGOFFSET(%rsp)
 	movq  %rcx,RIP-ARGOFFSET(%rsp)
 	CFI_REL_OFFSET rip,RIP-ARGOFFSET
 	GET_THREAD_INFO(%rcx)
@@ -339,19 +465,19 @@ system_call_fastpath:
 	movq %rax,RAX-ARGOFFSET(%rsp)
 /*
  * Syscall return path ending with SYSRET (fast path)
- * Has incomplete stack frame and undefined top of stack. 
- */		
+ * Has incomplete stack frame and undefined top of stack.
+ */
 ret_from_sys_call:
 	movl $_TIF_ALLWORK_MASK,%edi
 	/* edi:	flagmask */
-sysret_check:		
+sysret_check:
 	LOCKDEP_SYS_EXIT
 	GET_THREAD_INFO(%rcx)
 	DISABLE_INTERRUPTS(CLBR_NONE)
 	TRACE_IRQS_OFF
 	movl TI_flags(%rcx),%edx
 	andl %edi,%edx
-	jnz  sysret_careful 
+	jnz  sysret_careful
 	CFI_REMEMBER_STATE
 	/*
 	 * sysretq will re-enable interrupts:
@@ -366,7 +492,7 @@ sysret_check:
 
 	CFI_RESTORE_STATE
 	/* Handle reschedules */
-	/* edx:	work, edi: workmask */	
+	/* edx:	work, edi: workmask */
 sysret_careful:
 	bt $TIF_NEED_RESCHED,%edx
 	jnc sysret_signal
@@ -379,7 +505,7 @@ sysret_careful:
 	CFI_ADJUST_CFA_OFFSET -8
 	jmp sysret_check
 
-	/* Handle a signal */ 
+	/* Handle a signal */
 sysret_signal:
 	TRACE_IRQS_ON
 	ENABLE_INTERRUPTS(CLBR_NONE)
@@ -388,17 +514,20 @@ sysret_signal:
 	jc sysret_audit
 #endif
 	/* edx:	work flags (arg3) */
-	leaq do_notify_resume(%rip),%rax
 	leaq -ARGOFFSET(%rsp),%rdi # &pt_regs -> arg1
 	xorl %esi,%esi # oldset -> arg2
-	call ptregscall_common
+	SAVE_REST
+	FIXUP_TOP_OF_STACK %r11
+	call do_notify_resume
+	RESTORE_TOP_OF_STACK %r11
+	RESTORE_REST
 	movl $_TIF_WORK_MASK,%edi
 	/* Use IRET because user could have changed frame. This
 	   works because ptregscall_common has called FIXUP_TOP_OF_STACK. */
 	DISABLE_INTERRUPTS(CLBR_NONE)
 	TRACE_IRQS_OFF
 	jmp int_with_check
-	
+
 badsys:
 	movq $-ENOSYS,RAX-ARGOFFSET(%rsp)
 	jmp ret_from_sys_call
@@ -437,7 +566,7 @@ sysret_audit:
 #endif	/* CONFIG_AUDITSYSCALL */
 
 	/* Do syscall tracing */
-tracesys:			 
+tracesys:
 #ifdef CONFIG_AUDITSYSCALL
 	testl $(_TIF_WORK_SYSCALL_ENTRY & ~_TIF_SYSCALL_AUDIT),TI_flags(%rcx)
 	jz auditsys
@@ -460,8 +589,8 @@ tracesys:
 	call *sys_call_table(,%rax,8)
 	movq %rax,RAX-ARGOFFSET(%rsp)
 	/* Use IRET because user could have changed frame */
-		
-/* 
+
+/*
  * Syscall return path ending with IRET.
  * Has correct top of stack, but partial stack frame.
  */
@@ -505,18 +634,18 @@ int_very_careful:
 	TRACE_IRQS_ON
 	ENABLE_INTERRUPTS(CLBR_NONE)
 	SAVE_REST
-	/* Check for syscall exit trace */	
+	/* Check for syscall exit trace */
 	testl $_TIF_WORK_SYSCALL_EXIT,%edx
 	jz int_signal
 	pushq %rdi
 	CFI_ADJUST_CFA_OFFSET 8
-	leaq 8(%rsp),%rdi	# &ptregs -> arg1	
+	leaq 8(%rsp),%rdi	# &ptregs -> arg1
 	call syscall_trace_leave
 	popq %rdi
 	CFI_ADJUST_CFA_OFFSET -8
 	andl $~(_TIF_WORK_SYSCALL_EXIT|_TIF_SYSCALL_EMU),%edi
 	jmp int_restore_rest
-	
+
 int_signal:
 	testl $_TIF_DO_NOTIFY_MASK,%edx
 	jz 1f
@@ -531,22 +660,24 @@ int_restore_rest:
 	jmp int_with_check
 	CFI_ENDPROC
 END(system_call)
-		
-/* 
+
+/*
  * Certain special system calls that need to save a complete full stack frame.
- */ 								
-	
+ */
 	.macro PTREGSCALL label,func,arg
-	.globl \label
-\label:
-	leaq	\func(%rip),%rax
-	leaq    -ARGOFFSET+8(%rsp),\arg /* 8 for return address */
-	jmp	ptregscall_common
+ENTRY(\label)
+	PARTIAL_FRAME 1 8		/* offset 8: return address */
+	subq $REST_SKIP, %rsp
+	CFI_ADJUST_CFA_OFFSET REST_SKIP
+	call save_rest
+	DEFAULT_FRAME 0 8		/* offset 8: return address */
+	leaq 8(%rsp), \arg	/* pt_regs pointer */
+	call \func
+	jmp ptregscall_common
+	CFI_ENDPROC
 END(\label)
 	.endm
 
-	CFI_STARTPROC
-
 	PTREGSCALL stub_clone, sys_clone, %r8
 	PTREGSCALL stub_fork, sys_fork, %rdi
 	PTREGSCALL stub_vfork, sys_vfork, %rdi
@@ -554,25 +685,18 @@ END(\label)
 	PTREGSCALL stub_iopl, sys_iopl, %rsi
 
 ENTRY(ptregscall_common)
-	popq %r11
-	CFI_ADJUST_CFA_OFFSET -8
-	CFI_REGISTER rip, r11
-	SAVE_REST
-	movq %r11, %r15
-	CFI_REGISTER rip, r15
-	FIXUP_TOP_OF_STACK %r11
-	call *%rax
-	RESTORE_TOP_OF_STACK %r11
-	movq %r15, %r11
-	CFI_REGISTER rip, r11
-	RESTORE_REST
-	pushq %r11
-	CFI_ADJUST_CFA_OFFSET 8
-	CFI_REL_OFFSET rip, 0
-	ret
+	DEFAULT_FRAME 1 8	/* offset 8: return address */
+	RESTORE_TOP_OF_STACK %r11, 8
+	movq_cfi_restore R15+8, r15
+	movq_cfi_restore R14+8, r14
+	movq_cfi_restore R13+8, r13
+	movq_cfi_restore R12+8, r12
+	movq_cfi_restore RBP+8, rbp
+	movq_cfi_restore RBX+8, rbx
+	ret $REST_SKIP		/* pop extended registers */
 	CFI_ENDPROC
 END(ptregscall_common)
-	
+
 ENTRY(stub_execve)
 	CFI_STARTPROC
 	popq %r11
@@ -588,11 +712,11 @@ ENTRY(stub_execve)
 	jmp int_ret_from_sys_call
 	CFI_ENDPROC
 END(stub_execve)
-	
+
 /*
  * sigreturn is special because it needs to restore all registers on return.
  * This cannot be done with SYSRET, so use the IRET return path instead.
- */                
+ */
 ENTRY(stub_rt_sigreturn)
 	CFI_STARTPROC
 	addq $8, %rsp
@@ -608,70 +732,70 @@ ENTRY(stub_rt_sigreturn)
 END(stub_rt_sigreturn)
 
 /*
- * initial frame state for interrupts and exceptions
+ * Build the entry stubs and pointer table with some assembler magic.
+ * We pack 7 stubs into a single 32-byte chunk, which will fit in a
+ * single cache line on all modern x86 implementations.
  */
-	.macro _frame ref
-	CFI_STARTPROC simple
-	CFI_SIGNAL_FRAME
-	CFI_DEF_CFA rsp,SS+8-\ref
-	/*CFI_REL_OFFSET ss,SS-\ref*/
-	CFI_REL_OFFSET rsp,RSP-\ref
-	/*CFI_REL_OFFSET rflags,EFLAGS-\ref*/
-	/*CFI_REL_OFFSET cs,CS-\ref*/
-	CFI_REL_OFFSET rip,RIP-\ref
-	.endm
+	.section .init.rodata,"a"
+ENTRY(interrupt)
+	.text
+	.p2align 5
+	.p2align CONFIG_X86_L1_CACHE_SHIFT
+ENTRY(irq_entries_start)
+	INTR_FRAME
+vector=FIRST_EXTERNAL_VECTOR
+.rept (NR_VECTORS-FIRST_EXTERNAL_VECTOR+6)/7
+	.balign 32
+  .rept	7
+    .if vector < NR_VECTORS
+      .if vector <> FIRST_EXTERNAL_VECTOR
+	CFI_ADJUST_CFA_OFFSET -8
+      .endif
+1:	pushq $(~vector+0x80)	/* Note: always in signed byte range */
+	CFI_ADJUST_CFA_OFFSET 8
+      .if ((vector-FIRST_EXTERNAL_VECTOR)%7) <> 6
+	jmp 2f
+      .endif
+      .previous
+	.quad 1b
+      .text
+vector=vector+1
+    .endif
+  .endr
+2:	jmp common_interrupt
+.endr
+	CFI_ENDPROC
+END(irq_entries_start)
 
-/* initial frame state for interrupts (and exceptions without error code) */
-#define INTR_FRAME _frame RIP
-/* initial frame state for exceptions with error code (and interrupts with
-   vector already pushed) */
-#define XCPT_FRAME _frame ORIG_RAX
+.previous
+END(interrupt)
+.previous
 
-/* 
+/*
  * Interrupt entry/exit.
  *
  * Interrupt entry points save only callee clobbered registers in fast path.
- *	
- * Entry runs with interrupts off.	
- */ 
+ *
+ * Entry runs with interrupts off.
+ */
 
-/* 0(%rsp): interrupt number */ 
+/* 0(%rsp): ~(interrupt number) */
 	.macro interrupt func
-	cld
-	SAVE_ARGS
-	leaq -ARGOFFSET(%rsp),%rdi	# arg1 for handler
-	pushq %rbp
-	/*
-	 * Save rbp twice: One is for marking the stack frame, as usual, and the
-	 * other, to fill pt_regs properly. This is because bx comes right
-	 * before the last saved register in that structure, and not bp. If the
-	 * base pointer were in the place bx is today, this would not be needed.
-	 */
-	movq %rbp, -8(%rsp)
-	CFI_ADJUST_CFA_OFFSET	8
-	CFI_REL_OFFSET		rbp, 0
-	movq %rsp,%rbp
-	CFI_DEF_CFA_REGISTER	rbp
-	testl $3,CS(%rdi)
-	je 1f
-	SWAPGS
-	/* irqcount is used to check if a CPU is already on an interrupt
-	   stack or not. While this is essentially redundant with preempt_count
-	   it is a little cheaper to use a separate counter in the PDA
-	   (short of moving irq_enter into assembly, which would be too
-	    much work) */
-1:	incl	%gs:pda_irqcount
-	cmoveq %gs:pda_irqstackptr,%rsp
-	push    %rbp			# backlink for old unwinder
-	/*
-	 * We entered an interrupt context - irqs are off:
-	 */
-	TRACE_IRQS_OFF
+	subq $10*8, %rsp
+	CFI_ADJUST_CFA_OFFSET 10*8
+	call save_args
+	PARTIAL_FRAME 0
 	call \func
 	.endm
 
-ENTRY(common_interrupt)
+	/*
+	 * The interrupt stubs push (~vector+0x80) onto the stack and
+	 * then jump to common_interrupt.
+	 */
+	.p2align CONFIG_X86_L1_CACHE_SHIFT
+common_interrupt:
 	XCPT_FRAME
+	addq $-0x80,(%rsp)		/* Adjust vector to [-256,-1] range */
 	interrupt do_IRQ
 	/* 0(%rsp): oldrsp-ARGOFFSET */
 ret_from_intr:
@@ -685,12 +809,12 @@ exit_intr:
 	GET_THREAD_INFO(%rcx)
 	testl $3,CS-ARGOFFSET(%rsp)
 	je retint_kernel
-	
+
 	/* Interrupt came from user space */
 	/*
 	 * Has a correct top of stack, but a partial stack frame
 	 * %rcx: thread info. Interrupts off.
-	 */		
+	 */
 retint_with_reschedule:
 	movl $_TIF_WORK_MASK,%edi
 retint_check:
@@ -763,20 +887,20 @@ retint_careful:
 	pushq %rdi
 	CFI_ADJUST_CFA_OFFSET	8
 	call  schedule
-	popq %rdi		
+	popq %rdi
 	CFI_ADJUST_CFA_OFFSET	-8
 	GET_THREAD_INFO(%rcx)
 	DISABLE_INTERRUPTS(CLBR_NONE)
 	TRACE_IRQS_OFF
 	jmp retint_check
-	
+
 retint_signal:
 	testl $_TIF_DO_NOTIFY_MASK,%edx
 	jz    retint_swapgs
 	TRACE_IRQS_ON
 	ENABLE_INTERRUPTS(CLBR_NONE)
 	SAVE_REST
-	movq $-1,ORIG_RAX(%rsp) 			
+	movq $-1,ORIG_RAX(%rsp)
 	xorl %esi,%esi		# oldset
 	movq %rsp,%rdi		# &pt_regs
 	call do_notify_resume
@@ -798,324 +922,211 @@ ENTRY(retint_kernel)
 	jnc  retint_restore_args
 	call preempt_schedule_irq
 	jmp exit_intr
-#endif	
+#endif
 
 	CFI_ENDPROC
 END(common_interrupt)
-	
+
 /*
  * APIC interrupts.
- */		
-	.macro apicinterrupt num,func
+ */
+.macro apicinterrupt num sym do_sym
+ENTRY(\sym)
 	INTR_FRAME
 	pushq $~(\num)
 	CFI_ADJUST_CFA_OFFSET 8
-	interrupt \func
+	interrupt \do_sym
 	jmp ret_from_intr
 	CFI_ENDPROC
-	.endm
-
-ENTRY(thermal_interrupt)
-	apicinterrupt THERMAL_APIC_VECTOR,smp_thermal_interrupt
-END(thermal_interrupt)
-
-ENTRY(threshold_interrupt)
-	apicinterrupt THRESHOLD_APIC_VECTOR,mce_threshold_interrupt
-END(threshold_interrupt)
-
-#ifdef CONFIG_SMP	
-ENTRY(reschedule_interrupt)
-	apicinterrupt RESCHEDULE_VECTOR,smp_reschedule_interrupt
-END(reschedule_interrupt)
-
-	.macro INVALIDATE_ENTRY num
-ENTRY(invalidate_interrupt\num)
-	apicinterrupt INVALIDATE_TLB_VECTOR_START+\num,smp_invalidate_interrupt	
-END(invalidate_interrupt\num)
-	.endm
+END(\sym)
+.endm
 
-	INVALIDATE_ENTRY 0
-	INVALIDATE_ENTRY 1
-	INVALIDATE_ENTRY 2
-	INVALIDATE_ENTRY 3
-	INVALIDATE_ENTRY 4
-	INVALIDATE_ENTRY 5
-	INVALIDATE_ENTRY 6
-	INVALIDATE_ENTRY 7
-
-ENTRY(call_function_interrupt)
-	apicinterrupt CALL_FUNCTION_VECTOR,smp_call_function_interrupt
-END(call_function_interrupt)
-ENTRY(call_function_single_interrupt)
-	apicinterrupt CALL_FUNCTION_SINGLE_VECTOR,smp_call_function_single_interrupt
-END(call_function_single_interrupt)
-ENTRY(irq_move_cleanup_interrupt)
-	apicinterrupt IRQ_MOVE_CLEANUP_VECTOR,smp_irq_move_cleanup_interrupt
-END(irq_move_cleanup_interrupt)
+#ifdef CONFIG_SMP
+apicinterrupt IRQ_MOVE_CLEANUP_VECTOR \
+	irq_move_cleanup_interrupt smp_irq_move_cleanup_interrupt
 #endif
 
-ENTRY(apic_timer_interrupt)
-	apicinterrupt LOCAL_TIMER_VECTOR,smp_apic_timer_interrupt
-END(apic_timer_interrupt)
+apicinterrupt UV_BAU_MESSAGE \
+	uv_bau_message_intr1 uv_bau_message_interrupt
+apicinterrupt LOCAL_TIMER_VECTOR \
+	apic_timer_interrupt smp_apic_timer_interrupt
+
+#ifdef CONFIG_SMP
+apicinterrupt INVALIDATE_TLB_VECTOR_START+0 \
+	invalidate_interrupt0 smp_invalidate_interrupt
+apicinterrupt INVALIDATE_TLB_VECTOR_START+1 \
+	invalidate_interrupt1 smp_invalidate_interrupt
+apicinterrupt INVALIDATE_TLB_VECTOR_START+2 \
+	invalidate_interrupt2 smp_invalidate_interrupt
+apicinterrupt INVALIDATE_TLB_VECTOR_START+3 \
+	invalidate_interrupt3 smp_invalidate_interrupt
+apicinterrupt INVALIDATE_TLB_VECTOR_START+4 \
+	invalidate_interrupt4 smp_invalidate_interrupt
+apicinterrupt INVALIDATE_TLB_VECTOR_START+5 \
+	invalidate_interrupt5 smp_invalidate_interrupt
+apicinterrupt INVALIDATE_TLB_VECTOR_START+6 \
+	invalidate_interrupt6 smp_invalidate_interrupt
+apicinterrupt INVALIDATE_TLB_VECTOR_START+7 \
+	invalidate_interrupt7 smp_invalidate_interrupt
+#endif
 
-ENTRY(uv_bau_message_intr1)
-	apicinterrupt 220,uv_bau_message_interrupt
-END(uv_bau_message_intr1)
+apicinterrupt THRESHOLD_APIC_VECTOR \
+	threshold_interrupt mce_threshold_interrupt
+apicinterrupt THERMAL_APIC_VECTOR \
+	thermal_interrupt smp_thermal_interrupt
+
+#ifdef CONFIG_SMP
+apicinterrupt CALL_FUNCTION_SINGLE_VECTOR \
+	call_function_single_interrupt smp_call_function_single_interrupt
+apicinterrupt CALL_FUNCTION_VECTOR \
+	call_function_interrupt smp_call_function_interrupt
+apicinterrupt RESCHEDULE_VECTOR \
+	reschedule_interrupt smp_reschedule_interrupt
+#endif
 
-ENTRY(error_interrupt)
-	apicinterrupt ERROR_APIC_VECTOR,smp_error_interrupt
-END(error_interrupt)
+apicinterrupt ERROR_APIC_VECTOR \
+	error_interrupt smp_error_interrupt
+apicinterrupt SPURIOUS_APIC_VECTOR \
+	spurious_interrupt smp_spurious_interrupt
 
-ENTRY(spurious_interrupt)
-	apicinterrupt SPURIOUS_APIC_VECTOR,smp_spurious_interrupt
-END(spurious_interrupt)
-				
 /*
  * Exception entry points.
- */ 		
-	.macro zeroentry sym
+ */
+.macro zeroentry sym do_sym
+ENTRY(\sym)
 	INTR_FRAME
 	PARAVIRT_ADJUST_EXCEPTION_FRAME
-	pushq $0	/* push error code/oldrax */ 
-	CFI_ADJUST_CFA_OFFSET 8
-	pushq %rax	/* push real oldrax to the rdi slot */ 
-	CFI_ADJUST_CFA_OFFSET 8
-	CFI_REL_OFFSET rax,0
-	leaq  \sym(%rip),%rax
-	jmp error_entry
+	pushq_cfi $-1		/* ORIG_RAX: no syscall to restart */
+	subq $15*8,%rsp
+	CFI_ADJUST_CFA_OFFSET 15*8
+	call error_entry
+	DEFAULT_FRAME 0
+	movq %rsp,%rdi		/* pt_regs pointer */
+	xorl %esi,%esi		/* no error code */
+	call \do_sym
+	jmp error_exit		/* %ebx: no swapgs flag */
 	CFI_ENDPROC
-	.endm	
+END(\sym)
+.endm
 
-	.macro errorentry sym
-	XCPT_FRAME
+.macro paranoidzeroentry sym do_sym
+ENTRY(\sym)
+	INTR_FRAME
 	PARAVIRT_ADJUST_EXCEPTION_FRAME
-	pushq %rax
+	pushq $-1		/* ORIG_RAX: no syscall to restart */
 	CFI_ADJUST_CFA_OFFSET 8
-	CFI_REL_OFFSET rax,0
-	leaq  \sym(%rip),%rax
-	jmp error_entry
+	subq $15*8, %rsp
+	call save_paranoid
+	TRACE_IRQS_OFF
+	movq %rsp,%rdi		/* pt_regs pointer */
+	xorl %esi,%esi		/* no error code */
+	call \do_sym
+	jmp paranoid_exit	/* %ebx: no swapgs flag */
 	CFI_ENDPROC
-	.endm
+END(\sym)
+.endm
 
-	/* error code is on the stack already */
-	/* handle NMI like exceptions that can happen everywhere */
-	.macro paranoidentry sym, ist=0, irqtrace=1
-	SAVE_ALL
-	cld
-	movl $1,%ebx
-	movl  $MSR_GS_BASE,%ecx
-	rdmsr
-	testl %edx,%edx
-	js    1f
-	SWAPGS
-	xorl  %ebx,%ebx
-1:
-	.if \ist
-	movq	%gs:pda_data_offset, %rbp
-	.endif
-	.if \irqtrace
-	TRACE_IRQS_OFF
-	.endif
-	movq %rsp,%rdi
-	movq ORIG_RAX(%rsp),%rsi
-	movq $-1,ORIG_RAX(%rsp)
-	.if \ist
-	subq	$EXCEPTION_STKSZ, per_cpu__init_tss + TSS_ist + (\ist - 1) * 8(%rbp)
-	.endif
-	call \sym
-	.if \ist
-	addq	$EXCEPTION_STKSZ, per_cpu__init_tss + TSS_ist + (\ist - 1) * 8(%rbp)
-	.endif
-	DISABLE_INTERRUPTS(CLBR_NONE)
-	.if \irqtrace
+.macro paranoidzeroentry_ist sym do_sym ist
+ENTRY(\sym)
+	INTR_FRAME
+	PARAVIRT_ADJUST_EXCEPTION_FRAME
+	pushq $-1		/* ORIG_RAX: no syscall to restart */
+	CFI_ADJUST_CFA_OFFSET 8
+	subq $15*8, %rsp
+	call save_paranoid
 	TRACE_IRQS_OFF
-	.endif
-	.endm
+	movq %rsp,%rdi		/* pt_regs pointer */
+	xorl %esi,%esi		/* no error code */
+	movq %gs:pda_data_offset, %rbp
+	subq $EXCEPTION_STKSZ, per_cpu__init_tss + TSS_ist + (\ist - 1) * 8(%rbp)
+	call \do_sym
+	addq $EXCEPTION_STKSZ, per_cpu__init_tss + TSS_ist + (\ist - 1) * 8(%rbp)
+	jmp paranoid_exit	/* %ebx: no swapgs flag */
+	CFI_ENDPROC
+END(\sym)
+.endm
 
-	/*
- 	 * "Paranoid" exit path from exception stack.
-  	 * Paranoid because this is used by NMIs and cannot take
-	 * any kernel state for granted.
-	 * We don't do kernel preemption checks here, because only
-	 * NMI should be common and it does not enable IRQs and
-	 * cannot get reschedule ticks.
-	 *
-	 * "trace" is 0 for the NMI handler only, because irq-tracing
-	 * is fundamentally NMI-unsafe. (we cannot change the soft and
-	 * hard flags at once, atomically)
-	 */
-	.macro paranoidexit trace=1
-	/* ebx:	no swapgs flag */
-paranoid_exit\trace:
-	testl %ebx,%ebx				/* swapgs needed? */
-	jnz paranoid_restore\trace
-	testl $3,CS(%rsp)
-	jnz   paranoid_userspace\trace
-paranoid_swapgs\trace:
-	.if \trace
-	TRACE_IRQS_IRETQ 0
-	.endif
-	SWAPGS_UNSAFE_STACK
-paranoid_restore\trace:
-	RESTORE_ALL 8
-	jmp irq_return
-paranoid_userspace\trace:
-	GET_THREAD_INFO(%rcx)
-	movl TI_flags(%rcx),%ebx
-	andl $_TIF_WORK_MASK,%ebx
-	jz paranoid_swapgs\trace
-	movq %rsp,%rdi			/* &pt_regs */
-	call sync_regs
-	movq %rax,%rsp			/* switch stack for scheduling */
-	testl $_TIF_NEED_RESCHED,%ebx
-	jnz paranoid_schedule\trace
-	movl %ebx,%edx			/* arg3: thread flags */
-	.if \trace
-	TRACE_IRQS_ON
-	.endif
-	ENABLE_INTERRUPTS(CLBR_NONE)
-	xorl %esi,%esi 			/* arg2: oldset */
-	movq %rsp,%rdi 			/* arg1: &pt_regs */
-	call do_notify_resume
-	DISABLE_INTERRUPTS(CLBR_NONE)
-	.if \trace
-	TRACE_IRQS_OFF
-	.endif
-	jmp paranoid_userspace\trace
-paranoid_schedule\trace:
-	.if \trace
-	TRACE_IRQS_ON
-	.endif
-	ENABLE_INTERRUPTS(CLBR_ANY)
-	call schedule
-	DISABLE_INTERRUPTS(CLBR_ANY)
-	.if \trace
-	TRACE_IRQS_OFF
-	.endif
-	jmp paranoid_userspace\trace
+.macro errorentry sym do_sym
+ENTRY(\sym)
+	XCPT_FRAME
+	PARAVIRT_ADJUST_EXCEPTION_FRAME
+	subq $15*8,%rsp
+	CFI_ADJUST_CFA_OFFSET 15*8
+	call error_entry
+	DEFAULT_FRAME 0
+	movq %rsp,%rdi			/* pt_regs pointer */
+	movq ORIG_RAX(%rsp),%rsi	/* get error code */
+	movq $-1,ORIG_RAX(%rsp)		/* no syscall to restart */
+	call \do_sym
+	jmp error_exit			/* %ebx: no swapgs flag */
 	CFI_ENDPROC
-	.endm
+END(\sym)
+.endm
 
-/*
- * Exception entry point. This expects an error code/orig_rax on the stack
- * and the exception handler in %rax.	
- */ 		  				
-KPROBE_ENTRY(error_entry)
-	_frame RDI
-	CFI_REL_OFFSET rax,0
-	/* rdi slot contains rax, oldrax contains error code */
-	cld	
-	subq  $14*8,%rsp
-	CFI_ADJUST_CFA_OFFSET	(14*8)
-	movq %rsi,13*8(%rsp)
-	CFI_REL_OFFSET	rsi,RSI
-	movq 14*8(%rsp),%rsi	/* load rax from rdi slot */
-	CFI_REGISTER	rax,rsi
-	movq %rdx,12*8(%rsp)
-	CFI_REL_OFFSET	rdx,RDX
-	movq %rcx,11*8(%rsp)
-	CFI_REL_OFFSET	rcx,RCX
-	movq %rsi,10*8(%rsp)	/* store rax */ 
-	CFI_REL_OFFSET	rax,RAX
-	movq %r8, 9*8(%rsp)
-	CFI_REL_OFFSET	r8,R8
-	movq %r9, 8*8(%rsp)
-	CFI_REL_OFFSET	r9,R9
-	movq %r10,7*8(%rsp)
-	CFI_REL_OFFSET	r10,R10
-	movq %r11,6*8(%rsp)
-	CFI_REL_OFFSET	r11,R11
-	movq %rbx,5*8(%rsp) 
-	CFI_REL_OFFSET	rbx,RBX
-	movq %rbp,4*8(%rsp) 
-	CFI_REL_OFFSET	rbp,RBP
-	movq %r12,3*8(%rsp) 
-	CFI_REL_OFFSET	r12,R12
-	movq %r13,2*8(%rsp) 
-	CFI_REL_OFFSET	r13,R13
-	movq %r14,1*8(%rsp) 
-	CFI_REL_OFFSET	r14,R14
-	movq %r15,(%rsp) 
-	CFI_REL_OFFSET	r15,R15
-	xorl %ebx,%ebx	
-	testl $3,CS(%rsp)
-	je  error_kernelspace
-error_swapgs:	
-	SWAPGS
-error_sti:
-	TRACE_IRQS_OFF
-	movq %rdi,RDI(%rsp) 	
-	CFI_REL_OFFSET	rdi,RDI
-	movq %rsp,%rdi
-	movq ORIG_RAX(%rsp),%rsi	/* get error code */ 
-	movq $-1,ORIG_RAX(%rsp)
-	call *%rax
-	/* ebx:	no swapgs flag (1: don't need swapgs, 0: need it) */
-error_exit:
-	movl %ebx,%eax
-	RESTORE_REST
-	DISABLE_INTERRUPTS(CLBR_NONE)
+	/* error code is on the stack already */
+.macro paranoiderrorentry sym do_sym
+ENTRY(\sym)
+	XCPT_FRAME
+	PARAVIRT_ADJUST_EXCEPTION_FRAME
+	subq $15*8,%rsp
+	CFI_ADJUST_CFA_OFFSET 15*8
+	call save_paranoid
+	DEFAULT_FRAME 0
 	TRACE_IRQS_OFF
-	GET_THREAD_INFO(%rcx)	
-	testl %eax,%eax
-	jne  retint_kernel
-	LOCKDEP_SYS_EXIT_IRQ
-	movl  TI_flags(%rcx),%edx
-	movl  $_TIF_WORK_MASK,%edi
-	andl  %edi,%edx
-	jnz  retint_careful
-	jmp retint_swapgs
+	movq %rsp,%rdi			/* pt_regs pointer */
+	movq ORIG_RAX(%rsp),%rsi	/* get error code */
+	movq $-1,ORIG_RAX(%rsp)		/* no syscall to restart */
+	call \do_sym
+	jmp paranoid_exit		/* %ebx: no swapgs flag */
 	CFI_ENDPROC
+END(\sym)
+.endm
 
-error_kernelspace:
-	incl %ebx
-       /* There are two places in the kernel that can potentially fault with
-          usergs. Handle them here. The exception handlers after
-	   iret run with kernel gs again, so don't set the user space flag.
-	   B stepping K8s sometimes report an truncated RIP for IRET 
-	   exceptions returning to compat mode. Check for these here too. */
-	leaq irq_return(%rip),%rcx
-	cmpq %rcx,RIP(%rsp)
-	je   error_swapgs
-	movl %ecx,%ecx	/* zero extend */
-	cmpq %rcx,RIP(%rsp)
-	je   error_swapgs
-	cmpq $gs_change,RIP(%rsp)
-        je   error_swapgs
-	jmp  error_sti
-KPROBE_END(error_entry)
-	
-       /* Reload gs selector with exception handling */
-       /* edi:  new selector */ 
+zeroentry divide_error do_divide_error
+zeroentry overflow do_overflow
+zeroentry bounds do_bounds
+zeroentry invalid_op do_invalid_op
+zeroentry device_not_available do_device_not_available
+paranoiderrorentry double_fault do_double_fault
+zeroentry coprocessor_segment_overrun do_coprocessor_segment_overrun
+errorentry invalid_TSS do_invalid_TSS
+errorentry segment_not_present do_segment_not_present
+zeroentry spurious_interrupt_bug do_spurious_interrupt_bug
+zeroentry coprocessor_error do_coprocessor_error
+errorentry alignment_check do_alignment_check
+zeroentry simd_coprocessor_error do_simd_coprocessor_error
+
+	/* Reload gs selector with exception handling */
+	/* edi:  new selector */
 ENTRY(native_load_gs_index)
 	CFI_STARTPROC
 	pushf
 	CFI_ADJUST_CFA_OFFSET 8
 	DISABLE_INTERRUPTS(CLBR_ANY | ~(CLBR_RDI))
-        SWAPGS
-gs_change:     
-        movl %edi,%gs   
+	SWAPGS
+gs_change:
+	movl %edi,%gs
 2:	mfence		/* workaround */
 	SWAPGS
-        popf
+	popf
 	CFI_ADJUST_CFA_OFFSET -8
-        ret
+	ret
 	CFI_ENDPROC
-ENDPROC(native_load_gs_index)
-       
-        .section __ex_table,"a"
-        .align 8
-        .quad gs_change,bad_gs
-        .previous
-        .section .fixup,"ax"
+END(native_load_gs_index)
+
+	.section __ex_table,"a"
+	.align 8
+	.quad gs_change,bad_gs
+	.previous
+	.section .fixup,"ax"
 	/* running with kernelgs */
-bad_gs: 
+bad_gs:
 	SWAPGS			/* switch back to user gs */
 	xorl %eax,%eax
-        movl %eax,%gs
-        jmp  2b
-        .previous       
-	
+	movl %eax,%gs
+	jmp  2b
+	.previous
+
 /*
  * Create a kernel thread.
  *
@@ -1138,7 +1149,7 @@ ENTRY(kernel_thread)
 
 	xorl %r8d,%r8d
 	xorl %r9d,%r9d
-	
+
 	# clone now
 	call do_fork
 	movq %rax,RAX(%rsp)
@@ -1149,15 +1160,15 @@ ENTRY(kernel_thread)
 	 * so internally to the x86_64 port you can rely on kernel_thread()
 	 * not to reschedule the child before returning, this avoids the need
 	 * of hacks for example to fork off the per-CPU idle tasks.
-         * [Hopefully no generic code relies on the reschedule -AK]	
+	 * [Hopefully no generic code relies on the reschedule -AK]
 	 */
 	RESTORE_ALL
 	UNFAKE_STACK_FRAME
 	ret
 	CFI_ENDPROC
-ENDPROC(kernel_thread)
-	
-child_rip:
+END(kernel_thread)
+
+ENTRY(child_rip)
 	pushq $0		# fake return address
 	CFI_STARTPROC
 	/*
@@ -1170,8 +1181,9 @@ child_rip:
 	# exit
 	mov %eax, %edi
 	call do_exit
+	ud2			# padding for call trace
 	CFI_ENDPROC
-ENDPROC(child_rip)
+END(child_rip)
 
 /*
  * execve(). This function needs to use IRET, not SYSRET, to set up all state properly.
@@ -1191,10 +1203,10 @@ ENDPROC(child_rip)
 ENTRY(kernel_execve)
 	CFI_STARTPROC
 	FAKE_STACK_FRAME $0
-	SAVE_ALL	
+	SAVE_ALL
 	movq %rsp,%rcx
 	call sys_execve
-	movq %rax, RAX(%rsp)	
+	movq %rax, RAX(%rsp)
 	RESTORE_REST
 	testq %rax,%rax
 	je int_ret_from_sys_call
@@ -1202,129 +1214,7 @@ ENTRY(kernel_execve)
 	UNFAKE_STACK_FRAME
 	ret
 	CFI_ENDPROC
-ENDPROC(kernel_execve)
-
-KPROBE_ENTRY(page_fault)
-	errorentry do_page_fault
-KPROBE_END(page_fault)
-
-ENTRY(coprocessor_error)
-	zeroentry do_coprocessor_error
-END(coprocessor_error)
-
-ENTRY(simd_coprocessor_error)
-	zeroentry do_simd_coprocessor_error	
-END(simd_coprocessor_error)
-
-ENTRY(device_not_available)
-	zeroentry do_device_not_available
-END(device_not_available)
-
-	/* runs on exception stack */
-KPROBE_ENTRY(debug)
- 	INTR_FRAME
-	PARAVIRT_ADJUST_EXCEPTION_FRAME
-	pushq $0
-	CFI_ADJUST_CFA_OFFSET 8		
-	paranoidentry do_debug, DEBUG_STACK
-	paranoidexit
-KPROBE_END(debug)
-
-	/* runs on exception stack */	
-KPROBE_ENTRY(nmi)
-	INTR_FRAME
-	PARAVIRT_ADJUST_EXCEPTION_FRAME
-	pushq $-1
-	CFI_ADJUST_CFA_OFFSET 8
-	paranoidentry do_nmi, 0, 0
-#ifdef CONFIG_TRACE_IRQFLAGS
-	paranoidexit 0
-#else
-	jmp paranoid_exit1
- 	CFI_ENDPROC
-#endif
-KPROBE_END(nmi)
-
-KPROBE_ENTRY(int3)
- 	INTR_FRAME
-	PARAVIRT_ADJUST_EXCEPTION_FRAME
- 	pushq $0
- 	CFI_ADJUST_CFA_OFFSET 8
- 	paranoidentry do_int3, DEBUG_STACK
- 	jmp paranoid_exit1
- 	CFI_ENDPROC
-KPROBE_END(int3)
-
-ENTRY(overflow)
-	zeroentry do_overflow
-END(overflow)
-
-ENTRY(bounds)
-	zeroentry do_bounds
-END(bounds)
-
-ENTRY(invalid_op)
-	zeroentry do_invalid_op	
-END(invalid_op)
-
-ENTRY(coprocessor_segment_overrun)
-	zeroentry do_coprocessor_segment_overrun
-END(coprocessor_segment_overrun)
-
-	/* runs on exception stack */
-ENTRY(double_fault)
-	XCPT_FRAME
-	PARAVIRT_ADJUST_EXCEPTION_FRAME
-	paranoidentry do_double_fault
-	jmp paranoid_exit1
-	CFI_ENDPROC
-END(double_fault)
-
-ENTRY(invalid_TSS)
-	errorentry do_invalid_TSS
-END(invalid_TSS)
-
-ENTRY(segment_not_present)
-	errorentry do_segment_not_present
-END(segment_not_present)
-
-	/* runs on exception stack */
-ENTRY(stack_segment)
-	XCPT_FRAME
-	PARAVIRT_ADJUST_EXCEPTION_FRAME
-	paranoidentry do_stack_segment
-	jmp paranoid_exit1
-	CFI_ENDPROC
-END(stack_segment)
-
-KPROBE_ENTRY(general_protection)
-	errorentry do_general_protection
-KPROBE_END(general_protection)
-
-ENTRY(alignment_check)
-	errorentry do_alignment_check
-END(alignment_check)
-
-ENTRY(divide_error)
-	zeroentry do_divide_error
-END(divide_error)
-
-ENTRY(spurious_interrupt_bug)
-	zeroentry do_spurious_interrupt_bug
-END(spurious_interrupt_bug)
-
-#ifdef CONFIG_X86_MCE
-	/* runs on exception stack */
-ENTRY(machine_check)
-	INTR_FRAME
-	PARAVIRT_ADJUST_EXCEPTION_FRAME
-	pushq $0
-	CFI_ADJUST_CFA_OFFSET 8	
-	paranoidentry do_machine_check
-	jmp paranoid_exit1
-	CFI_ENDPROC
-END(machine_check)
-#endif
+END(kernel_execve)
 
 /* Call softirq on interrupt stack. Interrupts are off. */
 ENTRY(call_softirq)
@@ -1344,40 +1234,33 @@ ENTRY(call_softirq)
 	decl %gs:pda_irqcount
 	ret
 	CFI_ENDPROC
-ENDPROC(call_softirq)
-
-KPROBE_ENTRY(ignore_sysret)
-	CFI_STARTPROC
-	mov $-ENOSYS,%eax
-	sysret
-	CFI_ENDPROC
-ENDPROC(ignore_sysret)
+END(call_softirq)
 
 #ifdef CONFIG_XEN
-ENTRY(xen_hypervisor_callback)
-	zeroentry xen_do_hypervisor_callback
-END(xen_hypervisor_callback)
+zeroentry xen_hypervisor_callback xen_do_hypervisor_callback
 
 /*
-# A note on the "critical region" in our callback handler.
-# We want to avoid stacking callback handlers due to events occurring
-# during handling of the last event. To do this, we keep events disabled
-# until we've done all processing. HOWEVER, we must enable events before
-# popping the stack frame (can't be done atomically) and so it would still
-# be possible to get enough handler activations to overflow the stack.
-# Although unlikely, bugs of that kind are hard to track down, so we'd
-# like to avoid the possibility.
-# So, on entry to the handler we detect whether we interrupted an
-# existing activation in its critical region -- if so, we pop the current
-# activation and restart the handler using the previous one.
-*/
+ * A note on the "critical region" in our callback handler.
+ * We want to avoid stacking callback handlers due to events occurring
+ * during handling of the last event. To do this, we keep events disabled
+ * until we've done all processing. HOWEVER, we must enable events before
+ * popping the stack frame (can't be done atomically) and so it would still
+ * be possible to get enough handler activations to overflow the stack.
+ * Although unlikely, bugs of that kind are hard to track down, so we'd
+ * like to avoid the possibility.
+ * So, on entry to the handler we detect whether we interrupted an
+ * existing activation in its critical region -- if so, we pop the current
+ * activation and restart the handler using the previous one.
+ */
 ENTRY(xen_do_hypervisor_callback)   # do_hypervisor_callback(struct *pt_regs)
 	CFI_STARTPROC
-/* Since we don't modify %rdi, evtchn_do_upall(struct *pt_regs) will
-   see the correct pointer to the pt_regs */
+/*
+ * Since we don't modify %rdi, evtchn_do_upall(struct *pt_regs) will
+ * see the correct pointer to the pt_regs
+ */
 	movq %rdi, %rsp            # we don't return, adjust the stack frame
 	CFI_ENDPROC
-	CFI_DEFAULT_STACK
+	DEFAULT_FRAME
 11:	incl %gs:pda_irqcount
 	movq %rsp,%rbp
 	CFI_DEF_CFA_REGISTER rbp
@@ -1392,23 +1275,26 @@ ENTRY(xen_do_hypervisor_callback)   # do_hypervisor_callback(struct *pt_regs)
 END(do_hypervisor_callback)
 
 /*
-# Hypervisor uses this for application faults while it executes.
-# We get here for two reasons:
-#  1. Fault while reloading DS, ES, FS or GS
-#  2. Fault while executing IRET
-# Category 1 we do not need to fix up as Xen has already reloaded all segment
-# registers that could be reloaded and zeroed the others.
-# Category 2 we fix up by killing the current process. We cannot use the
-# normal Linux return path in this case because if we use the IRET hypercall
-# to pop the stack frame we end up in an infinite loop of failsafe callbacks.
-# We distinguish between categories by comparing each saved segment register
-# with its current contents: any discrepancy means we in category 1.
-*/
+ * Hypervisor uses this for application faults while it executes.
+ * We get here for two reasons:
+ *  1. Fault while reloading DS, ES, FS or GS
+ *  2. Fault while executing IRET
+ * Category 1 we do not need to fix up as Xen has already reloaded all segment
+ * registers that could be reloaded and zeroed the others.
+ * Category 2 we fix up by killing the current process. We cannot use the
+ * normal Linux return path in this case because if we use the IRET hypercall
+ * to pop the stack frame we end up in an infinite loop of failsafe callbacks.
+ * We distinguish between categories by comparing each saved segment register
+ * with its current contents: any discrepancy means we in category 1.
+ */
 ENTRY(xen_failsafe_callback)
-	framesz = (RIP-0x30)	/* workaround buggy gas */
-	_frame framesz
-	CFI_REL_OFFSET rcx, 0
-	CFI_REL_OFFSET r11, 8
+	INTR_FRAME 1 (6*8)
+	/*CFI_REL_OFFSET gs,GS*/
+	/*CFI_REL_OFFSET fs,FS*/
+	/*CFI_REL_OFFSET es,ES*/
+	/*CFI_REL_OFFSET ds,DS*/
+	CFI_REL_OFFSET r11,8
+	CFI_REL_OFFSET rcx,0
 	movw %ds,%cx
 	cmpw %cx,0x10(%rsp)
 	CFI_REMEMBER_STATE
@@ -1429,12 +1315,9 @@ ENTRY(xen_failsafe_callback)
 	CFI_RESTORE r11
 	addq $0x30,%rsp
 	CFI_ADJUST_CFA_OFFSET -0x30
-	pushq $0
-	CFI_ADJUST_CFA_OFFSET 8
-	pushq %r11
-	CFI_ADJUST_CFA_OFFSET 8
-	pushq %rcx
-	CFI_ADJUST_CFA_OFFSET 8
+	pushq_cfi $0	/* RIP */
+	pushq_cfi %r11
+	pushq_cfi %rcx
 	jmp general_protection
 	CFI_RESTORE_STATE
 1:	/* Segment mismatch => Category 1 (Bad segment). Retry the IRET. */
@@ -1444,11 +1327,223 @@ ENTRY(xen_failsafe_callback)
 	CFI_RESTORE r11
 	addq $0x30,%rsp
 	CFI_ADJUST_CFA_OFFSET -0x30
-	pushq $0
-	CFI_ADJUST_CFA_OFFSET 8
+	pushq_cfi $0
 	SAVE_ALL
 	jmp error_exit
 	CFI_ENDPROC
 END(xen_failsafe_callback)
 
 #endif /* CONFIG_XEN */
+
+/*
+ * Some functions should be protected against kprobes
+ */
+	.pushsection .kprobes.text, "ax"
+
+paranoidzeroentry_ist debug do_debug DEBUG_STACK
+paranoidzeroentry_ist int3 do_int3 DEBUG_STACK
+paranoiderrorentry stack_segment do_stack_segment
+errorentry general_protection do_general_protection
+errorentry page_fault do_page_fault
+#ifdef CONFIG_X86_MCE
+paranoidzeroentry machine_check do_machine_check
+#endif
+
+	/*
+	 * "Paranoid" exit path from exception stack.
+	 * Paranoid because this is used by NMIs and cannot take
+	 * any kernel state for granted.
+	 * We don't do kernel preemption checks here, because only
+	 * NMI should be common and it does not enable IRQs and
+	 * cannot get reschedule ticks.
+	 *
+	 * "trace" is 0 for the NMI handler only, because irq-tracing
+	 * is fundamentally NMI-unsafe. (we cannot change the soft and
+	 * hard flags at once, atomically)
+	 */
+
+	/* ebx:	no swapgs flag */
+ENTRY(paranoid_exit)
+	INTR_FRAME
+	DISABLE_INTERRUPTS(CLBR_NONE)
+	TRACE_IRQS_OFF
+	testl %ebx,%ebx				/* swapgs needed? */
+	jnz paranoid_restore
+	testl $3,CS(%rsp)
+	jnz   paranoid_userspace
+paranoid_swapgs:
+	TRACE_IRQS_IRETQ 0
+	SWAPGS_UNSAFE_STACK
+paranoid_restore:
+	RESTORE_ALL 8
+	jmp irq_return
+paranoid_userspace:
+	GET_THREAD_INFO(%rcx)
+	movl TI_flags(%rcx),%ebx
+	andl $_TIF_WORK_MASK,%ebx
+	jz paranoid_swapgs
+	movq %rsp,%rdi			/* &pt_regs */
+	call sync_regs
+	movq %rax,%rsp			/* switch stack for scheduling */
+	testl $_TIF_NEED_RESCHED,%ebx
+	jnz paranoid_schedule
+	movl %ebx,%edx			/* arg3: thread flags */
+	TRACE_IRQS_ON
+	ENABLE_INTERRUPTS(CLBR_NONE)
+	xorl %esi,%esi 			/* arg2: oldset */
+	movq %rsp,%rdi 			/* arg1: &pt_regs */
+	call do_notify_resume
+	DISABLE_INTERRUPTS(CLBR_NONE)
+	TRACE_IRQS_OFF
+	jmp paranoid_userspace
+paranoid_schedule:
+	TRACE_IRQS_ON
+	ENABLE_INTERRUPTS(CLBR_ANY)
+	call schedule
+	DISABLE_INTERRUPTS(CLBR_ANY)
+	TRACE_IRQS_OFF
+	jmp paranoid_userspace
+	CFI_ENDPROC
+END(paranoid_exit)
+
+/*
+ * Exception entry point. This expects an error code/orig_rax on the stack.
+ * returns in "no swapgs flag" in %ebx.
+ */
+ENTRY(error_entry)
+	XCPT_FRAME
+	CFI_ADJUST_CFA_OFFSET 15*8
+	/* oldrax contains error code */
+	cld
+	movq_cfi rdi, RDI+8
+	movq_cfi rsi, RSI+8
+	movq_cfi rdx, RDX+8
+	movq_cfi rcx, RCX+8
+	movq_cfi rax, RAX+8
+	movq_cfi  r8,  R8+8
+	movq_cfi  r9,  R9+8
+	movq_cfi r10, R10+8
+	movq_cfi r11, R11+8
+	movq_cfi rbx, RBX+8
+	movq_cfi rbp, RBP+8
+	movq_cfi r12, R12+8
+	movq_cfi r13, R13+8
+	movq_cfi r14, R14+8
+	movq_cfi r15, R15+8
+	xorl %ebx,%ebx
+	testl $3,CS+8(%rsp)
+	je error_kernelspace
+error_swapgs:
+	SWAPGS
+error_sti:
+	TRACE_IRQS_OFF
+	ret
+	CFI_ENDPROC
+
+/*
+ * There are two places in the kernel that can potentially fault with
+ * usergs. Handle them here. The exception handlers after iret run with
+ * kernel gs again, so don't set the user space flag. B stepping K8s
+ * sometimes report an truncated RIP for IRET exceptions returning to
+ * compat mode. Check for these here too.
+ */
+error_kernelspace:
+	incl %ebx
+	leaq irq_return(%rip),%rcx
+	cmpq %rcx,RIP+8(%rsp)
+	je error_swapgs
+	movl %ecx,%ecx	/* zero extend */
+	cmpq %rcx,RIP+8(%rsp)
+	je error_swapgs
+	cmpq $gs_change,RIP+8(%rsp)
+	je error_swapgs
+	jmp error_sti
+END(error_entry)
+
+
+/* ebx:	no swapgs flag (1: don't need swapgs, 0: need it) */
+ENTRY(error_exit)
+	DEFAULT_FRAME
+	movl %ebx,%eax
+	RESTORE_REST
+	DISABLE_INTERRUPTS(CLBR_NONE)
+	TRACE_IRQS_OFF
+	GET_THREAD_INFO(%rcx)
+	testl %eax,%eax
+	jne retint_kernel
+	LOCKDEP_SYS_EXIT_IRQ
+	movl TI_flags(%rcx),%edx
+	movl $_TIF_WORK_MASK,%edi
+	andl %edi,%edx
+	jnz retint_careful
+	jmp retint_swapgs
+	CFI_ENDPROC
+END(error_exit)
+
+
+	/* runs on exception stack */
+ENTRY(nmi)
+	INTR_FRAME
+	PARAVIRT_ADJUST_EXCEPTION_FRAME
+	pushq_cfi $-1
+	subq $15*8, %rsp
+	CFI_ADJUST_CFA_OFFSET 15*8
+	call save_paranoid
+	DEFAULT_FRAME 0
+	/* paranoidentry do_nmi, 0; without TRACE_IRQS_OFF */
+	movq %rsp,%rdi
+	movq $-1,%rsi
+	call do_nmi
+#ifdef CONFIG_TRACE_IRQFLAGS
+	/* paranoidexit; without TRACE_IRQS_OFF */
+	/* ebx:	no swapgs flag */
+	DISABLE_INTERRUPTS(CLBR_NONE)
+	testl %ebx,%ebx				/* swapgs needed? */
+	jnz nmi_restore
+	testl $3,CS(%rsp)
+	jnz nmi_userspace
+nmi_swapgs:
+	SWAPGS_UNSAFE_STACK
+nmi_restore:
+	RESTORE_ALL 8
+	jmp irq_return
+nmi_userspace:
+	GET_THREAD_INFO(%rcx)
+	movl TI_flags(%rcx),%ebx
+	andl $_TIF_WORK_MASK,%ebx
+	jz nmi_swapgs
+	movq %rsp,%rdi			/* &pt_regs */
+	call sync_regs
+	movq %rax,%rsp			/* switch stack for scheduling */
+	testl $_TIF_NEED_RESCHED,%ebx
+	jnz nmi_schedule
+	movl %ebx,%edx			/* arg3: thread flags */
+	ENABLE_INTERRUPTS(CLBR_NONE)
+	xorl %esi,%esi 			/* arg2: oldset */
+	movq %rsp,%rdi 			/* arg1: &pt_regs */
+	call do_notify_resume
+	DISABLE_INTERRUPTS(CLBR_NONE)
+	jmp nmi_userspace
+nmi_schedule:
+	ENABLE_INTERRUPTS(CLBR_ANY)
+	call schedule
+	DISABLE_INTERRUPTS(CLBR_ANY)
+	jmp nmi_userspace
+	CFI_ENDPROC
+#else
+	jmp paranoid_exit
+	CFI_ENDPROC
+#endif
+END(nmi)
+
+ENTRY(ignore_sysret)
+	CFI_STARTPROC
+	mov $-ENOSYS,%eax
+	sysret
+	CFI_ENDPROC
+END(ignore_sysret)
+
+/*
+ * End of kprobes section
+ */
+	.popsection
diff --git a/arch/x86/kernel/es7000_32.c b/arch/x86/kernel/es7000_32.c
index 0aa2c443d600..53699c931ad4 100644
--- a/arch/x86/kernel/es7000_32.c
+++ b/arch/x86/kernel/es7000_32.c
@@ -38,8 +38,11 @@
 #include <asm/io.h>
 #include <asm/nmi.h>
 #include <asm/smp.h>
+#include <asm/atomic.h>
 #include <asm/apicdef.h>
 #include <mach_mpparse.h>
+#include <asm/genapic.h>
+#include <asm/setup.h>
 
 /*
  * ES7000 chipsets
@@ -161,6 +164,43 @@ es7000_rename_gsi(int ioapic, int gsi)
 	return gsi;
 }
 
+static int wakeup_secondary_cpu_via_mip(int cpu, unsigned long eip)
+{
+	unsigned long vect = 0, psaival = 0;
+
+	if (psai == NULL)
+		return -1;
+
+	vect = ((unsigned long)__pa(eip)/0x1000) << 16;
+	psaival = (0x1000000 | vect | cpu);
+
+	while (*psai & 0x1000000)
+		;
+
+	*psai = psaival;
+
+	return 0;
+}
+
+static void noop_wait_for_deassert(atomic_t *deassert_not_used)
+{
+}
+
+static int __init es7000_update_genapic(void)
+{
+	genapic->wakeup_cpu = wakeup_secondary_cpu_via_mip;
+
+	/* MPENTIUMIII */
+	if (boot_cpu_data.x86 == 6 &&
+	    (boot_cpu_data.x86_model >= 7 || boot_cpu_data.x86_model <= 11)) {
+		es7000_update_genapic_to_cluster();
+		genapic->wait_for_init_deassert = noop_wait_for_deassert;
+		genapic->wakeup_cpu = wakeup_secondary_cpu_via_mip;
+	}
+
+	return 0;
+}
+
 void __init
 setup_unisys(void)
 {
@@ -176,6 +216,8 @@ setup_unisys(void)
 	else
 		es7000_plat = ES7000_CLASSIC;
 	ioapic_renumber_irq = es7000_rename_gsi;
+
+	x86_quirks->update_genapic = es7000_update_genapic;
 }
 
 /*
@@ -317,26 +359,6 @@ es7000_mip_write(struct mip_reg *mip_reg)
 	return status;
 }
 
-int
-es7000_start_cpu(int cpu, unsigned long eip)
-{
-	unsigned long vect = 0, psaival = 0;
-
-	if (psai == NULL)
-		return -1;
-
-	vect = ((unsigned long)__pa(eip)/0x1000) << 16;
-	psaival = (0x1000000 | vect | cpu);
-
-	while (*psai & 0x1000000)
-                ;
-
-	*psai = psaival;
-
-	return 0;
-
-}
-
 void __init
 es7000_sw_apic(void)
 {
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index 50ea0ac8c9bf..bb137f7297ed 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -14,14 +14,17 @@
 #include <linux/uaccess.h>
 #include <linux/ftrace.h>
 #include <linux/percpu.h>
+#include <linux/sched.h>
 #include <linux/init.h>
 #include <linux/list.h>
 
 #include <asm/ftrace.h>
+#include <linux/ftrace.h>
 #include <asm/nops.h>
+#include <asm/nmi.h>
 
 
-static unsigned char ftrace_nop[MCOUNT_INSN_SIZE];
+#ifdef CONFIG_DYNAMIC_FTRACE
 
 union ftrace_code_union {
 	char code[MCOUNT_INSN_SIZE];
@@ -31,18 +34,12 @@ union ftrace_code_union {
 	} __attribute__((packed));
 };
 
-
 static int ftrace_calc_offset(long ip, long addr)
 {
 	return (int)(addr - ip);
 }
 
-unsigned char *ftrace_nop_replace(void)
-{
-	return ftrace_nop;
-}
-
-unsigned char *ftrace_call_replace(unsigned long ip, unsigned long addr)
+static unsigned char *ftrace_call_replace(unsigned long ip, unsigned long addr)
 {
 	static union ftrace_code_union calc;
 
@@ -56,7 +53,143 @@ unsigned char *ftrace_call_replace(unsigned long ip, unsigned long addr)
 	return calc.code;
 }
 
-int
+/*
+ * Modifying code must take extra care. On an SMP machine, if
+ * the code being modified is also being executed on another CPU
+ * that CPU will have undefined results and possibly take a GPF.
+ * We use kstop_machine to stop other CPUS from exectuing code.
+ * But this does not stop NMIs from happening. We still need
+ * to protect against that. We separate out the modification of
+ * the code to take care of this.
+ *
+ * Two buffers are added: An IP buffer and a "code" buffer.
+ *
+ * 1) Put the instruction pointer into the IP buffer
+ *    and the new code into the "code" buffer.
+ * 2) Set a flag that says we are modifying code
+ * 3) Wait for any running NMIs to finish.
+ * 4) Write the code
+ * 5) clear the flag.
+ * 6) Wait for any running NMIs to finish.
+ *
+ * If an NMI is executed, the first thing it does is to call
+ * "ftrace_nmi_enter". This will check if the flag is set to write
+ * and if it is, it will write what is in the IP and "code" buffers.
+ *
+ * The trick is, it does not matter if everyone is writing the same
+ * content to the code location. Also, if a CPU is executing code
+ * it is OK to write to that code location if the contents being written
+ * are the same as what exists.
+ */
+
+static atomic_t in_nmi = ATOMIC_INIT(0);
+static int mod_code_status;		/* holds return value of text write */
+static int mod_code_write;		/* set when NMI should do the write */
+static void *mod_code_ip;		/* holds the IP to write to */
+static void *mod_code_newcode;		/* holds the text to write to the IP */
+
+static unsigned nmi_wait_count;
+static atomic_t nmi_update_count = ATOMIC_INIT(0);
+
+int ftrace_arch_read_dyn_info(char *buf, int size)
+{
+	int r;
+
+	r = snprintf(buf, size, "%u %u",
+		     nmi_wait_count,
+		     atomic_read(&nmi_update_count));
+	return r;
+}
+
+static void ftrace_mod_code(void)
+{
+	/*
+	 * Yes, more than one CPU process can be writing to mod_code_status.
+	 *    (and the code itself)
+	 * But if one were to fail, then they all should, and if one were
+	 * to succeed, then they all should.
+	 */
+	mod_code_status = probe_kernel_write(mod_code_ip, mod_code_newcode,
+					     MCOUNT_INSN_SIZE);
+
+}
+
+void ftrace_nmi_enter(void)
+{
+	atomic_inc(&in_nmi);
+	/* Must have in_nmi seen before reading write flag */
+	smp_mb();
+	if (mod_code_write) {
+		ftrace_mod_code();
+		atomic_inc(&nmi_update_count);
+	}
+}
+
+void ftrace_nmi_exit(void)
+{
+	/* Finish all executions before clearing in_nmi */
+	smp_wmb();
+	atomic_dec(&in_nmi);
+}
+
+static void wait_for_nmi(void)
+{
+	int waited = 0;
+
+	while (atomic_read(&in_nmi)) {
+		waited = 1;
+		cpu_relax();
+	}
+
+	if (waited)
+		nmi_wait_count++;
+}
+
+static int
+do_ftrace_mod_code(unsigned long ip, void *new_code)
+{
+	mod_code_ip = (void *)ip;
+	mod_code_newcode = new_code;
+
+	/* The buffers need to be visible before we let NMIs write them */
+	smp_wmb();
+
+	mod_code_write = 1;
+
+	/* Make sure write bit is visible before we wait on NMIs */
+	smp_mb();
+
+	wait_for_nmi();
+
+	/* Make sure all running NMIs have finished before we write the code */
+	smp_mb();
+
+	ftrace_mod_code();
+
+	/* Make sure the write happens before clearing the bit */
+	smp_wmb();
+
+	mod_code_write = 0;
+
+	/* make sure NMIs see the cleared bit */
+	smp_mb();
+
+	wait_for_nmi();
+
+	return mod_code_status;
+}
+
+
+
+
+static unsigned char ftrace_nop[MCOUNT_INSN_SIZE];
+
+static unsigned char *ftrace_nop_replace(void)
+{
+	return ftrace_nop;
+}
+
+static int
 ftrace_modify_code(unsigned long ip, unsigned char *old_code,
 		   unsigned char *new_code)
 {
@@ -81,7 +214,7 @@ ftrace_modify_code(unsigned long ip, unsigned char *old_code,
 		return -EINVAL;
 
 	/* replace the text with the new text */
-	if (probe_kernel_write((void *)ip, new_code, MCOUNT_INSN_SIZE))
+	if (do_ftrace_mod_code(ip, new_code))
 		return -EPERM;
 
 	sync_core();
@@ -89,6 +222,29 @@ ftrace_modify_code(unsigned long ip, unsigned char *old_code,
 	return 0;
 }
 
+int ftrace_make_nop(struct module *mod,
+		    struct dyn_ftrace *rec, unsigned long addr)
+{
+	unsigned char *new, *old;
+	unsigned long ip = rec->ip;
+
+	old = ftrace_call_replace(ip, addr);
+	new = ftrace_nop_replace();
+
+	return ftrace_modify_code(rec->ip, old, new);
+}
+
+int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
+{
+	unsigned char *new, *old;
+	unsigned long ip = rec->ip;
+
+	old = ftrace_nop_replace();
+	new = ftrace_call_replace(ip, addr);
+
+	return ftrace_modify_code(rec->ip, old, new);
+}
+
 int ftrace_update_ftrace_func(ftrace_func_t func)
 {
 	unsigned long ip = (unsigned long)(&ftrace_call);
@@ -165,3 +321,139 @@ int __init ftrace_dyn_arch_init(void *data)
 
 	return 0;
 }
+#endif
+
+#ifdef CONFIG_FUNCTION_RET_TRACER
+
+#ifndef CONFIG_DYNAMIC_FTRACE
+
+/*
+ * These functions are picked from those used on
+ * this page for dynamic ftrace. They have been
+ * simplified to ignore all traces in NMI context.
+ */
+static atomic_t in_nmi;
+
+void ftrace_nmi_enter(void)
+{
+	atomic_inc(&in_nmi);
+}
+
+void ftrace_nmi_exit(void)
+{
+	atomic_dec(&in_nmi);
+}
+#endif /* !CONFIG_DYNAMIC_FTRACE */
+
+/* Add a function return address to the trace stack on thread info.*/
+static int push_return_trace(unsigned long ret, unsigned long long time,
+				unsigned long func)
+{
+	int index;
+
+	if (!current->ret_stack)
+		return -EBUSY;
+
+	/* The return trace stack is full */
+	if (current->curr_ret_stack == FTRACE_RETFUNC_DEPTH - 1) {
+		atomic_inc(&current->trace_overrun);
+		return -EBUSY;
+	}
+
+	index = ++current->curr_ret_stack;
+	barrier();
+	current->ret_stack[index].ret = ret;
+	current->ret_stack[index].func = func;
+	current->ret_stack[index].calltime = time;
+
+	return 0;
+}
+
+/* Retrieve a function return address to the trace stack on thread info.*/
+static void pop_return_trace(unsigned long *ret, unsigned long long *time,
+				unsigned long *func, unsigned long *overrun)
+{
+	int index;
+
+	index = current->curr_ret_stack;
+	*ret = current->ret_stack[index].ret;
+	*func = current->ret_stack[index].func;
+	*time = current->ret_stack[index].calltime;
+	*overrun = atomic_read(&current->trace_overrun);
+	current->curr_ret_stack--;
+}
+
+/*
+ * Send the trace to the ring-buffer.
+ * @return the original return address.
+ */
+unsigned long ftrace_return_to_handler(void)
+{
+	struct ftrace_retfunc trace;
+	pop_return_trace(&trace.ret, &trace.calltime, &trace.func,
+			&trace.overrun);
+	trace.rettime = cpu_clock(raw_smp_processor_id());
+	ftrace_function_return(&trace);
+
+	return trace.ret;
+}
+
+/*
+ * Hook the return address and push it in the stack of return addrs
+ * in current thread info.
+ */
+void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr)
+{
+	unsigned long old;
+	unsigned long long calltime;
+	int faulted;
+	unsigned long return_hooker = (unsigned long)
+				&return_to_handler;
+
+	/* Nmi's are currently unsupported */
+	if (atomic_read(&in_nmi))
+		return;
+
+	/*
+	 * Protect against fault, even if it shouldn't
+	 * happen. This tool is too much intrusive to
+	 * ignore such a protection.
+	 */
+	asm volatile(
+		"1: movl (%[parent_old]), %[old]\n"
+		"2: movl %[return_hooker], (%[parent_replaced])\n"
+		"   movl $0, %[faulted]\n"
+
+		".section .fixup, \"ax\"\n"
+		"3: movl $1, %[faulted]\n"
+		".previous\n"
+
+		".section __ex_table, \"a\"\n"
+		"   .long 1b, 3b\n"
+		"   .long 2b, 3b\n"
+		".previous\n"
+
+		: [parent_replaced] "=r" (parent), [old] "=r" (old),
+		  [faulted] "=r" (faulted)
+		: [parent_old] "0" (parent), [return_hooker] "r" (return_hooker)
+		: "memory"
+	);
+
+	if (WARN_ON(faulted)) {
+		unregister_ftrace_return();
+		return;
+	}
+
+	if (WARN_ON(!__kernel_text_address(old))) {
+		unregister_ftrace_return();
+		*parent = old;
+		return;
+	}
+
+	calltime = cpu_clock(raw_smp_processor_id());
+
+	if (push_return_trace(old, calltime, self_addr) == -EBUSY)
+		*parent = old;
+}
+
+#endif /* CONFIG_FUNCTION_RET_TRACER */
diff --git a/arch/x86/kernel/genapic_64.c b/arch/x86/kernel/genapic_64.c
index 6c9bfc9e1e95..2bced78b0b8e 100644
--- a/arch/x86/kernel/genapic_64.c
+++ b/arch/x86/kernel/genapic_64.c
@@ -21,6 +21,7 @@
 #include <asm/smp.h>
 #include <asm/ipi.h>
 #include <asm/genapic.h>
+#include <asm/setup.h>
 
 extern struct genapic apic_flat;
 extern struct genapic apic_physflat;
@@ -53,6 +54,9 @@ void __init setup_apic_routing(void)
 			genapic = &apic_physflat;
 		printk(KERN_INFO "Setting APIC routing to %s\n", genapic->name);
 	}
+
+	if (x86_quirks->update_genapic)
+		x86_quirks->update_genapic();
 }
 
 /* Same for both flat and physical. */
diff --git a/arch/x86/kernel/genx2apic_uv_x.c b/arch/x86/kernel/genx2apic_uv_x.c
index 2c7dbdb98278..221299f4509f 100644
--- a/arch/x86/kernel/genx2apic_uv_x.c
+++ b/arch/x86/kernel/genx2apic_uv_x.c
@@ -10,6 +10,7 @@
 
 #include <linux/kernel.h>
 #include <linux/threads.h>
+#include <linux/cpu.h>
 #include <linux/cpumask.h>
 #include <linux/string.h>
 #include <linux/ctype.h>
@@ -17,6 +18,9 @@
 #include <linux/sched.h>
 #include <linux/module.h>
 #include <linux/hardirq.h>
+#include <linux/timer.h>
+#include <linux/proc_fs.h>
+#include <asm/current.h>
 #include <asm/smp.h>
 #include <asm/ipi.h>
 #include <asm/genapic.h>
@@ -356,6 +360,103 @@ static __init void uv_rtc_init(void)
 }
 
 /*
+ * percpu heartbeat timer
+ */
+static void uv_heartbeat(unsigned long ignored)
+{
+	struct timer_list *timer = &uv_hub_info->scir.timer;
+	unsigned char bits = uv_hub_info->scir.state;
+
+	/* flip heartbeat bit */
+	bits ^= SCIR_CPU_HEARTBEAT;
+
+	/* is this cpu idle? */
+	if (idle_cpu(raw_smp_processor_id()))
+		bits &= ~SCIR_CPU_ACTIVITY;
+	else
+		bits |= SCIR_CPU_ACTIVITY;
+
+	/* update system controller interface reg */
+	uv_set_scir_bits(bits);
+
+	/* enable next timer period */
+	mod_timer(timer, jiffies + SCIR_CPU_HB_INTERVAL);
+}
+
+static void __cpuinit uv_heartbeat_enable(int cpu)
+{
+	if (!uv_cpu_hub_info(cpu)->scir.enabled) {
+		struct timer_list *timer = &uv_cpu_hub_info(cpu)->scir.timer;
+
+		uv_set_cpu_scir_bits(cpu, SCIR_CPU_HEARTBEAT|SCIR_CPU_ACTIVITY);
+		setup_timer(timer, uv_heartbeat, cpu);
+		timer->expires = jiffies + SCIR_CPU_HB_INTERVAL;
+		add_timer_on(timer, cpu);
+		uv_cpu_hub_info(cpu)->scir.enabled = 1;
+	}
+
+	/* check boot cpu */
+	if (!uv_cpu_hub_info(0)->scir.enabled)
+		uv_heartbeat_enable(0);
+}
+
+#ifdef CONFIG_HOTPLUG_CPU
+static void __cpuinit uv_heartbeat_disable(int cpu)
+{
+	if (uv_cpu_hub_info(cpu)->scir.enabled) {
+		uv_cpu_hub_info(cpu)->scir.enabled = 0;
+		del_timer(&uv_cpu_hub_info(cpu)->scir.timer);
+	}
+	uv_set_cpu_scir_bits(cpu, 0xff);
+}
+
+/*
+ * cpu hotplug notifier
+ */
+static __cpuinit int uv_scir_cpu_notify(struct notifier_block *self,
+				       unsigned long action, void *hcpu)
+{
+	long cpu = (long)hcpu;
+
+	switch (action) {
+	case CPU_ONLINE:
+		uv_heartbeat_enable(cpu);
+		break;
+	case CPU_DOWN_PREPARE:
+		uv_heartbeat_disable(cpu);
+		break;
+	default:
+		break;
+	}
+	return NOTIFY_OK;
+}
+
+static __init void uv_scir_register_cpu_notifier(void)
+{
+	hotcpu_notifier(uv_scir_cpu_notify, 0);
+}
+
+#else /* !CONFIG_HOTPLUG_CPU */
+
+static __init void uv_scir_register_cpu_notifier(void)
+{
+}
+
+static __init int uv_init_heartbeat(void)
+{
+	int cpu;
+
+	if (is_uv_system())
+		for_each_online_cpu(cpu)
+			uv_heartbeat_enable(cpu);
+	return 0;
+}
+
+late_initcall(uv_init_heartbeat);
+
+#endif /* !CONFIG_HOTPLUG_CPU */
+
+/*
  * Called on each cpu to initialize the per_cpu UV data area.
  * 	ZZZ hotplug not supported yet
  */
@@ -428,7 +529,7 @@ void __init uv_system_init(void)
 
 	uv_bios_init();
 	uv_bios_get_sn_info(0, &uv_type, &sn_partition_id,
-			    &uv_coherency_id, &uv_region_size);
+			    &sn_coherency_id, &sn_region_size);
 	uv_rtc_init();
 
 	for_each_present_cpu(cpu) {
@@ -450,7 +551,8 @@ void __init uv_system_init(void)
 		uv_cpu_hub_info(cpu)->gpa_mask = (1 << (m_val + n_val)) - 1;
 		uv_cpu_hub_info(cpu)->gnode_upper = gnode_upper;
 		uv_cpu_hub_info(cpu)->global_mmr_base = mmr_base;
-		uv_cpu_hub_info(cpu)->coherency_domain_number = uv_coherency_id;
+		uv_cpu_hub_info(cpu)->coherency_domain_number = sn_coherency_id;
+		uv_cpu_hub_info(cpu)->scir.offset = SCIR_LOCAL_MMR_BASE + lcpu;
 		uv_node_to_blade[nid] = blade;
 		uv_cpu_to_blade[cpu] = blade;
 		max_pnode = max(pnode, max_pnode);
@@ -467,4 +569,6 @@ void __init uv_system_init(void)
 	map_mmioh_high(max_pnode);
 
 	uv_cpu_init();
+	uv_scir_register_cpu_notifier();
+	proc_mkdir("sgi_uv", NULL);
 }
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index 067d8de913f6..3f0a3edf0a57 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -33,7 +33,9 @@
  * HPET address is set in acpi/boot.c, when an ACPI entry exists
  */
 unsigned long				hpet_address;
-unsigned long				hpet_num_timers;
+#ifdef CONFIG_PCI_MSI
+static unsigned long			hpet_num_timers;
+#endif
 static void __iomem			*hpet_virt_address;
 
 struct hpet_dev {
diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c
index 60eb84eb77a0..1d3d0e71b044 100644
--- a/arch/x86/kernel/irq_64.c
+++ b/arch/x86/kernel/irq_64.c
@@ -18,7 +18,6 @@
 #include <asm/idle.h>
 #include <asm/smp.h>
 
-#ifdef CONFIG_DEBUG_STACKOVERFLOW
 /*
  * Probabilistic stack overflow check:
  *
@@ -28,19 +27,18 @@
  */
 static inline void stack_overflow_check(struct pt_regs *regs)
 {
+#ifdef CONFIG_DEBUG_STACKOVERFLOW
 	u64 curbase = (u64)task_stack_page(current);
-	static unsigned long warned = -60*HZ;
-
-	if (regs->sp >= curbase && regs->sp <= curbase + THREAD_SIZE &&
-	    regs->sp <  curbase + sizeof(struct thread_info) + 128 &&
-	    time_after(jiffies, warned + 60*HZ)) {
-		printk("do_IRQ: %s near stack overflow (cur:%Lx,sp:%lx)\n",
-		       current->comm, curbase, regs->sp);
-		show_stack(NULL,NULL);
-		warned = jiffies;
-	}
-}
+
+	WARN_ONCE(regs->sp >= curbase &&
+		  regs->sp <= curbase + THREAD_SIZE &&
+		  regs->sp <  curbase + sizeof(struct thread_info) +
+					sizeof(struct pt_regs) + 128,
+
+		  "do_IRQ: %s near stack overflow (cur:%Lx,sp:%lx)\n",
+			current->comm, curbase, regs->sp);
 #endif
+}
 
 /*
  * do_IRQ handles all normal device IRQ's (the special
@@ -60,9 +58,7 @@ asmlinkage unsigned int do_IRQ(struct pt_regs *regs)
 	irq_enter();
 	irq = __get_cpu_var(vector_irq)[vector];
 
-#ifdef CONFIG_DEBUG_STACKOVERFLOW
 	stack_overflow_check(regs);
-#endif
 
 	desc = irq_to_desc(irq);
 	if (likely(desc))
diff --git a/arch/x86/kernel/irqinit_32.c b/arch/x86/kernel/irqinit_32.c
index 845aa9803e80..607db63044a5 100644
--- a/arch/x86/kernel/irqinit_32.c
+++ b/arch/x86/kernel/irqinit_32.c
@@ -129,7 +129,7 @@ void __init native_init_IRQ(void)
 	for (i =  FIRST_EXTERNAL_VECTOR; i < NR_VECTORS; i++) {
 		/* SYSCALL_VECTOR was reserved in trap_init. */
 		if (i != SYSCALL_VECTOR)
-			set_intr_gate(i, interrupt[i]);
+			set_intr_gate(i, interrupt[i-FIRST_EXTERNAL_VECTOR]);
 	}
 
 
diff --git a/arch/x86/kernel/irqinit_64.c b/arch/x86/kernel/irqinit_64.c
index ff0235391285..8670b3ce626e 100644
--- a/arch/x86/kernel/irqinit_64.c
+++ b/arch/x86/kernel/irqinit_64.c
@@ -24,41 +24,6 @@
 #include <asm/i8259.h>
 
 /*
- * Common place to define all x86 IRQ vectors
- *
- * This builds up the IRQ handler stubs using some ugly macros in irq.h
- *
- * These macros create the low-level assembly IRQ routines that save
- * register context and call do_IRQ(). do_IRQ() then does all the
- * operations that are needed to keep the AT (or SMP IOAPIC)
- * interrupt-controller happy.
- */
-
-#define IRQ_NAME2(nr) nr##_interrupt(void)
-#define IRQ_NAME(nr) IRQ_NAME2(IRQ##nr)
-
-/*
- *	SMP has a few special interrupts for IPI messages
- */
-
-#define BUILD_IRQ(nr)				\
-	asmlinkage void IRQ_NAME(nr);		\
-	asm("\n.text\n.p2align\n"		\
-	    "IRQ" #nr "_interrupt:\n\t"		\
-	    "push $~(" #nr ") ; "		\
-	    "jmp common_interrupt\n"		\
-	    ".previous");
-
-#define BI(x,y) \
-	BUILD_IRQ(x##y)
-
-#define BUILD_16_IRQS(x) \
-	BI(x,0) BI(x,1) BI(x,2) BI(x,3) \
-	BI(x,4) BI(x,5) BI(x,6) BI(x,7) \
-	BI(x,8) BI(x,9) BI(x,a) BI(x,b) \
-	BI(x,c) BI(x,d) BI(x,e) BI(x,f)
-
-/*
  * ISA PIC or low IO-APIC triggered (INTA-cycle or APIC) interrupts:
  * (these are usually mapped to vectors 0x30-0x3f)
  */
@@ -73,37 +38,6 @@
  *
  * (these are usually mapped into the 0x30-0xff vector range)
  */
-				      BUILD_16_IRQS(0x2) BUILD_16_IRQS(0x3)
-BUILD_16_IRQS(0x4) BUILD_16_IRQS(0x5) BUILD_16_IRQS(0x6) BUILD_16_IRQS(0x7)
-BUILD_16_IRQS(0x8) BUILD_16_IRQS(0x9) BUILD_16_IRQS(0xa) BUILD_16_IRQS(0xb)
-BUILD_16_IRQS(0xc) BUILD_16_IRQS(0xd) BUILD_16_IRQS(0xe) BUILD_16_IRQS(0xf)
-
-#undef BUILD_16_IRQS
-#undef BI
-
-
-#define IRQ(x,y) \
-	IRQ##x##y##_interrupt
-
-#define IRQLIST_16(x) \
-	IRQ(x,0), IRQ(x,1), IRQ(x,2), IRQ(x,3), \
-	IRQ(x,4), IRQ(x,5), IRQ(x,6), IRQ(x,7), \
-	IRQ(x,8), IRQ(x,9), IRQ(x,a), IRQ(x,b), \
-	IRQ(x,c), IRQ(x,d), IRQ(x,e), IRQ(x,f)
-
-/* for the irq vectors */
-static void (*__initdata interrupt[NR_VECTORS - FIRST_EXTERNAL_VECTOR])(void) = {
-					  IRQLIST_16(0x2), IRQLIST_16(0x3),
-	IRQLIST_16(0x4), IRQLIST_16(0x5), IRQLIST_16(0x6), IRQLIST_16(0x7),
-	IRQLIST_16(0x8), IRQLIST_16(0x9), IRQLIST_16(0xa), IRQLIST_16(0xb),
-	IRQLIST_16(0xc), IRQLIST_16(0xd), IRQLIST_16(0xe), IRQLIST_16(0xf)
-};
-
-#undef IRQ
-#undef IRQLIST_16
-
-
-
 
 /*
  * IRQ2 is cascade interrupt to second interrupt controller
diff --git a/arch/x86/kernel/machine_kexec_32.c b/arch/x86/kernel/machine_kexec_32.c
index 7a385746509a..37f420018a41 100644
--- a/arch/x86/kernel/machine_kexec_32.c
+++ b/arch/x86/kernel/machine_kexec_32.c
@@ -13,6 +13,7 @@
 #include <linux/numa.h>
 #include <linux/ftrace.h>
 #include <linux/suspend.h>
+#include <linux/gfp.h>
 
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
@@ -25,15 +26,6 @@
 #include <asm/system.h>
 #include <asm/cacheflush.h>
 
-#define PAGE_ALIGNED __attribute__ ((__aligned__(PAGE_SIZE)))
-static u32 kexec_pgd[1024] PAGE_ALIGNED;
-#ifdef CONFIG_X86_PAE
-static u32 kexec_pmd0[1024] PAGE_ALIGNED;
-static u32 kexec_pmd1[1024] PAGE_ALIGNED;
-#endif
-static u32 kexec_pte0[1024] PAGE_ALIGNED;
-static u32 kexec_pte1[1024] PAGE_ALIGNED;
-
 static void set_idt(void *newidt, __u16 limit)
 {
 	struct desc_ptr curidt;
@@ -76,6 +68,76 @@ static void load_segments(void)
 #undef __STR
 }
 
+static void machine_kexec_free_page_tables(struct kimage *image)
+{
+	free_page((unsigned long)image->arch.pgd);
+#ifdef CONFIG_X86_PAE
+	free_page((unsigned long)image->arch.pmd0);
+	free_page((unsigned long)image->arch.pmd1);
+#endif
+	free_page((unsigned long)image->arch.pte0);
+	free_page((unsigned long)image->arch.pte1);
+}
+
+static int machine_kexec_alloc_page_tables(struct kimage *image)
+{
+	image->arch.pgd = (pgd_t *)get_zeroed_page(GFP_KERNEL);
+#ifdef CONFIG_X86_PAE
+	image->arch.pmd0 = (pmd_t *)get_zeroed_page(GFP_KERNEL);
+	image->arch.pmd1 = (pmd_t *)get_zeroed_page(GFP_KERNEL);
+#endif
+	image->arch.pte0 = (pte_t *)get_zeroed_page(GFP_KERNEL);
+	image->arch.pte1 = (pte_t *)get_zeroed_page(GFP_KERNEL);
+	if (!image->arch.pgd ||
+#ifdef CONFIG_X86_PAE
+	    !image->arch.pmd0 || !image->arch.pmd1 ||
+#endif
+	    !image->arch.pte0 || !image->arch.pte1) {
+		machine_kexec_free_page_tables(image);
+		return -ENOMEM;
+	}
+	return 0;
+}
+
+static void machine_kexec_page_table_set_one(
+	pgd_t *pgd, pmd_t *pmd, pte_t *pte,
+	unsigned long vaddr, unsigned long paddr)
+{
+	pud_t *pud;
+
+	pgd += pgd_index(vaddr);
+#ifdef CONFIG_X86_PAE
+	if (!(pgd_val(*pgd) & _PAGE_PRESENT))
+		set_pgd(pgd, __pgd(__pa(pmd) | _PAGE_PRESENT));
+#endif
+	pud = pud_offset(pgd, vaddr);
+	pmd = pmd_offset(pud, vaddr);
+	if (!(pmd_val(*pmd) & _PAGE_PRESENT))
+		set_pmd(pmd, __pmd(__pa(pte) | _PAGE_TABLE));
+	pte = pte_offset_kernel(pmd, vaddr);
+	set_pte(pte, pfn_pte(paddr >> PAGE_SHIFT, PAGE_KERNEL_EXEC));
+}
+
+static void machine_kexec_prepare_page_tables(struct kimage *image)
+{
+	void *control_page;
+	pmd_t *pmd = 0;
+
+	control_page = page_address(image->control_code_page);
+#ifdef CONFIG_X86_PAE
+	pmd = image->arch.pmd0;
+#endif
+	machine_kexec_page_table_set_one(
+		image->arch.pgd, pmd, image->arch.pte0,
+		(unsigned long)control_page, __pa(control_page));
+#ifdef CONFIG_X86_PAE
+	pmd = image->arch.pmd1;
+#endif
+	machine_kexec_page_table_set_one(
+		image->arch.pgd, pmd, image->arch.pte1,
+		__pa(control_page), __pa(control_page));
+}
+
 /*
  * A architecture hook called to validate the
  * proposed image and prepare the control pages
@@ -87,12 +149,20 @@ static void load_segments(void)
  * reboot code buffer to allow us to avoid allocations
  * later.
  *
- * Make control page executable.
+ * - Make control page executable.
+ * - Allocate page tables
+ * - Setup page tables
  */
 int machine_kexec_prepare(struct kimage *image)
 {
+	int error;
+
 	if (nx_enabled)
 		set_pages_x(image->control_code_page, 1);
+	error = machine_kexec_alloc_page_tables(image);
+	if (error)
+		return error;
+	machine_kexec_prepare_page_tables(image);
 	return 0;
 }
 
@@ -104,6 +174,7 @@ void machine_kexec_cleanup(struct kimage *image)
 {
 	if (nx_enabled)
 		set_pages_nx(image->control_code_page, 1);
+	machine_kexec_free_page_tables(image);
 }
 
 /*
@@ -150,18 +221,7 @@ void machine_kexec(struct kimage *image)
 	relocate_kernel_ptr = control_page;
 	page_list[PA_CONTROL_PAGE] = __pa(control_page);
 	page_list[VA_CONTROL_PAGE] = (unsigned long)control_page;
-	page_list[PA_PGD] = __pa(kexec_pgd);
-	page_list[VA_PGD] = (unsigned long)kexec_pgd;
-#ifdef CONFIG_X86_PAE
-	page_list[PA_PMD_0] = __pa(kexec_pmd0);
-	page_list[VA_PMD_0] = (unsigned long)kexec_pmd0;
-	page_list[PA_PMD_1] = __pa(kexec_pmd1);
-	page_list[VA_PMD_1] = (unsigned long)kexec_pmd1;
-#endif
-	page_list[PA_PTE_0] = __pa(kexec_pte0);
-	page_list[VA_PTE_0] = (unsigned long)kexec_pte0;
-	page_list[PA_PTE_1] = __pa(kexec_pte1);
-	page_list[VA_PTE_1] = (unsigned long)kexec_pte1;
+	page_list[PA_PGD] = __pa(image->arch.pgd);
 
 	if (image->type == KEXEC_TYPE_DEFAULT)
 		page_list[PA_SWAP_PAGE] = (page_to_pfn(image->swap_page)
diff --git a/arch/x86/kernel/microcode_core.c b/arch/x86/kernel/microcode_core.c
index 82fb2809ce32..5b711a534495 100644
--- a/arch/x86/kernel/microcode_core.c
+++ b/arch/x86/kernel/microcode_core.c
@@ -99,7 +99,7 @@ MODULE_LICENSE("GPL");
 
 #define MICROCODE_VERSION 	"2.00"
 
-struct microcode_ops *microcode_ops;
+static struct microcode_ops *microcode_ops;
 
 /* no concurrent ->write()s are allowed on /dev/cpu/microcode */
 static DEFINE_MUTEX(microcode_mutex);
@@ -203,7 +203,7 @@ MODULE_ALIAS_MISCDEV(MICROCODE_MINOR);
 #endif
 
 /* fake device for request_firmware */
-struct platform_device *microcode_pdev;
+static struct platform_device *microcode_pdev;
 
 static ssize_t reload_store(struct sys_device *dev,
 			    struct sysdev_attribute *attr,
@@ -319,7 +319,7 @@ static int microcode_resume_cpu(int cpu)
 	return 0;
 }
 
-void microcode_update_cpu(int cpu)
+static void microcode_update_cpu(int cpu)
 {
 	struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
 	int err = 0;
diff --git a/arch/x86/kernel/microcode_intel.c b/arch/x86/kernel/microcode_intel.c
index 622dc4a21784..c34c820ee486 100644
--- a/arch/x86/kernel/microcode_intel.c
+++ b/arch/x86/kernel/microcode_intel.c
@@ -465,7 +465,7 @@ static void microcode_fini_cpu(int cpu)
 	uci->mc = NULL;
 }
 
-struct microcode_ops microcode_intel_ops = {
+static struct microcode_ops microcode_intel_ops = {
 	.request_microcode_user		  = request_microcode_user,
 	.request_microcode_fw             = request_microcode_fw,
 	.collect_cpu_info                 = collect_cpu_info,
diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c
index f98f4e1dba09..0f4c1fd5a1f4 100644
--- a/arch/x86/kernel/mpparse.c
+++ b/arch/x86/kernel/mpparse.c
@@ -604,6 +604,9 @@ static void __init __get_smp_config(unsigned int early)
 		printk(KERN_INFO "Using ACPI for processor (LAPIC) "
 		       "configuration information\n");
 
+	if (!mpf)
+		return;
+
 	printk(KERN_INFO "Intel MultiProcessor Specification v1.%d\n",
 	       mpf->mpf_specification);
 #if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_X86_32)
diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c
index 2c97f07f1c2c..8bd1bf9622a7 100644
--- a/arch/x86/kernel/nmi.c
+++ b/arch/x86/kernel/nmi.c
@@ -131,6 +131,11 @@ static void report_broken_nmi(int cpu, int *prev_nmi_count)
 	atomic_dec(&nmi_active);
 }
 
+static void __acpi_nmi_disable(void *__unused)
+{
+	apic_write(APIC_LVT0, APIC_DM_NMI | APIC_LVT_MASKED);
+}
+
 int __init check_nmi_watchdog(void)
 {
 	unsigned int *prev_nmi_count;
@@ -179,8 +184,12 @@ int __init check_nmi_watchdog(void)
 	kfree(prev_nmi_count);
 	return 0;
 error:
-	if (nmi_watchdog == NMI_IO_APIC && !timer_through_8259)
-		disable_8259A_irq(0);
+	if (nmi_watchdog == NMI_IO_APIC) {
+		if (!timer_through_8259)
+			disable_8259A_irq(0);
+		on_each_cpu(__acpi_nmi_disable, NULL, 1);
+	}
+
 #ifdef CONFIG_X86_32
 	timer_ack = 0;
 #endif
@@ -199,12 +208,17 @@ static int __init setup_nmi_watchdog(char *str)
 		++str;
 	}
 
-	get_option(&str, &nmi);
-
-	if (nmi >= NMI_INVALID)
-		return 0;
+	if (!strncmp(str, "lapic", 5))
+		nmi_watchdog = NMI_LOCAL_APIC;
+	else if (!strncmp(str, "ioapic", 6))
+		nmi_watchdog = NMI_IO_APIC;
+	else {
+		get_option(&str, &nmi);
+		if (nmi >= NMI_INVALID)
+			return 0;
+		nmi_watchdog = nmi;
+	}
 
-	nmi_watchdog = nmi;
 	return 1;
 }
 __setup("nmi_watchdog=", setup_nmi_watchdog);
@@ -285,11 +299,6 @@ void acpi_nmi_enable(void)
 		on_each_cpu(__acpi_nmi_enable, NULL, 1);
 }
 
-static void __acpi_nmi_disable(void *__unused)
-{
-	apic_write(APIC_LVT0, APIC_DM_NMI | APIC_LVT_MASKED);
-}
-
 /*
  * Disable timer based NMIs on all CPUs:
  */
@@ -340,6 +349,8 @@ void stop_apic_nmi_watchdog(void *unused)
 		return;
 	if (nmi_watchdog == NMI_LOCAL_APIC)
 		lapic_watchdog_stop();
+	else
+		__acpi_nmi_disable(NULL);
 	__get_cpu_var(wd_enabled) = 0;
 	atomic_dec(&nmi_active);
 }
@@ -465,6 +476,24 @@ nmi_watchdog_tick(struct pt_regs *regs, unsigned reason)
 
 #ifdef CONFIG_SYSCTL
 
+static void enable_ioapic_nmi_watchdog_single(void *unused)
+{
+	__get_cpu_var(wd_enabled) = 1;
+	atomic_inc(&nmi_active);
+	__acpi_nmi_enable(NULL);
+}
+
+static void enable_ioapic_nmi_watchdog(void)
+{
+	on_each_cpu(enable_ioapic_nmi_watchdog_single, NULL, 1);
+	touch_nmi_watchdog();
+}
+
+static void disable_ioapic_nmi_watchdog(void)
+{
+	on_each_cpu(stop_apic_nmi_watchdog, NULL, 1);
+}
+
 static int __init setup_unknown_nmi_panic(char *str)
 {
 	unknown_nmi_panic = 1;
@@ -507,6 +536,11 @@ int proc_nmi_enabled(struct ctl_table *table, int write, struct file *file,
 			enable_lapic_nmi_watchdog();
 		else
 			disable_lapic_nmi_watchdog();
+	} else if (nmi_watchdog == NMI_IO_APIC) {
+		if (nmi_watchdog_enabled)
+			enable_ioapic_nmi_watchdog();
+		else
+			disable_ioapic_nmi_watchdog();
 	} else {
 		printk(KERN_WARNING
 			"NMI watchdog doesn't know what hardware to touch\n");
diff --git a/arch/x86/kernel/numaq_32.c b/arch/x86/kernel/numaq_32.c
index 4caff39078e0..0deea37a53cf 100644
--- a/arch/x86/kernel/numaq_32.c
+++ b/arch/x86/kernel/numaq_32.c
@@ -31,7 +31,7 @@
 #include <asm/numaq.h>
 #include <asm/topology.h>
 #include <asm/processor.h>
-#include <asm/mpspec.h>
+#include <asm/genapic.h>
 #include <asm/e820.h>
 #include <asm/setup.h>
 
@@ -235,6 +235,13 @@ static int __init numaq_setup_ioapic_ids(void)
 	return 1;
 }
 
+static int __init numaq_update_genapic(void)
+{
+	genapic->wakeup_cpu = wakeup_secondary_cpu_via_nmi;
+
+	return 0;
+}
+
 static struct x86_quirks numaq_x86_quirks __initdata = {
 	.arch_pre_time_init	= numaq_pre_time_init,
 	.arch_time_init		= NULL,
@@ -250,6 +257,7 @@ static struct x86_quirks numaq_x86_quirks __initdata = {
 	.mpc_oem_pci_bus	= mpc_oem_pci_bus,
 	.smp_read_mpc_oem	= smp_read_mpc_oem,
 	.setup_ioapic_ids	= numaq_setup_ioapic_ids,
+	.update_genapic		= numaq_update_genapic,
 };
 
 void numaq_mps_oem_check(struct mp_config_table *mpc, char *oem,
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index 192624820217..b9089c971a8c 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -6,6 +6,7 @@
 #include <asm/proto.h>
 #include <asm/dma.h>
 #include <asm/iommu.h>
+#include <asm/gart.h>
 #include <asm/calgary.h>
 #include <asm/amd_iommu.h>
 
@@ -30,11 +31,6 @@ int no_iommu __read_mostly;
 /* Set this to 1 if there is a HW IOMMU in the system */
 int iommu_detected __read_mostly = 0;
 
-/* This tells the BIO block layer to assume merging. Default to off
-   because we cannot guarantee merging later. */
-int iommu_bio_merge __read_mostly = 0;
-EXPORT_SYMBOL(iommu_bio_merge);
-
 dma_addr_t bad_dma_address __read_mostly = 0;
 EXPORT_SYMBOL(bad_dma_address);
 
@@ -42,7 +38,7 @@ EXPORT_SYMBOL(bad_dma_address);
    be probably a smaller DMA mask, but this is bug-to-bug compatible
    to older i386. */
 struct device x86_dma_fallback_dev = {
-	.bus_id = "fallback device",
+	.init_name = "fallback device",
 	.coherent_dma_mask = DMA_32BIT_MASK,
 	.dma_mask = &x86_dma_fallback_dev.coherent_dma_mask,
 };
@@ -188,7 +184,6 @@ static __init int iommu_setup(char *p)
 		}
 
 		if (!strncmp(p, "biomerge", 8)) {
-			iommu_bio_merge = 4096;
 			iommu_merge = 1;
 			force_iommu = 1;
 		}
diff --git a/arch/x86/kernel/pci-gart_64.c b/arch/x86/kernel/pci-gart_64.c
index a42b02b4df68..ba7ad83e20a8 100644
--- a/arch/x86/kernel/pci-gart_64.c
+++ b/arch/x86/kernel/pci-gart_64.c
@@ -123,6 +123,8 @@ static void free_iommu(unsigned long offset, int size)
 
 	spin_lock_irqsave(&iommu_bitmap_lock, flags);
 	iommu_area_free(iommu_gart_bitmap, offset, size);
+	if (offset >= next_bit)
+		next_bit = offset + size;
 	spin_unlock_irqrestore(&iommu_bitmap_lock, flags);
 }
 
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index c622772744d8..a4da7c4b3129 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -8,6 +8,7 @@
 #include <linux/pm.h>
 #include <linux/clockchips.h>
 #include <asm/system.h>
+#include <asm/apic.h>
 
 unsigned long idle_halt;
 EXPORT_SYMBOL(idle_halt);
@@ -122,6 +123,21 @@ void default_idle(void)
 EXPORT_SYMBOL(default_idle);
 #endif
 
+void stop_this_cpu(void *dummy)
+{
+	local_irq_disable();
+	/*
+	 * Remove this CPU:
+	 */
+	cpu_clear(smp_processor_id(), cpu_online_map);
+	disable_local_APIC();
+
+	for (;;) {
+		if (hlt_works(smp_processor_id()))
+			halt();
+	}
+}
+
 static void do_nothing(void *unused)
 {
 }
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index c958120fb1b6..3180e79c3697 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -16,6 +16,7 @@
 
 #include <stdarg.h>
 
+#include <linux/stackprotector.h>
 #include <linux/cpu.h>
 #include <linux/errno.h>
 #include <linux/sched.h>
@@ -109,6 +110,17 @@ static inline void play_dead(void)
 void cpu_idle(void)
 {
 	current_thread_info()->status |= TS_POLLING;
+
+	/*
+	 * If we're the non-boot CPU, nothing set the PDA stack
+	 * canary up for us - and if we are the boot CPU we have
+	 * a 0 stack canary. This is a good place for updating
+	 * it, as we wont ever return from this function (so the
+	 * invalid canaries already on the stack wont ever
+	 * trigger):
+	 */
+	boot_init_stack_canary();
+
 	/* endless idle loop with no priority at all */
 	while (1) {
 		tick_nohz_stop_sched_tick(1);
@@ -647,7 +659,6 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 		  (unsigned long)task_stack_page(next_p) +
 		  THREAD_SIZE - PDA_STACKOFFSET);
 #ifdef CONFIG_CC_STACKPROTECTOR
-	write_pda(stack_canary, next_p->stack_canary);
 	/*
 	 * Build time only check to make sure the stack_canary is at
 	 * offset 40 in the pda; this is a gcc ABI requirement
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index 0a6d8c12e10d..06180dff5b2e 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -929,17 +929,16 @@ void __cpuinit ptrace_bts_init_intel(struct cpuinfo_x86 *c)
 	switch (c->x86) {
 	case 0x6:
 		switch (c->x86_model) {
+		case 0 ... 0xC:
+			/* sorry, don't know about them */
+			break;
 		case 0xD:
 		case 0xE: /* Pentium M */
 			bts_configure(&bts_cfg_pentium_m);
 			break;
-		case 0xF: /* Core2 */
-        case 0x1C: /* Atom */
+		default: /* Core2, Atom, ... */
 			bts_configure(&bts_cfg_core2);
 			break;
-		default:
-			/* sorry, don't know about them */
-			break;
 		}
 		break;
 	case 0xF:
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index cc5a2545dd41..0acde8f300a1 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -21,6 +21,9 @@
 # include <asm/iommu.h>
 #endif
 
+#include <mach_ipi.h>
+
+
 /*
  * Power off function, if any
  */
@@ -29,14 +32,17 @@ EXPORT_SYMBOL(pm_power_off);
 
 static const struct desc_ptr no_idt = {};
 static int reboot_mode;
-enum reboot_type reboot_type = BOOT_KBD;
+enum reboot_type reboot_type = BOOT_ACPI;
 int reboot_force;
 
 #if defined(CONFIG_X86_32) && defined(CONFIG_SMP)
 static int reboot_cpu = -1;
 #endif
 
-/* reboot=b[ios] | s[mp] | t[riple] | k[bd] | e[fi] [, [w]arm | [c]old]
+/* This is set by the PCI code if either type 1 or type 2 PCI is detected */
+bool port_cf9_safe = false;
+
+/* reboot=b[ios] | s[mp] | t[riple] | k[bd] | e[fi] [, [w]arm | [c]old] | p[ci]
    warm   Don't set the cold reboot flag
    cold   Set the cold reboot flag
    bios   Reboot by jumping through the BIOS (only for X86_32)
@@ -45,6 +51,7 @@ static int reboot_cpu = -1;
    kbd    Use the keyboard controller. cold reset (default)
    acpi   Use the RESET_REG in the FADT
    efi    Use efi reset_system runtime service
+   pci    Use the so-called "PCI reset register", CF9
    force  Avoid anything that could hang.
  */
 static int __init reboot_setup(char *str)
@@ -79,6 +86,7 @@ static int __init reboot_setup(char *str)
 		case 'k':
 		case 't':
 		case 'e':
+		case 'p':
 			reboot_type = *str;
 			break;
 
@@ -404,12 +412,27 @@ static void native_machine_emergency_restart(void)
 			reboot_type = BOOT_KBD;
 			break;
 
-
 		case BOOT_EFI:
 			if (efi_enabled)
-				efi.reset_system(reboot_mode ? EFI_RESET_WARM : EFI_RESET_COLD,
+				efi.reset_system(reboot_mode ?
+						 EFI_RESET_WARM :
+						 EFI_RESET_COLD,
 						 EFI_SUCCESS, 0, NULL);
+			reboot_type = BOOT_KBD;
+			break;
 
+		case BOOT_CF9:
+			port_cf9_safe = true;
+			/* fall through */
+
+		case BOOT_CF9_COND:
+			if (port_cf9_safe) {
+				u8 cf9 = inb(0xcf9) & ~6;
+				outb(cf9|2, 0xcf9); /* Request hard reset */
+				udelay(50);
+				outb(cf9|6, 0xcf9); /* Actually do the reset */
+				udelay(50);
+			}
 			reboot_type = BOOT_KBD;
 			break;
 		}
@@ -470,6 +493,11 @@ static void native_machine_restart(char *__unused)
 
 static void native_machine_halt(void)
 {
+	/* stop other cpus and apics */
+	machine_shutdown();
+
+	/* stop this cpu */
+	stop_this_cpu(NULL);
 }
 
 static void native_machine_power_off(void)
@@ -523,3 +551,95 @@ void machine_crash_shutdown(struct pt_regs *regs)
 	machine_ops.crash_shutdown(regs);
 }
 #endif
+
+
+#if defined(CONFIG_SMP)
+
+/* This keeps a track of which one is crashing cpu. */
+static int crashing_cpu;
+static nmi_shootdown_cb shootdown_callback;
+
+static atomic_t waiting_for_crash_ipi;
+
+static int crash_nmi_callback(struct notifier_block *self,
+			unsigned long val, void *data)
+{
+	int cpu;
+
+	if (val != DIE_NMI_IPI)
+		return NOTIFY_OK;
+
+	cpu = raw_smp_processor_id();
+
+	/* Don't do anything if this handler is invoked on crashing cpu.
+	 * Otherwise, system will completely hang. Crashing cpu can get
+	 * an NMI if system was initially booted with nmi_watchdog parameter.
+	 */
+	if (cpu == crashing_cpu)
+		return NOTIFY_STOP;
+	local_irq_disable();
+
+	shootdown_callback(cpu, (struct die_args *)data);
+
+	atomic_dec(&waiting_for_crash_ipi);
+	/* Assume hlt works */
+	halt();
+	for (;;)
+		cpu_relax();
+
+	return 1;
+}
+
+static void smp_send_nmi_allbutself(void)
+{
+	cpumask_t mask = cpu_online_map;
+	cpu_clear(safe_smp_processor_id(), mask);
+	if (!cpus_empty(mask))
+		send_IPI_mask(mask, NMI_VECTOR);
+}
+
+static struct notifier_block crash_nmi_nb = {
+	.notifier_call = crash_nmi_callback,
+};
+
+/* Halt all other CPUs, calling the specified function on each of them
+ *
+ * This function can be used to halt all other CPUs on crash
+ * or emergency reboot time. The function passed as parameter
+ * will be called inside a NMI handler on all CPUs.
+ */
+void nmi_shootdown_cpus(nmi_shootdown_cb callback)
+{
+	unsigned long msecs;
+	local_irq_disable();
+
+	/* Make a note of crashing cpu. Will be used in NMI callback.*/
+	crashing_cpu = safe_smp_processor_id();
+
+	shootdown_callback = callback;
+
+	atomic_set(&waiting_for_crash_ipi, num_online_cpus() - 1);
+	/* Would it be better to replace the trap vector here? */
+	if (register_die_notifier(&crash_nmi_nb))
+		return;		/* return what? */
+	/* Ensure the new callback function is set before sending
+	 * out the NMI
+	 */
+	wmb();
+
+	smp_send_nmi_allbutself();
+
+	msecs = 1000; /* Wait at most a second for the other cpus to stop */
+	while ((atomic_read(&waiting_for_crash_ipi) > 0) && msecs) {
+		mdelay(1);
+		msecs--;
+	}
+
+	/* Leave the nmi callback set */
+}
+#else /* !CONFIG_SMP */
+void nmi_shootdown_cpus(nmi_shootdown_cb callback)
+{
+	/* No other CPUs to shoot down */
+}
+#endif
diff --git a/arch/x86/kernel/relocate_kernel_32.S b/arch/x86/kernel/relocate_kernel_32.S
index 6f50664b2ba5..a160f3119725 100644
--- a/arch/x86/kernel/relocate_kernel_32.S
+++ b/arch/x86/kernel/relocate_kernel_32.S
@@ -10,15 +10,12 @@
 #include <asm/page.h>
 #include <asm/kexec.h>
 #include <asm/processor-flags.h>
-#include <asm/pgtable.h>
 
 /*
  * Must be relocatable PIC code callable as a C function
  */
 
 #define PTR(x) (x << 2)
-#define PAGE_ATTR (_PAGE_PRESENT | _PAGE_RW | _PAGE_ACCESSED | _PAGE_DIRTY)
-#define PAE_PGD_ATTR (_PAGE_PRESENT)
 
 /* control_page + KEXEC_CONTROL_CODE_MAX_SIZE
  * ~ control_page + PAGE_SIZE are used as data storage and stack for
@@ -39,7 +36,6 @@
 #define CP_PA_BACKUP_PAGES_MAP	DATA(0x1c)
 
 	.text
-	.align PAGE_SIZE
 	.globl relocate_kernel
 relocate_kernel:
 	/* Save the CPU context, used for jumping back */
@@ -60,117 +56,6 @@ relocate_kernel:
 	movl	%cr4, %eax
 	movl	%eax, CR4(%edi)
 
-#ifdef CONFIG_X86_PAE
-	/* map the control page at its virtual address */
-
-	movl	PTR(VA_PGD)(%ebp), %edi
-	movl	PTR(VA_CONTROL_PAGE)(%ebp), %eax
-	andl	$0xc0000000, %eax
-	shrl	$27, %eax
-	addl	%edi, %eax
-
-	movl	PTR(PA_PMD_0)(%ebp), %edx
-	orl	$PAE_PGD_ATTR, %edx
-	movl	%edx, (%eax)
-
-	movl	PTR(VA_PMD_0)(%ebp), %edi
-	movl	PTR(VA_CONTROL_PAGE)(%ebp), %eax
-	andl	$0x3fe00000, %eax
-	shrl	$18, %eax
-	addl	%edi, %eax
-
-	movl	PTR(PA_PTE_0)(%ebp), %edx
-	orl	$PAGE_ATTR, %edx
-	movl	%edx, (%eax)
-
-	movl	PTR(VA_PTE_0)(%ebp), %edi
-	movl	PTR(VA_CONTROL_PAGE)(%ebp), %eax
-	andl	$0x001ff000, %eax
-	shrl	$9, %eax
-	addl	%edi, %eax
-
-	movl	PTR(PA_CONTROL_PAGE)(%ebp), %edx
-	orl	$PAGE_ATTR, %edx
-	movl	%edx, (%eax)
-
-	/* identity map the control page at its physical address */
-
-	movl	PTR(VA_PGD)(%ebp), %edi
-	movl	PTR(PA_CONTROL_PAGE)(%ebp), %eax
-	andl	$0xc0000000, %eax
-	shrl	$27, %eax
-	addl	%edi, %eax
-
-	movl	PTR(PA_PMD_1)(%ebp), %edx
-	orl	$PAE_PGD_ATTR, %edx
-	movl	%edx, (%eax)
-
-	movl	PTR(VA_PMD_1)(%ebp), %edi
-	movl	PTR(PA_CONTROL_PAGE)(%ebp), %eax
-	andl	$0x3fe00000, %eax
-	shrl	$18, %eax
-	addl	%edi, %eax
-
-	movl	PTR(PA_PTE_1)(%ebp), %edx
-	orl	$PAGE_ATTR, %edx
-	movl	%edx, (%eax)
-
-	movl	PTR(VA_PTE_1)(%ebp), %edi
-	movl	PTR(PA_CONTROL_PAGE)(%ebp), %eax
-	andl	$0x001ff000, %eax
-	shrl	$9, %eax
-	addl	%edi, %eax
-
-	movl	PTR(PA_CONTROL_PAGE)(%ebp), %edx
-	orl	$PAGE_ATTR, %edx
-	movl	%edx, (%eax)
-#else
-	/* map the control page at its virtual address */
-
-	movl	PTR(VA_PGD)(%ebp), %edi
-	movl	PTR(VA_CONTROL_PAGE)(%ebp), %eax
-	andl	$0xffc00000, %eax
-	shrl	$20, %eax
-	addl	%edi, %eax
-
-	movl	PTR(PA_PTE_0)(%ebp), %edx
-	orl	$PAGE_ATTR, %edx
-	movl	%edx, (%eax)
-
-	movl	PTR(VA_PTE_0)(%ebp), %edi
-	movl	PTR(VA_CONTROL_PAGE)(%ebp), %eax
-	andl	$0x003ff000, %eax
-	shrl	$10, %eax
-	addl	%edi, %eax
-
-	movl	PTR(PA_CONTROL_PAGE)(%ebp), %edx
-	orl	$PAGE_ATTR, %edx
-	movl	%edx, (%eax)
-
-	/* identity map the control page at its physical address */
-
-	movl	PTR(VA_PGD)(%ebp), %edi
-	movl	PTR(PA_CONTROL_PAGE)(%ebp), %eax
-	andl	$0xffc00000, %eax
-	shrl	$20, %eax
-	addl	%edi, %eax
-
-	movl	PTR(PA_PTE_1)(%ebp), %edx
-	orl	$PAGE_ATTR, %edx
-	movl	%edx, (%eax)
-
-	movl	PTR(VA_PTE_1)(%ebp), %edi
-	movl	PTR(PA_CONTROL_PAGE)(%ebp), %eax
-	andl	$0x003ff000, %eax
-	shrl	$10, %eax
-	addl	%edi, %eax
-
-	movl	PTR(PA_CONTROL_PAGE)(%ebp), %edx
-	orl	$PAGE_ATTR, %edx
-	movl	%edx, (%eax)
-#endif
-
-relocate_new_kernel:
 	/* read the arguments and say goodbye to the stack */
 	movl  20+4(%esp), %ebx /* page_list */
 	movl  20+8(%esp), %ebp /* list of pages */
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 9d5674f7b6cc..fe011bca2402 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -93,11 +93,13 @@
 #include <asm/desc.h>
 #include <asm/dma.h>
 #include <asm/iommu.h>
+#include <asm/gart.h>
 #include <asm/mmu_context.h>
 #include <asm/proto.h>
 
 #include <mach_apic.h>
 #include <asm/paravirt.h>
+#include <asm/hypervisor.h>
 
 #include <asm/percpu.h>
 #include <asm/topology.h>
@@ -583,161 +585,24 @@ static int __init setup_elfcorehdr(char *arg)
 early_param("elfcorehdr", setup_elfcorehdr);
 #endif
 
-static struct x86_quirks default_x86_quirks __initdata;
-
-struct x86_quirks *x86_quirks __initdata = &default_x86_quirks;
-
-/*
- * Some BIOSes seem to corrupt the low 64k of memory during events
- * like suspend/resume and unplugging an HDMI cable.  Reserve all
- * remaining free memory in that area and fill it with a distinct
- * pattern.
- */
-#ifdef CONFIG_X86_CHECK_BIOS_CORRUPTION
-#define MAX_SCAN_AREAS	8
-
-static int __read_mostly memory_corruption_check = -1;
-
-static unsigned __read_mostly corruption_check_size = 64*1024;
-static unsigned __read_mostly corruption_check_period = 60; /* seconds */
-
-static struct e820entry scan_areas[MAX_SCAN_AREAS];
-static int num_scan_areas;
-
-
-static int set_corruption_check(char *arg)
-{
-	char *end;
-
-	memory_corruption_check = simple_strtol(arg, &end, 10);
-
-	return (*end == 0) ? 0 : -EINVAL;
-}
-early_param("memory_corruption_check", set_corruption_check);
-
-static int set_corruption_check_period(char *arg)
-{
-	char *end;
-
-	corruption_check_period = simple_strtoul(arg, &end, 10);
-
-	return (*end == 0) ? 0 : -EINVAL;
-}
-early_param("memory_corruption_check_period", set_corruption_check_period);
-
-static int set_corruption_check_size(char *arg)
+static int __init default_update_genapic(void)
 {
-	char *end;
-	unsigned size;
-
-	size = memparse(arg, &end);
-
-	if (*end == '\0')
-		corruption_check_size = size;
-
-	return (size == corruption_check_size) ? 0 : -EINVAL;
-}
-early_param("memory_corruption_check_size", set_corruption_check_size);
-
-
-static void __init setup_bios_corruption_check(void)
-{
-	u64 addr = PAGE_SIZE;	/* assume first page is reserved anyway */
-
-	if (memory_corruption_check == -1) {
-		memory_corruption_check =
-#ifdef CONFIG_X86_BOOTPARAM_MEMORY_CORRUPTION_CHECK
-			1
-#else
-			0
+#ifdef CONFIG_X86_SMP
+# if defined(CONFIG_X86_GENERICARCH) || defined(CONFIG_X86_64)
+	genapic->wakeup_cpu = wakeup_secondary_cpu_via_init;
+# endif
 #endif
-			;
-	}
-
-	if (corruption_check_size == 0)
-		memory_corruption_check = 0;
-
-	if (!memory_corruption_check)
-		return;
-
-	corruption_check_size = round_up(corruption_check_size, PAGE_SIZE);
 
-	while(addr < corruption_check_size && num_scan_areas < MAX_SCAN_AREAS) {
-		u64 size;
-		addr = find_e820_area_size(addr, &size, PAGE_SIZE);
-
-		if (addr == 0)
-			break;
-
-		if ((addr + size) > corruption_check_size)
-			size = corruption_check_size - addr;
-
-		if (size == 0)
-			break;
-
-		e820_update_range(addr, size, E820_RAM, E820_RESERVED);
-		scan_areas[num_scan_areas].addr = addr;
-		scan_areas[num_scan_areas].size = size;
-		num_scan_areas++;
-
-		/* Assume we've already mapped this early memory */
-		memset(__va(addr), 0, size);
-
-		addr += size;
-	}
-
-	printk(KERN_INFO "Scanning %d areas for low memory corruption\n",
-	       num_scan_areas);
-	update_e820();
-}
-
-static struct timer_list periodic_check_timer;
-
-void check_for_bios_corruption(void)
-{
-	int i;
-	int corruption = 0;
-
-	if (!memory_corruption_check)
-		return;
-
-	for(i = 0; i < num_scan_areas; i++) {
-		unsigned long *addr = __va(scan_areas[i].addr);
-		unsigned long size = scan_areas[i].size;
-
-		for(; size; addr++, size -= sizeof(unsigned long)) {
-			if (!*addr)
-				continue;
-			printk(KERN_ERR "Corrupted low memory at %p (%lx phys) = %08lx\n",
-			       addr, __pa(addr), *addr);
-			corruption = 1;
-			*addr = 0;
-		}
-	}
-
-	WARN(corruption, KERN_ERR "Memory corruption detected in low memory\n");
-}
-
-static void periodic_check_for_corruption(unsigned long data)
-{
-	check_for_bios_corruption();
-	mod_timer(&periodic_check_timer, round_jiffies(jiffies + corruption_check_period*HZ));
+	return 0;
 }
 
-void start_periodic_check_for_corruption(void)
-{
-	if (!memory_corruption_check || corruption_check_period == 0)
-		return;
-
-	printk(KERN_INFO "Scanning for low memory corruption every %d seconds\n",
-	       corruption_check_period);
+static struct x86_quirks default_x86_quirks __initdata = {
+	.update_genapic         = default_update_genapic,
+};
 
-	init_timer(&periodic_check_timer);
-	periodic_check_timer.function = &periodic_check_for_corruption;
-	periodic_check_for_corruption(0);
-}
-#endif
+struct x86_quirks *x86_quirks __initdata = &default_x86_quirks;
 
+#ifdef CONFIG_X86_RESERVE_LOW_64K
 static int __init dmi_low_memory_corruption(const struct dmi_system_id *d)
 {
 	printk(KERN_NOTICE
@@ -749,6 +614,7 @@ static int __init dmi_low_memory_corruption(const struct dmi_system_id *d)
 
 	return 0;
 }
+#endif
 
 /* List of systems that have known low memory corruption BIOS problems */
 static struct dmi_system_id __initdata bad_bios_dmi_table[] = {
@@ -909,6 +775,12 @@ void __init setup_arch(char **cmdline_p)
 
 	dmi_check_system(bad_bios_dmi_table);
 
+	/*
+	 * VMware detection requires dmi to be available, so this
+	 * needs to be done after dmi_scan_machine, for the BP.
+	 */
+	init_hypervisor(&boot_cpu_data);
+
 #ifdef CONFIG_X86_32
 	probe_roms();
 #endif
diff --git a/arch/x86/kernel/signal_32.c b/arch/x86/kernel/signal.c
index d6dd057d0f22..b1f4d34e0a38 100644
--- a/arch/x86/kernel/signal_32.c
+++ b/arch/x86/kernel/signal.c
@@ -1,32 +1,37 @@
 /*
  *  Copyright (C) 1991, 1992  Linus Torvalds
+ *  Copyright (C) 2000, 2001, 2002 Andi Kleen SuSE Labs
  *
  *  1997-11-28  Modified for POSIX.1b signals by Richard Henderson
  *  2000-06-20  Pentium III FXSR, SSE support by Gareth Hughes
+ *  2000-2002   x86-64 support by Andi Kleen
  */
-#include <linux/list.h>
 
-#include <linux/personality.h>
-#include <linux/binfmts.h>
-#include <linux/suspend.h>
+#include <linux/sched.h>
+#include <linux/mm.h>
+#include <linux/smp.h>
 #include <linux/kernel.h>
-#include <linux/ptrace.h>
 #include <linux/signal.h>
-#include <linux/stddef.h>
-#include <linux/unistd.h>
 #include <linux/errno.h>
-#include <linux/sched.h>
 #include <linux/wait.h>
+#include <linux/ptrace.h>
 #include <linux/tracehook.h>
-#include <linux/elf.h>
-#include <linux/smp.h>
-#include <linux/mm.h>
+#include <linux/unistd.h>
+#include <linux/stddef.h>
+#include <linux/personality.h>
+#include <linux/uaccess.h>
 
 #include <asm/processor.h>
 #include <asm/ucontext.h>
-#include <asm/uaccess.h>
 #include <asm/i387.h>
 #include <asm/vdso.h>
+
+#ifdef CONFIG_X86_64
+#include <asm/proto.h>
+#include <asm/ia32_unistd.h>
+#include <asm/mce.h>
+#endif /* CONFIG_X86_64 */
+
 #include <asm/syscall.h>
 #include <asm/syscalls.h>
 
@@ -45,74 +50,6 @@
 # define FIX_EFLAGS	__FIX_EFLAGS
 #endif
 
-/*
- * Atomically swap in the new signal mask, and wait for a signal.
- */
-asmlinkage int
-sys_sigsuspend(int history0, int history1, old_sigset_t mask)
-{
-	mask &= _BLOCKABLE;
-	spin_lock_irq(&current->sighand->siglock);
-	current->saved_sigmask = current->blocked;
-	siginitset(&current->blocked, mask);
-	recalc_sigpending();
-	spin_unlock_irq(&current->sighand->siglock);
-
-	current->state = TASK_INTERRUPTIBLE;
-	schedule();
-	set_restore_sigmask();
-
-	return -ERESTARTNOHAND;
-}
-
-asmlinkage int
-sys_sigaction(int sig, const struct old_sigaction __user *act,
-	      struct old_sigaction __user *oact)
-{
-	struct k_sigaction new_ka, old_ka;
-	int ret;
-
-	if (act) {
-		old_sigset_t mask;
-
-		if (!access_ok(VERIFY_READ, act, sizeof(*act)) ||
-		    __get_user(new_ka.sa.sa_handler, &act->sa_handler) ||
-		    __get_user(new_ka.sa.sa_restorer, &act->sa_restorer))
-			return -EFAULT;
-
-		__get_user(new_ka.sa.sa_flags, &act->sa_flags);
-		__get_user(mask, &act->sa_mask);
-		siginitset(&new_ka.sa.sa_mask, mask);
-	}
-
-	ret = do_sigaction(sig, act ? &new_ka : NULL, oact ? &old_ka : NULL);
-
-	if (!ret && oact) {
-		if (!access_ok(VERIFY_WRITE, oact, sizeof(*oact)) ||
-		    __put_user(old_ka.sa.sa_handler, &oact->sa_handler) ||
-		    __put_user(old_ka.sa.sa_restorer, &oact->sa_restorer))
-			return -EFAULT;
-
-		__put_user(old_ka.sa.sa_flags, &oact->sa_flags);
-		__put_user(old_ka.sa.sa_mask.sig[0], &oact->sa_mask);
-	}
-
-	return ret;
-}
-
-asmlinkage int sys_sigaltstack(unsigned long bx)
-{
-	/*
-	 * This is needed to make gcc realize it doesn't own the
-	 * "struct pt_regs"
-	 */
-	struct pt_regs *regs = (struct pt_regs *)&bx;
-	const stack_t __user *uss = (const stack_t __user *)bx;
-	stack_t __user *uoss = (stack_t __user *)regs->cx;
-
-	return do_sigaltstack(uss, uoss, regs->sp);
-}
-
 #define COPY(x)			{		\
 	err |= __get_user(regs->x, &sc->x);	\
 }
@@ -123,7 +60,7 @@ asmlinkage int sys_sigaltstack(unsigned long bx)
 		regs->seg = tmp;			\
 }
 
-#define COPY_SEG_STRICT(seg)	{			\
+#define COPY_SEG_CPL3(seg)	{			\
 		unsigned short tmp;			\
 		err |= __get_user(tmp, &sc->seg);	\
 		regs->seg = tmp | 3;			\
@@ -135,9 +72,6 @@ asmlinkage int sys_sigaltstack(unsigned long bx)
 		loadsegment(seg, tmp);			\
 }
 
-/*
- * Do a signal return; undo the signal stack.
- */
 static int
 restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc,
 		   unsigned long *pax)
@@ -149,14 +83,36 @@ restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc,
 	/* Always make any pending restarted system calls return -EINTR */
 	current_thread_info()->restart_block.fn = do_no_restart_syscall;
 
+#ifdef CONFIG_X86_32
 	GET_SEG(gs);
 	COPY_SEG(fs);
 	COPY_SEG(es);
 	COPY_SEG(ds);
+#endif /* CONFIG_X86_32 */
+
 	COPY(di); COPY(si); COPY(bp); COPY(sp); COPY(bx);
 	COPY(dx); COPY(cx); COPY(ip);
-	COPY_SEG_STRICT(cs);
-	COPY_SEG_STRICT(ss);
+
+#ifdef CONFIG_X86_64
+	COPY(r8);
+	COPY(r9);
+	COPY(r10);
+	COPY(r11);
+	COPY(r12);
+	COPY(r13);
+	COPY(r14);
+	COPY(r15);
+#endif /* CONFIG_X86_64 */
+
+#ifdef CONFIG_X86_32
+	COPY_SEG_CPL3(cs);
+	COPY_SEG_CPL3(ss);
+#else /* !CONFIG_X86_32 */
+	/* Kernel saves and restores only the CS segment register on signals,
+	 * which is the bare minimum needed to allow mixed 32/64-bit code.
+	 * App's signal handler can save/restore other segments if needed. */
+	COPY_SEG_CPL3(cs);
+#endif /* CONFIG_X86_32 */
 
 	err |= __get_user(tmpflags, &sc->flags);
 	regs->flags = (regs->flags & ~FIX_EFLAGS) | (tmpflags & FIX_EFLAGS);
@@ -169,102 +125,24 @@ restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc,
 	return err;
 }
 
-asmlinkage unsigned long sys_sigreturn(unsigned long __unused)
-{
-	struct sigframe __user *frame;
-	struct pt_regs *regs;
-	unsigned long ax;
-	sigset_t set;
-
-	regs = (struct pt_regs *) &__unused;
-	frame = (struct sigframe __user *)(regs->sp - 8);
-
-	if (!access_ok(VERIFY_READ, frame, sizeof(*frame)))
-		goto badframe;
-	if (__get_user(set.sig[0], &frame->sc.oldmask) || (_NSIG_WORDS > 1
-		&& __copy_from_user(&set.sig[1], &frame->extramask,
-				    sizeof(frame->extramask))))
-		goto badframe;
-
-	sigdelsetmask(&set, ~_BLOCKABLE);
-	spin_lock_irq(&current->sighand->siglock);
-	current->blocked = set;
-	recalc_sigpending();
-	spin_unlock_irq(&current->sighand->siglock);
-
-	if (restore_sigcontext(regs, &frame->sc, &ax))
-		goto badframe;
-	return ax;
-
-badframe:
-	if (show_unhandled_signals && printk_ratelimit()) {
-		printk("%s%s[%d] bad frame in sigreturn frame:"
-			"%p ip:%lx sp:%lx oeax:%lx",
-		    task_pid_nr(current) > 1 ? KERN_INFO : KERN_EMERG,
-		    current->comm, task_pid_nr(current), frame, regs->ip,
-		    regs->sp, regs->orig_ax);
-		print_vma_addr(" in ", regs->ip);
-		printk(KERN_CONT "\n");
-	}
-
-	force_sig(SIGSEGV, current);
-
-	return 0;
-}
-
-static long do_rt_sigreturn(struct pt_regs *regs)
-{
-	struct rt_sigframe __user *frame;
-	unsigned long ax;
-	sigset_t set;
-
-	frame = (struct rt_sigframe __user *)(regs->sp - sizeof(long));
-	if (!access_ok(VERIFY_READ, frame, sizeof(*frame)))
-		goto badframe;
-	if (__copy_from_user(&set, &frame->uc.uc_sigmask, sizeof(set)))
-		goto badframe;
-
-	sigdelsetmask(&set, ~_BLOCKABLE);
-	spin_lock_irq(&current->sighand->siglock);
-	current->blocked = set;
-	recalc_sigpending();
-	spin_unlock_irq(&current->sighand->siglock);
-
-	if (restore_sigcontext(regs, &frame->uc.uc_mcontext, &ax))
-		goto badframe;
-
-	if (do_sigaltstack(&frame->uc.uc_stack, NULL, regs->sp) == -EFAULT)
-		goto badframe;
-
-	return ax;
-
-badframe:
-	signal_fault(regs, frame, "rt_sigreturn");
-	return 0;
-}
-
-asmlinkage int sys_rt_sigreturn(unsigned long __unused)
-{
-	struct pt_regs *regs = (struct pt_regs *)&__unused;
-
-	return do_rt_sigreturn(regs);
-}
-
-/*
- * Set up a signal frame.
- */
 static int
 setup_sigcontext(struct sigcontext __user *sc, void __user *fpstate,
 		 struct pt_regs *regs, unsigned long mask)
 {
-	int tmp, err = 0;
+	int err = 0;
 
-	err |= __put_user(regs->fs, (unsigned int __user *)&sc->fs);
-	savesegment(gs, tmp);
-	err |= __put_user(tmp, (unsigned int __user *)&sc->gs);
+#ifdef CONFIG_X86_32
+	{
+		unsigned int tmp;
 
+		savesegment(gs, tmp);
+		err |= __put_user(tmp, (unsigned int __user *)&sc->gs);
+	}
+	err |= __put_user(regs->fs, (unsigned int __user *)&sc->fs);
 	err |= __put_user(regs->es, (unsigned int __user *)&sc->es);
 	err |= __put_user(regs->ds, (unsigned int __user *)&sc->ds);
+#endif /* CONFIG_X86_32 */
+
 	err |= __put_user(regs->di, &sc->di);
 	err |= __put_user(regs->si, &sc->si);
 	err |= __put_user(regs->bp, &sc->bp);
@@ -273,19 +151,33 @@ setup_sigcontext(struct sigcontext __user *sc, void __user *fpstate,
 	err |= __put_user(regs->dx, &sc->dx);
 	err |= __put_user(regs->cx, &sc->cx);
 	err |= __put_user(regs->ax, &sc->ax);
+#ifdef CONFIG_X86_64
+	err |= __put_user(regs->r8, &sc->r8);
+	err |= __put_user(regs->r9, &sc->r9);
+	err |= __put_user(regs->r10, &sc->r10);
+	err |= __put_user(regs->r11, &sc->r11);
+	err |= __put_user(regs->r12, &sc->r12);
+	err |= __put_user(regs->r13, &sc->r13);
+	err |= __put_user(regs->r14, &sc->r14);
+	err |= __put_user(regs->r15, &sc->r15);
+#endif /* CONFIG_X86_64 */
+
 	err |= __put_user(current->thread.trap_no, &sc->trapno);
 	err |= __put_user(current->thread.error_code, &sc->err);
 	err |= __put_user(regs->ip, &sc->ip);
+#ifdef CONFIG_X86_32
 	err |= __put_user(regs->cs, (unsigned int __user *)&sc->cs);
 	err |= __put_user(regs->flags, &sc->flags);
 	err |= __put_user(regs->sp, &sc->sp_at_signal);
 	err |= __put_user(regs->ss, (unsigned int __user *)&sc->ss);
+#else /* !CONFIG_X86_32 */
+	err |= __put_user(regs->flags, &sc->flags);
+	err |= __put_user(regs->cs, &sc->cs);
+	err |= __put_user(0, &sc->gs);
+	err |= __put_user(0, &sc->fs);
+#endif /* CONFIG_X86_32 */
 
-	tmp = save_i387_xstate(fpstate);
-	if (tmp < 0)
-		err = 1;
-	else
-		err |= __put_user(tmp ? fpstate : NULL, &sc->fpstate);
+	err |= __put_user(fpstate, &sc->fpstate);
 
 	/* non-iBCS2 extensions.. */
 	err |= __put_user(mask, &sc->oldmask);
@@ -295,6 +187,32 @@ setup_sigcontext(struct sigcontext __user *sc, void __user *fpstate,
 }
 
 /*
+ * Set up a signal frame.
+ */
+#ifdef CONFIG_X86_32
+static const struct {
+	u16 poplmovl;
+	u32 val;
+	u16 int80;
+} __attribute__((packed)) retcode = {
+	0xb858,		/* popl %eax; movl $..., %eax */
+	__NR_sigreturn,
+	0x80cd,		/* int $0x80 */
+};
+
+static const struct {
+	u8  movl;
+	u32 val;
+	u16 int80;
+	u8  pad;
+} __attribute__((packed)) rt_retcode = {
+	0xb8,		/* movl $..., %eax */
+	__NR_rt_sigreturn,
+	0x80cd,		/* int $0x80 */
+	0
+};
+
+/*
  * Determine which stack to use..
  */
 static inline void __user *
@@ -328,6 +246,8 @@ get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, size_t frame_size,
 	if (used_math()) {
 		sp = sp - sig_xstate_size;
 		*fpstate = (struct _fpstate *) sp;
+		if (save_i387_xstate(*fpstate) < 0)
+			return (void __user *)-1L;
 	}
 
 	sp -= frame_size;
@@ -383,9 +303,7 @@ __setup_frame(int sig, struct k_sigaction *ka, sigset_t *set,
 	 * reasons and because gdb uses it as a signature to notice
 	 * signal handler stack frames.
 	 */
-	err |= __put_user(0xb858, (short __user *)(frame->retcode+0));
-	err |= __put_user(__NR_sigreturn, (int __user *)(frame->retcode+2));
-	err |= __put_user(0x80cd, (short __user *)(frame->retcode+6));
+	err |= __put_user(*((u64 *)&retcode), (u64 *)frame->retcode);
 
 	if (err)
 		return -EFAULT;
@@ -454,9 +372,7 @@ static int __setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
 	 * reasons and because gdb uses it as a signature to notice
 	 * signal handler stack frames.
 	 */
-	err |= __put_user(0xb8, (char __user *)(frame->retcode+0));
-	err |= __put_user(__NR_rt_sigreturn, (int __user *)(frame->retcode+1));
-	err |= __put_user(0x80cd, (short __user *)(frame->retcode+5));
+	err |= __put_user(*((u64 *)&rt_retcode), (u64 *)frame->retcode);
 
 	if (err)
 		return -EFAULT;
@@ -475,23 +391,300 @@ static int __setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
 
 	return 0;
 }
+#else /* !CONFIG_X86_32 */
+/*
+ * Determine which stack to use..
+ */
+static void __user *
+get_stack(struct k_sigaction *ka, unsigned long sp, unsigned long size)
+{
+	/* Default to using normal stack - redzone*/
+	sp -= 128;
+
+	/* This is the X/Open sanctioned signal stack switching.  */
+	if (ka->sa.sa_flags & SA_ONSTACK) {
+		if (sas_ss_flags(sp) == 0)
+			sp = current->sas_ss_sp + current->sas_ss_size;
+	}
+
+	return (void __user *)round_down(sp - size, 64);
+}
+
+static int __setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
+			    sigset_t *set, struct pt_regs *regs)
+{
+	struct rt_sigframe __user *frame;
+	void __user *fp = NULL;
+	int err = 0;
+	struct task_struct *me = current;
+
+	if (used_math()) {
+		fp = get_stack(ka, regs->sp, sig_xstate_size);
+		frame = (void __user *)round_down(
+			(unsigned long)fp - sizeof(struct rt_sigframe), 16) - 8;
+
+		if (save_i387_xstate(fp) < 0)
+			return -EFAULT;
+	} else
+		frame = get_stack(ka, regs->sp, sizeof(struct rt_sigframe)) - 8;
+
+	if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame)))
+		return -EFAULT;
+
+	if (ka->sa.sa_flags & SA_SIGINFO) {
+		if (copy_siginfo_to_user(&frame->info, info))
+			return -EFAULT;
+	}
+
+	/* Create the ucontext.  */
+	if (cpu_has_xsave)
+		err |= __put_user(UC_FP_XSTATE, &frame->uc.uc_flags);
+	else
+		err |= __put_user(0, &frame->uc.uc_flags);
+	err |= __put_user(0, &frame->uc.uc_link);
+	err |= __put_user(me->sas_ss_sp, &frame->uc.uc_stack.ss_sp);
+	err |= __put_user(sas_ss_flags(regs->sp),
+			  &frame->uc.uc_stack.ss_flags);
+	err |= __put_user(me->sas_ss_size, &frame->uc.uc_stack.ss_size);
+	err |= setup_sigcontext(&frame->uc.uc_mcontext, fp, regs, set->sig[0]);
+	err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set));
+
+	/* Set up to return from userspace.  If provided, use a stub
+	   already in userspace.  */
+	/* x86-64 should always use SA_RESTORER. */
+	if (ka->sa.sa_flags & SA_RESTORER) {
+		err |= __put_user(ka->sa.sa_restorer, &frame->pretcode);
+	} else {
+		/* could use a vstub here */
+		return -EFAULT;
+	}
+
+	if (err)
+		return -EFAULT;
+
+	/* Set up registers for signal handler */
+	regs->di = sig;
+	/* In case the signal handler was declared without prototypes */
+	regs->ax = 0;
+
+	/* This also works for non SA_SIGINFO handlers because they expect the
+	   next argument after the signal number on the stack. */
+	regs->si = (unsigned long)&frame->info;
+	regs->dx = (unsigned long)&frame->uc;
+	regs->ip = (unsigned long) ka->sa.sa_handler;
+
+	regs->sp = (unsigned long)frame;
+
+	/* Set up the CS register to run signal handlers in 64-bit mode,
+	   even if the handler happens to be interrupting 32-bit code. */
+	regs->cs = __USER_CS;
+
+	return 0;
+}
+#endif /* CONFIG_X86_32 */
+
+#ifdef CONFIG_X86_32
+/*
+ * Atomically swap in the new signal mask, and wait for a signal.
+ */
+asmlinkage int
+sys_sigsuspend(int history0, int history1, old_sigset_t mask)
+{
+	mask &= _BLOCKABLE;
+	spin_lock_irq(&current->sighand->siglock);
+	current->saved_sigmask = current->blocked;
+	siginitset(&current->blocked, mask);
+	recalc_sigpending();
+	spin_unlock_irq(&current->sighand->siglock);
+
+	current->state = TASK_INTERRUPTIBLE;
+	schedule();
+	set_restore_sigmask();
+
+	return -ERESTARTNOHAND;
+}
+
+asmlinkage int
+sys_sigaction(int sig, const struct old_sigaction __user *act,
+	      struct old_sigaction __user *oact)
+{
+	struct k_sigaction new_ka, old_ka;
+	int ret;
+
+	if (act) {
+		old_sigset_t mask;
+
+		if (!access_ok(VERIFY_READ, act, sizeof(*act)) ||
+		    __get_user(new_ka.sa.sa_handler, &act->sa_handler) ||
+		    __get_user(new_ka.sa.sa_restorer, &act->sa_restorer))
+			return -EFAULT;
+
+		__get_user(new_ka.sa.sa_flags, &act->sa_flags);
+		__get_user(mask, &act->sa_mask);
+		siginitset(&new_ka.sa.sa_mask, mask);
+	}
+
+	ret = do_sigaction(sig, act ? &new_ka : NULL, oact ? &old_ka : NULL);
+
+	if (!ret && oact) {
+		if (!access_ok(VERIFY_WRITE, oact, sizeof(*oact)) ||
+		    __put_user(old_ka.sa.sa_handler, &oact->sa_handler) ||
+		    __put_user(old_ka.sa.sa_restorer, &oact->sa_restorer))
+			return -EFAULT;
+
+		__put_user(old_ka.sa.sa_flags, &oact->sa_flags);
+		__put_user(old_ka.sa.sa_mask.sig[0], &oact->sa_mask);
+	}
+
+	return ret;
+}
+#endif /* CONFIG_X86_32 */
+
+#ifdef CONFIG_X86_32
+asmlinkage int sys_sigaltstack(unsigned long bx)
+{
+	/*
+	 * This is needed to make gcc realize it doesn't own the
+	 * "struct pt_regs"
+	 */
+	struct pt_regs *regs = (struct pt_regs *)&bx;
+	const stack_t __user *uss = (const stack_t __user *)bx;
+	stack_t __user *uoss = (stack_t __user *)regs->cx;
+
+	return do_sigaltstack(uss, uoss, regs->sp);
+}
+#else /* !CONFIG_X86_32 */
+asmlinkage long
+sys_sigaltstack(const stack_t __user *uss, stack_t __user *uoss,
+		struct pt_regs *regs)
+{
+	return do_sigaltstack(uss, uoss, regs->sp);
+}
+#endif /* CONFIG_X86_32 */
+
+/*
+ * Do a signal return; undo the signal stack.
+ */
+#ifdef CONFIG_X86_32
+asmlinkage unsigned long sys_sigreturn(unsigned long __unused)
+{
+	struct sigframe __user *frame;
+	struct pt_regs *regs;
+	unsigned long ax;
+	sigset_t set;
+
+	regs = (struct pt_regs *) &__unused;
+	frame = (struct sigframe __user *)(regs->sp - 8);
+
+	if (!access_ok(VERIFY_READ, frame, sizeof(*frame)))
+		goto badframe;
+	if (__get_user(set.sig[0], &frame->sc.oldmask) || (_NSIG_WORDS > 1
+		&& __copy_from_user(&set.sig[1], &frame->extramask,
+				    sizeof(frame->extramask))))
+		goto badframe;
+
+	sigdelsetmask(&set, ~_BLOCKABLE);
+	spin_lock_irq(&current->sighand->siglock);
+	current->blocked = set;
+	recalc_sigpending();
+	spin_unlock_irq(&current->sighand->siglock);
+
+	if (restore_sigcontext(regs, &frame->sc, &ax))
+		goto badframe;
+	return ax;
+
+badframe:
+	if (show_unhandled_signals && printk_ratelimit()) {
+		printk("%s%s[%d] bad frame in sigreturn frame:"
+			"%p ip:%lx sp:%lx oeax:%lx",
+		    task_pid_nr(current) > 1 ? KERN_INFO : KERN_EMERG,
+		    current->comm, task_pid_nr(current), frame, regs->ip,
+		    regs->sp, regs->orig_ax);
+		print_vma_addr(" in ", regs->ip);
+		printk(KERN_CONT "\n");
+	}
+
+	force_sig(SIGSEGV, current);
+
+	return 0;
+}
+#endif /* CONFIG_X86_32 */
+
+static long do_rt_sigreturn(struct pt_regs *regs)
+{
+	struct rt_sigframe __user *frame;
+	unsigned long ax;
+	sigset_t set;
+
+	frame = (struct rt_sigframe __user *)(regs->sp - sizeof(long));
+	if (!access_ok(VERIFY_READ, frame, sizeof(*frame)))
+		goto badframe;
+	if (__copy_from_user(&set, &frame->uc.uc_sigmask, sizeof(set)))
+		goto badframe;
+
+	sigdelsetmask(&set, ~_BLOCKABLE);
+	spin_lock_irq(&current->sighand->siglock);
+	current->blocked = set;
+	recalc_sigpending();
+	spin_unlock_irq(&current->sighand->siglock);
+
+	if (restore_sigcontext(regs, &frame->uc.uc_mcontext, &ax))
+		goto badframe;
+
+	if (do_sigaltstack(&frame->uc.uc_stack, NULL, regs->sp) == -EFAULT)
+		goto badframe;
+
+	return ax;
+
+badframe:
+	signal_fault(regs, frame, "rt_sigreturn");
+	return 0;
+}
+
+#ifdef CONFIG_X86_32
+asmlinkage int sys_rt_sigreturn(unsigned long __unused)
+{
+	struct pt_regs *regs = (struct pt_regs *)&__unused;
+
+	return do_rt_sigreturn(regs);
+}
+#else /* !CONFIG_X86_32 */
+asmlinkage long sys_rt_sigreturn(struct pt_regs *regs)
+{
+	return do_rt_sigreturn(regs);
+}
+#endif /* CONFIG_X86_32 */
 
 /*
  * OK, we're invoking a handler:
  */
 static int signr_convert(int sig)
 {
+#ifdef CONFIG_X86_32
 	struct thread_info *info = current_thread_info();
 
 	if (info->exec_domain && info->exec_domain->signal_invmap && sig < 32)
 		return info->exec_domain->signal_invmap[sig];
+#endif /* CONFIG_X86_32 */
 	return sig;
 }
 
+#ifdef CONFIG_X86_32
+
 #define is_ia32	1
 #define ia32_setup_frame	__setup_frame
 #define ia32_setup_rt_frame	__setup_rt_frame
 
+#else /* !CONFIG_X86_32 */
+
+#ifdef CONFIG_IA32_EMULATION
+#define is_ia32	test_thread_flag(TIF_IA32)
+#else /* !CONFIG_IA32_EMULATION */
+#define is_ia32	0
+#endif /* CONFIG_IA32_EMULATION */
+
+#endif /* CONFIG_X86_32 */
+
 static int
 setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
 	       sigset_t *set, struct pt_regs *regs)
@@ -592,7 +785,13 @@ handle_signal(unsigned long sig, siginfo_t *info, struct k_sigaction *ka,
 	return 0;
 }
 
+#ifdef CONFIG_X86_32
 #define NR_restart_syscall	__NR_restart_syscall
+#else /* !CONFIG_X86_32 */
+#define NR_restart_syscall	\
+	test_thread_flag(TIF_IA32) ? __NR_ia32_restart_syscall : __NR_restart_syscall
+#endif /* CONFIG_X86_32 */
+
 /*
  * Note that 'init' is a special process: it doesn't get signals it doesn't
  * want to handle. Thus you cannot kill init even with a SIGKILL even by
diff --git a/arch/x86/kernel/signal_64.c b/arch/x86/kernel/signal_64.c
deleted file mode 100644
index a5c9627f4db9..000000000000
--- a/arch/x86/kernel/signal_64.c
+++ /dev/null
@@ -1,516 +0,0 @@
-/*
- *  Copyright (C) 1991, 1992  Linus Torvalds
- *  Copyright (C) 2000, 2001, 2002 Andi Kleen SuSE Labs
- *
- *  1997-11-28  Modified for POSIX.1b signals by Richard Henderson
- *  2000-06-20  Pentium III FXSR, SSE support by Gareth Hughes
- *  2000-2002   x86-64 support by Andi Kleen
- */
-
-#include <linux/sched.h>
-#include <linux/mm.h>
-#include <linux/smp.h>
-#include <linux/kernel.h>
-#include <linux/signal.h>
-#include <linux/errno.h>
-#include <linux/wait.h>
-#include <linux/ptrace.h>
-#include <linux/tracehook.h>
-#include <linux/unistd.h>
-#include <linux/stddef.h>
-#include <linux/personality.h>
-#include <linux/compiler.h>
-#include <linux/uaccess.h>
-
-#include <asm/processor.h>
-#include <asm/ucontext.h>
-#include <asm/i387.h>
-#include <asm/proto.h>
-#include <asm/ia32_unistd.h>
-#include <asm/mce.h>
-#include <asm/syscall.h>
-#include <asm/syscalls.h>
-#include "sigframe.h"
-
-#define _BLOCKABLE (~(sigmask(SIGKILL) | sigmask(SIGSTOP)))
-
-#define __FIX_EFLAGS	(X86_EFLAGS_AC | X86_EFLAGS_OF | \
-			 X86_EFLAGS_DF | X86_EFLAGS_TF | X86_EFLAGS_SF | \
-			 X86_EFLAGS_ZF | X86_EFLAGS_AF | X86_EFLAGS_PF | \
-			 X86_EFLAGS_CF)
-
-#ifdef CONFIG_X86_32
-# define FIX_EFLAGS	(__FIX_EFLAGS | X86_EFLAGS_RF)
-#else
-# define FIX_EFLAGS	__FIX_EFLAGS
-#endif
-
-asmlinkage long
-sys_sigaltstack(const stack_t __user *uss, stack_t __user *uoss,
-		struct pt_regs *regs)
-{
-	return do_sigaltstack(uss, uoss, regs->sp);
-}
-
-#define COPY(x)			{		\
-	err |= __get_user(regs->x, &sc->x);	\
-}
-
-#define COPY_SEG_STRICT(seg)	{			\
-		unsigned short tmp;			\
-		err |= __get_user(tmp, &sc->seg);	\
-		regs->seg = tmp | 3;			\
-}
-
-/*
- * Do a signal return; undo the signal stack.
- */
-static int
-restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc,
-		   unsigned long *pax)
-{
-	void __user *buf;
-	unsigned int tmpflags;
-	unsigned int err = 0;
-
-	/* Always make any pending restarted system calls return -EINTR */
-	current_thread_info()->restart_block.fn = do_no_restart_syscall;
-
-	COPY(di); COPY(si); COPY(bp); COPY(sp); COPY(bx);
-	COPY(dx); COPY(cx); COPY(ip);
-	COPY(r8);
-	COPY(r9);
-	COPY(r10);
-	COPY(r11);
-	COPY(r12);
-	COPY(r13);
-	COPY(r14);
-	COPY(r15);
-
-	/* Kernel saves and restores only the CS segment register on signals,
-	 * which is the bare minimum needed to allow mixed 32/64-bit code.
-	 * App's signal handler can save/restore other segments if needed. */
-	COPY_SEG_STRICT(cs);
-
-	err |= __get_user(tmpflags, &sc->flags);
-	regs->flags = (regs->flags & ~FIX_EFLAGS) | (tmpflags & FIX_EFLAGS);
-	regs->orig_ax = -1;		/* disable syscall checks */
-
-	err |= __get_user(buf, &sc->fpstate);
-	err |= restore_i387_xstate(buf);
-
-	err |= __get_user(*pax, &sc->ax);
-	return err;
-}
-
-static long do_rt_sigreturn(struct pt_regs *regs)
-{
-	struct rt_sigframe __user *frame;
-	unsigned long ax;
-	sigset_t set;
-
-	frame = (struct rt_sigframe __user *)(regs->sp - sizeof(long));
-	if (!access_ok(VERIFY_READ, frame, sizeof(*frame)))
-		goto badframe;
-	if (__copy_from_user(&set, &frame->uc.uc_sigmask, sizeof(set)))
-		goto badframe;
-
-	sigdelsetmask(&set, ~_BLOCKABLE);
-	spin_lock_irq(&current->sighand->siglock);
-	current->blocked = set;
-	recalc_sigpending();
-	spin_unlock_irq(&current->sighand->siglock);
-
-	if (restore_sigcontext(regs, &frame->uc.uc_mcontext, &ax))
-		goto badframe;
-
-	if (do_sigaltstack(&frame->uc.uc_stack, NULL, regs->sp) == -EFAULT)
-		goto badframe;
-
-	return ax;
-
-badframe:
-	signal_fault(regs, frame, "rt_sigreturn");
-	return 0;
-}
-
-asmlinkage long sys_rt_sigreturn(struct pt_regs *regs)
-{
-	return do_rt_sigreturn(regs);
-}
-
-/*
- * Set up a signal frame.
- */
-
-static inline int
-setup_sigcontext(struct sigcontext __user *sc, struct pt_regs *regs,
-		unsigned long mask, struct task_struct *me)
-{
-	int err = 0;
-
-	err |= __put_user(regs->cs, &sc->cs);
-	err |= __put_user(0, &sc->gs);
-	err |= __put_user(0, &sc->fs);
-
-	err |= __put_user(regs->di, &sc->di);
-	err |= __put_user(regs->si, &sc->si);
-	err |= __put_user(regs->bp, &sc->bp);
-	err |= __put_user(regs->sp, &sc->sp);
-	err |= __put_user(regs->bx, &sc->bx);
-	err |= __put_user(regs->dx, &sc->dx);
-	err |= __put_user(regs->cx, &sc->cx);
-	err |= __put_user(regs->ax, &sc->ax);
-	err |= __put_user(regs->r8, &sc->r8);
-	err |= __put_user(regs->r9, &sc->r9);
-	err |= __put_user(regs->r10, &sc->r10);
-	err |= __put_user(regs->r11, &sc->r11);
-	err |= __put_user(regs->r12, &sc->r12);
-	err |= __put_user(regs->r13, &sc->r13);
-	err |= __put_user(regs->r14, &sc->r14);
-	err |= __put_user(regs->r15, &sc->r15);
-	err |= __put_user(me->thread.trap_no, &sc->trapno);
-	err |= __put_user(me->thread.error_code, &sc->err);
-	err |= __put_user(regs->ip, &sc->ip);
-	err |= __put_user(regs->flags, &sc->flags);
-	err |= __put_user(mask, &sc->oldmask);
-	err |= __put_user(me->thread.cr2, &sc->cr2);
-
-	return err;
-}
-
-/*
- * Determine which stack to use..
- */
-
-static void __user *
-get_stack(struct k_sigaction *ka, struct pt_regs *regs, unsigned long size)
-{
-	unsigned long sp;
-
-	/* Default to using normal stack - redzone*/
-	sp = regs->sp - 128;
-
-	/* This is the X/Open sanctioned signal stack switching.  */
-	if (ka->sa.sa_flags & SA_ONSTACK) {
-		if (sas_ss_flags(sp) == 0)
-			sp = current->sas_ss_sp + current->sas_ss_size;
-	}
-
-	return (void __user *)round_down(sp - size, 64);
-}
-
-static int __setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
-			    sigset_t *set, struct pt_regs *regs)
-{
-	struct rt_sigframe __user *frame;
-	void __user *fp = NULL;
-	int err = 0;
-	struct task_struct *me = current;
-
-	if (used_math()) {
-		fp = get_stack(ka, regs, sig_xstate_size);
-		frame = (void __user *)round_down(
-			(unsigned long)fp - sizeof(struct rt_sigframe), 16) - 8;
-
-		if (save_i387_xstate(fp) < 0)
-			return -EFAULT;
-	} else
-		frame = get_stack(ka, regs, sizeof(struct rt_sigframe)) - 8;
-
-	if (!access_ok(VERIFY_WRITE, frame, sizeof(*frame)))
-		return -EFAULT;
-
-	if (ka->sa.sa_flags & SA_SIGINFO) {
-		if (copy_siginfo_to_user(&frame->info, info))
-			return -EFAULT;
-	}
-
-	/* Create the ucontext.  */
-	if (cpu_has_xsave)
-		err |= __put_user(UC_FP_XSTATE, &frame->uc.uc_flags);
-	else
-		err |= __put_user(0, &frame->uc.uc_flags);
-	err |= __put_user(0, &frame->uc.uc_link);
-	err |= __put_user(me->sas_ss_sp, &frame->uc.uc_stack.ss_sp);
-	err |= __put_user(sas_ss_flags(regs->sp),
-			  &frame->uc.uc_stack.ss_flags);
-	err |= __put_user(me->sas_ss_size, &frame->uc.uc_stack.ss_size);
-	err |= setup_sigcontext(&frame->uc.uc_mcontext, regs, set->sig[0], me);
-	err |= __put_user(fp, &frame->uc.uc_mcontext.fpstate);
-	if (sizeof(*set) == 16) {
-		__put_user(set->sig[0], &frame->uc.uc_sigmask.sig[0]);
-		__put_user(set->sig[1], &frame->uc.uc_sigmask.sig[1]);
-	} else
-		err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set));
-
-	/* Set up to return from userspace.  If provided, use a stub
-	   already in userspace.  */
-	/* x86-64 should always use SA_RESTORER. */
-	if (ka->sa.sa_flags & SA_RESTORER) {
-		err |= __put_user(ka->sa.sa_restorer, &frame->pretcode);
-	} else {
-		/* could use a vstub here */
-		return -EFAULT;
-	}
-
-	if (err)
-		return -EFAULT;
-
-	/* Set up registers for signal handler */
-	regs->di = sig;
-	/* In case the signal handler was declared without prototypes */
-	regs->ax = 0;
-
-	/* This also works for non SA_SIGINFO handlers because they expect the
-	   next argument after the signal number on the stack. */
-	regs->si = (unsigned long)&frame->info;
-	regs->dx = (unsigned long)&frame->uc;
-	regs->ip = (unsigned long) ka->sa.sa_handler;
-
-	regs->sp = (unsigned long)frame;
-
-	/* Set up the CS register to run signal handlers in 64-bit mode,
-	   even if the handler happens to be interrupting 32-bit code. */
-	regs->cs = __USER_CS;
-
-	return 0;
-}
-
-/*
- * OK, we're invoking a handler
- */
-static int signr_convert(int sig)
-{
-	return sig;
-}
-
-#ifdef CONFIG_IA32_EMULATION
-#define is_ia32	test_thread_flag(TIF_IA32)
-#else
-#define is_ia32	0
-#endif
-
-static int
-setup_rt_frame(int sig, struct k_sigaction *ka, siginfo_t *info,
-	       sigset_t *set, struct pt_regs *regs)
-{
-	int usig = signr_convert(sig);
-	int ret;
-
-	/* Set up the stack frame */
-	if (is_ia32) {
-		if (ka->sa.sa_flags & SA_SIGINFO)
-			ret = ia32_setup_rt_frame(usig, ka, info, set, regs);
-		else
-			ret = ia32_setup_frame(usig, ka, set, regs);
-	} else
-		ret = __setup_rt_frame(sig, ka, info, set, regs);
-
-	if (ret) {
-		force_sigsegv(sig, current);
-		return -EFAULT;
-	}
-
-	return ret;
-}
-
-static int
-handle_signal(unsigned long sig, siginfo_t *info, struct k_sigaction *ka,
-	      sigset_t *oldset, struct pt_regs *regs)
-{
-	int ret;
-
-	/* Are we from a system call? */
-	if (syscall_get_nr(current, regs) >= 0) {
-		/* If so, check system call restarting.. */
-		switch (syscall_get_error(current, regs)) {
-		case -ERESTART_RESTARTBLOCK:
-		case -ERESTARTNOHAND:
-			regs->ax = -EINTR;
-			break;
-
-		case -ERESTARTSYS:
-			if (!(ka->sa.sa_flags & SA_RESTART)) {
-				regs->ax = -EINTR;
-				break;
-			}
-		/* fallthrough */
-		case -ERESTARTNOINTR:
-			regs->ax = regs->orig_ax;
-			regs->ip -= 2;
-			break;
-		}
-	}
-
-	/*
-	 * If TF is set due to a debugger (TIF_FORCED_TF), clear the TF
-	 * flag so that register information in the sigcontext is correct.
-	 */
-	if (unlikely(regs->flags & X86_EFLAGS_TF) &&
-	    likely(test_and_clear_thread_flag(TIF_FORCED_TF)))
-		regs->flags &= ~X86_EFLAGS_TF;
-
-	ret = setup_rt_frame(sig, ka, info, oldset, regs);
-
-	if (ret)
-		return ret;
-
-#ifdef CONFIG_X86_64
-	/*
-	 * This has nothing to do with segment registers,
-	 * despite the name.  This magic affects uaccess.h
-	 * macros' behavior.  Reset it to the normal setting.
-	 */
-	set_fs(USER_DS);
-#endif
-
-	/*
-	 * Clear the direction flag as per the ABI for function entry.
-	 */
-	regs->flags &= ~X86_EFLAGS_DF;
-
-	/*
-	 * Clear TF when entering the signal handler, but
-	 * notify any tracer that was single-stepping it.
-	 * The tracer may want to single-step inside the
-	 * handler too.
-	 */
-	regs->flags &= ~X86_EFLAGS_TF;
-
-	spin_lock_irq(&current->sighand->siglock);
-	sigorsets(&current->blocked, &current->blocked, &ka->sa.sa_mask);
-	if (!(ka->sa.sa_flags & SA_NODEFER))
-		sigaddset(&current->blocked, sig);
-	recalc_sigpending();
-	spin_unlock_irq(&current->sighand->siglock);
-
-	tracehook_signal_handler(sig, info, ka, regs,
-				 test_thread_flag(TIF_SINGLESTEP));
-
-	return 0;
-}
-
-#define NR_restart_syscall	\
-	test_thread_flag(TIF_IA32) ? __NR_ia32_restart_syscall : __NR_restart_syscall
-/*
- * Note that 'init' is a special process: it doesn't get signals it doesn't
- * want to handle. Thus you cannot kill init even with a SIGKILL even by
- * mistake.
- */
-static void do_signal(struct pt_regs *regs)
-{
-	struct k_sigaction ka;
-	siginfo_t info;
-	int signr;
-	sigset_t *oldset;
-
-	/*
-	 * We want the common case to go fast, which is why we may in certain
-	 * cases get here from kernel mode. Just return without doing anything
-	 * if so.
-	 * X86_32: vm86 regs switched out by assembly code before reaching
-	 * here, so testing against kernel CS suffices.
-	 */
-	if (!user_mode(regs))
-		return;
-
-	if (current_thread_info()->status & TS_RESTORE_SIGMASK)
-		oldset = &current->saved_sigmask;
-	else
-		oldset = &current->blocked;
-
-	signr = get_signal_to_deliver(&info, &ka, regs, NULL);
-	if (signr > 0) {
-		/*
-		 * Re-enable any watchpoints before delivering the
-		 * signal to user space. The processor register will
-		 * have been cleared if the watchpoint triggered
-		 * inside the kernel.
-		 */
-		if (current->thread.debugreg7)
-			set_debugreg(current->thread.debugreg7, 7);
-
-		/* Whee! Actually deliver the signal.  */
-		if (handle_signal(signr, &info, &ka, oldset, regs) == 0) {
-			/*
-			 * A signal was successfully delivered; the saved
-			 * sigmask will have been stored in the signal frame,
-			 * and will be restored by sigreturn, so we can simply
-			 * clear the TS_RESTORE_SIGMASK flag.
-			 */
-			current_thread_info()->status &= ~TS_RESTORE_SIGMASK;
-		}
-		return;
-	}
-
-	/* Did we come from a system call? */
-	if (syscall_get_nr(current, regs) >= 0) {
-		/* Restart the system call - no handlers present */
-		switch (syscall_get_error(current, regs)) {
-		case -ERESTARTNOHAND:
-		case -ERESTARTSYS:
-		case -ERESTARTNOINTR:
-			regs->ax = regs->orig_ax;
-			regs->ip -= 2;
-			break;
-
-		case -ERESTART_RESTARTBLOCK:
-			regs->ax = NR_restart_syscall;
-			regs->ip -= 2;
-			break;
-		}
-	}
-
-	/*
-	 * If there's no signal to deliver, we just put the saved sigmask
-	 * back.
-	 */
-	if (current_thread_info()->status & TS_RESTORE_SIGMASK) {
-		current_thread_info()->status &= ~TS_RESTORE_SIGMASK;
-		sigprocmask(SIG_SETMASK, &current->saved_sigmask, NULL);
-	}
-}
-
-/*
- * notification of userspace execution resumption
- * - triggered by the TIF_WORK_MASK flags
- */
-void
-do_notify_resume(struct pt_regs *regs, void *unused, __u32 thread_info_flags)
-{
-#if defined(CONFIG_X86_64) && defined(CONFIG_X86_MCE)
-	/* notify userspace of pending MCEs */
-	if (thread_info_flags & _TIF_MCE_NOTIFY)
-		mce_notify_user();
-#endif /* CONFIG_X86_64 && CONFIG_X86_MCE */
-
-	/* deal with pending signal delivery */
-	if (thread_info_flags & _TIF_SIGPENDING)
-		do_signal(regs);
-
-	if (thread_info_flags & _TIF_NOTIFY_RESUME) {
-		clear_thread_flag(TIF_NOTIFY_RESUME);
-		tracehook_notify_resume(regs);
-	}
-
-#ifdef CONFIG_X86_32
-	clear_thread_flag(TIF_IRET);
-#endif /* CONFIG_X86_32 */
-}
-
-void signal_fault(struct pt_regs *regs, void __user *frame, char *where)
-{
-	struct task_struct *me = current;
-
-	if (show_unhandled_signals && printk_ratelimit()) {
-		printk(KERN_INFO
-		       "%s[%d] bad frame in %s frame:%p ip:%lx sp:%lx orax:%lx",
-		       me->comm, me->pid, where, frame,
-		       regs->ip, regs->sp, regs->orig_ax);
-		print_vma_addr(" in ", regs->ip);
-		printk(KERN_CONT "\n");
-	}
-
-	force_sig(SIGSEGV, me);
-}
diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c
index 18f9b19f5f8f..3f92b134ab90 100644
--- a/arch/x86/kernel/smp.c
+++ b/arch/x86/kernel/smp.c
@@ -140,19 +140,6 @@ void native_send_call_func_ipi(cpumask_t mask)
 		send_IPI_mask(mask, CALL_FUNCTION_VECTOR);
 }
 
-static void stop_this_cpu(void *dummy)
-{
-	local_irq_disable();
-	/*
-	 * Remove this CPU:
-	 */
-	cpu_clear(smp_processor_id(), cpu_online_map);
-	disable_local_APIC();
-	if (hlt_works(smp_processor_id()))
-		for (;;) halt();
-	for (;;);
-}
-
 /*
  * this function calls the 'stop' function on all other CPUs in the system.
  */
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 7b1093397319..0e9f446269f4 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -62,6 +62,7 @@
 #include <asm/mtrr.h>
 #include <asm/vmi.h>
 #include <asm/genapic.h>
+#include <asm/setup.h>
 #include <linux/mc146818rtc.h>
 
 #include <mach_apic.h>
@@ -536,7 +537,7 @@ static void impress_friends(void)
 	pr_debug("Before bogocount - setting activated=1.\n");
 }
 
-static inline void __inquire_remote_apic(int apicid)
+void __inquire_remote_apic(int apicid)
 {
 	unsigned i, regs[] = { APIC_ID >> 4, APIC_LVR >> 4, APIC_SPIV >> 4 };
 	char *names[] = { "ID", "VERSION", "SPIV" };
@@ -575,14 +576,13 @@ static inline void __inquire_remote_apic(int apicid)
 	}
 }
 
-#ifdef WAKE_SECONDARY_VIA_NMI
 /*
  * Poke the other CPU in the eye via NMI to wake it up. Remember that the normal
  * INIT, INIT, STARTUP sequence will reset the chip hard for us, and this
  * won't ... remember to clear down the APIC, etc later.
  */
-static int __devinit
-wakeup_secondary_cpu(int logical_apicid, unsigned long start_eip)
+int __devinit
+wakeup_secondary_cpu_via_nmi(int logical_apicid, unsigned long start_eip)
 {
 	unsigned long send_status, accept_status = 0;
 	int maxlvt;
@@ -599,7 +599,7 @@ wakeup_secondary_cpu(int logical_apicid, unsigned long start_eip)
 	 * Give the other CPU some time to accept the IPI.
 	 */
 	udelay(200);
-	if (APIC_INTEGRATED(apic_version[phys_apicid])) {
+	if (APIC_INTEGRATED(apic_version[boot_cpu_physical_apicid])) {
 		maxlvt = lapic_get_maxlvt();
 		if (maxlvt > 3)			/* Due to the Pentium erratum 3AP.  */
 			apic_write(APIC_ESR, 0);
@@ -614,11 +614,9 @@ wakeup_secondary_cpu(int logical_apicid, unsigned long start_eip)
 
 	return (send_status | accept_status);
 }
-#endif	/* WAKE_SECONDARY_VIA_NMI */
 
-#ifdef WAKE_SECONDARY_VIA_INIT
-static int __devinit
-wakeup_secondary_cpu(int phys_apicid, unsigned long start_eip)
+int __devinit
+wakeup_secondary_cpu_via_init(int phys_apicid, unsigned long start_eip)
 {
 	unsigned long send_status, accept_status = 0;
 	int maxlvt, num_starts, j;
@@ -737,7 +735,6 @@ wakeup_secondary_cpu(int phys_apicid, unsigned long start_eip)
 
 	return (send_status | accept_status);
 }
-#endif	/* WAKE_SECONDARY_VIA_INIT */
 
 struct create_idle {
 	struct work_struct work;
diff --git a/arch/x86/kernel/stacktrace.c b/arch/x86/kernel/stacktrace.c
index a03e7f6d90c3..10786af95545 100644
--- a/arch/x86/kernel/stacktrace.c
+++ b/arch/x86/kernel/stacktrace.c
@@ -6,6 +6,7 @@
 #include <linux/sched.h>
 #include <linux/stacktrace.h>
 #include <linux/module.h>
+#include <linux/uaccess.h>
 #include <asm/stacktrace.h>
 
 static void save_stack_warning(void *data, char *msg)
@@ -83,3 +84,66 @@ void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
 		trace->entries[trace->nr_entries++] = ULONG_MAX;
 }
 EXPORT_SYMBOL_GPL(save_stack_trace_tsk);
+
+/* Userspace stacktrace - based on kernel/trace/trace_sysprof.c */
+
+struct stack_frame {
+	const void __user	*next_fp;
+	unsigned long		ret_addr;
+};
+
+static int copy_stack_frame(const void __user *fp, struct stack_frame *frame)
+{
+	int ret;
+
+	if (!access_ok(VERIFY_READ, fp, sizeof(*frame)))
+		return 0;
+
+	ret = 1;
+	pagefault_disable();
+	if (__copy_from_user_inatomic(frame, fp, sizeof(*frame)))
+		ret = 0;
+	pagefault_enable();
+
+	return ret;
+}
+
+static inline void __save_stack_trace_user(struct stack_trace *trace)
+{
+	const struct pt_regs *regs = task_pt_regs(current);
+	const void __user *fp = (const void __user *)regs->bp;
+
+	if (trace->nr_entries < trace->max_entries)
+		trace->entries[trace->nr_entries++] = regs->ip;
+
+	while (trace->nr_entries < trace->max_entries) {
+		struct stack_frame frame;
+
+		frame.next_fp = NULL;
+		frame.ret_addr = 0;
+		if (!copy_stack_frame(fp, &frame))
+			break;
+		if ((unsigned long)fp < regs->sp)
+			break;
+		if (frame.ret_addr) {
+			trace->entries[trace->nr_entries++] =
+				frame.ret_addr;
+		}
+		if (fp == frame.next_fp)
+			break;
+		fp = frame.next_fp;
+	}
+}
+
+void save_stack_trace_user(struct stack_trace *trace)
+{
+	/*
+	 * Trace user stack if we are not a kernel thread
+	 */
+	if (current->mm) {
+		__save_stack_trace_user(trace);
+	}
+	if (trace->nr_entries < trace->max_entries)
+		trace->entries[trace->nr_entries++] = ULONG_MAX;
+}
+
diff --git a/arch/x86/kernel/time_64.c b/arch/x86/kernel/time_64.c
index cb19d650c216..418a095c5796 100644
--- a/arch/x86/kernel/time_64.c
+++ b/arch/x86/kernel/time_64.c
@@ -80,6 +80,8 @@ unsigned long __init calibrate_cpu(void)
 			break;
 	no_ctr_free = (i == 4);
 	if (no_ctr_free) {
+		WARN(1, KERN_WARNING "Warning: AMD perfctrs busy ... "
+		     "cpu_khz value may be incorrect.\n");
 		i = 3;
 		rdmsrl(MSR_K7_EVNTSEL3, evntsel3);
 		wrmsrl(MSR_K7_EVNTSEL3, 0);
diff --git a/arch/x86/kernel/tlb_uv.c b/arch/x86/kernel/tlb_uv.c
index 04431f34fd16..6a00e5faaa74 100644
--- a/arch/x86/kernel/tlb_uv.c
+++ b/arch/x86/kernel/tlb_uv.c
@@ -566,14 +566,10 @@ static int __init uv_ptc_init(void)
 	if (!is_uv_system())
 		return 0;
 
-	if (!proc_mkdir("sgi_uv", NULL))
-		return -EINVAL;
-
 	proc_uv_ptc = create_proc_entry(UV_PTC_BASENAME, 0444, NULL);
 	if (!proc_uv_ptc) {
 		printk(KERN_ERR "unable to create %s proc entry\n",
 		       UV_PTC_BASENAME);
-		remove_proc_entry("sgi_uv", NULL);
 		return -EINVAL;
 	}
 	proc_uv_ptc->proc_fops = &proc_uv_ptc_operations;
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 424093b157d3..599e58168631 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -15,6 +15,7 @@
 #include <asm/vgtod.h>
 #include <asm/time.h>
 #include <asm/delay.h>
+#include <asm/hypervisor.h>
 
 unsigned int cpu_khz;           /* TSC clocks / usec, not used here */
 EXPORT_SYMBOL(cpu_khz);
@@ -31,6 +32,7 @@ static int tsc_unstable;
    erroneous rdtsc usage on !cpu_has_tsc processors */
 static int tsc_disabled = -1;
 
+static int tsc_clocksource_reliable;
 /*
  * Scheduler clock - returns current time in nanosec units.
  */
@@ -98,6 +100,15 @@ int __init notsc_setup(char *str)
 
 __setup("notsc", notsc_setup);
 
+static int __init tsc_setup(char *str)
+{
+	if (!strcmp(str, "reliable"))
+		tsc_clocksource_reliable = 1;
+	return 1;
+}
+
+__setup("tsc=", tsc_setup);
+
 #define MAX_RETRIES     5
 #define SMI_TRESHOLD    50000
 
@@ -352,9 +363,15 @@ unsigned long native_calibrate_tsc(void)
 {
 	u64 tsc1, tsc2, delta, ref1, ref2;
 	unsigned long tsc_pit_min = ULONG_MAX, tsc_ref_min = ULONG_MAX;
-	unsigned long flags, latch, ms, fast_calibrate;
+	unsigned long flags, latch, ms, fast_calibrate, tsc_khz;
 	int hpet = is_hpet_enabled(), i, loopmin;
 
+	tsc_khz = get_hypervisor_tsc_freq();
+	if (tsc_khz) {
+		printk(KERN_INFO "TSC: Frequency read from the hypervisor\n");
+		return tsc_khz;
+	}
+
 	local_irq_save(flags);
 	fast_calibrate = quick_pit_calibrate();
 	local_irq_restore(flags);
@@ -731,24 +748,21 @@ static struct dmi_system_id __initdata bad_tsc_dmi_table[] = {
 	{}
 };
 
-/*
- * Geode_LX - the OLPC CPU has a possibly a very reliable TSC
- */
+static void __init check_system_tsc_reliable(void)
+{
 #ifdef CONFIG_MGEODE_LX
-/* RTSC counts during suspend */
+	/* RTSC counts during suspend */
 #define RTSC_SUSP 0x100
-
-static void __init check_geode_tsc_reliable(void)
-{
 	unsigned long res_low, res_high;
 
 	rdmsr_safe(MSR_GEODE_BUSCONT_CONF0, &res_low, &res_high);
+	/* Geode_LX - the OLPC CPU has a possibly a very reliable TSC */
 	if (res_low & RTSC_SUSP)
-		clocksource_tsc.flags &= ~CLOCK_SOURCE_MUST_VERIFY;
-}
-#else
-static inline void check_geode_tsc_reliable(void) { }
+		tsc_clocksource_reliable = 1;
 #endif
+	if (boot_cpu_has(X86_FEATURE_TSC_RELIABLE))
+		tsc_clocksource_reliable = 1;
+}
 
 /*
  * Make an educated guess if the TSC is trustworthy and synchronized
@@ -783,6 +797,8 @@ static void __init init_tsc_clocksource(void)
 {
 	clocksource_tsc.mult = clocksource_khz2mult(tsc_khz,
 			clocksource_tsc.shift);
+	if (tsc_clocksource_reliable)
+		clocksource_tsc.flags &= ~CLOCK_SOURCE_MUST_VERIFY;
 	/* lower the rating if we already know its unstable: */
 	if (check_tsc_unstable()) {
 		clocksource_tsc.rating = 0;
@@ -843,7 +859,7 @@ void __init tsc_init(void)
 	if (unsynchronized_tsc())
 		mark_tsc_unstable("TSCs unsynchronized");
 
-	check_geode_tsc_reliable();
+	check_system_tsc_reliable();
 	init_tsc_clocksource();
 }
 
diff --git a/arch/x86/kernel/tsc_sync.c b/arch/x86/kernel/tsc_sync.c
index 1c0dfbca87c1..bf36328f6ef9 100644
--- a/arch/x86/kernel/tsc_sync.c
+++ b/arch/x86/kernel/tsc_sync.c
@@ -112,6 +112,12 @@ void __cpuinit check_tsc_sync_source(int cpu)
 	if (unsynchronized_tsc())
 		return;
 
+	if (boot_cpu_has(X86_FEATURE_TSC_RELIABLE)) {
+		printk(KERN_INFO
+		       "Skipping synchronization checks as TSC is reliable.\n");
+		return;
+	}
+
 	printk(KERN_INFO "checking TSC synchronization [CPU#%d -> CPU#%d]:",
 			  smp_processor_id(), cpu);
 
@@ -165,7 +171,7 @@ void __cpuinit check_tsc_sync_target(void)
 {
 	int cpus = 2;
 
-	if (unsynchronized_tsc())
+	if (unsynchronized_tsc() || boot_cpu_has(X86_FEATURE_TSC_RELIABLE))
 		return;
 
 	/*
diff --git a/arch/x86/kernel/vsyscall_64.c b/arch/x86/kernel/vsyscall_64.c
index 0b8b6690a86d..44153afc9067 100644
--- a/arch/x86/kernel/vsyscall_64.c
+++ b/arch/x86/kernel/vsyscall_64.c
@@ -17,6 +17,9 @@
  *  want per guest time just set the kernel.vsyscall64 sysctl to 0.
  */
 
+/* Disable profiling for userspace code: */
+#define DISABLE_BRANCH_PROFILING
+
 #include <linux/time.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
@@ -128,7 +131,16 @@ static __always_inline void do_vgettimeofday(struct timeval * tv)
 			gettimeofday(tv,NULL);
 			return;
 		}
+
+		/*
+		 * Surround the RDTSC by barriers, to make sure it's not
+		 * speculated to outside the seqlock critical section and
+		 * does not cause time warps:
+		 */
+		rdtsc_barrier();
 		now = vread();
+		rdtsc_barrier();
+
 		base = __vsyscall_gtod_data.clock.cycle_last;
 		mask = __vsyscall_gtod_data.clock.mask;
 		mult = __vsyscall_gtod_data.clock.mult;
diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c
index a5d8e1ace1cf..50a779264bb1 100644
--- a/arch/x86/lguest/boot.c
+++ b/arch/x86/lguest/boot.c
@@ -590,7 +590,8 @@ static void __init lguest_init_IRQ(void)
 		 * a straightforward 1 to 1 mapping, so force that here. */
 		__get_cpu_var(vector_irq)[vector] = i;
 		if (vector != SYSCALL_VECTOR) {
-			set_intr_gate(vector, interrupt[vector]);
+			set_intr_gate(vector,
+				      interrupt[vector-FIRST_EXTERNAL_VECTOR]);
 			set_irq_chip_and_handler_name(i, &lguest_irq_controller,
 						      handle_level_irq,
 						      "level");
diff --git a/arch/x86/lib/usercopy_32.c b/arch/x86/lib/usercopy_32.c
index 9e68075544f6..4a20b2f9a381 100644
--- a/arch/x86/lib/usercopy_32.c
+++ b/arch/x86/lib/usercopy_32.c
@@ -39,7 +39,7 @@ static inline int __movsl_is_ok(unsigned long a1, unsigned long a2, unsigned lon
 #define __do_strncpy_from_user(dst, src, count, res)			   \
 do {									   \
 	int __d0, __d1, __d2;						   \
-	might_sleep();							   \
+	might_fault();							   \
 	__asm__ __volatile__(						   \
 		"	testl %1,%1\n"					   \
 		"	jz 2f\n"					   \
@@ -126,7 +126,7 @@ EXPORT_SYMBOL(strncpy_from_user);
 #define __do_clear_user(addr,size)					\
 do {									\
 	int __d0;							\
-	might_sleep();							\
+	might_fault();							\
 	__asm__ __volatile__(						\
 		"0:	rep; stosl\n"					\
 		"	movl %2,%0\n"					\
@@ -155,7 +155,7 @@ do {									\
 unsigned long
 clear_user(void __user *to, unsigned long n)
 {
-	might_sleep();
+	might_fault();
 	if (access_ok(VERIFY_WRITE, to, n))
 		__do_clear_user(to, n);
 	return n;
@@ -197,7 +197,7 @@ long strnlen_user(const char __user *s, long n)
 	unsigned long mask = -__addr_ok(s);
 	unsigned long res, tmp;
 
-	might_sleep();
+	might_fault();
 
 	__asm__ __volatile__(
 		"	testl %0, %0\n"
diff --git a/arch/x86/lib/usercopy_64.c b/arch/x86/lib/usercopy_64.c
index f4df6e7c718b..64d6c84e6353 100644
--- a/arch/x86/lib/usercopy_64.c
+++ b/arch/x86/lib/usercopy_64.c
@@ -15,7 +15,7 @@
 #define __do_strncpy_from_user(dst,src,count,res)			   \
 do {									   \
 	long __d0, __d1, __d2;						   \
-	might_sleep();							   \
+	might_fault();							   \
 	__asm__ __volatile__(						   \
 		"	testq %1,%1\n"					   \
 		"	jz 2f\n"					   \
@@ -64,7 +64,7 @@ EXPORT_SYMBOL(strncpy_from_user);
 unsigned long __clear_user(void __user *addr, unsigned long size)
 {
 	long __d0;
-	might_sleep();
+	might_fault();
 	/* no memory constraint because it doesn't change any memory gcc knows
 	   about */
 	asm volatile(
diff --git a/arch/x86/mach-generic/bigsmp.c b/arch/x86/mach-generic/bigsmp.c
index 3c3b471ea496..3624a364b7f3 100644
--- a/arch/x86/mach-generic/bigsmp.c
+++ b/arch/x86/mach-generic/bigsmp.c
@@ -17,6 +17,7 @@
 #include <asm/bigsmp/apic.h>
 #include <asm/bigsmp/ipi.h>
 #include <asm/mach-default/mach_mpparse.h>
+#include <asm/mach-default/mach_wakecpu.h>
 
 static int dmi_bigsmp; /* can be set by dmi scanners */
 
diff --git a/arch/x86/mach-generic/default.c b/arch/x86/mach-generic/default.c
index 9e835a11a13a..e63a4a76d8cd 100644
--- a/arch/x86/mach-generic/default.c
+++ b/arch/x86/mach-generic/default.c
@@ -16,6 +16,7 @@
 #include <asm/mach-default/mach_apic.h>
 #include <asm/mach-default/mach_ipi.h>
 #include <asm/mach-default/mach_mpparse.h>
+#include <asm/mach-default/mach_wakecpu.h>
 
 /* should be called last. */
 static int probe_default(void)
diff --git a/arch/x86/mach-generic/es7000.c b/arch/x86/mach-generic/es7000.c
index 28459cab3ddb..7b4e6d0d1690 100644
--- a/arch/x86/mach-generic/es7000.c
+++ b/arch/x86/mach-generic/es7000.c
@@ -16,7 +16,19 @@
 #include <asm/es7000/apic.h>
 #include <asm/es7000/ipi.h>
 #include <asm/es7000/mpparse.h>
-#include <asm/es7000/wakecpu.h>
+#include <asm/mach-default/mach_wakecpu.h>
+
+void __init es7000_update_genapic_to_cluster(void)
+{
+	genapic->target_cpus = target_cpus_cluster;
+	genapic->int_delivery_mode = INT_DELIVERY_MODE_CLUSTER;
+	genapic->int_dest_mode = INT_DEST_MODE_CLUSTER;
+	genapic->no_balance_irq = NO_BALANCE_IRQ_CLUSTER;
+
+	genapic->init_apic_ldr = init_apic_ldr_cluster;
+
+	genapic->cpu_mask_to_apicid = cpu_mask_to_apicid_cluster;
+}
 
 static int probe_es7000(void)
 {
diff --git a/arch/x86/mach-generic/probe.c b/arch/x86/mach-generic/probe.c
index 5a7e4619e1c4..c346d9d0226f 100644
--- a/arch/x86/mach-generic/probe.c
+++ b/arch/x86/mach-generic/probe.c
@@ -15,6 +15,7 @@
 #include <asm/mpspec.h>
 #include <asm/apicdef.h>
 #include <asm/genapic.h>
+#include <asm/setup.h>
 
 extern struct genapic apic_numaq;
 extern struct genapic apic_summit;
@@ -57,6 +58,9 @@ static int __init parse_apic(char *arg)
 		}
 	}
 
+	if (x86_quirks->update_genapic)
+		x86_quirks->update_genapic();
+
 	/* Parsed again by __setup for debug/verbose */
 	return 0;
 }
@@ -72,12 +76,15 @@ void __init generic_bigsmp_probe(void)
 	 * - we find more than 8 CPUs in acpi LAPIC listing with xAPIC support
 	 */
 
-	if (!cmdline_apic && genapic == &apic_default)
+	if (!cmdline_apic && genapic == &apic_default) {
 		if (apic_bigsmp.probe()) {
 			genapic = &apic_bigsmp;
+			if (x86_quirks->update_genapic)
+				x86_quirks->update_genapic();
 			printk(KERN_INFO "Overriding APIC driver with %s\n",
 			       genapic->name);
 		}
+	}
 #endif
 }
 
@@ -94,6 +101,9 @@ void __init generic_apic_probe(void)
 		/* Not visible without early console */
 		if (!apic_probe[i])
 			panic("Didn't find an APIC driver");
+
+		if (x86_quirks->update_genapic)
+			x86_quirks->update_genapic();
 	}
 	printk(KERN_INFO "Using APIC driver %s\n", genapic->name);
 }
@@ -108,6 +118,8 @@ int __init mps_oem_check(struct mp_config_table *mpc, char *oem,
 		if (apic_probe[i]->mps_oem_check(mpc, oem, productid)) {
 			if (!cmdline_apic) {
 				genapic = apic_probe[i];
+				if (x86_quirks->update_genapic)
+					x86_quirks->update_genapic();
 				printk(KERN_INFO "Switched to APIC driver `%s'.\n",
 				       genapic->name);
 			}
@@ -124,6 +136,8 @@ int __init acpi_madt_oem_check(char *oem_id, char *oem_table_id)
 		if (apic_probe[i]->acpi_madt_oem_check(oem_id, oem_table_id)) {
 			if (!cmdline_apic) {
 				genapic = apic_probe[i];
+				if (x86_quirks->update_genapic)
+					x86_quirks->update_genapic();
 				printk(KERN_INFO "Switched to APIC driver `%s'.\n",
 				       genapic->name);
 			}
diff --git a/arch/x86/mach-generic/summit.c b/arch/x86/mach-generic/summit.c
index 6272b5e69da6..2c6d234e0009 100644
--- a/arch/x86/mach-generic/summit.c
+++ b/arch/x86/mach-generic/summit.c
@@ -16,6 +16,7 @@
 #include <asm/summit/apic.h>
 #include <asm/summit/ipi.h>
 #include <asm/summit/mpparse.h>
+#include <asm/mach-default/mach_wakecpu.h>
 
 static int probe_summit(void)
 {
diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile
index fea4565ff576..d8cc96a2738f 100644
--- a/arch/x86/mm/Makefile
+++ b/arch/x86/mm/Makefile
@@ -8,9 +8,8 @@ obj-$(CONFIG_X86_PTDUMP)	+= dump_pagetables.o
 
 obj-$(CONFIG_HIGHMEM)		+= highmem_32.o
 
-obj-$(CONFIG_MMIOTRACE_HOOKS)	+= kmmio.o
 obj-$(CONFIG_MMIOTRACE)		+= mmiotrace.o
-mmiotrace-y			:= pf_in.o mmio-mod.o
+mmiotrace-y			:= kmmio.o pf_in.o mmio-mod.o
 obj-$(CONFIG_MMIOTRACE_TEST)	+= testmmiotrace.o
 
 obj-$(CONFIG_NUMA)		+= numa_$(BITS).o
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 31e8730fa246..353a70d2fe71 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -26,6 +26,7 @@
 #include <linux/kprobes.h>
 #include <linux/uaccess.h>
 #include <linux/kdebug.h>
+#include <linux/magic.h>
 
 #include <asm/system.h>
 #include <asm/desc.h>
@@ -53,7 +54,7 @@
 
 static inline int kmmio_fault(struct pt_regs *regs, unsigned long addr)
 {
-#ifdef CONFIG_MMIOTRACE_HOOKS
+#ifdef CONFIG_MMIOTRACE
 	if (unlikely(is_kmmio_active()))
 		if (kmmio_handler(regs, addr) == 1)
 			return -1;
@@ -413,6 +414,7 @@ static noinline void pgtable_bad(unsigned long address, struct pt_regs *regs,
 				 unsigned long error_code)
 {
 	unsigned long flags = oops_begin();
+	int sig = SIGKILL;
 	struct task_struct *tsk;
 
 	printk(KERN_ALERT "%s: Corrupted page table at address %lx\n",
@@ -423,8 +425,8 @@ static noinline void pgtable_bad(unsigned long address, struct pt_regs *regs,
 	tsk->thread.trap_no = 14;
 	tsk->thread.error_code = error_code;
 	if (__die("Bad pagetable", regs, error_code))
-		regs = NULL;
-	oops_end(flags, regs, SIGKILL);
+		sig = 0;
+	oops_end(flags, regs, sig);
 }
 #endif
 
@@ -588,8 +590,11 @@ void __kprobes do_page_fault(struct pt_regs *regs, unsigned long error_code)
 	unsigned long address;
 	int write, si_code;
 	int fault;
+	unsigned long *stackend;
+
 #ifdef CONFIG_X86_64
 	unsigned long flags;
+	int sig;
 #endif
 
 	tsk = current;
@@ -840,6 +845,10 @@ no_context:
 
 	show_fault_oops(regs, error_code, address);
 
+ 	stackend = end_of_stack(tsk);
+	if (*stackend != STACK_END_MAGIC)
+		printk(KERN_ALERT "Thread overran stack, or stack corrupted\n");
+
 	tsk->thread.cr2 = address;
 	tsk->thread.trap_no = 14;
 	tsk->thread.error_code = error_code;
@@ -849,11 +858,12 @@ no_context:
 	bust_spinlocks(0);
 	do_exit(SIGKILL);
 #else
+	sig = SIGKILL;
 	if (__die("Oops", regs, error_code))
-		regs = NULL;
+		sig = 0;
 	/* Executive summary in case the body of the oops scrolled away */
 	printk(KERN_EMERG "CR2: %016lx\n", address);
-	oops_end(flags, regs, SIGKILL);
+	oops_end(flags, regs, sig);
 #endif
 
 /*
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index c483f4242079..84e8b6bfd6e3 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -102,6 +102,8 @@ static pmd_t * __init one_md_table_init(pgd_t *pgd)
 		set_pgd(pgd, __pgd(__pa(pmd_table) | _PAGE_PRESENT));
 		pud = pud_offset(pgd, 0);
 		BUG_ON(pmd_table != pmd_offset(pud, 0));
+
+		return pmd_table;
 	}
 #endif
 	pud = pud_offset(pgd, 0);
@@ -329,6 +331,8 @@ int devmem_is_allowed(unsigned long pagenr)
 {
 	if (pagenr <= 256)
 		return 1;
+	if (iomem_is_exclusive(pagenr << PAGE_SHIFT))
+		return 0;
 	if (!page_is_ram(pagenr))
 		return 1;
 	return 0;
@@ -969,8 +973,6 @@ void __init mem_init(void)
 	int codesize, reservedpages, datasize, initsize;
 	int tmp;
 
-	start_periodic_check_for_corruption();
-
 #ifdef CONFIG_FLATMEM
 	BUG_ON(!mem_map);
 #endif
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 9db01db6e3cd..c8ff49e3c5f4 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -888,6 +888,8 @@ int devmem_is_allowed(unsigned long pagenr)
 {
 	if (pagenr <= 256)
 		return 1;
+	if (iomem_is_exclusive(pagenr << PAGE_SHIFT))
+		return 0;
 	if (!page_is_ram(pagenr))
 		return 1;
 	return 0;
@@ -902,8 +904,6 @@ void __init mem_init(void)
 	long codesize, reservedpages, datasize, initsize;
 	unsigned long absent_pages;
 
-	start_periodic_check_for_corruption();
-
 	pci_iommu_alloc();
 
 	/* clear_bss() already clear the empty_zero_page */
diff --git a/arch/x86/oprofile/nmi_int.c b/arch/x86/oprofile/nmi_int.c
index 022cd41ea9b4..202864ad49a7 100644
--- a/arch/x86/oprofile/nmi_int.c
+++ b/arch/x86/oprofile/nmi_int.c
@@ -401,14 +401,13 @@ static int __init ppro_init(char **cpu_type)
 		*cpu_type = "i386/pii";
 		break;
 	case 6 ... 8:
+	case 10 ... 11:
 		*cpu_type = "i386/piii";
 		break;
 	case 9:
+	case 13:
 		*cpu_type = "i386/p6_mobile";
 		break;
-	case 10 ... 13:
-		*cpu_type = "i386/p6";
-		break;
 	case 14:
 		*cpu_type = "i386/core";
 		break;
diff --git a/arch/x86/oprofile/op_model_ppro.c b/arch/x86/oprofile/op_model_ppro.c
index 716d26f0e5d4..e9f80c744cf3 100644
--- a/arch/x86/oprofile/op_model_ppro.c
+++ b/arch/x86/oprofile/op_model_ppro.c
@@ -156,6 +156,8 @@ static void ppro_start(struct op_msrs const * const msrs)
 	unsigned int low, high;
 	int i;
 
+	if (!reset_value)
+		return;
 	for (i = 0; i < num_counters; ++i) {
 		if (reset_value[i]) {
 			CTRL_READ(low, high, msrs, i);
@@ -171,6 +173,8 @@ static void ppro_stop(struct op_msrs const * const msrs)
 	unsigned int low, high;
 	int i;
 
+	if (!reset_value)
+		return;
 	for (i = 0; i < num_counters; ++i) {
 		if (!reset_value[i])
 			continue;
diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c
index b67732bbb85a..03c9d0b6b4b7 100644
--- a/arch/x86/pci/common.c
+++ b/arch/x86/pci/common.c
@@ -23,6 +23,12 @@ unsigned int pci_probe = PCI_PROBE_BIOS | PCI_PROBE_CONF1 | PCI_PROBE_CONF2 |
 unsigned int pci_early_dump_regs;
 static int pci_bf_sort;
 int pci_routeirq;
+int noioapicquirk;
+#ifdef CONFIG_X86_REROUTE_FOR_BROKEN_BOOT_IRQS
+int noioapicreroute = 0;
+#else
+int noioapicreroute = 1;
+#endif
 int pcibios_last_bus = -1;
 unsigned long pirq_table_addr;
 struct pci_bus *pci_root_bus;
@@ -519,6 +525,17 @@ char * __devinit  pcibios_setup(char *str)
 	} else if (!strcmp(str, "skip_isa_align")) {
 		pci_probe |= PCI_CAN_SKIP_ISA_ALIGN;
 		return NULL;
+	} else if (!strcmp(str, "noioapicquirk")) {
+		noioapicquirk = 1;
+		return NULL;
+	} else if (!strcmp(str, "ioapicreroute")) {
+		if (noioapicreroute != -1)
+			noioapicreroute = 0;
+		return NULL;
+	} else if (!strcmp(str, "noioapicreroute")) {
+		if (noioapicreroute != -1)
+			noioapicreroute = 1;
+		return NULL;
 	}
 	return str;
 }
@@ -546,6 +563,14 @@ void pcibios_disable_device (struct pci_dev *dev)
 		pcibios_disable_irq(dev);
 }
 
+int pci_ext_cfg_avail(struct pci_dev *dev)
+{
+	if (raw_pci_ext_ops)
+		return 1;
+	else
+		return 0;
+}
+
 struct pci_bus * __devinit pci_scan_bus_on_node(int busno, struct pci_ops *ops, int node)
 {
 	struct pci_bus *bus = NULL;
diff --git a/arch/x86/pci/direct.c b/arch/x86/pci/direct.c
index 9915293500fb..9a5af6c8fbe9 100644
--- a/arch/x86/pci/direct.c
+++ b/arch/x86/pci/direct.c
@@ -173,7 +173,7 @@ static int pci_conf2_write(unsigned int seg, unsigned int bus,
 
 #undef PCI_CONF2_ADDRESS
 
-static struct pci_raw_ops pci_direct_conf2 = {
+struct pci_raw_ops pci_direct_conf2 = {
 	.read =		pci_conf2_read,
 	.write =	pci_conf2_write,
 };
@@ -289,6 +289,7 @@ int __init pci_direct_probe(void)
 
 	if (pci_check_type1()) {
 		raw_pci_ops = &pci_direct_conf1;
+		port_cf9_safe = true;
 		return 1;
 	}
 	release_resource(region);
@@ -305,6 +306,7 @@ int __init pci_direct_probe(void)
 
 	if (pci_check_type2()) {
 		raw_pci_ops = &pci_direct_conf2;
+		port_cf9_safe = true;
 		return 2;
 	}
 
diff --git a/arch/x86/pci/pci.h b/arch/x86/pci/pci.h
index 15b9cf6be729..1959018aac02 100644
--- a/arch/x86/pci/pci.h
+++ b/arch/x86/pci/pci.h
@@ -96,6 +96,7 @@ extern struct pci_raw_ops *raw_pci_ops;
 extern struct pci_raw_ops *raw_pci_ext_ops;
 
 extern struct pci_raw_ops pci_direct_conf1;
+extern bool port_cf9_safe;
 
 /* arch_initcall level */
 extern int pci_direct_probe(void);
diff --git a/arch/x86/vdso/vclock_gettime.c b/arch/x86/vdso/vclock_gettime.c
index 1ef0f90813d6..d9d35824c56f 100644
--- a/arch/x86/vdso/vclock_gettime.c
+++ b/arch/x86/vdso/vclock_gettime.c
@@ -9,6 +9,9 @@
  * Also alternative() doesn't work.
  */
 
+/* Disable profiling for userspace code: */
+#define DISABLE_BRANCH_PROFILING
+
 #include <linux/kernel.h>
 #include <linux/posix-timers.h>
 #include <linux/time.h>
diff --git a/arch/x86/vdso/vdso32-setup.c b/arch/x86/vdso/vdso32-setup.c
index 513f330c5832..1241f118ab56 100644
--- a/arch/x86/vdso/vdso32-setup.c
+++ b/arch/x86/vdso/vdso32-setup.c
@@ -310,7 +310,7 @@ int __init sysenter_setup(void)
 }
 
 /* Setup a VMA at program startup for the vsyscall page */
-int arch_setup_additional_pages(struct linux_binprm *bprm, int exstack)
+int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
 {
 	struct mm_struct *mm = current->mm;
 	unsigned long addr;
diff --git a/arch/x86/vdso/vma.c b/arch/x86/vdso/vma.c
index 257ba4a10abf..9c98cc6ba978 100644
--- a/arch/x86/vdso/vma.c
+++ b/arch/x86/vdso/vma.c
@@ -98,7 +98,7 @@ static unsigned long vdso_addr(unsigned long start, unsigned len)
 
 /* Setup a VMA at program startup for the vsyscall page.
    Not called for compat tasks */
-int arch_setup_additional_pages(struct linux_binprm *bprm, int exstack)
+int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
 {
 	struct mm_struct *mm = current->mm;
 	unsigned long addr;
diff --git a/arch/xtensa/Makefile b/arch/xtensa/Makefile
index 015b6b2a26b9..1da55fe4beff 100644
--- a/arch/xtensa/Makefile
+++ b/arch/xtensa/Makefile
@@ -33,6 +33,15 @@ KBUILD_CFLAGS += -ffreestanding
 
 KBUILD_CFLAGS += -pipe -mlongcalls
 
+vardirs := $(patsubst %,arch/xtensa/variants/%/,$(variant-y))
+plfdirs := $(patsubst %,arch/xtensa/platforms/%/,$(platform-y))
+
+ifeq ($(KBUILD_SRC),)
+KBUILD_CPPFLAGS += $(patsubst %,-I%include,$(vardirs) $(plfdirs))
+else
+KBUILD_CPPFLAGS += $(patsubst %,-I$(srctree)/%include,$(vardirs) $(plfdirs))
+endif
+
 KBUILD_DEFCONFIG := iss_defconfig
 
 # ramdisk/initrd support
@@ -66,21 +75,6 @@ libs-y		+= arch/xtensa/lib/ $(LIBGCC)
 
 boot		:= arch/xtensa/boot
 
-archinc		:= include/asm-xtensa
-
-archprepare: $(archinc)/.platform
-
-# Update processor variant and platform symlinks if something which affects
-# them changed.
-
-$(archinc)/.platform: $(wildcard include/config/arch/*.h) include/config/auto.conf
-	@echo '  SYMLINK $(archinc)/variant -> $(archinc)/variant-$(VARIANT)'
-	$(Q)mkdir -p $(archinc)
-	$(Q)ln -fsn $(srctree)/$(archinc)/variant-$(VARIANT) $(archinc)/variant
-	@echo '  SYMLINK $(archinc)/platform -> $(archinc)/platform-$(PLATFORM)'
-	$(Q)ln -fsn $(srctree)/$(archinc)/platform-$(PLATFORM) $(archinc)/platform
-	@touch $@
-
 
 all: zImage
 
@@ -89,10 +83,6 @@ bzImage : zImage
 zImage zImage.initrd: vmlinux
 	$(Q)$(MAKE) $(build)=$(boot) $@
 
-CLEAN_FILES	+= arch/xtensa/vmlinux.lds                      \
-		   $(archinc)/platform $(archinc)/variant	\
-		   $(archinc)/.platform
-
 define archhelp
   @echo '* zImage      - Compressed kernel image (arch/xtensa/boot/images/zImage.*)'
 endef
diff --git a/arch/xtensa/boot/boot-elf/boot.lds.S b/arch/xtensa/boot/boot-elf/boot.lds.S
index 849dfcafd518..4e53b74dc44b 100644
--- a/arch/xtensa/boot/boot-elf/boot.lds.S
+++ b/arch/xtensa/boot/boot-elf/boot.lds.S
@@ -1,4 +1,4 @@
-#include <asm/variant/core.h>
+#include <variant/core.h>
 OUTPUT_ARCH(xtensa)
 ENTRY(_ResetVector)
 
diff --git a/arch/xtensa/boot/boot-redboot/bootstrap.S b/arch/xtensa/boot/boot-redboot/bootstrap.S
index 84848123e2a8..5582e8cfac8f 100644
--- a/arch/xtensa/boot/boot-redboot/bootstrap.S
+++ b/arch/xtensa/boot/boot-redboot/bootstrap.S
@@ -1,4 +1,4 @@
-#include <asm/variant/core.h>
+#include <variant/core.h>
 #include <asm/regs.h>
 #include <asm/asmmacro.h>
 #include <asm/cacheasm.h>
diff --git a/include/asm-xtensa/Kbuild b/arch/xtensa/include/asm/Kbuild
index c68e1680da01..c68e1680da01 100644
--- a/include/asm-xtensa/Kbuild
+++ b/arch/xtensa/include/asm/Kbuild
diff --git a/include/asm-xtensa/asmmacro.h b/arch/xtensa/include/asm/asmmacro.h
index 76915cabad17..755320f6e0bc 100644
--- a/include/asm-xtensa/asmmacro.h
+++ b/arch/xtensa/include/asm/asmmacro.h
@@ -11,7 +11,7 @@
 #ifndef _XTENSA_ASMMACRO_H
 #define _XTENSA_ASMMACRO_H
 
-#include <asm/variant/core.h>
+#include <variant/core.h>
 
 /*
  * Some little helpers for loops. Use zero-overhead-loops
diff --git a/include/asm-xtensa/atomic.h b/arch/xtensa/include/asm/atomic.h
index b3b23540f14d..b3b23540f14d 100644
--- a/include/asm-xtensa/atomic.h
+++ b/arch/xtensa/include/asm/atomic.h
diff --git a/include/asm-xtensa/auxvec.h b/arch/xtensa/include/asm/auxvec.h
index 257dec75c5af..257dec75c5af 100644
--- a/include/asm-xtensa/auxvec.h
+++ b/arch/xtensa/include/asm/auxvec.h
diff --git a/include/asm-xtensa/bitops.h b/arch/xtensa/include/asm/bitops.h
index 23261e8f2e5a..23261e8f2e5a 100644
--- a/include/asm-xtensa/bitops.h
+++ b/arch/xtensa/include/asm/bitops.h
diff --git a/include/asm-xtensa/bootparam.h b/arch/xtensa/include/asm/bootparam.h
index 9983f2c1b7ee..9983f2c1b7ee 100644
--- a/include/asm-xtensa/bootparam.h
+++ b/arch/xtensa/include/asm/bootparam.h
diff --git a/include/asm-xtensa/bug.h b/arch/xtensa/include/asm/bug.h
index 3e52d72712f1..3e52d72712f1 100644
--- a/include/asm-xtensa/bug.h
+++ b/arch/xtensa/include/asm/bug.h
diff --git a/include/asm-xtensa/bugs.h b/arch/xtensa/include/asm/bugs.h
index 69b29d198249..69b29d198249 100644
--- a/include/asm-xtensa/bugs.h
+++ b/arch/xtensa/include/asm/bugs.h
diff --git a/include/asm-xtensa/byteorder.h b/arch/xtensa/include/asm/byteorder.h
index 765edf17a9a4..07d10ad364d1 100644
--- a/include/asm-xtensa/byteorder.h
+++ b/arch/xtensa/include/asm/byteorder.h
@@ -14,7 +14,17 @@
 #include <asm/types.h>
 #include <linux/compiler.h>
 
-static __inline__ __attribute_const__ __u32 ___arch__swab32(__u32 x)
+#ifdef __XTENSA_EL__
+# define __LITTLE_ENDIAN
+#elif defined(__XTENSA_EB__)
+# define __BIG_ENDIAN
+#else
+# error processor byte order undefined!
+#endif
+
+#define __SWAB_64_THRU_32__
+
+static inline __attribute_const__ __u32 __arch_swab32(__u32 x)
 {
     __u32 res;
     /* instruction sequence from Xtensa ISA release 2/2000 */
@@ -28,8 +38,9 @@ static __inline__ __attribute_const__ __u32 ___arch__swab32(__u32 x)
 	    );
     return res;
 }
+#define __arch_swab32 __arch_swab32
 
-static __inline__ __attribute_const__ __u16 ___arch__swab16(__u16 x)
+static inline __attribute_const__ __u16 __arch_swab16(__u16 x)
 {
     /* Given that 'short' values are signed (i.e., can be negative),
      * we cannot assume that the upper 16-bits of the register are
@@ -62,21 +73,8 @@ static __inline__ __attribute_const__ __u16 ___arch__swab16(__u16 x)
 
     return res;
 }
+#define __arch_swab16 __arch_swab16
 
-#define __arch__swab32(x) ___arch__swab32(x)
-#define __arch__swab16(x) ___arch__swab16(x)
-
-#if !defined(__STRICT_ANSI__) || defined(__KERNEL__)
-#  define __BYTEORDER_HAS_U64__
-#  define __SWAB_64_THRU_32__
-#endif
-
-#ifdef __XTENSA_EL__
-# include <linux/byteorder/little_endian.h>
-#elif defined(__XTENSA_EB__)
-# include <linux/byteorder/big_endian.h>
-#else
-# error processor byte order undefined!
-#endif
+#include <linux/byteorder.h>
 
 #endif /* _XTENSA_BYTEORDER_H */
diff --git a/include/asm-xtensa/cache.h b/arch/xtensa/include/asm/cache.h
index 3bba2a540cf0..f04c9891142f 100644
--- a/include/asm-xtensa/cache.h
+++ b/arch/xtensa/include/asm/cache.h
@@ -11,7 +11,7 @@
 #ifndef _XTENSA_CACHE_H
 #define _XTENSA_CACHE_H
 
-#include <asm/variant/core.h>
+#include <variant/core.h>
 
 #define L1_CACHE_SHIFT	XCHAL_DCACHE_LINEWIDTH
 #define L1_CACHE_BYTES	XCHAL_DCACHE_LINESIZE
diff --git a/include/asm-xtensa/cacheasm.h b/arch/xtensa/include/asm/cacheasm.h
index 2c20a58f94cd..2c20a58f94cd 100644
--- a/include/asm-xtensa/cacheasm.h
+++ b/arch/xtensa/include/asm/cacheasm.h
diff --git a/include/asm-xtensa/cacheflush.h b/arch/xtensa/include/asm/cacheflush.h
index 94c4c53a099e..94c4c53a099e 100644
--- a/include/asm-xtensa/cacheflush.h
+++ b/arch/xtensa/include/asm/cacheflush.h
diff --git a/include/asm-xtensa/checksum.h b/arch/xtensa/include/asm/checksum.h
index 23534c60b3a4..f84d3f00774a 100644
--- a/include/asm-xtensa/checksum.h
+++ b/arch/xtensa/include/asm/checksum.h
@@ -12,7 +12,7 @@
 #define _XTENSA_CHECKSUM_H
 
 #include <linux/in6.h>
-#include <asm/variant/core.h>
+#include <variant/core.h>
 
 /*
  * computes the checksum of a memory block at buff, length len,
diff --git a/include/asm-xtensa/coprocessor.h b/arch/xtensa/include/asm/coprocessor.h
index 1cbcf9001a41..65a285d8d3fb 100644
--- a/include/asm-xtensa/coprocessor.h
+++ b/arch/xtensa/include/asm/coprocessor.h
@@ -13,11 +13,11 @@
 #define _XTENSA_COPROCESSOR_H
 
 #include <linux/stringify.h>
-#include <asm/variant/tie.h>
+#include <variant/tie.h>
 #include <asm/types.h>
 
 #ifdef __ASSEMBLY__
-# include <asm/variant/tie-asm.h>
+# include <variant/tie-asm.h>
 
 .macro	xchal_sa_start  a b
 	.set .Lxchal_pofs_, 0
diff --git a/include/asm-xtensa/cpumask.h b/arch/xtensa/include/asm/cpumask.h
index ebeede397db3..ebeede397db3 100644
--- a/include/asm-xtensa/cpumask.h
+++ b/arch/xtensa/include/asm/cpumask.h
diff --git a/include/asm-xtensa/cputime.h b/arch/xtensa/include/asm/cputime.h
index a7fb864a50ae..a7fb864a50ae 100644
--- a/include/asm-xtensa/cputime.h
+++ b/arch/xtensa/include/asm/cputime.h
diff --git a/include/asm-xtensa/current.h b/arch/xtensa/include/asm/current.h
index 8d1eb5d78649..8d1eb5d78649 100644
--- a/include/asm-xtensa/current.h
+++ b/arch/xtensa/include/asm/current.h
diff --git a/include/asm-xtensa/delay.h b/arch/xtensa/include/asm/delay.h
index e1d8c9e010c1..e1d8c9e010c1 100644
--- a/include/asm-xtensa/delay.h
+++ b/arch/xtensa/include/asm/delay.h
diff --git a/include/asm-xtensa/device.h b/arch/xtensa/include/asm/device.h
index d8f9872b0e2d..d8f9872b0e2d 100644
--- a/include/asm-xtensa/device.h
+++ b/arch/xtensa/include/asm/device.h
diff --git a/include/asm-xtensa/div64.h b/arch/xtensa/include/asm/div64.h
index f35678cb0a9b..f35678cb0a9b 100644
--- a/include/asm-xtensa/div64.h
+++ b/arch/xtensa/include/asm/div64.h
diff --git a/include/asm-xtensa/dma-mapping.h b/arch/xtensa/include/asm/dma-mapping.h
index 51882ae3db4d..51882ae3db4d 100644
--- a/include/asm-xtensa/dma-mapping.h
+++ b/arch/xtensa/include/asm/dma-mapping.h
diff --git a/include/asm-xtensa/dma.h b/arch/xtensa/include/asm/dma.h
index e30f3abf48f0..e30f3abf48f0 100644
--- a/include/asm-xtensa/dma.h
+++ b/arch/xtensa/include/asm/dma.h
diff --git a/include/asm-xtensa/elf.h b/arch/xtensa/include/asm/elf.h
index c3f53e755ca5..c3f53e755ca5 100644
--- a/include/asm-xtensa/elf.h
+++ b/arch/xtensa/include/asm/elf.h
diff --git a/include/asm-xtensa/emergency-restart.h b/arch/xtensa/include/asm/emergency-restart.h
index 108d8c48e42e..108d8c48e42e 100644
--- a/include/asm-xtensa/emergency-restart.h
+++ b/arch/xtensa/include/asm/emergency-restart.h
diff --git a/include/asm-xtensa/errno.h b/arch/xtensa/include/asm/errno.h
index a0f3b96b79b4..a0f3b96b79b4 100644
--- a/include/asm-xtensa/errno.h
+++ b/arch/xtensa/include/asm/errno.h
diff --git a/include/asm-xtensa/fb.h b/arch/xtensa/include/asm/fb.h
index c7df38030992..c7df38030992 100644
--- a/include/asm-xtensa/fb.h
+++ b/arch/xtensa/include/asm/fb.h
diff --git a/include/asm-xtensa/fcntl.h b/arch/xtensa/include/asm/fcntl.h
index 46ab12db5739..46ab12db5739 100644
--- a/include/asm-xtensa/fcntl.h
+++ b/arch/xtensa/include/asm/fcntl.h
diff --git a/include/asm-xtensa/futex.h b/arch/xtensa/include/asm/futex.h
index 0b745828f42b..0b745828f42b 100644
--- a/include/asm-xtensa/futex.h
+++ b/arch/xtensa/include/asm/futex.h
diff --git a/include/asm-xtensa/hardirq.h b/arch/xtensa/include/asm/hardirq.h
index 87cb19d1b10c..87cb19d1b10c 100644
--- a/include/asm-xtensa/hardirq.h
+++ b/arch/xtensa/include/asm/hardirq.h
diff --git a/include/asm-xtensa/highmem.h b/arch/xtensa/include/asm/highmem.h
index 0a046ca5a687..0a046ca5a687 100644
--- a/include/asm-xtensa/highmem.h
+++ b/arch/xtensa/include/asm/highmem.h
diff --git a/include/asm-xtensa/hw_irq.h b/arch/xtensa/include/asm/hw_irq.h
index 3ddbea759b2b..3ddbea759b2b 100644
--- a/include/asm-xtensa/hw_irq.h
+++ b/arch/xtensa/include/asm/hw_irq.h
diff --git a/include/asm-xtensa/io.h b/arch/xtensa/include/asm/io.h
index 07b7299dab20..07b7299dab20 100644
--- a/include/asm-xtensa/io.h
+++ b/arch/xtensa/include/asm/io.h
diff --git a/include/asm-xtensa/ioctl.h b/arch/xtensa/include/asm/ioctl.h
index b279fe06dfe5..b279fe06dfe5 100644
--- a/include/asm-xtensa/ioctl.h
+++ b/arch/xtensa/include/asm/ioctl.h
diff --git a/include/asm-xtensa/ioctls.h b/arch/xtensa/include/asm/ioctls.h
index 0ffa942954b9..0ffa942954b9 100644
--- a/include/asm-xtensa/ioctls.h
+++ b/arch/xtensa/include/asm/ioctls.h
diff --git a/include/asm-xtensa/ipcbuf.h b/arch/xtensa/include/asm/ipcbuf.h
index c33aa6a42145..c33aa6a42145 100644
--- a/include/asm-xtensa/ipcbuf.h
+++ b/arch/xtensa/include/asm/ipcbuf.h
diff --git a/include/asm-xtensa/irq.h b/arch/xtensa/include/asm/irq.h
index fc73b7f11aff..1620d1e0e695 100644
--- a/include/asm-xtensa/irq.h
+++ b/arch/xtensa/include/asm/irq.h
@@ -11,8 +11,8 @@
 #ifndef _XTENSA_IRQ_H
 #define _XTENSA_IRQ_H
 
-#include <asm/platform/hardware.h>
-#include <asm/variant/core.h>
+#include <platform/hardware.h>
+#include <variant/core.h>
 
 #ifndef PLATFORM_NR_IRQS
 # define PLATFORM_NR_IRQS 0
diff --git a/include/asm-xtensa/irq_regs.h b/arch/xtensa/include/asm/irq_regs.h
index 3dd9c0b70270..3dd9c0b70270 100644
--- a/include/asm-xtensa/irq_regs.h
+++ b/arch/xtensa/include/asm/irq_regs.h
diff --git a/include/asm-xtensa/kdebug.h b/arch/xtensa/include/asm/kdebug.h
index 6ece1b037665..6ece1b037665 100644
--- a/include/asm-xtensa/kdebug.h
+++ b/arch/xtensa/include/asm/kdebug.h
diff --git a/include/asm-xtensa/kmap_types.h b/arch/xtensa/include/asm/kmap_types.h
index 9e822d2e3bce..9e822d2e3bce 100644
--- a/include/asm-xtensa/kmap_types.h
+++ b/arch/xtensa/include/asm/kmap_types.h
diff --git a/include/asm-xtensa/linkage.h b/arch/xtensa/include/asm/linkage.h
index bf2128a99d79..bf2128a99d79 100644
--- a/include/asm-xtensa/linkage.h
+++ b/arch/xtensa/include/asm/linkage.h
diff --git a/include/asm-xtensa/local.h b/arch/xtensa/include/asm/local.h
index 48723e550d14..48723e550d14 100644
--- a/include/asm-xtensa/local.h
+++ b/arch/xtensa/include/asm/local.h
diff --git a/include/asm-xtensa/mman.h b/arch/xtensa/include/asm/mman.h
index 9b92620c8a1e..9b92620c8a1e 100644
--- a/include/asm-xtensa/mman.h
+++ b/arch/xtensa/include/asm/mman.h
diff --git a/include/asm-xtensa/mmu.h b/arch/xtensa/include/asm/mmu.h
index 44c5bb04c55c..44c5bb04c55c 100644
--- a/include/asm-xtensa/mmu.h
+++ b/arch/xtensa/include/asm/mmu.h
diff --git a/include/asm-xtensa/mmu_context.h b/arch/xtensa/include/asm/mmu_context.h
index c0fd8e5b4513..c0fd8e5b4513 100644
--- a/include/asm-xtensa/mmu_context.h
+++ b/arch/xtensa/include/asm/mmu_context.h
diff --git a/include/asm-xtensa/module.h b/arch/xtensa/include/asm/module.h
index d9b34bee4d42..d9b34bee4d42 100644
--- a/include/asm-xtensa/module.h
+++ b/arch/xtensa/include/asm/module.h
diff --git a/include/asm-xtensa/msgbuf.h b/arch/xtensa/include/asm/msgbuf.h
index 693c96755280..693c96755280 100644
--- a/include/asm-xtensa/msgbuf.h
+++ b/arch/xtensa/include/asm/msgbuf.h
diff --git a/include/asm-xtensa/mutex.h b/arch/xtensa/include/asm/mutex.h
index 458c1f7fbc18..458c1f7fbc18 100644
--- a/include/asm-xtensa/mutex.h
+++ b/arch/xtensa/include/asm/mutex.h
diff --git a/include/asm-xtensa/page.h b/arch/xtensa/include/asm/page.h
index 11f7dc2dbec7..11f7dc2dbec7 100644
--- a/include/asm-xtensa/page.h
+++ b/arch/xtensa/include/asm/page.h
diff --git a/include/asm-xtensa/param.h b/arch/xtensa/include/asm/param.h
index ba03d5aeab6b..ba03d5aeab6b 100644
--- a/include/asm-xtensa/param.h
+++ b/arch/xtensa/include/asm/param.h
diff --git a/include/asm-xtensa/pci-bridge.h b/arch/xtensa/include/asm/pci-bridge.h
index 00fcbd7c534a..00fcbd7c534a 100644
--- a/include/asm-xtensa/pci-bridge.h
+++ b/arch/xtensa/include/asm/pci-bridge.h
diff --git a/include/asm-xtensa/pci.h b/arch/xtensa/include/asm/pci.h
index 66410acf18b4..66410acf18b4 100644
--- a/include/asm-xtensa/pci.h
+++ b/arch/xtensa/include/asm/pci.h
diff --git a/include/asm-xtensa/percpu.h b/arch/xtensa/include/asm/percpu.h
index 6d2bc2ada9d1..6d2bc2ada9d1 100644
--- a/include/asm-xtensa/percpu.h
+++ b/arch/xtensa/include/asm/percpu.h
diff --git a/include/asm-xtensa/pgalloc.h b/arch/xtensa/include/asm/pgalloc.h
index 4f4a7987eded..4f4a7987eded 100644
--- a/include/asm-xtensa/pgalloc.h
+++ b/arch/xtensa/include/asm/pgalloc.h
diff --git a/include/asm-xtensa/pgtable.h b/arch/xtensa/include/asm/pgtable.h
index 8014d96b21f1..8014d96b21f1 100644
--- a/include/asm-xtensa/pgtable.h
+++ b/arch/xtensa/include/asm/pgtable.h
diff --git a/include/asm-xtensa/platform.h b/arch/xtensa/include/asm/platform.h
index 48135a9718b0..e3d5a48ad495 100644
--- a/include/asm-xtensa/platform.h
+++ b/arch/xtensa/include/asm/platform.h
@@ -1,6 +1,4 @@
 /*
- * include/asm-xtensa/platform.h
- *
  * Platform specific functions
  *
  * This file is subject to the terms and conditions of the GNU General
diff --git a/include/asm-xtensa/poll.h b/arch/xtensa/include/asm/poll.h
index 9d2d5993f068..9d2d5993f068 100644
--- a/include/asm-xtensa/poll.h
+++ b/arch/xtensa/include/asm/poll.h
diff --git a/include/asm-xtensa/posix_types.h b/arch/xtensa/include/asm/posix_types.h
index 43f9dd1126a4..43f9dd1126a4 100644
--- a/include/asm-xtensa/posix_types.h
+++ b/arch/xtensa/include/asm/posix_types.h
diff --git a/include/asm-xtensa/processor.h b/arch/xtensa/include/asm/processor.h
index 4918a4e96d42..07387d3b99f4 100644
--- a/include/asm-xtensa/processor.h
+++ b/arch/xtensa/include/asm/processor.h
@@ -11,7 +11,7 @@
 #ifndef _XTENSA_PROCESSOR_H
 #define _XTENSA_PROCESSOR_H
 
-#include <asm/variant/core.h>
+#include <variant/core.h>
 #include <asm/coprocessor.h>
 
 #include <linux/compiler.h>
diff --git a/include/asm-xtensa/ptrace.h b/arch/xtensa/include/asm/ptrace.h
index 089b0db44816..905e1e619654 100644
--- a/include/asm-xtensa/ptrace.h
+++ b/arch/xtensa/include/asm/ptrace.h
@@ -111,7 +111,7 @@ struct pt_regs {
 	unsigned long areg[16];		/* 128 (64) */
 };
 
-#include <asm/variant/core.h>
+#include <variant/core.h>
 
 # define task_pt_regs(tsk) ((struct pt_regs*) \
   (task_stack_page(tsk) + KERNEL_STACK_SIZE - (XCHAL_NUM_AREGS-16)*4) - 1)
diff --git a/include/asm-xtensa/regs.h b/arch/xtensa/include/asm/regs.h
index d4baed246928..d4baed246928 100644
--- a/include/asm-xtensa/regs.h
+++ b/arch/xtensa/include/asm/regs.h
diff --git a/include/asm-xtensa/resource.h b/arch/xtensa/include/asm/resource.h
index 17b5ab311771..17b5ab311771 100644
--- a/include/asm-xtensa/resource.h
+++ b/arch/xtensa/include/asm/resource.h
diff --git a/include/asm-xtensa/rmap.h b/arch/xtensa/include/asm/rmap.h
index 649588b7e9ad..649588b7e9ad 100644
--- a/include/asm-xtensa/rmap.h
+++ b/arch/xtensa/include/asm/rmap.h
diff --git a/include/asm-xtensa/rwsem.h b/arch/xtensa/include/asm/rwsem.h
index e39edf5c86f2..e39edf5c86f2 100644
--- a/include/asm-xtensa/rwsem.h
+++ b/arch/xtensa/include/asm/rwsem.h
diff --git a/include/asm-xtensa/scatterlist.h b/arch/xtensa/include/asm/scatterlist.h
index 810080bb0a2b..810080bb0a2b 100644
--- a/include/asm-xtensa/scatterlist.h
+++ b/arch/xtensa/include/asm/scatterlist.h
diff --git a/include/asm-xtensa/sections.h b/arch/xtensa/include/asm/sections.h
index 40b5191b55a2..40b5191b55a2 100644
--- a/include/asm-xtensa/sections.h
+++ b/arch/xtensa/include/asm/sections.h
diff --git a/include/asm-xtensa/segment.h b/arch/xtensa/include/asm/segment.h
index a2eb547a1a75..a2eb547a1a75 100644
--- a/include/asm-xtensa/segment.h
+++ b/arch/xtensa/include/asm/segment.h
diff --git a/include/asm-xtensa/sembuf.h b/arch/xtensa/include/asm/sembuf.h
index c15870493b33..c15870493b33 100644
--- a/include/asm-xtensa/sembuf.h
+++ b/arch/xtensa/include/asm/sembuf.h
diff --git a/include/asm-xtensa/serial.h b/arch/xtensa/include/asm/serial.h
index ec04114fcf0b..a8a2493260f6 100644
--- a/include/asm-xtensa/serial.h
+++ b/arch/xtensa/include/asm/serial.h
@@ -13,6 +13,6 @@
 #ifndef _XTENSA_SERIAL_H
 #define _XTENSA_SERIAL_H
 
-#include <asm/platform/serial.h>
+#include <platform/serial.h>
 
 #endif	/* _XTENSA_SERIAL_H */
diff --git a/include/asm-xtensa/setup.h b/arch/xtensa/include/asm/setup.h
index e3636520d8cc..e3636520d8cc 100644
--- a/include/asm-xtensa/setup.h
+++ b/arch/xtensa/include/asm/setup.h
diff --git a/include/asm-xtensa/shmbuf.h b/arch/xtensa/include/asm/shmbuf.h
index ad4b0121782c..ad4b0121782c 100644
--- a/include/asm-xtensa/shmbuf.h
+++ b/arch/xtensa/include/asm/shmbuf.h
diff --git a/include/asm-xtensa/shmparam.h b/arch/xtensa/include/asm/shmparam.h
index c8cc16c3da9e..c8cc16c3da9e 100644
--- a/include/asm-xtensa/shmparam.h
+++ b/arch/xtensa/include/asm/shmparam.h
diff --git a/include/asm-xtensa/sigcontext.h b/arch/xtensa/include/asm/sigcontext.h
index 03383af8c3b7..03383af8c3b7 100644
--- a/include/asm-xtensa/sigcontext.h
+++ b/arch/xtensa/include/asm/sigcontext.h
diff --git a/include/asm-xtensa/siginfo.h b/arch/xtensa/include/asm/siginfo.h
index 6916248295df..6916248295df 100644
--- a/include/asm-xtensa/siginfo.h
+++ b/arch/xtensa/include/asm/siginfo.h
diff --git a/include/asm-xtensa/signal.h b/arch/xtensa/include/asm/signal.h
index 633ba73bc4d2..633ba73bc4d2 100644
--- a/include/asm-xtensa/signal.h
+++ b/arch/xtensa/include/asm/signal.h
diff --git a/include/asm-xtensa/smp.h b/arch/xtensa/include/asm/smp.h
index 83c569e3bdbd..83c569e3bdbd 100644
--- a/include/asm-xtensa/smp.h
+++ b/arch/xtensa/include/asm/smp.h
diff --git a/include/asm-xtensa/socket.h b/arch/xtensa/include/asm/socket.h
index 6100682b1da2..6100682b1da2 100644
--- a/include/asm-xtensa/socket.h
+++ b/arch/xtensa/include/asm/socket.h
diff --git a/include/asm-xtensa/sockios.h b/arch/xtensa/include/asm/sockios.h
index efe0af379f01..efe0af379f01 100644
--- a/include/asm-xtensa/sockios.h
+++ b/arch/xtensa/include/asm/sockios.h
diff --git a/include/asm-xtensa/spinlock.h b/arch/xtensa/include/asm/spinlock.h
index 8ff23649581b..8ff23649581b 100644
--- a/include/asm-xtensa/spinlock.h
+++ b/arch/xtensa/include/asm/spinlock.h
diff --git a/include/asm-xtensa/stat.h b/arch/xtensa/include/asm/stat.h
index c4992038cee0..c4992038cee0 100644
--- a/include/asm-xtensa/stat.h
+++ b/arch/xtensa/include/asm/stat.h
diff --git a/include/asm-xtensa/statfs.h b/arch/xtensa/include/asm/statfs.h
index 9c3d1a213136..9c3d1a213136 100644
--- a/include/asm-xtensa/statfs.h
+++ b/arch/xtensa/include/asm/statfs.h
diff --git a/include/asm-xtensa/string.h b/arch/xtensa/include/asm/string.h
index 5fb8c27cbef5..5fb8c27cbef5 100644
--- a/include/asm-xtensa/string.h
+++ b/arch/xtensa/include/asm/string.h
diff --git a/include/asm-xtensa/syscall.h b/arch/xtensa/include/asm/syscall.h
index 05cebf8f62b1..05cebf8f62b1 100644
--- a/include/asm-xtensa/syscall.h
+++ b/arch/xtensa/include/asm/syscall.h
diff --git a/include/asm-xtensa/system.h b/arch/xtensa/include/asm/system.h
index 62b1e8f3c13c..62b1e8f3c13c 100644
--- a/include/asm-xtensa/system.h
+++ b/arch/xtensa/include/asm/system.h
diff --git a/include/asm-xtensa/termbits.h b/arch/xtensa/include/asm/termbits.h
index 85aa6a3c0b6e..85aa6a3c0b6e 100644
--- a/include/asm-xtensa/termbits.h
+++ b/arch/xtensa/include/asm/termbits.h
diff --git a/include/asm-xtensa/termios.h b/arch/xtensa/include/asm/termios.h
index 4673f42f88a7..4673f42f88a7 100644
--- a/include/asm-xtensa/termios.h
+++ b/arch/xtensa/include/asm/termios.h
diff --git a/include/asm-xtensa/thread_info.h b/arch/xtensa/include/asm/thread_info.h
index 0f4fe1faf9ba..0f4fe1faf9ba 100644
--- a/include/asm-xtensa/thread_info.h
+++ b/arch/xtensa/include/asm/thread_info.h
diff --git a/include/asm-xtensa/timex.h b/arch/xtensa/include/asm/timex.h
index b83a8181d448..b83a8181d448 100644
--- a/include/asm-xtensa/timex.h
+++ b/arch/xtensa/include/asm/timex.h
diff --git a/include/asm-xtensa/tlb.h b/arch/xtensa/include/asm/tlb.h
index 31c220faca02..31c220faca02 100644
--- a/include/asm-xtensa/tlb.h
+++ b/arch/xtensa/include/asm/tlb.h
diff --git a/include/asm-xtensa/tlbflush.h b/arch/xtensa/include/asm/tlbflush.h
index 46d240074f74..46d240074f74 100644
--- a/include/asm-xtensa/tlbflush.h
+++ b/arch/xtensa/include/asm/tlbflush.h
diff --git a/include/asm-xtensa/topology.h b/arch/xtensa/include/asm/topology.h
index 7309e38a0ccb..7309e38a0ccb 100644
--- a/include/asm-xtensa/topology.h
+++ b/arch/xtensa/include/asm/topology.h
diff --git a/include/asm-xtensa/types.h b/arch/xtensa/include/asm/types.h
index c89569a8da0c..c89569a8da0c 100644
--- a/include/asm-xtensa/types.h
+++ b/arch/xtensa/include/asm/types.h
diff --git a/include/asm-xtensa/uaccess.h b/arch/xtensa/include/asm/uaccess.h
index b8528426ab1f..b8528426ab1f 100644
--- a/include/asm-xtensa/uaccess.h
+++ b/arch/xtensa/include/asm/uaccess.h
diff --git a/include/asm-xtensa/ucontext.h b/arch/xtensa/include/asm/ucontext.h
index 94c94ed3e00a..94c94ed3e00a 100644
--- a/include/asm-xtensa/ucontext.h
+++ b/arch/xtensa/include/asm/ucontext.h
diff --git a/include/asm-xtensa/unaligned.h b/arch/xtensa/include/asm/unaligned.h
index 8f3424fc5d18..8e7ed046bfed 100644
--- a/include/asm-xtensa/unaligned.h
+++ b/arch/xtensa/include/asm/unaligned.h
@@ -10,20 +10,20 @@
 #ifndef _ASM_XTENSA_UNALIGNED_H
 #define _ASM_XTENSA_UNALIGNED_H
 
-#ifdef __XTENSA_EL__
-# include <linux/unaligned/le_memmove.h>
+#include <asm/byteorder.h>
+
+#ifdef __LITTLE_ENDIAN
+# include <linux/unaligned/le_struct.h>
 # include <linux/unaligned/be_byteshift.h>
 # include <linux/unaligned/generic.h>
 # define get_unaligned	__get_unaligned_le
 # define put_unaligned	__put_unaligned_le
-#elif defined(__XTENSA_EB__)
-# include <linux/unaligned/be_memmove.h>
+#else
+# include <linux/unaligned/be_struct.h>
 # include <linux/unaligned/le_byteshift.h>
 # include <linux/unaligned/generic.h>
 # define get_unaligned	__get_unaligned_be
 # define put_unaligned	__put_unaligned_be
-#else
-# error processor byte order undefined!
 #endif
 
 #endif	/* _ASM_XTENSA_UNALIGNED_H */
diff --git a/include/asm-xtensa/unistd.h b/arch/xtensa/include/asm/unistd.h
index c092c8fbb2cf..c092c8fbb2cf 100644
--- a/include/asm-xtensa/unistd.h
+++ b/arch/xtensa/include/asm/unistd.h
diff --git a/include/asm-xtensa/user.h b/arch/xtensa/include/asm/user.h
index 2c3ed23354a8..2c3ed23354a8 100644
--- a/include/asm-xtensa/user.h
+++ b/arch/xtensa/include/asm/user.h
diff --git a/include/asm-xtensa/vga.h b/arch/xtensa/include/asm/vga.h
index 1fd8cab3a297..1fd8cab3a297 100644
--- a/include/asm-xtensa/vga.h
+++ b/arch/xtensa/include/asm/vga.h
diff --git a/include/asm-xtensa/xor.h b/arch/xtensa/include/asm/xor.h
index e7b1f083991d..e7b1f083991d 100644
--- a/include/asm-xtensa/xor.h
+++ b/arch/xtensa/include/asm/xor.h
diff --git a/arch/xtensa/kernel/entry.S b/arch/xtensa/kernel/entry.S
index dfd35dcc1cb5..a51d36a27389 100644
--- a/arch/xtensa/kernel/entry.S
+++ b/arch/xtensa/kernel/entry.S
@@ -25,7 +25,7 @@
 #include <asm/page.h>
 #include <asm/signal.h>
 #include <asm/tlbflush.h>
-#include <asm/variant/tie-asm.h>
+#include <variant/tie-asm.h>
 
 /* Unimplemented features. */
 
diff --git a/arch/xtensa/kernel/vmlinux.lds.S b/arch/xtensa/kernel/vmlinux.lds.S
index 51f4fb6f16f9..d506774f4b05 100644
--- a/arch/xtensa/kernel/vmlinux.lds.S
+++ b/arch/xtensa/kernel/vmlinux.lds.S
@@ -16,7 +16,7 @@
 
 #include <asm-generic/vmlinux.lds.h>
 
-#include <asm/variant/core.h>
+#include <variant/core.h>
 OUTPUT_ARCH(xtensa)
 ENTRY(_start)
 
diff --git a/arch/xtensa/lib/checksum.S b/arch/xtensa/lib/checksum.S
index 9d9cd990afa6..df397f932d0e 100644
--- a/arch/xtensa/lib/checksum.S
+++ b/arch/xtensa/lib/checksum.S
@@ -16,7 +16,7 @@
 
 #include <asm/errno.h>
 #include <linux/linkage.h>
-#include <asm/variant/core.h>
+#include <variant/core.h>
 
 /*
  * computes a partial checksum, e.g. for TCP/UDP fragments
diff --git a/arch/xtensa/lib/memcopy.S b/arch/xtensa/lib/memcopy.S
index ddda8f4bc862..ea59dcd03866 100644
--- a/arch/xtensa/lib/memcopy.S
+++ b/arch/xtensa/lib/memcopy.S
@@ -9,7 +9,7 @@
  * Copyright (C) 2002 - 2005 Tensilica Inc.
  */
 
-#include <asm/variant/core.h>
+#include <variant/core.h>
 
 	.macro	src_b	r, w0, w1
 #ifdef __XTENSA_EB__
diff --git a/arch/xtensa/lib/memset.S b/arch/xtensa/lib/memset.S
index 56a17495b2db..10b8c400f175 100644
--- a/arch/xtensa/lib/memset.S
+++ b/arch/xtensa/lib/memset.S
@@ -11,7 +11,7 @@
  *  Copyright (C) 2002 Tensilica Inc.
  */
 
-#include <asm/variant/core.h>
+#include <variant/core.h>
 
 /*
  * void *memset(void *dst, int c, size_t length)
diff --git a/arch/xtensa/lib/strncpy_user.S b/arch/xtensa/lib/strncpy_user.S
index b2655d94558d..9f603cdaaa68 100644
--- a/arch/xtensa/lib/strncpy_user.S
+++ b/arch/xtensa/lib/strncpy_user.S
@@ -11,7 +11,7 @@
  *  Copyright (C) 2002 Tensilica Inc.
  */
 
-#include <asm/variant/core.h>
+#include <variant/core.h>
 #include <linux/errno.h>
 
 /* Load or store instructions that may cause exceptions use the EX macro. */
diff --git a/arch/xtensa/lib/strnlen_user.S b/arch/xtensa/lib/strnlen_user.S
index ad3f616322ca..23f2a89816a1 100644
--- a/arch/xtensa/lib/strnlen_user.S
+++ b/arch/xtensa/lib/strnlen_user.S
@@ -11,7 +11,7 @@
  *  Copyright (C) 2002 Tensilica Inc.
  */
 
-#include <asm/variant/core.h>
+#include <variant/core.h>
 
 /* Load or store instructions that may cause exceptions use the EX macro. */
 
diff --git a/arch/xtensa/lib/usercopy.S b/arch/xtensa/lib/usercopy.S
index a8ab1d4fe0ae..46d60314bb16 100644
--- a/arch/xtensa/lib/usercopy.S
+++ b/arch/xtensa/lib/usercopy.S
@@ -53,7 +53,7 @@
  *	a11/ original length
  */
 
-#include <asm/variant/core.h>
+#include <variant/core.h>
 
 #ifdef __XTENSA_EB__
 #define ALIGN(R, W0, W1) src	R, W0, W1
diff --git a/arch/xtensa/platforms/iss/console.c b/arch/xtensa/platforms/iss/console.c
index 9141e3690731..efed8897bef3 100644
--- a/arch/xtensa/platforms/iss/console.c
+++ b/arch/xtensa/platforms/iss/console.c
@@ -1,5 +1,5 @@
 /*
- * arch/xtensa/platform-iss/console.c
+ * arch/xtensa/platforms/iss/console.c
  *
  * This file is subject to the terms and conditions of the GNU General Public
  * License.  See the file "COPYING" in the main directory of this archive
@@ -24,7 +24,7 @@
 #include <asm/uaccess.h>
 #include <asm/irq.h>
 
-#include <asm/platform/simcall.h>
+#include <platform/simcall.h>
 
 #include <linux/tty.h>
 #include <linux/tty_flip.h>
diff --git a/include/asm-xtensa/platform-iss/hardware.h b/arch/xtensa/platforms/iss/include/platform/hardware.h
index 6930c12adc16..6930c12adc16 100644
--- a/include/asm-xtensa/platform-iss/hardware.h
+++ b/arch/xtensa/platforms/iss/include/platform/hardware.h
diff --git a/include/asm-xtensa/platform-iss/simcall.h b/arch/xtensa/platforms/iss/include/platform/simcall.h
index b7952c06a2b7..b7952c06a2b7 100644
--- a/include/asm-xtensa/platform-iss/simcall.h
+++ b/arch/xtensa/platforms/iss/include/platform/simcall.h
diff --git a/arch/xtensa/platforms/iss/io.c b/arch/xtensa/platforms/iss/io.c
index 5b161a5cb65f..571d0b24f895 100644
--- a/arch/xtensa/platforms/iss/io.c
+++ b/arch/xtensa/platforms/iss/io.c
@@ -3,7 +3,7 @@
 #if 0
 
 #include <asm/io.h>
-#include <xtensa/simcall.h>
+#include <platform/platform-iss/simcall.h>
 
 extern int __simc ();
 
diff --git a/arch/xtensa/platforms/iss/network.c b/arch/xtensa/platforms/iss/network.c
index 11a20adc1409..4eb36fd0f930 100644
--- a/arch/xtensa/platforms/iss/network.c
+++ b/arch/xtensa/platforms/iss/network.c
@@ -1,6 +1,6 @@
 /*
  *
- * arch/xtensa/platform-iss/network.c
+ * arch/xtensa/platforms/iss/network.c
  *
  * Platform specific initialization.
  *
@@ -33,7 +33,7 @@
 #include <linux/rtnetlink.h>
 #include <linux/platform_device.h>
 
-#include <asm/platform/simcall.h>
+#include <platform/simcall.h>
 
 #define DRIVER_NAME "iss-netdev"
 #define ETH_MAX_PACKET 1500
diff --git a/arch/xtensa/platforms/xt2000/Makefile b/arch/xtensa/platforms/xt2000/Makefile
new file mode 100644
index 000000000000..54d018e45bfc
--- /dev/null
+++ b/arch/xtensa/platforms/xt2000/Makefile
@@ -0,0 +1,5 @@
+#
+# Makefile for the Tensilica XT2000 Emulation Board
+#
+
+obj-y 			= setup.o
diff --git a/arch/xtensa/platforms/xt2000/include/platform/hardware.h b/arch/xtensa/platforms/xt2000/include/platform/hardware.h
new file mode 100644
index 000000000000..41459ad07766
--- /dev/null
+++ b/arch/xtensa/platforms/xt2000/include/platform/hardware.h
@@ -0,0 +1,55 @@
+/*
+ * platform/hardware.h
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 2001 Tensilica Inc.
+ */
+
+/*
+ * This file contains the hardware configuration of the XT2000 board.
+ */
+
+#ifndef _XTENSA_XT2000_HARDWARE_H
+#define _XTENSA_XT2000_HARDWARE_H
+
+#include <variant/core.h>
+#include <asm/io.h>
+
+/* 
+ * Memory configuration.
+ */
+
+#define PLATFORM_DEFAULT_MEM_START 0x00000000
+#define PLATFORM_DEFAULT_MEM_SIZE 0x08000000
+
+/*
+ * Number of platform IRQs
+ */
+#define PLATFORM_NR_IRQS 3
+/*
+ * On-board components.
+ */
+
+#define SONIC83934_INTNUM	XCHAL_EXTINT3_NUM
+#define SONIC83934_ADDR		IOADDR(0x0d030000)
+
+/*
+ * V3-PCI
+ */
+
+/* The XT2000 uses the V3 as a cascaded interrupt controller for the PCI bus */
+
+#define IRQ_PCI_A		(XCHAL_NUM_INTERRUPTS + 0)
+#define IRQ_PCI_B		(XCHAL_NUM_INTERRUPTS + 1)
+#define IRQ_PCI_C		(XCHAL_NUM_INTERRUPTS + 2)
+
+/*
+ * Various other components.
+ */
+
+#define XT2000_LED_ADDR		IOADDR(0x0d040000)
+
+#endif /* _XTENSA_XT2000_HARDWARE_H */
diff --git a/arch/xtensa/platforms/xt2000/include/platform/serial.h b/arch/xtensa/platforms/xt2000/include/platform/serial.h
new file mode 100644
index 000000000000..7226cf732b47
--- /dev/null
+++ b/arch/xtensa/platforms/xt2000/include/platform/serial.h
@@ -0,0 +1,28 @@
+/*
+ * platform/serial.h
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 2001 Tensilica Inc.
+ */
+
+#ifndef _XTENSA_XT2000_SERIAL_H
+#define _XTENSA_XT2000_SERIAL_H
+
+#include <variant/core.h>
+#include <asm/io.h>
+
+/*  National-Semi PC16552D DUART:  */
+
+#define DUART16552_1_INTNUM	XCHAL_EXTINT4_NUM
+#define DUART16552_2_INTNUM	XCHAL_EXTINT5_NUM
+
+#define DUART16552_1_ADDR	IOADDR(0x0d050020)	/* channel 1 */
+#define DUART16552_2_ADDR	IOADDR(0x0d050000)	/* channel 2 */
+
+#define DUART16552_XTAL_FREQ	18432000	/* crystal frequency in Hz */
+#define BASE_BAUD ( DUART16552_XTAL_FREQ / 16 )
+
+#endif /* _XTENSA_XT2000_SERIAL_H */
diff --git a/arch/xtensa/platforms/xt2000/setup.c b/arch/xtensa/platforms/xt2000/setup.c
new file mode 100644
index 000000000000..9e83940ac265
--- /dev/null
+++ b/arch/xtensa/platforms/xt2000/setup.c
@@ -0,0 +1,181 @@
+/*
+ * arch/xtensa/platforms/xt2000/setup.c
+ *
+ * Platform specific functions for the XT2000 board.
+ *
+ * Authors:	Chris Zankel <chris@zankel.net>
+ *		Joe Taylor <joe@tensilica.com>
+ *
+ * Copyright 2001 - 2004 Tensilica Inc.
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ *
+ */
+#include <linux/stddef.h>
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/errno.h>
+#include <linux/reboot.h>
+#include <linux/kdev_t.h>
+#include <linux/types.h>
+#include <linux/major.h>
+#include <linux/console.h>
+#include <linux/delay.h>
+#include <linux/stringify.h>
+#include <linux/platform_device.h>
+#include <linux/serial.h>
+#include <linux/serial_8250.h>
+
+#include <asm/processor.h>
+#include <asm/platform.h>
+#include <asm/bootparam.h>
+#include <platform/hardware.h>
+#include <platform/serial.h>
+
+/* Assumes s points to an 8-chr string.  No checking for NULL. */
+
+static void led_print (int f, char *s)
+{
+	unsigned long* led_addr = (unsigned long*) (XT2000_LED_ADDR + 0xE0) + f;
+	int i;
+	for (i = f; i < 8; i++)
+		if ((*led_addr++ = *s++) == 0)
+		    break;
+}
+
+void platform_halt(void)
+{
+	led_print (0, "  HALT  ");
+	local_irq_disable();
+	while (1);
+}
+
+void platform_power_off(void)
+{
+	led_print (0, "POWEROFF");
+	local_irq_disable();
+	while (1);
+}
+
+void platform_restart(void)
+{
+	/* Flush and reset the mmu, simulate a processor reset, and
+	 * jump to the reset vector. */
+
+	__asm__ __volatile__ ("movi	a2, 15\n\t"
+			      "wsr	a2, " __stringify(ICOUNTLEVEL) "\n\t"
+			      "movi	a2, 0\n\t"
+			      "wsr	a2, " __stringify(ICOUNT) "\n\t"
+			      "wsr	a2, " __stringify(IBREAKENABLE) "\n\t"
+			      "wsr	a2, " __stringify(LCOUNT) "\n\t"
+			      "movi	a2, 0x1f\n\t"
+			      "wsr	a2, " __stringify(PS) "\n\t"
+			      "isync\n\t"
+			      "jx	%0\n\t"
+			      :
+			      : "a" (XCHAL_RESET_VECTOR_VADDR)
+			      : "a2"
+			      );
+
+	/* control never gets here */
+}
+
+void __init platform_setup(char** cmdline)
+{
+	led_print (0, "LINUX   ");
+}
+
+/* early initialization */
+
+extern sysmem_info_t __initdata sysmem;
+
+void platform_init(bp_tag_t* first)
+{
+	/* Set default memory block if not provided by the bootloader. */
+
+	if (sysmem.nr_banks == 0) {
+		sysmem.nr_banks = 1;
+		sysmem.bank[0].start = PLATFORM_DEFAULT_MEM_START;
+		sysmem.bank[0].end = PLATFORM_DEFAULT_MEM_START
+				     + PLATFORM_DEFAULT_MEM_SIZE;
+	}
+}
+
+/* Heartbeat. Let the LED blink. */
+
+void platform_heartbeat(void)
+{
+	static int i=0, t = 0;
+
+	if (--t < 0)
+	{
+		t = 59;
+		led_print(7, i ? ".": " ");
+		i ^= 1;
+	}
+}
+
+//#define RS_TABLE_SIZE 2
+//#define STD_COM_FLAGS (ASYNC_BOOT_AUTOCONF|ASYNC_SKIP_TEST)
+
+#define _SERIAL_PORT(_base,_irq)					\
+{									\
+	.mapbase	= (_base),					\
+	.membase	= (void*)(_base),				\
+	.irq		= (_irq),					\
+	.uartclk	= DUART16552_XTAL_FREQ,				\
+	.iotype		= UPIO_MEM,					\
+	.flags		= UPF_BOOT_AUTOCONF,				\
+	.regshift	= 2,						\
+}
+
+static struct plat_serial8250_port xt2000_serial_data[] = {
+#if XCHAL_HAVE_BE
+	_SERIAL_PORT(DUART16552_1_ADDR + 3, DUART16552_1_INTNUM),
+	_SERIAL_PORT(DUART16552_2_ADDR + 3, DUART16552_2_INTNUM),
+#else
+	_SERIAL_PORT(DUART16552_1_ADDR, DUART16552_1_INTNUM),
+	_SERIAL_PORT(DUART16552_2_ADDR, DUART16552_2_INTNUM),
+#endif
+	{ }
+};
+
+static struct platform_device xt2000_serial8250_device = {
+	.name		= "serial8250",
+	.id		= PLAT8250_DEV_PLATFORM,
+	.dev		= {
+	    .platform_data = xt2000_serial_data,
+	},
+};
+
+static struct resource xt2000_sonic_res[] = {
+	{
+		.start = SONIC83934_ADDR,
+		.end   = SONIC83934_ADDR + 0xff,
+		.flags = IORESOURCE_MEM,
+	},
+	{
+		.start = SONIC83934_INTNUM,
+		.end = SONIC83934_INTNUM,
+		.flags = IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device xt2000_sonic_device = {
+	.name		= "xtsonic",
+	.num_resources	= ARRAY_SIZE(xt2000_sonic_res),
+	.resource		= xt2000_sonic_res,
+};
+
+static int __init xt2000_setup_devinit(void)
+{
+	platform_device_register(&xt2000_serial8250_device);
+	platform_device_register(&xt2000_sonic_device);
+
+	return 0;
+}
+
+device_initcall(xt2000_setup_devinit);
diff --git a/include/asm-xtensa/variant-dc232b/core.h b/arch/xtensa/variants/dc232b/include/variant/core.h
index 525bd3d90154..525bd3d90154 100644
--- a/include/asm-xtensa/variant-dc232b/core.h
+++ b/arch/xtensa/variants/dc232b/include/variant/core.h
diff --git a/include/asm-xtensa/variant-dc232b/tie-asm.h b/arch/xtensa/variants/dc232b/include/variant/tie-asm.h
index ed4f53f529db..ed4f53f529db 100644
--- a/include/asm-xtensa/variant-dc232b/tie-asm.h
+++ b/arch/xtensa/variants/dc232b/include/variant/tie-asm.h
diff --git a/include/asm-xtensa/variant-dc232b/tie.h b/arch/xtensa/variants/dc232b/include/variant/tie.h
index 018e81af4393..018e81af4393 100644
--- a/include/asm-xtensa/variant-dc232b/tie.h
+++ b/arch/xtensa/variants/dc232b/include/variant/tie.h
diff --git a/include/asm-xtensa/variant-fsf/core.h b/arch/xtensa/variants/fsf/include/variant/core.h
index 2f337605c744..2f337605c744 100644
--- a/include/asm-xtensa/variant-fsf/core.h
+++ b/arch/xtensa/variants/fsf/include/variant/core.h
diff --git a/include/asm-xtensa/variant-fsf/tie-asm.h b/arch/xtensa/variants/fsf/include/variant/tie-asm.h
index 68a73bf4ffc5..68a73bf4ffc5 100644
--- a/include/asm-xtensa/variant-fsf/tie-asm.h
+++ b/arch/xtensa/variants/fsf/include/variant/tie-asm.h
diff --git a/include/asm-xtensa/variant-fsf/tie.h b/arch/xtensa/variants/fsf/include/variant/tie.h
index bf4020116df5..bf4020116df5 100644
--- a/include/asm-xtensa/variant-fsf/tie.h
+++ b/arch/xtensa/variants/fsf/include/variant/tie.h
diff --git a/block/blk-barrier.c b/block/blk-barrier.c
index 5c99ff8d2db8..6e72d661ae42 100644
--- a/block/blk-barrier.c
+++ b/block/blk-barrier.c
@@ -161,7 +161,7 @@ static inline struct request *start_ordered(struct request_queue *q,
 	/*
 	 * Prep proxy barrier request.
 	 */
-	blkdev_dequeue_request(rq);
+	elv_dequeue_request(q, rq);
 	q->orig_bar_rq = rq;
 	rq = &q->bar_rq;
 	blk_rq_init(q, rq);
@@ -219,7 +219,7 @@ int blk_do_ordered(struct request_queue *q, struct request **rqp)
 			 * This can happen when the queue switches to
 			 * ORDERED_NONE while this request is on it.
 			 */
-			blkdev_dequeue_request(rq);
+			elv_dequeue_request(q, rq);
 			if (__blk_end_request(rq, -EOPNOTSUPP,
 					      blk_rq_bytes(rq)))
 				BUG();
diff --git a/block/blk-core.c b/block/blk-core.c
index 10e8a64a5a5b..c36aa98fafa3 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -592,7 +592,7 @@ blk_init_queue_node(request_fn_proc *rfn, spinlock_t *lock, int node_id)
 				   1 << QUEUE_FLAG_STACKABLE);
 	q->queue_lock		= lock;
 
-	blk_queue_segment_boundary(q, 0xffffffff);
+	blk_queue_segment_boundary(q, BLK_SEG_BOUNDARY_MASK);
 
 	blk_queue_make_request(q, __make_request);
 	blk_queue_max_segment_size(q, MAX_SEGMENT_SIZE);
@@ -1637,6 +1637,28 @@ int blk_insert_cloned_request(struct request_queue *q, struct request *rq)
 EXPORT_SYMBOL_GPL(blk_insert_cloned_request);
 
 /**
+ * blkdev_dequeue_request - dequeue request and start timeout timer
+ * @req: request to dequeue
+ *
+ * Dequeue @req and start timeout timer on it.  This hands off the
+ * request to the driver.
+ *
+ * Block internal functions which don't want to start timer should
+ * call elv_dequeue_request().
+ */
+void blkdev_dequeue_request(struct request *req)
+{
+	elv_dequeue_request(req->q, req);
+
+	/*
+	 * We are now handing the request to the hardware, add the
+	 * timeout handler.
+	 */
+	blk_add_timer(req);
+}
+EXPORT_SYMBOL(blkdev_dequeue_request);
+
+/**
  * __end_that_request_first - end I/O on a request
  * @req:      the request being processed
  * @error:    %0 for success, < %0 for error
@@ -1774,7 +1796,7 @@ static void end_that_request_last(struct request *req, int error)
 		blk_queue_end_tag(req->q, req);
 
 	if (blk_queued_rq(req))
-		blkdev_dequeue_request(req);
+		elv_dequeue_request(req->q, req);
 
 	if (unlikely(laptop_mode) && blk_fs_request(req))
 		laptop_io_completion();
diff --git a/block/blk-map.c b/block/blk-map.c
index 0f4b4b881811..2990447f45e9 100644
--- a/block/blk-map.c
+++ b/block/blk-map.c
@@ -224,7 +224,7 @@ int blk_rq_map_user_iov(struct request_queue *q, struct request *rq,
 		 */
 		bio_get(bio);
 		bio_endio(bio, 0);
-		bio_unmap_user(bio);
+		__blk_rq_unmap_user(bio);
 		return -EINVAL;
 	}
 
diff --git a/block/blk-settings.c b/block/blk-settings.c
index 41392fbe19ff..afa55e14e278 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -125,6 +125,9 @@ void blk_queue_make_request(struct request_queue *q, make_request_fn *mfn)
 	q->nr_requests = BLKDEV_MAX_RQ;
 	blk_queue_max_phys_segments(q, MAX_PHYS_SEGMENTS);
 	blk_queue_max_hw_segments(q, MAX_HW_SEGMENTS);
+	blk_queue_segment_boundary(q, BLK_SEG_BOUNDARY_MASK);
+	blk_queue_max_segment_size(q, MAX_SEGMENT_SIZE);
+
 	q->make_request_fn = mfn;
 	q->backing_dev_info.ra_pages =
 			(VM_MAX_READAHEAD * 1024) / PAGE_CACHE_SIZE;
@@ -314,6 +317,7 @@ void blk_queue_stack_limits(struct request_queue *t, struct request_queue *b)
 	/* zero is "infinity" */
 	t->max_sectors = min_not_zero(t->max_sectors, b->max_sectors);
 	t->max_hw_sectors = min_not_zero(t->max_hw_sectors, b->max_hw_sectors);
+	t->seg_boundary_mask = min_not_zero(t->seg_boundary_mask, b->seg_boundary_mask);
 
 	t->max_phys_segments = min(t->max_phys_segments, b->max_phys_segments);
 	t->max_hw_segments = min(t->max_hw_segments, b->max_hw_segments);
diff --git a/block/bsg.c b/block/bsg.c
index e8bd2475682a..d414bb5607e8 100644
--- a/block/bsg.c
+++ b/block/bsg.c
@@ -42,7 +42,7 @@ struct bsg_device {
 	int done_cmds;
 	wait_queue_head_t wq_done;
 	wait_queue_head_t wq_free;
-	char name[BUS_ID_SIZE];
+	char name[20];
 	int max_queue;
 	unsigned long flags;
 };
@@ -202,6 +202,8 @@ static int blk_fill_sgv4_hdr_rq(struct request_queue *q, struct request *rq,
 		rq->timeout = q->sg_timeout;
 	if (!rq->timeout)
 		rq->timeout = BLK_DEFAULT_SG_TIMEOUT;
+	if (rq->timeout < BLK_MIN_SG_TIMEOUT)
+		rq->timeout = BLK_MIN_SG_TIMEOUT;
 
 	return 0;
 }
@@ -779,7 +781,7 @@ static struct bsg_device *bsg_add_device(struct inode *inode,
 	mutex_lock(&bsg_mutex);
 	hlist_add_head(&bd->dev_list, bsg_dev_idx_hash(iminor(inode)));
 
-	strncpy(bd->name, rq->bsg_dev.class_dev->bus_id, sizeof(bd->name) - 1);
+	strncpy(bd->name, dev_name(rq->bsg_dev.class_dev), sizeof(bd->name) - 1);
 	dprintk("bound to <%s>, max queue %d\n",
 		format_dev_t(buf, inode->i_rdev), bd->max_queue);
 
@@ -990,7 +992,7 @@ int bsg_register_queue(struct request_queue *q, struct device *parent,
 	if (name)
 		devname = name;
 	else
-		devname = parent->bus_id;
+		devname = dev_name(parent);
 
 	/*
 	 * we need a proper transport to send commands, not a stacked device
diff --git a/block/compat_ioctl.c b/block/compat_ioctl.c
index 3d3e7a46f38c..67eb93cff699 100644
--- a/block/compat_ioctl.c
+++ b/block/compat_ioctl.c
@@ -677,6 +677,29 @@ static int compat_blkdev_driver_ioctl(struct block_device *bdev, fmode_t mode,
 	case DVD_WRITE_STRUCT:
 	case DVD_AUTH:
 		arg = (unsigned long)compat_ptr(arg);
+	/* These intepret arg as an unsigned long, not as a pointer,
+	 * so we must not do compat_ptr() conversion. */
+	case HDIO_SET_MULTCOUNT:
+	case HDIO_SET_UNMASKINTR:
+	case HDIO_SET_KEEPSETTINGS:
+	case HDIO_SET_32BIT:
+	case HDIO_SET_NOWERR:
+	case HDIO_SET_DMA:
+	case HDIO_SET_PIO_MODE:
+	case HDIO_SET_NICE:
+	case HDIO_SET_WCACHE:
+	case HDIO_SET_ACOUSTIC:
+	case HDIO_SET_BUSSTATE:
+	case HDIO_SET_ADDRESS:
+	case CDROMEJECT_SW:
+	case CDROM_SET_OPTIONS:
+	case CDROM_CLEAR_OPTIONS:
+	case CDROM_SELECT_SPEED:
+	case CDROM_SELECT_DISC:
+	case CDROM_MEDIA_CHANGED:
+	case CDROM_DRIVE_STATUS:
+	case CDROM_LOCKDOOR:
+	case CDROM_DEBUG:
 		break;
 	default:
 		/* unknown ioctl number */
@@ -699,8 +722,14 @@ long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg)
 	struct backing_dev_info *bdi;
 	loff_t size;
 
+	/*
+	 * O_NDELAY can be altered using fcntl(.., F_SETFL, ..), so we have
+	 * to updated it before every ioctl.
+	 */
 	if (file->f_flags & O_NDELAY)
-		mode |= FMODE_NDELAY_NOW;
+		mode |= FMODE_NDELAY;
+	else
+		mode &= ~FMODE_NDELAY;
 
 	switch (cmd) {
 	case HDIO_GETGEO:
diff --git a/block/elevator.c b/block/elevator.c
index 9ac82dde99dd..a6951f76ba0c 100644
--- a/block/elevator.c
+++ b/block/elevator.c
@@ -844,14 +844,7 @@ void elv_dequeue_request(struct request_queue *q, struct request *rq)
 	 */
 	if (blk_account_rq(rq))
 		q->in_flight++;
-
-	/*
-	 * We are now handing the request to the hardware, add the
-	 * timeout handler.
-	 */
-	blk_add_timer(rq);
 }
-EXPORT_SYMBOL(elv_dequeue_request);
 
 int elv_queue_empty(struct request_queue *q)
 {
diff --git a/block/genhd.c b/block/genhd.c
index 27549e470da5..1c1fc39ea6a8 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -1069,7 +1069,7 @@ dev_t blk_lookup_devt(const char *name, int partno)
 		struct gendisk *disk = dev_to_disk(dev);
 		struct hd_struct *part;
 
-		if (strcmp(dev->bus_id, name))
+		if (strcmp(dev_name(dev), name))
 			continue;
 
 		part = disk_get_part(disk, partno);
@@ -1102,6 +1102,7 @@ struct gendisk *alloc_disk_node(int minors, int node_id)
 			kfree(disk);
 			return NULL;
 		}
+		disk->node_id = node_id;
 		if (disk_expand_part_tbl(disk, 0)) {
 			free_part_stats(&disk->part0);
 			kfree(disk);
@@ -1116,7 +1117,6 @@ struct gendisk *alloc_disk_node(int minors, int node_id)
 		device_initialize(disk_to_dev(disk));
 		INIT_WORK(&disk->async_notify,
 			media_change_notify_thread);
-		disk->node_id = node_id;
 	}
 	return disk;
 }
diff --git a/block/scsi_ioctl.c b/block/scsi_ioctl.c
index 5963cf91a3a0..d0bb92cbefb9 100644
--- a/block/scsi_ioctl.c
+++ b/block/scsi_ioctl.c
@@ -208,6 +208,8 @@ static int blk_fill_sghdr_rq(struct request_queue *q, struct request *rq,
 		rq->timeout = q->sg_timeout;
 	if (!rq->timeout)
 		rq->timeout = BLK_DEFAULT_SG_TIMEOUT;
+	if (rq->timeout < BLK_MIN_SG_TIMEOUT)
+		rq->timeout = BLK_MIN_SG_TIMEOUT;
 
 	return 0;
 }
diff --git a/drivers/Kconfig b/drivers/Kconfig
index 2f557f570ade..00cf9553f740 100644
--- a/drivers/Kconfig
+++ b/drivers/Kconfig
@@ -107,4 +107,6 @@ source "drivers/uio/Kconfig"
 source "drivers/xen/Kconfig"
 
 source "drivers/staging/Kconfig"
+
+source "drivers/platform/Kconfig"
 endmenu
diff --git a/drivers/Makefile b/drivers/Makefile
index fceb71a741c3..51ea896691a6 100644
--- a/drivers/Makefile
+++ b/drivers/Makefile
@@ -57,6 +57,7 @@ obj-$(CONFIG_ATA_OVER_ETH)	+= block/aoe/
 obj-$(CONFIG_PARIDE) 		+= block/paride/
 obj-$(CONFIG_TC)		+= tc/
 obj-$(CONFIG_UWB)		+= uwb/
+obj-$(CONFIG_USB_OTG_UTILS)	+= usb/otg/
 obj-$(CONFIG_USB)		+= usb/
 obj-$(CONFIG_USB_MUSB_HDRC)	+= usb/musb/
 obj-$(CONFIG_PCI)		+= usb/
@@ -102,3 +103,4 @@ obj-$(CONFIG_SSB)		+= ssb/
 obj-$(CONFIG_VIRTIO)		+= virtio/
 obj-$(CONFIG_REGULATOR)		+= regulator/
 obj-$(CONFIG_STAGING)		+= staging/
+obj-y				+= platform/
diff --git a/drivers/acpi/battery.c b/drivers/acpi/battery.c
index a0a178dd189c..1423b0c0cd2e 100644
--- a/drivers/acpi/battery.c
+++ b/drivers/acpi/battery.c
@@ -174,15 +174,6 @@ static int acpi_battery_get_property(struct power_supply *psy,
 		break;
 	case POWER_SUPPLY_PROP_CURRENT_NOW:
 		val->intval = battery->current_now * 1000;
-		/* if power units are mW, convert to mA by
-		   dividing by current voltage (mV/1000) */
-		if (!battery->power_unit) {
-			if (battery->voltage_now) {
-				val->intval /= battery->voltage_now;
-				val->intval *= 1000;
-			} else
-				val->intval = -1;
-		}
 		break;
 	case POWER_SUPPLY_PROP_CHARGE_FULL_DESIGN:
 	case POWER_SUPPLY_PROP_ENERGY_FULL_DESIGN:
diff --git a/drivers/acpi/dispatcher/dsmethod.c b/drivers/acpi/dispatcher/dsmethod.c
index 279a5a60a0dd..77b7039a26e4 100644
--- a/drivers/acpi/dispatcher/dsmethod.c
+++ b/drivers/acpi/dispatcher/dsmethod.c
@@ -412,6 +412,9 @@ acpi_ds_call_control_method(struct acpi_thread_state *thread,
 
 	if (obj_desc->method.method_flags & AML_METHOD_INTERNAL_ONLY) {
 		status = obj_desc->method.implementation(next_walk_state);
+		if (status == AE_OK) {
+			status = AE_CTRL_TERMINATE;
+		}
 	}
 
 	return_ACPI_STATUS(status);
diff --git a/drivers/acpi/dispatcher/dsopcode.c b/drivers/acpi/dispatcher/dsopcode.c
index 69fae5905bb8..50c892a49fa3 100644
--- a/drivers/acpi/dispatcher/dsopcode.c
+++ b/drivers/acpi/dispatcher/dsopcode.c
@@ -1140,10 +1140,29 @@ acpi_ds_exec_begin_control_op(struct acpi_walk_state *walk_state,
 			  op->common.aml_opcode, walk_state));
 
 	switch (op->common.aml_opcode) {
-	case AML_IF_OP:
 	case AML_WHILE_OP:
 
 		/*
+		 * If this is an additional iteration of a while loop, continue.
+		 * There is no need to allocate a new control state.
+		 */
+		if (walk_state->control_state) {
+			if (walk_state->control_state->control.aml_predicate_start
+				== (walk_state->parser_state.aml - 1)) {
+
+				/* Reset the state to start-of-loop */
+
+				walk_state->control_state->common.state =
+				    ACPI_CONTROL_CONDITIONAL_EXECUTING;
+				break;
+			}
+		}
+
+		/*lint -fallthrough */
+
+	case AML_IF_OP:
+
+		/*
 		 * IF/WHILE: Create a new control state to manage these
 		 * constructs. We need to manage these as a stack, in order
 		 * to handle nesting.
@@ -1243,13 +1262,36 @@ acpi_ds_exec_end_control_op(struct acpi_walk_state * walk_state,
 
 		ACPI_DEBUG_PRINT((ACPI_DB_DISPATCH, "[WHILE_OP] Op=%p\n", op));
 
-		if (walk_state->control_state->common.value) {
+		control_state = walk_state->control_state;
+		if (control_state->common.value) {
 
-			/* Predicate was true, go back and evaluate it again! */
+			/* Predicate was true, the body of the loop was just executed */
 
+			/*
+			 * This loop counter mechanism allows the interpreter to escape
+			 * possibly infinite loops. This can occur in poorly written AML
+			 * when the hardware does not respond within a while loop and the
+			 * loop does not implement a timeout.
+			 */
+			control_state->control.loop_count++;
+			if (control_state->control.loop_count >
+				ACPI_MAX_LOOP_ITERATIONS) {
+				status = AE_AML_INFINITE_LOOP;
+				break;
+			}
+
+			/*
+			 * Go back and evaluate the predicate and maybe execute the loop
+			 * another time
+			 */
 			status = AE_CTRL_PENDING;
+			walk_state->aml_last_while =
+			    control_state->control.aml_predicate_start;
+			break;
 		}
 
+		/* Predicate was false, terminate this while loop */
+
 		ACPI_DEBUG_PRINT((ACPI_DB_DISPATCH,
 				  "[WHILE_OP] termination! Op=%p\n", op));
 
@@ -1257,9 +1299,6 @@ acpi_ds_exec_end_control_op(struct acpi_walk_state * walk_state,
 
 		control_state =
 		    acpi_ut_pop_generic_state(&walk_state->control_state);
-
-		walk_state->aml_last_while =
-		    control_state->control.aml_predicate_start;
 		acpi_ut_delete_generic_state(control_state);
 		break;
 
diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c
index 30f3ef236ecb..60db1b235592 100644
--- a/drivers/acpi/ec.c
+++ b/drivers/acpi/ec.c
@@ -978,9 +978,9 @@ static const struct acpi_device_id ec_device_ids[] = {
 
 int __init acpi_ec_ecdt_probe(void)
 {
-	int ret;
 	acpi_status status;
 	struct acpi_table_ecdt *ecdt_ptr;
+	acpi_handle dummy;
 
 	boot_ec = make_acpi_ec();
 	if (!boot_ec)
@@ -1006,30 +1006,31 @@ int __init acpi_ec_ecdt_probe(void)
 		boot_ec->gpe = ecdt_ptr->gpe;
 		boot_ec->handle = ACPI_ROOT_OBJECT;
 		acpi_get_handle(ACPI_ROOT_OBJECT, ecdt_ptr->id, &boot_ec->handle);
-	} else {
-		/* This workaround is needed only on some broken machines,
-		 * which require early EC, but fail to provide ECDT */
-		acpi_handle x;
-		printk(KERN_DEBUG PREFIX "Look up EC in DSDT\n");
-		status = acpi_get_devices(ec_device_ids[0].id, ec_parse_device,
-						boot_ec, NULL);
-		/* Check that acpi_get_devices actually find something */
-		if (ACPI_FAILURE(status) || !boot_ec->handle)
-			goto error;
-		/* We really need to limit this workaround, the only ASUS,
-		 * which needs it, has fake EC._INI method, so use it as flag.
-		 * Keep boot_ec struct as it will be needed soon.
-		 */
-		if (ACPI_FAILURE(acpi_get_handle(boot_ec->handle, "_INI", &x)))
-			return -ENODEV;
+		/* Add some basic check against completely broken table */
+		if (boot_ec->data_addr != boot_ec->command_addr)
+			goto install;
+	/* fall through */
 	}
-
-	ret = ec_install_handlers(boot_ec);
-	if (!ret) {
+	/* This workaround is needed only on some broken machines,
+	 * which require early EC, but fail to provide ECDT */
+	printk(KERN_DEBUG PREFIX "Look up EC in DSDT\n");
+	status = acpi_get_devices(ec_device_ids[0].id, ec_parse_device,
+					boot_ec, NULL);
+	/* Check that acpi_get_devices actually find something */
+	if (ACPI_FAILURE(status) || !boot_ec->handle)
+		goto error;
+	/* We really need to limit this workaround, the only ASUS,
+	 * which needs it, has fake EC._INI method, so use it as flag.
+	 * Keep boot_ec struct as it will be needed soon.
+	 */
+	if (ACPI_FAILURE(acpi_get_handle(boot_ec->handle, "_INI", &dummy)))
+		return -ENODEV;
+install:
+	if (!ec_install_handlers(boot_ec)) {
 		first_ec = boot_ec;
 		return 0;
 	}
-      error:
+error:
 	kfree(boot_ec);
 	boot_ec = NULL;
 	return -ENODEV;
diff --git a/drivers/acpi/events/evevent.c b/drivers/acpi/events/evevent.c
index c56c5c6ea77b..6ddf938290f1 100644
--- a/drivers/acpi/events/evevent.c
+++ b/drivers/acpi/events/evevent.c
@@ -72,8 +72,8 @@ acpi_status acpi_ev_initialize_events(void)
 
 	/*
 	 * Initialize the Fixed and General Purpose Events. This is done prior to
-	 * enabling SCIs to prevent interrupts from occurring before the handlers are
-	 * installed.
+	 * enabling SCIs to prevent interrupts from occurring before the handlers
+	 * are installed.
 	 */
 	status = acpi_ev_fixed_event_initialize();
 	if (ACPI_FAILURE(status)) {
@@ -192,8 +192,8 @@ static acpi_status acpi_ev_fixed_event_initialize(void)
 	acpi_status status;
 
 	/*
-	 * Initialize the structure that keeps track of fixed event handlers
-	 * and enable the fixed events.
+	 * Initialize the structure that keeps track of fixed event handlers and
+	 * enable the fixed events.
 	 */
 	for (i = 0; i < ACPI_NUM_FIXED_EVENTS; i++) {
 		acpi_gbl_fixed_event_handlers[i].handler = NULL;
@@ -237,7 +237,7 @@ u32 acpi_ev_fixed_event_detect(void)
 
 	/*
 	 * Read the fixed feature status and enable registers, as all the cases
-	 * depend on their values.  Ignore errors here.
+	 * depend on their values. Ignore errors here.
 	 */
 	(void)acpi_hw_register_read(ACPI_REGISTER_PM1_STATUS, &fixed_status);
 	(void)acpi_hw_register_read(ACPI_REGISTER_PM1_ENABLE, &fixed_enable);
@@ -291,8 +291,8 @@ static u32 acpi_ev_fixed_event_dispatch(u32 event)
 				status_register_id, 1);
 
 	/*
-	 * Make sure we've got a handler.  If not, report an error.
-	 * The event is disabled to prevent further interrupts.
+	 * Make sure we've got a handler. If not, report an error. The event is
+	 * disabled to prevent further interrupts.
 	 */
 	if (NULL == acpi_gbl_fixed_event_handlers[event].handler) {
 		(void)acpi_set_register(acpi_gbl_fixed_event_info[event].
diff --git a/drivers/acpi/events/evgpe.c b/drivers/acpi/events/evgpe.c
index f45c74fe745e..12b49d312ad3 100644
--- a/drivers/acpi/events/evgpe.c
+++ b/drivers/acpi/events/evgpe.c
@@ -125,7 +125,7 @@ acpi_ev_update_gpe_enable_masks(struct acpi_gpe_event_info *gpe_event_info,
 	    (1 <<
 	     (gpe_event_info->gpe_number - gpe_register_info->base_gpe_number));
 
-	/* 1) Disable case.  Simply clear all enable bits */
+	/* 1) Disable case. Simply clear all enable bits */
 
 	if (type == ACPI_GPE_DISABLE) {
 		ACPI_CLEAR_BIT(gpe_register_info->enable_for_wake,
@@ -134,7 +134,7 @@ acpi_ev_update_gpe_enable_masks(struct acpi_gpe_event_info *gpe_event_info,
 		return_ACPI_STATUS(AE_OK);
 	}
 
-	/* 2) Enable case.  Set/Clear the appropriate enable bits */
+	/* 2) Enable case. Set/Clear the appropriate enable bits */
 
 	switch (gpe_event_info->flags & ACPI_GPE_TYPE_MASK) {
 	case ACPI_GPE_TYPE_WAKE:
@@ -295,7 +295,7 @@ acpi_status acpi_ev_disable_gpe(struct acpi_gpe_event_info *gpe_event_info)
  *
  * FUNCTION:    acpi_ev_get_gpe_event_info
  *
- * PARAMETERS:  gpe_device          - Device node.  NULL for GPE0/GPE1
+ * PARAMETERS:  gpe_device          - Device node. NULL for GPE0/GPE1
  *              gpe_number          - Raw GPE number
  *
  * RETURN:      A GPE event_info struct. NULL if not a valid GPE
@@ -372,7 +372,7 @@ struct acpi_gpe_event_info *acpi_ev_get_gpe_event_info(acpi_handle gpe_device,
  *
  * RETURN:      INTERRUPT_HANDLED or INTERRUPT_NOT_HANDLED
  *
- * DESCRIPTION: Detect if any GP events have occurred.  This function is
+ * DESCRIPTION: Detect if any GP events have occurred. This function is
  *              executed at interrupt level.
  *
  ******************************************************************************/
@@ -400,8 +400,8 @@ u32 acpi_ev_gpe_detect(struct acpi_gpe_xrupt_info * gpe_xrupt_list)
 
 	/*
 	 * We need to obtain the GPE lock for both the data structs and registers
-	 * Note: Not necessary to obtain the hardware lock, since the GPE registers
-	 * are owned by the gpe_lock.
+	 * Note: Not necessary to obtain the hardware lock, since the GPE
+	 * registers are owned by the gpe_lock.
 	 */
 	flags = acpi_os_acquire_lock(acpi_gbl_gpe_lock);
 
@@ -410,9 +410,8 @@ u32 acpi_ev_gpe_detect(struct acpi_gpe_xrupt_info * gpe_xrupt_list)
 	gpe_block = gpe_xrupt_list->gpe_block_list_head;
 	while (gpe_block) {
 		/*
-		 * Read all of the 8-bit GPE status and enable registers
-		 * in this GPE block, saving all of them.
-		 * Find all currently active GP events.
+		 * Read all of the 8-bit GPE status and enable registers in this GPE
+		 * block, saving all of them. Find all currently active GP events.
 		 */
 		for (i = 0; i < gpe_block->register_count; i++) {
 
@@ -527,8 +526,8 @@ static void ACPI_SYSTEM_XFACE acpi_ev_asynch_execute_gpe_method(void *context)
 	(void)acpi_ev_enable_gpe(gpe_event_info, FALSE);
 
 	/*
-	 * Take a snapshot of the GPE info for this level - we copy the
-	 * info to prevent a race condition with remove_handler/remove_block.
+	 * Take a snapshot of the GPE info for this level - we copy the info to
+	 * prevent a race condition with remove_handler/remove_block.
 	 */
 	ACPI_MEMCPY(&local_gpe_event_info, gpe_event_info,
 		    sizeof(struct acpi_gpe_event_info));
@@ -539,8 +538,8 @@ static void ACPI_SYSTEM_XFACE acpi_ev_asynch_execute_gpe_method(void *context)
 	}
 
 	/*
-	 * Must check for control method type dispatch one more
-	 * time to avoid race with ev_gpe_install_handler
+	 * Must check for control method type dispatch one more time to avoid a
+	 * race with ev_gpe_install_handler
 	 */
 	if ((local_gpe_event_info.flags & ACPI_GPE_DISPATCH_MASK) ==
 	    ACPI_GPE_DISPATCH_METHOD) {
@@ -584,8 +583,8 @@ static void acpi_ev_asynch_enable_gpe(void *context)
 	if ((gpe_event_info->flags & ACPI_GPE_XRUPT_TYPE_MASK) ==
 	    ACPI_GPE_LEVEL_TRIGGERED) {
 		/*
-		 * GPE is level-triggered, we clear the GPE status bit after
-		 * handling the event.
+		 * GPE is level-triggered, we clear the GPE status bit after handling
+		 * the event.
 		 */
 		status = acpi_hw_clear_gpe(gpe_event_info);
 		if (ACPI_FAILURE(status)) {
@@ -624,7 +623,7 @@ acpi_ev_gpe_dispatch(struct acpi_gpe_event_info *gpe_event_info, u32 gpe_number)
 	acpi_os_gpe_count(gpe_number);
 
 	/*
-	 * If edge-triggered, clear the GPE status bit now.  Note that
+	 * If edge-triggered, clear the GPE status bit now. Note that
 	 * level-triggered events are cleared after the GPE is serviced.
 	 */
 	if ((gpe_event_info->flags & ACPI_GPE_XRUPT_TYPE_MASK) ==
@@ -650,7 +649,8 @@ acpi_ev_gpe_dispatch(struct acpi_gpe_event_info *gpe_event_info, u32 gpe_number)
 
 		/*
 		 * Invoke the installed handler (at interrupt level)
-		 * Ignore return status for now.  TBD: leave GPE disabled on error?
+		 * Ignore return status for now.
+		 * TBD: leave GPE disabled on error?
 		 */
 		(void)gpe_event_info->dispatch.handler->address(gpe_event_info->
 								dispatch.
@@ -708,7 +708,7 @@ acpi_ev_gpe_dispatch(struct acpi_gpe_event_info *gpe_event_info, u32 gpe_number)
 			    gpe_number));
 
 		/*
-		 * Disable the GPE. The GPE will remain disabled until the ACPI
+		 * Disable the GPE. The GPE will remain disabled until the ACPICA
 		 * Core Subsystem is restarted, or a handler is installed.
 		 */
 		status = acpi_ev_disable_gpe(gpe_event_info);
diff --git a/drivers/acpi/events/evgpeblk.c b/drivers/acpi/events/evgpeblk.c
index 73c058e2f5c2..7537cda54050 100644
--- a/drivers/acpi/events/evgpeblk.c
+++ b/drivers/acpi/events/evgpeblk.c
@@ -309,17 +309,17 @@ acpi_ev_save_method_info(acpi_handle obj_handle,
 	     (gpe_block->block_base_number +
 	      (gpe_block->register_count * 8)))) {
 		/*
-		 * Not valid for this GPE block, just ignore it
-		 * However, it may be valid for a different GPE block, since GPE0 and GPE1
-		 * methods both appear under \_GPE.
+		 * Not valid for this GPE block, just ignore it. However, it may be
+		 * valid for a different GPE block, since GPE0 and GPE1 methods both
+		 * appear under \_GPE.
 		 */
 		return_ACPI_STATUS(AE_OK);
 	}
 
 	/*
-	 * Now we can add this information to the gpe_event_info block
-	 * for use during dispatch of this GPE. Default type is RUNTIME, although
-	 * this may change when the _PRW methods are executed later.
+	 * Now we can add this information to the gpe_event_info block for use
+	 * during dispatch of this GPE. Default type is RUNTIME, although this may
+	 * change when the _PRW methods are executed later.
 	 */
 	gpe_event_info =
 	    &gpe_block->event_info[gpe_number - gpe_block->block_base_number];
@@ -394,8 +394,8 @@ acpi_ev_match_prw_and_gpe(acpi_handle obj_handle,
 	gpe_block = gpe_info->gpe_block;
 
 	/*
-	 * The _PRW object must return a package, we are only interested
-	 * in the first element
+	 * The _PRW object must return a package, we are only interested in the
+	 * first element
 	 */
 	obj_desc = pkg_desc->package.elements[0];
 
@@ -434,7 +434,7 @@ acpi_ev_match_prw_and_gpe(acpi_handle obj_handle,
 	/*
 	 * Is this GPE within this block?
 	 *
-	 * TRUE iff these conditions are true:
+	 * TRUE if and only if these conditions are true:
 	 *     1) The GPE devices match.
 	 *     2) The GPE index(number) is within the range of the Gpe Block
 	 *          associated with the GPE device.
@@ -457,6 +457,7 @@ acpi_ev_match_prw_and_gpe(acpi_handle obj_handle,
 		if (ACPI_FAILURE(status)) {
 			goto cleanup;
 		}
+
 		status =
 		    acpi_ev_update_gpe_enable_masks(gpe_event_info,
 						    ACPI_GPE_DISABLE);
@@ -476,9 +477,9 @@ acpi_ev_match_prw_and_gpe(acpi_handle obj_handle,
  * RETURN:      A GPE interrupt block
  *
  * DESCRIPTION: Get or Create a GPE interrupt block. There is one interrupt
- *              block per unique interrupt level used for GPEs.
- *              Should be called only when the GPE lists are semaphore locked
- *              and not subject to change.
+ *              block per unique interrupt level used for GPEs. Should be
+ *              called only when the GPE lists are semaphore locked and not
+ *              subject to change.
  *
  ******************************************************************************/
 
@@ -608,8 +609,9 @@ acpi_ev_delete_gpe_xrupt(struct acpi_gpe_xrupt_info *gpe_xrupt)
  *
  * FUNCTION:    acpi_ev_install_gpe_block
  *
- * PARAMETERS:  gpe_block       - New GPE block
- *              interrupt_number - Xrupt to be associated with this GPE block
+ * PARAMETERS:  gpe_block               - New GPE block
+ *              interrupt_number        - Xrupt to be associated with this
+ *                                        GPE block
  *
  * RETURN:      Status
  *
@@ -666,7 +668,7 @@ acpi_ev_install_gpe_block(struct acpi_gpe_block_info *gpe_block,
  *
  * FUNCTION:    acpi_ev_delete_gpe_block
  *
- * PARAMETERS:  gpe_block       - Existing GPE block
+ * PARAMETERS:  gpe_block           - Existing GPE block
  *
  * RETURN:      Status
  *
@@ -786,9 +788,9 @@ acpi_ev_create_gpe_info_blocks(struct acpi_gpe_block_info *gpe_block)
 
 	/*
 	 * Initialize the GPE Register and Event structures. A goal of these
-	 * tables is to hide the fact that there are two separate GPE register sets
-	 * in a given GPE hardware block, the status registers occupy the first half,
-	 * and the enable registers occupy the second half.
+	 * tables is to hide the fact that there are two separate GPE register
+	 * sets in a given GPE hardware block, the status registers occupy the
+	 * first half, and the enable registers occupy the second half.
 	 */
 	this_register = gpe_register_info;
 	this_event = gpe_event_info;
diff --git a/drivers/acpi/events/evmisc.c b/drivers/acpi/events/evmisc.c
index 1d5670be729a..dbac5b3248a0 100644
--- a/drivers/acpi/events/evmisc.c
+++ b/drivers/acpi/events/evmisc.c
@@ -49,11 +49,7 @@
 #define _COMPONENT          ACPI_EVENTS
 ACPI_MODULE_NAME("evmisc")
 
-/* Pointer to FACS needed for the Global Lock */
-static struct acpi_table_facs *facs = NULL;
-
 /* Local prototypes */
-
 static void ACPI_SYSTEM_XFACE acpi_ev_notify_dispatch(void *context);
 
 static u32 acpi_ev_global_lock_handler(void *context);
@@ -152,7 +148,9 @@ acpi_ev_queue_notify_request(struct acpi_namespace_node * node,
 			break;
 
 		default:
+
 			/* All other types are not supported */
+
 			return (AE_TYPE);
 		}
 	}
@@ -193,9 +191,8 @@ acpi_ev_queue_notify_request(struct acpi_namespace_node * node,
 			acpi_ut_delete_generic_state(notify_info);
 		}
 	} else {
-		/*
-		 * There is no notify handler (per-device or system) for this device.
-		 */
+		/* There is no notify handler (per-device or system) for this device */
+
 		ACPI_DEBUG_PRINT((ACPI_DB_INFO,
 				  "No notify handler for Notify (%4.4s, %X) node %p\n",
 				  acpi_ut_get_node_name(node), notify_value,
@@ -229,9 +226,8 @@ static void ACPI_SYSTEM_XFACE acpi_ev_notify_dispatch(void *context)
 	ACPI_FUNCTION_ENTRY();
 
 	/*
-	 * We will invoke a global notify handler if installed.
-	 * This is done _before_ we invoke the per-device handler attached
-	 * to the device.
+	 * We will invoke a global notify handler if installed. This is done
+	 * _before_ we invoke the per-device handler attached to the device.
 	 */
 	if (notify_info->notify.value <= ACPI_MAX_SYS_NOTIFY) {
 
@@ -299,7 +295,7 @@ static u32 acpi_ev_global_lock_handler(void *context)
 	 * If we don't get it now, it will be marked pending and we will
 	 * take another interrupt when it becomes free.
 	 */
-	ACPI_ACQUIRE_GLOBAL_LOCK(facs, acquired);
+	ACPI_ACQUIRE_GLOBAL_LOCK(acpi_gbl_FACS, acquired);
 	if (acquired) {
 
 		/* Got the lock, now wake all threads waiting for it */
@@ -336,34 +332,27 @@ acpi_status acpi_ev_init_global_lock_handler(void)
 
 	ACPI_FUNCTION_TRACE(ev_init_global_lock_handler);
 
-	status = acpi_get_table_by_index(ACPI_TABLE_INDEX_FACS,
-					 ACPI_CAST_INDIRECT_PTR(struct
-								acpi_table_header,
-								&facs));
-	if (ACPI_FAILURE(status)) {
-		return_ACPI_STATUS(status);
-	}
+	/* Attempt installation of the global lock handler */
 
-	acpi_gbl_global_lock_present = TRUE;
 	status = acpi_install_fixed_event_handler(ACPI_EVENT_GLOBAL,
 						  acpi_ev_global_lock_handler,
 						  NULL);
 
 	/*
-	 * If the global lock does not exist on this platform, the attempt
-	 * to enable GBL_STATUS will fail (the GBL_ENABLE bit will not stick)
-	 * Map to AE_OK, but mark global lock as not present.
-	 * Any attempt to actually use the global lock will be flagged
-	 * with an error.
+	 * If the global lock does not exist on this platform, the attempt to
+	 * enable GBL_STATUS will fail (the GBL_ENABLE bit will not stick).
+	 * Map to AE_OK, but mark global lock as not present. Any attempt to
+	 * actually use the global lock will be flagged with an error.
 	 */
 	if (status == AE_NO_HARDWARE_RESPONSE) {
 		ACPI_ERROR((AE_INFO,
 			    "No response from Global Lock hardware, disabling lock"));
 
 		acpi_gbl_global_lock_present = FALSE;
-		status = AE_OK;
+		return_ACPI_STATUS(AE_OK);
 	}
 
+	acpi_gbl_global_lock_present = TRUE;
 	return_ACPI_STATUS(status);
 }
 
@@ -462,8 +451,8 @@ acpi_status acpi_ev_acquire_global_lock(u16 timeout)
 	}
 
 	/*
-	 * Make sure that a global lock actually exists. If not, just treat
-	 * the lock as a standard mutex.
+	 * Make sure that a global lock actually exists. If not, just treat the
+	 * lock as a standard mutex.
 	 */
 	if (!acpi_gbl_global_lock_present) {
 		acpi_gbl_global_lock_acquired = TRUE;
@@ -472,7 +461,7 @@ acpi_status acpi_ev_acquire_global_lock(u16 timeout)
 
 	/* Attempt to acquire the actual hardware lock */
 
-	ACPI_ACQUIRE_GLOBAL_LOCK(facs, acquired);
+	ACPI_ACQUIRE_GLOBAL_LOCK(acpi_gbl_FACS, acquired);
 	if (acquired) {
 
 		/* We got the lock */
@@ -536,7 +525,7 @@ acpi_status acpi_ev_release_global_lock(void)
 
 		/* Allow any thread to release the lock */
 
-		ACPI_RELEASE_GLOBAL_LOCK(facs, pending);
+		ACPI_RELEASE_GLOBAL_LOCK(acpi_gbl_FACS, pending);
 
 		/*
 		 * If the pending bit was set, we must write GBL_RLS to the control
@@ -582,8 +571,8 @@ void acpi_ev_terminate(void)
 
 	if (acpi_gbl_events_initialized) {
 		/*
-		 * Disable all event-related functionality.
-		 * In all cases, on error, print a message but obviously we don't abort.
+		 * Disable all event-related functionality. In all cases, on error,
+		 * print a message but obviously we don't abort.
 		 */
 
 		/* Disable all fixed events */
diff --git a/drivers/acpi/events/evregion.c b/drivers/acpi/events/evregion.c
index 236fbd1ca438..3ddddbfa8db7 100644
--- a/drivers/acpi/events/evregion.c
+++ b/drivers/acpi/events/evregion.c
@@ -48,16 +48,8 @@
 
 #define _COMPONENT          ACPI_EVENTS
 ACPI_MODULE_NAME("evregion")
-#define ACPI_NUM_DEFAULT_SPACES     4
-static u8 acpi_gbl_default_address_spaces[ACPI_NUM_DEFAULT_SPACES] = {
-	ACPI_ADR_SPACE_SYSTEM_MEMORY,
-	ACPI_ADR_SPACE_SYSTEM_IO,
-	ACPI_ADR_SPACE_PCI_CONFIG,
-	ACPI_ADR_SPACE_DATA_TABLE
-};
 
 /* Local prototypes */
-
 static acpi_status
 acpi_ev_reg_run(acpi_handle obj_handle,
 		u32 level, void *context, void **return_value);
@@ -66,6 +58,17 @@ static acpi_status
 acpi_ev_install_handler(acpi_handle obj_handle,
 			u32 level, void *context, void **return_value);
 
+/* These are the address spaces that will get default handlers */
+
+#define ACPI_NUM_DEFAULT_SPACES     4
+
+static u8 acpi_gbl_default_address_spaces[ACPI_NUM_DEFAULT_SPACES] = {
+	ACPI_ADR_SPACE_SYSTEM_MEMORY,
+	ACPI_ADR_SPACE_SYSTEM_IO,
+	ACPI_ADR_SPACE_PCI_CONFIG,
+	ACPI_ADR_SPACE_DATA_TABLE
+};
+
 /*******************************************************************************
  *
  * FUNCTION:    acpi_ev_install_region_handlers
@@ -91,18 +94,19 @@ acpi_status acpi_ev_install_region_handlers(void)
 	}
 
 	/*
-	 * All address spaces (PCI Config, EC, SMBus) are scope dependent
-	 * and registration must occur for a specific device.
+	 * All address spaces (PCI Config, EC, SMBus) are scope dependent and
+	 * registration must occur for a specific device.
 	 *
-	 * In the case of the system memory and IO address spaces there is currently
-	 * no device associated with the address space.  For these we use the root.
+	 * In the case of the system memory and IO address spaces there is
+	 * currently no device associated with the address space. For these we
+	 * use the root.
 	 *
-	 * We install the default PCI config space handler at the root so
-	 * that this space is immediately available even though the we have
-	 * not enumerated all the PCI Root Buses yet.  This is to conform
-	 * to the ACPI specification which states that the PCI config
-	 * space must be always available -- even though we are nowhere
-	 * near ready to find the PCI root buses at this point.
+	 * We install the default PCI config space handler at the root so that
+	 * this space is immediately available even though the we have not
+	 * enumerated all the PCI Root Buses yet. This is to conform to the ACPI
+	 * specification which states that the PCI config space must be always
+	 * available -- even though we are nowhere near ready to find the PCI root
+	 * buses at this point.
 	 *
 	 * NOTE: We ignore AE_ALREADY_EXISTS because this means that a handler
 	 * has already been installed (via acpi_install_address_space_handler).
@@ -160,12 +164,11 @@ acpi_status acpi_ev_initialize_op_regions(void)
 		return_ACPI_STATUS(status);
 	}
 
-	/*
-	 * Run the _REG methods for op_regions in each default address space
-	 */
-	for (i = 0; i < ACPI_NUM_DEFAULT_SPACES; i++) {
+	/* Run the _REG methods for op_regions in each default address space */
 
-		/* TBD: Make sure handler is the DEFAULT handler, otherwise
+	for (i = 0; i < ACPI_NUM_DEFAULT_SPACES; i++) {
+		/*
+		 * TBD: Make sure handler is the DEFAULT handler, otherwise
 		 * _REG will have already been run.
 		 */
 		status = acpi_ev_execute_reg_methods(acpi_gbl_root_node,
@@ -318,13 +321,13 @@ acpi_ev_address_space_dispatch(union acpi_operand_object *region_obj,
 	}
 
 	/*
-	 * It may be the case that the region has never been initialized
+	 * It may be the case that the region has never been initialized.
 	 * Some types of regions require special init code
 	 */
 	if (!(region_obj->region.flags & AOPOBJ_SETUP_COMPLETE)) {
-		/*
-		 * This region has not been initialized yet, do it
-		 */
+
+		/* This region has not been initialized yet, do it */
+
 		region_setup = handler_desc->address_space.setup;
 		if (!region_setup) {
 
@@ -339,9 +342,9 @@ acpi_ev_address_space_dispatch(union acpi_operand_object *region_obj,
 		}
 
 		/*
-		 * We must exit the interpreter because the region
-		 * setup will potentially execute control methods
-		 * (e.g., _REG method for this region)
+		 * We must exit the interpreter because the region setup will
+		 * potentially execute control methods (for example, the _REG method
+		 * for this region)
 		 */
 		acpi_ex_exit_interpreter();
 
@@ -364,9 +367,8 @@ acpi_ev_address_space_dispatch(union acpi_operand_object *region_obj,
 			return_ACPI_STATUS(status);
 		}
 
-		/*
-		 * Region initialization may have been completed by region_setup
-		 */
+		/* Region initialization may have been completed by region_setup */
+
 		if (!(region_obj->region.flags & AOPOBJ_SETUP_COMPLETE)) {
 			region_obj->region.flags |= AOPOBJ_SETUP_COMPLETE;
 
@@ -521,8 +523,8 @@ acpi_ev_detach_region(union acpi_operand_object *region_obj,
 			}
 
 			/*
-			 * If the region has been activated, call the setup handler
-			 * with the deactivate notification
+			 * If the region has been activated, call the setup handler with
+			 * the deactivate notification
 			 */
 			if (region_obj->region.flags & AOPOBJ_SETUP_COMPLETE) {
 				region_setup = handler_obj->address_space.setup;
@@ -668,8 +670,8 @@ acpi_ev_install_handler(acpi_handle obj_handle,
 	}
 
 	/*
-	 * We only care about regions.and objects
-	 * that are allowed to have address space handlers
+	 * We only care about regions and objects that are allowed to have
+	 * address space handlers
 	 */
 	if ((node->type != ACPI_TYPE_DEVICE) &&
 	    (node->type != ACPI_TYPE_REGION) && (node != acpi_gbl_root_node)) {
@@ -710,9 +712,9 @@ acpi_ev_install_handler(acpi_handle obj_handle,
 				/*
 				 * Since the object we found it on was a device, then it
 				 * means that someone has already installed a handler for
-				 * the branch of the namespace from this device on.  Just
+				 * the branch of the namespace from this device on. Just
 				 * bail out telling the walk routine to not traverse this
-				 * branch.  This preserves the scoping rule for handlers.
+				 * branch. This preserves the scoping rule for handlers.
 				 */
 				return (AE_CTRL_DEPTH);
 			}
@@ -723,9 +725,8 @@ acpi_ev_install_handler(acpi_handle obj_handle,
 		}
 
 		/*
-		 * As long as the device didn't have a handler for this
-		 * space we don't care about it.  We just ignore it and
-		 * proceed.
+		 * As long as the device didn't have a handler for this space we
+		 * don't care about it. We just ignore it and proceed.
 		 */
 		return (AE_OK);
 	}
@@ -733,16 +734,14 @@ acpi_ev_install_handler(acpi_handle obj_handle,
 	/* Object is a Region */
 
 	if (obj_desc->region.space_id != handler_obj->address_space.space_id) {
-		/*
-		 * This region is for a different address space
-		 * -- just ignore it
-		 */
+
+		/* This region is for a different address space, just ignore it */
+
 		return (AE_OK);
 	}
 
 	/*
-	 * Now we have a region and it is for the handler's address
-	 * space type.
+	 * Now we have a region and it is for the handler's address space type.
 	 *
 	 * First disconnect region for any previous handler (if any)
 	 */
@@ -786,9 +785,8 @@ acpi_ev_install_space_handler(struct acpi_namespace_node * node,
 	ACPI_FUNCTION_TRACE(ev_install_space_handler);
 
 	/*
-	 * This registration is valid for only the types below
-	 * and the root.  This is where the default handlers
-	 * get placed.
+	 * This registration is valid for only the types below and the root. This
+	 * is where the default handlers get placed.
 	 */
 	if ((node->type != ACPI_TYPE_DEVICE) &&
 	    (node->type != ACPI_TYPE_PROCESSOR) &&
@@ -848,8 +846,8 @@ acpi_ev_install_space_handler(struct acpi_namespace_node * node,
 	obj_desc = acpi_ns_get_attached_object(node);
 	if (obj_desc) {
 		/*
-		 * The attached device object already exists.
-		 * Make sure the handler is not already installed.
+		 * The attached device object already exists. Make sure the handler
+		 * is not already installed.
 		 */
 		handler_obj = obj_desc->device.handler;
 
@@ -864,8 +862,8 @@ acpi_ev_install_space_handler(struct acpi_namespace_node * node,
 				    handler) {
 					/*
 					 * It is (relatively) OK to attempt to install the SAME
-					 * handler twice. This can easily happen
-					 * with PCI_Config space.
+					 * handler twice. This can easily happen with the
+					 * PCI_Config space.
 					 */
 					status = AE_SAME_HANDLER;
 					goto unlock_and_exit;
@@ -925,9 +923,8 @@ acpi_ev_install_space_handler(struct acpi_namespace_node * node,
 	/*
 	 * Install the handler
 	 *
-	 * At this point there is no existing handler.
-	 * Just allocate the object for the handler and link it
-	 * into the list.
+	 * At this point there is no existing handler. Just allocate the object
+	 * for the handler and link it into the list.
 	 */
 	handler_obj =
 	    acpi_ut_create_internal_object(ACPI_TYPE_LOCAL_ADDRESS_HANDLER);
@@ -1000,11 +997,10 @@ acpi_ev_execute_reg_methods(struct acpi_namespace_node *node,
 	ACPI_FUNCTION_TRACE(ev_execute_reg_methods);
 
 	/*
-	 * Run all _REG methods for all Operation Regions for this
-	 * space ID.  This is a separate walk in order to handle any
-	 * interdependencies between regions and _REG methods.  (i.e. handlers
-	 * must be installed for all regions of this Space ID before we
-	 * can run any _REG methods)
+	 * Run all _REG methods for all Operation Regions for this space ID. This
+	 * is a separate walk in order to handle any interdependencies between
+	 * regions and _REG methods. (i.e. handlers must be installed for all
+	 * regions of this Space ID before we can run any _REG methods)
 	 */
 	status = acpi_ns_walk_namespace(ACPI_TYPE_ANY, node, ACPI_UINT32_MAX,
 					ACPI_NS_WALK_UNLOCK, acpi_ev_reg_run,
@@ -1042,8 +1038,8 @@ acpi_ev_reg_run(acpi_handle obj_handle,
 	}
 
 	/*
-	 * We only care about regions.and objects
-	 * that are allowed to have address space handlers
+	 * We only care about regions.and objects that are allowed to have address
+	 * space handlers
 	 */
 	if ((node->type != ACPI_TYPE_REGION) && (node != acpi_gbl_root_node)) {
 		return (AE_OK);
@@ -1062,10 +1058,9 @@ acpi_ev_reg_run(acpi_handle obj_handle,
 	/* Object is a Region */
 
 	if (obj_desc->region.space_id != space_id) {
-		/*
-		 * This region is for a different address space
-		 * -- just ignore it
-		 */
+
+		/* This region is for a different address space, just ignore it */
+
 		return (AE_OK);
 	}
 
diff --git a/drivers/acpi/events/evrgnini.c b/drivers/acpi/events/evrgnini.c
index 6b94b38df07d..f9e561ee9a71 100644
--- a/drivers/acpi/events/evrgnini.c
+++ b/drivers/acpi/events/evrgnini.c
@@ -233,9 +233,9 @@ acpi_ev_pci_config_region_setup(acpi_handle handle,
 				if (ACPI_FAILURE(status)) {
 					if (status == AE_SAME_HANDLER) {
 						/*
-						 * It is OK if the handler is already installed on the root
-						 * bridge.  Still need to return a context object for the
-						 * new PCI_Config operation region, however.
+						 * It is OK if the handler is already installed on the
+						 * root bridge. Still need to return a context object
+						 * for the new PCI_Config operation region, however.
 						 */
 						status = AE_OK;
 					} else {
@@ -272,8 +272,8 @@ acpi_ev_pci_config_region_setup(acpi_handle handle,
 	}
 
 	/*
-	 * For PCI_Config space access, we need the segment, bus,
-	 * device and function numbers.  Acquire them here.
+	 * For PCI_Config space access, we need the segment, bus, device and
+	 * function numbers. Acquire them here.
 	 *
 	 * Find the parent device object. (This allows the operation region to be
 	 * within a subscope under the device, such as a control method.)
@@ -289,16 +289,16 @@ acpi_ev_pci_config_region_setup(acpi_handle handle,
 	}
 
 	/*
-	 * Get the PCI device and function numbers from the _ADR object
-	 * contained in the parent's scope.
+	 * Get the PCI device and function numbers from the _ADR object contained
+	 * in the parent's scope.
 	 */
 	status =
 	    acpi_ut_evaluate_numeric_object(METHOD_NAME__ADR, pci_device_node,
 					    &pci_value);
 
 	/*
-	 * The default is zero, and since the allocation above zeroed
-	 * the data, just do nothing on failure.
+	 * The default is zero, and since the allocation above zeroed the data,
+	 * just do nothing on failure.
 	 */
 	if (ACPI_SUCCESS(status)) {
 		pci_id->device = ACPI_HIWORD(ACPI_LODWORD(pci_value));
@@ -382,9 +382,8 @@ static u8 acpi_ev_is_pci_root_bridge(struct acpi_namespace_node *node)
 	struct acpi_compatible_id_list *cid;
 	u32 i;
 
-	/*
-	 * Get the _HID and check for a PCI Root Bridge
-	 */
+	/* Get the _HID and check for a PCI Root Bridge */
+
 	status = acpi_ut_execute_HID(node, &hid);
 	if (ACPI_FAILURE(status)) {
 		return (FALSE);
@@ -394,10 +393,8 @@ static u8 acpi_ev_is_pci_root_bridge(struct acpi_namespace_node *node)
 		return (TRUE);
 	}
 
-	/*
-	 * The _HID did not match.
-	 * Get the _CID and check for a PCI Root Bridge
-	 */
+	/* The _HID did not match. Get the _CID and check for a PCI Root Bridge */
+
 	status = acpi_ut_execute_CID(node, &cid);
 	if (ACPI_FAILURE(status)) {
 		return (FALSE);
@@ -516,9 +513,9 @@ acpi_ev_default_region_setup(acpi_handle handle,
  *              Get the appropriate address space handler for a newly
  *              created region.
  *
- *              This also performs address space specific initialization.  For
+ *              This also performs address space specific initialization. For
  *              example, PCI regions must have an _ADR object that contains
- *              a PCI address in the scope of the definition.  This address is
+ *              a PCI address in the scope of the definition. This address is
  *              required to perform an access to PCI config space.
  *
  * MUTEX:       Interpreter should be unlocked, because we may run the _REG
@@ -572,7 +569,7 @@ acpi_ev_initialize_region(union acpi_operand_object *region_obj,
 	if (ACPI_SUCCESS(status)) {
 		/*
 		 * The _REG method is optional and there can be only one per region
-		 * definition.  This will be executed when the handler is attached
+		 * definition. This will be executed when the handler is attached
 		 * or removed
 		 */
 		region_obj2->extra.method_REG = method_node;
@@ -670,10 +667,8 @@ acpi_ev_initialize_region(union acpi_operand_object *region_obj,
 			}
 		}
 
-		/*
-		 * This node does not have the handler we need;
-		 * Pop up one level
-		 */
+		/* This node does not have the handler we need; Pop up one level */
+
 		node = acpi_ns_get_parent_node(node);
 	}
 
diff --git a/drivers/acpi/events/evsci.c b/drivers/acpi/events/evsci.c
index 2a8b77877610..b5fc8055a473 100644
--- a/drivers/acpi/events/evsci.c
+++ b/drivers/acpi/events/evsci.c
@@ -115,10 +115,8 @@ u32 ACPI_SYSTEM_XFACE acpi_ev_gpe_xrupt_handler(void *context)
 	 * if this interrupt handler is installed, ACPI is enabled.
 	 */
 
-	/*
-	 * GPEs:
-	 * Check for and dispatch any GPEs that have occurred
-	 */
+	/* GPEs: Check for and dispatch any GPEs that have occurred */
+
 	interrupt_handled |= acpi_ev_gpe_detect(gpe_xrupt_list);
 
 	return_UINT32(interrupt_handled);
@@ -158,11 +156,11 @@ u32 acpi_ev_install_sci_handler(void)
  * RETURN:      E_OK if handler uninstalled OK, E_ERROR if handler was not
  *              installed to begin with
  *
- * DESCRIPTION: Remove the SCI interrupt handler.  No further SCIs will be
+ * DESCRIPTION: Remove the SCI interrupt handler. No further SCIs will be
  *              taken.
  *
  * Note:  It doesn't seem important to disable all events or set the event
- *        enable registers to their original values.  The OS should disable
+ *        enable registers to their original values. The OS should disable
  *        the SCI interrupt level when the handler is removed, so no more
  *        events will come in.
  *
diff --git a/drivers/acpi/events/evxface.c b/drivers/acpi/events/evxface.c
index 94a6efe020be..a2867875c74e 100644
--- a/drivers/acpi/events/evxface.c
+++ b/drivers/acpi/events/evxface.c
@@ -267,7 +267,7 @@ acpi_install_notify_handler(acpi_handle device,
 	/*
 	 * Root Object:
 	 * Registering a notify handler on the root object indicates that the
-	 * caller wishes to receive notifications for all objects.  Note that
+	 * caller wishes to receive notifications for all objects. Note that
 	 * only one <external> global handler can be regsitered (per notify type).
 	 */
 	if (device == ACPI_ROOT_OBJECT) {
diff --git a/drivers/acpi/events/evxfevnt.c b/drivers/acpi/events/evxfevnt.c
index 41554f736b68..669b8ca4984b 100644
--- a/drivers/acpi/events/evxfevnt.c
+++ b/drivers/acpi/events/evxfevnt.c
@@ -161,8 +161,8 @@ acpi_status acpi_enable_event(u32 event, u32 flags)
 	}
 
 	/*
-	 * Enable the requested fixed event (by writing a one to the
-	 * enable register bit)
+	 * Enable the requested fixed event (by writing a one to the enable
+	 * register bit)
 	 */
 	status =
 	    acpi_set_register(acpi_gbl_fixed_event_info[event].
@@ -343,8 +343,8 @@ acpi_status acpi_disable_event(u32 event, u32 flags)
 	}
 
 	/*
-	 * Disable the requested fixed event (by writing a zero to the
-	 * enable register bit)
+	 * Disable the requested fixed event (by writing a zero to the enable
+	 * register bit)
 	 */
 	status =
 	    acpi_set_register(acpi_gbl_fixed_event_info[event].
@@ -396,8 +396,8 @@ acpi_status acpi_clear_event(u32 event)
 	}
 
 	/*
-	 * Clear the requested fixed event (By writing a one to the
-	 * status register bit)
+	 * Clear the requested fixed event (By writing a one to the status
+	 * register bit)
 	 */
 	status =
 	    acpi_set_register(acpi_gbl_fixed_event_info[event].
diff --git a/drivers/acpi/executer/exfldio.c b/drivers/acpi/executer/exfldio.c
index 9ff9d1f4615d..94500c4ef8bf 100644
--- a/drivers/acpi/executer/exfldio.c
+++ b/drivers/acpi/executer/exfldio.c
@@ -498,14 +498,13 @@ acpi_ex_field_datum_io(union acpi_operand_object *obj_desc,
 			return_ACPI_STATUS(status);
 		}
 
-		ACPI_DEBUG_PRINT((ACPI_DB_BFIELD,
-				  "I/O to Data Register: ValuePtr %p\n",
-				  value));
-
 		if (read_write == ACPI_READ) {
 
 			/* Read the datum from the data_register */
 
+			ACPI_DEBUG_PRINT((ACPI_DB_BFIELD,
+					  "Read from Data Register\n"));
+
 			status =
 			    acpi_ex_extract_from_field(obj_desc->index_field.
 						       data_obj, value,
@@ -513,6 +512,10 @@ acpi_ex_field_datum_io(union acpi_operand_object *obj_desc,
 		} else {
 			/* Write the datum to the data_register */
 
+			ACPI_DEBUG_PRINT((ACPI_DB_BFIELD,
+					  "Write to Data Register: Value %8.8X%8.8X\n",
+					  ACPI_FORMAT_UINT64(*value)));
+
 			status =
 			    acpi_ex_insert_into_field(obj_desc->index_field.
 						      data_obj, value,
diff --git a/drivers/acpi/hardware/hwsleep.c b/drivers/acpi/hardware/hwsleep.c
index 25dccdf179b9..5ec727ffcbe3 100644
--- a/drivers/acpi/hardware/hwsleep.c
+++ b/drivers/acpi/hardware/hwsleep.c
@@ -52,31 +52,19 @@ ACPI_MODULE_NAME("hwsleep")
  *
  * FUNCTION:    acpi_set_firmware_waking_vector
  *
- * PARAMETERS:  physical_address    - Physical address of ACPI real mode
+ * PARAMETERS:  physical_address    - 32-bit physical address of ACPI real mode
  *                                    entry point.
  *
  * RETURN:      Status
  *
- * DESCRIPTION: Access function for the firmware_waking_vector field in FACS
+ * DESCRIPTION: Sets the 32-bit firmware_waking_vector field of the FACS
  *
  ******************************************************************************/
 acpi_status
-acpi_set_firmware_waking_vector(acpi_physical_address physical_address)
+acpi_set_firmware_waking_vector(u32 physical_address)
 {
-	struct acpi_table_facs *facs;
-	acpi_status status;
-
 	ACPI_FUNCTION_TRACE(acpi_set_firmware_waking_vector);
 
-	/* Get the FACS */
-
-	status = acpi_get_table_by_index(ACPI_TABLE_INDEX_FACS,
-					 ACPI_CAST_INDIRECT_PTR(struct
-								acpi_table_header,
-								&facs));
-	if (ACPI_FAILURE(status)) {
-		return_ACPI_STATUS(status);
-	}
 
 	/*
 	 * According to the ACPI specification 2.0c and later, the 64-bit
@@ -85,10 +73,16 @@ acpi_set_firmware_waking_vector(acpi_physical_address physical_address)
 	 * Protected Mode.  Some systems (for example HP dv5-1004nr) are known
 	 * to fail to resume if the 64-bit vector is used.
 	 */
-	if (facs->version >= 1)
-		facs->xfirmware_waking_vector = 0;
 
-	facs->firmware_waking_vector = (u32)physical_address;
+	/* Set the 32-bit vector */
+
+	acpi_gbl_FACS->firmware_waking_vector = physical_address;
+
+	/* Clear the 64-bit vector if it exists */
+
+	if ((acpi_gbl_FACS->length > 32) && (acpi_gbl_FACS->version >= 1)) {
+		acpi_gbl_FACS->xfirmware_waking_vector = 0;
+	}
 
 	return_ACPI_STATUS(AE_OK);
 }
@@ -97,48 +91,39 @@ ACPI_EXPORT_SYMBOL(acpi_set_firmware_waking_vector)
 
 /*******************************************************************************
  *
- * FUNCTION:    acpi_get_firmware_waking_vector
+ * FUNCTION:    acpi_set_firmware_waking_vector64
  *
- * PARAMETERS:  *physical_address   - Where the contents of
- *                                    the firmware_waking_vector field of
- *                                    the FACS will be returned.
+ * PARAMETERS:  physical_address    - 64-bit physical address of ACPI protected
+ *                                    mode entry point.
  *
- * RETURN:      Status, vector
+ * RETURN:      Status
  *
- * DESCRIPTION: Access function for the firmware_waking_vector field in FACS
+ * DESCRIPTION: Sets the 64-bit X_firmware_waking_vector field of the FACS, if
+ *              it exists in the table.
  *
  ******************************************************************************/
-#ifdef ACPI_FUTURE_USAGE
 acpi_status
-acpi_get_firmware_waking_vector(acpi_physical_address * physical_address)
+acpi_set_firmware_waking_vector64(u64 physical_address)
 {
-	struct acpi_table_facs *facs;
-	acpi_status status;
+	ACPI_FUNCTION_TRACE(acpi_set_firmware_waking_vector64);
 
-	ACPI_FUNCTION_TRACE(acpi_get_firmware_waking_vector);
-
-	if (!physical_address) {
-		return_ACPI_STATUS(AE_BAD_PARAMETER);
-	}
 
-	/* Get the FACS */
+	/* Determine if the 64-bit vector actually exists */
 
-	status = acpi_get_table_by_index(ACPI_TABLE_INDEX_FACS,
-					 ACPI_CAST_INDIRECT_PTR(struct
-								acpi_table_header,
-								&facs));
-	if (ACPI_FAILURE(status)) {
-		return_ACPI_STATUS(status);
+	if ((acpi_gbl_FACS->length <= 32) || (acpi_gbl_FACS->version < 1)) {
+		return_ACPI_STATUS(AE_NOT_EXIST);
 	}
 
-	/* Get the vector */
-	*physical_address = (acpi_physical_address)facs->firmware_waking_vector;
+	/* Clear 32-bit vector, set the 64-bit X_ vector */
+
+	acpi_gbl_FACS->firmware_waking_vector = 0;
+	acpi_gbl_FACS->xfirmware_waking_vector = physical_address;
 
 	return_ACPI_STATUS(AE_OK);
 }
 
-ACPI_EXPORT_SYMBOL(acpi_get_firmware_waking_vector)
-#endif
+ACPI_EXPORT_SYMBOL(acpi_set_firmware_waking_vector64)
+
 /*******************************************************************************
  *
  * FUNCTION:    acpi_enter_sleep_state_prep
diff --git a/drivers/acpi/namespace/nsaccess.c b/drivers/acpi/namespace/nsaccess.c
index c39a7f68b889..35b0e46bd095 100644
--- a/drivers/acpi/namespace/nsaccess.c
+++ b/drivers/acpi/namespace/nsaccess.c
@@ -165,12 +165,9 @@ acpi_status acpi_ns_root_initialize(void)
 
 				obj_desc->method.method_flags =
 				    AML_METHOD_INTERNAL_ONLY;
-
-#ifndef ACPI_DUMP_APP
 				obj_desc->method.implementation =
 				    acpi_ut_osi_implementation;
 #endif
-#endif
 				break;
 
 			case ACPI_TYPE_INTEGER:
@@ -521,11 +518,11 @@ acpi_ns_lookup(union acpi_generic_state *scope_info,
 	}
 
 	/*
-	 * Search namespace for each segment of the name.  Loop through and
+	 * Search namespace for each segment of the name. Loop through and
 	 * verify (or add to the namespace) each name segment.
 	 *
 	 * The object type is significant only at the last name
-	 * segment.  (We don't care about the types along the path, only
+	 * segment. (We don't care about the types along the path, only
 	 * the type of the final target object.)
 	 */
 	this_search_type = ACPI_TYPE_ANY;
@@ -591,6 +588,10 @@ acpi_ns_lookup(union acpi_generic_state *scope_info,
 			 * segments).
 			 */
 			if (this_node->type == ACPI_TYPE_LOCAL_ALIAS) {
+				if (!this_node->object) {
+					return_ACPI_STATUS(AE_NOT_EXIST);
+				}
+
 				if (acpi_ns_opens_scope
 				    (((struct acpi_namespace_node *)this_node->
 				      object)->type)) {
diff --git a/drivers/acpi/namespace/nseval.c b/drivers/acpi/namespace/nseval.c
index 4cdf03ac2b46..b95bfbbf5617 100644
--- a/drivers/acpi/namespace/nseval.c
+++ b/drivers/acpi/namespace/nseval.c
@@ -89,6 +89,7 @@ acpi_status acpi_ns_evaluate(struct acpi_evaluate_info * info)
 	/* Initialize the return value to an invalid object */
 
 	info->return_object = NULL;
+	info->param_count = 0;
 
 	/*
 	 * Get the actual namespace node for the target object. Handles these cases:
@@ -141,41 +142,17 @@ acpi_status acpi_ns_evaluate(struct acpi_evaluate_info * info)
 			return_ACPI_STATUS(AE_NULL_OBJECT);
 		}
 
-		/*
-		 * Calculate the number of arguments being passed to the method
-		 */
+		/* Count the number of arguments being passed to the method */
 
-		info->param_count = 0;
 		if (info->parameters) {
-			while (info->parameters[info->param_count])
+			while (info->parameters[info->param_count]) {
+				if (info->param_count > ACPI_METHOD_MAX_ARG) {
+					return_ACPI_STATUS(AE_LIMIT);
+				}
 				info->param_count++;
+			}
 		}
 
-		/*
-		 * Warning if too few or too many arguments have been passed by the
-		 * caller. We don't want to abort here with an error because an
-		 * incorrect number of arguments may not cause the method to fail.
-		 * However, the method will fail if there are too few arguments passed
-		 * and the method attempts to use one of the missing ones.
-		 */
-
-		if (info->param_count < info->obj_desc->method.param_count) {
-			ACPI_WARNING((AE_INFO,
-				    "Insufficient arguments - "
-				    "method [%4.4s] needs %d, found %d",
-				    acpi_ut_get_node_name(info->resolved_node),
-				    info->obj_desc->method.param_count,
-				    info->param_count));
-		} else if (info->param_count >
-				info->obj_desc->method.param_count) {
-			ACPI_WARNING((AE_INFO,
-				      "Excess arguments - "
-				      "method [%4.4s] needs %d, found %d",
-				      acpi_ut_get_node_name(info->
-							    resolved_node),
-				      info->obj_desc->method.param_count,
-				      info->param_count));
-		}
 
 		ACPI_DUMP_PATHNAME(info->resolved_node, "Execute Method:",
 				   ACPI_LV_INFO, _COMPONENT);
@@ -264,32 +241,13 @@ acpi_status acpi_ns_evaluate(struct acpi_evaluate_info * info)
 		}
 	}
 
-	/* Validation of return values for ACPI-predefined methods and objects */
-
-	if ((status == AE_OK) || (status == AE_CTRL_RETURN_VALUE)) {
-		/*
-		 * If this is the first evaluation, check the return value. This
-		 * ensures that any warnings will only be emitted during the very
-		 * first evaluation of the object.
-		 */
-		if (!(node->flags & ANOBJ_EVALUATED)) {
-			/*
-			 * Check for a predefined ACPI name. If found, validate the
-			 * returned object.
-			 *
-			 * Note: Ignore return status for now, emit warnings if there are
-			 * problems with the returned object. May change later to abort
-			 * the method on invalid return object.
-			 */
-			(void)acpi_ns_check_predefined_names(node,
-							     info->
-							     return_object);
-		}
-
-		/* Mark the node as having been evaluated */
-
-		node->flags |= ANOBJ_EVALUATED;
-	}
+	/*
+	 * Check input argument count against the ASL-defined count for a method.
+	 * Also check predefined names: argument count and return value against
+	 * the ACPI specification. Some incorrect return value types are repaired.
+	 */
+	(void)acpi_ns_check_predefined_names(node, info->param_count,
+		status, &info->return_object);
 
 	/* Check if there is a return value that must be dealt with */
 
diff --git a/drivers/acpi/namespace/nspredef.c b/drivers/acpi/namespace/nspredef.c
index 0f17cf0898c9..8d354baaed53 100644
--- a/drivers/acpi/namespace/nspredef.c
+++ b/drivers/acpi/namespace/nspredef.c
@@ -72,7 +72,7 @@ ACPI_MODULE_NAME("nspredef")
 /* Local prototypes */
 static acpi_status
 acpi_ns_check_package(char *pathname,
-		      union acpi_operand_object *return_object,
+		      union acpi_operand_object **return_object_ptr,
 		      const union acpi_predefined_info *predefined);
 
 static acpi_status
@@ -82,13 +82,18 @@ acpi_ns_check_package_elements(char *pathname,
 
 static acpi_status
 acpi_ns_check_object_type(char *pathname,
-			  union acpi_operand_object *return_object,
+			  union acpi_operand_object **return_object_ptr,
 			  u32 expected_btypes, u32 package_index);
 
 static acpi_status
 acpi_ns_check_reference(char *pathname,
 			union acpi_operand_object *return_object);
 
+static acpi_status
+acpi_ns_repair_object(u32 expected_btypes,
+		      u32 package_index,
+		      union acpi_operand_object **return_object_ptr);
+
 /*
  * Names for the types that can be returned by the predefined objects.
  * Used for warning messages. Must be in the same order as the ACPI_RTYPEs
@@ -108,8 +113,8 @@ static const char *acpi_rtype_names[] = {
  * FUNCTION:    acpi_ns_check_predefined_names
  *
  * PARAMETERS:  Node            - Namespace node for the method/object
- *              return_object   - Object returned from the evaluation of this
- *                                method/object
+ *              return_object_ptr - Pointer to the object returned from the
+ *                                evaluation of a method or object
  *
  * RETURN:      Status
  *
@@ -119,8 +124,11 @@ static const char *acpi_rtype_names[] = {
 
 acpi_status
 acpi_ns_check_predefined_names(struct acpi_namespace_node *node,
-			       union acpi_operand_object *return_object)
+			       u32 user_param_count,
+			       acpi_status return_status,
+			       union acpi_operand_object **return_object_ptr)
 {
+	union acpi_operand_object *return_object = *return_object_ptr;
 	acpi_status status = AE_OK;
 	const union acpi_predefined_info *predefined;
 	char *pathname;
@@ -128,12 +136,6 @@ acpi_ns_check_predefined_names(struct acpi_namespace_node *node,
 	/* Match the name for this method/object against the predefined list */
 
 	predefined = acpi_ns_check_for_predefined_name(node);
-	if (!predefined) {
-
-		/* Name was not one of the predefined names */
-
-		return (AE_OK);
-	}
 
 	/* Get the full pathname to the object, for use in error messages */
 
@@ -143,10 +145,37 @@ acpi_ns_check_predefined_names(struct acpi_namespace_node *node,
 	}
 
 	/*
-	 * Check that the parameter count for this method is in accordance
-	 * with the ACPI specification.
+	 * Check that the parameter count for this method matches the ASL
+	 * definition. For predefined names, ensure that both the caller and
+	 * the method itself are in accordance with the ACPI specification.
 	 */
-	acpi_ns_check_parameter_count(pathname, node, predefined);
+	acpi_ns_check_parameter_count(pathname, node, user_param_count,
+				      predefined);
+
+	/* If not a predefined name, we cannot validate the return object */
+
+	if (!predefined) {
+		goto exit;
+	}
+
+	/* If the method failed, we cannot validate the return object */
+
+	if ((return_status != AE_OK) && (return_status != AE_CTRL_RETURN_VALUE)) {
+		goto exit;
+	}
+
+	/*
+	 * Only validate the return value on the first successful evaluation of
+	 * the method. This ensures that any warnings will only be emitted during
+	 * the very first evaluation of the method/object.
+	 */
+	if (node->flags & ANOBJ_EVALUATED) {
+		goto exit;
+	}
+
+	/* Mark the node as having been successfully evaluated */
+
+	node->flags |= ANOBJ_EVALUATED;
 
 	/*
 	 * If there is no return value, check if we require a return value for
@@ -171,7 +200,7 @@ acpi_ns_check_predefined_names(struct acpi_namespace_node *node,
 	 * We have a return value, but if one wasn't expected, just exit, this is
 	 * not a problem
 	 *
-	 * For example, if "Implicit return value" is enabled, methods will
+	 * For example, if the "Implicit Return" feature is enabled, methods will
 	 * always return a value
 	 */
 	if (!predefined->info.expected_btypes) {
@@ -182,7 +211,7 @@ acpi_ns_check_predefined_names(struct acpi_namespace_node *node,
 	 * Check that the type of the return object is what is expected for
 	 * this predefined name
 	 */
-	status = acpi_ns_check_object_type(pathname, return_object,
+	status = acpi_ns_check_object_type(pathname, return_object_ptr,
 					   predefined->info.expected_btypes,
 					   ACPI_NOT_PACKAGE);
 	if (ACPI_FAILURE(status)) {
@@ -193,11 +222,12 @@ acpi_ns_check_predefined_names(struct acpi_namespace_node *node,
 
 	if (ACPI_GET_OBJECT_TYPE(return_object) == ACPI_TYPE_PACKAGE) {
 		status =
-		    acpi_ns_check_package(pathname, return_object, predefined);
+		    acpi_ns_check_package(pathname, return_object_ptr,
+					  predefined);
 	}
 
       exit:
-	if (pathname) {
+	if (pathname != predefined->info.name) {
 		ACPI_FREE(pathname);
 	}
 
@@ -210,6 +240,7 @@ acpi_ns_check_predefined_names(struct acpi_namespace_node *node,
  *
  * PARAMETERS:  Pathname        - Full pathname to the node (for error msgs)
  *              Node            - Namespace node for the method/object
+ *              user_param_count - Number of args passed in by the caller
  *              Predefined      - Pointer to entry in predefined name table
  *
  * RETURN:      None
@@ -223,32 +254,76 @@ acpi_ns_check_predefined_names(struct acpi_namespace_node *node,
 void
 acpi_ns_check_parameter_count(char *pathname,
 			      struct acpi_namespace_node *node,
+			      u32 user_param_count,
 			      const union acpi_predefined_info *predefined)
 {
 	u32 param_count;
 	u32 required_params_current;
 	u32 required_params_old;
 
-	/*
-	 * Check that the ASL-defined parameter count is what is expected for
-	 * this predefined name.
-	 *
-	 * Methods have 0-7 parameters. All other types have zero.
-	 */
+	/* Methods have 0-7 parameters. All other types have zero. */
+
 	param_count = 0;
 	if (node->type == ACPI_TYPE_METHOD) {
 		param_count = node->object->method.param_count;
 	}
 
-	/* Validate parameter count - allow two different legal counts (_SCP) */
+	/* Argument count check for non-predefined methods/objects */
+
+	if (!predefined) {
+		/*
+		 * Warning if too few or too many arguments have been passed by the
+		 * caller. An incorrect number of arguments may not cause the method
+		 * to fail. However, the method will fail if there are too few
+		 * arguments and the method attempts to use one of the missing ones.
+		 */
+		if (user_param_count < param_count) {
+			ACPI_WARNING((AE_INFO,
+				      "%s: Insufficient arguments - needs %d, found %d",
+				      pathname, param_count, user_param_count));
+		} else if (user_param_count > param_count) {
+			ACPI_WARNING((AE_INFO,
+				      "%s: Excess arguments - needs %d, found %d",
+				      pathname, param_count, user_param_count));
+		}
+		return;
+	}
+
+	/* Allow two different legal argument counts (_SCP, etc.) */
 
 	required_params_current = predefined->info.param_count & 0x0F;
 	required_params_old = predefined->info.param_count >> 4;
 
+	if (user_param_count != ACPI_UINT32_MAX) {
+
+		/* Validate the user-supplied parameter count */
+
+		if ((user_param_count != required_params_current) &&
+		    (user_param_count != required_params_old)) {
+			ACPI_WARNING((AE_INFO,
+				      "%s: Parameter count mismatch - caller passed %d, ACPI requires %d",
+				      pathname, user_param_count,
+				      required_params_current));
+		}
+	}
+
+	/*
+	 * Only validate the argument count on the first successful evaluation of
+	 * the method. This ensures that any warnings will only be emitted during
+	 * the very first evaluation of the method/object.
+	 */
+	if (node->flags & ANOBJ_EVALUATED) {
+		return;
+	}
+
+	/*
+	 * Check that the ASL-defined parameter count is what is expected for
+	 * this predefined name.
+	 */
 	if ((param_count != required_params_current) &&
 	    (param_count != required_params_old)) {
 		ACPI_WARNING((AE_INFO,
-			      "%s: Parameter count mismatch - ASL declared %d, expected %d",
+			      "%s: Parameter count mismatch - ASL declared %d, ACPI requires %d",
 			      pathname, param_count, required_params_current));
 	}
 }
@@ -307,8 +382,8 @@ const union acpi_predefined_info *acpi_ns_check_for_predefined_name(struct
  * FUNCTION:    acpi_ns_check_package
  *
  * PARAMETERS:  Pathname        - Full pathname to the node (for error msgs)
- *              return_object   - Object returned from the evaluation of a
- *                                method or object
+ *              return_object_ptr - Pointer to the object returned from the
+ *                                evaluation of a method or object
  *              Predefined      - Pointer to entry in predefined name table
  *
  * RETURN:      Status
@@ -320,9 +395,10 @@ const union acpi_predefined_info *acpi_ns_check_for_predefined_name(struct
 
 static acpi_status
 acpi_ns_check_package(char *pathname,
-		      union acpi_operand_object *return_object,
+		      union acpi_operand_object **return_object_ptr,
 		      const union acpi_predefined_info *predefined)
 {
+	union acpi_operand_object *return_object = *return_object_ptr;
 	const union acpi_predefined_info *package;
 	union acpi_operand_object *sub_package;
 	union acpi_operand_object **elements;
@@ -408,7 +484,7 @@ acpi_ns_check_package(char *pathname,
 		 * elements must be of the same type
 		 */
 		for (i = 0; i < count; i++) {
-			status = acpi_ns_check_object_type(pathname, *elements,
+			status = acpi_ns_check_object_type(pathname, elements,
 							   package->ret_info.
 							   object_type1, i);
 			if (ACPI_FAILURE(status)) {
@@ -441,7 +517,7 @@ acpi_ns_check_package(char *pathname,
 
 				status =
 				    acpi_ns_check_object_type(pathname,
-							      *elements,
+							      elements,
 							      package->
 							      ret_info3.
 							      object_type[i],
@@ -454,7 +530,7 @@ acpi_ns_check_package(char *pathname,
 
 				status =
 				    acpi_ns_check_object_type(pathname,
-							      *elements,
+							      elements,
 							      package->
 							      ret_info3.
 							      tail_object_type,
@@ -471,7 +547,7 @@ acpi_ns_check_package(char *pathname,
 
 		/* First element is the (Integer) count of sub-packages to follow */
 
-		status = acpi_ns_check_object_type(pathname, *elements,
+		status = acpi_ns_check_object_type(pathname, elements,
 						   ACPI_RTYPE_INTEGER, 0);
 		if (ACPI_FAILURE(status)) {
 			return (status);
@@ -509,7 +585,7 @@ acpi_ns_check_package(char *pathname,
 			/* Each sub-object must be of type Package */
 
 			status =
-			    acpi_ns_check_object_type(pathname, sub_package,
+			    acpi_ns_check_object_type(pathname, &sub_package,
 						      ACPI_RTYPE_PACKAGE, i);
 			if (ACPI_FAILURE(status)) {
 				return (status);
@@ -567,12 +643,8 @@ acpi_ns_check_package(char *pathname,
 				for (j = 0; j < expected_count; j++) {
 					status =
 					    acpi_ns_check_object_type(pathname,
-								      sub_elements
-								      [j],
-								      package->
-								      ret_info2.
-								      object_type
-								      [j], j);
+						&sub_elements[j],
+						package->ret_info2.object_type[j], j);
 					if (ACPI_FAILURE(status)) {
 						return (status);
 					}
@@ -611,7 +683,7 @@ acpi_ns_check_package(char *pathname,
 
 				status =
 				    acpi_ns_check_object_type(pathname,
-							      *sub_elements,
+							      sub_elements,
 							      ACPI_RTYPE_INTEGER,
 							      0);
 				if (ACPI_FAILURE(status)) {
@@ -708,7 +780,7 @@ acpi_ns_check_package_elements(char *pathname,
 	 * The second group can have a count of zero.
 	 */
 	for (i = 0; i < count1; i++) {
-		status = acpi_ns_check_object_type(pathname, *this_element,
+		status = acpi_ns_check_object_type(pathname, this_element,
 						   type1, i);
 		if (ACPI_FAILURE(status)) {
 			return (status);
@@ -717,7 +789,7 @@ acpi_ns_check_package_elements(char *pathname,
 	}
 
 	for (i = 0; i < count2; i++) {
-		status = acpi_ns_check_object_type(pathname, *this_element,
+		status = acpi_ns_check_object_type(pathname, this_element,
 						   type2, (i + count1));
 		if (ACPI_FAILURE(status)) {
 			return (status);
@@ -733,8 +805,8 @@ acpi_ns_check_package_elements(char *pathname,
  * FUNCTION:    acpi_ns_check_object_type
  *
  * PARAMETERS:  Pathname        - Full pathname to the node (for error msgs)
- *              return_object   - Object return from the execution of this
- *                                method/object
+ *              return_object_ptr - Pointer to the object returned from the
+ *                                evaluation of a method or object
  *              expected_btypes - Bitmap of expected return type(s)
  *              package_index   - Index of object within parent package (if
  *                                applicable - ACPI_NOT_PACKAGE otherwise)
@@ -748,9 +820,10 @@ acpi_ns_check_package_elements(char *pathname,
 
 static acpi_status
 acpi_ns_check_object_type(char *pathname,
-			  union acpi_operand_object *return_object,
+			  union acpi_operand_object **return_object_ptr,
 			  u32 expected_btypes, u32 package_index)
 {
+	union acpi_operand_object *return_object = *return_object_ptr;
 	acpi_status status = AE_OK;
 	u32 return_btype;
 	char type_buffer[48];	/* Room for 5 types */
@@ -814,6 +887,14 @@ acpi_ns_check_object_type(char *pathname,
 	/* Is the object one of the expected types? */
 
 	if (!(return_btype & expected_btypes)) {
+
+		/* Type mismatch -- attempt repair of the returned object */
+
+		status = acpi_ns_repair_object(expected_btypes, package_index,
+					       return_object_ptr);
+		if (ACPI_SUCCESS(status)) {
+			return (status);
+		}
 		goto type_error_exit;
 	}
 
@@ -898,3 +979,86 @@ acpi_ns_check_reference(char *pathname,
 
 	return (AE_AML_OPERAND_TYPE);
 }
+
+/*******************************************************************************
+ *
+ * FUNCTION:    acpi_ns_repair_object
+ *
+ * PARAMETERS:  Pathname        - Full pathname to the node (for error msgs)
+ *              package_index   - Used to determine if target is in a package
+ *              return_object_ptr - Pointer to the object returned from the
+ *                                evaluation of a method or object
+ *
+ * RETURN:      Status. AE_OK if repair was successful.
+ *
+ * DESCRIPTION: Attempt to repair/convert a return object of a type that was
+ *              not expected.
+ *
+ ******************************************************************************/
+
+static acpi_status
+acpi_ns_repair_object(u32 expected_btypes,
+		      u32 package_index,
+		      union acpi_operand_object **return_object_ptr)
+{
+	union acpi_operand_object *return_object = *return_object_ptr;
+	union acpi_operand_object *new_object;
+	acpi_size length;
+
+	switch (ACPI_GET_OBJECT_TYPE(return_object)) {
+	case ACPI_TYPE_BUFFER:
+
+		if (!(expected_btypes & ACPI_RTYPE_STRING)) {
+			return (AE_AML_OPERAND_TYPE);
+		}
+
+		/*
+		 * Have a Buffer, expected a String, convert. Use a to_string
+		 * conversion, no transform performed on the buffer data. The best
+		 * example of this is the _BIF method, where the string data from
+		 * the battery is often (incorrectly) returned as buffer object(s).
+		 */
+		length = 0;
+		while ((length < return_object->buffer.length) &&
+		       (return_object->buffer.pointer[length])) {
+			length++;
+		}
+
+		/* Allocate a new string object */
+
+		new_object = acpi_ut_create_string_object(length);
+		if (!new_object) {
+			return (AE_NO_MEMORY);
+		}
+
+		/*
+		 * Copy the raw buffer data with no transform. String is already NULL
+		 * terminated at Length+1.
+		 */
+		ACPI_MEMCPY(new_object->string.pointer,
+			    return_object->buffer.pointer, length);
+
+		/* Install the new return object */
+
+		acpi_ut_remove_reference(return_object);
+		*return_object_ptr = new_object;
+
+		/*
+		 * If the object is a package element, we need to:
+		 * 1. Decrement the reference count of the orignal object, it was
+		 *    incremented when building the package
+		 * 2. Increment the reference count of the new object, it will be
+		 *    decremented when releasing the package
+		 */
+		if (package_index != ACPI_NOT_PACKAGE) {
+			acpi_ut_remove_reference(return_object);
+			acpi_ut_add_reference(new_object);
+		}
+		return (AE_OK);
+
+	default:
+		break;
+	}
+
+	return (AE_AML_OPERAND_TYPE);
+}
diff --git a/drivers/acpi/namespace/nsutils.c b/drivers/acpi/namespace/nsutils.c
index b0817e1127b1..337fb04e0388 100644
--- a/drivers/acpi/namespace/nsutils.c
+++ b/drivers/acpi/namespace/nsutils.c
@@ -314,9 +314,15 @@ void acpi_ns_get_internal_name_length(struct acpi_namestring_info *info)
 	 *
 	 * strlen() + 1 covers the first name_seg, which has no path separator
 	 */
-	if (acpi_ns_valid_root_prefix(next_external_char[0])) {
+	if (acpi_ns_valid_root_prefix(*next_external_char)) {
 		info->fully_qualified = TRUE;
 		next_external_char++;
+
+		/* Skip redundant root_prefix, like \\_SB.PCI0.SBRG.EC0 */
+
+		while (acpi_ns_valid_root_prefix(*next_external_char)) {
+			next_external_char++;
+		}
 	} else {
 		/*
 		 * Handle Carat prefixes
diff --git a/drivers/acpi/parser/psparse.c b/drivers/acpi/parser/psparse.c
index 68e932f215ea..5156203883d7 100644
--- a/drivers/acpi/parser/psparse.c
+++ b/drivers/acpi/parser/psparse.c
@@ -447,10 +447,22 @@ acpi_status acpi_ps_parse_aml(struct acpi_walk_state *walk_state)
 			  walk_state, walk_state->parser_state.aml,
 			  walk_state->parser_state.aml_size));
 
+	if (!walk_state->parser_state.aml) {
+		return_ACPI_STATUS(AE_NULL_OBJECT);
+	}
+
 	/* Create and initialize a new thread state */
 
 	thread = acpi_ut_create_thread_state();
 	if (!thread) {
+		if (walk_state->method_desc) {
+
+			/* Executing a control method - additional cleanup */
+
+			acpi_ds_terminate_control_method(
+				walk_state->method_desc, walk_state);
+		}
+
 		acpi_ds_delete_walk_state(walk_state);
 		return_ACPI_STATUS(AE_NO_MEMORY);
 	}
diff --git a/drivers/acpi/parser/psxface.c b/drivers/acpi/parser/psxface.c
index 270469aae842..41b0c8c052a8 100644
--- a/drivers/acpi/parser/psxface.c
+++ b/drivers/acpi/parser/psxface.c
@@ -45,6 +45,7 @@
 #include <acpi/acparser.h>
 #include <acpi/acdispat.h>
 #include <acpi/acinterp.h>
+#include <acpi/amlcode.h>
 
 #define _COMPONENT          ACPI_PARSER
 ACPI_MODULE_NAME("psxface")
@@ -278,6 +279,38 @@ acpi_status acpi_ps_execute_method(struct acpi_evaluate_info *info)
 		goto cleanup;
 	}
 
+	/* Invoke an internal method if necessary */
+
+	if (info->obj_desc->method.method_flags & AML_METHOD_INTERNAL_ONLY) {
+		status = info->obj_desc->method.implementation(walk_state);
+		info->return_object = walk_state->return_desc;
+
+		/* Cleanup states */
+
+		acpi_ds_scope_stack_clear(walk_state);
+		acpi_ps_cleanup_scope(&walk_state->parser_state);
+		acpi_ds_terminate_control_method(walk_state->method_desc,
+						 walk_state);
+		acpi_ds_delete_walk_state(walk_state);
+		goto cleanup;
+	}
+
+	/*
+	 * Start method evaluation with an implicit return of zero.
+	 * This is done for Windows compatibility.
+	 */
+	if (acpi_gbl_enable_interpreter_slack) {
+		walk_state->implicit_return_obj =
+		    acpi_ut_create_internal_object(ACPI_TYPE_INTEGER);
+		if (!walk_state->implicit_return_obj) {
+			status = AE_NO_MEMORY;
+			acpi_ds_delete_walk_state(walk_state);
+			goto cleanup;
+		}
+
+		walk_state->implicit_return_obj->integer.value = 0;
+	}
+
 	/* Parse the AML */
 
 	status = acpi_ps_parse_aml(walk_state);
diff --git a/drivers/acpi/pci_irq.c b/drivers/acpi/pci_irq.c
index 11acaee14d66..bf79d83bdfbb 100644
--- a/drivers/acpi/pci_irq.c
+++ b/drivers/acpi/pci_irq.c
@@ -384,6 +384,27 @@ acpi_pci_free_irq(struct acpi_prt_entry *entry,
 	return irq;
 }
 
+#ifdef CONFIG_X86_IO_APIC
+extern int noioapicquirk;
+
+static int bridge_has_boot_interrupt_variant(struct pci_bus *bus)
+{
+	struct pci_bus *bus_it;
+
+	for (bus_it = bus ; bus_it ; bus_it = bus_it->parent) {
+		if (!bus_it->self)
+			return 0;
+
+		printk(KERN_INFO "vendor=%04x device=%04x\n", bus_it->self->vendor,
+				bus_it->self->device);
+
+		if (bus_it->self->irq_reroute_variant)
+			return bus_it->self->irq_reroute_variant;
+	}
+	return 0;
+}
+#endif /* CONFIG_X86_IO_APIC */
+
 /*
  * acpi_pci_irq_lookup
  * success: return IRQ >= 0
@@ -413,6 +434,41 @@ acpi_pci_irq_lookup(struct pci_bus *bus,
 	}
 
 	ret = func(entry, triggering, polarity, link);
+
+#ifdef CONFIG_X86_IO_APIC
+	/*
+	 * Some chipsets (e.g. intel 6700PXH) generate a legacy INTx when the
+	 * IRQ entry in the chipset's IO-APIC is masked (as, e.g. the RT kernel
+	 * does during interrupt handling). When this INTx generation cannot be
+	 * disabled, we reroute these interrupts to their legacy equivalent to
+	 * get rid of spurious interrupts.
+	 */
+        if (!noioapicquirk) {
+		switch (bridge_has_boot_interrupt_variant(bus)) {
+		case 0:
+			/* no rerouting necessary */
+			break;
+
+		case INTEL_IRQ_REROUTE_VARIANT:
+			/*
+			 * Remap according to INTx routing table in 6700PXH
+			 * specs, intel order number 302628-002, section
+			 * 2.15.2. Other chipsets (80332, ...) have the same
+			 * mapping and are handled here as well.
+			 */
+			printk(KERN_INFO "pci irq %d -> rerouted to legacy "
+					 "irq %d\n", ret, (ret % 4) + 16);
+			ret = (ret % 4) + 16;
+			break;
+
+		default:
+			printk(KERN_INFO "not rerouting irq %d to legacy irq: "
+					 "unknown mapping\n", ret);
+			break;
+		}
+	}
+#endif /* CONFIG_X86_IO_APIC */
+
 	return ret;
 }
 
diff --git a/drivers/acpi/pci_root.c b/drivers/acpi/pci_root.c
index 642554b1b60c..5b38a026d122 100644
--- a/drivers/acpi/pci_root.c
+++ b/drivers/acpi/pci_root.c
@@ -31,6 +31,7 @@
 #include <linux/spinlock.h>
 #include <linux/pm.h>
 #include <linux/pci.h>
+#include <linux/pci-acpi.h>
 #include <linux/acpi.h>
 #include <acpi/acpi_bus.h>
 #include <acpi/acpi_drivers.h>
@@ -193,6 +194,7 @@ static int __devinit acpi_pci_root_add(struct acpi_device *device)
 	unsigned long long value = 0;
 	acpi_handle handle = NULL;
 	struct acpi_device *child;
+	u32 flags, base_flags;
 
 
 	if (!device)
@@ -210,6 +212,13 @@ static int __devinit acpi_pci_root_add(struct acpi_device *device)
 
 	device->ops.bind = acpi_pci_bind;
 
+	/*
+	 * All supported architectures that use ACPI have support for
+	 * PCI domains, so we indicate this in _OSC support capabilities.
+	 */
+	flags = base_flags = OSC_PCI_SEGMENT_GROUPS_SUPPORT;
+	pci_acpi_osc_support(device->handle, flags);
+
 	/* 
 	 * Segment
 	 * -------
@@ -335,6 +344,17 @@ static int __devinit acpi_pci_root_add(struct acpi_device *device)
 	list_for_each_entry(child, &device->children, node)
 		acpi_pci_bridge_scan(child);
 
+	/* Indicate support for various _OSC capabilities. */
+	if (pci_ext_cfg_avail(root->bus->self))
+		flags |= OSC_EXT_PCI_CONFIG_SUPPORT;
+	if (pcie_aspm_enabled())
+		flags |= OSC_ACTIVE_STATE_PWR_SUPPORT |
+			OSC_CLOCK_PWR_CAPABILITY_SUPPORT;
+	if (pci_msi_enabled())
+		flags |= OSC_MSI_SUPPORT;
+	if (flags != base_flags)
+		pci_acpi_osc_support(device->handle, flags);
+
       end:
 	if (result) {
 		if (!list_empty(&root->node))
diff --git a/drivers/acpi/sleep/main.c b/drivers/acpi/sleep/main.c
index 28a691cc625e..14b21b6d1f20 100644
--- a/drivers/acpi/sleep/main.c
+++ b/drivers/acpi/sleep/main.c
@@ -102,6 +102,20 @@ void __init acpi_old_suspend_ordering(void)
  */
 static bool set_sci_en_on_resume;
 
+/*
+ * The ACPI specification wants us to save NVS memory regions during hibernation
+ * and to restore them during the subsequent resume.  However, it is not certain
+ * if this mechanism is going to work on all machines, so we allow the user to
+ * disable this mechanism using the 'acpi_sleep=s4_nonvs' kernel command line
+ * option.
+ */
+static bool s4_no_nvs;
+
+void __init acpi_s4_no_nvs(void)
+{
+	s4_no_nvs = true;
+}
+
 /**
  *	acpi_pm_disable_gpes - Disable the GPEs.
  */
@@ -394,9 +408,25 @@ void __init acpi_no_s4_hw_signature(void)
 
 static int acpi_hibernation_begin(void)
 {
-	acpi_target_sleep_state = ACPI_STATE_S4;
-	acpi_sleep_tts_switch(acpi_target_sleep_state);
-	return 0;
+	int error;
+
+	error = s4_no_nvs ? 0 : hibernate_nvs_alloc();
+	if (!error) {
+		acpi_target_sleep_state = ACPI_STATE_S4;
+		acpi_sleep_tts_switch(acpi_target_sleep_state);
+	}
+
+	return error;
+}
+
+static int acpi_hibernation_pre_snapshot(void)
+{
+	int error = acpi_pm_prepare();
+
+	if (!error)
+		hibernate_nvs_save();
+
+	return error;
 }
 
 static int acpi_hibernation_enter(void)
@@ -417,6 +447,12 @@ static int acpi_hibernation_enter(void)
 	return ACPI_SUCCESS(status) ? 0 : -EFAULT;
 }
 
+static void acpi_hibernation_finish(void)
+{
+	hibernate_nvs_free();
+	acpi_pm_finish();
+}
+
 static void acpi_hibernation_leave(void)
 {
 	/*
@@ -432,6 +468,8 @@ static void acpi_hibernation_leave(void)
 			"cannot resume!\n");
 		panic("ACPI S4 hardware signature mismatch");
 	}
+	/* Restore the NVS memory area */
+	hibernate_nvs_restore();
 }
 
 static void acpi_pm_enable_gpes(void)
@@ -442,8 +480,8 @@ static void acpi_pm_enable_gpes(void)
 static struct platform_hibernation_ops acpi_hibernation_ops = {
 	.begin = acpi_hibernation_begin,
 	.end = acpi_pm_end,
-	.pre_snapshot = acpi_pm_prepare,
-	.finish = acpi_pm_finish,
+	.pre_snapshot = acpi_hibernation_pre_snapshot,
+	.finish = acpi_hibernation_finish,
 	.prepare = acpi_pm_prepare,
 	.enter = acpi_hibernation_enter,
 	.leave = acpi_hibernation_leave,
@@ -469,8 +507,22 @@ static int acpi_hibernation_begin_old(void)
 
 	error = acpi_sleep_prepare(ACPI_STATE_S4);
 
+	if (!error) {
+		if (!s4_no_nvs)
+			error = hibernate_nvs_alloc();
+		if (!error)
+			acpi_target_sleep_state = ACPI_STATE_S4;
+	}
+	return error;
+}
+
+static int acpi_hibernation_pre_snapshot_old(void)
+{
+	int error = acpi_pm_disable_gpes();
+
 	if (!error)
-		acpi_target_sleep_state = ACPI_STATE_S4;
+		hibernate_nvs_save();
+
 	return error;
 }
 
@@ -481,8 +533,8 @@ static int acpi_hibernation_begin_old(void)
 static struct platform_hibernation_ops acpi_hibernation_ops_old = {
 	.begin = acpi_hibernation_begin_old,
 	.end = acpi_pm_end,
-	.pre_snapshot = acpi_pm_disable_gpes,
-	.finish = acpi_pm_finish,
+	.pre_snapshot = acpi_hibernation_pre_snapshot_old,
+	.finish = acpi_hibernation_finish,
 	.prepare = acpi_pm_disable_gpes,
 	.enter = acpi_hibernation_enter,
 	.leave = acpi_hibernation_leave,
diff --git a/drivers/acpi/tables/tbfadt.c b/drivers/acpi/tables/tbfadt.c
index 2817158fb6a1..14661a861c58 100644
--- a/drivers/acpi/tables/tbfadt.c
+++ b/drivers/acpi/tables/tbfadt.c
@@ -48,7 +48,7 @@
 ACPI_MODULE_NAME("tbfadt")
 
 /* Local prototypes */
-static void inline
+static inline void
 acpi_tb_init_generic_address(struct acpi_generic_address *generic_address,
 			     u8 byte_width, u64 address);
 
@@ -122,7 +122,7 @@ static struct acpi_fadt_info fadt_info_table[] = {
  *
  ******************************************************************************/
 
-static void inline
+static inline void
 acpi_tb_init_generic_address(struct acpi_generic_address *generic_address,
 			     u8 byte_width, u64 address)
 {
@@ -286,14 +286,27 @@ static void acpi_tb_convert_fadt(void)
 
 	acpi_gbl_FADT.header.length = sizeof(struct acpi_table_fadt);
 
-	/* Expand the 32-bit FACS and DSDT addresses to 64-bit as necessary */
-
+	/*
+	 * Expand the 32-bit FACS and DSDT addresses to 64-bit as necessary.
+	 * Later code will always use the X 64-bit field. Also, check for an
+	 * address mismatch between the 32-bit and 64-bit address fields
+	 * (FIRMWARE_CTRL/X_FIRMWARE_CTRL, DSDT/X_DSDT) which would indicate
+	 * the presence of two FACS or two DSDT tables.
+	 */
 	if (!acpi_gbl_FADT.Xfacs) {
 		acpi_gbl_FADT.Xfacs = (u64) acpi_gbl_FADT.facs;
+	} else if (acpi_gbl_FADT.facs &&
+		   (acpi_gbl_FADT.Xfacs != (u64) acpi_gbl_FADT.facs)) {
+		ACPI_WARNING((AE_INFO,
+		    "32/64 FACS address mismatch in FADT - two FACS tables!"));
 	}
 
 	if (!acpi_gbl_FADT.Xdsdt) {
 		acpi_gbl_FADT.Xdsdt = (u64) acpi_gbl_FADT.dsdt;
+	} else if (acpi_gbl_FADT.dsdt &&
+		   (acpi_gbl_FADT.Xdsdt != (u64) acpi_gbl_FADT.dsdt)) {
+		ACPI_WARNING((AE_INFO,
+		    "32/64 DSDT address mismatch in FADT - two DSDT tables!"));
 	}
 
 	/*
diff --git a/drivers/acpi/tables/tbutils.c b/drivers/acpi/tables/tbutils.c
index 0cc92ef5236f..50e677711e5b 100644
--- a/drivers/acpi/tables/tbutils.c
+++ b/drivers/acpi/tables/tbutils.c
@@ -113,6 +113,30 @@ acpi_tb_check_xsdt(acpi_physical_address address)
 
 /*******************************************************************************
  *
+ * FUNCTION:    acpi_tb_initialize_facs
+ *
+ * PARAMETERS:  None
+ *
+ * RETURN:      Status
+ *
+ * DESCRIPTION: Create a permanent mapping for the FADT and save it in a global
+ *              for accessing the Global Lock and Firmware Waking Vector
+ *
+ ******************************************************************************/
+
+acpi_status acpi_tb_initialize_facs(void)
+{
+	acpi_status status;
+
+	status = acpi_get_table_by_index(ACPI_TABLE_INDEX_FACS,
+					 ACPI_CAST_INDIRECT_PTR(struct
+								acpi_table_header,
+								&acpi_gbl_FACS));
+	return status;
+}
+
+/*******************************************************************************
+ *
  * FUNCTION:    acpi_tb_tables_loaded
  *
  * PARAMETERS:  None
diff --git a/drivers/acpi/utilities/uteval.c b/drivers/acpi/utilities/uteval.c
index 352747e49c7a..df2b511b595a 100644
--- a/drivers/acpi/utilities/uteval.c
+++ b/drivers/acpi/utilities/uteval.c
@@ -129,7 +129,7 @@ acpi_status acpi_ut_osi_implementation(struct acpi_walk_state *walk_state)
 
 			/* The interface is supported */
 
-			return_ACPI_STATUS(AE_CTRL_TERMINATE);
+			return_ACPI_STATUS(AE_OK);
 		}
 	}
 
@@ -143,13 +143,13 @@ acpi_status acpi_ut_osi_implementation(struct acpi_walk_state *walk_state)
 
 		/* The interface is supported */
 
-		return_ACPI_STATUS(AE_CTRL_TERMINATE);
+		return_ACPI_STATUS(AE_OK);
 	}
 
 	/* The interface is not supported */
 
 	return_desc->integer.value = 0;
-	return_ACPI_STATUS(AE_CTRL_TERMINATE);
+	return_ACPI_STATUS(AE_OK);
 }
 
 /*******************************************************************************
diff --git a/drivers/acpi/utilities/utglobal.c b/drivers/acpi/utilities/utglobal.c
index 670551b95e56..f06a2aa50e57 100644
--- a/drivers/acpi/utilities/utglobal.c
+++ b/drivers/acpi/utilities/utglobal.c
@@ -352,7 +352,7 @@ const char *acpi_gbl_region_types[ACPI_NUM_PREDEFINED_REGIONS] = {
 	"PCI_Config",
 	"EmbeddedControl",
 	"SMBus",
-	"CMOS",
+	"SystemCMOS",
 	"PCIBARTarget",
 	"DataTable"
 };
@@ -771,6 +771,7 @@ acpi_status acpi_ut_init_globals(void)
 	acpi_gbl_global_lock_mutex = NULL;
 	acpi_gbl_global_lock_acquired = FALSE;
 	acpi_gbl_global_lock_handle = 0;
+	acpi_gbl_global_lock_present = FALSE;
 
 	/* Miscellaneous variables */
 
diff --git a/drivers/acpi/utilities/utxface.c b/drivers/acpi/utilities/utxface.c
index c198a4d40583..7ca8952eb1b8 100644
--- a/drivers/acpi/utilities/utxface.c
+++ b/drivers/acpi/utilities/utxface.c
@@ -45,6 +45,7 @@
 #include <acpi/acevents.h>
 #include <acpi/acnamesp.h>
 #include <acpi/acdebug.h>
+#include <acpi/actables.h>
 
 #define _COMPONENT          ACPI_UTILITIES
 ACPI_MODULE_NAME("utxface")
@@ -148,6 +149,16 @@ acpi_status acpi_enable_subsystem(u32 flags)
 	}
 
 	/*
+	 * Obtain a permanent mapping for the FACS. This is required for the
+	 * Global Lock and the Firmware Waking Vector
+	 */
+	status = acpi_tb_initialize_facs();
+	if (ACPI_FAILURE(status)) {
+		ACPI_WARNING((AE_INFO, "Could not map the FACS table"));
+		return_ACPI_STATUS(status);
+	}
+
+	/*
 	 * Install the default op_region handlers. These are installed unless
 	 * other handlers have already been installed via the
 	 * install_address_space_handler interface.
diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c
index a67b8e7c712d..656448c7fef9 100644
--- a/drivers/ata/ahci.c
+++ b/drivers/ata/ahci.c
@@ -1119,14 +1119,14 @@ static void ahci_start_port(struct ata_port *ap)
 
 	/* turn on LEDs */
 	if (ap->flags & ATA_FLAG_EM) {
-		ata_port_for_each_link(link, ap) {
+		ata_for_each_link(link, ap, EDGE) {
 			emp = &pp->em_priv[link->pmp];
 			ahci_transmit_led_message(ap, emp->led_state, 4);
 		}
 	}
 
 	if (ap->flags & ATA_FLAG_SW_ACTIVITY)
-		ata_port_for_each_link(link, ap)
+		ata_for_each_link(link, ap, EDGE)
 			ahci_init_sw_activity(link);
 
 }
@@ -1361,7 +1361,7 @@ static ssize_t ahci_led_show(struct ata_port *ap, char *buf)
 	struct ahci_em_priv *emp;
 	int rc = 0;
 
-	ata_port_for_each_link(link, ap) {
+	ata_for_each_link(link, ap, EDGE) {
 		emp = &pp->em_priv[link->pmp];
 		rc += sprintf(buf, "%lx\n", emp->led_state);
 	}
@@ -1941,7 +1941,7 @@ static void ahci_error_intr(struct ata_port *ap, u32 irq_stat)
 	u32 serror;
 
 	/* determine active link */
-	ata_port_for_each_link(link, ap)
+	ata_for_each_link(link, ap, EDGE)
 		if (ata_link_active(link))
 			break;
 	if (!link)
diff --git a/drivers/ata/ata_generic.c b/drivers/ata/ata_generic.c
index 5c33767e66de..dc48a6398abe 100644
--- a/drivers/ata/ata_generic.c
+++ b/drivers/ata/ata_generic.c
@@ -57,10 +57,7 @@ static int generic_set_mode(struct ata_link *link, struct ata_device **unused)
 	if (pdev->vendor == PCI_VENDOR_ID_CENATEK)
 		dma_enabled = 0xFF;
 
-	ata_link_for_each_dev(dev, link) {
-		if (!ata_dev_enabled(dev))
-			continue;
-
+	ata_for_each_dev(dev, link, ENABLED) {
 		/* We don't really care */
 		dev->pio_mode = XFER_PIO_0;
 		dev->dma_mode = XFER_MW_DMA_0;
diff --git a/drivers/ata/libata-acpi.c b/drivers/ata/libata-acpi.c
index c012307d0ba6..ef02e488d468 100644
--- a/drivers/ata/libata-acpi.c
+++ b/drivers/ata/libata-acpi.c
@@ -89,7 +89,7 @@ void ata_acpi_associate_sata_port(struct ata_port *ap)
 
 		ap->link.device->acpi_handle = NULL;
 
-		ata_port_for_each_link(link, ap) {
+		ata_for_each_link(link, ap, EDGE) {
 			acpi_integer adr = SATA_ADR(ap->port_no, link->pmp);
 
 			link->device->acpi_handle =
@@ -129,8 +129,8 @@ static void ata_acpi_detach_device(struct ata_port *ap, struct ata_device *dev)
 		struct ata_link *tlink;
 		struct ata_device *tdev;
 
-		ata_port_for_each_link(tlink, ap)
-			ata_link_for_each_dev(tdev, tlink)
+		ata_for_each_link(tlink, ap, EDGE)
+			ata_for_each_dev(tdev, tlink, ALL)
 				tdev->flags |= ATA_DFLAG_DETACH;
 	}
 
@@ -588,12 +588,9 @@ int ata_acpi_cbl_80wire(struct ata_port *ap, const struct ata_acpi_gtm *gtm)
 {
 	struct ata_device *dev;
 
-	ata_link_for_each_dev(dev, &ap->link) {
+	ata_for_each_dev(dev, &ap->link, ENABLED) {
 		unsigned long xfer_mask, udma_mask;
 
-		if (!ata_dev_enabled(dev))
-			continue;
-
 		xfer_mask = ata_acpi_gtm_xfermask(dev, gtm);
 		ata_unpack_xfermask(xfer_mask, NULL, NULL, &udma_mask);
 
@@ -893,7 +890,7 @@ void ata_acpi_on_resume(struct ata_port *ap)
 		 * use values set by _STM.  Cache _GTF result and
 		 * schedule _GTF.
 		 */
-		ata_link_for_each_dev(dev, &ap->link) {
+		ata_for_each_dev(dev, &ap->link, ALL) {
 			ata_acpi_clear_gtf(dev);
 			if (ata_dev_enabled(dev) &&
 			    ata_dev_get_GTF(dev, NULL) >= 0)
@@ -904,7 +901,7 @@ void ata_acpi_on_resume(struct ata_port *ap)
 		 * there's no reason to evaluate IDE _GTF early
 		 * without _STM.  Clear cache and schedule _GTF.
 		 */
-		ata_link_for_each_dev(dev, &ap->link) {
+		ata_for_each_dev(dev, &ap->link, ALL) {
 			ata_acpi_clear_gtf(dev);
 			if (ata_dev_enabled(dev))
 				dev->flags |= ATA_DFLAG_ACPI_PENDING;
@@ -932,8 +929,8 @@ void ata_acpi_set_state(struct ata_port *ap, pm_message_t state)
 	if (state.event == PM_EVENT_ON)
 		acpi_bus_set_power(ap->acpi_handle, ACPI_STATE_D0);
 
-	ata_link_for_each_dev(dev, &ap->link) {
-		if (dev->acpi_handle && ata_dev_enabled(dev))
+	ata_for_each_dev(dev, &ap->link, ENABLED) {
+		if (dev->acpi_handle)
 			acpi_bus_set_power(dev->acpi_handle,
 				state.event == PM_EVENT_ON ?
 					ACPI_STATE_D0 : ACPI_STATE_D3);
diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index 5e2eb740df46..ad844fb325ae 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -163,43 +163,119 @@ MODULE_LICENSE("GPL");
 MODULE_VERSION(DRV_VERSION);
 
 
-/*
- * Iterator helpers.  Don't use directly.
+/**
+ *	ata_link_next - link iteration helper
+ *	@link: the previous link, NULL to start
+ *	@ap: ATA port containing links to iterate
+ *	@mode: iteration mode, one of ATA_LITER_*
+ *
+ *	LOCKING:
+ *	Host lock or EH context.
  *
- * LOCKING:
- * Host lock or EH context.
+ *	RETURNS:
+ *	Pointer to the next link.
  */
-struct ata_link *__ata_port_next_link(struct ata_port *ap,
-				      struct ata_link *link, bool dev_only)
+struct ata_link *ata_link_next(struct ata_link *link, struct ata_port *ap,
+			       enum ata_link_iter_mode mode)
 {
+	BUG_ON(mode != ATA_LITER_EDGE &&
+	       mode != ATA_LITER_PMP_FIRST && mode != ATA_LITER_HOST_FIRST);
+
 	/* NULL link indicates start of iteration */
-	if (!link) {
-		if (dev_only && sata_pmp_attached(ap))
-			return ap->pmp_link;
-		return &ap->link;
-	}
+	if (!link)
+		switch (mode) {
+		case ATA_LITER_EDGE:
+		case ATA_LITER_PMP_FIRST:
+			if (sata_pmp_attached(ap))
+				return ap->pmp_link;
+			/* fall through */
+		case ATA_LITER_HOST_FIRST:
+			return &ap->link;
+		}
 
-	/* we just iterated over the host master link, what's next? */
-	if (link == &ap->link) {
-		if (!sata_pmp_attached(ap)) {
-			if (unlikely(ap->slave_link) && !dev_only)
+	/* we just iterated over the host link, what's next? */
+	if (link == &ap->link)
+		switch (mode) {
+		case ATA_LITER_HOST_FIRST:
+			if (sata_pmp_attached(ap))
+				return ap->pmp_link;
+			/* fall through */
+		case ATA_LITER_PMP_FIRST:
+			if (unlikely(ap->slave_link))
 				return ap->slave_link;
+			/* fall through */
+		case ATA_LITER_EDGE:
 			return NULL;
 		}
-		return ap->pmp_link;
-	}
 
 	/* slave_link excludes PMP */
 	if (unlikely(link == ap->slave_link))
 		return NULL;
 
-	/* iterate to the next PMP link */
+	/* we were over a PMP link */
 	if (++link < ap->pmp_link + ap->nr_pmp_links)
 		return link;
+
+	if (mode == ATA_LITER_PMP_FIRST)
+		return &ap->link;
+
 	return NULL;
 }
 
 /**
+ *	ata_dev_next - device iteration helper
+ *	@dev: the previous device, NULL to start
+ *	@link: ATA link containing devices to iterate
+ *	@mode: iteration mode, one of ATA_DITER_*
+ *
+ *	LOCKING:
+ *	Host lock or EH context.
+ *
+ *	RETURNS:
+ *	Pointer to the next device.
+ */
+struct ata_device *ata_dev_next(struct ata_device *dev, struct ata_link *link,
+				enum ata_dev_iter_mode mode)
+{
+	BUG_ON(mode != ATA_DITER_ENABLED && mode != ATA_DITER_ENABLED_REVERSE &&
+	       mode != ATA_DITER_ALL && mode != ATA_DITER_ALL_REVERSE);
+
+	/* NULL dev indicates start of iteration */
+	if (!dev)
+		switch (mode) {
+		case ATA_DITER_ENABLED:
+		case ATA_DITER_ALL:
+			dev = link->device;
+			goto check;
+		case ATA_DITER_ENABLED_REVERSE:
+		case ATA_DITER_ALL_REVERSE:
+			dev = link->device + ata_link_max_devices(link) - 1;
+			goto check;
+		}
+
+ next:
+	/* move to the next one */
+	switch (mode) {
+	case ATA_DITER_ENABLED:
+	case ATA_DITER_ALL:
+		if (++dev < link->device + ata_link_max_devices(link))
+			goto check;
+		return NULL;
+	case ATA_DITER_ENABLED_REVERSE:
+	case ATA_DITER_ALL_REVERSE:
+		if (--dev >= link->device)
+			goto check;
+		return NULL;
+	}
+
+ check:
+	if ((mode == ATA_DITER_ENABLED || mode == ATA_DITER_ENABLED_REVERSE) &&
+	    !ata_dev_enabled(dev))
+		goto next;
+	return dev;
+}
+
+/**
  *	ata_dev_phys_link - find physical link for a device
  *	@dev: ATA device to look up physical link for
  *
@@ -1107,8 +1183,8 @@ static void ata_lpm_enable(struct ata_host *host)
 
 	for (i = 0; i < host->n_ports; i++) {
 		ap = host->ports[i];
-		ata_port_for_each_link(link, ap) {
-			ata_link_for_each_dev(dev, link)
+		ata_for_each_link(link, ap, EDGE) {
+			ata_for_each_dev(dev, link, ALL)
 				ata_dev_disable_pm(dev);
 		}
 	}
@@ -2594,11 +2670,11 @@ int ata_bus_probe(struct ata_port *ap)
 
 	ata_port_probe(ap);
 
-	ata_link_for_each_dev(dev, &ap->link)
+	ata_for_each_dev(dev, &ap->link, ALL)
 		tries[dev->devno] = ATA_PROBE_MAX_TRIES;
 
  retry:
-	ata_link_for_each_dev(dev, &ap->link) {
+	ata_for_each_dev(dev, &ap->link, ALL) {
 		/* If we issue an SRST then an ATA drive (not ATAPI)
 		 * may change configuration and be in PIO0 timing. If
 		 * we do a hard reset (or are coming from power on)
@@ -2620,7 +2696,7 @@ int ata_bus_probe(struct ata_port *ap)
 	/* reset and determine device classes */
 	ap->ops->phy_reset(ap);
 
-	ata_link_for_each_dev(dev, &ap->link) {
+	ata_for_each_dev(dev, &ap->link, ALL) {
 		if (!(ap->flags & ATA_FLAG_DISABLED) &&
 		    dev->class != ATA_DEV_UNKNOWN)
 			classes[dev->devno] = dev->class;
@@ -2636,7 +2712,7 @@ int ata_bus_probe(struct ata_port *ap)
 	   specific sequence bass-ackwards so that PDIAG- is released by
 	   the slave device */
 
-	ata_link_for_each_dev_reverse(dev, &ap->link) {
+	ata_for_each_dev(dev, &ap->link, ALL_REVERSE) {
 		if (tries[dev->devno])
 			dev->class = classes[dev->devno];
 
@@ -2653,24 +2729,19 @@ int ata_bus_probe(struct ata_port *ap)
 	if (ap->ops->cable_detect)
 		ap->cbl = ap->ops->cable_detect(ap);
 
-	/* We may have SATA bridge glue hiding here irrespective of the
-	   reported cable types and sensed types */
-	ata_link_for_each_dev(dev, &ap->link) {
-		if (!ata_dev_enabled(dev))
-			continue;
-		/* SATA drives indicate we have a bridge. We don't know which
-		   end of the link the bridge is which is a problem */
+	/* We may have SATA bridge glue hiding here irrespective of
+	 * the reported cable types and sensed types.  When SATA
+	 * drives indicate we have a bridge, we don't know which end
+	 * of the link the bridge is which is a problem.
+	 */
+	ata_for_each_dev(dev, &ap->link, ENABLED)
 		if (ata_id_is_sata(dev->id))
 			ap->cbl = ATA_CBL_SATA;
-	}
 
 	/* After the identify sequence we can now set up the devices. We do
 	   this in the normal order so that the user doesn't get confused */
 
-	ata_link_for_each_dev(dev, &ap->link) {
-		if (!ata_dev_enabled(dev))
-			continue;
-
+	ata_for_each_dev(dev, &ap->link, ENABLED) {
 		ap->link.eh_context.i.flags |= ATA_EHI_PRINTINFO;
 		rc = ata_dev_configure(dev);
 		ap->link.eh_context.i.flags &= ~ATA_EHI_PRINTINFO;
@@ -2683,9 +2754,8 @@ int ata_bus_probe(struct ata_port *ap)
 	if (rc)
 		goto fail;
 
-	ata_link_for_each_dev(dev, &ap->link)
-		if (ata_dev_enabled(dev))
-			return 0;
+	ata_for_each_dev(dev, &ap->link, ENABLED)
+		return 0;
 
 	/* no device present, disable port */
 	ata_port_disable(ap);
@@ -3331,13 +3401,10 @@ int ata_do_set_mode(struct ata_link *link, struct ata_device **r_failed_dev)
 	int rc = 0, used_dma = 0, found = 0;
 
 	/* step 1: calculate xfer_mask */
-	ata_link_for_each_dev(dev, link) {
+	ata_for_each_dev(dev, link, ENABLED) {
 		unsigned long pio_mask, dma_mask;
 		unsigned int mode_mask;
 
-		if (!ata_dev_enabled(dev))
-			continue;
-
 		mode_mask = ATA_DMA_MASK_ATA;
 		if (dev->class == ATA_DEV_ATAPI)
 			mode_mask = ATA_DMA_MASK_ATAPI;
@@ -3366,10 +3433,7 @@ int ata_do_set_mode(struct ata_link *link, struct ata_device **r_failed_dev)
 		goto out;
 
 	/* step 2: always set host PIO timings */
-	ata_link_for_each_dev(dev, link) {
-		if (!ata_dev_enabled(dev))
-			continue;
-
+	ata_for_each_dev(dev, link, ENABLED) {
 		if (dev->pio_mode == 0xff) {
 			ata_dev_printk(dev, KERN_WARNING, "no PIO support\n");
 			rc = -EINVAL;
@@ -3383,8 +3447,8 @@ int ata_do_set_mode(struct ata_link *link, struct ata_device **r_failed_dev)
 	}
 
 	/* step 3: set host DMA timings */
-	ata_link_for_each_dev(dev, link) {
-		if (!ata_dev_enabled(dev) || !ata_dma_enabled(dev))
+	ata_for_each_dev(dev, link, ENABLED) {
+		if (!ata_dma_enabled(dev))
 			continue;
 
 		dev->xfer_mode = dev->dma_mode;
@@ -3394,11 +3458,7 @@ int ata_do_set_mode(struct ata_link *link, struct ata_device **r_failed_dev)
 	}
 
 	/* step 4: update devices' xfer mode */
-	ata_link_for_each_dev(dev, link) {
-		/* don't update suspended devices' xfer mode */
-		if (!ata_dev_enabled(dev))
-			continue;
-
+	ata_for_each_dev(dev, link, ENABLED) {
 		rc = ata_dev_set_mode(dev);
 		if (rc)
 			goto out;
@@ -4210,9 +4270,9 @@ static int cable_is_40wire(struct ata_port *ap)
 	 * - if you have a non detect capable drive you don't want it
 	 *   to colour the choice
 	 */
-	ata_port_for_each_link(link, ap) {
-		ata_link_for_each_dev(dev, link) {
-			if (ata_dev_enabled(dev) && !ata_is_40wire(dev))
+	ata_for_each_link(link, ap, EDGE) {
+		ata_for_each_dev(dev, link, ENABLED) {
+			if (!ata_is_40wire(dev))
 				return 0;
 		}
 	}
@@ -4619,7 +4679,6 @@ static struct ata_queued_cmd *ata_qc_new(struct ata_port *ap)
 /**
  *	ata_qc_new_init - Request an available ATA command, and initialize it
  *	@dev: Device from whom we request an available command structure
- *	@tag: command tag
  *
  *	LOCKING:
  *	None.
@@ -5165,7 +5224,7 @@ static int ata_host_request_pm(struct ata_host *host, pm_message_t mesg,
 		}
 
 		ap->pflags |= ATA_PFLAG_PM_PENDING;
-		__ata_port_for_each_link(link, ap) {
+		ata_for_each_link(link, ap, HOST_FIRST) {
 			link->eh_info.action |= action;
 			link->eh_info.flags |= ehi_flags;
 		}
@@ -5994,8 +6053,6 @@ int ata_host_activate(struct ata_host *host, int irq,
 static void ata_port_detach(struct ata_port *ap)
 {
 	unsigned long flags;
-	struct ata_link *link;
-	struct ata_device *dev;
 
 	if (!ap->ops->error_handler)
 		goto skip_eh;
@@ -6003,28 +6060,15 @@ static void ata_port_detach(struct ata_port *ap)
 	/* tell EH we're leaving & flush EH */
 	spin_lock_irqsave(ap->lock, flags);
 	ap->pflags |= ATA_PFLAG_UNLOADING;
+	ata_port_schedule_eh(ap);
 	spin_unlock_irqrestore(ap->lock, flags);
 
+	/* wait till EH commits suicide */
 	ata_port_wait_eh(ap);
 
-	/* EH is now guaranteed to see UNLOADING - EH context belongs
-	 * to us.  Restore SControl and disable all existing devices.
-	 */
-	__ata_port_for_each_link(link, ap) {
-		sata_scr_write(link, SCR_CONTROL, link->saved_scontrol & 0xff0);
-		ata_link_for_each_dev(dev, link)
-			ata_dev_disable(dev);
-	}
+	/* it better be dead now */
+	WARN_ON(!(ap->pflags & ATA_PFLAG_UNLOADED));
 
-	/* Final freeze & EH.  All in-flight commands are aborted.  EH
-	 * will be skipped and retrials will be terminated with bad
-	 * target.
-	 */
-	spin_lock_irqsave(ap->lock, flags);
-	ata_port_freeze(ap);	/* won't be thawed */
-	spin_unlock_irqrestore(ap->lock, flags);
-
-	ata_port_wait_eh(ap);
 	cancel_rearming_delayed_work(&ap->hotplug_task);
 
  skip_eh:
@@ -6475,7 +6519,8 @@ EXPORT_SYMBOL_GPL(ata_base_port_ops);
 EXPORT_SYMBOL_GPL(sata_port_ops);
 EXPORT_SYMBOL_GPL(ata_dummy_port_ops);
 EXPORT_SYMBOL_GPL(ata_dummy_port_info);
-EXPORT_SYMBOL_GPL(__ata_port_next_link);
+EXPORT_SYMBOL_GPL(ata_link_next);
+EXPORT_SYMBOL_GPL(ata_dev_next);
 EXPORT_SYMBOL_GPL(ata_std_bios_param);
 EXPORT_SYMBOL_GPL(ata_host_init);
 EXPORT_SYMBOL_GPL(ata_host_alloc);
diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c
index 32da9a93ce44..8147a8386370 100644
--- a/drivers/ata/libata-eh.c
+++ b/drivers/ata/libata-eh.c
@@ -422,7 +422,7 @@ static void ata_eh_clear_action(struct ata_link *link, struct ata_device *dev,
 
 	if (!dev) {
 		ehi->action &= ~action;
-		ata_link_for_each_dev(tdev, link)
+		ata_for_each_dev(tdev, link, ALL)
 			ehi->dev_action[tdev->devno] &= ~action;
 	} else {
 		/* doesn't make sense for port-wide EH actions */
@@ -430,7 +430,7 @@ static void ata_eh_clear_action(struct ata_link *link, struct ata_device *dev,
 
 		/* break ehi->action into ehi->dev_action */
 		if (ehi->action & action) {
-			ata_link_for_each_dev(tdev, link)
+			ata_for_each_dev(tdev, link, ALL)
 				ehi->dev_action[tdev->devno] |=
 					ehi->action & action;
 			ehi->action &= ~action;
@@ -491,6 +491,31 @@ enum blk_eh_timer_return ata_scsi_timed_out(struct scsi_cmnd *cmd)
 	return ret;
 }
 
+static void ata_eh_unload(struct ata_port *ap)
+{
+	struct ata_link *link;
+	struct ata_device *dev;
+	unsigned long flags;
+
+	/* Restore SControl IPM and SPD for the next driver and
+	 * disable attached devices.
+	 */
+	ata_for_each_link(link, ap, PMP_FIRST) {
+		sata_scr_write(link, SCR_CONTROL, link->saved_scontrol & 0xff0);
+		ata_for_each_dev(dev, link, ALL)
+			ata_dev_disable(dev);
+	}
+
+	/* freeze and set UNLOADED */
+	spin_lock_irqsave(ap->lock, flags);
+
+	ata_port_freeze(ap);			/* won't be thawed */
+	ap->pflags &= ~ATA_PFLAG_EH_PENDING;	/* clear pending from freeze */
+	ap->pflags |= ATA_PFLAG_UNLOADED;
+
+	spin_unlock_irqrestore(ap->lock, flags);
+}
+
 /**
  *	ata_scsi_error - SCSI layer error handler callback
  *	@host: SCSI host on which error occurred
@@ -592,7 +617,7 @@ void ata_scsi_error(struct Scsi_Host *host)
 		/* fetch & clear EH info */
 		spin_lock_irqsave(ap->lock, flags);
 
-		__ata_port_for_each_link(link, ap) {
+		ata_for_each_link(link, ap, HOST_FIRST) {
 			struct ata_eh_context *ehc = &link->eh_context;
 			struct ata_device *dev;
 
@@ -600,12 +625,9 @@ void ata_scsi_error(struct Scsi_Host *host)
 			link->eh_context.i = link->eh_info;
 			memset(&link->eh_info, 0, sizeof(link->eh_info));
 
-			ata_link_for_each_dev(dev, link) {
+			ata_for_each_dev(dev, link, ENABLED) {
 				int devno = dev->devno;
 
-				if (!ata_dev_enabled(dev))
-					continue;
-
 				ehc->saved_xfer_mode[devno] = dev->xfer_mode;
 				if (ata_ncq_enabled(dev))
 					ehc->saved_ncq_enabled |= 1 << devno;
@@ -621,8 +643,13 @@ void ata_scsi_error(struct Scsi_Host *host)
 		/* invoke EH, skip if unloading or suspended */
 		if (!(ap->pflags & (ATA_PFLAG_UNLOADING | ATA_PFLAG_SUSPENDED)))
 			ap->ops->error_handler(ap);
-		else
+		else {
+			/* if unloading, commence suicide */
+			if ((ap->pflags & ATA_PFLAG_UNLOADING) &&
+			    !(ap->pflags & ATA_PFLAG_UNLOADED))
+				ata_eh_unload(ap);
 			ata_eh_finish(ap);
+		}
 
 		/* process port suspend request */
 		ata_eh_handle_port_suspend(ap);
@@ -644,7 +671,7 @@ void ata_scsi_error(struct Scsi_Host *host)
 		}
 
 		/* this run is complete, make sure EH info is clear */
-		__ata_port_for_each_link(link, ap)
+		ata_for_each_link(link, ap, HOST_FIRST)
 			memset(&link->eh_info, 0, sizeof(link->eh_info));
 
 		/* Clear host_eh_scheduled while holding ap->lock such
@@ -1025,7 +1052,7 @@ int sata_async_notification(struct ata_port *ap)
 		struct ata_link *link;
 
 		/* check and notify ATAPI AN */
-		ata_port_for_each_link(link, ap) {
+		ata_for_each_link(link, ap, EDGE) {
 			if (!(sntf & (1 << link->pmp)))
 				continue;
 
@@ -2005,7 +2032,7 @@ void ata_eh_autopsy(struct ata_port *ap)
 {
 	struct ata_link *link;
 
-	ata_port_for_each_link(link, ap)
+	ata_for_each_link(link, ap, EDGE)
 		ata_eh_link_autopsy(link);
 
 	/* Handle the frigging slave link.  Autopsy is done similarly
@@ -2219,7 +2246,7 @@ void ata_eh_report(struct ata_port *ap)
 {
 	struct ata_link *link;
 
-	__ata_port_for_each_link(link, ap)
+	ata_for_each_link(link, ap, HOST_FIRST)
 		ata_eh_link_report(link);
 }
 
@@ -2230,7 +2257,7 @@ static int ata_do_reset(struct ata_link *link, ata_reset_fn_t reset,
 	struct ata_device *dev;
 
 	if (clear_classes)
-		ata_link_for_each_dev(dev, link)
+		ata_for_each_dev(dev, link, ALL)
 			classes[dev->devno] = ATA_DEV_UNKNOWN;
 
 	return reset(link, classes, deadline);
@@ -2294,7 +2321,7 @@ int ata_eh_reset(struct ata_link *link, int classify,
 
 	ata_eh_about_to_do(link, NULL, ATA_EH_RESET);
 
-	ata_link_for_each_dev(dev, link) {
+	ata_for_each_dev(dev, link, ALL) {
 		/* If we issue an SRST then an ATA drive (not ATAPI)
 		 * may change configuration and be in PIO0 timing. If
 		 * we do a hard reset (or are coming from power on)
@@ -2355,7 +2382,7 @@ int ata_eh_reset(struct ata_link *link, int classify,
 						"port disabled. ignoring.\n");
 				ehc->i.action &= ~ATA_EH_RESET;
 
-				ata_link_for_each_dev(dev, link)
+				ata_for_each_dev(dev, link, ALL)
 					classes[dev->devno] = ATA_DEV_NONE;
 
 				rc = 0;
@@ -2369,7 +2396,7 @@ int ata_eh_reset(struct ata_link *link, int classify,
 		 * bang classes and return.
 		 */
 		if (reset && !(ehc->i.action & ATA_EH_RESET)) {
-			ata_link_for_each_dev(dev, link)
+			ata_for_each_dev(dev, link, ALL)
 				classes[dev->devno] = ATA_DEV_NONE;
 			rc = 0;
 			goto out;
@@ -2454,7 +2481,7 @@ int ata_eh_reset(struct ata_link *link, int classify,
 	/*
 	 * Post-reset processing
 	 */
-	ata_link_for_each_dev(dev, link) {
+	ata_for_each_dev(dev, link, ALL) {
 		/* After the reset, the device state is PIO 0 and the
 		 * controller state is undefined.  Reset also wakes up
 		 * drives from sleeping mode.
@@ -2510,7 +2537,7 @@ int ata_eh_reset(struct ata_link *link, int classify,
 	 * can be reliably detected and retried.
 	 */
 	nr_unknown = 0;
-	ata_link_for_each_dev(dev, link) {
+	ata_for_each_dev(dev, link, ALL) {
 		/* convert all ATA_DEV_UNKNOWN to ATA_DEV_NONE */
 		if (classes[dev->devno] == ATA_DEV_UNKNOWN) {
 			classes[dev->devno] = ATA_DEV_NONE;
@@ -2619,8 +2646,8 @@ static inline void ata_eh_pull_park_action(struct ata_port *ap)
 
 	spin_lock_irqsave(ap->lock, flags);
 	INIT_COMPLETION(ap->park_req_pending);
-	ata_port_for_each_link(link, ap) {
-		ata_link_for_each_dev(dev, link) {
+	ata_for_each_link(link, ap, EDGE) {
+		ata_for_each_dev(dev, link, ALL) {
 			struct ata_eh_info *ehi = &link->eh_info;
 
 			link->eh_context.i.dev_action[dev->devno] |=
@@ -2675,7 +2702,7 @@ static int ata_eh_revalidate_and_attach(struct ata_link *link,
 	 * be done backwards such that PDIAG- is released by the slave
 	 * device before the master device is identified.
 	 */
-	ata_link_for_each_dev_reverse(dev, link) {
+	ata_for_each_dev(dev, link, ALL_REVERSE) {
 		unsigned int action = ata_eh_dev_action(dev);
 		unsigned int readid_flags = 0;
 
@@ -2744,7 +2771,7 @@ static int ata_eh_revalidate_and_attach(struct ata_link *link,
 	/* Configure new devices forward such that user doesn't see
 	 * device detection messages backwards.
 	 */
-	ata_link_for_each_dev(dev, link) {
+	ata_for_each_dev(dev, link, ALL) {
 		if (!(new_mask & (1 << dev->devno)) ||
 		    dev->class == ATA_DEV_PMP)
 			continue;
@@ -2793,10 +2820,7 @@ int ata_set_mode(struct ata_link *link, struct ata_device **r_failed_dev)
 	int rc;
 
 	/* if data transfer is verified, clear DUBIOUS_XFER on ering top */
-	ata_link_for_each_dev(dev, link) {
-		if (!ata_dev_enabled(dev))
-			continue;
-
+	ata_for_each_dev(dev, link, ENABLED) {
 		if (!(dev->flags & ATA_DFLAG_DUBIOUS_XFER)) {
 			struct ata_ering_entry *ent;
 
@@ -2813,14 +2837,11 @@ int ata_set_mode(struct ata_link *link, struct ata_device **r_failed_dev)
 		rc = ata_do_set_mode(link, r_failed_dev);
 
 	/* if transfer mode has changed, set DUBIOUS_XFER on device */
-	ata_link_for_each_dev(dev, link) {
+	ata_for_each_dev(dev, link, ENABLED) {
 		struct ata_eh_context *ehc = &link->eh_context;
 		u8 saved_xfer_mode = ehc->saved_xfer_mode[dev->devno];
 		u8 saved_ncq = !!(ehc->saved_ncq_enabled & (1 << dev->devno));
 
-		if (!ata_dev_enabled(dev))
-			continue;
-
 		if (dev->xfer_mode != saved_xfer_mode ||
 		    ata_ncq_enabled(dev) != saved_ncq)
 			dev->flags |= ATA_DFLAG_DUBIOUS_XFER;
@@ -2881,9 +2902,8 @@ static int ata_link_nr_enabled(struct ata_link *link)
 	struct ata_device *dev;
 	int cnt = 0;
 
-	ata_link_for_each_dev(dev, link)
-		if (ata_dev_enabled(dev))
-			cnt++;
+	ata_for_each_dev(dev, link, ENABLED)
+		cnt++;
 	return cnt;
 }
 
@@ -2892,7 +2912,7 @@ static int ata_link_nr_vacant(struct ata_link *link)
 	struct ata_device *dev;
 	int cnt = 0;
 
-	ata_link_for_each_dev(dev, link)
+	ata_for_each_dev(dev, link, ALL)
 		if (dev->class == ATA_DEV_UNKNOWN)
 			cnt++;
 	return cnt;
@@ -2918,7 +2938,7 @@ static int ata_eh_skip_recovery(struct ata_link *link)
 		return 0;
 
 	/* skip if class codes for all vacant slots are ATA_DEV_NONE */
-	ata_link_for_each_dev(dev, link) {
+	ata_for_each_dev(dev, link, ALL) {
 		if (dev->class == ATA_DEV_UNKNOWN &&
 		    ehc->classes[dev->devno] != ATA_DEV_NONE)
 			return 0;
@@ -3026,7 +3046,7 @@ int ata_eh_recover(struct ata_port *ap, ata_prereset_fn_t prereset,
 	DPRINTK("ENTER\n");
 
 	/* prep for recovery */
-	ata_port_for_each_link(link, ap) {
+	ata_for_each_link(link, ap, EDGE) {
 		struct ata_eh_context *ehc = &link->eh_context;
 
 		/* re-enable link? */
@@ -3038,7 +3058,7 @@ int ata_eh_recover(struct ata_port *ap, ata_prereset_fn_t prereset,
 			ata_eh_done(link, NULL, ATA_EH_ENABLE_LINK);
 		}
 
-		ata_link_for_each_dev(dev, link) {
+		ata_for_each_dev(dev, link, ALL) {
 			if (link->flags & ATA_LFLAG_NO_RETRY)
 				ehc->tries[dev->devno] = 1;
 			else
@@ -3068,19 +3088,19 @@ int ata_eh_recover(struct ata_port *ap, ata_prereset_fn_t prereset,
 		goto out;
 
 	/* prep for EH */
-	ata_port_for_each_link(link, ap) {
+	ata_for_each_link(link, ap, EDGE) {
 		struct ata_eh_context *ehc = &link->eh_context;
 
 		/* skip EH if possible. */
 		if (ata_eh_skip_recovery(link))
 			ehc->i.action = 0;
 
-		ata_link_for_each_dev(dev, link)
+		ata_for_each_dev(dev, link, ALL)
 			ehc->classes[dev->devno] = ATA_DEV_UNKNOWN;
 	}
 
 	/* reset */
-	ata_port_for_each_link(link, ap) {
+	ata_for_each_link(link, ap, EDGE) {
 		struct ata_eh_context *ehc = &link->eh_context;
 
 		if (!(ehc->i.action & ATA_EH_RESET))
@@ -3105,8 +3125,8 @@ int ata_eh_recover(struct ata_port *ap, ata_prereset_fn_t prereset,
 		ata_eh_pull_park_action(ap);
 
 		deadline = jiffies;
-		ata_port_for_each_link(link, ap) {
-			ata_link_for_each_dev(dev, link) {
+		ata_for_each_link(link, ap, EDGE) {
+			ata_for_each_dev(dev, link, ALL) {
 				struct ata_eh_context *ehc = &link->eh_context;
 				unsigned long tmp;
 
@@ -3134,8 +3154,8 @@ int ata_eh_recover(struct ata_port *ap, ata_prereset_fn_t prereset,
 		deadline = wait_for_completion_timeout(&ap->park_req_pending,
 						       deadline - now);
 	} while (deadline);
-	ata_port_for_each_link(link, ap) {
-		ata_link_for_each_dev(dev, link) {
+	ata_for_each_link(link, ap, EDGE) {
+		ata_for_each_dev(dev, link, ALL) {
 			if (!(link->eh_context.unloaded_mask &
 			      (1 << dev->devno)))
 				continue;
@@ -3146,7 +3166,7 @@ int ata_eh_recover(struct ata_port *ap, ata_prereset_fn_t prereset,
 	}
 
 	/* the rest */
-	ata_port_for_each_link(link, ap) {
+	ata_for_each_link(link, ap, EDGE) {
 		struct ata_eh_context *ehc = &link->eh_context;
 
 		/* revalidate existing devices and attach new ones */
@@ -3172,7 +3192,7 @@ int ata_eh_recover(struct ata_port *ap, ata_prereset_fn_t prereset,
 		 * disrupting the current users of the device.
 		 */
 		if (ehc->i.flags & ATA_EHI_DID_RESET) {
-			ata_link_for_each_dev(dev, link) {
+			ata_for_each_dev(dev, link, ALL) {
 				if (dev->class != ATA_DEV_ATAPI)
 					continue;
 				rc = atapi_eh_clear_ua(dev);
@@ -3183,7 +3203,7 @@ int ata_eh_recover(struct ata_port *ap, ata_prereset_fn_t prereset,
 
 		/* configure link power saving */
 		if (ehc->i.action & ATA_EH_LPM)
-			ata_link_for_each_dev(dev, link)
+			ata_for_each_dev(dev, link, ALL)
 				ata_dev_enable_pm(dev, ap->pm_policy);
 
 		/* this link is okay now */
@@ -3288,7 +3308,7 @@ void ata_do_eh(struct ata_port *ap, ata_prereset_fn_t prereset,
 	rc = ata_eh_recover(ap, prereset, softreset, hardreset, postreset,
 			    NULL);
 	if (rc) {
-		ata_link_for_each_dev(dev, &ap->link)
+		ata_for_each_dev(dev, &ap->link, ALL)
 			ata_dev_disable(dev);
 	}
 
diff --git a/drivers/ata/libata-pmp.c b/drivers/ata/libata-pmp.c
index b65db309c181..98ca07a2db87 100644
--- a/drivers/ata/libata-pmp.c
+++ b/drivers/ata/libata-pmp.c
@@ -321,7 +321,7 @@ static void sata_pmp_quirks(struct ata_port *ap)
 
 	if (vendor == 0x1095 && devid == 0x3726) {
 		/* sil3726 quirks */
-		ata_port_for_each_link(link, ap) {
+		ata_for_each_link(link, ap, EDGE) {
 			/* Class code report is unreliable and SRST
 			 * times out under certain configurations.
 			 */
@@ -336,7 +336,7 @@ static void sata_pmp_quirks(struct ata_port *ap)
 		}
 	} else if (vendor == 0x1095 && devid == 0x4723) {
 		/* sil4723 quirks */
-		ata_port_for_each_link(link, ap) {
+		ata_for_each_link(link, ap, EDGE) {
 			/* class code report is unreliable */
 			if (link->pmp < 2)
 				link->flags |= ATA_LFLAG_ASSUME_ATA;
@@ -348,7 +348,7 @@ static void sata_pmp_quirks(struct ata_port *ap)
 		}
 	} else if (vendor == 0x1095 && devid == 0x4726) {
 		/* sil4726 quirks */
-		ata_port_for_each_link(link, ap) {
+		ata_for_each_link(link, ap, EDGE) {
 			/* Class code report is unreliable and SRST
 			 * times out under certain configurations.
 			 * Config device can be at port 0 or 5 and
@@ -450,7 +450,7 @@ int sata_pmp_attach(struct ata_device *dev)
 	if (ap->ops->pmp_attach)
 		ap->ops->pmp_attach(ap);
 
-	ata_port_for_each_link(tlink, ap)
+	ata_for_each_link(tlink, ap, EDGE)
 		sata_link_init_spd(tlink);
 
 	ata_acpi_associate_sata_port(ap);
@@ -487,7 +487,7 @@ static void sata_pmp_detach(struct ata_device *dev)
 	if (ap->ops->pmp_detach)
 		ap->ops->pmp_detach(ap);
 
-	ata_port_for_each_link(tlink, ap)
+	ata_for_each_link(tlink, ap, EDGE)
 		ata_eh_detach_dev(tlink->device);
 
 	spin_lock_irqsave(ap->lock, flags);
@@ -700,7 +700,7 @@ static int sata_pmp_eh_recover_pmp(struct ata_port *ap,
 		}
 
 		/* PMP is reset, SErrors cannot be trusted, scan all */
-		ata_port_for_each_link(tlink, ap) {
+		ata_for_each_link(tlink, ap, EDGE) {
 			struct ata_eh_context *ehc = &tlink->eh_context;
 
 			ehc->i.probe_mask |= ATA_ALL_DEVICES;
@@ -768,7 +768,7 @@ static int sata_pmp_eh_handle_disabled_links(struct ata_port *ap)
 
 	spin_lock_irqsave(ap->lock, flags);
 
-	ata_port_for_each_link(link, ap) {
+	ata_for_each_link(link, ap, EDGE) {
 		if (!(link->flags & ATA_LFLAG_DISABLED))
 			continue;
 
@@ -852,7 +852,7 @@ static int sata_pmp_eh_recover(struct ata_port *ap)
 	int cnt, rc;
 
 	pmp_tries = ATA_EH_PMP_TRIES;
-	ata_port_for_each_link(link, ap)
+	ata_for_each_link(link, ap, EDGE)
 		link_tries[link->pmp] = ATA_EH_PMP_LINK_TRIES;
 
  retry:
@@ -861,7 +861,7 @@ static int sata_pmp_eh_recover(struct ata_port *ap)
 		rc = ata_eh_recover(ap, ops->prereset, ops->softreset,
 				    ops->hardreset, ops->postreset, NULL);
 		if (rc) {
-			ata_link_for_each_dev(dev, &ap->link)
+			ata_for_each_dev(dev, &ap->link, ALL)
 				ata_dev_disable(dev);
 			return rc;
 		}
@@ -870,7 +870,7 @@ static int sata_pmp_eh_recover(struct ata_port *ap)
 			return 0;
 
 		/* new PMP online */
-		ata_port_for_each_link(link, ap)
+		ata_for_each_link(link, ap, EDGE)
 			link_tries[link->pmp] = ATA_EH_PMP_LINK_TRIES;
 
 		/* fall through */
@@ -942,7 +942,7 @@ static int sata_pmp_eh_recover(struct ata_port *ap)
 	}
 
 	cnt = 0;
-	ata_port_for_each_link(link, ap) {
+	ata_for_each_link(link, ap, EDGE) {
 		if (!(gscr_error & (1 << link->pmp)))
 			continue;
 
diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c
index 47c7afcb36f2..d763b2b79a96 100644
--- a/drivers/ata/libata-scsi.c
+++ b/drivers/ata/libata-scsi.c
@@ -3229,12 +3229,12 @@ void ata_scsi_scan_host(struct ata_port *ap, int sync)
 		return;
 
  repeat:
-	ata_port_for_each_link(link, ap) {
-		ata_link_for_each_dev(dev, link) {
+	ata_for_each_link(link, ap, EDGE) {
+		ata_for_each_dev(dev, link, ENABLED) {
 			struct scsi_device *sdev;
 			int channel = 0, id = 0;
 
-			if (!ata_dev_enabled(dev) || dev->sdev)
+			if (dev->sdev)
 				continue;
 
 			if (ata_is_host_link(link))
@@ -3255,9 +3255,9 @@ void ata_scsi_scan_host(struct ata_port *ap, int sync)
 	 * failure occurred, scan would have failed silently.  Check
 	 * whether all devices are attached.
 	 */
-	ata_port_for_each_link(link, ap) {
-		ata_link_for_each_dev(dev, link) {
-			if (ata_dev_enabled(dev) && !dev->sdev)
+	ata_for_each_link(link, ap, EDGE) {
+		ata_for_each_dev(dev, link, ENABLED) {
+			if (!dev->sdev)
 				goto exit_loop;
 		}
 	}
@@ -3369,7 +3369,7 @@ static void ata_scsi_remove_dev(struct ata_device *dev)
 
 	if (sdev) {
 		ata_dev_printk(dev, KERN_INFO, "detaching (SCSI %s)\n",
-			       sdev->sdev_gendev.bus_id);
+			       dev_name(&sdev->sdev_gendev));
 
 		scsi_remove_device(sdev);
 		scsi_device_put(sdev);
@@ -3381,7 +3381,7 @@ static void ata_scsi_handle_link_detach(struct ata_link *link)
 	struct ata_port *ap = link->ap;
 	struct ata_device *dev;
 
-	ata_link_for_each_dev(dev, link) {
+	ata_for_each_dev(dev, link, ALL) {
 		unsigned long flags;
 
 		if (!(dev->flags & ATA_DFLAG_DETACHED))
@@ -3496,7 +3496,7 @@ static int ata_scsi_user_scan(struct Scsi_Host *shost, unsigned int channel,
 	if (devno == SCAN_WILD_CARD) {
 		struct ata_link *link;
 
-		ata_port_for_each_link(link, ap) {
+		ata_for_each_link(link, ap, EDGE) {
 			struct ata_eh_info *ehi = &link->eh_info;
 			ehi->probe_mask |= ATA_ALL_DEVICES;
 			ehi->action |= ATA_EH_RESET;
@@ -3544,11 +3544,11 @@ void ata_scsi_dev_rescan(struct work_struct *work)
 
 	spin_lock_irqsave(ap->lock, flags);
 
-	ata_port_for_each_link(link, ap) {
-		ata_link_for_each_dev(dev, link) {
+	ata_for_each_link(link, ap, EDGE) {
+		ata_for_each_dev(dev, link, ENABLED) {
 			struct scsi_device *sdev = dev->sdev;
 
-			if (!ata_dev_enabled(dev) || !sdev)
+			if (!sdev)
 				continue;
 			if (scsi_device_get(sdev))
 				continue;
diff --git a/drivers/ata/pata_bf54x.c b/drivers/ata/pata_bf54x.c
index 1266924c11f9..1050fed96b2b 100644
--- a/drivers/ata/pata_bf54x.c
+++ b/drivers/ata/pata_bf54x.c
@@ -356,7 +356,6 @@ static void bfin_set_piomode(struct ata_port *ap, struct ata_device *adev)
  *	bfin_set_dmamode - Initialize host controller PATA DMA timings
  *	@ap: Port whose timings we are configuring
  *	@adev: um
- *	@udma: udma mode, 0 - 6
  *
  *	Set UDMA mode for device.
  *
diff --git a/drivers/ata/pata_it821x.c b/drivers/ata/pata_it821x.c
index 860ede526282..f828a29d7756 100644
--- a/drivers/ata/pata_it821x.c
+++ b/drivers/ata/pata_it821x.c
@@ -465,24 +465,22 @@ static int it821x_smart_set_mode(struct ata_link *link, struct ata_device **unus
 {
 	struct ata_device *dev;
 
-	ata_link_for_each_dev(dev, link) {
-		if (ata_dev_enabled(dev)) {
-			/* We don't really care */
-			dev->pio_mode = XFER_PIO_0;
-			dev->dma_mode = XFER_MW_DMA_0;
-			/* We do need the right mode information for DMA or PIO
-			   and this comes from the current configuration flags */
-			if (ata_id_has_dma(dev->id)) {
-				ata_dev_printk(dev, KERN_INFO, "configured for DMA\n");
-				dev->xfer_mode = XFER_MW_DMA_0;
-				dev->xfer_shift = ATA_SHIFT_MWDMA;
-				dev->flags &= ~ATA_DFLAG_PIO;
-			} else {
-				ata_dev_printk(dev, KERN_INFO, "configured for PIO\n");
-				dev->xfer_mode = XFER_PIO_0;
-				dev->xfer_shift = ATA_SHIFT_PIO;
-				dev->flags |= ATA_DFLAG_PIO;
-			}
+	ata_for_each_dev(dev, link, ENABLED) {
+		/* We don't really care */
+		dev->pio_mode = XFER_PIO_0;
+		dev->dma_mode = XFER_MW_DMA_0;
+		/* We do need the right mode information for DMA or PIO
+		   and this comes from the current configuration flags */
+		if (ata_id_has_dma(dev->id)) {
+			ata_dev_printk(dev, KERN_INFO, "configured for DMA\n");
+			dev->xfer_mode = XFER_MW_DMA_0;
+			dev->xfer_shift = ATA_SHIFT_MWDMA;
+			dev->flags &= ~ATA_DFLAG_PIO;
+		} else {
+			ata_dev_printk(dev, KERN_INFO, "configured for PIO\n");
+			dev->xfer_mode = XFER_PIO_0;
+			dev->xfer_shift = ATA_SHIFT_PIO;
+			dev->flags |= ATA_DFLAG_PIO;
 		}
 	}
 	return 0;
diff --git a/drivers/ata/pata_ixp4xx_cf.c b/drivers/ata/pata_ixp4xx_cf.c
index 2014253f6c88..b173c157ab00 100644
--- a/drivers/ata/pata_ixp4xx_cf.c
+++ b/drivers/ata/pata_ixp4xx_cf.c
@@ -30,14 +30,12 @@ static int ixp4xx_set_mode(struct ata_link *link, struct ata_device **error)
 {
 	struct ata_device *dev;
 
-	ata_link_for_each_dev(dev, link) {
-		if (ata_dev_enabled(dev)) {
-			ata_dev_printk(dev, KERN_INFO, "configured for PIO0\n");
-			dev->pio_mode = XFER_PIO_0;
-			dev->xfer_mode = XFER_PIO_0;
-			dev->xfer_shift = ATA_SHIFT_PIO;
-			dev->flags |= ATA_DFLAG_PIO;
-		}
+	ata_for_each_dev(dev, link, ENABLED) {
+		ata_dev_printk(dev, KERN_INFO, "configured for PIO0\n");
+		dev->pio_mode = XFER_PIO_0;
+		dev->xfer_mode = XFER_PIO_0;
+		dev->xfer_shift = ATA_SHIFT_PIO;
+		dev->flags |= ATA_DFLAG_PIO;
 	}
 	return 0;
 }
diff --git a/drivers/ata/pata_legacy.c b/drivers/ata/pata_legacy.c
index 930c2208640b..6c1d778b63a9 100644
--- a/drivers/ata/pata_legacy.c
+++ b/drivers/ata/pata_legacy.c
@@ -194,15 +194,12 @@ static int legacy_set_mode(struct ata_link *link, struct ata_device **unused)
 {
 	struct ata_device *dev;
 
-	ata_link_for_each_dev(dev, link) {
-		if (ata_dev_enabled(dev)) {
-			ata_dev_printk(dev, KERN_INFO,
-						"configured for PIO\n");
-			dev->pio_mode = XFER_PIO_0;
-			dev->xfer_mode = XFER_PIO_0;
-			dev->xfer_shift = ATA_SHIFT_PIO;
-			dev->flags |= ATA_DFLAG_PIO;
-		}
+	ata_for_each_dev(dev, link, ENABLED) {
+		ata_dev_printk(dev, KERN_INFO, "configured for PIO\n");
+		dev->pio_mode = XFER_PIO_0;
+		dev->xfer_mode = XFER_PIO_0;
+		dev->xfer_shift = ATA_SHIFT_PIO;
+		dev->flags |= ATA_DFLAG_PIO;
 	}
 	return 0;
 }
@@ -641,7 +638,6 @@ static void qdi6500_set_piomode(struct ata_port *ap, struct ata_device *adev)
  *	qdi6580dp_set_piomode		-	PIO setup for dual channel
  *	@ap: Port
  *	@adev: Device
- *	@irq: interrupt line
  *
  *	In dual channel mode the 6580 has one clock per channel and we have
  *	to software clockswitch in qc_issue.
@@ -1028,7 +1024,7 @@ static __init int legacy_init_one(struct legacy_probe *probe)
 	/* Nothing found means we drop the port as its probably not there */
 
 	ret = -ENODEV;
-	ata_link_for_each_dev(dev, &ap->link) {
+	ata_for_each_dev(dev, &ap->link, ALL) {
 		if (!ata_dev_absent(dev)) {
 			legacy_host[probe->slot] = host;
 			ld->platform_dev = pdev;
diff --git a/drivers/ata/pata_oldpiix.c b/drivers/ata/pata_oldpiix.c
index c0dbc46a348e..2c1a91c40c1a 100644
--- a/drivers/ata/pata_oldpiix.c
+++ b/drivers/ata/pata_oldpiix.c
@@ -116,7 +116,6 @@ static void oldpiix_set_piomode (struct ata_port *ap, struct ata_device *adev)
  *	oldpiix_set_dmamode - Initialize host controller PATA DMA timings
  *	@ap: Port whose timings we are configuring
  *	@adev: Device to program
- *	@isich: True if the device is an ICH and has IOCFG registers
  *
  *	Set MWDMA mode for device, in host controller PCI config space.
  *
diff --git a/drivers/ata/pata_pdc2027x.c b/drivers/ata/pata_pdc2027x.c
index 0e1c2c1134d3..e94efccaa482 100644
--- a/drivers/ata/pata_pdc2027x.c
+++ b/drivers/ata/pata_pdc2027x.c
@@ -281,7 +281,6 @@ static unsigned long pdc2027x_mode_filter(struct ata_device *adev, unsigned long
  *	pdc2027x_set_piomode - Initialize host controller PATA PIO timings
  *	@ap: Port to configure
  *	@adev: um
- *	@pio: PIO mode, 0 - 4
  *
  *	Set PIO mode for device.
  *
@@ -326,7 +325,6 @@ static void pdc2027x_set_piomode(struct ata_port *ap, struct ata_device *adev)
  *	pdc2027x_set_dmamode - Initialize host controller PATA UDMA timings
  *	@ap: Port to configure
  *	@adev: um
- *	@udma: udma mode, XFER_UDMA_0 to XFER_UDMA_6
  *
  *	Set UDMA mode for device.
  *
@@ -406,23 +404,20 @@ static int pdc2027x_set_mode(struct ata_link *link, struct ata_device **r_failed
 	if (rc < 0)
 		return rc;
 
-	ata_link_for_each_dev(dev, link) {
-		if (ata_dev_enabled(dev)) {
+	ata_for_each_dev(dev, link, ENABLED) {
+		pdc2027x_set_piomode(ap, dev);
 
-			pdc2027x_set_piomode(ap, dev);
+		/*
+		 * Enable prefetch if the device support PIO only.
+		 */
+		if (dev->xfer_shift == ATA_SHIFT_PIO) {
+			u32 ctcr1 = ioread32(dev_mmio(ap, dev, PDC_CTCR1));
+			ctcr1 |= (1 << 25);
+			iowrite32(ctcr1, dev_mmio(ap, dev, PDC_CTCR1));
 
-			/*
-			 * Enable prefetch if the device support PIO only.
-			 */
-			if (dev->xfer_shift == ATA_SHIFT_PIO) {
-				u32 ctcr1 = ioread32(dev_mmio(ap, dev, PDC_CTCR1));
-				ctcr1 |= (1 << 25);
-				iowrite32(ctcr1, dev_mmio(ap, dev, PDC_CTCR1));
-
-				PDPRINTK("Turn on prefetch\n");
-			} else {
-				pdc2027x_set_dmamode(ap, dev);
-			}
+			PDPRINTK("Turn on prefetch\n");
+		} else {
+			pdc2027x_set_dmamode(ap, dev);
 		}
 	}
 	return 0;
diff --git a/drivers/ata/pata_platform.c b/drivers/ata/pata_platform.c
index 77e4e3b17f54..6afa07a37648 100644
--- a/drivers/ata/pata_platform.c
+++ b/drivers/ata/pata_platform.c
@@ -34,14 +34,12 @@ static int pata_platform_set_mode(struct ata_link *link, struct ata_device **unu
 {
 	struct ata_device *dev;
 
-	ata_link_for_each_dev(dev, link) {
-		if (ata_dev_enabled(dev)) {
-			/* We don't really care */
-			dev->pio_mode = dev->xfer_mode = XFER_PIO_0;
-			dev->xfer_shift = ATA_SHIFT_PIO;
-			dev->flags |= ATA_DFLAG_PIO;
-			ata_dev_printk(dev, KERN_INFO, "configured for PIO\n");
-		}
+	ata_for_each_dev(dev, link, ENABLED) {
+		/* We don't really care */
+		dev->pio_mode = dev->xfer_mode = XFER_PIO_0;
+		dev->xfer_shift = ATA_SHIFT_PIO;
+		dev->flags |= ATA_DFLAG_PIO;
+		ata_dev_printk(dev, KERN_INFO, "configured for PIO\n");
 	}
 	return 0;
 }
diff --git a/drivers/ata/pata_radisys.c b/drivers/ata/pata_radisys.c
index 0b0aa452de14..695d44ae52c6 100644
--- a/drivers/ata/pata_radisys.c
+++ b/drivers/ata/pata_radisys.c
@@ -81,7 +81,6 @@ static void radisys_set_piomode (struct ata_port *ap, struct ata_device *adev)
  *	radisys_set_dmamode - Initialize host controller PATA DMA timings
  *	@ap: Port whose timings we are configuring
  *	@adev: Device to program
- *	@isich: True if the device is an ICH and has IOCFG registers
  *
  *	Set MWDMA mode for device, in host controller PCI config space.
  *
diff --git a/drivers/ata/pata_rz1000.c b/drivers/ata/pata_rz1000.c
index 7dfd1f3f6f3a..46d6bc1bf1e9 100644
--- a/drivers/ata/pata_rz1000.c
+++ b/drivers/ata/pata_rz1000.c
@@ -38,15 +38,13 @@ static int rz1000_set_mode(struct ata_link *link, struct ata_device **unused)
 {
 	struct ata_device *dev;
 
-	ata_link_for_each_dev(dev, link) {
-		if (ata_dev_enabled(dev)) {
-			/* We don't really care */
-			dev->pio_mode = XFER_PIO_0;
-			dev->xfer_mode = XFER_PIO_0;
-			dev->xfer_shift = ATA_SHIFT_PIO;
-			dev->flags |= ATA_DFLAG_PIO;
-			ata_dev_printk(dev, KERN_INFO, "configured for PIO\n");
-		}
+	ata_for_each_dev(dev, link, ENABLED) {
+		/* We don't really care */
+		dev->pio_mode = XFER_PIO_0;
+		dev->xfer_mode = XFER_PIO_0;
+		dev->xfer_shift = ATA_SHIFT_PIO;
+		dev->flags |= ATA_DFLAG_PIO;
+		ata_dev_printk(dev, KERN_INFO, "configured for PIO\n");
 	}
 	return 0;
 }
diff --git a/drivers/ata/pata_scc.c b/drivers/ata/pata_scc.c
index cf3707e516a2..d447f1cb46ec 100644
--- a/drivers/ata/pata_scc.c
+++ b/drivers/ata/pata_scc.c
@@ -210,7 +210,6 @@ static void scc_set_piomode (struct ata_port *ap, struct ata_device *adev)
  *	scc_set_dmamode - Initialize host controller PATA DMA timings
  *	@ap: Port whose timings we are configuring
  *	@adev: um
- *	@udma: udma mode, 0 - 6
  *
  *	Set UDMA mode for device.
  *
diff --git a/drivers/ata/pata_serverworks.c b/drivers/ata/pata_serverworks.c
index 72e41c9f969b..8d2fd9dd40c7 100644
--- a/drivers/ata/pata_serverworks.c
+++ b/drivers/ata/pata_serverworks.c
@@ -138,7 +138,6 @@ static struct sv_cable_table cable_detect[] = {
 /**
  *	serverworks_cable_detect	-	cable detection
  *	@ap: ATA port
- *	@deadline: deadline jiffies for the operation
  *
  *	Perform cable detection according to the device and subvendor
  *	identifications
diff --git a/drivers/ata/pata_sis.c b/drivers/ata/pata_sis.c
index d34236611752..60a3f00546bb 100644
--- a/drivers/ata/pata_sis.c
+++ b/drivers/ata/pata_sis.c
@@ -113,7 +113,6 @@ static int sis_133_cable_detect(struct ata_port *ap)
 /**
  *	sis_66_cable_detect	-	check for 40/80 pin
  *	@ap: Port
- *	@deadline: deadline jiffies for the operation
  *
  *	Perform cable detection on the UDMA66, UDMA100 and early UDMA133
  *	SiS IDE controllers.
diff --git a/drivers/ata/sata_mv.c b/drivers/ata/sata_mv.c
index 2b24ae58b52e..86918634a4c5 100644
--- a/drivers/ata/sata_mv.c
+++ b/drivers/ata/sata_mv.c
@@ -1836,7 +1836,6 @@ static void mv_unexpected_intr(struct ata_port *ap, int edma_was_enabled)
 /**
  *      mv_err_intr - Handle error interrupts on the port
  *      @ap: ATA channel to manipulate
- *      @qc: affected command (non-NCQ), or NULL
  *
  *      Most cases require a full reset of the chip's state machine,
  *      which also performs a COMRESET.
diff --git a/drivers/ata/sata_sil.c b/drivers/ata/sata_sil.c
index 031d7b7dee34..177370921774 100644
--- a/drivers/ata/sata_sil.c
+++ b/drivers/ata/sata_sil.c
@@ -278,7 +278,7 @@ static int sil_set_mode(struct ata_link *link, struct ata_device **r_failed)
 	if (rc)
 		return rc;
 
-	ata_link_for_each_dev(dev, link) {
+	ata_for_each_dev(dev, link, ALL) {
 		if (!ata_dev_enabled(dev))
 			dev_mode[dev->devno] = 0;	/* PIO0/1/2 */
 		else if (dev->flags & ATA_DFLAG_PIO)
diff --git a/drivers/base/attribute_container.c b/drivers/base/attribute_container.c
index f57652db0a2a..b9cda053d3c0 100644
--- a/drivers/base/attribute_container.c
+++ b/drivers/base/attribute_container.c
@@ -167,7 +167,7 @@ attribute_container_add_device(struct device *dev,
 		ic->classdev.parent = get_device(dev);
 		ic->classdev.class = cont->class;
 		cont->class->dev_release = attribute_container_release;
-		strcpy(ic->classdev.bus_id, dev->bus_id);
+		dev_set_name(&ic->classdev, dev_name(dev));
 		if (fn)
 			fn(cont, dev, &ic->classdev);
 		else
diff --git a/drivers/base/bus.c b/drivers/base/bus.c
index 5aee1c0169ea..83f32b891fa9 100644
--- a/drivers/base/bus.c
+++ b/drivers/base/bus.c
@@ -333,7 +333,7 @@ static int match_name(struct device *dev, void *data)
 {
 	const char *name = data;
 
-	return sysfs_streq(name, dev->bus_id);
+	return sysfs_streq(name, dev_name(dev));
 }
 
 /**
@@ -461,12 +461,12 @@ int bus_add_device(struct device *dev)
 	int error = 0;
 
 	if (bus) {
-		pr_debug("bus: '%s': add device %s\n", bus->name, dev->bus_id);
+		pr_debug("bus: '%s': add device %s\n", bus->name, dev_name(dev));
 		error = device_add_attrs(bus, dev);
 		if (error)
 			goto out_put;
 		error = sysfs_create_link(&bus->p->devices_kset->kobj,
-						&dev->kobj, dev->bus_id);
+						&dev->kobj, dev_name(dev));
 		if (error)
 			goto out_id;
 		error = sysfs_create_link(&dev->kobj,
@@ -482,7 +482,7 @@ int bus_add_device(struct device *dev)
 out_deprecated:
 	sysfs_remove_link(&dev->kobj, "subsystem");
 out_subsys:
-	sysfs_remove_link(&bus->p->devices_kset->kobj, dev->bus_id);
+	sysfs_remove_link(&bus->p->devices_kset->kobj, dev_name(dev));
 out_id:
 	device_remove_attrs(bus, dev);
 out_put:
@@ -526,13 +526,13 @@ void bus_remove_device(struct device *dev)
 		sysfs_remove_link(&dev->kobj, "subsystem");
 		remove_deprecated_bus_links(dev);
 		sysfs_remove_link(&dev->bus->p->devices_kset->kobj,
-				  dev->bus_id);
+				  dev_name(dev));
 		device_remove_attrs(dev->bus, dev);
 		if (klist_node_attached(&dev->knode_bus))
 			klist_del(&dev->knode_bus);
 
 		pr_debug("bus: '%s': remove device %s\n",
-			 dev->bus->name, dev->bus_id);
+			 dev->bus->name, dev_name(dev));
 		device_release_driver(dev);
 		bus_put(dev->bus);
 	}
diff --git a/drivers/base/core.c b/drivers/base/core.c
index 8c2cc2648f5a..14aa2b6953c9 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -119,7 +119,7 @@ static void device_release(struct kobject *kobj)
 	else
 		WARN(1, KERN_ERR "Device '%s' does not have a release() "
 			"function, it is broken and must be fixed.\n",
-			dev->bus_id);
+			dev_name(dev));
 }
 
 static struct kobj_type device_ktype = {
@@ -209,7 +209,7 @@ static int dev_uevent(struct kset *kset, struct kobject *kobj,
 		retval = dev->bus->uevent(dev, env);
 		if (retval)
 			pr_debug("device: '%s': %s: bus uevent() returned %d\n",
-				 dev->bus_id, __func__, retval);
+				 dev_name(dev), __func__, retval);
 	}
 
 	/* have the class specific function add its stuff */
@@ -217,7 +217,7 @@ static int dev_uevent(struct kset *kset, struct kobject *kobj,
 		retval = dev->class->dev_uevent(dev, env);
 		if (retval)
 			pr_debug("device: '%s': %s: class uevent() "
-				 "returned %d\n", dev->bus_id,
+				 "returned %d\n", dev_name(dev),
 				 __func__, retval);
 	}
 
@@ -226,7 +226,7 @@ static int dev_uevent(struct kset *kset, struct kobject *kobj,
 		retval = dev->type->uevent(dev, env);
 		if (retval)
 			pr_debug("device: '%s': %s: dev_type uevent() "
-				 "returned %d\n", dev->bus_id,
+				 "returned %d\n", dev_name(dev),
 				 __func__, retval);
 	}
 
@@ -672,7 +672,7 @@ static int device_add_class_symlinks(struct device *dev)
 	if (dev->kobj.parent != &dev->class->p->class_subsys.kobj &&
 	    device_is_not_partition(dev)) {
 		error = sysfs_create_link(&dev->class->p->class_subsys.kobj,
-					  &dev->kobj, dev->bus_id);
+					  &dev->kobj, dev_name(dev));
 		if (error)
 			goto out_subsys;
 	}
@@ -712,11 +712,11 @@ out_busid:
 	if (dev->kobj.parent != &dev->class->p->class_subsys.kobj &&
 	    device_is_not_partition(dev))
 		sysfs_remove_link(&dev->class->p->class_subsys.kobj,
-				  dev->bus_id);
+				  dev_name(dev));
 #else
 	/* link in the class directory pointing to the device */
 	error = sysfs_create_link(&dev->class->p->class_subsys.kobj,
-				  &dev->kobj, dev->bus_id);
+				  &dev->kobj, dev_name(dev));
 	if (error)
 		goto out_subsys;
 
@@ -729,7 +729,7 @@ out_busid:
 	return 0;
 
 out_busid:
-	sysfs_remove_link(&dev->class->p->class_subsys.kobj, dev->bus_id);
+	sysfs_remove_link(&dev->class->p->class_subsys.kobj, dev_name(dev));
 #endif
 
 out_subsys:
@@ -758,12 +758,12 @@ static void device_remove_class_symlinks(struct device *dev)
 	if (dev->kobj.parent != &dev->class->p->class_subsys.kobj &&
 	    device_is_not_partition(dev))
 		sysfs_remove_link(&dev->class->p->class_subsys.kobj,
-				  dev->bus_id);
+				  dev_name(dev));
 #else
 	if (dev->parent && device_is_not_partition(dev))
 		sysfs_remove_link(&dev->kobj, "device");
 
-	sysfs_remove_link(&dev->class->p->class_subsys.kobj, dev->bus_id);
+	sysfs_remove_link(&dev->class->p->class_subsys.kobj, dev_name(dev));
 #endif
 
 	sysfs_remove_link(&dev->kobj, "subsystem");
@@ -866,7 +866,7 @@ int device_add(struct device *dev)
 	if (!strlen(dev->bus_id))
 		goto done;
 
-	pr_debug("device: '%s': %s\n", dev->bus_id, __func__);
+	pr_debug("device: '%s': %s\n", dev_name(dev), __func__);
 
 	parent = get_device(dev->parent);
 	setup_parent(dev, parent);
@@ -876,7 +876,7 @@ int device_add(struct device *dev)
 		set_dev_node(dev, dev_to_node(parent));
 
 	/* first, register with generic layer. */
-	error = kobject_add(&dev->kobj, dev->kobj.parent, "%s", dev->bus_id);
+	error = kobject_add(&dev->kobj, dev->kobj.parent, "%s", dev_name(dev));
 	if (error)
 		goto Error;
 
@@ -1086,7 +1086,7 @@ void device_del(struct device *dev)
  */
 void device_unregister(struct device *dev)
 {
-	pr_debug("device: '%s': %s\n", dev->bus_id, __func__);
+	pr_debug("device: '%s': %s\n", dev_name(dev), __func__);
 	device_del(dev);
 	put_device(dev);
 }
@@ -1199,7 +1199,7 @@ EXPORT_SYMBOL_GPL(device_remove_file);
 
 static void device_create_release(struct device *dev)
 {
-	pr_debug("device: '%s': %s\n", dev->bus_id, __func__);
+	pr_debug("device: '%s': %s\n", dev_name(dev), __func__);
 	kfree(dev);
 }
 
@@ -1344,7 +1344,7 @@ int device_rename(struct device *dev, char *new_name)
 	if (!dev)
 		return -EINVAL;
 
-	pr_debug("device: '%s': %s: renaming to '%s'\n", dev->bus_id,
+	pr_debug("device: '%s': %s: renaming to '%s'\n", dev_name(dev),
 		 __func__, new_name);
 
 #ifdef CONFIG_SYSFS_DEPRECATED
@@ -1381,7 +1381,7 @@ int device_rename(struct device *dev, char *new_name)
 #else
 	if (dev->class) {
 		error = sysfs_create_link_nowarn(&dev->class->p->class_subsys.kobj,
-						 &dev->kobj, dev->bus_id);
+						 &dev->kobj, dev_name(dev));
 		if (error)
 			goto out;
 		sysfs_remove_link(&dev->class->p->class_subsys.kobj,
@@ -1459,8 +1459,8 @@ int device_move(struct device *dev, struct device *new_parent)
 	new_parent = get_device(new_parent);
 	new_parent_kobj = get_device_parent(dev, new_parent);
 
-	pr_debug("device: '%s': %s: moving to '%s'\n", dev->bus_id,
-		 __func__, new_parent ? new_parent->bus_id : "<NULL>");
+	pr_debug("device: '%s': %s: moving to '%s'\n", dev_name(dev),
+		 __func__, new_parent ? dev_name(new_parent) : "<NULL>");
 	error = kobject_move(&dev->kobj, new_parent_kobj);
 	if (error) {
 		cleanup_glue_dir(dev, new_parent_kobj);
diff --git a/drivers/base/dd.c b/drivers/base/dd.c
index 20febc00a525..17a8e45cf9c6 100644
--- a/drivers/base/dd.c
+++ b/drivers/base/dd.c
@@ -34,7 +34,7 @@ static void driver_bound(struct device *dev)
 		return;
 	}
 
-	pr_debug("driver: '%s': %s: bound to device '%s'\n", dev->bus_id,
+	pr_debug("driver: '%s': %s: bound to device '%s'\n", dev_name(dev),
 		 __func__, dev->driver->name);
 
 	if (dev->bus)
@@ -104,13 +104,13 @@ static int really_probe(struct device *dev, struct device_driver *drv)
 
 	atomic_inc(&probe_count);
 	pr_debug("bus: '%s': %s: probing driver %s with device %s\n",
-		 drv->bus->name, __func__, drv->name, dev->bus_id);
+		 drv->bus->name, __func__, drv->name, dev_name(dev));
 	WARN_ON(!list_empty(&dev->devres_head));
 
 	dev->driver = drv;
 	if (driver_sysfs_add(dev)) {
 		printk(KERN_ERR "%s: driver_sysfs_add(%s) failed\n",
-			__func__, dev->bus_id);
+			__func__, dev_name(dev));
 		goto probe_failed;
 	}
 
@@ -127,7 +127,7 @@ static int really_probe(struct device *dev, struct device_driver *drv)
 	driver_bound(dev);
 	ret = 1;
 	pr_debug("bus: '%s': %s: bound device %s to driver %s\n",
-		 drv->bus->name, __func__, dev->bus_id, drv->name);
+		 drv->bus->name, __func__, dev_name(dev), drv->name);
 	goto done;
 
 probe_failed:
@@ -139,7 +139,7 @@ probe_failed:
 		/* driver matched but the probe failed */
 		printk(KERN_WARNING
 		       "%s: probe of %s failed with error %d\n",
-		       drv->name, dev->bus_id, ret);
+		       drv->name, dev_name(dev), ret);
 	}
 	/*
 	 * Ignore errors returned by ->probe so that the next driver can try
@@ -194,7 +194,7 @@ int driver_probe_device(struct device_driver *drv, struct device *dev)
 		goto done;
 
 	pr_debug("bus: '%s': %s: matched device %s with driver %s\n",
-		 drv->bus->name, __func__, dev->bus_id, drv->name);
+		 drv->bus->name, __func__, dev_name(dev), drv->name);
 
 	ret = really_probe(dev, drv);
 
diff --git a/drivers/base/firmware_class.c b/drivers/base/firmware_class.c
index b7e571031ecd..44699d9dd85c 100644
--- a/drivers/base/firmware_class.c
+++ b/drivers/base/firmware_class.c
@@ -291,12 +291,6 @@ firmware_class_timeout(u_long data)
 	fw_load_abort(fw_priv);
 }
 
-static inline void fw_setup_device_id(struct device *f_dev, struct device *dev)
-{
-	/* XXX warning we should watch out for name collisions */
-	strlcpy(f_dev->bus_id, dev->bus_id, BUS_ID_SIZE);
-}
-
 static int fw_register_device(struct device **dev_p, const char *fw_name,
 			      struct device *device)
 {
@@ -321,7 +315,7 @@ static int fw_register_device(struct device **dev_p, const char *fw_name,
 	fw_priv->timeout.data = (u_long) fw_priv;
 	init_timer(&fw_priv->timeout);
 
-	fw_setup_device_id(f_dev, device);
+	dev_set_name(f_dev, dev_name(device));
 	f_dev->parent = device;
 	f_dev->class = &firmware_class;
 	dev_set_drvdata(f_dev, fw_priv);
diff --git a/drivers/base/isa.c b/drivers/base/isa.c
index efd577574948..479694b6cbe3 100644
--- a/drivers/base/isa.c
+++ b/drivers/base/isa.c
@@ -11,7 +11,7 @@
 #include <linux/isa.h>
 
 static struct device isa_bus = {
-	.bus_id		= "isa"
+	.init_name	= "isa"
 };
 
 struct isa_dev {
@@ -135,9 +135,8 @@ int isa_register_driver(struct isa_driver *isa_driver, unsigned int ndev)
 		isa_dev->dev.parent	= &isa_bus;
 		isa_dev->dev.bus	= &isa_bus_type;
 
-		snprintf(isa_dev->dev.bus_id, BUS_ID_SIZE, "%s.%u",
-				isa_driver->driver.name, id);
-
+		dev_set_name(&isa_dev->dev, "%s.%u",
+			     isa_driver->driver.name, id);
 		isa_dev->dev.platform_data	= isa_driver;
 		isa_dev->dev.release		= isa_dev_release;
 		isa_dev->id			= id;
diff --git a/drivers/base/platform.c b/drivers/base/platform.c
index dfcbfe504867..349a1013603f 100644
--- a/drivers/base/platform.c
+++ b/drivers/base/platform.c
@@ -24,7 +24,7 @@
 				 driver))
 
 struct device platform_bus = {
-	.bus_id		= "platform",
+	.init_name	= "platform",
 };
 EXPORT_SYMBOL_GPL(platform_bus);
 
@@ -242,16 +242,15 @@ int platform_device_add(struct platform_device *pdev)
 	pdev->dev.bus = &platform_bus_type;
 
 	if (pdev->id != -1)
-		snprintf(pdev->dev.bus_id, BUS_ID_SIZE, "%s.%d", pdev->name,
-			 pdev->id);
+		dev_set_name(&pdev->dev, "%s.%d", pdev->name,  pdev->id);
 	else
-		strlcpy(pdev->dev.bus_id, pdev->name, BUS_ID_SIZE);
+		dev_set_name(&pdev->dev, pdev->name);
 
 	for (i = 0; i < pdev->num_resources; i++) {
 		struct resource *p, *r = &pdev->resource[i];
 
 		if (r->name == NULL)
-			r->name = pdev->dev.bus_id;
+			r->name = dev_name(&pdev->dev);
 
 		p = r->parent;
 		if (!p) {
@@ -264,14 +263,14 @@ int platform_device_add(struct platform_device *pdev)
 		if (p && insert_resource(p, r)) {
 			printk(KERN_ERR
 			       "%s: failed to claim resource %d\n",
-			       pdev->dev.bus_id, i);
+			       dev_name(&pdev->dev), i);
 			ret = -EBUSY;
 			goto failed;
 		}
 	}
 
 	pr_debug("Registering platform device '%s'. Parent at %s\n",
-		 pdev->dev.bus_id, pdev->dev.parent->bus_id);
+		 dev_name(&pdev->dev), dev_name(pdev->dev.parent));
 
 	ret = device_add(&pdev->dev);
 	if (ret == 0)
@@ -503,8 +502,6 @@ int platform_driver_register(struct platform_driver *drv)
 		drv->driver.suspend = platform_drv_suspend;
 	if (drv->resume)
 		drv->driver.resume = platform_drv_resume;
-	if (drv->pm)
-		drv->driver.pm = &drv->pm->base;
 	return driver_register(&drv->driver);
 }
 EXPORT_SYMBOL_GPL(platform_driver_register);
@@ -609,7 +606,7 @@ static int platform_match(struct device *dev, struct device_driver *drv)
 	struct platform_device *pdev;
 
 	pdev = container_of(dev, struct platform_device, dev);
-	return (strncmp(pdev->name, drv->name, BUS_ID_SIZE) == 0);
+	return (strcmp(pdev->name, drv->name) == 0);
 }
 
 #ifdef CONFIG_PM_SLEEP
@@ -686,7 +683,10 @@ static int platform_pm_suspend(struct device *dev)
 	struct device_driver *drv = dev->driver;
 	int ret = 0;
 
-	if (drv && drv->pm) {
+	if (!drv)
+		return 0;
+
+	if (drv->pm) {
 		if (drv->pm->suspend)
 			ret = drv->pm->suspend(dev);
 	} else {
@@ -698,16 +698,15 @@ static int platform_pm_suspend(struct device *dev)
 
 static int platform_pm_suspend_noirq(struct device *dev)
 {
-	struct platform_driver *pdrv;
+	struct device_driver *drv = dev->driver;
 	int ret = 0;
 
-	if (!dev->driver)
+	if (!drv)
 		return 0;
 
-	pdrv = to_platform_driver(dev->driver);
-	if (pdrv->pm) {
-		if (pdrv->pm->suspend_noirq)
-			ret = pdrv->pm->suspend_noirq(dev);
+	if (drv->pm) {
+		if (drv->pm->suspend_noirq)
+			ret = drv->pm->suspend_noirq(dev);
 	} else {
 		ret = platform_legacy_suspend_late(dev, PMSG_SUSPEND);
 	}
@@ -720,7 +719,10 @@ static int platform_pm_resume(struct device *dev)
 	struct device_driver *drv = dev->driver;
 	int ret = 0;
 
-	if (drv && drv->pm) {
+	if (!drv)
+		return 0;
+
+	if (drv->pm) {
 		if (drv->pm->resume)
 			ret = drv->pm->resume(dev);
 	} else {
@@ -732,16 +734,15 @@ static int platform_pm_resume(struct device *dev)
 
 static int platform_pm_resume_noirq(struct device *dev)
 {
-	struct platform_driver *pdrv;
+	struct device_driver *drv = dev->driver;
 	int ret = 0;
 
-	if (!dev->driver)
+	if (!drv)
 		return 0;
 
-	pdrv = to_platform_driver(dev->driver);
-	if (pdrv->pm) {
-		if (pdrv->pm->resume_noirq)
-			ret = pdrv->pm->resume_noirq(dev);
+	if (drv->pm) {
+		if (drv->pm->resume_noirq)
+			ret = drv->pm->resume_noirq(dev);
 	} else {
 		ret = platform_legacy_resume_early(dev);
 	}
@@ -780,16 +781,15 @@ static int platform_pm_freeze(struct device *dev)
 
 static int platform_pm_freeze_noirq(struct device *dev)
 {
-	struct platform_driver *pdrv;
+	struct device_driver *drv = dev->driver;
 	int ret = 0;
 
-	if (!dev->driver)
+	if (!drv)
 		return 0;
 
-	pdrv = to_platform_driver(dev->driver);
-	if (pdrv->pm) {
-		if (pdrv->pm->freeze_noirq)
-			ret = pdrv->pm->freeze_noirq(dev);
+	if (drv->pm) {
+		if (drv->pm->freeze_noirq)
+			ret = drv->pm->freeze_noirq(dev);
 	} else {
 		ret = platform_legacy_suspend_late(dev, PMSG_FREEZE);
 	}
@@ -802,7 +802,10 @@ static int platform_pm_thaw(struct device *dev)
 	struct device_driver *drv = dev->driver;
 	int ret = 0;
 
-	if (drv && drv->pm) {
+	if (!drv)
+		return 0;
+
+	if (drv->pm) {
 		if (drv->pm->thaw)
 			ret = drv->pm->thaw(dev);
 	} else {
@@ -814,16 +817,15 @@ static int platform_pm_thaw(struct device *dev)
 
 static int platform_pm_thaw_noirq(struct device *dev)
 {
-	struct platform_driver *pdrv;
+	struct device_driver *drv = dev->driver;
 	int ret = 0;
 
-	if (!dev->driver)
+	if (!drv)
 		return 0;
 
-	pdrv = to_platform_driver(dev->driver);
-	if (pdrv->pm) {
-		if (pdrv->pm->thaw_noirq)
-			ret = pdrv->pm->thaw_noirq(dev);
+	if (drv->pm) {
+		if (drv->pm->thaw_noirq)
+			ret = drv->pm->thaw_noirq(dev);
 	} else {
 		ret = platform_legacy_resume_early(dev);
 	}
@@ -836,7 +838,10 @@ static int platform_pm_poweroff(struct device *dev)
 	struct device_driver *drv = dev->driver;
 	int ret = 0;
 
-	if (drv && drv->pm) {
+	if (!drv)
+		return 0;
+
+	if (drv->pm) {
 		if (drv->pm->poweroff)
 			ret = drv->pm->poweroff(dev);
 	} else {
@@ -848,16 +853,15 @@ static int platform_pm_poweroff(struct device *dev)
 
 static int platform_pm_poweroff_noirq(struct device *dev)
 {
-	struct platform_driver *pdrv;
+	struct device_driver *drv = dev->driver;
 	int ret = 0;
 
-	if (!dev->driver)
+	if (!drv)
 		return 0;
 
-	pdrv = to_platform_driver(dev->driver);
-	if (pdrv->pm) {
-		if (pdrv->pm->poweroff_noirq)
-			ret = pdrv->pm->poweroff_noirq(dev);
+	if (drv->pm) {
+		if (drv->pm->poweroff_noirq)
+			ret = drv->pm->poweroff_noirq(dev);
 	} else {
 		ret = platform_legacy_suspend_late(dev, PMSG_HIBERNATE);
 	}
@@ -870,7 +874,10 @@ static int platform_pm_restore(struct device *dev)
 	struct device_driver *drv = dev->driver;
 	int ret = 0;
 
-	if (drv && drv->pm) {
+	if (!drv)
+		return 0;
+
+	if (drv->pm) {
 		if (drv->pm->restore)
 			ret = drv->pm->restore(dev);
 	} else {
@@ -882,16 +889,15 @@ static int platform_pm_restore(struct device *dev)
 
 static int platform_pm_restore_noirq(struct device *dev)
 {
-	struct platform_driver *pdrv;
+	struct device_driver *drv = dev->driver;
 	int ret = 0;
 
-	if (!dev->driver)
+	if (!drv)
 		return 0;
 
-	pdrv = to_platform_driver(dev->driver);
-	if (pdrv->pm) {
-		if (pdrv->pm->restore_noirq)
-			ret = pdrv->pm->restore_noirq(dev);
+	if (drv->pm) {
+		if (drv->pm->restore_noirq)
+			ret = drv->pm->restore_noirq(dev);
 	} else {
 		ret = platform_legacy_resume_early(dev);
 	}
@@ -912,17 +918,15 @@ static int platform_pm_restore_noirq(struct device *dev)
 
 #endif /* !CONFIG_HIBERNATION */
 
-static struct pm_ext_ops platform_pm_ops = {
-	.base = {
-		.prepare = platform_pm_prepare,
-		.complete = platform_pm_complete,
-		.suspend = platform_pm_suspend,
-		.resume = platform_pm_resume,
-		.freeze = platform_pm_freeze,
-		.thaw = platform_pm_thaw,
-		.poweroff = platform_pm_poweroff,
-		.restore = platform_pm_restore,
-	},
+static struct dev_pm_ops platform_dev_pm_ops = {
+	.prepare = platform_pm_prepare,
+	.complete = platform_pm_complete,
+	.suspend = platform_pm_suspend,
+	.resume = platform_pm_resume,
+	.freeze = platform_pm_freeze,
+	.thaw = platform_pm_thaw,
+	.poweroff = platform_pm_poweroff,
+	.restore = platform_pm_restore,
 	.suspend_noirq = platform_pm_suspend_noirq,
 	.resume_noirq = platform_pm_resume_noirq,
 	.freeze_noirq = platform_pm_freeze_noirq,
@@ -931,7 +935,7 @@ static struct pm_ext_ops platform_pm_ops = {
 	.restore_noirq = platform_pm_restore_noirq,
 };
 
-#define PLATFORM_PM_OPS_PTR	&platform_pm_ops
+#define PLATFORM_PM_OPS_PTR	(&platform_dev_pm_ops)
 
 #else /* !CONFIG_PM_SLEEP */
 
diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c
index 692c20ba5144..670c9d6c1407 100644
--- a/drivers/base/power/main.c
+++ b/drivers/base/power/main.c
@@ -76,7 +76,7 @@ void device_pm_add(struct device *dev)
 	if (dev->parent) {
 		if (dev->parent->power.status >= DPM_SUSPENDING)
 			dev_warn(dev, "parent %s should not be sleeping\n",
-				dev->parent->bus_id);
+				 dev_name(dev->parent));
 	} else if (transition_started) {
 		/*
 		 * We refuse to register parentless devices while a PM
@@ -112,7 +112,8 @@ void device_pm_remove(struct device *dev)
  *	@ops:	PM operations to choose from.
  *	@state:	PM transition of the system being carried out.
  */
-static int pm_op(struct device *dev, struct pm_ops *ops, pm_message_t state)
+static int pm_op(struct device *dev, struct dev_pm_ops *ops,
+			pm_message_t state)
 {
 	int error = 0;
 
@@ -174,7 +175,7 @@ static int pm_op(struct device *dev, struct pm_ops *ops, pm_message_t state)
  *	The operation is executed with interrupts disabled by the only remaining
  *	functional CPU in the system.
  */
-static int pm_noirq_op(struct device *dev, struct pm_ext_ops *ops,
+static int pm_noirq_op(struct device *dev, struct dev_pm_ops *ops,
 			pm_message_t state)
 {
 	int error = 0;
@@ -354,7 +355,7 @@ static int resume_device(struct device *dev, pm_message_t state)
 	if (dev->bus) {
 		if (dev->bus->pm) {
 			pm_dev_dbg(dev, state, "");
-			error = pm_op(dev, &dev->bus->pm->base, state);
+			error = pm_op(dev, dev->bus->pm, state);
 		} else if (dev->bus->resume) {
 			pm_dev_dbg(dev, state, "legacy ");
 			error = dev->bus->resume(dev);
@@ -451,9 +452,9 @@ static void complete_device(struct device *dev, pm_message_t state)
 		dev->type->pm->complete(dev);
 	}
 
-	if (dev->bus && dev->bus->pm && dev->bus->pm->base.complete) {
+	if (dev->bus && dev->bus->pm && dev->bus->pm->complete) {
 		pm_dev_dbg(dev, state, "completing ");
-		dev->bus->pm->base.complete(dev);
+		dev->bus->pm->complete(dev);
 	}
 
 	up(&dev->sem);
@@ -624,7 +625,7 @@ static int suspend_device(struct device *dev, pm_message_t state)
 	if (dev->bus) {
 		if (dev->bus->pm) {
 			pm_dev_dbg(dev, state, "");
-			error = pm_op(dev, &dev->bus->pm->base, state);
+			error = pm_op(dev, dev->bus->pm, state);
 		} else if (dev->bus->suspend) {
 			pm_dev_dbg(dev, state, "legacy ");
 			error = dev->bus->suspend(dev, state);
@@ -685,10 +686,10 @@ static int prepare_device(struct device *dev, pm_message_t state)
 
 	down(&dev->sem);
 
-	if (dev->bus && dev->bus->pm && dev->bus->pm->base.prepare) {
+	if (dev->bus && dev->bus->pm && dev->bus->pm->prepare) {
 		pm_dev_dbg(dev, state, "preparing ");
-		error = dev->bus->pm->base.prepare(dev);
-		suspend_report_result(dev->bus->pm->base.prepare, error);
+		error = dev->bus->pm->prepare(dev);
+		suspend_report_result(dev->bus->pm->prepare, error);
 		if (error)
 			goto End;
 	}
diff --git a/drivers/base/power/trace.c b/drivers/base/power/trace.c
index 2aa6e8fc4def..0a1a2c4dbc6e 100644
--- a/drivers/base/power/trace.c
+++ b/drivers/base/power/trace.c
@@ -140,7 +140,7 @@ static unsigned int hash_string(unsigned int seed, const char *data, unsigned in
 
 void set_trace_device(struct device *dev)
 {
-	dev_hash_value = hash_string(DEVSEED, dev->bus_id, DEVHASH);
+	dev_hash_value = hash_string(DEVSEED, dev_name(dev), DEVHASH);
 }
 EXPORT_SYMBOL(set_trace_device);
 
@@ -192,7 +192,7 @@ static int show_dev_hash(unsigned int value)
 
 	while (entry != &dpm_list) {
 		struct device * dev = to_device(entry);
-		unsigned int hash = hash_string(DEVSEED, dev->bus_id, DEVHASH);
+		unsigned int hash = hash_string(DEVSEED, dev_name(dev), DEVHASH);
 		if (hash == value) {
 			dev_info(dev, "hash matches\n");
 			match++;
diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c
index f20bf359b84f..edda7b6b077b 100644
--- a/drivers/block/pktcdvd.c
+++ b/drivers/block/pktcdvd.c
@@ -2790,7 +2790,7 @@ static int pkt_new_dev(struct pktcdvd_device *pd, dev_t dev)
 	return 0;
 
 out_mem:
-	blkdev_put(bdev, FMODE_READ|FMODE_WRITE);
+	blkdev_put(bdev, FMODE_READ | FMODE_NDELAY);
 	/* This is safe: open() is still holding a reference. */
 	module_put(THIS_MODULE);
 	return ret;
@@ -2975,7 +2975,7 @@ static int pkt_remove_dev(dev_t pkt_dev)
 	pkt_debugfs_dev_remove(pd);
 	pkt_sysfs_dev_remove(pd);
 
-	blkdev_put(pd->bdev, FMODE_READ|FMODE_WRITE);
+	blkdev_put(pd->bdev, FMODE_READ | FMODE_NDELAY);
 
 	remove_proc_entry(pd->name, pkt_proc);
 	DPRINTK(DRIVER_NAME": writer %s unmapped\n", pd->name);
diff --git a/drivers/block/ub.c b/drivers/block/ub.c
index 048d71d244d7..12fb816db7b0 100644
--- a/drivers/block/ub.c
+++ b/drivers/block/ub.c
@@ -1579,7 +1579,7 @@ static void ub_reset_task(struct work_struct *work)
 	struct ub_dev *sc = container_of(work, struct ub_dev, reset_work);
 	unsigned long flags;
 	struct ub_lun *lun;
-	int lkr, rc;
+	int rc;
 
 	if (!sc->reset) {
 		printk(KERN_WARNING "%s: Running reset unrequested\n",
@@ -1597,10 +1597,11 @@ static void ub_reset_task(struct work_struct *work)
 	} else if (sc->dev->actconfig->desc.bNumInterfaces != 1) {
 		;
 	} else {
-		if ((lkr = usb_lock_device_for_reset(sc->dev, sc->intf)) < 0) {
+		rc = usb_lock_device_for_reset(sc->dev, sc->intf);
+		if (rc < 0) {
 			printk(KERN_NOTICE
 			    "%s: usb_lock_device_for_reset failed (%d)\n",
-			    sc->name, lkr);
+			    sc->name, rc);
 		} else {
 			rc = usb_reset_device(sc->dev);
 			if (rc < 0) {
@@ -1608,9 +1609,7 @@ static void ub_reset_task(struct work_struct *work)
 				    "usb_lock_device_for_reset failed (%d)\n",
 				    sc->name, rc);
 			}
-
-			if (lkr)
-				usb_unlock_device(sc->dev);
+			usb_unlock_device(sc->dev);
 		}
 	}
 
diff --git a/drivers/char/Kconfig b/drivers/char/Kconfig
index 43d6ba83a191..c602b547cc6e 100644
--- a/drivers/char/Kconfig
+++ b/drivers/char/Kconfig
@@ -622,6 +622,16 @@ config HVC_BEAT
 	help
 	  Toshiba's Cell Reference Set Beat Console device driver
 
+config HVC_IUCV
+	bool "z/VM IUCV Hypervisor console support (VM only)"
+	depends on S390
+	select HVC_DRIVER
+	select IUCV
+	default y
+	help
+	  This driver provides a Hypervisor console (HVC) back-end to access
+	  a Linux (console) terminal via a z/VM IUCV communication path.
+
 config HVC_XEN
 	bool "Xen Hypervisor Console support"
 	depends on XEN
@@ -631,6 +641,12 @@ config HVC_XEN
 	help
 	  Xen virtual console device driver
 
+config HVC_UDBG
+       bool "udbg based fake hypervisor console"
+       depends on PPC && EXPERIMENTAL
+       select HVC_DRIVER
+       default n
+
 config VIRTIO_CONSOLE
 	tristate "Virtio console"
 	depends on VIRTIO
diff --git a/drivers/char/Makefile b/drivers/char/Makefile
index 438f71317c5c..0e5ced85fb2b 100644
--- a/drivers/char/Makefile
+++ b/drivers/char/Makefile
@@ -50,6 +50,8 @@ obj-$(CONFIG_HVC_BEAT)		+= hvc_beat.o
 obj-$(CONFIG_HVC_DRIVER)	+= hvc_console.o
 obj-$(CONFIG_HVC_IRQ)		+= hvc_irq.o
 obj-$(CONFIG_HVC_XEN)		+= hvc_xen.o
+obj-$(CONFIG_HVC_UDBG)		+= hvc_udbg.o
+obj-$(CONFIG_HVC_IUCV)		+= hvc_iucv.o
 obj-$(CONFIG_VIRTIO_CONSOLE)	+= virtio_console.o
 obj-$(CONFIG_RAW_DRIVER)	+= raw.o
 obj-$(CONFIG_SGI_SNSC)		+= snsc.o snsc_event.o
diff --git a/drivers/char/bsr.c b/drivers/char/bsr.c
index 456f54db73e2..977dfb1096a0 100644
--- a/drivers/char/bsr.c
+++ b/drivers/char/bsr.c
@@ -60,6 +60,8 @@ struct bsr_dev {
 	unsigned bsr_num;      /* bsr id number for its type */
 	int      bsr_minor;
 
+	struct list_head bsr_list;
+
 	dev_t    bsr_dev;
 	struct cdev bsr_cdev;
 	struct device *bsr_device;
@@ -67,8 +69,8 @@ struct bsr_dev {
 
 };
 
-static unsigned num_bsr_devs;
-static struct bsr_dev *bsr_devs;
+static unsigned total_bsr_devs;
+static struct list_head bsr_devs = LIST_HEAD_INIT(bsr_devs);
 static struct class *bsr_class;
 static int bsr_major;
 
@@ -146,24 +148,25 @@ const static struct file_operations bsr_fops = {
 
 static void bsr_cleanup_devs(void)
 {
-	int i;
-	for (i=0 ; i < num_bsr_devs; i++) {
-		struct bsr_dev *cur = bsr_devs + i;
+	struct bsr_dev *cur, *n;
+
+	list_for_each_entry_safe(cur, n, &bsr_devs, bsr_list) {
 		if (cur->bsr_device) {
 			cdev_del(&cur->bsr_cdev);
 			device_del(cur->bsr_device);
 		}
+		list_del(&cur->bsr_list);
+		kfree(cur);
 	}
-
-	kfree(bsr_devs);
 }
 
-static int bsr_create_devs(struct device_node *bn)
+static int bsr_add_node(struct device_node *bn)
 {
-	int bsr_stride_len, bsr_bytes_len;
+	int bsr_stride_len, bsr_bytes_len, num_bsr_devs;
 	const u32 *bsr_stride;
 	const u32 *bsr_bytes;
 	unsigned i;
+	int ret = -ENODEV;
 
 	bsr_stride = of_get_property(bn, "ibm,lock-stride", &bsr_stride_len);
 	bsr_bytes  = of_get_property(bn, "ibm,#lock-bytes", &bsr_bytes_len);
@@ -171,35 +174,36 @@ static int bsr_create_devs(struct device_node *bn)
 	if (!bsr_stride || !bsr_bytes ||
 	    (bsr_stride_len != bsr_bytes_len)) {
 		printk(KERN_ERR "bsr of-node has missing/incorrect property\n");
-		return -ENODEV;
+		return ret;
 	}
 
 	num_bsr_devs = bsr_bytes_len / sizeof(u32);
 
-	/* only a warning, its informational since we'll fail and exit */
-	WARN_ON(num_bsr_devs > BSR_MAX_DEVS);
-
-	bsr_devs = kzalloc(sizeof(struct bsr_dev) * num_bsr_devs, GFP_KERNEL);
-	if (!bsr_devs)
-		return -ENOMEM;
-
 	for (i = 0 ; i < num_bsr_devs; i++) {
-		struct bsr_dev *cur = bsr_devs + i;
+		struct bsr_dev *cur = kzalloc(sizeof(struct bsr_dev),
+					      GFP_KERNEL);
 		struct resource res;
 		int result;
 
+		if (!cur) {
+			printk(KERN_ERR "Unable to alloc bsr dev\n");
+			ret = -ENOMEM;
+			goto out_err;
+		}
+
 		result = of_address_to_resource(bn, i, &res);
 		if (result < 0) {
-			printk(KERN_ERR "bsr of-node has invalid reg property\n");
-			goto out_err;
+			printk(KERN_ERR "bsr of-node has invalid reg property, skipping\n");
+			kfree(cur);
+			continue;
 		}
 
-		cur->bsr_minor  = i;
+		cur->bsr_minor  = i + total_bsr_devs;
 		cur->bsr_addr   = res.start;
 		cur->bsr_len    = res.end - res.start + 1;
 		cur->bsr_bytes  = bsr_bytes[i];
 		cur->bsr_stride = bsr_stride[i];
-		cur->bsr_dev    = MKDEV(bsr_major, i);
+		cur->bsr_dev    = MKDEV(bsr_major, i + total_bsr_devs);
 
 		switch(cur->bsr_bytes) {
 		case 8:
@@ -220,14 +224,15 @@ static int bsr_create_devs(struct device_node *bn)
 		}
 
 		cur->bsr_num = bsr_types[cur->bsr_type];
-		bsr_types[cur->bsr_type] = cur->bsr_num + 1;
 		snprintf(cur->bsr_name, 32, "bsr%d_%d",
 			 cur->bsr_bytes, cur->bsr_num);
 
 		cdev_init(&cur->bsr_cdev, &bsr_fops);
 		result = cdev_add(&cur->bsr_cdev, cur->bsr_dev, 1);
-		if (result)
+		if (result) {
+			kfree(cur);
 			goto out_err;
+		}
 
 		cur->bsr_device = device_create(bsr_class, NULL, cur->bsr_dev,
 						cur, cur->bsr_name);
@@ -235,16 +240,37 @@ static int bsr_create_devs(struct device_node *bn)
 			printk(KERN_ERR "device_create failed for %s\n",
 			       cur->bsr_name);
 			cdev_del(&cur->bsr_cdev);
+			kfree(cur);
 			goto out_err;
 		}
+
+		bsr_types[cur->bsr_type] = cur->bsr_num + 1;
+		list_add_tail(&cur->bsr_list, &bsr_devs);
 	}
 
+	total_bsr_devs += num_bsr_devs;
+
 	return 0;
 
  out_err:
 
 	bsr_cleanup_devs();
-	return -ENODEV;
+	return ret;
+}
+
+static int bsr_create_devs(struct device_node *bn)
+{
+	int ret;
+
+	while (bn) {
+		ret = bsr_add_node(bn);
+		if (ret) {
+			of_node_put(bn);
+			return ret;
+		}
+		bn = of_find_compatible_node(bn, NULL, "ibm,bsr");
+	}
+	return 0;
 }
 
 static int __init bsr_init(void)
@@ -254,7 +280,7 @@ static int __init bsr_init(void)
 	int ret = -ENODEV;
 	int result;
 
-	np = of_find_compatible_node(NULL, "ibm,bsr", "ibm,bsr");
+	np = of_find_compatible_node(NULL, NULL, "ibm,bsr");
 	if (!np)
 		goto out_err;
 
@@ -272,10 +298,10 @@ static int __init bsr_init(void)
 		goto out_err_2;
 	}
 
-	if ((ret = bsr_create_devs(np)) < 0)
+	if ((ret = bsr_create_devs(np)) < 0) {
+		np = NULL;
 		goto out_err_3;
-
-	of_node_put(np);
+	}
 
 	return 0;
 
diff --git a/drivers/char/ds1620.c b/drivers/char/ds1620.c
index 74e9cd81b5b2..61f0146e215d 100644
--- a/drivers/char/ds1620.c
+++ b/drivers/char/ds1620.c
@@ -43,52 +43,51 @@ static const char *fan_state[] = { "off", "on", "on (hardwired)" };
  *  chance that the WaveArtist driver could touch these bits to
  *  enable or disable the speaker.
  */
-extern spinlock_t gpio_lock;
 extern unsigned int system_rev;
 
 static inline void netwinder_ds1620_set_clk(int clk)
 {
-	gpio_modify_op(GPIO_DSCLK, clk ? GPIO_DSCLK : 0);
+	nw_gpio_modify_op(GPIO_DSCLK, clk ? GPIO_DSCLK : 0);
 }
 
 static inline void netwinder_ds1620_set_data(int dat)
 {
-	gpio_modify_op(GPIO_DATA, dat ? GPIO_DATA : 0);
+	nw_gpio_modify_op(GPIO_DATA, dat ? GPIO_DATA : 0);
 }
 
 static inline int netwinder_ds1620_get_data(void)
 {
-	return gpio_read() & GPIO_DATA;
+	return nw_gpio_read() & GPIO_DATA;
 }
 
 static inline void netwinder_ds1620_set_data_dir(int dir)
 {
-	gpio_modify_io(GPIO_DATA, dir ? GPIO_DATA : 0);
+	nw_gpio_modify_io(GPIO_DATA, dir ? GPIO_DATA : 0);
 }
 
 static inline void netwinder_ds1620_reset(void)
 {
-	cpld_modify(CPLD_DS_ENABLE, 0);
-	cpld_modify(CPLD_DS_ENABLE, CPLD_DS_ENABLE);
+	nw_cpld_modify(CPLD_DS_ENABLE, 0);
+	nw_cpld_modify(CPLD_DS_ENABLE, CPLD_DS_ENABLE);
 }
 
 static inline void netwinder_lock(unsigned long *flags)
 {
-	spin_lock_irqsave(&gpio_lock, *flags);
+	spin_lock_irqsave(&nw_gpio_lock, *flags);
 }
 
 static inline void netwinder_unlock(unsigned long *flags)
 {
-	spin_unlock_irqrestore(&gpio_lock, *flags);
+	spin_unlock_irqrestore(&nw_gpio_lock, *flags);
 }
 
 static inline void netwinder_set_fan(int i)
 {
 	unsigned long flags;
 
-	spin_lock_irqsave(&gpio_lock, flags);
-	gpio_modify_op(GPIO_FAN, i ? GPIO_FAN : 0);
-	spin_unlock_irqrestore(&gpio_lock, flags);
+	spin_lock_irqsave(&nw_gpio_lock, flags);
+	nw_gpio_modify_op(GPIO_FAN, i ? GPIO_FAN : 0);
+	spin_unlock_irqrestore(&nw_gpio_lock, flags);
 }
 
 static inline int netwinder_get_fan(void)
@@ -96,7 +95,7 @@ static inline int netwinder_get_fan(void)
 	if ((system_rev & 0xf000) == 0x4000)
 		return FAN_ALWAYS_ON;
 
-	return (gpio_read() & GPIO_FAN) ? FAN_ON : FAN_OFF;
+	return (nw_gpio_read() & GPIO_FAN) ? FAN_ON : FAN_OFF;
 }
 
 /*
diff --git a/drivers/char/hvc_console.c b/drivers/char/hvc_console.c
index 5b819b12675a..74ecb5b2968e 100644
--- a/drivers/char/hvc_console.c
+++ b/drivers/char/hvc_console.c
@@ -689,10 +689,8 @@ EXPORT_SYMBOL_GPL(hvc_poll);
  */
 void hvc_resize(struct hvc_struct *hp, struct winsize ws)
 {
-	if ((hp->ws.ws_row != ws.ws_row) || (hp->ws.ws_col != ws.ws_col)) {
-		hp->ws = ws;
-		schedule_work(&hp->tty_resize);
-	}
+	hp->ws = ws;
+	schedule_work(&hp->tty_resize);
 }
 
 /*
diff --git a/drivers/char/hvc_console.h b/drivers/char/hvc_console.h
index 8297dbc2e6ec..3c85d78c975c 100644
--- a/drivers/char/hvc_console.h
+++ b/drivers/char/hvc_console.h
@@ -48,7 +48,7 @@ struct hvc_struct {
 	spinlock_t lock;
 	int index;
 	struct tty_struct *tty;
-	unsigned int count;
+	int count;
 	int do_wakeup;
 	char *outbuf;
 	int outbuf_size;
diff --git a/drivers/char/hvc_iseries.c b/drivers/char/hvc_iseries.c
index b74a2f8ab908..449727b6166d 100644
--- a/drivers/char/hvc_iseries.c
+++ b/drivers/char/hvc_iseries.c
@@ -575,8 +575,10 @@ static int __init hvc_find_vtys(void)
 		 * of console adapters.
 		 */
 		if ((num_found >= MAX_NR_HVC_CONSOLES) ||
-				(num_found >= VTTY_PORTS))
+				(num_found >= VTTY_PORTS)) {
+			of_node_put(vty);
 			break;
+		}
 
 		vtermno = of_get_property(vty, "reg", NULL);
 		if (!vtermno)
diff --git a/drivers/char/hvc_iucv.c b/drivers/char/hvc_iucv.c
new file mode 100644
index 000000000000..5ea7d7713fca
--- /dev/null
+++ b/drivers/char/hvc_iucv.c
@@ -0,0 +1,850 @@
+/*
+ * hvc_iucv.c - z/VM IUCV back-end for the Hypervisor Console (HVC)
+ *
+ * This back-end for HVC provides terminal access via
+ * z/VM IUCV communication paths.
+ *
+ * Copyright IBM Corp. 2008.
+ *
+ * Author(s):	Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
+ */
+#define KMSG_COMPONENT		"hvc_iucv"
+
+#include <linux/types.h>
+#include <asm/ebcdic.h>
+#include <linux/mempool.h>
+#include <linux/module.h>
+#include <linux/tty.h>
+#include <net/iucv/iucv.h>
+
+#include "hvc_console.h"
+
+
+/* HVC backend for z/VM IUCV */
+#define HVC_IUCV_MAGIC		0xc9e4c3e5
+#define MAX_HVC_IUCV_LINES	HVC_ALLOC_TTY_ADAPTERS
+#define MEMPOOL_MIN_NR		(PAGE_SIZE / sizeof(struct iucv_tty_buffer)/4)
+
+/* IUCV TTY message  */
+#define MSG_VERSION		0x02	/* Message version */
+#define MSG_TYPE_ERROR		0x01	/* Error message */
+#define MSG_TYPE_TERMENV	0x02	/* Terminal environment variable */
+#define MSG_TYPE_TERMIOS	0x04	/* Terminal IO struct update */
+#define MSG_TYPE_WINSIZE	0x08	/* Terminal window size update */
+#define MSG_TYPE_DATA		0x10	/* Terminal data */
+
+#define MSG_SIZE(s)		((s) + offsetof(struct iucv_tty_msg, data))
+struct iucv_tty_msg {
+	u8	version;		/* Message version */
+	u8	type;			/* Message type */
+#define MSG_MAX_DATALEN		(~(u16)0)
+	u16	datalen;		/* Payload length */
+	u8	data[];			/* Payload buffer */
+} __attribute__((packed));
+
+enum iucv_state_t {
+	IUCV_DISCONN	= 0,
+	IUCV_CONNECTED	= 1,
+	IUCV_SEVERED	= 2,
+};
+
+enum tty_state_t {
+	TTY_CLOSED	= 0,
+	TTY_OPENED	= 1,
+};
+
+struct hvc_iucv_private {
+	struct hvc_struct	*hvc; /* HVC console struct reference */
+	u8			srv_name[8];	/* IUCV service name (ebcdic) */
+	enum iucv_state_t	iucv_state;	/* IUCV connection status */
+	enum tty_state_t	tty_state;	/* TTY status */
+	struct iucv_path	*path;		/* IUCV path pointer */
+	spinlock_t		lock;		/* hvc_iucv_private lock */
+	struct list_head	tty_outqueue;	/* outgoing IUCV messages */
+	struct list_head	tty_inqueue;	/* incoming IUCV messages */
+};
+
+struct iucv_tty_buffer {
+	struct list_head	list;	/* list pointer */
+	struct iucv_message	msg;	/* store an incoming IUCV message */
+	size_t			offset;	/* data buffer offset */
+	struct iucv_tty_msg	*mbuf;	/* buffer to store input/output data */
+};
+
+/* IUCV callback handler */
+static	int hvc_iucv_path_pending(struct iucv_path *, u8[8], u8[16]);
+static void hvc_iucv_path_severed(struct iucv_path *, u8[16]);
+static void hvc_iucv_msg_pending(struct iucv_path *, struct iucv_message *);
+static void hvc_iucv_msg_complete(struct iucv_path *, struct iucv_message *);
+
+
+/* Kernel module parameters */
+static unsigned long hvc_iucv_devices;
+
+/* Array of allocated hvc iucv tty lines... */
+static struct hvc_iucv_private *hvc_iucv_table[MAX_HVC_IUCV_LINES];
+
+/* Kmem cache and mempool for iucv_tty_buffer elements */
+static struct kmem_cache *hvc_iucv_buffer_cache;
+static mempool_t *hvc_iucv_mempool;
+
+/* IUCV handler callback functions */
+static struct iucv_handler hvc_iucv_handler = {
+	.path_pending  = hvc_iucv_path_pending,
+	.path_severed  = hvc_iucv_path_severed,
+	.message_complete = hvc_iucv_msg_complete,
+	.message_pending  = hvc_iucv_msg_pending,
+};
+
+
+/**
+ * hvc_iucv_get_private() - Return a struct hvc_iucv_private instance.
+ * @num:	The HVC virtual terminal number (vtermno)
+ *
+ * This function returns the struct hvc_iucv_private instance that corresponds
+ * to the HVC virtual terminal number specified as parameter @num.
+ */
+struct hvc_iucv_private *hvc_iucv_get_private(uint32_t num)
+{
+	if ((num < HVC_IUCV_MAGIC) || (num - HVC_IUCV_MAGIC > hvc_iucv_devices))
+		return NULL;
+	return hvc_iucv_table[num - HVC_IUCV_MAGIC];
+}
+
+/**
+ * alloc_tty_buffer() - Returns a new struct iucv_tty_buffer element.
+ * @size:	Size of the internal buffer used to store data.
+ * @flags:	Memory allocation flags passed to mempool.
+ *
+ * This function allocates a new struct iucv_tty_buffer element and, optionally,
+ * allocates an internal data buffer with the specified size @size.
+ * Note: The total message size arises from the internal buffer size and the
+ *	 members of the iucv_tty_msg structure.
+ *
+ * The function returns NULL if memory allocation has failed.
+ */
+static struct iucv_tty_buffer *alloc_tty_buffer(size_t size, gfp_t flags)
+{
+	struct iucv_tty_buffer *bufp;
+
+	bufp = mempool_alloc(hvc_iucv_mempool, flags);
+	if (!bufp)
+		return NULL;
+	memset(bufp, 0, sizeof(struct iucv_tty_buffer));
+
+	if (size > 0) {
+		bufp->msg.length = MSG_SIZE(size);
+		bufp->mbuf = kmalloc(bufp->msg.length, flags);
+		if (!bufp->mbuf) {
+			mempool_free(bufp, hvc_iucv_mempool);
+			return NULL;
+		}
+		bufp->mbuf->version = MSG_VERSION;
+		bufp->mbuf->type    = MSG_TYPE_DATA;
+		bufp->mbuf->datalen = (u16) size;
+	}
+	return bufp;
+}
+
+/**
+ * destroy_tty_buffer() - destroy struct iucv_tty_buffer element.
+ * @bufp:	Pointer to a struct iucv_tty_buffer element, SHALL NOT be NULL.
+ *
+ * The destroy_tty_buffer() function frees the internal data buffer and returns
+ * the struct iucv_tty_buffer element back to the mempool for freeing.
+ */
+static void destroy_tty_buffer(struct iucv_tty_buffer *bufp)
+{
+	kfree(bufp->mbuf);
+	mempool_free(bufp, hvc_iucv_mempool);
+}
+
+/**
+ * destroy_tty_buffer_list() - call destroy_tty_buffer() for each list element.
+ * @list:	List head pointer to a list containing struct iucv_tty_buffer
+ *		elements.
+ *
+ * Calls destroy_tty_buffer() for each struct iucv_tty_buffer element in the
+ * list @list.
+ */
+static void destroy_tty_buffer_list(struct list_head *list)
+{
+	struct iucv_tty_buffer *ent, *next;
+
+	list_for_each_entry_safe(ent, next, list, list) {
+		list_del(&ent->list);
+		destroy_tty_buffer(ent);
+	}
+}
+
+/**
+ * hvc_iucv_write() - Receive IUCV message write data to HVC console buffer.
+ * @priv:		Pointer to hvc_iucv_private structure.
+ * @buf:		HVC console buffer for writing received terminal data.
+ * @count:		HVC console buffer size.
+ * @has_more_data:	Pointer to an int variable.
+ *
+ * The function picks up pending messages from the input queue and receives
+ * the message data that is then written to the specified buffer @buf.
+ * If the buffer size @count is less than the data message size, then the
+ * message is kept on the input queue and @has_more_data is set to 1.
+ * If the message data has been entirely written, the message is removed from
+ * the input queue.
+ *
+ * The function returns the number of bytes written to the terminal, zero if
+ * there are no pending data messages available or if there is no established
+ * IUCV path.
+ * If the IUCV path has been severed, then -EPIPE is returned to cause a
+ * hang up (that is issued by the HVC console layer).
+ */
+static int hvc_iucv_write(struct hvc_iucv_private *priv,
+			  char *buf, int count, int *has_more_data)
+{
+	struct iucv_tty_buffer *rb;
+	int written;
+	int rc;
+
+	/* Immediately return if there is no IUCV connection */
+	if (priv->iucv_state == IUCV_DISCONN)
+		return 0;
+
+	/* If the IUCV path has been severed, return -EPIPE to inform the
+	 * hvc console layer to hang up the tty device. */
+	if (priv->iucv_state == IUCV_SEVERED)
+		return -EPIPE;
+
+	/* check if there are pending messages */
+	if (list_empty(&priv->tty_inqueue))
+		return 0;
+
+	/* receive a iucv message and flip data to the tty (ldisc) */
+	rb = list_first_entry(&priv->tty_inqueue, struct iucv_tty_buffer, list);
+
+	written = 0;
+	if (!rb->mbuf) { /* message not yet received ... */
+		/* allocate mem to store msg data; if no memory is available
+		 * then leave the buffer on the list and re-try later */
+		rb->mbuf = kmalloc(rb->msg.length, GFP_ATOMIC);
+		if (!rb->mbuf)
+			return -ENOMEM;
+
+		rc = __iucv_message_receive(priv->path, &rb->msg, 0,
+					    rb->mbuf, rb->msg.length, NULL);
+		switch (rc) {
+		case 0: /* Successful	    */
+			break;
+		case 2:	/* No message found */
+		case 9: /* Message purged   */
+			break;
+		default:
+			written = -EIO;
+		}
+		/* remove buffer if an error has occured or received data
+		 * is not correct */
+		if (rc || (rb->mbuf->version != MSG_VERSION) ||
+			  (rb->msg.length    != MSG_SIZE(rb->mbuf->datalen)))
+			goto out_remove_buffer;
+	}
+
+	switch (rb->mbuf->type) {
+	case MSG_TYPE_DATA:
+		written = min_t(int, rb->mbuf->datalen - rb->offset, count);
+		memcpy(buf, rb->mbuf->data + rb->offset, written);
+		if (written < (rb->mbuf->datalen - rb->offset)) {
+			rb->offset += written;
+			*has_more_data = 1;
+			goto out_written;
+		}
+		break;
+
+	case MSG_TYPE_WINSIZE:
+		if (rb->mbuf->datalen != sizeof(struct winsize))
+			break;
+		hvc_resize(priv->hvc, *((struct winsize *)rb->mbuf->data));
+		break;
+
+	case MSG_TYPE_ERROR:	/* ignored ... */
+	case MSG_TYPE_TERMENV:	/* ignored ... */
+	case MSG_TYPE_TERMIOS:	/* ignored ... */
+		break;
+	}
+
+out_remove_buffer:
+	list_del(&rb->list);
+	destroy_tty_buffer(rb);
+	*has_more_data = !list_empty(&priv->tty_inqueue);
+
+out_written:
+	return written;
+}
+
+/**
+ * hvc_iucv_get_chars() - HVC get_chars operation.
+ * @vtermno:	HVC virtual terminal number.
+ * @buf:	Pointer to a buffer to store data
+ * @count:	Size of buffer available for writing
+ *
+ * The hvc_console thread calls this method to read characters from
+ * the terminal backend. If an IUCV communication path has been established,
+ * pending IUCV messages are received and data is copied into buffer @buf
+ * up to @count bytes.
+ *
+ * Locking:	The routine gets called under an irqsave() spinlock; and
+ *		the routine locks the struct hvc_iucv_private->lock to call
+ *		helper functions.
+ */
+static int hvc_iucv_get_chars(uint32_t vtermno, char *buf, int count)
+{
+	struct hvc_iucv_private *priv = hvc_iucv_get_private(vtermno);
+	int written;
+	int has_more_data;
+
+	if (count <= 0)
+		return 0;
+
+	if (!priv)
+		return -ENODEV;
+
+	spin_lock(&priv->lock);
+	has_more_data = 0;
+	written = hvc_iucv_write(priv, buf, count, &has_more_data);
+	spin_unlock(&priv->lock);
+
+	/* if there are still messages on the queue... schedule another run */
+	if (has_more_data)
+		hvc_kick();
+
+	return written;
+}
+
+/**
+ * hvc_iucv_send() - Send an IUCV message containing terminal data.
+ * @priv:	Pointer to struct hvc_iucv_private instance.
+ * @buf:	Buffer containing data to send.
+ * @size:	Size of buffer and amount of data to send.
+ *
+ * If an IUCV communication path is established, the function copies the buffer
+ * data to a newly allocated struct iucv_tty_buffer element, sends the data and
+ * puts the element to the outqueue.
+ *
+ * If there is no IUCV communication path established, the function returns 0.
+ * If an existing IUCV communicaton path has been severed, the function returns
+ * -EPIPE (can be passed to HVC layer to cause a tty hangup).
+ */
+static int hvc_iucv_send(struct hvc_iucv_private *priv, const char *buf,
+			 int count)
+{
+	struct iucv_tty_buffer *sb;
+	int rc;
+	u16 len;
+
+	if (priv->iucv_state == IUCV_SEVERED)
+		return -EPIPE;
+
+	if (priv->iucv_state == IUCV_DISCONN)
+		return 0;
+
+	len = min_t(u16, MSG_MAX_DATALEN, count);
+
+	/* allocate internal buffer to store msg data and also compute total
+	 * message length */
+	sb = alloc_tty_buffer(len, GFP_ATOMIC);
+	if (!sb)
+		return -ENOMEM;
+
+	sb->mbuf->datalen = len;
+	memcpy(sb->mbuf->data, buf, len);
+
+	list_add_tail(&sb->list, &priv->tty_outqueue);
+
+	rc = __iucv_message_send(priv->path, &sb->msg, 0, 0,
+				 (void *) sb->mbuf, sb->msg.length);
+	if (rc) {
+		list_del(&sb->list);
+		destroy_tty_buffer(sb);
+		len = 0;
+	}
+
+	return len;
+}
+
+/**
+ * hvc_iucv_put_chars() - HVC put_chars operation.
+ * @vtermno:	HVC virtual terminal number.
+ * @buf:	Pointer to an buffer to read data from
+ * @count:	Size of buffer available for reading
+ *
+ * The hvc_console thread calls this method to write characters from
+ * to the terminal backend.
+ * The function calls hvc_iucv_send() under the lock of the
+ * struct hvc_iucv_private instance that corresponds to the tty @vtermno.
+ *
+ * Locking:	The method gets called under an irqsave() spinlock; and
+ *		locks struct hvc_iucv_private->lock.
+ */
+static int hvc_iucv_put_chars(uint32_t vtermno, const char *buf, int count)
+{
+	struct hvc_iucv_private *priv = hvc_iucv_get_private(vtermno);
+	int sent;
+
+	if (count <= 0)
+		return 0;
+
+	if (!priv)
+		return -ENODEV;
+
+	spin_lock(&priv->lock);
+	sent = hvc_iucv_send(priv, buf, count);
+	spin_unlock(&priv->lock);
+
+	return sent;
+}
+
+/**
+ * hvc_iucv_notifier_add() - HVC notifier for opening a TTY for the first time.
+ * @hp:	Pointer to the HVC device (struct hvc_struct)
+ * @id:	Additional data (originally passed to hvc_alloc): the index of an struct
+ *	hvc_iucv_private instance.
+ *
+ * The function sets the tty state to TTY_OPEN for the struct hvc_iucv_private
+ * instance that is derived from @id. Always returns 0.
+ *
+ * Locking:	struct hvc_iucv_private->lock, spin_lock_bh
+ */
+static int hvc_iucv_notifier_add(struct hvc_struct *hp, int id)
+{
+	struct hvc_iucv_private *priv;
+
+	priv = hvc_iucv_get_private(id);
+	if (!priv)
+		return 0;
+
+	spin_lock_bh(&priv->lock);
+	priv->tty_state = TTY_OPENED;
+	spin_unlock_bh(&priv->lock);
+
+	return 0;
+}
+
+/**
+ * hvc_iucv_cleanup() - Clean up function if the tty portion is finally closed.
+ * @priv:	Pointer to the struct hvc_iucv_private instance.
+ *
+ * The functions severs the established IUCV communication path (if any), and
+ * destroy struct iucv_tty_buffer elements from the in- and outqueue. Finally,
+ * the functions resets the states to TTY_CLOSED and IUCV_DISCONN.
+ */
+static void hvc_iucv_cleanup(struct hvc_iucv_private *priv)
+{
+	destroy_tty_buffer_list(&priv->tty_outqueue);
+	destroy_tty_buffer_list(&priv->tty_inqueue);
+
+	priv->tty_state = TTY_CLOSED;
+	priv->iucv_state = IUCV_DISCONN;
+}
+
+/**
+ * hvc_iucv_notifier_hangup() - HVC notifier for tty hangups.
+ * @hp: Pointer to the HVC device (struct hvc_struct)
+ * @id: Additional data (originally passed to hvc_alloc): the index of an struct
+ *	hvc_iucv_private instance.
+ *
+ * This routine notifies the HVC backend that a tty hangup (carrier loss,
+ * virtual or otherwise) has occured.
+ *
+ * The HVC backend for z/VM IUCV ignores virtual hangups (vhangup()), to keep
+ * an existing IUCV communication path established.
+ * (Background: vhangup() is called from user space (by getty or login) to
+ *		disable writing to the tty by other applications).
+ *
+ * If the tty has been opened (e.g. getty) and an established IUCV path has been
+ * severed (we caused the tty hangup in that case), then the functions invokes
+ * hvc_iucv_cleanup() to clean up.
+ *
+ * Locking:	struct hvc_iucv_private->lock
+ */
+static void hvc_iucv_notifier_hangup(struct hvc_struct *hp, int id)
+{
+	struct hvc_iucv_private *priv;
+
+	priv = hvc_iucv_get_private(id);
+	if (!priv)
+		return;
+
+	spin_lock_bh(&priv->lock);
+	/* NOTE: If the hangup was scheduled by ourself (from the iucv
+	 *	 path_servered callback [IUCV_SEVERED]), then we have to
+	 *	 finally clean up the tty backend structure and set state to
+	 *	 TTY_CLOSED.
+	 *
+	 *	 If the tty was hung up otherwise (e.g. vhangup()), then we
+	 *	 ignore this hangup and keep an established IUCV path open...
+	 *	 (...the reason is that we are not able to connect back to the
+	 *	 client if we disconnect on hang up) */
+	priv->tty_state = TTY_CLOSED;
+
+	if (priv->iucv_state == IUCV_SEVERED)
+		hvc_iucv_cleanup(priv);
+	spin_unlock_bh(&priv->lock);
+}
+
+/**
+ * hvc_iucv_notifier_del() - HVC notifier for closing a TTY for the last time.
+ * @hp:		Pointer to the HVC device (struct hvc_struct)
+ * @id:		Additional data (originally passed to hvc_alloc):
+ *		the index of an struct hvc_iucv_private instance.
+ *
+ * This routine notifies the HVC backend that the last tty device file
+ * descriptor has been closed.
+ * The function calls hvc_iucv_cleanup() to clean up the struct hvc_iucv_private
+ * instance.
+ *
+ * Locking:	struct hvc_iucv_private->lock
+ */
+static void hvc_iucv_notifier_del(struct hvc_struct *hp, int id)
+{
+	struct hvc_iucv_private *priv;
+	struct iucv_path	*path;
+
+	priv = hvc_iucv_get_private(id);
+	if (!priv)
+		return;
+
+	spin_lock_bh(&priv->lock);
+	path = priv->path;		/* save reference to IUCV path */
+	priv->path = NULL;
+	hvc_iucv_cleanup(priv);
+	spin_unlock_bh(&priv->lock);
+
+	/* sever IUCV path outside of priv->lock due to lock ordering of:
+	 * priv->lock <--> iucv_table_lock */
+	if (path) {
+		iucv_path_sever(path, NULL);
+		iucv_path_free(path);
+	}
+}
+
+/**
+ * hvc_iucv_path_pending() - IUCV handler to process a connection request.
+ * @path:	Pending path (struct iucv_path)
+ * @ipvmid:	Originator z/VM system identifier
+ * @ipuser:	User specified data for this path
+ *		(AF_IUCV: port/service name and originator port)
+ *
+ * The function uses the @ipuser data to check to determine if the pending
+ * path belongs to a terminal managed by this HVC backend.
+ * If the check is successful, then an additional check is done to ensure
+ * that a terminal cannot be accessed multiple times (only one connection
+ * to a terminal is allowed). In that particular case, the pending path is
+ * severed. If it is the first connection, the pending path is accepted and
+ * associated to the struct hvc_iucv_private. The iucv state is updated to
+ * reflect that a communication path has been established.
+ *
+ * Returns 0 if the path belongs to a terminal managed by the this HVC backend;
+ * otherwise returns -ENODEV in order to dispatch this path to other handlers.
+ *
+ * Locking:	struct hvc_iucv_private->lock
+ */
+static	int hvc_iucv_path_pending(struct iucv_path *path,
+				  u8 ipvmid[8], u8 ipuser[16])
+{
+	struct hvc_iucv_private *priv;
+	u8 nuser_data[16];
+	int i, rc;
+
+	priv = NULL;
+	for (i = 0; i < hvc_iucv_devices; i++)
+		if (hvc_iucv_table[i] &&
+		    (0 == memcmp(hvc_iucv_table[i]->srv_name, ipuser, 8))) {
+			priv = hvc_iucv_table[i];
+			break;
+		}
+
+	if (!priv)
+		return -ENODEV;
+
+	spin_lock(&priv->lock);
+
+	/* If the terminal is already connected or being severed, then sever
+	 * this path to enforce that there is only ONE established communication
+	 * path per terminal. */
+	if (priv->iucv_state != IUCV_DISCONN) {
+		iucv_path_sever(path, ipuser);
+		iucv_path_free(path);
+		goto out_path_handled;
+	}
+
+	/* accept path */
+	memcpy(nuser_data, ipuser + 8, 8);  /* remote service (for af_iucv) */
+	memcpy(nuser_data + 8, ipuser, 8);  /* local service  (for af_iucv) */
+	path->msglim = 0xffff;		    /* IUCV MSGLIMIT */
+	path->flags &= ~IUCV_IPRMDATA;	    /* TODO: use IUCV_IPRMDATA */
+	rc = iucv_path_accept(path, &hvc_iucv_handler, nuser_data, priv);
+	if (rc) {
+		iucv_path_sever(path, ipuser);
+		iucv_path_free(path);
+		goto out_path_handled;
+	}
+	priv->path = path;
+	priv->iucv_state = IUCV_CONNECTED;
+
+out_path_handled:
+	spin_unlock(&priv->lock);
+	return 0;
+}
+
+/**
+ * hvc_iucv_path_severed() - IUCV handler to process a path sever.
+ * @path:	Pending path (struct iucv_path)
+ * @ipuser:	User specified data for this path
+ *		(AF_IUCV: port/service name and originator port)
+ *
+ * The function also severs the path (as required by the IUCV protocol) and
+ * sets the iucv state to IUCV_SEVERED for the associated struct
+ * hvc_iucv_private instance. Later, the IUCV_SEVERED state triggers a tty
+ * hangup (hvc_iucv_get_chars() / hvc_iucv_write()).
+ *
+ * If tty portion of the HVC is closed then clean up the outqueue in addition.
+ *
+ * Locking:	struct hvc_iucv_private->lock
+ */
+static void hvc_iucv_path_severed(struct iucv_path *path, u8 ipuser[16])
+{
+	struct hvc_iucv_private *priv = path->private;
+
+	spin_lock(&priv->lock);
+	priv->iucv_state = IUCV_SEVERED;
+
+	/* NOTE: If the tty has not yet been opened by a getty program
+	 *	 (e.g. to see console messages), then cleanup the
+	 *	 hvc_iucv_private structure to allow re-connects.
+	 *
+	 *	 If the tty has been opened, the get_chars() callback returns
+	 *	 -EPIPE to signal the hvc console layer to hang up the tty. */
+	priv->path = NULL;
+	if (priv->tty_state == TTY_CLOSED)
+		hvc_iucv_cleanup(priv);
+	spin_unlock(&priv->lock);
+
+	/* finally sever path (outside of priv->lock due to lock ordering) */
+	iucv_path_sever(path, ipuser);
+	iucv_path_free(path);
+}
+
+/**
+ * hvc_iucv_msg_pending() - IUCV handler to process an incoming IUCV message.
+ * @path:	Pending path (struct iucv_path)
+ * @msg:	Pointer to the IUCV message
+ *
+ * The function stores an incoming message on the input queue for later
+ * processing (by hvc_iucv_get_chars() / hvc_iucv_write()).
+ * However, if the tty has not yet been opened, the message is rejected.
+ *
+ * Locking:	struct hvc_iucv_private->lock
+ */
+static void hvc_iucv_msg_pending(struct iucv_path *path,
+				 struct iucv_message *msg)
+{
+	struct hvc_iucv_private *priv = path->private;
+	struct iucv_tty_buffer *rb;
+
+	spin_lock(&priv->lock);
+
+	/* reject messages if tty has not yet been opened */
+	if (priv->tty_state == TTY_CLOSED) {
+		iucv_message_reject(path, msg);
+		goto unlock_return;
+	}
+
+	/* allocate buffer an empty buffer element */
+	rb = alloc_tty_buffer(0, GFP_ATOMIC);
+	if (!rb) {
+		iucv_message_reject(path, msg);
+		goto unlock_return;	/* -ENOMEM */
+	}
+	rb->msg = *msg;
+
+	list_add_tail(&rb->list, &priv->tty_inqueue);
+
+	hvc_kick();	/* wakup hvc console thread */
+
+unlock_return:
+	spin_unlock(&priv->lock);
+}
+
+/**
+ * hvc_iucv_msg_complete() - IUCV handler to process message completion
+ * @path:	Pending path (struct iucv_path)
+ * @msg:	Pointer to the IUCV message
+ *
+ * The function is called upon completion of message delivery and the
+ * message is removed from the outqueue. Additional delivery information
+ * can be found in msg->audit: rejected messages (0x040000 (IPADRJCT)) and
+ * purged messages (0x010000 (IPADPGNR)).
+ *
+ * Locking:	struct hvc_iucv_private->lock
+ */
+static void hvc_iucv_msg_complete(struct iucv_path *path,
+				  struct iucv_message *msg)
+{
+	struct hvc_iucv_private *priv = path->private;
+	struct iucv_tty_buffer	*ent, *next;
+	LIST_HEAD(list_remove);
+
+	spin_lock(&priv->lock);
+	list_for_each_entry_safe(ent, next, &priv->tty_outqueue, list)
+		if (ent->msg.id == msg->id) {
+			list_move(&ent->list, &list_remove);
+			break;
+		}
+	spin_unlock(&priv->lock);
+	destroy_tty_buffer_list(&list_remove);
+}
+
+
+/* HVC operations */
+static struct hv_ops hvc_iucv_ops = {
+	.get_chars = hvc_iucv_get_chars,
+	.put_chars = hvc_iucv_put_chars,
+	.notifier_add = hvc_iucv_notifier_add,
+	.notifier_del = hvc_iucv_notifier_del,
+	.notifier_hangup = hvc_iucv_notifier_hangup,
+};
+
+/**
+ * hvc_iucv_alloc() - Allocates a new struct hvc_iucv_private instance
+ * @id:	hvc_iucv_table index
+ *
+ * This function allocates a new hvc_iucv_private struct and put the
+ * instance into hvc_iucv_table at index @id.
+ * Returns 0 on success; otherwise non-zero.
+ */
+static int __init hvc_iucv_alloc(int id)
+{
+	struct hvc_iucv_private *priv;
+	char name[9];
+	int rc;
+
+	priv = kzalloc(sizeof(struct hvc_iucv_private), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	spin_lock_init(&priv->lock);
+	INIT_LIST_HEAD(&priv->tty_outqueue);
+	INIT_LIST_HEAD(&priv->tty_inqueue);
+
+	/* Finally allocate hvc */
+	priv->hvc = hvc_alloc(HVC_IUCV_MAGIC + id,
+			      HVC_IUCV_MAGIC + id, &hvc_iucv_ops, PAGE_SIZE);
+	if (IS_ERR(priv->hvc)) {
+		rc = PTR_ERR(priv->hvc);
+		kfree(priv);
+		return rc;
+	}
+
+	/* setup iucv related information */
+	snprintf(name, 9, "ihvc%-4d", id);
+	memcpy(priv->srv_name, name, 8);
+	ASCEBC(priv->srv_name, 8);
+
+	hvc_iucv_table[id] = priv;
+	return 0;
+}
+
+/**
+ * hvc_iucv_init() - Initialization of HVC backend for z/VM IUCV
+ */
+static int __init hvc_iucv_init(void)
+{
+	int rc, i;
+
+	if (!MACHINE_IS_VM) {
+		pr_warning("The z/VM IUCV Hypervisor console cannot be "
+			   "used without z/VM.\n");
+		return -ENODEV;
+	}
+
+	if (!hvc_iucv_devices)
+		return -ENODEV;
+
+	if (hvc_iucv_devices > MAX_HVC_IUCV_LINES)
+		return -EINVAL;
+
+	hvc_iucv_buffer_cache = kmem_cache_create(KMSG_COMPONENT,
+					   sizeof(struct iucv_tty_buffer),
+					   0, 0, NULL);
+	if (!hvc_iucv_buffer_cache) {
+		pr_err("Not enough memory for driver initialization "
+			"(rs=%d).\n", 1);
+		return -ENOMEM;
+	}
+
+	hvc_iucv_mempool = mempool_create_slab_pool(MEMPOOL_MIN_NR,
+						    hvc_iucv_buffer_cache);
+	if (!hvc_iucv_mempool) {
+		pr_err("Not enough memory for driver initialization "
+			"(rs=%d).\n", 2);
+		kmem_cache_destroy(hvc_iucv_buffer_cache);
+		return -ENOMEM;
+	}
+
+	/* allocate hvc_iucv_private structs */
+	for (i = 0; i < hvc_iucv_devices; i++) {
+		rc = hvc_iucv_alloc(i);
+		if (rc) {
+			pr_err("Could not create new z/VM IUCV HVC backend "
+				"rc=%d.\n", rc);
+			goto out_error_hvc;
+		}
+	}
+
+	/* register IUCV callback handler */
+	rc = iucv_register(&hvc_iucv_handler, 0);
+	if (rc) {
+		pr_err("Could not register iucv handler (rc=%d).\n", rc);
+		goto out_error_iucv;
+	}
+
+	return 0;
+
+out_error_iucv:
+	iucv_unregister(&hvc_iucv_handler, 0);
+out_error_hvc:
+	for (i = 0; i < hvc_iucv_devices; i++)
+		if (hvc_iucv_table[i]) {
+			if (hvc_iucv_table[i]->hvc)
+				hvc_remove(hvc_iucv_table[i]->hvc);
+			kfree(hvc_iucv_table[i]);
+		}
+	mempool_destroy(hvc_iucv_mempool);
+	kmem_cache_destroy(hvc_iucv_buffer_cache);
+	return rc;
+}
+
+/**
+ * hvc_iucv_console_init() - Early console initialization
+ */
+static	int __init hvc_iucv_console_init(void)
+{
+	if (!MACHINE_IS_VM || !hvc_iucv_devices)
+		return -ENODEV;
+	return hvc_instantiate(HVC_IUCV_MAGIC, 0, &hvc_iucv_ops);
+}
+
+/**
+ * hvc_iucv_config() - Parsing of hvc_iucv=  kernel command line parameter
+ * @val:	Parameter value (numeric)
+ */
+static	int __init hvc_iucv_config(char *val)
+{
+	 return strict_strtoul(val, 10, &hvc_iucv_devices);
+}
+
+
+module_init(hvc_iucv_init);
+console_initcall(hvc_iucv_console_init);
+__setup("hvc_iucv=", hvc_iucv_config);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("HVC back-end for z/VM IUCV.");
+MODULE_AUTHOR("Hendrik Brueckner <brueckner@linux.vnet.ibm.com>");
diff --git a/drivers/char/hvc_udbg.c b/drivers/char/hvc_udbg.c
new file mode 100644
index 000000000000..bd63ba878a56
--- /dev/null
+++ b/drivers/char/hvc_udbg.c
@@ -0,0 +1,96 @@
+/*
+ * udbg interface to hvc_console.c
+ *
+ * (C) Copyright David Gibson, IBM Corporation 2008.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
+ */
+
+#include <linux/console.h>
+#include <linux/delay.h>
+#include <linux/err.h>
+#include <linux/init.h>
+#include <linux/moduleparam.h>
+#include <linux/types.h>
+#include <linux/irq.h>
+
+#include <asm/udbg.h>
+
+#include "hvc_console.h"
+
+struct hvc_struct *hvc_udbg_dev;
+
+static int hvc_udbg_put(uint32_t vtermno, const char *buf, int count)
+{
+	int i;
+
+	for (i = 0; i < count; i++)
+		udbg_putc(buf[i]);
+
+	return i;
+}
+
+static int hvc_udbg_get(uint32_t vtermno, char *buf, int count)
+{
+	int i, c;
+
+	if (!udbg_getc_poll)
+		return 0;
+
+	for (i = 0; i < count; i++) {
+		if ((c = udbg_getc_poll()) == -1)
+			break;
+		buf[i] = c;
+	}
+
+	return i;
+}
+
+static struct hv_ops hvc_udbg_ops = {
+	.get_chars = hvc_udbg_get,
+	.put_chars = hvc_udbg_put,
+};
+
+static int __init hvc_udbg_init(void)
+{
+	struct hvc_struct *hp;
+
+	BUG_ON(hvc_udbg_dev);
+
+	hp = hvc_alloc(0, NO_IRQ, &hvc_udbg_ops, 16);
+	if (IS_ERR(hp))
+		return PTR_ERR(hp);
+
+	hvc_udbg_dev = hp;
+
+	return 0;
+}
+module_init(hvc_udbg_init);
+
+static void __exit hvc_udbg_exit(void)
+{
+	if (hvc_udbg_dev)
+		hvc_remove(hvc_udbg_dev);
+}
+module_exit(hvc_udbg_exit);
+
+static int __init hvc_udbg_console_init(void)
+{
+	hvc_instantiate(0, 0, &hvc_udbg_ops);
+	add_preferred_console("hvc", 0, NULL);
+
+	return 0;
+}
+console_initcall(hvc_udbg_console_init);
diff --git a/drivers/char/hvc_vio.c b/drivers/char/hvc_vio.c
index 019e0b58593d..bd62dc86b47d 100644
--- a/drivers/char/hvc_vio.c
+++ b/drivers/char/hvc_vio.c
@@ -153,8 +153,10 @@ static int hvc_find_vtys(void)
 		/* We have statically defined space for only a certain number
 		 * of console adapters.
 		 */
-		if (num_found >= MAX_NR_HVC_CONSOLES)
+		if (num_found >= MAX_NR_HVC_CONSOLES) {
+			of_node_put(vty);
 			break;
+		}
 
 		vtermno = of_get_property(vty, "reg", NULL);
 		if (!vtermno)
diff --git a/drivers/char/hvcs.c b/drivers/char/hvcs.c
index 473d9b14439a..6e6eb445d374 100644
--- a/drivers/char/hvcs.c
+++ b/drivers/char/hvcs.c
@@ -269,7 +269,7 @@ struct hvcs_struct {
 	unsigned int index;
 
 	struct tty_struct *tty;
-	unsigned int open_count;
+	int open_count;
 
 	/*
 	 * Used to tell the driver kernel_thread what operations need to take
diff --git a/drivers/char/hvsi.c b/drivers/char/hvsi.c
index 59c6f9ab94e4..af055287271a 100644
--- a/drivers/char/hvsi.c
+++ b/drivers/char/hvsi.c
@@ -75,7 +75,7 @@ struct hvsi_struct {
 	spinlock_t lock;
 	int index;
 	struct tty_struct *tty;
-	unsigned int count;
+	int count;
 	uint8_t throttle_buf[128];
 	uint8_t outbuf[N_OUTBUF]; /* to implement write_room and chars_in_buffer */
 	/* inbuf is for packet reassembly. leave a little room for leftovers. */
diff --git a/drivers/char/mwave/mwavedd.c b/drivers/char/mwave/mwavedd.c
index 4f8d67fed292..94ad2c3bfc4a 100644
--- a/drivers/char/mwave/mwavedd.c
+++ b/drivers/char/mwave/mwavedd.c
@@ -663,7 +663,7 @@ static int __init mwave_init(void)
 #if 0
 	/* sysfs */
 	memset(&mwave_device, 0, sizeof (struct device));
-	snprintf(mwave_device.bus_id, BUS_ID_SIZE, "mwave");
+	dev_set_name(&mwave_device, "mwave");
 
 	if (device_register(&mwave_device))
 		goto cleanup_error;
diff --git a/drivers/char/nwflash.c b/drivers/char/nwflash.c
index 006be92ee3f3..8c7df5ba088f 100644
--- a/drivers/char/nwflash.c
+++ b/drivers/char/nwflash.c
@@ -58,8 +58,6 @@ static volatile unsigned char *FLASH_BASE;
 static int gbFlashSize = KFLASH_SIZE;
 static DEFINE_MUTEX(nwflash_mutex);
 
-extern spinlock_t gpio_lock;
-
 static int get_flash_id(void)
 {
 	volatile unsigned int c1, c2;
@@ -616,9 +614,9 @@ static void kick_open(void)
 	 * we want to write a bit pattern XXX1 to Xilinx to enable
 	 * the write gate, which will be open for about the next 2ms.
 	 */
-	spin_lock_irqsave(&gpio_lock, flags);
-	cpld_modify(1, 1);
-	spin_unlock_irqrestore(&gpio_lock, flags);
+	spin_lock_irqsave(&nw_gpio_lock, flags);
+	nw_cpld_modify(CPLD_FLASH_WR_ENABLE, CPLD_FLASH_WR_ENABLE);
+	spin_unlock_irqrestore(&nw_gpio_lock, flags);
 
 	/*
 	 * let the ISA bus to catch on...
diff --git a/drivers/char/serial167.c b/drivers/char/serial167.c
index 3b23270eaa65..a8f15e6be594 100644
--- a/drivers/char/serial167.c
+++ b/drivers/char/serial167.c
@@ -418,7 +418,7 @@ static irqreturn_t cd2401_rxerr_interrupt(int irq, void *dev_id)
 							     TTY_OVERRUN);
 					/*
 					   If the flip buffer itself is
-					   overflowing, we still loose
+					   overflowing, we still lose
 					   the next incoming character.
 					 */
 					if (tty_buffer_request_room(tty, 1) !=
diff --git a/drivers/char/sysrq.c b/drivers/char/sysrq.c
index ce0d9da52a8a..94966edfb44d 100644
--- a/drivers/char/sysrq.c
+++ b/drivers/char/sysrq.c
@@ -274,6 +274,22 @@ static struct sysrq_key_op sysrq_showstate_blocked_op = {
 	.enable_mask	= SYSRQ_ENABLE_DUMP,
 };
 
+#ifdef CONFIG_TRACING
+#include <linux/ftrace.h>
+
+static void sysrq_ftrace_dump(int key, struct tty_struct *tty)
+{
+	ftrace_dump();
+}
+static struct sysrq_key_op sysrq_ftrace_dump_op = {
+	.handler	= sysrq_ftrace_dump,
+	.help_msg	= "dumpZ-ftrace-buffer",
+	.action_msg	= "Dump ftrace buffer",
+	.enable_mask	= SYSRQ_ENABLE_DUMP,
+};
+#else
+#define sysrq_ftrace_dump_op (*(struct sysrq_key_op *)0)
+#endif
 
 static void sysrq_handle_showmem(int key, struct tty_struct *tty)
 {
@@ -406,7 +422,7 @@ static struct sysrq_key_op *sysrq_key_table[36] = {
 	NULL,				/* x */
 	/* y: May be registered on sparc64 for global register dump */
 	NULL,				/* y */
-	NULL				/* z */
+	&sysrq_ftrace_dump_op,		/* z */
 };
 
 /* key2index calculation, -1 on invalid index */
diff --git a/drivers/firewire/fw-cdev.c b/drivers/firewire/fw-cdev.c
index ed03234cbea8..75bbd66f852e 100644
--- a/drivers/firewire/fw-cdev.c
+++ b/drivers/firewire/fw-cdev.c
@@ -24,9 +24,11 @@
 #include <linux/errno.h>
 #include <linux/device.h>
 #include <linux/vmalloc.h>
+#include <linux/mutex.h>
 #include <linux/poll.h>
 #include <linux/preempt.h>
 #include <linux/time.h>
+#include <linux/spinlock.h>
 #include <linux/delay.h>
 #include <linux/mm.h>
 #include <linux/idr.h>
@@ -107,7 +109,6 @@ static int fw_device_op_open(struct inode *inode, struct file *file)
 {
 	struct fw_device *device;
 	struct client *client;
-	unsigned long flags;
 
 	device = fw_device_get_by_devt(inode->i_rdev);
 	if (device == NULL)
@@ -132,9 +133,9 @@ static int fw_device_op_open(struct inode *inode, struct file *file)
 
 	file->private_data = client;
 
-	spin_lock_irqsave(&device->card->lock, flags);
+	mutex_lock(&device->client_list_mutex);
 	list_add_tail(&client->link, &device->client_list);
-	spin_unlock_irqrestore(&device->card->lock, flags);
+	mutex_unlock(&device->client_list_mutex);
 
 	return 0;
 }
@@ -205,12 +206,14 @@ fw_device_op_read(struct file *file,
 	return dequeue_event(client, buffer, count);
 }
 
-/* caller must hold card->lock so that node pointers can be dereferenced here */
 static void
 fill_bus_reset_event(struct fw_cdev_event_bus_reset *event,
 		     struct client *client)
 {
 	struct fw_card *card = client->device->card;
+	unsigned long flags;
+
+	spin_lock_irqsave(&card->lock, flags);
 
 	event->closure	     = client->bus_reset_closure;
 	event->type          = FW_CDEV_EVENT_BUS_RESET;
@@ -220,22 +223,20 @@ fill_bus_reset_event(struct fw_cdev_event_bus_reset *event,
 	event->bm_node_id    = 0; /* FIXME: We don't track the BM. */
 	event->irm_node_id   = card->irm_node->node_id;
 	event->root_node_id  = card->root_node->node_id;
+
+	spin_unlock_irqrestore(&card->lock, flags);
 }
 
 static void
 for_each_client(struct fw_device *device,
 		void (*callback)(struct client *client))
 {
-	struct fw_card *card = device->card;
 	struct client *c;
-	unsigned long flags;
-
-	spin_lock_irqsave(&card->lock, flags);
 
+	mutex_lock(&device->client_list_mutex);
 	list_for_each_entry(c, &device->client_list, link)
 		callback(c);
-
-	spin_unlock_irqrestore(&card->lock, flags);
+	mutex_unlock(&device->client_list_mutex);
 }
 
 static void
@@ -243,7 +244,7 @@ queue_bus_reset_event(struct client *client)
 {
 	struct bus_reset *bus_reset;
 
-	bus_reset = kzalloc(sizeof(*bus_reset), GFP_ATOMIC);
+	bus_reset = kzalloc(sizeof(*bus_reset), GFP_KERNEL);
 	if (bus_reset == NULL) {
 		fw_notify("Out of memory when allocating bus reset event\n");
 		return;
@@ -274,11 +275,11 @@ static int ioctl_get_info(struct client *client, void *buffer)
 {
 	struct fw_cdev_get_info *get_info = buffer;
 	struct fw_cdev_event_bus_reset bus_reset;
-	struct fw_card *card = client->device->card;
 	unsigned long ret = 0;
 
 	client->version = get_info->version;
 	get_info->version = FW_CDEV_VERSION;
+	get_info->card = client->device->card->index;
 
 	down_read(&fw_device_rwsem);
 
@@ -300,18 +301,12 @@ static int ioctl_get_info(struct client *client, void *buffer)
 	client->bus_reset_closure = get_info->bus_reset_closure;
 	if (get_info->bus_reset != 0) {
 		void __user *uptr = u64_to_uptr(get_info->bus_reset);
-		unsigned long flags;
 
-		spin_lock_irqsave(&card->lock, flags);
 		fill_bus_reset_event(&bus_reset, client);
-		spin_unlock_irqrestore(&card->lock, flags);
-
 		if (copy_to_user(uptr, &bus_reset, sizeof(bus_reset)))
 			return -EFAULT;
 	}
 
-	get_info->card = card->index;
-
 	return 0;
 }
 
@@ -990,7 +985,6 @@ static int fw_device_op_release(struct inode *inode, struct file *file)
 	struct client *client = file->private_data;
 	struct event *e, *next_e;
 	struct client_resource *r, *next_r;
-	unsigned long flags;
 
 	if (client->buffer.pages)
 		fw_iso_buffer_destroy(&client->buffer, client->device->card);
@@ -1009,9 +1003,9 @@ static int fw_device_op_release(struct inode *inode, struct file *file)
 	list_for_each_entry_safe(e, next_e, &client->event_list, link)
 		kfree(e);
 
-	spin_lock_irqsave(&client->device->card->lock, flags);
+	mutex_lock(&client->device->client_list_mutex);
 	list_del(&client->link);
-	spin_unlock_irqrestore(&client->device->card->lock, flags);
+	mutex_unlock(&client->device->client_list_mutex);
 
 	fw_device_put(client->device);
 	kfree(client);
diff --git a/drivers/firewire/fw-device.c b/drivers/firewire/fw-device.c
index 6b9be42c7b98..db86d3a2382e 100644
--- a/drivers/firewire/fw-device.c
+++ b/drivers/firewire/fw-device.c
@@ -26,8 +26,10 @@
 #include <linux/delay.h>
 #include <linux/idr.h>
 #include <linux/string.h>
+#include <linux/mutex.h>
 #include <linux/rwsem.h>
 #include <linux/semaphore.h>
+#include <linux/spinlock.h>
 #include <asm/system.h>
 #include <linux/ctype.h>
 #include "fw-transaction.h"
@@ -617,7 +619,7 @@ static int shutdown_unit(struct device *device, void *data)
  */
 DECLARE_RWSEM(fw_device_rwsem);
 
-static DEFINE_IDR(fw_device_idr);
+DEFINE_IDR(fw_device_idr);
 int fw_cdev_major;
 
 struct fw_device *fw_device_get_by_devt(dev_t devt)
@@ -923,6 +925,7 @@ void fw_node_event(struct fw_card *card, struct fw_node *node, int event)
 		device->node = fw_node_get(node);
 		device->node_id = node->node_id;
 		device->generation = card->generation;
+		mutex_init(&device->client_list_mutex);
 		INIT_LIST_HEAD(&device->client_list);
 
 		/*
diff --git a/drivers/firewire/fw-device.h b/drivers/firewire/fw-device.h
index 42305bbac72f..f8ef99566863 100644
--- a/drivers/firewire/fw-device.h
+++ b/drivers/firewire/fw-device.h
@@ -21,7 +21,9 @@
 
 #include <linux/fs.h>
 #include <linux/cdev.h>
+#include <linux/idr.h>
 #include <linux/rwsem.h>
+#include <linux/mutex.h>
 #include <asm/atomic.h>
 
 enum fw_device_state {
@@ -62,7 +64,10 @@ struct fw_device {
 	bool cmc;
 	struct fw_card *card;
 	struct device device;
+
+	struct mutex client_list_mutex;
 	struct list_head client_list;
+
 	u32 *config_rom;
 	size_t config_rom_length;
 	int config_rom_retries;
@@ -99,6 +104,7 @@ void fw_device_cdev_update(struct fw_device *device);
 void fw_device_cdev_remove(struct fw_device *device);
 
 extern struct rw_semaphore fw_device_rwsem;
+extern struct idr fw_device_idr;
 extern int fw_cdev_major;
 
 /*
diff --git a/drivers/firewire/fw-ohci.c b/drivers/firewire/fw-ohci.c
index 46610b090415..91f26c34a8d3 100644
--- a/drivers/firewire/fw-ohci.c
+++ b/drivers/firewire/fw-ohci.c
@@ -1762,6 +1762,28 @@ ohci_get_bus_time(struct fw_card *card)
 	return bus_time;
 }
 
+static void copy_iso_headers(struct iso_context *ctx, void *p)
+{
+	int i = ctx->header_length;
+
+	if (i + ctx->base.header_size > PAGE_SIZE)
+		return;
+
+	/*
+	 * The iso header is byteswapped to little endian by
+	 * the controller, but the remaining header quadlets
+	 * are big endian.  We want to present all the headers
+	 * as big endian, so we have to swap the first quadlet.
+	 */
+	if (ctx->base.header_size > 0)
+		*(u32 *) (ctx->header + i) = __swab32(*(u32 *) (p + 4));
+	if (ctx->base.header_size > 4)
+		*(u32 *) (ctx->header + i + 4) = __swab32(*(u32 *) p);
+	if (ctx->base.header_size > 8)
+		memcpy(ctx->header + i + 8, p + 8, ctx->base.header_size - 8);
+	ctx->header_length += ctx->base.header_size;
+}
+
 static int handle_ir_dualbuffer_packet(struct context *context,
 				       struct descriptor *d,
 				       struct descriptor *last)
@@ -1772,7 +1794,6 @@ static int handle_ir_dualbuffer_packet(struct context *context,
 	__le32 *ir_header;
 	size_t header_length;
 	void *p, *end;
-	int i;
 
 	if (db->first_res_count != 0 && db->second_res_count != 0) {
 		if (ctx->excess_bytes <= le16_to_cpu(db->second_req_count)) {
@@ -1785,25 +1806,14 @@ static int handle_ir_dualbuffer_packet(struct context *context,
 	header_length = le16_to_cpu(db->first_req_count) -
 		le16_to_cpu(db->first_res_count);
 
-	i = ctx->header_length;
 	p = db + 1;
 	end = p + header_length;
-	while (p < end && i + ctx->base.header_size <= PAGE_SIZE) {
-		/*
-		 * The iso header is byteswapped to little endian by
-		 * the controller, but the remaining header quadlets
-		 * are big endian.  We want to present all the headers
-		 * as big endian, so we have to swap the first
-		 * quadlet.
-		 */
-		*(u32 *) (ctx->header + i) = __swab32(*(u32 *) (p + 4));
-		memcpy(ctx->header + i + 4, p + 8, ctx->base.header_size - 4);
-		i += ctx->base.header_size;
+	while (p < end) {
+		copy_iso_headers(ctx, p);
 		ctx->excess_bytes +=
 			(le32_to_cpu(*(__le32 *)(p + 4)) >> 16) & 0xffff;
-		p += ctx->base.header_size + 4;
+		p += max(ctx->base.header_size, (size_t)8);
 	}
-	ctx->header_length = i;
 
 	ctx->excess_bytes -= le16_to_cpu(db->second_req_count) -
 		le16_to_cpu(db->second_res_count);
@@ -1829,7 +1839,6 @@ static int handle_ir_packet_per_buffer(struct context *context,
 	struct descriptor *pd;
 	__le32 *ir_header;
 	void *p;
-	int i;
 
 	for (pd = d; pd <= last; pd++) {
 		if (pd->transfer_status)
@@ -1839,21 +1848,8 @@ static int handle_ir_packet_per_buffer(struct context *context,
 		/* Descriptor(s) not done yet, stop iteration */
 		return 0;
 
-	i   = ctx->header_length;
-	p   = last + 1;
-
-	if (ctx->base.header_size > 0 &&
-			i + ctx->base.header_size <= PAGE_SIZE) {
-		/*
-		 * The iso header is byteswapped to little endian by
-		 * the controller, but the remaining header quadlets
-		 * are big endian.  We want to present all the headers
-		 * as big endian, so we have to swap the first quadlet.
-		 */
-		*(u32 *) (ctx->header + i) = __swab32(*(u32 *) (p + 4));
-		memcpy(ctx->header + i + 4, p + 8, ctx->base.header_size - 4);
-		ctx->header_length += ctx->base.header_size;
-	}
+	p = last + 1;
+	copy_iso_headers(ctx, p);
 
 	if (le16_to_cpu(last->control) & DESCRIPTOR_IRQ_ALWAYS) {
 		ir_header = (__le32 *) p;
@@ -2148,11 +2144,11 @@ ohci_queue_iso_receive_dualbuffer(struct fw_iso_context *base,
 	z = 2;
 
 	/*
-	 * The OHCI controller puts the status word in the header
-	 * buffer too, so we need 4 extra bytes per packet.
+	 * The OHCI controller puts the isochronous header and trailer in the
+	 * buffer, so we need at least 8 bytes.
 	 */
 	packet_count = p->header_length / ctx->base.header_size;
-	header_size = packet_count * (ctx->base.header_size + 4);
+	header_size = packet_count * max(ctx->base.header_size, (size_t)8);
 
 	/* Get header size in number of descriptors. */
 	header_z = DIV_ROUND_UP(header_size, sizeof(*d));
@@ -2170,7 +2166,8 @@ ohci_queue_iso_receive_dualbuffer(struct fw_iso_context *base,
 		db = (struct db_descriptor *) d;
 		db->control = cpu_to_le16(DESCRIPTOR_STATUS |
 					  DESCRIPTOR_BRANCH_ALWAYS);
-		db->first_size = cpu_to_le16(ctx->base.header_size + 4);
+		db->first_size =
+		    cpu_to_le16(max(ctx->base.header_size, (size_t)8));
 		if (p->skip && rest == p->payload_length) {
 			db->control |= cpu_to_le16(DESCRIPTOR_WAIT);
 			db->first_req_count = db->first_size;
@@ -2220,11 +2217,11 @@ ohci_queue_iso_receive_packet_per_buffer(struct fw_iso_context *base,
 	int page, offset, packet_count, header_size, payload_per_buffer;
 
 	/*
-	 * The OHCI controller puts the status word in the
-	 * buffer too, so we need 4 extra bytes per packet.
+	 * The OHCI controller puts the isochronous header and trailer in the
+	 * buffer, so we need at least 8 bytes.
 	 */
 	packet_count = p->header_length / ctx->base.header_size;
-	header_size  = ctx->base.header_size + 4;
+	header_size  = max(ctx->base.header_size, (size_t)8);
 
 	/* Get header size in number of descriptors. */
 	header_z = DIV_ROUND_UP(header_size, sizeof(*d));
diff --git a/drivers/firewire/fw-sbp2.c b/drivers/firewire/fw-sbp2.c
index e54403ee59e7..e88d5067448c 100644
--- a/drivers/firewire/fw-sbp2.c
+++ b/drivers/firewire/fw-sbp2.c
@@ -670,17 +670,6 @@ static void sbp2_agent_reset_no_wait(struct sbp2_logical_unit *lu)
 			&d, sizeof(d), complete_agent_reset_write_no_wait, t);
 }
 
-static void sbp2_set_generation(struct sbp2_logical_unit *lu, int generation)
-{
-	struct fw_card *card = fw_device(lu->tgt->unit->device.parent)->card;
-	unsigned long flags;
-
-	/* serialize with comparisons of lu->generation and card->generation */
-	spin_lock_irqsave(&card->lock, flags);
-	lu->generation = generation;
-	spin_unlock_irqrestore(&card->lock, flags);
-}
-
 static inline void sbp2_allow_block(struct sbp2_logical_unit *lu)
 {
 	/*
@@ -884,7 +873,7 @@ static void sbp2_login(struct work_struct *work)
 		goto out;
 
 	generation    = device->generation;
-	smp_rmb();    /* node_id must not be older than generation */
+	smp_rmb();    /* node IDs must not be older than generation */
 	node_id       = device->node_id;
 	local_node_id = device->card->node_id;
 
@@ -908,7 +897,8 @@ static void sbp2_login(struct work_struct *work)
 
 	tgt->node_id	  = node_id;
 	tgt->address_high = local_node_id << 16;
-	sbp2_set_generation(lu, generation);
+	smp_wmb();	  /* node IDs must not be older than generation */
+	lu->generation	  = generation;
 
 	lu->command_block_agent_address =
 		((u64)(be32_to_cpu(response.command_block_agent.high) & 0xffff)
@@ -1201,7 +1191,7 @@ static void sbp2_reconnect(struct work_struct *work)
 		goto out;
 
 	generation    = device->generation;
-	smp_rmb();    /* node_id must not be older than generation */
+	smp_rmb();    /* node IDs must not be older than generation */
 	node_id       = device->node_id;
 	local_node_id = device->card->node_id;
 
@@ -1228,7 +1218,8 @@ static void sbp2_reconnect(struct work_struct *work)
 
 	tgt->node_id      = node_id;
 	tgt->address_high = local_node_id << 16;
-	sbp2_set_generation(lu, generation);
+	smp_wmb();	  /* node IDs must not be older than generation */
+	lu->generation	  = generation;
 
 	fw_notify("%s: reconnected to LUN %04x (%d retries)\n",
 		  tgt->bus_id, lu->lun, lu->retries);
diff --git a/drivers/firewire/fw-transaction.c b/drivers/firewire/fw-transaction.c
index 022ac4fabb67..2986669d5dc8 100644
--- a/drivers/firewire/fw-transaction.c
+++ b/drivers/firewire/fw-transaction.c
@@ -19,6 +19,7 @@
  */
 
 #include <linux/completion.h>
+#include <linux/idr.h>
 #include <linux/kernel.h>
 #include <linux/kref.h>
 #include <linux/module.h>
@@ -968,6 +969,7 @@ static void __exit fw_core_cleanup(void)
 {
 	unregister_chrdev(fw_cdev_major, "firewire");
 	bus_unregister(&fw_bus_type);
+	idr_destroy(&fw_device_idr);
 }
 
 module_init(fw_core_init);
diff --git a/drivers/firmware/dmi-id.c b/drivers/firmware/dmi-id.c
index e880d6c8d896..5a76d056b9d0 100644
--- a/drivers/firmware/dmi-id.c
+++ b/drivers/firmware/dmi-id.c
@@ -223,7 +223,7 @@ static int __init dmi_id_init(void)
 	}
 
 	dmi_dev->class = &dmi_class;
-	strcpy(dmi_dev->bus_id, "id");
+	dev_set_name(dmi_dev, "id");
 	dmi_dev->groups = sys_dmi_attribute_groups;
 
 	ret = device_register(dmi_dev);
diff --git a/drivers/firmware/dmi_scan.c b/drivers/firmware/dmi_scan.c
index 8daf4793ac32..4a597d8c2f70 100644
--- a/drivers/firmware/dmi_scan.c
+++ b/drivers/firmware/dmi_scan.c
@@ -467,6 +467,17 @@ const char *dmi_get_system_info(int field)
 }
 EXPORT_SYMBOL(dmi_get_system_info);
 
+/**
+ *	dmi_name_in_serial - 	Check if string is in the DMI product serial
+ *				information.
+ */
+int dmi_name_in_serial(const char *str)
+{
+	int f = DMI_PRODUCT_SERIAL;
+	if (dmi_ident[f] && strstr(dmi_ident[f], str))
+		return 1;
+	return 0;
+}
 
 /**
  *	dmi_name_in_vendors - Check if string is anywhere in the DMI vendor information.
diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index 82020abc329e..35e7aea4222c 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -1213,7 +1213,7 @@ static int gpiolib_show(struct seq_file *s, void *unused)
 		if (dev)
 			seq_printf(s, ", %s/%s",
 				dev->bus ? dev->bus->name : "no-bus",
-				dev->bus_id);
+				dev_name(dev));
 		if (chip->label)
 			seq_printf(s, ", %s", chip->label);
 		if (chip->can_sleep)
diff --git a/drivers/gpu/drm/drm_sysfs.c b/drivers/gpu/drm/drm_sysfs.c
index 1611b9bcbe7f..98a575cccbe7 100644
--- a/drivers/gpu/drm/drm_sysfs.c
+++ b/drivers/gpu/drm/drm_sysfs.c
@@ -165,7 +165,7 @@ int drm_sysfs_device_add(struct drm_minor *minor)
 	minor->kdev.devt = minor->device;
 	minor_str = "card%d";
 
-	snprintf(minor->kdev.bus_id, BUS_ID_SIZE, minor_str, minor->index);
+	dev_set_name(&minor->kdev, minor_str, minor->index);
 
 	err = device_register(&minor->kdev);
 	if (err) {
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 0a4f39b9a0ec..adc972cc6bfc 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -244,6 +244,10 @@ typedef struct drm_i915_private {
 		 * List of objects currently involved in rendering from the
 		 * ringbuffer.
 		 *
+		 * Includes buffers having the contents of their GPU caches
+		 * flushed, not necessarily primitives.  last_rendering_seqno
+		 * represents when the rendering involved will be completed.
+		 *
 		 * A reference is held on the buffer while on this list.
 		 */
 		struct list_head active_list;
@@ -253,6 +257,8 @@ typedef struct drm_i915_private {
 		 * still have a write_domain which needs to be flushed before
 		 * unbinding.
 		 *
+		 * last_rendering_seqno is 0 while an object is in this list.
+		 *
 		 * A reference is held on the buffer while on this list.
 		 */
 		struct list_head flushing_list;
@@ -261,6 +267,8 @@ typedef struct drm_i915_private {
 		 * LRU list of objects which are not in the ringbuffer and
 		 * are ready to unbind, but are still in the GTT.
 		 *
+		 * last_rendering_seqno is 0 while an object is in this list.
+		 *
 		 * A reference is not held on the buffer while on this list,
 		 * as merely being GTT-bound shouldn't prevent its being
 		 * freed, and we'll pull it off the list in the free path.
@@ -371,8 +379,8 @@ struct drm_i915_gem_object {
 	uint32_t agp_type;
 
 	/**
-	 * Flagging of which individual pages are valid in GEM_DOMAIN_CPU when
-	 * GEM_DOMAIN_CPU is not in the object's read domain.
+	 * If present, while GEM_DOMAIN_CPU is in the read domain this array
+	 * flags which individual pages are valid.
 	 */
 	uint8_t *page_cpu_valid;
 };
@@ -394,9 +402,6 @@ struct drm_i915_gem_request {
 	/** Time at which this request was emitted, in jiffies. */
 	unsigned long emitted_jiffies;
 
-	/** Cache domains that were flushed at the start of the request. */
-	uint32_t flush_domains;
-
 	struct list_head list;
 };
 
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index d58ddef468f8..3fde82be014f 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -33,21 +33,21 @@
 
 #define I915_GEM_GPU_DOMAINS	(~(I915_GEM_DOMAIN_CPU | I915_GEM_DOMAIN_GTT))
 
-static int
-i915_gem_object_set_domain(struct drm_gem_object *obj,
-			    uint32_t read_domains,
-			    uint32_t write_domain);
-static int
-i915_gem_object_set_domain_range(struct drm_gem_object *obj,
-				 uint64_t offset,
-				 uint64_t size,
-				 uint32_t read_domains,
-				 uint32_t write_domain);
-static int
-i915_gem_set_domain(struct drm_gem_object *obj,
-		    struct drm_file *file_priv,
-		    uint32_t read_domains,
-		    uint32_t write_domain);
+static void
+i915_gem_object_set_to_gpu_domain(struct drm_gem_object *obj,
+				  uint32_t read_domains,
+				  uint32_t write_domain);
+static void i915_gem_object_flush_gpu_write_domain(struct drm_gem_object *obj);
+static void i915_gem_object_flush_gtt_write_domain(struct drm_gem_object *obj);
+static void i915_gem_object_flush_cpu_write_domain(struct drm_gem_object *obj);
+static int i915_gem_object_set_to_gtt_domain(struct drm_gem_object *obj,
+					     int write);
+static int i915_gem_object_set_to_cpu_domain(struct drm_gem_object *obj,
+					     int write);
+static int i915_gem_object_set_cpu_read_domain_range(struct drm_gem_object *obj,
+						     uint64_t offset,
+						     uint64_t size);
+static void i915_gem_object_set_to_full_cpu_read_domain(struct drm_gem_object *obj);
 static int i915_gem_object_get_page_list(struct drm_gem_object *obj);
 static void i915_gem_object_free_page_list(struct drm_gem_object *obj);
 static int i915_gem_object_wait_rendering(struct drm_gem_object *obj);
@@ -162,8 +162,8 @@ i915_gem_pread_ioctl(struct drm_device *dev, void *data,
 
 	mutex_lock(&dev->struct_mutex);
 
-	ret = i915_gem_object_set_domain_range(obj, args->offset, args->size,
-					       I915_GEM_DOMAIN_CPU, 0);
+	ret = i915_gem_object_set_cpu_read_domain_range(obj, args->offset,
+							args->size);
 	if (ret != 0) {
 		drm_gem_object_unreference(obj);
 		mutex_unlock(&dev->struct_mutex);
@@ -260,8 +260,7 @@ i915_gem_gtt_pwrite(struct drm_device *dev, struct drm_gem_object *obj,
 		mutex_unlock(&dev->struct_mutex);
 		return ret;
 	}
-	ret = i915_gem_set_domain(obj, file_priv,
-				  I915_GEM_DOMAIN_GTT, I915_GEM_DOMAIN_GTT);
+	ret = i915_gem_object_set_to_gtt_domain(obj, 1);
 	if (ret)
 		goto fail;
 
@@ -320,8 +319,7 @@ i915_gem_shmem_pwrite(struct drm_device *dev, struct drm_gem_object *obj,
 
 	mutex_lock(&dev->struct_mutex);
 
-	ret = i915_gem_set_domain(obj, file_priv,
-				  I915_GEM_DOMAIN_CPU, I915_GEM_DOMAIN_CPU);
+	ret = i915_gem_object_set_to_cpu_domain(obj, 1);
 	if (ret) {
 		mutex_unlock(&dev->struct_mutex);
 		return ret;
@@ -397,7 +395,8 @@ i915_gem_pwrite_ioctl(struct drm_device *dev, void *data,
 }
 
 /**
- * Called when user space prepares to use an object
+ * Called when user space prepares to use an object with the CPU, either
+ * through the mmap ioctl's mapping or a GTT mapping.
  */
 int
 i915_gem_set_domain_ioctl(struct drm_device *dev, void *data,
@@ -405,11 +404,26 @@ i915_gem_set_domain_ioctl(struct drm_device *dev, void *data,
 {
 	struct drm_i915_gem_set_domain *args = data;
 	struct drm_gem_object *obj;
+	uint32_t read_domains = args->read_domains;
+	uint32_t write_domain = args->write_domain;
 	int ret;
 
 	if (!(dev->driver->driver_features & DRIVER_GEM))
 		return -ENODEV;
 
+	/* Only handle setting domains to types used by the CPU. */
+	if (write_domain & ~(I915_GEM_DOMAIN_CPU | I915_GEM_DOMAIN_GTT))
+		return -EINVAL;
+
+	if (read_domains & ~(I915_GEM_DOMAIN_CPU | I915_GEM_DOMAIN_GTT))
+		return -EINVAL;
+
+	/* Having something in the write domain implies it's in the read
+	 * domain, and only that read domain.  Enforce that in the request.
+	 */
+	if (write_domain != 0 && read_domains != write_domain)
+		return -EINVAL;
+
 	obj = drm_gem_object_lookup(dev, file_priv, args->handle);
 	if (obj == NULL)
 		return -EBADF;
@@ -417,10 +431,21 @@ i915_gem_set_domain_ioctl(struct drm_device *dev, void *data,
 	mutex_lock(&dev->struct_mutex);
 #if WATCH_BUF
 	DRM_INFO("set_domain_ioctl %p(%d), %08x %08x\n",
-		 obj, obj->size, args->read_domains, args->write_domain);
+		 obj, obj->size, read_domains, write_domain);
 #endif
-	ret = i915_gem_set_domain(obj, file_priv,
-				  args->read_domains, args->write_domain);
+	if (read_domains & I915_GEM_DOMAIN_GTT) {
+		ret = i915_gem_object_set_to_gtt_domain(obj, write_domain != 0);
+
+		/* Silently promote "you're not bound, there was nothing to do"
+		 * to success, since the client was just asking us to
+		 * make sure everything was done.
+		 */
+		if (ret == -EINVAL)
+			ret = 0;
+	} else {
+		ret = i915_gem_object_set_to_cpu_domain(obj, write_domain != 0);
+	}
+
 	drm_gem_object_unreference(obj);
 	mutex_unlock(&dev->struct_mutex);
 	return ret;
@@ -455,10 +480,9 @@ i915_gem_sw_finish_ioctl(struct drm_device *dev, void *data,
 	obj_priv = obj->driver_private;
 
 	/* Pinned buffers may be scanout, so flush the cache */
-	if ((obj->write_domain & I915_GEM_DOMAIN_CPU) && obj_priv->pin_count) {
-		i915_gem_clflush_object(obj);
-		drm_agp_chipset_flush(dev);
-	}
+	if (obj_priv->pin_count)
+		i915_gem_object_flush_cpu_write_domain(obj);
+
 	drm_gem_object_unreference(obj);
 	mutex_unlock(&dev->struct_mutex);
 	return ret;
@@ -532,7 +556,7 @@ i915_gem_object_free_page_list(struct drm_gem_object *obj)
 }
 
 static void
-i915_gem_object_move_to_active(struct drm_gem_object *obj)
+i915_gem_object_move_to_active(struct drm_gem_object *obj, uint32_t seqno)
 {
 	struct drm_device *dev = obj->dev;
 	drm_i915_private_t *dev_priv = dev->dev_private;
@@ -546,8 +570,20 @@ i915_gem_object_move_to_active(struct drm_gem_object *obj)
 	/* Move from whatever list we were on to the tail of execution. */
 	list_move_tail(&obj_priv->list,
 		       &dev_priv->mm.active_list);
+	obj_priv->last_rendering_seqno = seqno;
 }
 
+static void
+i915_gem_object_move_to_flushing(struct drm_gem_object *obj)
+{
+	struct drm_device *dev = obj->dev;
+	drm_i915_private_t *dev_priv = dev->dev_private;
+	struct drm_i915_gem_object *obj_priv = obj->driver_private;
+
+	BUG_ON(!obj_priv->active);
+	list_move_tail(&obj_priv->list, &dev_priv->mm.flushing_list);
+	obj_priv->last_rendering_seqno = 0;
+}
 
 static void
 i915_gem_object_move_to_inactive(struct drm_gem_object *obj)
@@ -562,6 +598,7 @@ i915_gem_object_move_to_inactive(struct drm_gem_object *obj)
 	else
 		list_move_tail(&obj_priv->list, &dev_priv->mm.inactive_list);
 
+	obj_priv->last_rendering_seqno = 0;
 	if (obj_priv->active) {
 		obj_priv->active = 0;
 		drm_gem_object_unreference(obj);
@@ -610,10 +647,28 @@ i915_add_request(struct drm_device *dev, uint32_t flush_domains)
 
 	request->seqno = seqno;
 	request->emitted_jiffies = jiffies;
-	request->flush_domains = flush_domains;
 	was_empty = list_empty(&dev_priv->mm.request_list);
 	list_add_tail(&request->list, &dev_priv->mm.request_list);
 
+	/* Associate any objects on the flushing list matching the write
+	 * domain we're flushing with our flush.
+	 */
+	if (flush_domains != 0) {
+		struct drm_i915_gem_object *obj_priv, *next;
+
+		list_for_each_entry_safe(obj_priv, next,
+					 &dev_priv->mm.flushing_list, list) {
+			struct drm_gem_object *obj = obj_priv->obj;
+
+			if ((obj->write_domain & flush_domains) ==
+			    obj->write_domain) {
+				obj->write_domain = 0;
+				i915_gem_object_move_to_active(obj, seqno);
+			}
+		}
+
+	}
+
 	if (was_empty && !dev_priv->mm.suspended)
 		schedule_delayed_work(&dev_priv->mm.retire_work, HZ);
 	return seqno;
@@ -676,30 +731,10 @@ i915_gem_retire_request(struct drm_device *dev,
 			 __func__, request->seqno, obj);
 #endif
 
-		if (obj->write_domain != 0) {
-			list_move_tail(&obj_priv->list,
-				       &dev_priv->mm.flushing_list);
-		} else {
+		if (obj->write_domain != 0)
+			i915_gem_object_move_to_flushing(obj);
+		else
 			i915_gem_object_move_to_inactive(obj);
-		}
-	}
-
-	if (request->flush_domains != 0) {
-		struct drm_i915_gem_object *obj_priv, *next;
-
-		/* Clear the write domain and activity from any buffers
-		 * that are just waiting for a flush matching the one retired.
-		 */
-		list_for_each_entry_safe(obj_priv, next,
-					 &dev_priv->mm.flushing_list, list) {
-			struct drm_gem_object *obj = obj_priv->obj;
-
-			if (obj->write_domain & request->flush_domains) {
-				obj->write_domain = 0;
-				i915_gem_object_move_to_inactive(obj);
-			}
-		}
-
 	}
 }
 
@@ -892,25 +927,10 @@ i915_gem_object_wait_rendering(struct drm_gem_object *obj)
 	struct drm_i915_gem_object *obj_priv = obj->driver_private;
 	int ret;
 
-	/* If there are writes queued to the buffer, flush and
-	 * create a new seqno to wait for.
+	/* This function only exists to support waiting for existing rendering,
+	 * not for emitting required flushes.
 	 */
-	if (obj->write_domain & ~(I915_GEM_DOMAIN_CPU|I915_GEM_DOMAIN_GTT)) {
-		uint32_t write_domain = obj->write_domain;
-#if WATCH_BUF
-		DRM_INFO("%s: flushing object %p from write domain %08x\n",
-			  __func__, obj, write_domain);
-#endif
-		i915_gem_flush(dev, 0, write_domain);
-
-		i915_gem_object_move_to_active(obj);
-		obj_priv->last_rendering_seqno = i915_add_request(dev,
-								  write_domain);
-		BUG_ON(obj_priv->last_rendering_seqno == 0);
-#if WATCH_LRU
-		DRM_INFO("%s: flush moves to exec list %p\n", __func__, obj);
-#endif
-	}
+	BUG_ON((obj->write_domain & I915_GEM_GPU_DOMAINS) != 0);
 
 	/* If there is rendering queued on the buffer being evicted, wait for
 	 * it.
@@ -950,24 +970,16 @@ i915_gem_object_unbind(struct drm_gem_object *obj)
 		return -EINVAL;
 	}
 
-	/* Wait for any rendering to complete
-	 */
-	ret = i915_gem_object_wait_rendering(obj);
-	if (ret) {
-		DRM_ERROR("wait_rendering failed: %d\n", ret);
-		return ret;
-	}
-
 	/* Move the object to the CPU domain to ensure that
 	 * any possible CPU writes while it's not in the GTT
 	 * are flushed when we go to remap it. This will
 	 * also ensure that all pending GPU writes are finished
 	 * before we unbind.
 	 */
-	ret = i915_gem_object_set_domain(obj, I915_GEM_DOMAIN_CPU,
-					 I915_GEM_DOMAIN_CPU);
+	ret = i915_gem_object_set_to_cpu_domain(obj, 1);
 	if (ret) {
-		DRM_ERROR("set_domain failed: %d\n", ret);
+		if (ret != -ERESTARTSYS)
+			DRM_ERROR("set_domain failed: %d\n", ret);
 		return ret;
 	}
 
@@ -1083,6 +1095,19 @@ i915_gem_evict_something(struct drm_device *dev)
 }
 
 static int
+i915_gem_evict_everything(struct drm_device *dev)
+{
+	int ret;
+
+	for (;;) {
+		ret = i915_gem_evict_something(dev);
+		if (ret != 0)
+			break;
+	}
+	return ret;
+}
+
+static int
 i915_gem_object_get_page_list(struct drm_gem_object *obj)
 {
 	struct drm_i915_gem_object *obj_priv = obj->driver_private;
@@ -1168,7 +1193,8 @@ i915_gem_object_bind_to_gtt(struct drm_gem_object *obj, unsigned alignment)
 
 		ret = i915_gem_evict_something(dev);
 		if (ret != 0) {
-			DRM_ERROR("Failed to evict a buffer %d\n", ret);
+			if (ret != -ERESTARTSYS)
+				DRM_ERROR("Failed to evict a buffer %d\n", ret);
 			return ret;
 		}
 		goto search_free;
@@ -1228,6 +1254,143 @@ i915_gem_clflush_object(struct drm_gem_object *obj)
 	drm_clflush_pages(obj_priv->page_list, obj->size / PAGE_SIZE);
 }
 
+/** Flushes any GPU write domain for the object if it's dirty. */
+static void
+i915_gem_object_flush_gpu_write_domain(struct drm_gem_object *obj)
+{
+	struct drm_device *dev = obj->dev;
+	uint32_t seqno;
+
+	if ((obj->write_domain & I915_GEM_GPU_DOMAINS) == 0)
+		return;
+
+	/* Queue the GPU write cache flushing we need. */
+	i915_gem_flush(dev, 0, obj->write_domain);
+	seqno = i915_add_request(dev, obj->write_domain);
+	obj->write_domain = 0;
+	i915_gem_object_move_to_active(obj, seqno);
+}
+
+/** Flushes the GTT write domain for the object if it's dirty. */
+static void
+i915_gem_object_flush_gtt_write_domain(struct drm_gem_object *obj)
+{
+	if (obj->write_domain != I915_GEM_DOMAIN_GTT)
+		return;
+
+	/* No actual flushing is required for the GTT write domain.   Writes
+	 * to it immediately go to main memory as far as we know, so there's
+	 * no chipset flush.  It also doesn't land in render cache.
+	 */
+	obj->write_domain = 0;
+}
+
+/** Flushes the CPU write domain for the object if it's dirty. */
+static void
+i915_gem_object_flush_cpu_write_domain(struct drm_gem_object *obj)
+{
+	struct drm_device *dev = obj->dev;
+
+	if (obj->write_domain != I915_GEM_DOMAIN_CPU)
+		return;
+
+	i915_gem_clflush_object(obj);
+	drm_agp_chipset_flush(dev);
+	obj->write_domain = 0;
+}
+
+/**
+ * Moves a single object to the GTT read, and possibly write domain.
+ *
+ * This function returns when the move is complete, including waiting on
+ * flushes to occur.
+ */
+static int
+i915_gem_object_set_to_gtt_domain(struct drm_gem_object *obj, int write)
+{
+	struct drm_i915_gem_object *obj_priv = obj->driver_private;
+	int ret;
+
+	/* Not valid to be called on unbound objects. */
+	if (obj_priv->gtt_space == NULL)
+		return -EINVAL;
+
+	i915_gem_object_flush_gpu_write_domain(obj);
+	/* Wait on any GPU rendering and flushing to occur. */
+	ret = i915_gem_object_wait_rendering(obj);
+	if (ret != 0)
+		return ret;
+
+	/* If we're writing through the GTT domain, then CPU and GPU caches
+	 * will need to be invalidated at next use.
+	 */
+	if (write)
+		obj->read_domains &= I915_GEM_DOMAIN_GTT;
+
+	i915_gem_object_flush_cpu_write_domain(obj);
+
+	/* It should now be out of any other write domains, and we can update
+	 * the domain values for our changes.
+	 */
+	BUG_ON((obj->write_domain & ~I915_GEM_DOMAIN_GTT) != 0);
+	obj->read_domains |= I915_GEM_DOMAIN_GTT;
+	if (write) {
+		obj->write_domain = I915_GEM_DOMAIN_GTT;
+		obj_priv->dirty = 1;
+	}
+
+	return 0;
+}
+
+/**
+ * Moves a single object to the CPU read, and possibly write domain.
+ *
+ * This function returns when the move is complete, including waiting on
+ * flushes to occur.
+ */
+static int
+i915_gem_object_set_to_cpu_domain(struct drm_gem_object *obj, int write)
+{
+	struct drm_device *dev = obj->dev;
+	int ret;
+
+	i915_gem_object_flush_gpu_write_domain(obj);
+	/* Wait on any GPU rendering and flushing to occur. */
+	ret = i915_gem_object_wait_rendering(obj);
+	if (ret != 0)
+		return ret;
+
+	i915_gem_object_flush_gtt_write_domain(obj);
+
+	/* If we have a partially-valid cache of the object in the CPU,
+	 * finish invalidating it and free the per-page flags.
+	 */
+	i915_gem_object_set_to_full_cpu_read_domain(obj);
+
+	/* Flush the CPU cache if it's still invalid. */
+	if ((obj->read_domains & I915_GEM_DOMAIN_CPU) == 0) {
+		i915_gem_clflush_object(obj);
+		drm_agp_chipset_flush(dev);
+
+		obj->read_domains |= I915_GEM_DOMAIN_CPU;
+	}
+
+	/* It should now be out of any other write domains, and we can update
+	 * the domain values for our changes.
+	 */
+	BUG_ON((obj->write_domain & ~I915_GEM_DOMAIN_CPU) != 0);
+
+	/* If we're writing through the CPU, then the GPU read domains will
+	 * need to be invalidated at next use.
+	 */
+	if (write) {
+		obj->read_domains &= I915_GEM_DOMAIN_CPU;
+		obj->write_domain = I915_GEM_DOMAIN_CPU;
+	}
+
+	return 0;
+}
+
 /*
  * Set the next domain for the specified object. This
  * may not actually perform the necessary flushing/invaliding though,
@@ -1339,16 +1502,18 @@ i915_gem_clflush_object(struct drm_gem_object *obj)
  *		MI_FLUSH
  *		drm_agp_chipset_flush
  */
-static int
-i915_gem_object_set_domain(struct drm_gem_object *obj,
-			    uint32_t read_domains,
-			    uint32_t write_domain)
+static void
+i915_gem_object_set_to_gpu_domain(struct drm_gem_object *obj,
+				  uint32_t read_domains,
+				  uint32_t write_domain)
 {
 	struct drm_device		*dev = obj->dev;
 	struct drm_i915_gem_object	*obj_priv = obj->driver_private;
 	uint32_t			invalidate_domains = 0;
 	uint32_t			flush_domains = 0;
-	int				ret;
+
+	BUG_ON(read_domains & I915_GEM_DOMAIN_CPU);
+	BUG_ON(write_domain == I915_GEM_DOMAIN_CPU);
 
 #if WATCH_BUF
 	DRM_INFO("%s: object %p read %08x -> %08x write %08x -> %08x\n",
@@ -1385,34 +1550,11 @@ i915_gem_object_set_domain(struct drm_gem_object *obj,
 		DRM_INFO("%s: CPU domain flush %08x invalidate %08x\n",
 			 __func__, flush_domains, invalidate_domains);
 #endif
-		/*
-		 * If we're invaliding the CPU cache and flushing a GPU cache,
-		 * then pause for rendering so that the GPU caches will be
-		 * flushed before the cpu cache is invalidated
-		 */
-		if ((invalidate_domains & I915_GEM_DOMAIN_CPU) &&
-		    (flush_domains & ~(I915_GEM_DOMAIN_CPU |
-				       I915_GEM_DOMAIN_GTT))) {
-			ret = i915_gem_object_wait_rendering(obj);
-			if (ret)
-				return ret;
-		}
 		i915_gem_clflush_object(obj);
 	}
 
 	if ((write_domain | flush_domains) != 0)
 		obj->write_domain = write_domain;
-
-	/* If we're invalidating the CPU domain, clear the per-page CPU
-	 * domain list as well.
-	 */
-	if (obj_priv->page_cpu_valid != NULL &&
-	    (write_domain != 0 ||
-	     read_domains & I915_GEM_DOMAIN_CPU)) {
-		drm_free(obj_priv->page_cpu_valid, obj->size / PAGE_SIZE,
-			 DRM_MEM_DRIVER);
-		obj_priv->page_cpu_valid = NULL;
-	}
 	obj->read_domains = read_domains;
 
 	dev->invalidate_domains |= invalidate_domains;
@@ -1423,47 +1565,94 @@ i915_gem_object_set_domain(struct drm_gem_object *obj,
 		 obj->read_domains, obj->write_domain,
 		 dev->invalidate_domains, dev->flush_domains);
 #endif
-	return 0;
 }
 
 /**
- * Set the read/write domain on a range of the object.
+ * Moves the object from a partially CPU read to a full one.
  *
- * Currently only implemented for CPU reads, otherwise drops to normal
- * i915_gem_object_set_domain().
+ * Note that this only resolves i915_gem_object_set_cpu_read_domain_range(),
+ * and doesn't handle transitioning from !(read_domains & I915_GEM_DOMAIN_CPU).
  */
-static int
-i915_gem_object_set_domain_range(struct drm_gem_object *obj,
-				 uint64_t offset,
-				 uint64_t size,
-				 uint32_t read_domains,
-				 uint32_t write_domain)
+static void
+i915_gem_object_set_to_full_cpu_read_domain(struct drm_gem_object *obj)
 {
+	struct drm_device *dev = obj->dev;
 	struct drm_i915_gem_object *obj_priv = obj->driver_private;
-	int ret, i;
 
-	if (obj->read_domains & I915_GEM_DOMAIN_CPU)
-		return 0;
+	if (!obj_priv->page_cpu_valid)
+		return;
 
-	if (read_domains != I915_GEM_DOMAIN_CPU ||
-	    write_domain != 0)
-		return i915_gem_object_set_domain(obj,
-						  read_domains, write_domain);
+	/* If we're partially in the CPU read domain, finish moving it in.
+	 */
+	if (obj->read_domains & I915_GEM_DOMAIN_CPU) {
+		int i;
 
-	/* Wait on any GPU rendering to the object to be flushed. */
+		for (i = 0; i <= (obj->size - 1) / PAGE_SIZE; i++) {
+			if (obj_priv->page_cpu_valid[i])
+				continue;
+			drm_clflush_pages(obj_priv->page_list + i, 1);
+		}
+		drm_agp_chipset_flush(dev);
+	}
+
+	/* Free the page_cpu_valid mappings which are now stale, whether
+	 * or not we've got I915_GEM_DOMAIN_CPU.
+	 */
+	drm_free(obj_priv->page_cpu_valid, obj->size / PAGE_SIZE,
+		 DRM_MEM_DRIVER);
+	obj_priv->page_cpu_valid = NULL;
+}
+
+/**
+ * Set the CPU read domain on a range of the object.
+ *
+ * The object ends up with I915_GEM_DOMAIN_CPU in its read flags although it's
+ * not entirely valid.  The page_cpu_valid member of the object flags which
+ * pages have been flushed, and will be respected by
+ * i915_gem_object_set_to_cpu_domain() if it's called on to get a valid mapping
+ * of the whole object.
+ *
+ * This function returns when the move is complete, including waiting on
+ * flushes to occur.
+ */
+static int
+i915_gem_object_set_cpu_read_domain_range(struct drm_gem_object *obj,
+					  uint64_t offset, uint64_t size)
+{
+	struct drm_i915_gem_object *obj_priv = obj->driver_private;
+	int i, ret;
+
+	if (offset == 0 && size == obj->size)
+		return i915_gem_object_set_to_cpu_domain(obj, 0);
+
+	i915_gem_object_flush_gpu_write_domain(obj);
+	/* Wait on any GPU rendering and flushing to occur. */
 	ret = i915_gem_object_wait_rendering(obj);
-	if (ret)
+	if (ret != 0)
 		return ret;
+	i915_gem_object_flush_gtt_write_domain(obj);
 
+	/* If we're already fully in the CPU read domain, we're done. */
+	if (obj_priv->page_cpu_valid == NULL &&
+	    (obj->read_domains & I915_GEM_DOMAIN_CPU) != 0)
+		return 0;
+
+	/* Otherwise, create/clear the per-page CPU read domain flag if we're
+	 * newly adding I915_GEM_DOMAIN_CPU
+	 */
 	if (obj_priv->page_cpu_valid == NULL) {
 		obj_priv->page_cpu_valid = drm_calloc(1, obj->size / PAGE_SIZE,
 						      DRM_MEM_DRIVER);
-	}
+		if (obj_priv->page_cpu_valid == NULL)
+			return -ENOMEM;
+	} else if ((obj->read_domains & I915_GEM_DOMAIN_CPU) == 0)
+		memset(obj_priv->page_cpu_valid, 0, obj->size / PAGE_SIZE);
 
 	/* Flush the cache on any pages that are still invalid from the CPU's
 	 * perspective.
 	 */
-	for (i = offset / PAGE_SIZE; i <= (offset + size - 1) / PAGE_SIZE; i++) {
+	for (i = offset / PAGE_SIZE; i <= (offset + size - 1) / PAGE_SIZE;
+	     i++) {
 		if (obj_priv->page_cpu_valid[i])
 			continue;
 
@@ -1472,39 +1661,14 @@ i915_gem_object_set_domain_range(struct drm_gem_object *obj,
 		obj_priv->page_cpu_valid[i] = 1;
 	}
 
-	return 0;
-}
-
-/**
- * Once all of the objects have been set in the proper domain,
- * perform the necessary flush and invalidate operations.
- *
- * Returns the write domains flushed, for use in flush tracking.
- */
-static uint32_t
-i915_gem_dev_set_domain(struct drm_device *dev)
-{
-	uint32_t flush_domains = dev->flush_domains;
-
-	/*
-	 * Now that all the buffers are synced to the proper domains,
-	 * flush and invalidate the collected domains
+	/* It should now be out of any other write domains, and we can update
+	 * the domain values for our changes.
 	 */
-	if (dev->invalidate_domains | dev->flush_domains) {
-#if WATCH_EXEC
-		DRM_INFO("%s: invalidate_domains %08x flush_domains %08x\n",
-			  __func__,
-			 dev->invalidate_domains,
-			 dev->flush_domains);
-#endif
-		i915_gem_flush(dev,
-			       dev->invalidate_domains,
-			       dev->flush_domains);
-		dev->invalidate_domains = 0;
-		dev->flush_domains = 0;
-	}
+	BUG_ON((obj->write_domain & ~I915_GEM_DOMAIN_CPU) != 0);
 
-	return flush_domains;
+	obj->read_domains |= I915_GEM_DOMAIN_CPU;
+
+	return 0;
 }
 
 /**
@@ -1585,6 +1749,18 @@ i915_gem_object_pin_and_relocate(struct drm_gem_object *obj,
 			return -EINVAL;
 		}
 
+		if (reloc.write_domain & I915_GEM_DOMAIN_CPU ||
+		    reloc.read_domains & I915_GEM_DOMAIN_CPU) {
+			DRM_ERROR("reloc with read/write CPU domains: "
+				  "obj %p target %d offset %d "
+				  "read %08x write %08x",
+				  obj, reloc.target_handle,
+				  (int) reloc.offset,
+				  reloc.read_domains,
+				  reloc.write_domain);
+			return -EINVAL;
+		}
+
 		if (reloc.write_domain && target_obj->pending_write_domain &&
 		    reloc.write_domain != target_obj->pending_write_domain) {
 			DRM_ERROR("Write domain conflict: "
@@ -1625,19 +1801,11 @@ i915_gem_object_pin_and_relocate(struct drm_gem_object *obj,
 			continue;
 		}
 
-		/* Now that we're going to actually write some data in,
-		 * make sure that any rendering using this buffer's contents
-		 * is completed.
-		 */
-		i915_gem_object_wait_rendering(obj);
-
-		/* As we're writing through the gtt, flush
-		 * any CPU writes before we write the relocations
-		 */
-		if (obj->write_domain & I915_GEM_DOMAIN_CPU) {
-			i915_gem_clflush_object(obj);
-			drm_agp_chipset_flush(dev);
-			obj->write_domain = 0;
+		ret = i915_gem_object_set_to_gtt_domain(obj, 1);
+		if (ret != 0) {
+			drm_gem_object_unreference(target_obj);
+			i915_gem_object_unpin(obj);
+			return -EINVAL;
 		}
 
 		/* Map the page containing the relocation we're going to
@@ -1779,6 +1947,7 @@ i915_gem_execbuffer(struct drm_device *dev, void *data,
 	int ret, i, pinned = 0;
 	uint64_t exec_offset;
 	uint32_t seqno, flush_domains;
+	int pin_tries;
 
 #if WATCH_EXEC
 	DRM_INFO("buffers_ptr %d buffer_count %d len %08x\n",
@@ -1827,14 +1996,7 @@ i915_gem_execbuffer(struct drm_device *dev, void *data,
 		return -EBUSY;
 	}
 
-	/* Zero the gloabl flush/invalidate flags. These
-	 * will be modified as each object is bound to the
-	 * gtt
-	 */
-	dev->invalidate_domains = 0;
-	dev->flush_domains = 0;
-
-	/* Look up object handles and perform the relocations */
+	/* Look up object handles */
 	for (i = 0; i < args->buffer_count; i++) {
 		object_list[i] = drm_gem_object_lookup(dev, file_priv,
 						       exec_list[i].handle);
@@ -1844,17 +2006,39 @@ i915_gem_execbuffer(struct drm_device *dev, void *data,
 			ret = -EBADF;
 			goto err;
 		}
+	}
 
-		object_list[i]->pending_read_domains = 0;
-		object_list[i]->pending_write_domain = 0;
-		ret = i915_gem_object_pin_and_relocate(object_list[i],
-						       file_priv,
-						       &exec_list[i]);
-		if (ret) {
-			DRM_ERROR("object bind and relocate failed %d\n", ret);
+	/* Pin and relocate */
+	for (pin_tries = 0; ; pin_tries++) {
+		ret = 0;
+		for (i = 0; i < args->buffer_count; i++) {
+			object_list[i]->pending_read_domains = 0;
+			object_list[i]->pending_write_domain = 0;
+			ret = i915_gem_object_pin_and_relocate(object_list[i],
+							       file_priv,
+							       &exec_list[i]);
+			if (ret)
+				break;
+			pinned = i + 1;
+		}
+		/* success */
+		if (ret == 0)
+			break;
+
+		/* error other than GTT full, or we've already tried again */
+		if (ret != -ENOMEM || pin_tries >= 1) {
+			DRM_ERROR("Failed to pin buffers %d\n", ret);
 			goto err;
 		}
-		pinned = i + 1;
+
+		/* unpin all of our buffers */
+		for (i = 0; i < pinned; i++)
+			i915_gem_object_unpin(object_list[i]);
+
+		/* evict everyone we can from the aperture */
+		ret = i915_gem_evict_everything(dev);
+		if (ret)
+			goto err;
 	}
 
 	/* Set the pending read domains for the batch buffer to COMMAND */
@@ -1864,21 +2048,37 @@ i915_gem_execbuffer(struct drm_device *dev, void *data,
 
 	i915_verify_inactive(dev, __FILE__, __LINE__);
 
+	/* Zero the global flush/invalidate flags. These
+	 * will be modified as new domains are computed
+	 * for each object
+	 */
+	dev->invalidate_domains = 0;
+	dev->flush_domains = 0;
+
 	for (i = 0; i < args->buffer_count; i++) {
 		struct drm_gem_object *obj = object_list[i];
 
-		/* make sure all previous memory operations have passed */
-		ret = i915_gem_object_set_domain(obj,
-						 obj->pending_read_domains,
-						 obj->pending_write_domain);
-		if (ret)
-			goto err;
+		/* Compute new gpu domains and update invalidate/flush */
+		i915_gem_object_set_to_gpu_domain(obj,
+						  obj->pending_read_domains,
+						  obj->pending_write_domain);
 	}
 
 	i915_verify_inactive(dev, __FILE__, __LINE__);
 
-	/* Flush/invalidate caches and chipset buffer */
-	flush_domains = i915_gem_dev_set_domain(dev);
+	if (dev->invalidate_domains | dev->flush_domains) {
+#if WATCH_EXEC
+		DRM_INFO("%s: invalidate_domains %08x flush_domains %08x\n",
+			  __func__,
+			 dev->invalidate_domains,
+			 dev->flush_domains);
+#endif
+		i915_gem_flush(dev,
+			       dev->invalidate_domains,
+			       dev->flush_domains);
+		if (dev->flush_domains)
+			(void)i915_add_request(dev, dev->flush_domains);
+	}
 
 	i915_verify_inactive(dev, __FILE__, __LINE__);
 
@@ -1898,8 +2098,6 @@ i915_gem_execbuffer(struct drm_device *dev, void *data,
 			      ~0);
 #endif
 
-	(void)i915_add_request(dev, flush_domains);
-
 	/* Exec the batchbuffer */
 	ret = i915_dispatch_gem_execbuffer(dev, args, exec_offset);
 	if (ret) {
@@ -1927,10 +2125,8 @@ i915_gem_execbuffer(struct drm_device *dev, void *data,
 	i915_file_priv->mm.last_gem_seqno = seqno;
 	for (i = 0; i < args->buffer_count; i++) {
 		struct drm_gem_object *obj = object_list[i];
-		struct drm_i915_gem_object *obj_priv = obj->driver_private;
 
-		i915_gem_object_move_to_active(obj);
-		obj_priv->last_rendering_seqno = seqno;
+		i915_gem_object_move_to_active(obj, seqno);
 #if WATCH_LRU
 		DRM_INFO("%s: move to exec list %p\n", __func__, obj);
 #endif
@@ -2061,11 +2257,7 @@ i915_gem_pin_ioctl(struct drm_device *dev, void *data,
 	/* XXX - flush the CPU caches for pinned objects
 	 * as the X server doesn't manage domains yet
 	 */
-	if (obj->write_domain & I915_GEM_DOMAIN_CPU) {
-		i915_gem_clflush_object(obj);
-		drm_agp_chipset_flush(dev);
-		obj->write_domain = 0;
-	}
+	i915_gem_object_flush_cpu_write_domain(obj);
 	args->offset = obj_priv->gtt_offset;
 	drm_gem_object_unreference(obj);
 	mutex_unlock(&dev->struct_mutex);
@@ -2167,29 +2359,6 @@ void i915_gem_free_object(struct drm_gem_object *obj)
 	drm_free(obj->driver_private, 1, DRM_MEM_DRIVER);
 }
 
-static int
-i915_gem_set_domain(struct drm_gem_object *obj,
-		    struct drm_file *file_priv,
-		    uint32_t read_domains,
-		    uint32_t write_domain)
-{
-	struct drm_device *dev = obj->dev;
-	int ret;
-	uint32_t flush_domains;
-
-	BUG_ON(!mutex_is_locked(&dev->struct_mutex));
-
-	ret = i915_gem_object_set_domain(obj, read_domains, write_domain);
-	if (ret)
-		return ret;
-	flush_domains = i915_gem_dev_set_domain(obj->dev);
-
-	if (flush_domains & ~(I915_GEM_DOMAIN_CPU|I915_GEM_DOMAIN_GTT))
-		(void) i915_add_request(dev, flush_domains);
-
-	return 0;
-}
-
 /** Unbinds all objects that are on the given buffer list. */
 static int
 i915_gem_evict_from_list(struct drm_device *dev, struct list_head *head)
diff --git a/drivers/gpu/drm/i915/i915_gem_proc.c b/drivers/gpu/drm/i915/i915_gem_proc.c
index 93de15b4c9a7..e8d5abe1250e 100644
--- a/drivers/gpu/drm/i915/i915_gem_proc.c
+++ b/drivers/gpu/drm/i915/i915_gem_proc.c
@@ -166,10 +166,9 @@ static int i915_gem_request_info(char *buf, char **start, off_t offset,
 	list_for_each_entry(gem_request, &dev_priv->mm.request_list,
 			    list)
 	{
-		DRM_PROC_PRINT("    %d @ %d %08x\n",
+		DRM_PROC_PRINT("    %d @ %d\n",
 			       gem_request->seqno,
-			       (int) (jiffies - gem_request->emitted_jiffies),
-			       gem_request->flush_domains);
+			       (int) (jiffies - gem_request->emitted_jiffies));
 	}
 	if (len > request + offset)
 		return request;
diff --git a/drivers/gpu/drm/i915/i915_gem_tiling.c b/drivers/gpu/drm/i915/i915_gem_tiling.c
index e8b85ac4ca04..a8cb69469c64 100644
--- a/drivers/gpu/drm/i915/i915_gem_tiling.c
+++ b/drivers/gpu/drm/i915/i915_gem_tiling.c
@@ -119,9 +119,10 @@ i915_gem_detect_bit_6_swizzle(struct drm_device *dev)
 			    dcc & DCC_CHANNEL_XOR_DISABLE) {
 				swizzle_x = I915_BIT_6_SWIZZLE_9_10;
 				swizzle_y = I915_BIT_6_SWIZZLE_9;
-			} else if (IS_I965GM(dev) || IS_GM45(dev)) {
-				/* GM965 only does bit 11-based channel
-				 * randomization
+			} else if ((IS_I965GM(dev) || IS_GM45(dev)) &&
+				   (dcc & DCC_CHANNEL_XOR_BIT_17) == 0) {
+				/* GM965/GM45 does either bit 11 or bit 17
+				 * swizzling.
 				 */
 				swizzle_x = I915_BIT_6_SWIZZLE_9_10_11;
 				swizzle_y = I915_BIT_6_SWIZZLE_9_11;
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 0e476eba36e6..9d24aaeb8a45 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -522,6 +522,7 @@
 #define DCC_ADDRESSING_MODE_DUAL_CHANNEL_INTERLEAVED	(2 << 0)
 #define DCC_ADDRESSING_MODE_MASK			(3 << 0)
 #define DCC_CHANNEL_XOR_DISABLE				(1 << 10)
+#define DCC_CHANNEL_XOR_BIT_17				(1 << 9)
 
 /** 965 MCH register controlling DRAM channel configuration */
 #define C0DRB3			0x10206
diff --git a/drivers/hid/Kconfig b/drivers/hid/Kconfig
index b4fd8ca701a4..aadef9abc05d 100644
--- a/drivers/hid/Kconfig
+++ b/drivers/hid/Kconfig
@@ -107,13 +107,6 @@ config HID_BELKIN
 	---help---
 	Support for Belkin Flip KVM and Wireless keyboard.
 
-config HID_BRIGHT
-	tristate "Bright" if EMBEDDED
-	depends on USB_HID
-	default y
-	---help---
-	Support for Bright ABNT-2 keyboard.
-
 config HID_CHERRY
 	tristate "Cherry" if EMBEDDED
 	depends on USB_HID
@@ -135,14 +128,6 @@ config HID_CYPRESS
 	---help---
 	Support for cypress mouse and barcode readers.
 
-config HID_DELL
-	tristate "Dell" if EMBEDDED
-	depends on USB_HID
-	default y
-	---help---
-	Support for quirky Dell HID hardware that require
-	special LED handling (W7658 and SK8115 models)
-
 config HID_EZKEY
 	tristate "Ezkey" if EMBEDDED
 	depends on USB_HID
@@ -202,6 +187,13 @@ config HID_MONTEREY
 	---help---
 	Support for Monterey Genius KB29E.
 
+config HID_NTRIG
+	tristate "NTrig" if EMBEDDED
+	depends on USB_HID
+	default y
+	---help---
+	Support for N-Trig touch screen.
+
 config HID_PANTHERLORD
 	tristate "Pantherlord devices support" if EMBEDDED
 	depends on USB_HID
diff --git a/drivers/hid/Makefile b/drivers/hid/Makefile
index b09e43e7413e..7d34e8bf3de5 100644
--- a/drivers/hid/Makefile
+++ b/drivers/hid/Makefile
@@ -23,16 +23,15 @@ endif
 obj-$(CONFIG_HID_A4TECH)	+= hid-a4tech.o
 obj-$(CONFIG_HID_APPLE)		+= hid-apple.o
 obj-$(CONFIG_HID_BELKIN)	+= hid-belkin.o
-obj-$(CONFIG_HID_BRIGHT)	+= hid-bright.o
 obj-$(CONFIG_HID_CHERRY)	+= hid-cherry.o
 obj-$(CONFIG_HID_CHICONY)	+= hid-chicony.o
 obj-$(CONFIG_HID_CYPRESS)	+= hid-cypress.o
-obj-$(CONFIG_HID_DELL)		+= hid-dell.o
 obj-$(CONFIG_HID_EZKEY)		+= hid-ezkey.o
 obj-$(CONFIG_HID_GYRATION)	+= hid-gyration.o
 obj-$(CONFIG_HID_LOGITECH)	+= hid-logitech.o
 obj-$(CONFIG_HID_MICROSOFT)	+= hid-microsoft.o
 obj-$(CONFIG_HID_MONTEREY)	+= hid-monterey.o
+obj-$(CONFIG_HID_NTRIG)		+= hid-ntrig.o
 obj-$(CONFIG_HID_PANTHERLORD)	+= hid-pl.o
 obj-$(CONFIG_HID_PETALYNX)	+= hid-petalynx.o
 obj-$(CONFIG_HID_SAMSUNG)	+= hid-samsung.o
diff --git a/drivers/hid/hid-bright.c b/drivers/hid/hid-bright.c
deleted file mode 100644
index 38517a117dfd..000000000000
--- a/drivers/hid/hid-bright.c
+++ /dev/null
@@ -1,71 +0,0 @@
-/*
- *  HID driver for some bright "special" devices
- *
- *  Copyright (c) 2008 Mauro Carvalho Chehab <mchehab@redhat.com>
- *
- * Based on hid-dell driver
- */
-
-/*
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the Free
- * Software Foundation; either version 2 of the License, or (at your option)
- * any later version.
- */
-
-#include <linux/device.h>
-#include <linux/hid.h>
-#include <linux/module.h>
-
-#include "hid-ids.h"
-
-static int bright_probe(struct hid_device *hdev, const struct hid_device_id *id)
-{
-	int ret;
-
-	ret = hid_parse(hdev);
-	if (ret) {
-		dev_err(&hdev->dev, "parse failed\n");
-		goto err_free;
-	}
-
-	ret = hid_hw_start(hdev, HID_CONNECT_DEFAULT);
-	if (ret) {
-		dev_err(&hdev->dev, "hw start failed\n");
-		goto err_free;
-	}
-
-	usbhid_set_leds(hdev);
-
-	return 0;
-err_free:
-	return ret;
-}
-
-static const struct hid_device_id bright_devices[] = {
-	{ HID_USB_DEVICE(USB_VENDOR_ID_BRIGHT, USB_DEVICE_ID_BRIGHT_ABNT2) },
-	{ }
-};
-MODULE_DEVICE_TABLE(hid, bright_devices);
-
-static struct hid_driver bright_driver = {
-	.name = "bright",
-	.id_table = bright_devices,
-	.probe = bright_probe,
-};
-
-static int bright_init(void)
-{
-	return hid_register_driver(&bright_driver);
-}
-
-static void bright_exit(void)
-{
-	hid_unregister_driver(&bright_driver);
-}
-
-module_init(bright_init);
-module_exit(bright_exit);
-MODULE_LICENSE("GPL");
-
-HID_COMPAT_LOAD_DRIVER(bright);
diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c
index 40df3e1b4bd1..34cc3b0d01f6 100644
--- a/drivers/hid/hid-core.c
+++ b/drivers/hid/hid-core.c
@@ -1256,16 +1256,12 @@ static const struct hid_device_id hid_blacklist[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_FOUNTAIN_TP_ONLY) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_GEYSER1_TP_ONLY) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_BELKIN, USB_DEVICE_ID_FLIP_KVM) },
-	{ HID_USB_DEVICE(USB_VENDOR_ID_BRIGHT, USB_DEVICE_ID_BRIGHT_ABNT2) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_CHERRY, USB_DEVICE_ID_CHERRY_CYMOTION) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_CHICONY, USB_DEVICE_ID_CHICONY_TACTICAL_PAD) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_CYPRESS, USB_DEVICE_ID_CYPRESS_BARCODE_1) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_CYPRESS, USB_DEVICE_ID_CYPRESS_BARCODE_2) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_CYPRESS, USB_DEVICE_ID_CYPRESS_MOUSE) },
-	{ HID_USB_DEVICE(USB_VENDOR_ID_DELL, USB_DEVICE_ID_DELL_W7658) },
-	{ HID_USB_DEVICE(USB_VENDOR_ID_DELL, USB_DEVICE_ID_DELL_SK8115) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_EZKEY, USB_DEVICE_ID_BTC_8193) },
-	{ HID_USB_DEVICE(USB_VENDOR_ID_GENERIC_13BA, USB_DEVICE_ID_GENERIC_13BA_KBD_MOUSE) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_GAMERON, USB_DEVICE_ID_GAMERON_DUAL_PSX_ADAPTOR) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_GAMERON, USB_DEVICE_ID_GAMERON_DUAL_PCS_ADAPTOR) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_GREENASIA, 0x0003) },
@@ -1279,7 +1275,6 @@ static const struct hid_device_id hid_blacklist[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_DINOVO_DESKTOP) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_DINOVO_EDGE) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_DINOVO_MINI) },
-	{ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_KBD) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_ELITE_KBD) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_CORDLESS_DESKTOP_LX500) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_EXTREME_3D) },
@@ -1297,6 +1292,7 @@ static const struct hid_device_id hid_blacklist[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_PRESENTER_8K_USB) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_WIRELESS_OPTICAL_DESKTOP_3_0) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_MONTEREY, USB_DEVICE_ID_GENIUS_KB29E) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_NTRIG, USB_DEVICE_ID_NTRIG_TOUCH_SCREEN) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_PETALYNX, USB_DEVICE_ID_PETALYNX_MAXTER_REMOTE) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_SAMSUNG, USB_DEVICE_ID_SAMSUNG_IR_REMOTE) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_SONY, USB_DEVICE_ID_SONY_PS3_CONTROLLER) },
@@ -1308,12 +1304,92 @@ static const struct hid_device_id hid_blacklist[] = {
 	{ }
 };
 
+struct hid_dynid {
+	struct list_head list;
+	struct hid_device_id id;
+};
+
+/**
+ * store_new_id - add a new HID device ID to this driver and re-probe devices
+ * @driver: target device driver
+ * @buf: buffer for scanning device ID data
+ * @count: input size
+ *
+ * Adds a new dynamic hid device ID to this driver,
+ * and causes the driver to probe for all devices again.
+ */
+static ssize_t store_new_id(struct device_driver *drv, const char *buf,
+		size_t count)
+{
+	struct hid_driver *hdrv = container_of(drv, struct hid_driver, driver);
+	struct hid_dynid *dynid;
+	__u32 bus, vendor, product;
+	unsigned long driver_data = 0;
+	int ret;
+
+	ret = sscanf(buf, "%x %x %x %lx",
+			&bus, &vendor, &product, &driver_data);
+	if (ret < 3)
+		return -EINVAL;
+
+	dynid = kzalloc(sizeof(*dynid), GFP_KERNEL);
+	if (!dynid)
+		return -ENOMEM;
+
+	dynid->id.bus = bus;
+	dynid->id.vendor = vendor;
+	dynid->id.product = product;
+	dynid->id.driver_data = driver_data;
+
+	spin_lock(&hdrv->dyn_lock);
+	list_add_tail(&dynid->list, &hdrv->dyn_list);
+	spin_unlock(&hdrv->dyn_lock);
+
+	ret = 0;
+	if (get_driver(&hdrv->driver)) {
+		ret = driver_attach(&hdrv->driver);
+		put_driver(&hdrv->driver);
+	}
+
+	return ret ? : count;
+}
+static DRIVER_ATTR(new_id, S_IWUSR, NULL, store_new_id);
+
+static void hid_free_dynids(struct hid_driver *hdrv)
+{
+	struct hid_dynid *dynid, *n;
+
+	spin_lock(&hdrv->dyn_lock);
+	list_for_each_entry_safe(dynid, n, &hdrv->dyn_list, list) {
+		list_del(&dynid->list);
+		kfree(dynid);
+	}
+	spin_unlock(&hdrv->dyn_lock);
+}
+
+static const struct hid_device_id *hid_match_device(struct hid_device *hdev,
+		struct hid_driver *hdrv)
+{
+	struct hid_dynid *dynid;
+
+	spin_lock(&hdrv->dyn_lock);
+	list_for_each_entry(dynid, &hdrv->dyn_list, list) {
+		if (hid_match_one_id(hdev, &dynid->id)) {
+			spin_unlock(&hdrv->dyn_lock);
+			return &dynid->id;
+		}
+	}
+	spin_unlock(&hdrv->dyn_lock);
+
+	return hid_match_id(hdev, hdrv->id_table);
+}
+
 static int hid_bus_match(struct device *dev, struct device_driver *drv)
 {
 	struct hid_driver *hdrv = container_of(drv, struct hid_driver, driver);
 	struct hid_device *hdev = container_of(dev, struct hid_device, dev);
 
-	if (!hid_match_id(hdev, hdrv->id_table))
+	if (!hid_match_device(hdev, hdrv))
 		return 0;
 
 	/* generic wants all non-blacklisted */
@@ -1332,7 +1408,7 @@ static int hid_device_probe(struct device *dev)
 	int ret = 0;
 
 	if (!hdev->driver) {
-		id = hid_match_id(hdev, hdrv->id_table);
+		id = hid_match_device(hdev, hdrv);
 		if (id == NULL)
 			return -ENODEV;
 
@@ -1577,6 +1653,9 @@ static const struct hid_device_id hid_mouse_ignore_list[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING2_ANSI) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING2_ISO) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING2_JIS) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING3_ANSI) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING3_ISO) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING3_JIS) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_FOUNTAIN_TP_ONLY) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_GEYSER1_TP_ONLY) },
 	{ }
@@ -1618,9 +1697,10 @@ int hid_add_device(struct hid_device *hdev)
 	if (hid_ignore(hdev))
 		return -ENODEV;
 
-	/* XXX hack, any other cleaner solution < 20 bus_id bytes? */
-	sprintf(hdev->dev.bus_id, "%04X:%04X:%04X.%04X", hdev->bus,
-			hdev->vendor, hdev->product, atomic_inc_return(&id));
+	/* XXX hack, any other cleaner solution after the driver core
+	 * is converted to allow more than 20 bytes as the device name? */
+	dev_set_name(&hdev->dev, "%04X:%04X:%04X.%04X", hdev->bus,
+		     hdev->vendor, hdev->product, atomic_inc_return(&id));
 
 	ret = device_add(&hdev->dev);
 	if (!ret)
@@ -1695,18 +1775,33 @@ EXPORT_SYMBOL_GPL(hid_destroy_device);
 int __hid_register_driver(struct hid_driver *hdrv, struct module *owner,
 		const char *mod_name)
 {
+	int ret;
+
 	hdrv->driver.name = hdrv->name;
 	hdrv->driver.bus = &hid_bus_type;
 	hdrv->driver.owner = owner;
 	hdrv->driver.mod_name = mod_name;
 
-	return driver_register(&hdrv->driver);
+	INIT_LIST_HEAD(&hdrv->dyn_list);
+	spin_lock_init(&hdrv->dyn_lock);
+
+	ret = driver_register(&hdrv->driver);
+	if (ret)
+		return ret;
+
+	ret = driver_create_file(&hdrv->driver, &driver_attr_new_id);
+	if (ret)
+		driver_unregister(&hdrv->driver);
+
+	return ret;
 }
 EXPORT_SYMBOL_GPL(__hid_register_driver);
 
 void hid_unregister_driver(struct hid_driver *hdrv)
 {
+	driver_remove_file(&hdrv->driver, &driver_attr_new_id);
 	driver_unregister(&hdrv->driver);
+	hid_free_dynids(hdrv);
 }
 EXPORT_SYMBOL_GPL(hid_unregister_driver);
 
diff --git a/drivers/hid/hid-dell.c b/drivers/hid/hid-dell.c
deleted file mode 100644
index f5474300b83a..000000000000
--- a/drivers/hid/hid-dell.c
+++ /dev/null
@@ -1,76 +0,0 @@
-/*
- *  HID driver for some dell "special" devices
- *
- *  Copyright (c) 1999 Andreas Gal
- *  Copyright (c) 2000-2005 Vojtech Pavlik <vojtech@suse.cz>
- *  Copyright (c) 2005 Michael Haboustak <mike-@cinci.rr.com> for Concept2, Inc
- *  Copyright (c) 2006-2007 Jiri Kosina
- *  Copyright (c) 2007 Paul Walmsley
- *  Copyright (c) 2008 Jiri Slaby
- */
-
-/*
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the Free
- * Software Foundation; either version 2 of the License, or (at your option)
- * any later version.
- */
-
-#include <linux/device.h>
-#include <linux/hid.h>
-#include <linux/module.h>
-
-#include "hid-ids.h"
-
-static int dell_probe(struct hid_device *hdev, const struct hid_device_id *id)
-{
-	int ret;
-
-	ret = hid_parse(hdev);
-	if (ret) {
-		dev_err(&hdev->dev, "parse failed\n");
-		goto err_free;
-	}
-
-	ret = hid_hw_start(hdev, HID_CONNECT_DEFAULT);
-	if (ret) {
-		dev_err(&hdev->dev, "hw start failed\n");
-		goto err_free;
-	}
-
-	usbhid_set_leds(hdev);
-
-	return 0;
-err_free:
-	return ret;
-}
-
-static const struct hid_device_id dell_devices[] = {
-	{ HID_USB_DEVICE(USB_VENDOR_ID_DELL, USB_DEVICE_ID_DELL_W7658) },
-	{ HID_USB_DEVICE(USB_VENDOR_ID_DELL, USB_DEVICE_ID_DELL_SK8115) },
-	{ HID_USB_DEVICE(USB_VENDOR_ID_GENERIC_13BA, USB_DEVICE_ID_GENERIC_13BA_KBD_MOUSE) },
-	{ }
-};
-MODULE_DEVICE_TABLE(hid, dell_devices);
-
-static struct hid_driver dell_driver = {
-	.name = "dell",
-	.id_table = dell_devices,
-	.probe = dell_probe,
-};
-
-static int dell_init(void)
-{
-	return hid_register_driver(&dell_driver);
-}
-
-static void dell_exit(void)
-{
-	hid_unregister_driver(&dell_driver);
-}
-
-module_init(dell_init);
-module_exit(dell_exit);
-MODULE_LICENSE("GPL");
-
-HID_COMPAT_LOAD_DRIVER(dell);
diff --git a/drivers/hid/hid-dummy.c b/drivers/hid/hid-dummy.c
index e148f86fb58e..4a6af3cf192d 100644
--- a/drivers/hid/hid-dummy.c
+++ b/drivers/hid/hid-dummy.c
@@ -43,6 +43,9 @@ static int __init hid_dummy_init(void)
 #ifdef CONFIG_HID_MONTEREY_MODULE
 	HID_COMPAT_CALL_DRIVER(monterey);
 #endif
+#ifdef CONFIG_HID_NTRIG_MODULE
+	HID_COMPAT_CALL_DRIVER(ntrig);
+#endif
 #ifdef CONFIG_HID_PANTHERLORD_MODULE
 	HID_COMPAT_CALL_DRIVER(pantherlord);
 #endif
diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h
index 39289699c32f..2b7b6eeae8c6 100644
--- a/drivers/hid/hid-ids.h
+++ b/drivers/hid/hid-ids.h
@@ -107,9 +107,6 @@
 #define USB_VENDOR_ID_BELKIN           0x050d
 #define USB_DEVICE_ID_FLIP_KVM         0x3201
 
-#define USB_VENDOR_ID_BRIGHT		0x1241
-#define USB_DEVICE_ID_BRIGHT_ABNT2	0x1503
-
 #define USB_VENDOR_ID_BERKSHIRE		0x0c98
 #define USB_DEVICE_ID_BERKSHIRE_PCWD	0x1140
 
@@ -141,10 +138,6 @@
 #define USB_DEVICE_ID_CYPRESS_BARCODE_1	0xde61
 #define USB_DEVICE_ID_CYPRESS_BARCODE_2	0xde64
 
-#define USB_VENDOR_ID_DELL		0x413c
-#define USB_DEVICE_ID_DELL_W7658	0x2005
-#define USB_DEVICE_ID_DELL_SK8115	0x2105
-
 #define USB_VENDOR_ID_DELORME		0x1163
 #define USB_DEVICE_ID_DELORME_EARTHMATE 0x0100
 #define USB_DEVICE_ID_DELORME_EM_LT20	0x0200
@@ -167,9 +160,6 @@
 
 #define USB_VENDOR_ID_GENERAL_TOUCH	0x0dfc
 
-#define USB_VENDOR_ID_GENERIC_13BA	0x13ba
-#define USB_DEVICE_ID_GENERIC_13BA_KBD_MOUSE	0x0017
-
 #define USB_VENDOR_ID_GLAB		0x06c2
 #define USB_DEVICE_ID_4_PHIDGETSERVO_30	0x0038
 #define USB_DEVICE_ID_1_PHIDGETSERVO_30	0x0039
@@ -292,7 +282,6 @@
 #define USB_DEVICE_ID_LOGITECH_WHEEL	0xc294
 #define USB_DEVICE_ID_LOGITECH_MOMO_WHEEL	0xc295
 #define USB_DEVICE_ID_LOGITECH_ELITE_KBD	0xc30a
-#define USB_DEVICE_ID_LOGITECH_KBD	0xc311
 #define USB_DEVICE_ID_S510_RECEIVER	0xc50c
 #define USB_DEVICE_ID_S510_RECEIVER_2	0xc517
 #define USB_DEVICE_ID_LOGITECH_CORDLESS_DESKTOP_LX500	0xc512
@@ -339,6 +328,9 @@
 #define USB_VENDOR_ID_NEC		0x073e
 #define USB_DEVICE_ID_NEC_USB_GAME_PAD	0x0301
 
+#define USB_VENDOR_ID_NTRIG                0x1b96
+#define USB_DEVICE_ID_NTRIG_TOUCH_SCREEN   0x0001
+
 #define USB_VENDOR_ID_ONTRAK		0x0a07
 #define USB_DEVICE_ID_ONTRAK_ADU100	0x0064
 
diff --git a/drivers/hid/hid-lg.c b/drivers/hid/hid-lg.c
index 2bae340eafe2..83e07c9f4144 100644
--- a/drivers/hid/hid-lg.c
+++ b/drivers/hid/hid-lg.c
@@ -26,7 +26,6 @@
 #define LG_RDESC		0x001
 #define LG_BAD_RELATIVE_KEYS	0x002
 #define LG_DUPLICATE_USAGES	0x004
-#define LG_RESET_LEDS		0x008
 #define LG_EXPANDED_KEYMAP	0x010
 #define LG_IGNORE_DOUBLED_WHEEL	0x020
 #define LG_WIRELESS		0x040
@@ -248,9 +247,6 @@ static int lg_probe(struct hid_device *hdev, const struct hid_device_id *id)
 		goto err_free;
 	}
 
-	if (quirks & LG_RESET_LEDS)
-		usbhid_set_leds(hdev);
-
 	if (quirks & LG_FF)
 		lgff_init(hdev);
 	if (quirks & LG_FF2)
@@ -279,9 +275,6 @@ static const struct hid_device_id lg_devices[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_DINOVO_MINI),
 		.driver_data = LG_DUPLICATE_USAGES },
 
-	{ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_KBD),
-		.driver_data = LG_RESET_LEDS },
-
 	{ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_ELITE_KBD),
 		.driver_data = LG_IGNORE_DOUBLED_WHEEL | LG_EXPANDED_KEYMAP },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_CORDLESS_DESKTOP_LX500),
diff --git a/drivers/hid/hid-ntrig.c b/drivers/hid/hid-ntrig.c
new file mode 100644
index 000000000000..db44fbd7bdf6
--- /dev/null
+++ b/drivers/hid/hid-ntrig.c
@@ -0,0 +1,82 @@
+/*
+ *  HID driver for some ntrig "special" devices
+ *
+ *  Copyright (c) 1999 Andreas Gal
+ *  Copyright (c) 2000-2005 Vojtech Pavlik <vojtech@suse.cz>
+ *  Copyright (c) 2005 Michael Haboustak <mike-@cinci.rr.com> for Concept2, Inc
+ *  Copyright (c) 2006-2007 Jiri Kosina
+ *  Copyright (c) 2007 Paul Walmsley
+ *  Copyright (c) 2008 Jiri Slaby
+ *  Copyright (c) 2008 Rafi Rubin
+ *
+ */
+
+/*
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ */
+
+#include <linux/device.h>
+#include <linux/hid.h>
+#include <linux/module.h>
+
+#include "hid-ids.h"
+
+#define NTRIG_DUPLICATE_USAGES	0x001
+
+#define nt_map_key_clear(c)	hid_map_usage_clear(hi, usage, bit, max, \
+					EV_KEY, (c))
+
+static int ntrig_input_mapping(struct hid_device *hdev, struct hid_input *hi,
+		struct hid_field *field, struct hid_usage *usage,
+		unsigned long **bit, int *max)
+{
+	if ((usage->hid & HID_USAGE_PAGE) == HID_UP_DIGITIZER &&
+			(usage->hid & 0xff) == 0x47) {
+		nt_map_key_clear(BTN_TOOL_DOUBLETAP);
+		return 1;
+	}
+	return 0;
+}
+
+static int ntrig_input_mapped(struct hid_device *hdev, struct hid_input *hi,
+		struct hid_field *field, struct hid_usage *usage,
+		unsigned long **bit, int *max)
+{
+	if (usage->type == EV_KEY || usage->type == EV_REL
+			|| usage->type == EV_ABS)
+		clear_bit(usage->code, *bit);
+
+	return 0;
+}
+static const struct hid_device_id ntrig_devices[] = {
+	{ HID_USB_DEVICE(USB_VENDOR_ID_NTRIG, USB_DEVICE_ID_NTRIG_TOUCH_SCREEN),
+		.driver_data = NTRIG_DUPLICATE_USAGES },
+	{ }
+};
+MODULE_DEVICE_TABLE(hid, ntrig_devices);
+
+static struct hid_driver ntrig_driver = {
+	.name = "ntrig",
+	.id_table = ntrig_devices,
+	.input_mapping = ntrig_input_mapping,
+	.input_mapped = ntrig_input_mapped,
+};
+
+static int ntrig_init(void)
+{
+	return hid_register_driver(&ntrig_driver);
+}
+
+static void ntrig_exit(void)
+{
+	hid_unregister_driver(&ntrig_driver);
+}
+
+module_init(ntrig_init);
+module_exit(ntrig_exit);
+MODULE_LICENSE("GPL");
+
+HID_COMPAT_LOAD_DRIVER(ntrig);
diff --git a/drivers/hid/hidraw.c b/drivers/hid/hidraw.c
index 7685ae6808c4..aab5911c4e33 100644
--- a/drivers/hid/hidraw.c
+++ b/drivers/hid/hidraw.c
@@ -265,6 +265,34 @@ static long hidraw_ioctl(struct file *file, unsigned int cmd,
 				break;
 			}
 		default:
+			{
+				struct hid_device *hid = dev->hid;
+				if (_IOC_TYPE(cmd) != 'H' || _IOC_DIR(cmd) != _IOC_READ)
+					return -EINVAL;
+
+				if (_IOC_NR(cmd) == _IOC_NR(HIDIOCGRAWNAME(0))) {
+					int len;
+					if (!hid->name)
+						return 0;
+					len = strlen(hid->name) + 1;
+					if (len > _IOC_SIZE(cmd))
+						len = _IOC_SIZE(cmd);
+					return copy_to_user(user_arg, hid->name, len) ?
+						-EFAULT : len;
+				}
+
+				if (_IOC_NR(cmd) == _IOC_NR(HIDIOCGRAWPHYS(0))) {
+					int len;
+					if (!hid->phys)
+						return 0;
+					len = strlen(hid->phys) + 1;
+					if (len > _IOC_SIZE(cmd))
+						len = _IOC_SIZE(cmd);
+					return copy_to_user(user_arg, hid->phys, len) ?
+						-EFAULT : len;
+				}
+                }
+
 			ret = -ENOTTY;
 	}
 	unlock_kernel();
@@ -329,7 +357,7 @@ int hidraw_connect(struct hid_device *hid)
 		goto out;
 	}
 
-	dev->dev = device_create(hidraw_class, NULL, MKDEV(hidraw_major, minor),
+	dev->dev = device_create(hidraw_class, &hid->dev, MKDEV(hidraw_major, minor),
 				 NULL, "%s%d", "hidraw", minor);
 
 	if (IS_ERR(dev->dev)) {
diff --git a/drivers/hid/usbhid/hid-core.c b/drivers/hid/usbhid/hid-core.c
index 606369ea24ca..f0a0f72238ab 100644
--- a/drivers/hid/usbhid/hid-core.c
+++ b/drivers/hid/usbhid/hid-core.c
@@ -4,7 +4,7 @@
  *  Copyright (c) 1999 Andreas Gal
  *  Copyright (c) 2000-2005 Vojtech Pavlik <vojtech@suse.cz>
  *  Copyright (c) 2005 Michael Haboustak <mike-@cinci.rr.com> for Concept2, Inc
- *  Copyright (c) 2006-2007 Jiri Kosina
+ *  Copyright (c) 2006-2008 Jiri Kosina
  */
 
 /*
@@ -102,7 +102,7 @@ static void hid_reset(struct work_struct *work)
 	struct usbhid_device *usbhid =
 		container_of(work, struct usbhid_device, reset_work);
 	struct hid_device *hid = usbhid->hid;
-	int rc_lock, rc = 0;
+	int rc = 0;
 
 	if (test_bit(HID_CLEAR_HALT, &usbhid->iofl)) {
 		dev_dbg(&usbhid->intf->dev, "clear halt\n");
@@ -113,11 +113,10 @@ static void hid_reset(struct work_struct *work)
 
 	else if (test_bit(HID_RESET_PENDING, &usbhid->iofl)) {
 		dev_dbg(&usbhid->intf->dev, "resetting device\n");
-		rc = rc_lock = usb_lock_device_for_reset(hid_to_usb_dev(hid), usbhid->intf);
-		if (rc_lock >= 0) {
+		rc = usb_lock_device_for_reset(hid_to_usb_dev(hid), usbhid->intf);
+		if (rc == 0) {
 			rc = usb_reset_device(hid_to_usb_dev(hid));
-			if (rc_lock)
-				usb_unlock_device(hid_to_usb_dev(hid));
+			usb_unlock_device(hid_to_usb_dev(hid));
 		}
 		clear_bit(HID_RESET_PENDING, &usbhid->iofl);
 	}
@@ -641,9 +640,7 @@ static void hid_find_max_report(struct hid_device *hid, unsigned int type,
 	unsigned int size;
 
 	list_for_each_entry(report, &hid->report_enum[type].report_list, list) {
-		size = ((report->size - 1) >> 3) + 1;
-		if (type == HID_INPUT_REPORT && hid->report_enum[type].numbered)
-			size++;
+		size = ((report->size - 1) >> 3) + 1 + hid->report_enum[type].numbered;
 		if (*max < size)
 			*max = size;
 	}
@@ -653,13 +650,16 @@ static int hid_alloc_buffers(struct usb_device *dev, struct hid_device *hid)
 {
 	struct usbhid_device *usbhid = hid->driver_data;
 
-	if (!(usbhid->inbuf = usb_buffer_alloc(dev, usbhid->bufsize, GFP_ATOMIC, &usbhid->inbuf_dma)))
-		return -1;
-	if (!(usbhid->outbuf = usb_buffer_alloc(dev, usbhid->bufsize, GFP_ATOMIC, &usbhid->outbuf_dma)))
-		return -1;
-	if (!(usbhid->cr = usb_buffer_alloc(dev, sizeof(*(usbhid->cr)), GFP_ATOMIC, &usbhid->cr_dma)))
-		return -1;
-	if (!(usbhid->ctrlbuf = usb_buffer_alloc(dev, usbhid->bufsize, GFP_ATOMIC, &usbhid->ctrlbuf_dma)))
+	usbhid->inbuf = usb_buffer_alloc(dev, usbhid->bufsize, GFP_KERNEL,
+			&usbhid->inbuf_dma);
+	usbhid->outbuf = usb_buffer_alloc(dev, usbhid->bufsize, GFP_KERNEL,
+			&usbhid->outbuf_dma);
+	usbhid->cr = usb_buffer_alloc(dev, sizeof(*usbhid->cr), GFP_KERNEL,
+			&usbhid->cr_dma);
+	usbhid->ctrlbuf = usb_buffer_alloc(dev, usbhid->bufsize, GFP_KERNEL,
+			&usbhid->ctrlbuf_dma);
+	if (!usbhid->inbuf || !usbhid->outbuf || !usbhid->cr ||
+			!usbhid->ctrlbuf)
 		return -1;
 
 	return 0;
@@ -807,7 +807,7 @@ static int usbhid_start(struct hid_device *hid)
 		int interval;
 
 		endpoint = &interface->endpoint[n].desc;
-		if ((endpoint->bmAttributes & 3) != 3)		/* Not an interrupt endpoint */
+		if (!usb_endpoint_xfer_int(endpoint))
 			continue;
 
 		interval = endpoint->bInterval;
@@ -876,6 +876,15 @@ static int usbhid_start(struct hid_device *hid)
 
 	set_bit(HID_STARTED, &usbhid->iofl);
 
+	/* Some keyboards don't work until their LEDs have been set.
+	 * Since BIOSes do set the LEDs, it must be safe for any device
+	 * that supports the keyboard boot protocol.
+	 */
+	if (interface->desc.bInterfaceSubClass == USB_INTERFACE_SUBCLASS_BOOT &&
+			interface->desc.bInterfaceProtocol ==
+				USB_INTERFACE_PROTOCOL_KEYBOARD)
+		usbhid_set_leds(hid);
+
 	return 0;
 
 fail:
diff --git a/drivers/hid/usbhid/usbhid.h b/drivers/hid/usbhid/usbhid.h
index 332abcdf9956..9eb30564be9c 100644
--- a/drivers/hid/usbhid/usbhid.h
+++ b/drivers/hid/usbhid/usbhid.h
@@ -40,6 +40,16 @@ int usbhid_open(struct hid_device *hid);
 void usbhid_init_reports(struct hid_device *hid);
 void usbhid_submit_report(struct hid_device *hid, struct hid_report *report, unsigned char dir);
 
+/* iofl flags */
+#define HID_CTRL_RUNNING	1
+#define HID_OUT_RUNNING		2
+#define HID_IN_RUNNING		3
+#define HID_RESET_PENDING	4
+#define HID_SUSPENDED		5
+#define HID_CLEAR_HALT		6
+#define HID_DISCONNECTED	7
+#define HID_STARTED		8
+
 /*
  * USB-specific HID struct, to be pointed to
  * from struct hid_device->driver_data
diff --git a/drivers/hwmon/Kconfig b/drivers/hwmon/Kconfig
index c709e821f04b..37d251fdd124 100644
--- a/drivers/hwmon/Kconfig
+++ b/drivers/hwmon/Kconfig
@@ -304,9 +304,13 @@ config SENSORS_F75375S
 	  will be called f75375s.
 
 config SENSORS_FSCHER
-	tristate "FSC Hermes"
+	tristate "FSC Hermes (DEPRECATED)"
 	depends on X86 && I2C
 	help
+	  This driver is DEPRECATED please use the new merged fschmd
+	  ("FSC Poseidon, Scylla, Hermes, Heimdall and Heracles") driver
+	  instead.
+
 	  If you say yes here you get support for Fujitsu Siemens
 	  Computers Hermes sensor chips.
 
@@ -314,9 +318,13 @@ config SENSORS_FSCHER
 	  will be called fscher.
 
 config SENSORS_FSCPOS
-	tristate "FSC Poseidon"
+	tristate "FSC Poseidon (DEPRECATED)"
 	depends on X86 && I2C
 	help
+	  This driver is DEPRECATED please use the new merged fschmd
+	  ("FSC Poseidon, Scylla, Hermes, Heimdall and Heracles") driver
+	  instead.
+
 	  If you say yes here you get support for Fujitsu Siemens
 	  Computers Poseidon sensor chips.
 
@@ -325,14 +333,15 @@ config SENSORS_FSCPOS
 
 config SENSORS_FSCHMD
 	tristate "FSC Poseidon, Scylla, Hermes, Heimdall and Heracles"
-	depends on X86 && I2C && EXPERIMENTAL
+	depends on X86 && I2C
 	help
 	  If you say yes here you get support for various Fujitsu Siemens
-	  Computers sensor chips.
+	  Computers sensor chips, including support for the integrated
+	  watchdog.
 
-	  This is a new merged driver for FSC sensor chips which is intended
-	  as a replacment for the fscpos, fscscy and fscher drivers and adds
-	  support for several other FCS sensor chips.
+	  This is a merged driver for FSC sensor chips replacing the fscpos,
+	  fscscy and fscher drivers and adding support for several other FSC
+	  sensor chips.
 
 	  This driver can also be built as a module.  If so, the module
 	  will be called fschmd.
@@ -399,7 +408,8 @@ config SENSORS_IT87
 	select HWMON_VID
 	help
 	  If you say yes here you get support for ITE IT8705F, IT8712F,
-	  IT8716F, IT8718F and IT8726F sensor chips, and the SiS960 clone.
+	  IT8716F, IT8718F, IT8720F and IT8726F sensor chips, and the
+	  SiS960 clone.
 
 	  This driver can also be built as a module.  If so, the module
 	  will be called it87.
@@ -417,11 +427,12 @@ config SENSORS_LM63
 	  will be called lm63.
 
 config SENSORS_LM70
-	tristate "National Semiconductor LM70"
+	tristate "National Semiconductor LM70 / Texas Instruments TMP121"
 	depends on SPI_MASTER && EXPERIMENTAL
 	help
 	  If you say yes here you get support for the National Semiconductor
-	  LM70 digital temperature sensor chip.
+	  LM70 and Texas Instruments TMP121/TMP123 digital temperature
+	  sensor chips.
 
 	  This driver can also be built as a module.  If so, the module
 	  will be called lm70.
@@ -548,6 +559,17 @@ config SENSORS_LM93
 	  This driver can also be built as a module.  If so, the module
 	  will be called lm93.
 
+config SENSORS_LTC4245
+	tristate "Linear Technology LTC4245"
+	depends on I2C && EXPERIMENTAL
+	default n
+	help
+	  If you say yes here you get support for Linear Technology LTC4245
+	  Multiple Supply Hot Swap Controller I2C interface.
+
+	  This driver can also be built as a module. If so, the module will
+	  be called ltc4245.
+
 config SENSORS_MAX1111
 	tristate "Maxim MAX1111 Multichannel, Serial 8-bit ADC chip"
 	depends on SPI_MASTER
diff --git a/drivers/hwmon/Makefile b/drivers/hwmon/Makefile
index 58fc5be5355d..8fd124eff646 100644
--- a/drivers/hwmon/Makefile
+++ b/drivers/hwmon/Makefile
@@ -62,6 +62,7 @@ obj-$(CONFIG_SENSORS_LM87)	+= lm87.o
 obj-$(CONFIG_SENSORS_LM90)	+= lm90.o
 obj-$(CONFIG_SENSORS_LM92)	+= lm92.o
 obj-$(CONFIG_SENSORS_LM93)	+= lm93.o
+obj-$(CONFIG_SENSORS_LTC4245)	+= ltc4245.o
 obj-$(CONFIG_SENSORS_MAX1111)	+= max1111.o
 obj-$(CONFIG_SENSORS_MAX1619)	+= max1619.o
 obj-$(CONFIG_SENSORS_MAX6650)	+= max6650.o
diff --git a/drivers/hwmon/asb100.c b/drivers/hwmon/asb100.c
index 8a45a2e6ba8a..8acf82977e7b 100644
--- a/drivers/hwmon/asb100.c
+++ b/drivers/hwmon/asb100.c
@@ -53,7 +53,10 @@ static const unsigned short normal_i2c[] = { 0x2d, I2C_CLIENT_END };
 
 /* Insmod parameters */
 I2C_CLIENT_INSMOD_1(asb100);
-I2C_CLIENT_MODULE_PARM(force_subclients, "List of subclient addresses: "
+
+static unsigned short force_subclients[4];
+module_param_array(force_subclients, short, NULL, 0);
+MODULE_PARM_DESC(force_subclients, "List of subclient addresses: "
 	"{bus, clientaddr, subclientaddr1, subclientaddr2}");
 
 /* Voltage IN registers 0-6 */
diff --git a/drivers/hwmon/f71882fg.c b/drivers/hwmon/f71882fg.c
index 67067e9a323e..1cfd2231677a 100644
--- a/drivers/hwmon/f71882fg.c
+++ b/drivers/hwmon/f71882fg.c
@@ -1,6 +1,6 @@
 /***************************************************************************
  *   Copyright (C) 2006 by Hans Edgington <hans@edgington.nl>              *
- *   Copyright (C) 2007 by Hans de Goede  <j.w.r.degoede@hhs.nl>           *
+ *   Copyright (C) 2007,2008 by Hans de Goede <hdegoede@redhat.com>        *
  *                                                                         *
  *   This program is free software; you can redistribute it and/or modify  *
  *   it under the terms of the GNU General Public License as published by  *
@@ -27,11 +27,11 @@
 #include <linux/hwmon-sysfs.h>
 #include <linux/err.h>
 #include <linux/mutex.h>
-#include <asm/io.h>
+#include <linux/io.h>
 
 #define DRVNAME "f71882fg"
 
-#define SIO_F71882FG_LD_HWM	0x04	/* Hardware monitor logical device*/
+#define SIO_F71882FG_LD_HWM	0x04	/* Hardware monitor logical device */
 #define SIO_UNLOCK_KEY		0x87	/* Key to enable Super-I/O */
 #define SIO_LOCK_KEY		0xAA	/* Key to diasble Super-I/O */
 
@@ -43,6 +43,7 @@
 #define SIO_REG_ADDR		0x60	/* Logical device address (2 bytes) */
 
 #define SIO_FINTEK_ID		0x1934	/* Manufacturers ID */
+#define SIO_F71862_ID		0x0601	/* Chipset ID */
 #define SIO_F71882_ID		0x0541	/* Chipset ID */
 
 #define REGION_LENGTH		8
@@ -51,12 +52,14 @@
 
 #define F71882FG_REG_PECI		0x0A
 
-#define F71882FG_REG_IN_STATUS		0x12
-#define F71882FG_REG_IN_BEEP		0x13
+#define F71882FG_REG_IN_STATUS		0x12 /* f71882fg only */
+#define F71882FG_REG_IN_BEEP		0x13 /* f71882fg only */
 #define F71882FG_REG_IN(nr)		(0x20  + (nr))
-#define F71882FG_REG_IN1_HIGH		0x32
+#define F71882FG_REG_IN1_HIGH		0x32 /* f71882fg only */
 
 #define F71882FG_REG_FAN(nr)		(0xA0 + (16 * (nr)))
+#define F71882FG_REG_FAN_TARGET(nr)	(0xA2 + (16 * (nr)))
+#define F71882FG_REG_FAN_FULL_SPEED(nr)	(0xA4 + (16 * (nr)))
 #define F71882FG_REG_FAN_STATUS		0x92
 #define F71882FG_REG_FAN_BEEP		0x93
 
@@ -70,6 +73,17 @@
 #define F71882FG_REG_TEMP_TYPE		0x6B
 #define F71882FG_REG_TEMP_DIODE_OPEN	0x6F
 
+#define F71882FG_REG_PWM(nr)		(0xA3 + (16 * (nr)))
+#define F71882FG_REG_PWM_TYPE		0x94
+#define F71882FG_REG_PWM_ENABLE		0x96
+
+#define F71882FG_REG_FAN_HYST0		0x98
+#define F71882FG_REG_FAN_HYST1		0x99
+
+#define F71882FG_REG_POINT_PWM(pwm, point)	(0xAA + (point) + (16 * (pwm)))
+#define F71882FG_REG_POINT_TEMP(pwm, point)	(0xA6 + (point) + (16 * (pwm)))
+#define F71882FG_REG_POINT_MAPPING(nr)		(0xAF + 16 * (nr))
+
 #define	F71882FG_REG_START		0x01
 
 #define FAN_MIN_DETECT			366 /* Lowest detectable fanspeed */
@@ -78,7 +92,20 @@ static unsigned short force_id;
 module_param(force_id, ushort, 0);
 MODULE_PARM_DESC(force_id, "Override the detected device ID");
 
-static struct platform_device *f71882fg_pdev = NULL;
+static int fan_mode[4] = { 0, 0, 0, 0 };
+module_param_array(fan_mode, int, NULL, 0644);
+MODULE_PARM_DESC(fan_mode, "List of fan control modes (f71882fg only) "
+		 "(0=don't change, 1=pwm, 2=rpm)\n"
+		 "Note: this needs a write to pwm#_enable to take effect");
+
+enum chips { f71862fg, f71882fg };
+
+static const char *f71882fg_names[] = {
+	"f71862fg",
+	"f71882fg",
+};
+
+static struct platform_device *f71882fg_pdev;
 
 /* Super-I/O Function prototypes */
 static inline int superio_inb(int base, int reg);
@@ -87,8 +114,13 @@ static inline void superio_enter(int base);
 static inline void superio_select(int base, int ld);
 static inline void superio_exit(int base);
 
+struct f71882fg_sio_data {
+	enum chips type;
+};
+
 struct f71882fg_data {
 	unsigned short addr;
+	enum chips type;
 	struct device *hwmon_dev;
 
 	struct mutex update_lock;
@@ -102,6 +134,8 @@ struct f71882fg_data {
 	u8	in_status;
 	u8	in_beep;
 	u16	fan[4];
+	u16	fan_target[4];
+	u16	fan_full_speed[4];
 	u8	fan_status;
 	u8	fan_beep;
 	u8	temp[3];
@@ -112,9 +146,15 @@ struct f71882fg_data {
 	u8	temp_status;
 	u8	temp_beep;
 	u8	temp_diode_open;
+	u8	pwm[4];
+	u8	pwm_enable;
+	u8	pwm_auto_point_hyst[2];
+	u8	pwm_auto_point_mapping[4];
+	u8	pwm_auto_point_pwm[4][5];
+	u8	pwm_auto_point_temp[4][4];
 };
 
-/* Sysfs in*/
+/* Sysfs in */
 static ssize_t show_in(struct device *dev, struct device_attribute *devattr,
 	char *buf);
 static ssize_t show_in_max(struct device *dev, struct device_attribute
@@ -130,6 +170,10 @@ static ssize_t show_in_alarm(struct device *dev, struct device_attribute
 /* Sysfs Fan */
 static ssize_t show_fan(struct device *dev, struct device_attribute *devattr,
 	char *buf);
+static ssize_t show_fan_full_speed(struct device *dev,
+	struct device_attribute *devattr, char *buf);
+static ssize_t store_fan_full_speed(struct device *dev,
+	struct device_attribute *devattr, const char *buf, size_t count);
 static ssize_t show_fan_beep(struct device *dev, struct device_attribute
 	*devattr, char *buf);
 static ssize_t store_fan_beep(struct device *dev, struct device_attribute
@@ -163,16 +207,41 @@ static ssize_t show_temp_alarm(struct device *dev, struct device_attribute
 	*devattr, char *buf);
 static ssize_t show_temp_fault(struct device *dev, struct device_attribute
 	*devattr, char *buf);
+/* PWM and Auto point control */
+static ssize_t show_pwm(struct device *dev, struct device_attribute *devattr,
+	char *buf);
+static ssize_t store_pwm(struct device *dev, struct device_attribute *devattr,
+	const char *buf, size_t count);
+static ssize_t show_pwm_enable(struct device *dev,
+	struct device_attribute *devattr, char *buf);
+static ssize_t store_pwm_enable(struct device *dev,
+	struct device_attribute	*devattr, const char *buf, size_t count);
+static ssize_t show_pwm_interpolate(struct device *dev,
+	struct device_attribute *devattr, char *buf);
+static ssize_t store_pwm_interpolate(struct device *dev,
+	struct device_attribute *devattr, const char *buf, size_t count);
+static ssize_t show_pwm_auto_point_channel(struct device *dev,
+	struct device_attribute *devattr, char *buf);
+static ssize_t store_pwm_auto_point_channel(struct device *dev,
+	struct device_attribute *devattr, const char *buf, size_t count);
+static ssize_t show_pwm_auto_point_temp_hyst(struct device *dev,
+	struct device_attribute *devattr, char *buf);
+static ssize_t store_pwm_auto_point_temp_hyst(struct device *dev,
+	struct device_attribute *devattr, const char *buf, size_t count);
+static ssize_t show_pwm_auto_point_pwm(struct device *dev,
+	struct device_attribute *devattr, char *buf);
+static ssize_t store_pwm_auto_point_pwm(struct device *dev,
+	struct device_attribute *devattr, const char *buf, size_t count);
+static ssize_t show_pwm_auto_point_temp(struct device *dev,
+	struct device_attribute *devattr, char *buf);
+static ssize_t store_pwm_auto_point_temp(struct device *dev,
+	struct device_attribute *devattr, const char *buf, size_t count);
 /* Sysfs misc */
 static ssize_t show_name(struct device *dev, struct device_attribute *devattr,
 	char *buf);
 
 static int __devinit f71882fg_probe(struct platform_device * pdev);
-static int __devexit f71882fg_remove(struct platform_device *pdev);
-static int __init f71882fg_init(void);
-static int __init f71882fg_find(int sioaddr, unsigned short *address);
-static int __init f71882fg_device_add(unsigned short address);
-static void __exit f71882fg_exit(void);
+static int f71882fg_remove(struct platform_device *pdev);
 
 static struct platform_driver f71882fg_driver = {
 	.driver = {
@@ -183,84 +252,329 @@ static struct platform_driver f71882fg_driver = {
 	.remove		= __devexit_p(f71882fg_remove),
 };
 
-static struct device_attribute f71882fg_dev_attr[] =
-{
-	__ATTR( name, S_IRUGO, show_name, NULL ),
+static DEVICE_ATTR(name, S_IRUGO, show_name, NULL);
+
+static struct sensor_device_attribute_2 f718x2fg_in_temp_attr[] = {
+	SENSOR_ATTR_2(in0_input, S_IRUGO, show_in, NULL, 0, 0),
+	SENSOR_ATTR_2(in1_input, S_IRUGO, show_in, NULL, 0, 1),
+	SENSOR_ATTR_2(in2_input, S_IRUGO, show_in, NULL, 0, 2),
+	SENSOR_ATTR_2(in3_input, S_IRUGO, show_in, NULL, 0, 3),
+	SENSOR_ATTR_2(in4_input, S_IRUGO, show_in, NULL, 0, 4),
+	SENSOR_ATTR_2(in5_input, S_IRUGO, show_in, NULL, 0, 5),
+	SENSOR_ATTR_2(in6_input, S_IRUGO, show_in, NULL, 0, 6),
+	SENSOR_ATTR_2(in7_input, S_IRUGO, show_in, NULL, 0, 7),
+	SENSOR_ATTR_2(in8_input, S_IRUGO, show_in, NULL, 0, 8),
+	SENSOR_ATTR_2(temp1_input, S_IRUGO, show_temp, NULL, 0, 0),
+	SENSOR_ATTR_2(temp1_max, S_IRUGO|S_IWUSR, show_temp_max,
+		store_temp_max, 0, 0),
+	SENSOR_ATTR_2(temp1_max_hyst, S_IRUGO|S_IWUSR, show_temp_max_hyst,
+		store_temp_max_hyst, 0, 0),
+	SENSOR_ATTR_2(temp1_crit, S_IRUGO|S_IWUSR, show_temp_crit,
+		store_temp_crit, 0, 0),
+	SENSOR_ATTR_2(temp1_crit_hyst, S_IRUGO, show_temp_crit_hyst, NULL,
+		0, 0),
+	SENSOR_ATTR_2(temp1_type, S_IRUGO, show_temp_type, NULL, 0, 0),
+	SENSOR_ATTR_2(temp1_beep, S_IRUGO|S_IWUSR, show_temp_beep,
+		store_temp_beep, 0, 0),
+	SENSOR_ATTR_2(temp1_alarm, S_IRUGO, show_temp_alarm, NULL, 0, 0),
+	SENSOR_ATTR_2(temp1_fault, S_IRUGO, show_temp_fault, NULL, 0, 0),
+	SENSOR_ATTR_2(temp2_input, S_IRUGO, show_temp, NULL, 0, 1),
+	SENSOR_ATTR_2(temp2_max, S_IRUGO|S_IWUSR, show_temp_max,
+		store_temp_max, 0, 1),
+	SENSOR_ATTR_2(temp2_max_hyst, S_IRUGO|S_IWUSR, show_temp_max_hyst,
+		store_temp_max_hyst, 0, 1),
+	SENSOR_ATTR_2(temp2_crit, S_IRUGO|S_IWUSR, show_temp_crit,
+		store_temp_crit, 0, 1),
+	SENSOR_ATTR_2(temp2_crit_hyst, S_IRUGO, show_temp_crit_hyst, NULL,
+		0, 1),
+	SENSOR_ATTR_2(temp2_type, S_IRUGO, show_temp_type, NULL, 0, 1),
+	SENSOR_ATTR_2(temp2_beep, S_IRUGO|S_IWUSR, show_temp_beep,
+		store_temp_beep, 0, 1),
+	SENSOR_ATTR_2(temp2_alarm, S_IRUGO, show_temp_alarm, NULL, 0, 1),
+	SENSOR_ATTR_2(temp2_fault, S_IRUGO, show_temp_fault, NULL, 0, 1),
+	SENSOR_ATTR_2(temp3_input, S_IRUGO, show_temp, NULL, 0, 2),
+	SENSOR_ATTR_2(temp3_max, S_IRUGO|S_IWUSR, show_temp_max,
+		store_temp_max, 0, 2),
+	SENSOR_ATTR_2(temp3_max_hyst, S_IRUGO|S_IWUSR, show_temp_max_hyst,
+		store_temp_max_hyst, 0, 2),
+	SENSOR_ATTR_2(temp3_crit, S_IRUGO|S_IWUSR, show_temp_crit,
+		store_temp_crit, 0, 2),
+	SENSOR_ATTR_2(temp3_crit_hyst, S_IRUGO, show_temp_crit_hyst, NULL,
+		0, 2),
+	SENSOR_ATTR_2(temp3_type, S_IRUGO, show_temp_type, NULL, 0, 2),
+	SENSOR_ATTR_2(temp3_beep, S_IRUGO|S_IWUSR, show_temp_beep,
+		store_temp_beep, 0, 2),
+	SENSOR_ATTR_2(temp3_alarm, S_IRUGO, show_temp_alarm, NULL, 0, 2),
+	SENSOR_ATTR_2(temp3_fault, S_IRUGO, show_temp_fault, NULL, 0, 2),
+};
+
+static struct sensor_device_attribute_2 f71882fg_in_temp_attr[] = {
+	SENSOR_ATTR_2(in1_max, S_IRUGO|S_IWUSR, show_in_max, store_in_max,
+		0, 1),
+	SENSOR_ATTR_2(in1_beep, S_IRUGO|S_IWUSR, show_in_beep, store_in_beep,
+		0, 1),
+	SENSOR_ATTR_2(in1_alarm, S_IRUGO, show_in_alarm, NULL, 0, 1),
+};
+
+static struct sensor_device_attribute_2 f718x2fg_fan_attr[] = {
+	SENSOR_ATTR_2(fan1_input, S_IRUGO, show_fan, NULL, 0, 0),
+	SENSOR_ATTR_2(fan1_full_speed, S_IRUGO|S_IWUSR,
+		      show_fan_full_speed,
+		      store_fan_full_speed, 0, 0),
+	SENSOR_ATTR_2(fan1_beep, S_IRUGO|S_IWUSR, show_fan_beep,
+		store_fan_beep, 0, 0),
+	SENSOR_ATTR_2(fan1_alarm, S_IRUGO, show_fan_alarm, NULL, 0, 0),
+	SENSOR_ATTR_2(fan2_input, S_IRUGO, show_fan, NULL, 0, 1),
+	SENSOR_ATTR_2(fan2_full_speed, S_IRUGO|S_IWUSR,
+		      show_fan_full_speed,
+		      store_fan_full_speed, 0, 1),
+	SENSOR_ATTR_2(fan2_beep, S_IRUGO|S_IWUSR, show_fan_beep,
+		store_fan_beep, 0, 1),
+	SENSOR_ATTR_2(fan2_alarm, S_IRUGO, show_fan_alarm, NULL, 0, 1),
+	SENSOR_ATTR_2(fan3_input, S_IRUGO, show_fan, NULL, 0, 2),
+	SENSOR_ATTR_2(fan3_full_speed, S_IRUGO|S_IWUSR,
+		      show_fan_full_speed,
+		      store_fan_full_speed, 0, 2),
+	SENSOR_ATTR_2(fan3_beep, S_IRUGO|S_IWUSR, show_fan_beep,
+		store_fan_beep, 0, 2),
+	SENSOR_ATTR_2(fan3_alarm, S_IRUGO, show_fan_alarm, NULL, 0, 2),
+
+	SENSOR_ATTR_2(pwm1, S_IRUGO|S_IWUSR, show_pwm, store_pwm, 0, 0),
+	SENSOR_ATTR_2(pwm1_enable, S_IRUGO|S_IWUSR, show_pwm_enable,
+		      store_pwm_enable, 0, 0),
+	SENSOR_ATTR_2(pwm1_interpolate, S_IRUGO|S_IWUSR,
+		      show_pwm_interpolate, store_pwm_interpolate, 0, 0),
+	SENSOR_ATTR_2(pwm1_auto_channels_temp, S_IRUGO|S_IWUSR,
+		      show_pwm_auto_point_channel,
+		      store_pwm_auto_point_channel, 0, 0),
+
+	SENSOR_ATTR_2(pwm2, S_IRUGO|S_IWUSR, show_pwm, store_pwm, 0, 1),
+	SENSOR_ATTR_2(pwm2_enable, S_IRUGO|S_IWUSR, show_pwm_enable,
+		      store_pwm_enable, 0, 1),
+	SENSOR_ATTR_2(pwm2_interpolate, S_IRUGO|S_IWUSR,
+		      show_pwm_interpolate, store_pwm_interpolate, 0, 1),
+	SENSOR_ATTR_2(pwm2_auto_channels_temp, S_IRUGO|S_IWUSR,
+		      show_pwm_auto_point_channel,
+		      store_pwm_auto_point_channel, 0, 1),
+
+	SENSOR_ATTR_2(pwm3, S_IRUGO|S_IWUSR, show_pwm, store_pwm, 0, 2),
+	SENSOR_ATTR_2(pwm3_enable, S_IRUGO|S_IWUSR, show_pwm_enable,
+		      store_pwm_enable, 0, 2),
+	SENSOR_ATTR_2(pwm3_interpolate, S_IRUGO|S_IWUSR,
+		      show_pwm_interpolate, store_pwm_interpolate, 0, 2),
+	SENSOR_ATTR_2(pwm3_auto_channels_temp, S_IRUGO|S_IWUSR,
+		      show_pwm_auto_point_channel,
+		      store_pwm_auto_point_channel, 0, 2),
 };
 
-static struct sensor_device_attribute f71882fg_in_temp_attr[] =
-{
-	SENSOR_ATTR(in0_input, S_IRUGO, show_in, NULL, 0),
-	SENSOR_ATTR(in1_input, S_IRUGO, show_in, NULL, 1),
-	SENSOR_ATTR(in1_max, S_IRUGO|S_IWUSR, show_in_max, store_in_max, 1),
-	SENSOR_ATTR(in1_beep, S_IRUGO|S_IWUSR, show_in_beep, store_in_beep, 1),
-	SENSOR_ATTR(in1_alarm, S_IRUGO, show_in_alarm, NULL, 1),
-	SENSOR_ATTR(in2_input, S_IRUGO, show_in, NULL, 2),
-	SENSOR_ATTR(in3_input, S_IRUGO, show_in, NULL, 3),
-	SENSOR_ATTR(in4_input, S_IRUGO, show_in, NULL, 4),
-	SENSOR_ATTR(in5_input, S_IRUGO, show_in, NULL, 5),
-	SENSOR_ATTR(in6_input, S_IRUGO, show_in, NULL, 6),
-	SENSOR_ATTR(in7_input, S_IRUGO, show_in, NULL, 7),
-	SENSOR_ATTR(in8_input, S_IRUGO, show_in, NULL, 8),
-	SENSOR_ATTR(temp1_input, S_IRUGO, show_temp, NULL, 0),
-	SENSOR_ATTR(temp1_max, S_IRUGO|S_IWUSR, show_temp_max,
-		store_temp_max, 0),
-	SENSOR_ATTR(temp1_max_hyst, S_IRUGO|S_IWUSR, show_temp_max_hyst,
-		store_temp_max_hyst, 0),
-	SENSOR_ATTR(temp1_crit, S_IRUGO|S_IWUSR, show_temp_crit,
-		store_temp_crit, 0),
-	SENSOR_ATTR(temp1_crit_hyst, S_IRUGO, show_temp_crit_hyst, NULL, 0),
-	SENSOR_ATTR(temp1_type, S_IRUGO, show_temp_type, NULL, 0),
-	SENSOR_ATTR(temp1_beep, S_IRUGO|S_IWUSR, show_temp_beep,
-		store_temp_beep, 0),
-	SENSOR_ATTR(temp1_alarm, S_IRUGO, show_temp_alarm, NULL, 0),
-	SENSOR_ATTR(temp1_fault, S_IRUGO, show_temp_fault, NULL, 0),
-	SENSOR_ATTR(temp2_input, S_IRUGO, show_temp, NULL, 1),
-	SENSOR_ATTR(temp2_max, S_IRUGO|S_IWUSR, show_temp_max,
-		store_temp_max, 1),
-	SENSOR_ATTR(temp2_max_hyst, S_IRUGO|S_IWUSR, show_temp_max_hyst,
-		store_temp_max_hyst, 1),
-	SENSOR_ATTR(temp2_crit, S_IRUGO|S_IWUSR, show_temp_crit,
-		store_temp_crit, 1),
-	SENSOR_ATTR(temp2_crit_hyst, S_IRUGO, show_temp_crit_hyst, NULL, 1),
-	SENSOR_ATTR(temp2_type, S_IRUGO, show_temp_type, NULL, 1),
-	SENSOR_ATTR(temp2_beep, S_IRUGO|S_IWUSR, show_temp_beep,
-		store_temp_beep, 1),
-	SENSOR_ATTR(temp2_alarm, S_IRUGO, show_temp_alarm, NULL, 1),
-	SENSOR_ATTR(temp2_fault, S_IRUGO, show_temp_fault, NULL, 1),
-	SENSOR_ATTR(temp3_input, S_IRUGO, show_temp, NULL, 2),
-	SENSOR_ATTR(temp3_max, S_IRUGO|S_IWUSR, show_temp_max,
-		store_temp_max, 2),
-	SENSOR_ATTR(temp3_max_hyst, S_IRUGO|S_IWUSR, show_temp_max_hyst,
-		store_temp_max_hyst, 2),
-	SENSOR_ATTR(temp3_crit, S_IRUGO|S_IWUSR, show_temp_crit,
-		store_temp_crit, 2),
-	SENSOR_ATTR(temp3_crit_hyst, S_IRUGO, show_temp_crit_hyst, NULL, 2),
-	SENSOR_ATTR(temp3_type, S_IRUGO, show_temp_type, NULL, 2),
-	SENSOR_ATTR(temp3_beep, S_IRUGO|S_IWUSR, show_temp_beep,
-		store_temp_beep, 2),
-	SENSOR_ATTR(temp3_alarm, S_IRUGO, show_temp_alarm, NULL, 2),
-	SENSOR_ATTR(temp3_fault, S_IRUGO, show_temp_fault, NULL, 2)
+static struct sensor_device_attribute_2 f71862fg_fan_attr[] = {
+	SENSOR_ATTR_2(pwm1_auto_point1_pwm, S_IRUGO|S_IWUSR,
+		      show_pwm_auto_point_pwm, store_pwm_auto_point_pwm,
+		      1, 0),
+	SENSOR_ATTR_2(pwm1_auto_point2_pwm, S_IRUGO|S_IWUSR,
+		      show_pwm_auto_point_pwm, store_pwm_auto_point_pwm,
+		      4, 0),
+	SENSOR_ATTR_2(pwm1_auto_point1_temp, S_IRUGO|S_IWUSR,
+		      show_pwm_auto_point_temp, store_pwm_auto_point_temp,
+		      0, 0),
+	SENSOR_ATTR_2(pwm1_auto_point2_temp, S_IRUGO|S_IWUSR,
+		      show_pwm_auto_point_temp, store_pwm_auto_point_temp,
+		      3, 0),
+	SENSOR_ATTR_2(pwm1_auto_point1_temp_hyst, S_IRUGO|S_IWUSR,
+		      show_pwm_auto_point_temp_hyst,
+		      store_pwm_auto_point_temp_hyst,
+		      0, 0),
+	SENSOR_ATTR_2(pwm1_auto_point2_temp_hyst, S_IRUGO,
+		      show_pwm_auto_point_temp_hyst, NULL, 3, 0),
+
+	SENSOR_ATTR_2(pwm2_auto_point1_pwm, S_IRUGO|S_IWUSR,
+		      show_pwm_auto_point_pwm, store_pwm_auto_point_pwm,
+		      1, 1),
+	SENSOR_ATTR_2(pwm2_auto_point2_pwm, S_IRUGO|S_IWUSR,
+		      show_pwm_auto_point_pwm, store_pwm_auto_point_pwm,
+		      4, 1),
+	SENSOR_ATTR_2(pwm2_auto_point1_temp, S_IRUGO|S_IWUSR,
+		      show_pwm_auto_point_temp, store_pwm_auto_point_temp,
+		      0, 1),
+	SENSOR_ATTR_2(pwm2_auto_point2_temp, S_IRUGO|S_IWUSR,
+		      show_pwm_auto_point_temp, store_pwm_auto_point_temp,
+		      3, 1),
+	SENSOR_ATTR_2(pwm2_auto_point1_temp_hyst, S_IRUGO|S_IWUSR,
+		      show_pwm_auto_point_temp_hyst,
+		      store_pwm_auto_point_temp_hyst,
+		      0, 1),
+	SENSOR_ATTR_2(pwm2_auto_point2_temp_hyst, S_IRUGO,
+		      show_pwm_auto_point_temp_hyst, NULL, 3, 1),
 };
 
-static struct sensor_device_attribute f71882fg_fan_attr[] =
-{
-	SENSOR_ATTR(fan1_input, S_IRUGO, show_fan, NULL, 0),
-	SENSOR_ATTR(fan1_beep, S_IRUGO|S_IWUSR, show_fan_beep,
-		store_fan_beep, 0),
-	SENSOR_ATTR(fan1_alarm, S_IRUGO, show_fan_alarm, NULL, 0),
-	SENSOR_ATTR(fan2_input, S_IRUGO, show_fan, NULL, 1),
-	SENSOR_ATTR(fan2_beep, S_IRUGO|S_IWUSR, show_fan_beep,
-		store_fan_beep, 1),
-	SENSOR_ATTR(fan2_alarm, S_IRUGO, show_fan_alarm, NULL, 1),
-	SENSOR_ATTR(fan3_input, S_IRUGO, show_fan, NULL, 2),
-	SENSOR_ATTR(fan3_beep, S_IRUGO|S_IWUSR, show_fan_beep,
-		store_fan_beep, 2),
-	SENSOR_ATTR(fan3_alarm, S_IRUGO, show_fan_alarm, NULL, 2),
-	SENSOR_ATTR(fan4_input, S_IRUGO, show_fan, NULL, 3),
-	SENSOR_ATTR(fan4_beep, S_IRUGO|S_IWUSR, show_fan_beep,
-		store_fan_beep, 3),
-	SENSOR_ATTR(fan4_alarm, S_IRUGO, show_fan_alarm, NULL, 3)
+static struct sensor_device_attribute_2 f71882fg_fan_attr[] = {
+	SENSOR_ATTR_2(fan4_input, S_IRUGO, show_fan, NULL, 0, 3),
+	SENSOR_ATTR_2(fan4_full_speed, S_IRUGO|S_IWUSR,
+		      show_fan_full_speed,
+		      store_fan_full_speed, 0, 3),
+	SENSOR_ATTR_2(fan4_beep, S_IRUGO|S_IWUSR, show_fan_beep,
+		store_fan_beep, 0, 3),
+	SENSOR_ATTR_2(fan4_alarm, S_IRUGO, show_fan_alarm, NULL, 0, 3),
+
+	SENSOR_ATTR_2(pwm1_auto_point1_pwm, S_IRUGO|S_IWUSR,
+		      show_pwm_auto_point_pwm, store_pwm_auto_point_pwm,
+		      0, 0),
+	SENSOR_ATTR_2(pwm1_auto_point2_pwm, S_IRUGO|S_IWUSR,
+		      show_pwm_auto_point_pwm, store_pwm_auto_point_pwm,
+		      1, 0),
+	SENSOR_ATTR_2(pwm1_auto_point3_pwm, S_IRUGO|S_IWUSR,
+		      show_pwm_auto_point_pwm, store_pwm_auto_point_pwm,
+		      2, 0),
+	SENSOR_ATTR_2(pwm1_auto_point4_pwm, S_IRUGO|S_IWUSR,
+		      show_pwm_auto_point_pwm, store_pwm_auto_point_pwm,
+		      3, 0),
+	SENSOR_ATTR_2(pwm1_auto_point5_pwm, S_IRUGO|S_IWUSR,
+		      show_pwm_auto_point_pwm, store_pwm_auto_point_pwm,
+		      4, 0),
+	SENSOR_ATTR_2(pwm1_auto_point1_temp, S_IRUGO|S_IWUSR,
+		      show_pwm_auto_point_temp, store_pwm_auto_point_temp,
+		      0, 0),
+	SENSOR_ATTR_2(pwm1_auto_point2_temp, S_IRUGO|S_IWUSR,
+		      show_pwm_auto_point_temp, store_pwm_auto_point_temp,
+		      1, 0),
+	SENSOR_ATTR_2(pwm1_auto_point3_temp, S_IRUGO|S_IWUSR,
+		      show_pwm_auto_point_temp, store_pwm_auto_point_temp,
+		      2, 0),
+	SENSOR_ATTR_2(pwm1_auto_point4_temp, S_IRUGO|S_IWUSR,
+		      show_pwm_auto_point_temp, store_pwm_auto_point_temp,
+		      3, 0),
+	SENSOR_ATTR_2(pwm1_auto_point1_temp_hyst, S_IRUGO|S_IWUSR,
+		      show_pwm_auto_point_temp_hyst,
+		      store_pwm_auto_point_temp_hyst,
+		      0, 0),
+	SENSOR_ATTR_2(pwm1_auto_point2_temp_hyst, S_IRUGO,
+		      show_pwm_auto_point_temp_hyst, NULL, 1, 0),
+	SENSOR_ATTR_2(pwm1_auto_point3_temp_hyst, S_IRUGO,
+		      show_pwm_auto_point_temp_hyst, NULL, 2, 0),
+	SENSOR_ATTR_2(pwm1_auto_point4_temp_hyst, S_IRUGO,
+		      show_pwm_auto_point_temp_hyst, NULL, 3, 0),
+
+	SENSOR_ATTR_2(pwm2_auto_point1_pwm, S_IRUGO|S_IWUSR,
+		      show_pwm_auto_point_pwm, store_pwm_auto_point_pwm,
+		      0, 1),
+	SENSOR_ATTR_2(pwm2_auto_point2_pwm, S_IRUGO|S_IWUSR,
+		      show_pwm_auto_point_pwm, store_pwm_auto_point_pwm,
+		      1, 1),
+	SENSOR_ATTR_2(pwm2_auto_point3_pwm, S_IRUGO|S_IWUSR,
+		      show_pwm_auto_point_pwm, store_pwm_auto_point_pwm,
+		      2, 1),
+	SENSOR_ATTR_2(pwm2_auto_point4_pwm, S_IRUGO|S_IWUSR,
+		      show_pwm_auto_point_pwm, store_pwm_auto_point_pwm,
+		      3, 1),
+	SENSOR_ATTR_2(pwm2_auto_point5_pwm, S_IRUGO|S_IWUSR,
+		      show_pwm_auto_point_pwm, store_pwm_auto_point_pwm,
+		      4, 1),
+	SENSOR_ATTR_2(pwm2_auto_point1_temp, S_IRUGO|S_IWUSR,
+		      show_pwm_auto_point_temp, store_pwm_auto_point_temp,
+		      0, 1),
+	SENSOR_ATTR_2(pwm2_auto_point2_temp, S_IRUGO|S_IWUSR,
+		      show_pwm_auto_point_temp, store_pwm_auto_point_temp,
+		      1, 1),
+	SENSOR_ATTR_2(pwm2_auto_point3_temp, S_IRUGO|S_IWUSR,
+		      show_pwm_auto_point_temp, store_pwm_auto_point_temp,
+		      2, 1),
+	SENSOR_ATTR_2(pwm2_auto_point4_temp, S_IRUGO|S_IWUSR,
+		      show_pwm_auto_point_temp, store_pwm_auto_point_temp,
+		      3, 1),
+	SENSOR_ATTR_2(pwm2_auto_point1_temp_hyst, S_IRUGO|S_IWUSR,
+		      show_pwm_auto_point_temp_hyst,
+		      store_pwm_auto_point_temp_hyst,
+		      0, 1),
+	SENSOR_ATTR_2(pwm2_auto_point2_temp_hyst, S_IRUGO,
+		      show_pwm_auto_point_temp_hyst, NULL, 1, 1),
+	SENSOR_ATTR_2(pwm2_auto_point3_temp_hyst, S_IRUGO,
+		      show_pwm_auto_point_temp_hyst, NULL, 2, 1),
+	SENSOR_ATTR_2(pwm2_auto_point4_temp_hyst, S_IRUGO,
+		      show_pwm_auto_point_temp_hyst, NULL, 3, 1),
+
+	SENSOR_ATTR_2(pwm3_auto_point1_pwm, S_IRUGO|S_IWUSR,
+		      show_pwm_auto_point_pwm, store_pwm_auto_point_pwm,
+		      0, 2),
+	SENSOR_ATTR_2(pwm3_auto_point2_pwm, S_IRUGO|S_IWUSR,
+		      show_pwm_auto_point_pwm, store_pwm_auto_point_pwm,
+		      1, 2),
+	SENSOR_ATTR_2(pwm3_auto_point3_pwm, S_IRUGO|S_IWUSR,
+		      show_pwm_auto_point_pwm, store_pwm_auto_point_pwm,
+		      2, 2),
+	SENSOR_ATTR_2(pwm3_auto_point4_pwm, S_IRUGO|S_IWUSR,
+		      show_pwm_auto_point_pwm, store_pwm_auto_point_pwm,
+		      3, 2),
+	SENSOR_ATTR_2(pwm3_auto_point5_pwm, S_IRUGO|S_IWUSR,
+		      show_pwm_auto_point_pwm, store_pwm_auto_point_pwm,
+		      4, 2),
+	SENSOR_ATTR_2(pwm3_auto_point1_temp, S_IRUGO|S_IWUSR,
+		      show_pwm_auto_point_temp, store_pwm_auto_point_temp,
+		      0, 2),
+	SENSOR_ATTR_2(pwm3_auto_point2_temp, S_IRUGO|S_IWUSR,
+		      show_pwm_auto_point_temp, store_pwm_auto_point_temp,
+		      1, 2),
+	SENSOR_ATTR_2(pwm3_auto_point3_temp, S_IRUGO|S_IWUSR,
+		      show_pwm_auto_point_temp, store_pwm_auto_point_temp,
+		      2, 2),
+	SENSOR_ATTR_2(pwm3_auto_point4_temp, S_IRUGO|S_IWUSR,
+		      show_pwm_auto_point_temp, store_pwm_auto_point_temp,
+		      3, 2),
+	SENSOR_ATTR_2(pwm3_auto_point1_temp_hyst, S_IRUGO|S_IWUSR,
+		      show_pwm_auto_point_temp_hyst,
+		      store_pwm_auto_point_temp_hyst,
+		      0, 2),
+	SENSOR_ATTR_2(pwm3_auto_point2_temp_hyst, S_IRUGO,
+		      show_pwm_auto_point_temp_hyst, NULL, 1, 2),
+	SENSOR_ATTR_2(pwm3_auto_point3_temp_hyst, S_IRUGO,
+		      show_pwm_auto_point_temp_hyst, NULL, 2, 2),
+	SENSOR_ATTR_2(pwm3_auto_point4_temp_hyst, S_IRUGO,
+		      show_pwm_auto_point_temp_hyst, NULL, 3, 2),
+
+	SENSOR_ATTR_2(pwm4, S_IRUGO|S_IWUSR, show_pwm, store_pwm, 0, 3),
+	SENSOR_ATTR_2(pwm4_enable, S_IRUGO|S_IWUSR, show_pwm_enable,
+		      store_pwm_enable, 0, 3),
+	SENSOR_ATTR_2(pwm4_interpolate, S_IRUGO|S_IWUSR,
+		      show_pwm_interpolate, store_pwm_interpolate, 0, 3),
+	SENSOR_ATTR_2(pwm4_auto_channels_temp, S_IRUGO|S_IWUSR,
+		      show_pwm_auto_point_channel,
+		      store_pwm_auto_point_channel, 0, 3),
+	SENSOR_ATTR_2(pwm4_auto_point1_pwm, S_IRUGO|S_IWUSR,
+		      show_pwm_auto_point_pwm, store_pwm_auto_point_pwm,
+		      0, 3),
+	SENSOR_ATTR_2(pwm4_auto_point2_pwm, S_IRUGO|S_IWUSR,
+		      show_pwm_auto_point_pwm, store_pwm_auto_point_pwm,
+		      1, 3),
+	SENSOR_ATTR_2(pwm4_auto_point3_pwm, S_IRUGO|S_IWUSR,
+		      show_pwm_auto_point_pwm, store_pwm_auto_point_pwm,
+		      2, 3),
+	SENSOR_ATTR_2(pwm4_auto_point4_pwm, S_IRUGO|S_IWUSR,
+		      show_pwm_auto_point_pwm, store_pwm_auto_point_pwm,
+		      3, 3),
+	SENSOR_ATTR_2(pwm4_auto_point5_pwm, S_IRUGO|S_IWUSR,
+		      show_pwm_auto_point_pwm, store_pwm_auto_point_pwm,
+		      4, 3),
+	SENSOR_ATTR_2(pwm4_auto_point1_temp, S_IRUGO|S_IWUSR,
+		      show_pwm_auto_point_temp, store_pwm_auto_point_temp,
+		      0, 3),
+	SENSOR_ATTR_2(pwm4_auto_point2_temp, S_IRUGO|S_IWUSR,
+		      show_pwm_auto_point_temp, store_pwm_auto_point_temp,
+		      1, 3),
+	SENSOR_ATTR_2(pwm4_auto_point3_temp, S_IRUGO|S_IWUSR,
+		      show_pwm_auto_point_temp, store_pwm_auto_point_temp,
+		      2, 3),
+	SENSOR_ATTR_2(pwm4_auto_point4_temp, S_IRUGO|S_IWUSR,
+		      show_pwm_auto_point_temp, store_pwm_auto_point_temp,
+		      3, 3),
+	SENSOR_ATTR_2(pwm4_auto_point1_temp_hyst, S_IRUGO|S_IWUSR,
+		      show_pwm_auto_point_temp_hyst,
+		      store_pwm_auto_point_temp_hyst,
+		      0, 3),
+	SENSOR_ATTR_2(pwm4_auto_point2_temp_hyst, S_IRUGO,
+		      show_pwm_auto_point_temp_hyst, NULL, 1, 3),
+	SENSOR_ATTR_2(pwm4_auto_point3_temp_hyst, S_IRUGO,
+		      show_pwm_auto_point_temp_hyst, NULL, 2, 3),
+	SENSOR_ATTR_2(pwm4_auto_point4_temp_hyst, S_IRUGO,
+		      show_pwm_auto_point_temp_hyst, NULL, 3, 3),
 };
 
 
@@ -304,6 +618,11 @@ static inline u16 fan_from_reg(u16 reg)
 	return reg ? (1500000 / reg) : 0;
 }
 
+static inline u16 fan_to_reg(u16 fan)
+{
+	return fan ? (1500000 / fan) : 0;
+}
+
 static u8 f71882fg_read8(struct f71882fg_data *data, u8 reg)
 {
 	u8 val;
@@ -332,18 +651,31 @@ static void f71882fg_write8(struct f71882fg_data *data, u8 reg, u8 val)
 	outb(val, data->addr + DATA_REG_OFFSET);
 }
 
-static struct f71882fg_data *f71882fg_update_device(struct device * dev)
+static void f71882fg_write16(struct f71882fg_data *data, u8 reg, u16 val)
+{
+	outb(reg++, data->addr + ADDR_REG_OFFSET);
+	outb(val >> 8, data->addr + DATA_REG_OFFSET);
+	outb(reg, data->addr + ADDR_REG_OFFSET);
+	outb(val & 255, data->addr + DATA_REG_OFFSET);
+}
+
+static struct f71882fg_data *f71882fg_update_device(struct device *dev)
 {
 	struct f71882fg_data *data = dev_get_drvdata(dev);
 	int nr, reg, reg2;
+	int nr_fans = (data->type == f71862fg) ? 3 : 4;
 
 	mutex_lock(&data->update_lock);
 
 	/* Update once every 60 seconds */
 	if ( time_after(jiffies, data->last_limits + 60 * HZ ) ||
 			!data->valid) {
-		data->in1_max = f71882fg_read8(data, F71882FG_REG_IN1_HIGH);
-		data->in_beep = f71882fg_read8(data, F71882FG_REG_IN_BEEP);
+		if (data->type == f71882fg) {
+			data->in1_max =
+				f71882fg_read8(data, F71882FG_REG_IN1_HIGH);
+			data->in_beep =
+				f71882fg_read8(data, F71882FG_REG_IN_BEEP);
+		}
 
 		/* Get High & boundary temps*/
 		for (nr = 0; nr < 3; nr++) {
@@ -378,6 +710,50 @@ static struct f71882fg_data *f71882fg_update_device(struct device * dev)
 
 		data->fan_beep = f71882fg_read8(data, F71882FG_REG_FAN_BEEP);
 
+		data->pwm_enable = f71882fg_read8(data,
+						  F71882FG_REG_PWM_ENABLE);
+		data->pwm_auto_point_hyst[0] = f71882fg_read8(data,
+						      F71882FG_REG_FAN_HYST0);
+		data->pwm_auto_point_hyst[1] = f71882fg_read8(data,
+						      F71882FG_REG_FAN_HYST1);
+		for (nr = 0; nr < nr_fans; nr++) {
+			data->pwm_auto_point_mapping[nr] =
+			    f71882fg_read8(data,
+					   F71882FG_REG_POINT_MAPPING(nr));
+
+			if (data->type == f71882fg) {
+				int point;
+				for (point = 0; point < 5; point++) {
+					data->pwm_auto_point_pwm[nr][point] =
+						f71882fg_read8(data,
+							F71882FG_REG_POINT_PWM
+							(nr, point));
+				}
+				for (point = 0; point < 4; point++) {
+					data->pwm_auto_point_temp[nr][point] =
+						f71882fg_read8(data,
+							F71882FG_REG_POINT_TEMP
+							(nr, point));
+				}
+			} else {
+				data->pwm_auto_point_pwm[nr][1] =
+					f71882fg_read8(data,
+						F71882FG_REG_POINT_PWM
+						(nr, 1));
+				data->pwm_auto_point_pwm[nr][4] =
+					f71882fg_read8(data,
+						F71882FG_REG_POINT_PWM
+						(nr, 4));
+				data->pwm_auto_point_temp[nr][0] =
+					f71882fg_read8(data,
+						F71882FG_REG_POINT_TEMP
+						(nr, 0));
+				data->pwm_auto_point_temp[nr][3] =
+					f71882fg_read8(data,
+						F71882FG_REG_POINT_TEMP
+						(nr, 3));
+			}
+		}
 		data->last_limits = jiffies;
 	}
 
@@ -393,11 +769,20 @@ static struct f71882fg_data *f71882fg_update_device(struct device * dev)
 
 		data->fan_status = f71882fg_read8(data,
 						F71882FG_REG_FAN_STATUS);
-		for (nr = 0; nr < 4; nr++)
+		for (nr = 0; nr < nr_fans; nr++) {
 			data->fan[nr] = f71882fg_read16(data,
 						F71882FG_REG_FAN(nr));
+			data->fan_target[nr] =
+			    f71882fg_read16(data, F71882FG_REG_FAN_TARGET(nr));
+			data->fan_full_speed[nr] =
+			    f71882fg_read16(data,
+					    F71882FG_REG_FAN_FULL_SPEED(nr));
+			data->pwm[nr] =
+			    f71882fg_read8(data, F71882FG_REG_PWM(nr));
+		}
 
-		data->in_status = f71882fg_read8(data,
+		if (data->type == f71882fg)
+			data->in_status = f71882fg_read8(data,
 						F71882FG_REG_IN_STATUS);
 		for (nr = 0; nr < 9; nr++)
 			data->in[nr] = f71882fg_read8(data,
@@ -417,7 +802,7 @@ static ssize_t show_fan(struct device *dev, struct device_attribute *devattr,
 	char *buf)
 {
 	struct f71882fg_data *data = f71882fg_update_device(dev);
-	int nr = to_sensor_dev_attr(devattr)->index;
+	int nr = to_sensor_dev_attr_2(devattr)->index;
 	int speed = fan_from_reg(data->fan[nr]);
 
 	if (speed == FAN_MIN_DETECT)
@@ -426,11 +811,45 @@ static ssize_t show_fan(struct device *dev, struct device_attribute *devattr,
 	return sprintf(buf, "%d\n", speed);
 }
 
+static ssize_t show_fan_full_speed(struct device *dev,
+				   struct device_attribute *devattr, char *buf)
+{
+	struct f71882fg_data *data = f71882fg_update_device(dev);
+	int nr = to_sensor_dev_attr_2(devattr)->index;
+	int speed = fan_from_reg(data->fan_full_speed[nr]);
+	return sprintf(buf, "%d\n", speed);
+}
+
+static ssize_t store_fan_full_speed(struct device *dev,
+				    struct device_attribute *devattr,
+				    const char *buf, size_t count)
+{
+	struct f71882fg_data *data = dev_get_drvdata(dev);
+	int nr = to_sensor_dev_attr_2(devattr)->index;
+	long val = simple_strtol(buf, NULL, 10);
+
+	val = SENSORS_LIMIT(val, 23, 1500000);
+	val = fan_to_reg(val);
+
+	mutex_lock(&data->update_lock);
+	if (data->pwm_enable & (1 << (2 * nr)))
+		/* PWM mode */
+		count = -EINVAL;
+	else {
+		/* RPM mode */
+		f71882fg_write16(data, F71882FG_REG_FAN_FULL_SPEED(nr), val);
+		data->fan_full_speed[nr] = val;
+	}
+	mutex_unlock(&data->update_lock);
+
+	return count;
+}
+
 static ssize_t show_fan_beep(struct device *dev, struct device_attribute
 	*devattr, char *buf)
 {
 	struct f71882fg_data *data = f71882fg_update_device(dev);
-	int nr = to_sensor_dev_attr(devattr)->index;
+	int nr = to_sensor_dev_attr_2(devattr)->index;
 
 	if (data->fan_beep & (1 << nr))
 		return sprintf(buf, "1\n");
@@ -442,7 +861,7 @@ static ssize_t store_fan_beep(struct device *dev, struct device_attribute
 	*devattr, const char *buf, size_t count)
 {
 	struct f71882fg_data *data = dev_get_drvdata(dev);
-	int nr = to_sensor_dev_attr(devattr)->index;
+	int nr = to_sensor_dev_attr_2(devattr)->index;
 	int val = simple_strtoul(buf, NULL, 10);
 
 	mutex_lock(&data->update_lock);
@@ -461,7 +880,7 @@ static ssize_t show_fan_alarm(struct device *dev, struct device_attribute
 	*devattr, char *buf)
 {
 	struct f71882fg_data *data = f71882fg_update_device(dev);
-	int nr = to_sensor_dev_attr(devattr)->index;
+	int nr = to_sensor_dev_attr_2(devattr)->index;
 
 	if (data->fan_status & (1 << nr))
 		return sprintf(buf, "1\n");
@@ -473,7 +892,7 @@ static ssize_t show_in(struct device *dev, struct device_attribute *devattr,
 	char *buf)
 {
 	struct f71882fg_data *data = f71882fg_update_device(dev);
-	int nr = to_sensor_dev_attr(devattr)->index;
+	int nr = to_sensor_dev_attr_2(devattr)->index;
 
 	return sprintf(buf, "%d\n", data->in[nr] * 8);
 }
@@ -507,7 +926,7 @@ static ssize_t show_in_beep(struct device *dev, struct device_attribute
 	*devattr, char *buf)
 {
 	struct f71882fg_data *data = f71882fg_update_device(dev);
-	int nr = to_sensor_dev_attr(devattr)->index;
+	int nr = to_sensor_dev_attr_2(devattr)->index;
 
 	if (data->in_beep & (1 << nr))
 		return sprintf(buf, "1\n");
@@ -519,7 +938,7 @@ static ssize_t store_in_beep(struct device *dev, struct device_attribute
 	*devattr, const char *buf, size_t count)
 {
 	struct f71882fg_data *data = dev_get_drvdata(dev);
-	int nr = to_sensor_dev_attr(devattr)->index;
+	int nr = to_sensor_dev_attr_2(devattr)->index;
 	int val = simple_strtoul(buf, NULL, 10);
 
 	mutex_lock(&data->update_lock);
@@ -538,7 +957,7 @@ static ssize_t show_in_alarm(struct device *dev, struct device_attribute
 	*devattr, char *buf)
 {
 	struct f71882fg_data *data = f71882fg_update_device(dev);
-	int nr = to_sensor_dev_attr(devattr)->index;
+	int nr = to_sensor_dev_attr_2(devattr)->index;
 
 	if (data->in_status & (1 << nr))
 		return sprintf(buf, "1\n");
@@ -550,7 +969,7 @@ static ssize_t show_temp(struct device *dev, struct device_attribute *devattr,
 	char *buf)
 {
 	struct f71882fg_data *data = f71882fg_update_device(dev);
-	int nr = to_sensor_dev_attr(devattr)->index;
+	int nr = to_sensor_dev_attr_2(devattr)->index;
 
 	return sprintf(buf, "%d\n", data->temp[nr] * 1000);
 }
@@ -559,7 +978,7 @@ static ssize_t show_temp_max(struct device *dev, struct device_attribute
 	*devattr, char *buf)
 {
 	struct f71882fg_data *data = f71882fg_update_device(dev);
-	int nr = to_sensor_dev_attr(devattr)->index;
+	int nr = to_sensor_dev_attr_2(devattr)->index;
 
 	return sprintf(buf, "%d\n", data->temp_high[nr] * 1000);
 }
@@ -568,7 +987,7 @@ static ssize_t store_temp_max(struct device *dev, struct device_attribute
 	*devattr, const char *buf, size_t count)
 {
 	struct f71882fg_data *data = dev_get_drvdata(dev);
-	int nr = to_sensor_dev_attr(devattr)->index;
+	int nr = to_sensor_dev_attr_2(devattr)->index;
 	int val = simple_strtoul(buf, NULL, 10) / 1000;
 
 	if (val > 255)
@@ -586,7 +1005,7 @@ static ssize_t show_temp_max_hyst(struct device *dev, struct device_attribute
 	*devattr, char *buf)
 {
 	struct f71882fg_data *data = f71882fg_update_device(dev);
-	int nr = to_sensor_dev_attr(devattr)->index;
+	int nr = to_sensor_dev_attr_2(devattr)->index;
 
 	return sprintf(buf, "%d\n",
 		(data->temp_high[nr] - data->temp_hyst[nr]) * 1000);
@@ -596,7 +1015,7 @@ static ssize_t store_temp_max_hyst(struct device *dev, struct device_attribute
 	*devattr, const char *buf, size_t count)
 {
 	struct f71882fg_data *data = dev_get_drvdata(dev);
-	int nr = to_sensor_dev_attr(devattr)->index;
+	int nr = to_sensor_dev_attr_2(devattr)->index;
 	int val = simple_strtoul(buf, NULL, 10) / 1000;
 	ssize_t ret = count;
 
@@ -636,7 +1055,7 @@ static ssize_t show_temp_crit(struct device *dev, struct device_attribute
 	*devattr, char *buf)
 {
 	struct f71882fg_data *data = f71882fg_update_device(dev);
-	int nr = to_sensor_dev_attr(devattr)->index;
+	int nr = to_sensor_dev_attr_2(devattr)->index;
 
 	return sprintf(buf, "%d\n", data->temp_ovt[nr] * 1000);
 }
@@ -645,7 +1064,7 @@ static ssize_t store_temp_crit(struct device *dev, struct device_attribute
 	*devattr, const char *buf, size_t count)
 {
 	struct f71882fg_data *data = dev_get_drvdata(dev);
-	int nr = to_sensor_dev_attr(devattr)->index;
+	int nr = to_sensor_dev_attr_2(devattr)->index;
 	int val = simple_strtoul(buf, NULL, 10) / 1000;
 
 	if (val > 255)
@@ -663,7 +1082,7 @@ static ssize_t show_temp_crit_hyst(struct device *dev, struct device_attribute
 	*devattr, char *buf)
 {
 	struct f71882fg_data *data = f71882fg_update_device(dev);
-	int nr = to_sensor_dev_attr(devattr)->index;
+	int nr = to_sensor_dev_attr_2(devattr)->index;
 
 	return sprintf(buf, "%d\n",
 		(data->temp_ovt[nr] - data->temp_hyst[nr]) * 1000);
@@ -673,7 +1092,7 @@ static ssize_t show_temp_type(struct device *dev, struct device_attribute
 	*devattr, char *buf)
 {
 	struct f71882fg_data *data = f71882fg_update_device(dev);
-	int nr = to_sensor_dev_attr(devattr)->index;
+	int nr = to_sensor_dev_attr_2(devattr)->index;
 
 	return sprintf(buf, "%d\n", data->temp_type[nr]);
 }
@@ -682,7 +1101,7 @@ static ssize_t show_temp_beep(struct device *dev, struct device_attribute
 	*devattr, char *buf)
 {
 	struct f71882fg_data *data = f71882fg_update_device(dev);
-	int nr = to_sensor_dev_attr(devattr)->index;
+	int nr = to_sensor_dev_attr_2(devattr)->index;
 
 	if (data->temp_beep & (1 << (nr + 1)))
 		return sprintf(buf, "1\n");
@@ -694,7 +1113,7 @@ static ssize_t store_temp_beep(struct device *dev, struct device_attribute
 	*devattr, const char *buf, size_t count)
 {
 	struct f71882fg_data *data = dev_get_drvdata(dev);
-	int nr = to_sensor_dev_attr(devattr)->index;
+	int nr = to_sensor_dev_attr_2(devattr)->index;
 	int val = simple_strtoul(buf, NULL, 10);
 
 	mutex_lock(&data->update_lock);
@@ -713,7 +1132,7 @@ static ssize_t show_temp_alarm(struct device *dev, struct device_attribute
 	*devattr, char *buf)
 {
 	struct f71882fg_data *data = f71882fg_update_device(dev);
-	int nr = to_sensor_dev_attr(devattr)->index;
+	int nr = to_sensor_dev_attr_2(devattr)->index;
 
 	if (data->temp_status & (1 << (nr + 1)))
 		return sprintf(buf, "1\n");
@@ -725,7 +1144,7 @@ static ssize_t show_temp_fault(struct device *dev, struct device_attribute
 	*devattr, char *buf)
 {
 	struct f71882fg_data *data = f71882fg_update_device(dev);
-	int nr = to_sensor_dev_attr(devattr)->index;
+	int nr = to_sensor_dev_attr_2(devattr)->index;
 
 	if (data->temp_diode_open & (1 << (nr + 1)))
 		return sprintf(buf, "1\n");
@@ -733,91 +1152,462 @@ static ssize_t show_temp_fault(struct device *dev, struct device_attribute
 		return sprintf(buf, "0\n");
 }
 
+static ssize_t show_pwm(struct device *dev,
+			struct device_attribute *devattr, char *buf)
+{
+	struct f71882fg_data *data = f71882fg_update_device(dev);
+	int val, nr = to_sensor_dev_attr_2(devattr)->index;
+	if (data->pwm_enable & (1 << (2 * nr)))
+		/* PWM mode */
+		val = data->pwm[nr];
+	else {
+		/* RPM mode */
+		mutex_lock(&data->update_lock);
+		val = 255 * fan_from_reg(data->fan_target[nr])
+			/ fan_from_reg(data->fan_full_speed[nr]);
+		mutex_unlock(&data->update_lock);
+	}
+	return sprintf(buf, "%d\n", val);
+}
+
+static ssize_t store_pwm(struct device *dev,
+			 struct device_attribute *devattr, const char *buf,
+			 size_t count)
+{
+	/* struct f71882fg_data *data = dev_get_drvdata(dev); */
+	struct f71882fg_data *data = f71882fg_update_device(dev);
+	int nr = to_sensor_dev_attr_2(devattr)->index;
+	long val = simple_strtol(buf, NULL, 10);
+	val = SENSORS_LIMIT(val, 0, 255);
+
+	mutex_lock(&data->update_lock);
+	if (data->pwm_enable & (1 << (2 * nr))) {
+		/* PWM mode */
+		f71882fg_write8(data, F71882FG_REG_PWM(nr), val);
+		data->pwm[nr] = val;
+	} else {
+		/* RPM mode */
+		int target = val * fan_from_reg(data->fan_full_speed[nr]) / 255;
+		f71882fg_write16(data, F71882FG_REG_FAN_TARGET(nr),
+				 fan_to_reg(target));
+		data->fan_target[nr] = fan_to_reg(target);
+	}
+	mutex_unlock(&data->update_lock);
+
+	return count;
+}
+
+static ssize_t show_pwm_enable(struct device *dev,
+			       struct device_attribute *devattr, char *buf)
+{
+	int result;
+	struct f71882fg_data *data = f71882fg_update_device(dev);
+	int nr = to_sensor_dev_attr_2(devattr)->index;
+
+	if (data->pwm_enable & (2 << (2 * nr)))
+		result = 1;
+	else
+		result = 2;
+
+	return sprintf(buf, "%d\n", result);
+}
+
+static ssize_t store_pwm_enable(struct device *dev, struct device_attribute
+				*devattr, const char *buf, size_t count)
+{
+	struct f71882fg_data *data = dev_get_drvdata(dev);
+	int nr = to_sensor_dev_attr_2(devattr)->index;
+	long val = simple_strtol(buf, NULL, 10);
+	if (val < 1 || val > 2)
+		return -EINVAL;
+
+	mutex_lock(&data->update_lock);
+	switch (val) {
+	case 1:
+		data->pwm_enable |= 2 << (2 * nr);
+		break;		/* Manual */
+	case 2:
+		data->pwm_enable &= ~(2 << (2 * nr));
+		break;		/* Temperature ctrl */
+	}
+	if (data->type == f71882fg) {
+		switch (fan_mode[nr]) {
+		case 1:
+			data->pwm_enable |= 1 << (2 * nr);
+			break;		/* Duty cycle mode */
+		case 2:
+			data->pwm_enable &= ~(1 << (2 * nr));
+			break;		/* RPM mode */
+		}
+	}
+	f71882fg_write8(data, F71882FG_REG_PWM_ENABLE, data->pwm_enable);
+	mutex_unlock(&data->update_lock);
+
+	return count;
+}
+
+static ssize_t show_pwm_auto_point_pwm(struct device *dev,
+				       struct device_attribute *devattr,
+				       char *buf)
+{
+	int result;
+	struct f71882fg_data *data = f71882fg_update_device(dev);
+	int pwm = to_sensor_dev_attr_2(devattr)->index;
+	int point = to_sensor_dev_attr_2(devattr)->nr;
+
+	if (data->pwm_enable & (1 << (2 * pwm))) {
+		/* PWM mode */
+		result = data->pwm_auto_point_pwm[pwm][point];
+	} else {
+		/* RPM mode */
+		result = 32 * 255 / (32 + data->pwm_auto_point_pwm[pwm][point]);
+	}
+
+	return sprintf(buf, "%d\n", result);
+}
+
+static ssize_t store_pwm_auto_point_pwm(struct device *dev,
+					struct device_attribute *devattr,
+					const char *buf, size_t count)
+{
+	/* struct f71882fg_data *data = dev_get_drvdata(dev); */
+	struct f71882fg_data *data = f71882fg_update_device(dev);
+	int pwm = to_sensor_dev_attr_2(devattr)->index;
+	int point = to_sensor_dev_attr_2(devattr)->nr;
+	int val = simple_strtoul(buf, NULL, 10);
+	val = SENSORS_LIMIT(val, 0, 255);
+
+	mutex_lock(&data->update_lock);
+	if (data->pwm_enable & (1 << (2 * pwm))) {
+		/* PWM mode */
+	} else {
+		/* RPM mode */
+		if (val < 29)	/* Prevent negative numbers */
+			val = 255;
+		else
+			val = (255 - val) * 32 / val;
+	}
+	f71882fg_write8(data, F71882FG_REG_POINT_PWM(pwm, point), val);
+	data->pwm_auto_point_pwm[pwm][point] = val;
+	mutex_unlock(&data->update_lock);
+
+	return count;
+}
+
+static ssize_t show_pwm_auto_point_temp_hyst(struct device *dev,
+					     struct device_attribute *devattr,
+					     char *buf)
+{
+	int result = 0;
+	struct f71882fg_data *data = f71882fg_update_device(dev);
+	int nr = to_sensor_dev_attr_2(devattr)->index;
+	int point = to_sensor_dev_attr_2(devattr)->nr;
+
+	mutex_lock(&data->update_lock);
+	switch (nr) {
+	case 0:
+		result = data->pwm_auto_point_hyst[0] & 0x0f;
+		break;
+	case 1:
+		result = data->pwm_auto_point_hyst[0] >> 4;
+		break;
+	case 2:
+		result = data->pwm_auto_point_hyst[1] & 0x0f;
+		break;
+	case 3:
+		result = data->pwm_auto_point_hyst[1] >> 4;
+		break;
+	}
+	result = 1000 * (data->pwm_auto_point_temp[nr][point] - result);
+	mutex_unlock(&data->update_lock);
+
+	return sprintf(buf, "%d\n", result);
+}
+
+static ssize_t store_pwm_auto_point_temp_hyst(struct device *dev,
+					      struct device_attribute *devattr,
+					      const char *buf, size_t count)
+{
+	struct f71882fg_data *data = f71882fg_update_device(dev);
+	int nr = to_sensor_dev_attr_2(devattr)->index;
+	int point = to_sensor_dev_attr_2(devattr)->nr;
+	long val = simple_strtol(buf, NULL, 10) / 1000;
+
+	mutex_lock(&data->update_lock);
+	val = SENSORS_LIMIT(val, data->pwm_auto_point_temp[nr][point] - 15,
+				data->pwm_auto_point_temp[nr][point]);
+	val = data->pwm_auto_point_temp[nr][point] - val;
+
+	switch (nr) {
+	case 0:
+		val = (data->pwm_auto_point_hyst[0] & 0xf0) | val;
+		break;
+	case 1:
+		val = (data->pwm_auto_point_hyst[0] & 0x0f) | (val << 4);
+		break;
+	case 2:
+		val = (data->pwm_auto_point_hyst[1] & 0xf0) | val;
+		break;
+	case 3:
+		val = (data->pwm_auto_point_hyst[1] & 0x0f) | (val << 4);
+		break;
+	}
+	if (nr == 0 || nr == 1) {
+		f71882fg_write8(data, F71882FG_REG_FAN_HYST0, val);
+		data->pwm_auto_point_hyst[0] = val;
+	} else {
+		f71882fg_write8(data, F71882FG_REG_FAN_HYST1, val);
+		data->pwm_auto_point_hyst[1] = val;
+	}
+	mutex_unlock(&data->update_lock);
+
+	return count;
+}
+
+static ssize_t show_pwm_interpolate(struct device *dev,
+				    struct device_attribute *devattr, char *buf)
+{
+	int result;
+	struct f71882fg_data *data = f71882fg_update_device(dev);
+	int nr = to_sensor_dev_attr_2(devattr)->index;
+
+	result = (data->pwm_auto_point_mapping[nr] >> 4) & 1;
+
+	return sprintf(buf, "%d\n", result);
+}
+
+static ssize_t store_pwm_interpolate(struct device *dev,
+				     struct device_attribute *devattr,
+				     const char *buf, size_t count)
+{
+	/* struct f71882fg_data *data = dev_get_drvdata(dev); */
+	struct f71882fg_data *data = f71882fg_update_device(dev);
+	int nr = to_sensor_dev_attr_2(devattr)->index;
+	int val = simple_strtoul(buf, NULL, 10);
+	mutex_lock(&data->update_lock);
+	if (val)
+		val = data->pwm_auto_point_mapping[nr] | (1 << 4);
+	else
+		val = data->pwm_auto_point_mapping[nr] & (~(1 << 4));
+	f71882fg_write8(data, F71882FG_REG_POINT_MAPPING(nr), val);
+	data->pwm_auto_point_mapping[nr] = val;
+	mutex_unlock(&data->update_lock);
+
+	return count;
+}
+
+static ssize_t show_pwm_auto_point_channel(struct device *dev,
+					   struct device_attribute *devattr,
+					   char *buf)
+{
+	int result;
+	struct f71882fg_data *data = f71882fg_update_device(dev);
+	int nr = to_sensor_dev_attr_2(devattr)->index;
+
+	result = 1 << ((data->pwm_auto_point_mapping[nr] & 3) - 1);
+
+	return sprintf(buf, "%d\n", result);
+}
+
+static ssize_t store_pwm_auto_point_channel(struct device *dev,
+					    struct device_attribute *devattr,
+					    const char *buf, size_t count)
+{
+	/* struct f71882fg_data *data = dev_get_drvdata(dev); */
+	struct f71882fg_data *data = f71882fg_update_device(dev);
+	int nr = to_sensor_dev_attr_2(devattr)->index;
+	long val = simple_strtol(buf, NULL, 10);
+	switch (val) {
+	case 1:
+		val = 1;
+		break;
+	case 2:
+		val = 2;
+		break;
+	case 4:
+		val = 3;
+		break;
+	default:
+		return -EINVAL;
+	}
+	mutex_lock(&data->update_lock);
+	val = (data->pwm_auto_point_mapping[nr] & 0xfc) | val;
+	f71882fg_write8(data, F71882FG_REG_POINT_MAPPING(nr), val);
+	data->pwm_auto_point_mapping[nr] = val;
+	mutex_unlock(&data->update_lock);
+
+	return count;
+}
+
+static ssize_t show_pwm_auto_point_temp(struct device *dev,
+					struct device_attribute *devattr,
+					char *buf)
+{
+	int result;
+	struct f71882fg_data *data = f71882fg_update_device(dev);
+	int pwm = to_sensor_dev_attr_2(devattr)->index;
+	int point = to_sensor_dev_attr_2(devattr)->nr;
+
+	result = data->pwm_auto_point_temp[pwm][point];
+	return sprintf(buf, "%d\n", 1000 * result);
+}
+
+static ssize_t store_pwm_auto_point_temp(struct device *dev,
+					 struct device_attribute *devattr,
+					 const char *buf, size_t count)
+{
+	/* struct f71882fg_data *data = dev_get_drvdata(dev); */
+	struct f71882fg_data *data = f71882fg_update_device(dev);
+	int pwm = to_sensor_dev_attr_2(devattr)->index;
+	int point = to_sensor_dev_attr_2(devattr)->nr;
+	long val = simple_strtol(buf, NULL, 10) / 1000;
+	val = SENSORS_LIMIT(val, 0, 255);
+
+	mutex_lock(&data->update_lock);
+	f71882fg_write8(data, F71882FG_REG_POINT_TEMP(pwm, point), val);
+	data->pwm_auto_point_temp[pwm][point] = val;
+	mutex_unlock(&data->update_lock);
+
+	return count;
+}
+
 static ssize_t show_name(struct device *dev, struct device_attribute *devattr,
 	char *buf)
 {
-	return sprintf(buf, DRVNAME "\n");
+	struct f71882fg_data *data = dev_get_drvdata(dev);
+	return sprintf(buf, "%s\n", f71882fg_names[data->type]);
 }
 
+static int __devinit f71882fg_create_sysfs_files(struct platform_device *pdev,
+	struct sensor_device_attribute_2 *attr, int count)
+{
+	int err, i;
+
+	for (i = 0; i < count; i++) {
+		err = device_create_file(&pdev->dev, &attr[i].dev_attr);
+		if (err)
+			return err;
+	}
+	return 0;
+}
 
-static int __devinit f71882fg_probe(struct platform_device * pdev)
+static int __devinit f71882fg_probe(struct platform_device *pdev)
 {
 	struct f71882fg_data *data;
-	int err, i;
+	struct f71882fg_sio_data *sio_data = pdev->dev.platform_data;
+	int err;
 	u8 start_reg;
 
-	if (!(data = kzalloc(sizeof(struct f71882fg_data), GFP_KERNEL)))
+	data = kzalloc(sizeof(struct f71882fg_data), GFP_KERNEL);
+	if (!data)
 		return -ENOMEM;
 
 	data->addr = platform_get_resource(pdev, IORESOURCE_IO, 0)->start;
+	data->type = sio_data->type;
 	mutex_init(&data->update_lock);
 	platform_set_drvdata(pdev, data);
 
+	start_reg = f71882fg_read8(data, F71882FG_REG_START);
+	if (!(start_reg & 0x03)) {
+		dev_warn(&pdev->dev, "Hardware monitoring not activated\n");
+		err = -ENODEV;
+		goto exit_free;
+	}
+
+	/* If it is a 71862 and the fan / pwm part is enabled sanity check
+	   the pwm settings */
+	if (data->type == f71862fg && (start_reg & 0x02)) {
+		u8 reg = f71882fg_read8(data, F71882FG_REG_PWM_ENABLE);
+		if ((reg & 0x15) != 0x15) {
+			dev_err(&pdev->dev,
+				"Invalid (reserved) pwm settings: 0x%02x\n",
+				(unsigned int)reg);
+			err = -ENODEV;
+			goto exit_free;
+		}
+	}
+
 	/* Register sysfs interface files */
-	for (i = 0; i < ARRAY_SIZE(f71882fg_dev_attr); i++) {
-		err = device_create_file(&pdev->dev, &f71882fg_dev_attr[i]);
+	err = device_create_file(&pdev->dev, &dev_attr_name);
+	if (err)
+		goto exit_unregister_sysfs;
+
+	if (start_reg & 0x01) {
+		err = f71882fg_create_sysfs_files(pdev, f718x2fg_in_temp_attr,
+					ARRAY_SIZE(f718x2fg_in_temp_attr));
 		if (err)
 			goto exit_unregister_sysfs;
-	}
 
-	start_reg = f71882fg_read8(data, F71882FG_REG_START);
-	if (start_reg & 0x01) {
-		for (i = 0; i < ARRAY_SIZE(f71882fg_in_temp_attr); i++) {
-			err = device_create_file(&pdev->dev,
-					&f71882fg_in_temp_attr[i].dev_attr);
+		if (data->type == f71882fg) {
+			err = f71882fg_create_sysfs_files(pdev,
+					f71882fg_in_temp_attr,
+					ARRAY_SIZE(f71882fg_in_temp_attr));
 			if (err)
 				goto exit_unregister_sysfs;
 		}
 	}
 
 	if (start_reg & 0x02) {
-		for (i = 0; i < ARRAY_SIZE(f71882fg_fan_attr); i++) {
-			err = device_create_file(&pdev->dev,
-					&f71882fg_fan_attr[i].dev_attr);
-			if (err)
-				goto exit_unregister_sysfs;
+		err = f71882fg_create_sysfs_files(pdev, f718x2fg_fan_attr,
+					ARRAY_SIZE(f718x2fg_fan_attr));
+		if (err)
+			goto exit_unregister_sysfs;
+
+		if (data->type == f71862fg) {
+			err = f71882fg_create_sysfs_files(pdev,
+					f71862fg_fan_attr,
+					ARRAY_SIZE(f71862fg_fan_attr));
+		} else {
+			err = f71882fg_create_sysfs_files(pdev,
+					f71882fg_fan_attr,
+					ARRAY_SIZE(f71882fg_fan_attr));
 		}
+		if (err)
+			goto exit_unregister_sysfs;
 	}
 
 	data->hwmon_dev = hwmon_device_register(&pdev->dev);
 	if (IS_ERR(data->hwmon_dev)) {
 		err = PTR_ERR(data->hwmon_dev);
+		data->hwmon_dev = NULL;
 		goto exit_unregister_sysfs;
 	}
 
 	return 0;
 
 exit_unregister_sysfs:
-	for (i = 0; i < ARRAY_SIZE(f71882fg_dev_attr); i++)
-		device_remove_file(&pdev->dev, &f71882fg_dev_attr[i]);
-
-	for (i = 0; i < ARRAY_SIZE(f71882fg_in_temp_attr); i++)
-		device_remove_file(&pdev->dev,
-					&f71882fg_in_temp_attr[i].dev_attr);
-
-	for (i = 0; i < ARRAY_SIZE(f71882fg_fan_attr); i++)
-		device_remove_file(&pdev->dev, &f71882fg_fan_attr[i].dev_attr);
-
+	f71882fg_remove(pdev); /* Will unregister the sysfs files for us */
+	return err; /* f71882fg_remove() also frees our data */
+exit_free:
 	kfree(data);
-
 	return err;
 }
 
-static int __devexit f71882fg_remove(struct platform_device *pdev)
+static int f71882fg_remove(struct platform_device *pdev)
 {
 	int i;
 	struct f71882fg_data *data = platform_get_drvdata(pdev);
 
 	platform_set_drvdata(pdev, NULL);
-	hwmon_device_unregister(data->hwmon_dev);
+	if (data->hwmon_dev)
+		hwmon_device_unregister(data->hwmon_dev);
 
-	for (i = 0; i < ARRAY_SIZE(f71882fg_dev_attr); i++)
-		device_remove_file(&pdev->dev, &f71882fg_dev_attr[i]);
+	device_remove_file(&pdev->dev, &dev_attr_name);
+
+	for (i = 0; i < ARRAY_SIZE(f718x2fg_in_temp_attr); i++)
+		device_remove_file(&pdev->dev,
+					&f718x2fg_in_temp_attr[i].dev_attr);
 
 	for (i = 0; i < ARRAY_SIZE(f71882fg_in_temp_attr); i++)
 		device_remove_file(&pdev->dev,
 					&f71882fg_in_temp_attr[i].dev_attr);
 
+	for (i = 0; i < ARRAY_SIZE(f718x2fg_fan_attr); i++)
+		device_remove_file(&pdev->dev, &f718x2fg_fan_attr[i].dev_attr);
+
+	for (i = 0; i < ARRAY_SIZE(f71862fg_fan_attr); i++)
+		device_remove_file(&pdev->dev, &f71862fg_fan_attr[i].dev_attr);
+
 	for (i = 0; i < ARRAY_SIZE(f71882fg_fan_attr); i++)
 		device_remove_file(&pdev->dev, &f71882fg_fan_attr[i].dev_attr);
 
@@ -826,12 +1616,11 @@ static int __devexit f71882fg_remove(struct platform_device *pdev)
 	return 0;
 }
 
-static int __init f71882fg_find(int sioaddr, unsigned short *address)
+static int __init f71882fg_find(int sioaddr, unsigned short *address,
+	struct f71882fg_sio_data *sio_data)
 {
 	int err = -ENODEV;
 	u16 devid;
-	u8 start_reg;
-	struct f71882fg_data data;
 
 	superio_enter(sioaddr);
 
@@ -842,7 +1631,14 @@ static int __init f71882fg_find(int sioaddr, unsigned short *address)
 	}
 
 	devid = force_id ? force_id : superio_inw(sioaddr, SIO_REG_DEVID);
-	if (devid != SIO_F71882_ID) {
+	switch (devid) {
+	case SIO_F71862_ID:
+		sio_data->type = f71862fg;
+		break;
+	case SIO_F71882_ID:
+		sio_data->type = f71882fg;
+		break;
+	default:
 		printk(KERN_INFO DRVNAME ": Unsupported Fintek device\n");
 		goto exit;
 	}
@@ -861,24 +1657,17 @@ static int __init f71882fg_find(int sioaddr, unsigned short *address)
 	}
 	*address &= ~(REGION_LENGTH - 1);	/* Ignore 3 LSB */
 
-	data.addr = *address;
-	start_reg = f71882fg_read8(&data, F71882FG_REG_START);
-	if (!(start_reg & 0x03)) {
-		printk(KERN_WARNING DRVNAME
-			": Hardware monitoring not activated\n");
-		goto exit;
-	}
-
 	err = 0;
-	printk(KERN_INFO DRVNAME ": Found F71882FG chip at %#x, revision %d\n",
-		(unsigned int)*address,
+	printk(KERN_INFO DRVNAME ": Found %s chip at %#x, revision %d\n",
+		f71882fg_names[sio_data->type],	(unsigned int)*address,
 		(int)superio_inb(sioaddr, SIO_REG_DEVREV));
 exit:
 	superio_exit(sioaddr);
 	return err;
 }
 
-static int __init f71882fg_device_add(unsigned short address)
+static int __init f71882fg_device_add(unsigned short address,
+	const struct f71882fg_sio_data *sio_data)
 {
 	struct resource res = {
 		.start	= address,
@@ -898,6 +1687,13 @@ static int __init f71882fg_device_add(unsigned short address)
 		goto exit_device_put;
 	}
 
+	err = platform_device_add_data(f71882fg_pdev, sio_data,
+				       sizeof(struct f71882fg_sio_data));
+	if (err) {
+		printk(KERN_ERR DRVNAME ": Platform data allocation failed\n");
+		goto exit_device_put;
+	}
+
 	err = platform_device_add(f71882fg_pdev);
 	if (err) {
 		printk(KERN_ERR DRVNAME ": Device addition failed\n");
@@ -916,14 +1712,20 @@ static int __init f71882fg_init(void)
 {
 	int err = -ENODEV;
 	unsigned short address;
+	struct f71882fg_sio_data sio_data;
+
+	memset(&sio_data, 0, sizeof(sio_data));
 
-	if (f71882fg_find(0x2e, &address) && f71882fg_find(0x4e, &address))
+	if (f71882fg_find(0x2e, &address, &sio_data) &&
+	    f71882fg_find(0x4e, &address, &sio_data))
 		goto exit;
 
-	if ((err = platform_driver_register(&f71882fg_driver)))
+	err = platform_driver_register(&f71882fg_driver);
+	if (err)
 		goto exit;
 
-	if ((err = f71882fg_device_add(address)))
+	err = f71882fg_device_add(address, &sio_data);
+	if (err)
 		goto exit_driver;
 
 	return 0;
@@ -941,7 +1743,7 @@ static void __exit f71882fg_exit(void)
 }
 
 MODULE_DESCRIPTION("F71882FG Hardware Monitoring Driver");
-MODULE_AUTHOR("Hans Edgington (hans@edgington.nl)");
+MODULE_AUTHOR("Hans Edgington, Hans de Goede (hdegoede@redhat.com)");
 MODULE_LICENSE("GPL");
 
 module_init(f71882fg_init);
diff --git a/drivers/hwmon/fschmd.c b/drivers/hwmon/fschmd.c
index 967170368933..8bb1a44a1de5 100644
--- a/drivers/hwmon/fschmd.c
+++ b/drivers/hwmon/fschmd.c
@@ -1,6 +1,6 @@
 /* fschmd.c
  *
- * Copyright (C) 2007 Hans de Goede <j.w.r.degoede@hhs.nl>
+ * Copyright (C) 2007,2008 Hans de Goede <hdegoede@redhat.com>
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -42,11 +42,20 @@
 #include <linux/mutex.h>
 #include <linux/sysfs.h>
 #include <linux/dmi.h>
+#include <linux/fs.h>
+#include <linux/watchdog.h>
+#include <linux/miscdevice.h>
+#include <linux/uaccess.h>
+#include <linux/kref.h>
 
 /* Addresses to scan */
 static const unsigned short normal_i2c[] = { 0x73, I2C_CLIENT_END };
 
 /* Insmod parameters */
+static int nowayout = WATCHDOG_NOWAYOUT;
+module_param(nowayout, int, 0);
+MODULE_PARM_DESC(nowayout, "Watchdog cannot be stopped once started (default="
+	__MODULE_STRING(WATCHDOG_NOWAYOUT) ")");
 I2C_CLIENT_INSMOD_5(fscpos, fscher, fscscy, fschrc, fschmd);
 
 /*
@@ -63,13 +72,20 @@ I2C_CLIENT_INSMOD_5(fscpos, fscher, fscscy, fschrc, fschmd);
 #define FSCHMD_REG_EVENT_STATE		0x04
 #define FSCHMD_REG_CONTROL		0x05
 
-#define FSCHMD_CONTROL_ALERT_LED_MASK	0x01
+#define FSCHMD_CONTROL_ALERT_LED	0x01
 
-/* watchdog (support to be implemented) */
+/* watchdog */
 #define FSCHMD_REG_WDOG_PRESET		0x28
 #define FSCHMD_REG_WDOG_STATE		0x23
 #define FSCHMD_REG_WDOG_CONTROL		0x21
 
+#define FSCHMD_WDOG_CONTROL_TRIGGER	0x10
+#define FSCHMD_WDOG_CONTROL_STARTED	0x10 /* the same as trigger */
+#define FSCHMD_WDOG_CONTROL_STOP	0x20
+#define FSCHMD_WDOG_CONTROL_RESOLUTION	0x40
+
+#define FSCHMD_WDOG_STATE_CARDRESET	0x02
+
 /* voltages, weird order is to keep the same order as the old drivers */
 static const u8 FSCHMD_REG_VOLT[3] = { 0x45, 0x42, 0x48 };
 
@@ -115,8 +131,8 @@ static const u8 FSCHMD_REG_FAN_RIPPLE[5][6] = {
 static const int FSCHMD_NO_FAN_SENSORS[5] = { 3, 3, 6, 4, 5 };
 
 /* Fan status register bitmasks */
-#define FSCHMD_FAN_ALARM_MASK		0x04 /* called fault by FSC! */
-#define FSCHMD_FAN_NOT_PRESENT_MASK	0x08 /* not documented */
+#define FSCHMD_FAN_ALARM	0x04 /* called fault by FSC! */
+#define FSCHMD_FAN_NOT_PRESENT	0x08 /* not documented */
 
 
 /* actual temperature registers */
@@ -158,14 +174,11 @@ static const u8 FSCHER_REG_TEMP_AUTOP2[] =	{ 0x75, 0x85, 0x95 }; */
 static const int FSCHMD_NO_TEMP_SENSORS[5] = { 3, 3, 4, 3, 5 };
 
 /* temp status register bitmasks */
-#define FSCHMD_TEMP_WORKING_MASK	0x01
-#define FSCHMD_TEMP_ALERT_MASK		0x02
+#define FSCHMD_TEMP_WORKING	0x01
+#define FSCHMD_TEMP_ALERT	0x02
 /* there only really is an alarm if the sensor is working and alert == 1 */
 #define FSCHMD_TEMP_ALARM_MASK \
-	(FSCHMD_TEMP_WORKING_MASK | FSCHMD_TEMP_ALERT_MASK)
-
-/* our driver name */
-#define FSCHMD_NAME "fschmd"
+	(FSCHMD_TEMP_WORKING | FSCHMD_TEMP_ALERT)
 
 /*
  * Functions declarations
@@ -195,7 +208,7 @@ MODULE_DEVICE_TABLE(i2c, fschmd_id);
 static struct i2c_driver fschmd_driver = {
 	.class		= I2C_CLASS_HWMON,
 	.driver = {
-		.name	= FSCHMD_NAME,
+		.name	= "fschmd",
 	},
 	.probe		= fschmd_probe,
 	.remove		= fschmd_remove,
@@ -209,14 +222,26 @@ static struct i2c_driver fschmd_driver = {
  */
 
 struct fschmd_data {
+	struct i2c_client *client;
 	struct device *hwmon_dev;
 	struct mutex update_lock;
+	struct mutex watchdog_lock;
+	struct list_head list; /* member of the watchdog_data_list */
+	struct kref kref;
+	struct miscdevice watchdog_miscdev;
 	int kind;
+	unsigned long watchdog_is_open;
+	char watchdog_expect_close;
+	char watchdog_name[10]; /* must be unique to avoid sysfs conflict */
 	char valid; /* zero until following fields are valid */
 	unsigned long last_updated; /* in jiffies */
 
 	/* register values */
+	u8 revision;            /* chip revision */
 	u8 global_control;	/* global control register */
+	u8 watchdog_control;    /* watchdog control register */
+	u8 watchdog_state;      /* watchdog status register */
+	u8 watchdog_preset;     /* watchdog counter preset on trigger val */
 	u8 volt[3];		/* 12, 5, battery voltage */
 	u8 temp_act[5];		/* temperature */
 	u8 temp_status[5];	/* status of sensor */
@@ -228,11 +253,28 @@ struct fschmd_data {
 };
 
 /* Global variables to hold information read from special DMI tables, which are
-   available on FSC machines with an fscher or later chip. */
+   available on FSC machines with an fscher or later chip. There is no need to
+   protect these with a lock as they are only modified from our attach function
+   which always gets called with the i2c-core lock held and never accessed
+   before the attach function is done with them. */
 static int dmi_mult[3] = { 490, 200, 100 };
 static int dmi_offset[3] = { 0, 0, 0 };
 static int dmi_vref = -1;
 
+/* Somewhat ugly :( global data pointer list with all fschmd devices, so that
+   we can find our device data as when using misc_register there is no other
+   method to get to ones device data from the open fop. */
+static LIST_HEAD(watchdog_data_list);
+/* Note this lock not only protect list access, but also data.kref access */
+static DEFINE_MUTEX(watchdog_data_mutex);
+
+/* Release our data struct when we're detached from the i2c client *and* all
+   references to our watchdog device are released */
+static void fschmd_release_resources(struct kref *ref)
+{
+	struct fschmd_data *data = container_of(ref, struct fschmd_data, kref);
+	kfree(data);
+}
 
 /*
  * Sysfs attr show / store functions
@@ -300,7 +342,7 @@ static ssize_t show_temp_fault(struct device *dev,
 	struct fschmd_data *data = fschmd_update_device(dev);
 
 	/* bit 0 set means sensor working ok, so no fault! */
-	if (data->temp_status[index] & FSCHMD_TEMP_WORKING_MASK)
+	if (data->temp_status[index] & FSCHMD_TEMP_WORKING)
 		return sprintf(buf, "0\n");
 	else
 		return sprintf(buf, "1\n");
@@ -385,7 +427,7 @@ static ssize_t show_fan_alarm(struct device *dev,
 	int index = to_sensor_dev_attr(devattr)->index;
 	struct fschmd_data *data = fschmd_update_device(dev);
 
-	if (data->fan_status[index] & FSCHMD_FAN_ALARM_MASK)
+	if (data->fan_status[index] & FSCHMD_FAN_ALARM)
 		return sprintf(buf, "1\n");
 	else
 		return sprintf(buf, "0\n");
@@ -397,7 +439,7 @@ static ssize_t show_fan_fault(struct device *dev,
 	int index = to_sensor_dev_attr(devattr)->index;
 	struct fschmd_data *data = fschmd_update_device(dev);
 
-	if (data->fan_status[index] & FSCHMD_FAN_NOT_PRESENT_MASK)
+	if (data->fan_status[index] & FSCHMD_FAN_NOT_PRESENT)
 		return sprintf(buf, "1\n");
 	else
 		return sprintf(buf, "0\n");
@@ -449,7 +491,7 @@ static ssize_t show_alert_led(struct device *dev,
 {
 	struct fschmd_data *data = fschmd_update_device(dev);
 
-	if (data->global_control & FSCHMD_CONTROL_ALERT_LED_MASK)
+	if (data->global_control & FSCHMD_CONTROL_ALERT_LED)
 		return sprintf(buf, "1\n");
 	else
 		return sprintf(buf, "0\n");
@@ -467,9 +509,9 @@ static ssize_t store_alert_led(struct device *dev,
 	reg = i2c_smbus_read_byte_data(to_i2c_client(dev), FSCHMD_REG_CONTROL);
 
 	if (v)
-		reg |= FSCHMD_CONTROL_ALERT_LED_MASK;
+		reg |= FSCHMD_CONTROL_ALERT_LED;
 	else
-		reg &= ~FSCHMD_CONTROL_ALERT_LED_MASK;
+		reg &= ~FSCHMD_CONTROL_ALERT_LED;
 
 	i2c_smbus_write_byte_data(to_i2c_client(dev), FSCHMD_REG_CONTROL, reg);
 
@@ -551,7 +593,265 @@ static struct sensor_device_attribute fschmd_fan_attr[] = {
 
 
 /*
- * Real code
+ * Watchdog routines
+ */
+
+static int watchdog_set_timeout(struct fschmd_data *data, int timeout)
+{
+	int ret, resolution;
+	int kind = data->kind + 1; /* 0-x array index -> 1-x module param */
+
+	/* 2 second or 60 second resolution? */
+	if (timeout <= 510 || kind == fscpos || kind == fscscy)
+		resolution = 2;
+	else
+		resolution = 60;
+
+	if (timeout < resolution || timeout > (resolution * 255))
+		return -EINVAL;
+
+	mutex_lock(&data->watchdog_lock);
+	if (!data->client) {
+		ret = -ENODEV;
+		goto leave;
+	}
+
+	if (resolution == 2)
+		data->watchdog_control &= ~FSCHMD_WDOG_CONTROL_RESOLUTION;
+	else
+		data->watchdog_control |= FSCHMD_WDOG_CONTROL_RESOLUTION;
+
+	data->watchdog_preset = DIV_ROUND_UP(timeout, resolution);
+
+	/* Write new timeout value */
+	i2c_smbus_write_byte_data(data->client, FSCHMD_REG_WDOG_PRESET,
+		data->watchdog_preset);
+	/* Write new control register, do not trigger! */
+	i2c_smbus_write_byte_data(data->client, FSCHMD_REG_WDOG_CONTROL,
+		data->watchdog_control & ~FSCHMD_WDOG_CONTROL_TRIGGER);
+
+	ret = data->watchdog_preset * resolution;
+
+leave:
+	mutex_unlock(&data->watchdog_lock);
+	return ret;
+}
+
+static int watchdog_get_timeout(struct fschmd_data *data)
+{
+	int timeout;
+
+	mutex_lock(&data->watchdog_lock);
+	if (data->watchdog_control & FSCHMD_WDOG_CONTROL_RESOLUTION)
+		timeout = data->watchdog_preset * 60;
+	else
+		timeout = data->watchdog_preset * 2;
+	mutex_unlock(&data->watchdog_lock);
+
+	return timeout;
+}
+
+static int watchdog_trigger(struct fschmd_data *data)
+{
+	int ret = 0;
+
+	mutex_lock(&data->watchdog_lock);
+	if (!data->client) {
+		ret = -ENODEV;
+		goto leave;
+	}
+
+	data->watchdog_control |= FSCHMD_WDOG_CONTROL_TRIGGER;
+	i2c_smbus_write_byte_data(data->client, FSCHMD_REG_WDOG_CONTROL,
+					data->watchdog_control);
+leave:
+	mutex_unlock(&data->watchdog_lock);
+	return ret;
+}
+
+static int watchdog_stop(struct fschmd_data *data)
+{
+	int ret = 0;
+
+	mutex_lock(&data->watchdog_lock);
+	if (!data->client) {
+		ret = -ENODEV;
+		goto leave;
+	}
+
+	data->watchdog_control &= ~FSCHMD_WDOG_CONTROL_STARTED;
+	/* Don't store the stop flag in our watchdog control register copy, as
+	   its a write only bit (read always returns 0) */
+	i2c_smbus_write_byte_data(data->client, FSCHMD_REG_WDOG_CONTROL,
+		data->watchdog_control | FSCHMD_WDOG_CONTROL_STOP);
+leave:
+	mutex_unlock(&data->watchdog_lock);
+	return ret;
+}
+
+static int watchdog_open(struct inode *inode, struct file *filp)
+{
+	struct fschmd_data *pos, *data = NULL;
+
+	/* We get called from drivers/char/misc.c with misc_mtx hold, and we
+	   call misc_register() from fschmd_probe() with watchdog_data_mutex
+	   hold, as misc_register() takes the misc_mtx lock, this is a possible
+	   deadlock, so we use mutex_trylock here. */
+	if (!mutex_trylock(&watchdog_data_mutex))
+		return -ERESTARTSYS;
+	list_for_each_entry(pos, &watchdog_data_list, list) {
+		if (pos->watchdog_miscdev.minor == iminor(inode)) {
+			data = pos;
+			break;
+		}
+	}
+	/* Note we can never not have found data, so we don't check for this */
+	kref_get(&data->kref);
+	mutex_unlock(&watchdog_data_mutex);
+
+	if (test_and_set_bit(0, &data->watchdog_is_open))
+		return -EBUSY;
+
+	/* Start the watchdog */
+	watchdog_trigger(data);
+	filp->private_data = data;
+
+	return nonseekable_open(inode, filp);
+}
+
+static int watchdog_release(struct inode *inode, struct file *filp)
+{
+	struct fschmd_data *data = filp->private_data;
+
+	if (data->watchdog_expect_close) {
+		watchdog_stop(data);
+		data->watchdog_expect_close = 0;
+	} else {
+		watchdog_trigger(data);
+		dev_crit(&data->client->dev,
+			"unexpected close, not stopping watchdog!\n");
+	}
+
+	clear_bit(0, &data->watchdog_is_open);
+
+	mutex_lock(&watchdog_data_mutex);
+	kref_put(&data->kref, fschmd_release_resources);
+	mutex_unlock(&watchdog_data_mutex);
+
+	return 0;
+}
+
+static ssize_t watchdog_write(struct file *filp, const char __user *buf,
+	size_t count, loff_t *offset)
+{
+	size_t ret;
+	struct fschmd_data *data = filp->private_data;
+
+	if (count) {
+		if (!nowayout) {
+			size_t i;
+
+			/* Clear it in case it was set with a previous write */
+			data->watchdog_expect_close = 0;
+
+			for (i = 0; i != count; i++) {
+				char c;
+				if (get_user(c, buf + i))
+					return -EFAULT;
+				if (c == 'V')
+					data->watchdog_expect_close = 1;
+			}
+		}
+		ret = watchdog_trigger(data);
+		if (ret < 0)
+			return ret;
+	}
+	return count;
+}
+
+static int watchdog_ioctl(struct inode *inode, struct file *filp,
+	unsigned int cmd, unsigned long arg)
+{
+	static struct watchdog_info ident = {
+		.options = WDIOF_KEEPALIVEPING | WDIOF_SETTIMEOUT |
+				WDIOF_CARDRESET,
+		.identity = "FSC watchdog"
+	};
+	int i, ret = 0;
+	struct fschmd_data *data = filp->private_data;
+
+	switch (cmd) {
+	case WDIOC_GETSUPPORT:
+		ident.firmware_version = data->revision;
+		if (!nowayout)
+			ident.options |= WDIOF_MAGICCLOSE;
+		if (copy_to_user((void __user *)arg, &ident, sizeof(ident)))
+			ret = -EFAULT;
+		break;
+
+	case WDIOC_GETSTATUS:
+		ret = put_user(0, (int __user *)arg);
+		break;
+
+	case WDIOC_GETBOOTSTATUS:
+		if (data->watchdog_state & FSCHMD_WDOG_STATE_CARDRESET)
+			ret = put_user(WDIOF_CARDRESET, (int __user *)arg);
+		else
+			ret = put_user(0, (int __user *)arg);
+		break;
+
+	case WDIOC_KEEPALIVE:
+		ret = watchdog_trigger(data);
+		break;
+
+	case WDIOC_GETTIMEOUT:
+		i = watchdog_get_timeout(data);
+		ret = put_user(i, (int __user *)arg);
+		break;
+
+	case WDIOC_SETTIMEOUT:
+		if (get_user(i, (int __user *)arg)) {
+			ret = -EFAULT;
+			break;
+		}
+		ret = watchdog_set_timeout(data, i);
+		if (ret > 0)
+			ret = put_user(ret, (int __user *)arg);
+		break;
+
+	case WDIOC_SETOPTIONS:
+		if (get_user(i, (int __user *)arg)) {
+			ret = -EFAULT;
+			break;
+		}
+
+		if (i & WDIOS_DISABLECARD)
+			ret = watchdog_stop(data);
+		else if (i & WDIOS_ENABLECARD)
+			ret = watchdog_trigger(data);
+		else
+			ret = -EINVAL;
+
+		break;
+	default:
+		ret = -ENOTTY;
+	}
+
+	return ret;
+}
+
+static struct file_operations watchdog_fops = {
+	.owner = THIS_MODULE,
+	.llseek = no_llseek,
+	.open = watchdog_open,
+	.release = watchdog_release,
+	.write = watchdog_write,
+	.ioctl = watchdog_ioctl,
+};
+
+
+/*
+ * Detect, register, unregister and update device functions
  */
 
 /* DMI decode routine to read voltage scaling factors from special DMI tables,
@@ -661,9 +961,9 @@ static int fschmd_probe(struct i2c_client *client,
 			const struct i2c_device_id *id)
 {
 	struct fschmd_data *data;
-	u8 revision;
 	const char * const names[5] = { "Poseidon", "Hermes", "Scylla",
 					"Heracles", "Heimdall" };
+	const int watchdog_minors[] = { WATCHDOG_MINOR, 212, 213, 214, 215 };
 	int i, err;
 	enum chips kind = id->driver_data;
 
@@ -673,6 +973,13 @@ static int fschmd_probe(struct i2c_client *client,
 
 	i2c_set_clientdata(client, data);
 	mutex_init(&data->update_lock);
+	mutex_init(&data->watchdog_lock);
+	INIT_LIST_HEAD(&data->list);
+	kref_init(&data->kref);
+	/* Store client pointer in our data struct for watchdog usage
+	   (where the client is found through a data ptr instead of the
+	   otherway around) */
+	data->client = client;
 
 	if (kind == fscpos) {
 		/* The Poseidon has hardwired temp limits, fill these
@@ -683,16 +990,27 @@ static int fschmd_probe(struct i2c_client *client,
 	}
 
 	/* Read the special DMI table for fscher and newer chips */
-	if (kind == fscher || kind >= fschrc) {
+	if ((kind == fscher || kind >= fschrc) && dmi_vref == -1) {
 		dmi_walk(fschmd_dmi_decode);
 		if (dmi_vref == -1) {
-			printk(KERN_WARNING FSCHMD_NAME
-				": Couldn't get voltage scaling factors from "
+			dev_warn(&client->dev,
+				"Couldn't get voltage scaling factors from "
 				"BIOS DMI table, using builtin defaults\n");
 			dmi_vref = 33;
 		}
 	}
 
+	/* Read in some never changing registers */
+	data->revision = i2c_smbus_read_byte_data(client, FSCHMD_REG_REVISION);
+	data->global_control = i2c_smbus_read_byte_data(client,
+					FSCHMD_REG_CONTROL);
+	data->watchdog_control = i2c_smbus_read_byte_data(client,
+					FSCHMD_REG_WDOG_CONTROL);
+	data->watchdog_state = i2c_smbus_read_byte_data(client,
+					FSCHMD_REG_WDOG_STATE);
+	data->watchdog_preset = i2c_smbus_read_byte_data(client,
+					FSCHMD_REG_WDOG_PRESET);
+
 	/* i2c kind goes from 1-5, we want from 0-4 to address arrays */
 	data->kind = kind - 1;
 
@@ -735,9 +1053,43 @@ static int fschmd_probe(struct i2c_client *client,
 		goto exit_detach;
 	}
 
-	revision = i2c_smbus_read_byte_data(client, FSCHMD_REG_REVISION);
-	printk(KERN_INFO FSCHMD_NAME ": Detected FSC %s chip, revision: %d\n",
-		names[data->kind], (int) revision);
+	/* We take the data_mutex lock early so that watchdog_open() cannot
+	   run when misc_register() has completed, but we've not yet added
+	   our data to the watchdog_data_list (and set the default timeout) */
+	mutex_lock(&watchdog_data_mutex);
+	for (i = 0; i < ARRAY_SIZE(watchdog_minors); i++) {
+		/* Register our watchdog part */
+		snprintf(data->watchdog_name, sizeof(data->watchdog_name),
+			"watchdog%c", (i == 0) ? '\0' : ('0' + i));
+		data->watchdog_miscdev.name = data->watchdog_name;
+		data->watchdog_miscdev.fops = &watchdog_fops;
+		data->watchdog_miscdev.minor = watchdog_minors[i];
+		err = misc_register(&data->watchdog_miscdev);
+		if (err == -EBUSY)
+			continue;
+		if (err) {
+			data->watchdog_miscdev.minor = 0;
+			dev_err(&client->dev,
+				"Registering watchdog chardev: %d\n", err);
+			break;
+		}
+
+		list_add(&data->list, &watchdog_data_list);
+		watchdog_set_timeout(data, 60);
+		dev_info(&client->dev,
+			"Registered watchdog chardev major 10, minor: %d\n",
+			watchdog_minors[i]);
+		break;
+	}
+	if (i == ARRAY_SIZE(watchdog_minors)) {
+		data->watchdog_miscdev.minor = 0;
+		dev_warn(&client->dev, "Couldn't register watchdog chardev "
+			"(due to no free minor)\n");
+	}
+	mutex_unlock(&watchdog_data_mutex);
+
+	dev_info(&client->dev, "Detected FSC %s chip, revision: %d\n",
+		names[data->kind], (int) data->revision);
 
 	return 0;
 
@@ -751,6 +1103,24 @@ static int fschmd_remove(struct i2c_client *client)
 	struct fschmd_data *data = i2c_get_clientdata(client);
 	int i;
 
+	/* Unregister the watchdog (if registered) */
+	if (data->watchdog_miscdev.minor) {
+		misc_deregister(&data->watchdog_miscdev);
+		if (data->watchdog_is_open) {
+			dev_warn(&client->dev,
+				"i2c client detached with watchdog open! "
+				"Stopping watchdog.\n");
+			watchdog_stop(data);
+		}
+		mutex_lock(&watchdog_data_mutex);
+		list_del(&data->list);
+		mutex_unlock(&watchdog_data_mutex);
+		/* Tell the watchdog code the client is gone */
+		mutex_lock(&data->watchdog_lock);
+		data->client = NULL;
+		mutex_unlock(&data->watchdog_lock);
+	}
+
 	/* Check if registered in case we're called from fschmd_detect
 	   to cleanup after an error */
 	if (data->hwmon_dev)
@@ -765,7 +1135,10 @@ static int fschmd_remove(struct i2c_client *client)
 		device_remove_file(&client->dev,
 					&fschmd_fan_attr[i].dev_attr);
 
-	kfree(data);
+	mutex_lock(&watchdog_data_mutex);
+	kref_put(&data->kref, fschmd_release_resources);
+	mutex_unlock(&watchdog_data_mutex);
+
 	return 0;
 }
 
@@ -798,7 +1171,7 @@ static struct fschmd_data *fschmd_update_device(struct device *dev)
 					data->temp_act[i] < data->temp_max[i])
 				i2c_smbus_write_byte_data(client,
 					FSCHMD_REG_TEMP_STATE[data->kind][i],
-					FSCHMD_TEMP_ALERT_MASK);
+					FSCHMD_TEMP_ALERT);
 		}
 
 		for (i = 0; i < FSCHMD_NO_FAN_SENSORS[data->kind]; i++) {
@@ -816,28 +1189,17 @@ static struct fschmd_data *fschmd_update_device(struct device *dev)
 					FSCHMD_REG_FAN_MIN[data->kind][i]);
 
 			/* reset fan status if speed is back to > 0 */
-			if ((data->fan_status[i] & FSCHMD_FAN_ALARM_MASK) &&
+			if ((data->fan_status[i] & FSCHMD_FAN_ALARM) &&
 					data->fan_act[i])
 				i2c_smbus_write_byte_data(client,
 					FSCHMD_REG_FAN_STATE[data->kind][i],
-					FSCHMD_FAN_ALARM_MASK);
+					FSCHMD_FAN_ALARM);
 		}
 
 		for (i = 0; i < 3; i++)
 			data->volt[i] = i2c_smbus_read_byte_data(client,
 						FSCHMD_REG_VOLT[i]);
 
-		data->global_control = i2c_smbus_read_byte_data(client,
-						FSCHMD_REG_CONTROL);
-
-		/* To be implemented in the future
-		data->watchdog[0] = i2c_smbus_read_byte_data(client,
-						FSCHMD_REG_WDOG_PRESET);
-		data->watchdog[1] = i2c_smbus_read_byte_data(client,
-						FSCHMD_REG_WDOG_STATE);
-		data->watchdog[2] = i2c_smbus_read_byte_data(client,
-						FSCHMD_REG_WDOG_CONTROL); */
-
 		data->last_updated = jiffies;
 		data->valid = 1;
 	}
@@ -857,7 +1219,7 @@ static void __exit fschmd_exit(void)
 	i2c_del_driver(&fschmd_driver);
 }
 
-MODULE_AUTHOR("Hans de Goede <j.w.r.degoede@hhs.nl>");
+MODULE_AUTHOR("Hans de Goede <hdegoede@redhat.com>");
 MODULE_DESCRIPTION("FSC Poseidon, Hermes, Scylla, Heracles and "
 			"Heimdall driver");
 MODULE_LICENSE("GPL");
diff --git a/drivers/hwmon/hwmon.c b/drivers/hwmon/hwmon.c
index 076a59cdabe9..e15c3e7b07e9 100644
--- a/drivers/hwmon/hwmon.c
+++ b/drivers/hwmon/hwmon.c
@@ -76,7 +76,7 @@ void hwmon_device_unregister(struct device *dev)
 {
 	int id;
 
-	if (likely(sscanf(dev->bus_id, HWMON_ID_FORMAT, &id) == 1)) {
+	if (likely(sscanf(dev_name(dev), HWMON_ID_FORMAT, &id) == 1)) {
 		device_unregister(dev);
 		spin_lock(&idr_lock);
 		idr_remove(&hwmon_idr, id);
diff --git a/drivers/hwmon/i5k_amb.c b/drivers/hwmon/i5k_amb.c
index 2ede9388096b..27d7f72a5f11 100644
--- a/drivers/hwmon/i5k_amb.c
+++ b/drivers/hwmon/i5k_amb.c
@@ -490,6 +490,13 @@ static unsigned long chipset_ids[] = {
 	0
 };
 
+static struct pci_device_id i5k_amb_ids[] __devinitdata = {
+	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_5000_ERR) },
+	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_5400_ERR) },
+	{ 0, }
+};
+MODULE_DEVICE_TABLE(pci, i5k_amb_ids);
+
 static int __devinit i5k_amb_probe(struct platform_device *pdev)
 {
 	struct i5k_amb_data *data;
diff --git a/drivers/hwmon/it87.c b/drivers/hwmon/it87.c
index b74c95735f95..0e0d692f0c9e 100644
--- a/drivers/hwmon/it87.c
+++ b/drivers/hwmon/it87.c
@@ -14,6 +14,7 @@
               IT8712F  Super I/O chip w/LPC interface
               IT8716F  Super I/O chip w/LPC interface
               IT8718F  Super I/O chip w/LPC interface
+              IT8720F  Super I/O chip w/LPC interface
               IT8726F  Super I/O chip w/LPC interface
               Sis950   A clone of the IT8705F
 
@@ -52,7 +53,7 @@
 
 #define DRVNAME "it87"
 
-enum chips { it87, it8712, it8716, it8718 };
+enum chips { it87, it8712, it8716, it8718, it8720 };
 
 static unsigned short force_id;
 module_param(force_id, ushort, 0);
@@ -64,7 +65,10 @@ static struct platform_device *pdev;
 #define	DEV	0x07	/* Register: Logical device select */
 #define	VAL	0x2f	/* The value to read/write */
 #define PME	0x04	/* The device with the fan registers in it */
-#define GPIO	0x07	/* The device with the IT8718F VID value in it */
+
+/* The device with the IT8718F/IT8720F VID value in it */
+#define GPIO	0x07
+
 #define	DEVID	0x20	/* Register: Device ID */
 #define	DEVREV	0x22	/* Register: Device Revision */
 
@@ -113,6 +117,7 @@ superio_exit(void)
 #define IT8705F_DEVID 0x8705
 #define IT8716F_DEVID 0x8716
 #define IT8718F_DEVID 0x8718
+#define IT8720F_DEVID 0x8720
 #define IT8726F_DEVID 0x8726
 #define IT87_ACT_REG  0x30
 #define IT87_BASE_REG 0x60
@@ -150,8 +155,8 @@ static int fix_pwm_polarity;
 #define IT87_REG_ALARM2        0x02
 #define IT87_REG_ALARM3        0x03
 
-/* The IT8718F has the VID value in a different register, in Super-I/O
-   configuration space. */
+/* The IT8718F and IT8720F have the VID value in a different register, in
+   Super-I/O configuration space. */
 #define IT87_REG_VID           0x0a
 /* The IT8705F and IT8712F earlier than revision 0x08 use register 0x0b
    for fan divisors. Later IT8712F revisions must use 16-bit tachometer
@@ -282,7 +287,8 @@ static inline int has_16bit_fans(const struct it87_data *data)
 	return (data->type == it87 && data->revision >= 0x03)
 	    || (data->type == it8712 && data->revision >= 0x08)
 	    || data->type == it8716
-	    || data->type == it8718;
+	    || data->type == it8718
+	    || data->type == it8720;
 }
 
 static int it87_probe(struct platform_device *pdev);
@@ -992,6 +998,9 @@ static int __init it87_find(unsigned short *address,
 	case IT8718F_DEVID:
 		sio_data->type = it8718;
 		break;
+	case IT8720F_DEVID:
+		sio_data->type = it8720;
+		break;
 	case 0xffff:	/* No device at all */
 		goto exit;
 	default:
@@ -1022,7 +1031,8 @@ static int __init it87_find(unsigned short *address,
 		int reg;
 
 		superio_select(GPIO);
-		if (chip_type == it8718)
+		if ((chip_type == it8718) ||
+		    (chip_type == it8720))
 			sio_data->vid_value = superio_inb(IT87_SIO_VID_REG);
 
 		reg = superio_inb(IT87_SIO_PINX2_REG);
@@ -1068,6 +1078,7 @@ static int __devinit it87_probe(struct platform_device *pdev)
 		"it8712",
 		"it8716",
 		"it8718",
+		"it8720",
 	};
 
 	res = platform_get_resource(pdev, IORESOURCE_IO, 0);
@@ -1226,7 +1237,7 @@ static int __devinit it87_probe(struct platform_device *pdev)
 	}
 
 	if (data->type == it8712 || data->type == it8716
-	 || data->type == it8718) {
+	 || data->type == it8718 || data->type == it8720) {
 		data->vrm = vid_which_vrm();
 		/* VID reading from Super-I/O config space if available */
 		data->vid = sio_data->vid_value;
@@ -1513,7 +1524,8 @@ static struct it87_data *it87_update_device(struct device *dev)
 
 		data->sensor = it87_read_value(data, IT87_REG_TEMP_ENABLE);
 		/* The 8705 does not have VID capability.
-		   The 8718 does not use IT87_REG_VID for the same purpose. */
+		   The 8718 and the 8720 don't use IT87_REG_VID for the
+		   same purpose. */
 		if (data->type == it8712 || data->type == it8716) {
 			data->vid = it87_read_value(data, IT87_REG_VID);
 			/* The older IT8712F revisions had only 5 VID pins,
@@ -1608,7 +1620,7 @@ static void __exit sm_it87_exit(void)
 
 MODULE_AUTHOR("Chris Gauthron, "
 	      "Jean Delvare <khali@linux-fr.org>");
-MODULE_DESCRIPTION("IT8705F/8712F/8716F/8718F/8726F, SiS950 driver");
+MODULE_DESCRIPTION("IT8705F/8712F/8716F/8718F/8720F/8726F, SiS950 driver");
 module_param(update_vbat, bool, 0);
 MODULE_PARM_DESC(update_vbat, "Update vbat if set else return powerup value");
 module_param(fix_pwm_polarity, bool, 0);
diff --git a/drivers/hwmon/k8temp.c b/drivers/hwmon/k8temp.c
index bd2bde0ef95e..3b903845e12c 100644
--- a/drivers/hwmon/k8temp.c
+++ b/drivers/hwmon/k8temp.c
@@ -34,6 +34,7 @@
 
 #define TEMP_FROM_REG(val)	(((((val) >> 16) & 0xff) - 49) * 1000)
 #define REG_TEMP	0xe4
+#define REG_CPUID	0xfc
 #define SEL_PLACE	0x40
 #define SEL_CORE	0x04
 
@@ -47,6 +48,7 @@ struct k8temp_data {
 	/* registers values */
 	u8 sensorsp;		/* sensor presence bits - SEL_CORE & SEL_PLACE */
 	u32 temp[2][2];		/* core, place */
+	u8 fam;
 };
 
 static struct k8temp_data *k8temp_update_device(struct device *dev)
@@ -155,6 +157,19 @@ static int __devinit k8temp_probe(struct pci_dev *pdev,
 		goto exit;
 	}
 
+	/* get real PCI based cpuid, prior revF of fam 0Fh, this reg is 0 */
+	pci_read_config_dword(pdev, REG_CPUID, &cpuid);
+
+	data->fam = (cpuid & 0x00000f00) >> 8;
+	data->fam += (cpuid & 0x0ff00000) >> 20;
+
+	switch (data->fam) {
+	case 0xf:
+		dev_warn(&pdev->dev, "Temperature readouts might be wrong"
+					" - check errata #141\n");
+		break;
+	}
+
 	pci_read_config_byte(pdev, REG_TEMP, &scfg);
 	scfg &= ~(SEL_PLACE | SEL_CORE);		/* Select sensor 0, core0 */
 	pci_write_config_byte(pdev, REG_TEMP, scfg);
diff --git a/drivers/hwmon/lm70.c b/drivers/hwmon/lm70.c
index d435f003292d..ae6204f33214 100644
--- a/drivers/hwmon/lm70.c
+++ b/drivers/hwmon/lm70.c
@@ -37,9 +37,13 @@
 
 #define DRVNAME		"lm70"
 
+#define LM70_CHIP_LM70		0	/* original NS LM70 */
+#define LM70_CHIP_TMP121	1	/* TI TMP121/TMP123 */
+
 struct lm70 {
 	struct device *hwmon_dev;
 	struct mutex lock;
+	unsigned int chip;
 };
 
 /* sysfs hook function */
@@ -47,7 +51,7 @@ static ssize_t lm70_sense_temp(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
 	struct spi_device *spi = to_spi_device(dev);
-	int status, val;
+	int status, val = 0;
 	u8 rxbuf[2];
 	s16 raw=0;
 	struct lm70 *p_lm70 = dev_get_drvdata(&spi->dev);
@@ -65,12 +69,12 @@ static ssize_t lm70_sense_temp(struct device *dev,
 		"spi_write_then_read failed with status %d\n", status);
 		goto out;
 	}
-	dev_dbg(dev, "rxbuf[1] : 0x%x rxbuf[0] : 0x%x\n", rxbuf[1], rxbuf[0]);
-
-	raw = (rxbuf[1] << 8) + rxbuf[0];
-	dev_dbg(dev, "raw=0x%x\n", raw);
+	raw = (rxbuf[0] << 8) + rxbuf[1];
+	dev_dbg(dev, "rxbuf[0] : 0x%02x rxbuf[1] : 0x%02x raw=0x%04x\n",
+		rxbuf[0], rxbuf[1], raw);
 
 	/*
+	 * LM70:
 	 * The "raw" temperature read into rxbuf[] is a 16-bit signed 2's
 	 * complement value. Only the MSB 11 bits (1 sign + 10 temperature
 	 * bits) are meaningful; the LSB 5 bits are to be discarded.
@@ -80,8 +84,21 @@ static ssize_t lm70_sense_temp(struct device *dev,
 	 * by 0.25. Also multiply by 1000 to represent in millidegrees
 	 * Celsius.
 	 * So it's equivalent to multiplying by 0.25 * 1000 = 250.
+	 *
+	 * TMP121/TMP123:
+	 * 13 bits of 2's complement data, discard LSB 3 bits,
+	 * resolution 0.0625 degrees celsius.
 	 */
-	val = ((int)raw/32) * 250;
+	switch (p_lm70->chip) {
+	case LM70_CHIP_LM70:
+		val = ((int)raw / 32) * 250;
+		break;
+
+	case LM70_CHIP_TMP121:
+		val = ((int)raw / 8) * 625 / 10;
+		break;
+	}
+
 	status = sprintf(buf, "%d\n", val); /* millidegrees Celsius */
 out:
 	mutex_unlock(&p_lm70->lock);
@@ -93,27 +110,39 @@ static DEVICE_ATTR(temp1_input, S_IRUGO, lm70_sense_temp, NULL);
 static ssize_t lm70_show_name(struct device *dev, struct device_attribute
 			      *devattr, char *buf)
 {
-	return sprintf(buf, "lm70\n");
+	struct lm70 *p_lm70 = dev_get_drvdata(dev);
+	int ret;
+
+	switch (p_lm70->chip) {
+	case LM70_CHIP_LM70:
+		ret = sprintf(buf, "lm70\n");
+		break;
+	case LM70_CHIP_TMP121:
+		ret = sprintf(buf, "tmp121\n");
+		break;
+	default:
+		ret = -EINVAL;
+	}
+	return ret;
 }
 
 static DEVICE_ATTR(name, S_IRUGO, lm70_show_name, NULL);
 
 /*----------------------------------------------------------------------*/
 
-static int __devinit lm70_probe(struct spi_device *spi)
+static int __devinit common_probe(struct spi_device *spi, int chip)
 {
 	struct lm70 *p_lm70;
 	int status;
 
-	/* signaling is SPI_MODE_0 on a 3-wire link (shared SI/SO) */
-	if ((spi->mode & (SPI_CPOL|SPI_CPHA)) || !(spi->mode & SPI_3WIRE))
-		return -EINVAL;
+	/* NOTE:  we assume 8-bit words, and convert to 16 bits manually */
 
 	p_lm70 = kzalloc(sizeof *p_lm70, GFP_KERNEL);
 	if (!p_lm70)
 		return -ENOMEM;
 
 	mutex_init(&p_lm70->lock);
+	p_lm70->chip = chip;
 
 	/* sysfs hook */
 	p_lm70->hwmon_dev = hwmon_device_register(&spi->dev);
@@ -141,6 +170,24 @@ out_dev_reg_failed:
 	return status;
 }
 
+static int __devinit lm70_probe(struct spi_device *spi)
+{
+	/* signaling is SPI_MODE_0 on a 3-wire link (shared SI/SO) */
+	if ((spi->mode & (SPI_CPOL | SPI_CPHA)) || !(spi->mode & SPI_3WIRE))
+		return -EINVAL;
+
+	return common_probe(spi, LM70_CHIP_LM70);
+}
+
+static int __devinit tmp121_probe(struct spi_device *spi)
+{
+	/* signaling is SPI_MODE_0 with only MISO connected */
+	if (spi->mode & (SPI_CPOL | SPI_CPHA))
+		return -EINVAL;
+
+	return common_probe(spi, LM70_CHIP_TMP121);
+}
+
 static int __devexit lm70_remove(struct spi_device *spi)
 {
 	struct lm70 *p_lm70 = dev_get_drvdata(&spi->dev);
@@ -154,6 +201,15 @@ static int __devexit lm70_remove(struct spi_device *spi)
 	return 0;
 }
 
+static struct spi_driver tmp121_driver = {
+	.driver = {
+		.name	= "tmp121",
+		.owner	= THIS_MODULE,
+	},
+	.probe	= tmp121_probe,
+	.remove	= __devexit_p(lm70_remove),
+};
+
 static struct spi_driver lm70_driver = {
 	.driver = {
 		.name	= "lm70",
@@ -165,17 +221,26 @@ static struct spi_driver lm70_driver = {
 
 static int __init init_lm70(void)
 {
-	return spi_register_driver(&lm70_driver);
+	int ret = spi_register_driver(&lm70_driver);
+	if (ret)
+		return ret;
+
+	ret = spi_register_driver(&tmp121_driver);
+	if (ret)
+		spi_unregister_driver(&lm70_driver);
+
+	return ret;
 }
 
 static void __exit cleanup_lm70(void)
 {
 	spi_unregister_driver(&lm70_driver);
+	spi_unregister_driver(&tmp121_driver);
 }
 
 module_init(init_lm70);
 module_exit(cleanup_lm70);
 
 MODULE_AUTHOR("Kaiwan N Billimoria");
-MODULE_DESCRIPTION("National Semiconductor LM70 Linux driver");
+MODULE_DESCRIPTION("NS LM70 / TI TMP121/TMP123 Linux driver");
 MODULE_LICENSE("GPL");
diff --git a/drivers/hwmon/lm75.c b/drivers/hwmon/lm75.c
index 8f9595f2fb53..55bd87c15c9a 100644
--- a/drivers/hwmon/lm75.c
+++ b/drivers/hwmon/lm75.c
@@ -190,7 +190,7 @@ lm75_probe(struct i2c_client *client, const struct i2c_device_id *id)
 	}
 
 	dev_info(&client->dev, "%s: sensor '%s'\n",
-		data->hwmon_dev->bus_id, client->name);
+		 dev_name(data->hwmon_dev), client->name);
 
 	return 0;
 
diff --git a/drivers/hwmon/ltc4245.c b/drivers/hwmon/ltc4245.c
new file mode 100644
index 000000000000..034b2c515848
--- /dev/null
+++ b/drivers/hwmon/ltc4245.c
@@ -0,0 +1,567 @@
+/*
+ * Driver for Linear Technology LTC4245 I2C Multiple Supply Hot Swap Controller
+ *
+ * Copyright (C) 2008 Ira W. Snyder <iws@ovro.caltech.edu>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ *
+ * This driver is based on the ds1621 and ina209 drivers.
+ *
+ * Datasheet:
+ * http://www.linear.com/pc/downloadDocument.do?navId=H0,C1,C1003,C1006,C1140,P19392,D13517
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/err.h>
+#include <linux/slab.h>
+#include <linux/i2c.h>
+#include <linux/hwmon.h>
+#include <linux/hwmon-sysfs.h>
+
+/* Valid addresses are 0x20 - 0x3f
+ *
+ * For now, we do not probe, since some of these addresses
+ * are known to be unfriendly to probing */
+static const unsigned short normal_i2c[] = { I2C_CLIENT_END };
+
+/* Insmod parameters */
+I2C_CLIENT_INSMOD_1(ltc4245);
+
+/* Here are names of the chip's registers (a.k.a. commands) */
+enum ltc4245_cmd {
+	LTC4245_STATUS			= 0x00, /* readonly */
+	LTC4245_ALERT			= 0x01,
+	LTC4245_CONTROL			= 0x02,
+	LTC4245_ON			= 0x03,
+	LTC4245_FAULT1			= 0x04,
+	LTC4245_FAULT2			= 0x05,
+	LTC4245_GPIO			= 0x06,
+	LTC4245_ADCADR			= 0x07,
+
+	LTC4245_12VIN			= 0x10,
+	LTC4245_12VSENSE		= 0x11,
+	LTC4245_12VOUT			= 0x12,
+	LTC4245_5VIN			= 0x13,
+	LTC4245_5VSENSE			= 0x14,
+	LTC4245_5VOUT			= 0x15,
+	LTC4245_3VIN			= 0x16,
+	LTC4245_3VSENSE			= 0x17,
+	LTC4245_3VOUT			= 0x18,
+	LTC4245_VEEIN			= 0x19,
+	LTC4245_VEESENSE		= 0x1a,
+	LTC4245_VEEOUT			= 0x1b,
+	LTC4245_GPIOADC1		= 0x1c,
+	LTC4245_GPIOADC2		= 0x1d,
+	LTC4245_GPIOADC3		= 0x1e,
+};
+
+struct ltc4245_data {
+	struct device *hwmon_dev;
+
+	struct mutex update_lock;
+	bool valid;
+	unsigned long last_updated; /* in jiffies */
+
+	/* Control registers */
+	u8 cregs[0x08];
+
+	/* Voltage registers */
+	u8 vregs[0x0f];
+};
+
+static struct ltc4245_data *ltc4245_update_device(struct device *dev)
+{
+	struct i2c_client *client = to_i2c_client(dev);
+	struct ltc4245_data *data = i2c_get_clientdata(client);
+	s32 val;
+	int i;
+
+	mutex_lock(&data->update_lock);
+
+	if (time_after(jiffies, data->last_updated + HZ) || !data->valid) {
+
+		dev_dbg(&client->dev, "Starting ltc4245 update\n");
+
+		/* Read control registers -- 0x00 to 0x07 */
+		for (i = 0; i < ARRAY_SIZE(data->cregs); i++) {
+			val = i2c_smbus_read_byte_data(client, i);
+			if (unlikely(val < 0))
+				data->cregs[i] = 0;
+			else
+				data->cregs[i] = val;
+		}
+
+		/* Read voltage registers -- 0x10 to 0x1f */
+		for (i = 0; i < ARRAY_SIZE(data->vregs); i++) {
+			val = i2c_smbus_read_byte_data(client, i+0x10);
+			if (unlikely(val < 0))
+				data->vregs[i] = 0;
+			else
+				data->vregs[i] = val;
+		}
+
+		data->last_updated = jiffies;
+		data->valid = 1;
+	}
+
+	mutex_unlock(&data->update_lock);
+
+	return data;
+}
+
+/* Return the voltage from the given register in millivolts */
+static int ltc4245_get_voltage(struct device *dev, u8 reg)
+{
+	struct ltc4245_data *data = ltc4245_update_device(dev);
+	const u8 regval = data->vregs[reg - 0x10];
+	u32 voltage = 0;
+
+	switch (reg) {
+	case LTC4245_12VIN:
+	case LTC4245_12VOUT:
+		voltage = regval * 55;
+		break;
+	case LTC4245_5VIN:
+	case LTC4245_5VOUT:
+		voltage = regval * 22;
+		break;
+	case LTC4245_3VIN:
+	case LTC4245_3VOUT:
+		voltage = regval * 15;
+		break;
+	case LTC4245_VEEIN:
+	case LTC4245_VEEOUT:
+		voltage = regval * -55;
+		break;
+	case LTC4245_GPIOADC1:
+	case LTC4245_GPIOADC2:
+	case LTC4245_GPIOADC3:
+		voltage = regval * 10;
+		break;
+	default:
+		/* If we get here, the developer messed up */
+		WARN_ON_ONCE(1);
+		break;
+	}
+
+	return voltage;
+}
+
+/* Return the current in the given sense register in milliAmperes */
+static unsigned int ltc4245_get_current(struct device *dev, u8 reg)
+{
+	struct ltc4245_data *data = ltc4245_update_device(dev);
+	const u8 regval = data->vregs[reg - 0x10];
+	unsigned int voltage;
+	unsigned int curr;
+
+	/* The strange looking conversions that follow are fixed-point
+	 * math, since we cannot do floating point in the kernel.
+	 *
+	 * Step 1: convert sense register to microVolts
+	 * Step 2: convert voltage to milliAmperes
+	 *
+	 * If you play around with the V=IR equation, you come up with
+	 * the following: X uV / Y mOhm == Z mA
+	 *
+	 * With the resistors that are fractions of a milliOhm, we multiply
+	 * the voltage and resistance by 10, to shift the decimal point.
+	 * Now we can use the normal division operator again.
+	 */
+
+	switch (reg) {
+	case LTC4245_12VSENSE:
+		voltage = regval * 250; /* voltage in uV */
+		curr = voltage / 50; /* sense resistor 50 mOhm */
+		break;
+	case LTC4245_5VSENSE:
+		voltage = regval * 125; /* voltage in uV */
+		curr = (voltage * 10) / 35; /* sense resistor 3.5 mOhm */
+		break;
+	case LTC4245_3VSENSE:
+		voltage = regval * 125; /* voltage in uV */
+		curr = (voltage * 10) / 25; /* sense resistor 2.5 mOhm */
+		break;
+	case LTC4245_VEESENSE:
+		voltage = regval * 250; /* voltage in uV */
+		curr = voltage / 100; /* sense resistor 100 mOhm */
+		break;
+	default:
+		/* If we get here, the developer messed up */
+		WARN_ON_ONCE(1);
+		curr = 0;
+		break;
+	}
+
+	return curr;
+}
+
+static ssize_t ltc4245_show_voltage(struct device *dev,
+				    struct device_attribute *da,
+				    char *buf)
+{
+	struct sensor_device_attribute *attr = to_sensor_dev_attr(da);
+	const int voltage = ltc4245_get_voltage(dev, attr->index);
+
+	return snprintf(buf, PAGE_SIZE, "%d\n", voltage);
+}
+
+static ssize_t ltc4245_show_current(struct device *dev,
+				    struct device_attribute *da,
+				    char *buf)
+{
+	struct sensor_device_attribute *attr = to_sensor_dev_attr(da);
+	const unsigned int curr = ltc4245_get_current(dev, attr->index);
+
+	return snprintf(buf, PAGE_SIZE, "%u\n", curr);
+}
+
+static ssize_t ltc4245_show_power(struct device *dev,
+				  struct device_attribute *da,
+				  char *buf)
+{
+	struct sensor_device_attribute *attr = to_sensor_dev_attr(da);
+	const unsigned int curr = ltc4245_get_current(dev, attr->index);
+	const int output_voltage = ltc4245_get_voltage(dev, attr->index+1);
+
+	/* current in mA * voltage in mV == power in uW */
+	const unsigned int power = abs(output_voltage * curr);
+
+	return snprintf(buf, PAGE_SIZE, "%u\n", power);
+}
+
+static ssize_t ltc4245_show_alarm(struct device *dev,
+					  struct device_attribute *da,
+					  char *buf)
+{
+	struct sensor_device_attribute_2 *attr = to_sensor_dev_attr_2(da);
+	struct ltc4245_data *data = ltc4245_update_device(dev);
+	const u8 reg = data->cregs[attr->index];
+	const u32 mask = attr->nr;
+
+	return snprintf(buf, PAGE_SIZE, "%u\n", (reg & mask) ? 1 : 0);
+}
+
+/* These macros are used below in constructing device attribute objects
+ * for use with sysfs_create_group() to make a sysfs device file
+ * for each register.
+ */
+
+#define LTC4245_VOLTAGE(name, ltc4245_cmd_idx) \
+	static SENSOR_DEVICE_ATTR(name, S_IRUGO, \
+	ltc4245_show_voltage, NULL, ltc4245_cmd_idx)
+
+#define LTC4245_CURRENT(name, ltc4245_cmd_idx) \
+	static SENSOR_DEVICE_ATTR(name, S_IRUGO, \
+	ltc4245_show_current, NULL, ltc4245_cmd_idx)
+
+#define LTC4245_POWER(name, ltc4245_cmd_idx) \
+	static SENSOR_DEVICE_ATTR(name, S_IRUGO, \
+	ltc4245_show_power, NULL, ltc4245_cmd_idx)
+
+#define LTC4245_ALARM(name, mask, reg) \
+	static SENSOR_DEVICE_ATTR_2(name, S_IRUGO, \
+	ltc4245_show_alarm, NULL, (mask), reg)
+
+/* Construct a sensor_device_attribute structure for each register */
+
+/* Input voltages */
+LTC4245_VOLTAGE(in1_input,			LTC4245_12VIN);
+LTC4245_VOLTAGE(in2_input,			LTC4245_5VIN);
+LTC4245_VOLTAGE(in3_input,			LTC4245_3VIN);
+LTC4245_VOLTAGE(in4_input,			LTC4245_VEEIN);
+
+/* Input undervoltage alarms */
+LTC4245_ALARM(in1_min_alarm,	(1 << 0),	LTC4245_FAULT1);
+LTC4245_ALARM(in2_min_alarm,	(1 << 1),	LTC4245_FAULT1);
+LTC4245_ALARM(in3_min_alarm,	(1 << 2),	LTC4245_FAULT1);
+LTC4245_ALARM(in4_min_alarm,	(1 << 3),	LTC4245_FAULT1);
+
+/* Currents (via sense resistor) */
+LTC4245_CURRENT(curr1_input,			LTC4245_12VSENSE);
+LTC4245_CURRENT(curr2_input,			LTC4245_5VSENSE);
+LTC4245_CURRENT(curr3_input,			LTC4245_3VSENSE);
+LTC4245_CURRENT(curr4_input,			LTC4245_VEESENSE);
+
+/* Overcurrent alarms */
+LTC4245_ALARM(curr1_max_alarm,	(1 << 4),	LTC4245_FAULT1);
+LTC4245_ALARM(curr2_max_alarm,	(1 << 5),	LTC4245_FAULT1);
+LTC4245_ALARM(curr3_max_alarm,	(1 << 6),	LTC4245_FAULT1);
+LTC4245_ALARM(curr4_max_alarm,	(1 << 7),	LTC4245_FAULT1);
+
+/* Output voltages */
+LTC4245_VOLTAGE(in5_input,			LTC4245_12VOUT);
+LTC4245_VOLTAGE(in6_input,			LTC4245_5VOUT);
+LTC4245_VOLTAGE(in7_input,			LTC4245_3VOUT);
+LTC4245_VOLTAGE(in8_input,			LTC4245_VEEOUT);
+
+/* Power Bad alarms */
+LTC4245_ALARM(in5_min_alarm,	(1 << 0),	LTC4245_FAULT2);
+LTC4245_ALARM(in6_min_alarm,	(1 << 1),	LTC4245_FAULT2);
+LTC4245_ALARM(in7_min_alarm,	(1 << 2),	LTC4245_FAULT2);
+LTC4245_ALARM(in8_min_alarm,	(1 << 3),	LTC4245_FAULT2);
+
+/* GPIO voltages */
+LTC4245_VOLTAGE(in9_input,			LTC4245_GPIOADC1);
+LTC4245_VOLTAGE(in10_input,			LTC4245_GPIOADC2);
+LTC4245_VOLTAGE(in11_input,			LTC4245_GPIOADC3);
+
+/* Power Consumption (virtual) */
+LTC4245_POWER(power1_input,			LTC4245_12VSENSE);
+LTC4245_POWER(power2_input,			LTC4245_5VSENSE);
+LTC4245_POWER(power3_input,			LTC4245_3VSENSE);
+LTC4245_POWER(power4_input,			LTC4245_VEESENSE);
+
+/* Finally, construct an array of pointers to members of the above objects,
+ * as required for sysfs_create_group()
+ */
+static struct attribute *ltc4245_attributes[] = {
+	&sensor_dev_attr_in1_input.dev_attr.attr,
+	&sensor_dev_attr_in2_input.dev_attr.attr,
+	&sensor_dev_attr_in3_input.dev_attr.attr,
+	&sensor_dev_attr_in4_input.dev_attr.attr,
+
+	&sensor_dev_attr_in1_min_alarm.dev_attr.attr,
+	&sensor_dev_attr_in2_min_alarm.dev_attr.attr,
+	&sensor_dev_attr_in3_min_alarm.dev_attr.attr,
+	&sensor_dev_attr_in4_min_alarm.dev_attr.attr,
+
+	&sensor_dev_attr_curr1_input.dev_attr.attr,
+	&sensor_dev_attr_curr2_input.dev_attr.attr,
+	&sensor_dev_attr_curr3_input.dev_attr.attr,
+	&sensor_dev_attr_curr4_input.dev_attr.attr,
+
+	&sensor_dev_attr_curr1_max_alarm.dev_attr.attr,
+	&sensor_dev_attr_curr2_max_alarm.dev_attr.attr,
+	&sensor_dev_attr_curr3_max_alarm.dev_attr.attr,
+	&sensor_dev_attr_curr4_max_alarm.dev_attr.attr,
+
+	&sensor_dev_attr_in5_input.dev_attr.attr,
+	&sensor_dev_attr_in6_input.dev_attr.attr,
+	&sensor_dev_attr_in7_input.dev_attr.attr,
+	&sensor_dev_attr_in8_input.dev_attr.attr,
+
+	&sensor_dev_attr_in5_min_alarm.dev_attr.attr,
+	&sensor_dev_attr_in6_min_alarm.dev_attr.attr,
+	&sensor_dev_attr_in7_min_alarm.dev_attr.attr,
+	&sensor_dev_attr_in8_min_alarm.dev_attr.attr,
+
+	&sensor_dev_attr_in9_input.dev_attr.attr,
+	&sensor_dev_attr_in10_input.dev_attr.attr,
+	&sensor_dev_attr_in11_input.dev_attr.attr,
+
+	&sensor_dev_attr_power1_input.dev_attr.attr,
+	&sensor_dev_attr_power2_input.dev_attr.attr,
+	&sensor_dev_attr_power3_input.dev_attr.attr,
+	&sensor_dev_attr_power4_input.dev_attr.attr,
+
+	NULL,
+};
+
+static const struct attribute_group ltc4245_group = {
+	.attrs = ltc4245_attributes,
+};
+
+static int ltc4245_probe(struct i2c_client *client,
+			 const struct i2c_device_id *id)
+{
+	struct ltc4245_data *data;
+	int ret;
+
+	data = kzalloc(sizeof(*data), GFP_KERNEL);
+	if (!data) {
+		ret = -ENOMEM;
+		goto out_kzalloc;
+	}
+
+	i2c_set_clientdata(client, data);
+	mutex_init(&data->update_lock);
+
+	/* Initialize the LTC4245 chip */
+	/* TODO */
+
+	/* Register sysfs hooks */
+	ret = sysfs_create_group(&client->dev.kobj, &ltc4245_group);
+	if (ret)
+		goto out_sysfs_create_group;
+
+	data->hwmon_dev = hwmon_device_register(&client->dev);
+	if (IS_ERR(data->hwmon_dev)) {
+		ret = PTR_ERR(data->hwmon_dev);
+		goto out_hwmon_device_register;
+	}
+
+	return 0;
+
+out_hwmon_device_register:
+	sysfs_remove_group(&client->dev.kobj, &ltc4245_group);
+out_sysfs_create_group:
+	kfree(data);
+out_kzalloc:
+	return ret;
+}
+
+static int ltc4245_remove(struct i2c_client *client)
+{
+	struct ltc4245_data *data = i2c_get_clientdata(client);
+
+	hwmon_device_unregister(data->hwmon_dev);
+	sysfs_remove_group(&client->dev.kobj, &ltc4245_group);
+
+	kfree(data);
+
+	return 0;
+}
+
+/* Check that some bits in a control register appear at all possible
+ * locations without changing value
+ *
+ * @client: the i2c client to use
+ * @reg: the register to read
+ * @bits: the bits to check (0xff checks all bits,
+ *                           0x03 checks only the last two bits)
+ *
+ * return -ERRNO if the register read failed
+ * return -ENODEV if the register value doesn't stay constant at all
+ * possible addresses
+ *
+ * return 0 for success
+ */
+static int ltc4245_check_control_reg(struct i2c_client *client, u8 reg, u8 bits)
+{
+	int i;
+	s32 v, voff1, voff2;
+
+	/* Read register and check for error */
+	v = i2c_smbus_read_byte_data(client, reg);
+	if (v < 0)
+		return v;
+
+	v &= bits;
+
+	for (i = 0x00; i < 0xff; i += 0x20) {
+
+		voff1 = i2c_smbus_read_byte_data(client, reg + i);
+		if (voff1 < 0)
+			return voff1;
+
+		voff2 = i2c_smbus_read_byte_data(client, reg + i + 0x08);
+		if (voff2 < 0)
+			return voff2;
+
+		voff1 &= bits;
+		voff2 &= bits;
+
+		if (v != voff1 || v != voff2)
+			return -ENODEV;
+	}
+
+	return 0;
+}
+
+static int ltc4245_detect(struct i2c_client *client,
+			  int kind,
+			  struct i2c_board_info *info)
+{
+	struct i2c_adapter *adapter = client->adapter;
+
+	if (!i2c_check_functionality(adapter, I2C_FUNC_SMBUS_BYTE_DATA))
+		return -ENODEV;
+
+	if (kind < 0) {		/* probed detection - check the chip type */
+		s32 v;		/* 8 bits from the chip, or -ERRNO */
+
+		/* Chip registers 0x00-0x07 are control registers
+		 * Chip registers 0x10-0x1f are data registers
+		 *
+		 * Address bits b7-b5 are ignored. This makes the chip "repeat"
+		 * in steps of 0x20. Any control registers should appear with
+		 * the same values across all duplicated addresses.
+		 *
+		 * Register 0x02 bit b2 is reserved, expect 0
+		 * Register 0x07 bits b7 to b4 are reserved, expect 0
+		 *
+		 * Registers 0x01, 0x02 are control registers and should not
+		 * change on their own.
+		 *
+		 * Register 0x06 bits b6 and b7 are control bits, and should
+		 * not change on their own.
+		 *
+		 * Register 0x07 bits b3 to b0 are control bits, and should
+		 * not change on their own.
+		 */
+
+		/* read register 0x02 reserved bit, expect 0 */
+		v = i2c_smbus_read_byte_data(client, LTC4245_CONTROL);
+		if (v < 0 || (v & 0x04) != 0)
+			return -ENODEV;
+
+		/* read register 0x07 reserved bits, expect 0 */
+		v = i2c_smbus_read_byte_data(client, LTC4245_ADCADR);
+		if (v < 0 || (v & 0xf0) != 0)
+			return -ENODEV;
+
+		/* check that the alert register appears at all locations */
+		if (ltc4245_check_control_reg(client, LTC4245_ALERT, 0xff))
+			return -ENODEV;
+
+		/* check that the control register appears at all locations */
+		if (ltc4245_check_control_reg(client, LTC4245_CONTROL, 0xff))
+			return -ENODEV;
+
+		/* check that register 0x06 bits b6 and b7 stay constant */
+		if (ltc4245_check_control_reg(client, LTC4245_GPIO, 0xc0))
+			return -ENODEV;
+
+		/* check that register 0x07 bits b3-b0 stay constant */
+		if (ltc4245_check_control_reg(client, LTC4245_ADCADR, 0x0f))
+			return -ENODEV;
+	}
+
+	strlcpy(info->type, "ltc4245", I2C_NAME_SIZE);
+	dev_info(&adapter->dev, "ltc4245 %s at address 0x%02x\n",
+			kind < 0 ? "probed" : "forced",
+			client->addr);
+
+	return 0;
+}
+
+static const struct i2c_device_id ltc4245_id[] = {
+	{ "ltc4245", ltc4245 },
+	{ }
+};
+MODULE_DEVICE_TABLE(i2c, ltc4245_id);
+
+/* This is the driver that will be inserted */
+static struct i2c_driver ltc4245_driver = {
+	.class		= I2C_CLASS_HWMON,
+	.driver = {
+		.name	= "ltc4245",
+	},
+	.probe		= ltc4245_probe,
+	.remove		= ltc4245_remove,
+	.id_table	= ltc4245_id,
+	.detect		= ltc4245_detect,
+	.address_data	= &addr_data,
+};
+
+static int __init ltc4245_init(void)
+{
+	return i2c_add_driver(&ltc4245_driver);
+}
+
+static void __exit ltc4245_exit(void)
+{
+	i2c_del_driver(&ltc4245_driver);
+}
+
+MODULE_AUTHOR("Ira W. Snyder <iws@ovro.caltech.edu>");
+MODULE_DESCRIPTION("LTC4245 driver");
+MODULE_LICENSE("GPL");
+
+module_init(ltc4245_init);
+module_exit(ltc4245_exit);
diff --git a/drivers/hwmon/w83781d.c b/drivers/hwmon/w83781d.c
index fc12bd412e3a..dbfb30c588d8 100644
--- a/drivers/hwmon/w83781d.c
+++ b/drivers/hwmon/w83781d.c
@@ -58,7 +58,10 @@ static const unsigned short normal_i2c[] = { 0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d,
 						0x2e, 0x2f, I2C_CLIENT_END };
 /* Insmod parameters */
 I2C_CLIENT_INSMOD_4(w83781d, w83782d, w83783s, as99127f);
-I2C_CLIENT_MODULE_PARM(force_subclients, "List of subclient addresses: "
+
+static unsigned short force_subclients[4];
+module_param_array(force_subclients, short, NULL, 0);
+MODULE_PARM_DESC(force_subclients, "List of subclient addresses: "
 		    "{bus, clientaddr, subclientaddr1, subclientaddr2}");
 
 static int reset;
diff --git a/drivers/hwmon/w83791d.c b/drivers/hwmon/w83791d.c
index 5768def8a4f2..97851c5ba3a3 100644
--- a/drivers/hwmon/w83791d.c
+++ b/drivers/hwmon/w83791d.c
@@ -53,7 +53,10 @@ static const unsigned short normal_i2c[] = { 0x2c, 0x2d, 0x2e, 0x2f,
 
 /* Insmod parameters */
 I2C_CLIENT_INSMOD_1(w83791d);
-I2C_CLIENT_MODULE_PARM(force_subclients, "List of subclient addresses: "
+
+static unsigned short force_subclients[4];
+module_param_array(force_subclients, short, NULL, 0);
+MODULE_PARM_DESC(force_subclients, "List of subclient addresses: "
 			"{bus, clientaddr, subclientaddr1, subclientaddr2}");
 
 static int reset;
diff --git a/drivers/hwmon/w83792d.c b/drivers/hwmon/w83792d.c
index cf94c5b0c879..2be16194ddf3 100644
--- a/drivers/hwmon/w83792d.c
+++ b/drivers/hwmon/w83792d.c
@@ -51,7 +51,10 @@ static const unsigned short normal_i2c[] = { 0x2c, 0x2d, 0x2e, 0x2f,
 
 /* Insmod parameters */
 I2C_CLIENT_INSMOD_1(w83792d);
-I2C_CLIENT_MODULE_PARM(force_subclients, "List of subclient addresses: "
+
+static unsigned short force_subclients[4];
+module_param_array(force_subclients, short, NULL, 0);
+MODULE_PARM_DESC(force_subclients, "List of subclient addresses: "
 			"{bus, clientaddr, subclientaddr1, subclientaddr2}");
 
 static int init;
diff --git a/drivers/hwmon/w83793.c b/drivers/hwmon/w83793.c
index 0a739f1c69be..47dd398f7258 100644
--- a/drivers/hwmon/w83793.c
+++ b/drivers/hwmon/w83793.c
@@ -42,7 +42,10 @@ static const unsigned short normal_i2c[] = { 0x2c, 0x2d, 0x2e, 0x2f,
 
 /* Insmod parameters */
 I2C_CLIENT_INSMOD_1(w83793);
-I2C_CLIENT_MODULE_PARM(force_subclients, "List of subclient addresses: "
+
+static unsigned short force_subclients[4];
+module_param_array(force_subclients, short, NULL, 0);
+MODULE_PARM_DESC(force_subclients, "List of subclient addresses: "
 		       "{bus, clientaddr, subclientaddr1, subclientaddr2}");
 
 static int reset;
diff --git a/drivers/i2c/busses/i2c-ali1563.c b/drivers/i2c/busses/i2c-ali1563.c
index fc3e5b026423..dd9e796fad69 100644
--- a/drivers/i2c/busses/i2c-ali1563.c
+++ b/drivers/i2c/busses/i2c-ali1563.c
@@ -399,8 +399,8 @@ static int __devinit ali1563_probe(struct pci_dev * dev,
 	if ((error = ali1563_setup(dev)))
 		goto exit;
 	ali1563_adapter.dev.parent = &dev->dev;
-	sprintf(ali1563_adapter.name,"SMBus ALi 1563 Adapter @ %04x",
-		ali1563_smba);
+	snprintf(ali1563_adapter.name, sizeof(ali1563_adapter.name),
+		 "SMBus ALi 1563 Adapter @ %04x", ali1563_smba);
 	if ((error = i2c_add_adapter(&ali1563_adapter)))
 		goto exit_shutdown;
 	return 0;
diff --git a/drivers/i2c/busses/i2c-amd756-s4882.c b/drivers/i2c/busses/i2c-amd756-s4882.c
index 8ba2bcf727d3..378fcb5d5783 100644
--- a/drivers/i2c/busses/i2c-amd756-s4882.c
+++ b/drivers/i2c/busses/i2c-amd756-s4882.c
@@ -197,8 +197,8 @@ static int __init amd756_s4882_init(void)
 	for (i = 1; i < 5; i++) {
 		s4882_algo[i] = *(amd756_smbus.algo);
 		s4882_adapter[i] = amd756_smbus;
-		sprintf(s4882_adapter[i].name,
-			"SMBus 8111 adapter (CPU%d)", i-1);
+		snprintf(s4882_adapter[i].name, sizeof(s4882_adapter[i].name),
+			 "SMBus 8111 adapter (CPU%d)", i-1);
 		s4882_adapter[i].algo = s4882_algo+i;
 		s4882_adapter[i].dev.parent = amd756_smbus.dev.parent;
 	}
diff --git a/drivers/i2c/busses/i2c-amd756.c b/drivers/i2c/busses/i2c-amd756.c
index 424dad6f18d8..36bee5b9c952 100644
--- a/drivers/i2c/busses/i2c-amd756.c
+++ b/drivers/i2c/busses/i2c-amd756.c
@@ -380,8 +380,9 @@ static int __devinit amd756_probe(struct pci_dev *pdev,
 	/* set up the sysfs linkage to our parent device */
 	amd756_smbus.dev.parent = &pdev->dev;
 
-	sprintf(amd756_smbus.name, "SMBus %s adapter at %04x",
-		chipname[id->driver_data], amd756_ioport);
+	snprintf(amd756_smbus.name, sizeof(amd756_smbus.name),
+		 "SMBus %s adapter at %04x", chipname[id->driver_data],
+		 amd756_ioport);
 
 	error = i2c_add_adapter(&amd756_smbus);
 	if (error) {
diff --git a/drivers/i2c/busses/i2c-at91.c b/drivers/i2c/busses/i2c-at91.c
index 9efb02137254..67d9dc5b351b 100644
--- a/drivers/i2c/busses/i2c-at91.c
+++ b/drivers/i2c/busses/i2c-at91.c
@@ -222,7 +222,7 @@ static int __devinit at91_i2c_probe(struct platform_device *pdev)
 		rc = -ENOMEM;
 		goto fail2;
 	}
-	sprintf(adapter->name, "AT91");
+	snprintf(adapter->name, sizeof(adapter->name), "AT91");
 	adapter->algo = &at91_algorithm;
 	adapter->class = I2C_CLASS_HWMON;
 	adapter->dev.parent = &pdev->dev;
diff --git a/drivers/i2c/busses/i2c-bfin-twi.c b/drivers/i2c/busses/i2c-bfin-twi.c
index 3c855ff2992f..3fd2c417c1e0 100644
--- a/drivers/i2c/busses/i2c-bfin-twi.c
+++ b/drivers/i2c/busses/i2c-bfin-twi.c
@@ -656,7 +656,7 @@ static int i2c_bfin_twi_probe(struct platform_device *pdev)
 	strlcpy(p_adap->name, pdev->name, sizeof(p_adap->name));
 	p_adap->algo = &bfin_twi_algorithm;
 	p_adap->algo_data = iface;
-	p_adap->class = I2C_CLASS_ALL;
+	p_adap->class = I2C_CLASS_HWMON | I2C_CLASS_SPD;
 	p_adap->dev.parent = &pdev->dev;
 
 	rc = peripheral_request_list(pin_req[pdev->id], "i2c-bfin-twi");
diff --git a/drivers/i2c/busses/i2c-i801.c b/drivers/i2c/busses/i2c-i801.c
index 5123eb69a971..526625eaa84b 100644
--- a/drivers/i2c/busses/i2c-i801.c
+++ b/drivers/i2c/busses/i2c-i801.c
@@ -64,7 +64,7 @@
 #include <linux/init.h>
 #include <linux/i2c.h>
 #include <linux/acpi.h>
-#include <asm/io.h>
+#include <linux/io.h>
 
 /* I801 SMBus address offsets */
 #define SMBHSTSTS	(0 + i801_smba)
@@ -583,6 +583,40 @@ static struct pci_device_id i801_ids[] = {
 
 MODULE_DEVICE_TABLE (pci, i801_ids);
 
+#if defined CONFIG_INPUT_APANEL || defined CONFIG_INPUT_APANEL_MODULE
+static unsigned char apanel_addr;
+
+/* Scan the system ROM for the signature "FJKEYINF" */
+static __init const void __iomem *bios_signature(const void __iomem *bios)
+{
+	ssize_t offset;
+	const unsigned char signature[] = "FJKEYINF";
+
+	for (offset = 0; offset < 0x10000; offset += 0x10) {
+		if (check_signature(bios + offset, signature,
+				    sizeof(signature)-1))
+			return bios + offset;
+	}
+	return NULL;
+}
+
+static void __init input_apanel_init(void)
+{
+	void __iomem *bios;
+	const void __iomem *p;
+
+	bios = ioremap(0xF0000, 0x10000); /* Can't fail */
+	p = bios_signature(bios);
+	if (p) {
+		/* just use the first address */
+		apanel_addr = readb(p + 8 + 3) >> 1;
+	}
+	iounmap(bios);
+}
+#else
+static void __init input_apanel_init(void) {}
+#endif
+
 static int __devinit i801_probe(struct pci_dev *dev, const struct pci_device_id *id)
 {
 	unsigned char temp;
@@ -667,6 +701,19 @@ static int __devinit i801_probe(struct pci_dev *dev, const struct pci_device_id
 		dev_err(&dev->dev, "Failed to add SMBus adapter\n");
 		goto exit_release;
 	}
+
+	/* Register optional slaves */
+#if defined CONFIG_INPUT_APANEL || defined CONFIG_INPUT_APANEL_MODULE
+	if (apanel_addr) {
+		struct i2c_board_info info;
+
+		memset(&info, 0, sizeof(struct i2c_board_info));
+		info.addr = apanel_addr;
+		strlcpy(info.type, "fujitsu_apanel", I2C_NAME_SIZE);
+		i2c_new_device(&i801_adapter, &info);
+	}
+#endif
+
 	return 0;
 
 exit_release:
@@ -717,6 +764,7 @@ static struct pci_driver i801_driver = {
 
 static int __init i2c_i801_init(void)
 {
+	input_apanel_init();
 	return pci_register_driver(&i801_driver);
 }
 
diff --git a/drivers/i2c/busses/i2c-pxa.c b/drivers/i2c/busses/i2c-pxa.c
index 906f9b9d715d..6af68146c342 100644
--- a/drivers/i2c/busses/i2c-pxa.c
+++ b/drivers/i2c/busses/i2c-pxa.c
@@ -1016,7 +1016,7 @@ static int i2c_pxa_probe(struct platform_device *dev)
 	snprintf(i2c->adap.name, sizeof(i2c->adap.name), "pxa_i2c-i2c.%u",
 		 i2c->adap.nr);
 
-	i2c->clk = clk_get(&dev->dev, "I2CCLK");
+	i2c->clk = clk_get(&dev->dev, NULL);
 	if (IS_ERR(i2c->clk)) {
 		ret = PTR_ERR(i2c->clk);
 		goto eclk;
@@ -1076,10 +1076,10 @@ static int i2c_pxa_probe(struct platform_device *dev)
 
 #ifdef CONFIG_I2C_PXA_SLAVE
 	printk(KERN_INFO "I2C: %s: PXA I2C adapter, slave address %d\n",
-	       i2c->adap.dev.bus_id, i2c->slave_addr);
+	       dev_name(&i2c->adap.dev), i2c->slave_addr);
 #else
 	printk(KERN_INFO "I2C: %s: PXA I2C adapter\n",
-	       i2c->adap.dev.bus_id);
+	       dev_name(&i2c->adap.dev));
 #endif
 	return 0;
 
diff --git a/drivers/i2c/busses/i2c-s3c2410.c b/drivers/i2c/busses/i2c-s3c2410.c
index 1fac4e233133..54af2946de94 100644
--- a/drivers/i2c/busses/i2c-s3c2410.c
+++ b/drivers/i2c/busses/i2c-s3c2410.c
@@ -40,8 +40,8 @@
 #include <asm/io.h>
 
 #include <mach/regs-gpio.h>
-#include <asm/plat-s3c/regs-iic.h>
-#include <asm/plat-s3c/iic.h>
+#include <plat/regs-iic.h>
+#include <plat/iic.h>
 
 /* i2c controller state */
 
@@ -936,7 +936,7 @@ static int s3c24xx_i2c_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, i2c);
 
-	dev_info(&pdev->dev, "%s: S3C I2C adapter\n", i2c->adap.dev.bus_id);
+	dev_info(&pdev->dev, "%s: S3C I2C adapter\n", dev_name(&i2c->adap.dev));
 	return 0;
 
  err_cpufreq:
diff --git a/drivers/i2c/busses/i2c-sh7760.c b/drivers/i2c/busses/i2c-sh7760.c
index 5e0e254976de..baa28b73ae42 100644
--- a/drivers/i2c/busses/i2c-sh7760.c
+++ b/drivers/i2c/busses/i2c-sh7760.c
@@ -475,7 +475,7 @@ static int __devinit sh7760_i2c_probe(struct platform_device *pdev)
 
 	id->adap.nr = pdev->id;
 	id->adap.algo = &sh7760_i2c_algo;
-	id->adap.class = I2C_CLASS_ALL;
+	id->adap.class = I2C_CLASS_HWMON | I2C_CLASS_SPD;
 	id->adap.retries = 3;
 	id->adap.algo_data = id;
 	id->adap.dev.parent = &pdev->dev;
diff --git a/drivers/i2c/busses/i2c-sh_mobile.c b/drivers/i2c/busses/i2c-sh_mobile.c
index 3384a717fec0..1c01083b01b5 100644
--- a/drivers/i2c/busses/i2c-sh_mobile.c
+++ b/drivers/i2c/busses/i2c-sh_mobile.c
@@ -160,9 +160,39 @@ struct sh_mobile_i2c_data {
 
 static void activate_ch(struct sh_mobile_i2c_data *pd)
 {
+	unsigned long i2c_clk;
+	u_int32_t num;
+	u_int32_t denom;
+	u_int32_t tmp;
+
 	/* Make sure the clock is enabled */
 	clk_enable(pd->clk);
 
+	/* Get clock rate after clock is enabled */
+	i2c_clk = clk_get_rate(pd->clk);
+
+	/* Calculate the value for iccl. From the data sheet:
+	 * iccl = (p clock / transfer rate) * (L / (L + H))
+	 * where L and H are the SCL low/high ratio (5/4 in this case).
+	 * We also round off the result.
+	 */
+	num = i2c_clk * 5;
+	denom = NORMAL_SPEED * 9;
+	tmp = num * 10 / denom;
+	if (tmp % 10 >= 5)
+		pd->iccl = (u_int8_t)((num/denom) + 1);
+	else
+		pd->iccl = (u_int8_t)(num/denom);
+
+	/* Calculate the value for icch. From the data sheet:
+	   icch = (p clock / transfer rate) * (H / (L + H)) */
+	num = i2c_clk * 4;
+	tmp = num * 10 / denom;
+	if (tmp % 10 >= 5)
+		pd->icch = (u_int8_t)((num/denom) + 1);
+	else
+		pd->icch = (u_int8_t)(num/denom);
+
 	/* Enable channel and configure rx ack */
 	iowrite8(ioread8(ICCR(pd)) | ICCR_ICE, ICCR(pd));
 
@@ -459,40 +489,6 @@ static struct i2c_algorithm sh_mobile_i2c_algorithm = {
 	.master_xfer	= sh_mobile_i2c_xfer,
 };
 
-static void sh_mobile_i2c_setup_channel(struct platform_device *dev)
-{
-	struct sh_mobile_i2c_data *pd = platform_get_drvdata(dev);
-	unsigned long peripheral_clk = clk_get_rate(pd->clk);
-	u_int32_t num;
-	u_int32_t denom;
-	u_int32_t tmp;
-
-	spin_lock_init(&pd->lock);
-	init_waitqueue_head(&pd->wait);
-
-	/* Calculate the value for iccl. From the data sheet:
-	 * iccl = (p clock / transfer rate) * (L / (L + H))
-	 * where L and H are the SCL low/high ratio (5/4 in this case).
-	 * We also round off the result.
-	 */
-	num = peripheral_clk * 5;
-	denom = NORMAL_SPEED * 9;
-	tmp = num * 10 / denom;
-	if (tmp % 10 >= 5)
-		pd->iccl = (u_int8_t)((num/denom) + 1);
-	else
-		pd->iccl = (u_int8_t)(num/denom);
-
-	/* Calculate the value for icch. From the data sheet:
-	   icch = (p clock / transfer rate) * (H / (L + H)) */
-	num = peripheral_clk * 4;
-	tmp = num * 10 / denom;
-	if (tmp % 10 >= 5)
-		pd->icch = (u_int8_t)((num/denom) + 1);
-	else
-		pd->icch = (u_int8_t)(num/denom);
-}
-
 static int sh_mobile_i2c_hook_irqs(struct platform_device *dev, int hook)
 {
 	struct resource *res;
@@ -504,7 +500,7 @@ static int sh_mobile_i2c_hook_irqs(struct platform_device *dev, int hook)
 	while ((res = platform_get_resource(dev, IORESOURCE_IRQ, k))) {
 		for (n = res->start; hook && n <= res->end; n++) {
 			if (request_irq(n, sh_mobile_i2c_isr, IRQF_DISABLED,
-					dev->dev.bus_id, dev))
+					dev_name(&dev->dev), dev))
 				goto rollback;
 		}
 		k++;
@@ -533,6 +529,7 @@ static int sh_mobile_i2c_probe(struct platform_device *dev)
 	struct sh_mobile_i2c_data *pd;
 	struct i2c_adapter *adap;
 	struct resource *res;
+	char clk_name[8];
 	int size;
 	int ret;
 
@@ -542,9 +539,10 @@ static int sh_mobile_i2c_probe(struct platform_device *dev)
 		return -ENOMEM;
 	}
 
-	pd->clk = clk_get(&dev->dev, "peripheral_clk");
+	snprintf(clk_name, sizeof(clk_name), "i2c%d", dev->id);
+	pd->clk = clk_get(&dev->dev, clk_name);
 	if (IS_ERR(pd->clk)) {
-		dev_err(&dev->dev, "cannot get peripheral clock\n");
+		dev_err(&dev->dev, "cannot get clock \"%s\"\n", clk_name);
 		ret = PTR_ERR(pd->clk);
 		goto err;
 	}
@@ -586,7 +584,8 @@ static int sh_mobile_i2c_probe(struct platform_device *dev)
 
 	strlcpy(adap->name, dev->name, sizeof(adap->name));
 
-	sh_mobile_i2c_setup_channel(dev);
+	spin_lock_init(&pd->lock);
+	init_waitqueue_head(&pd->wait);
 
 	ret = i2c_add_numbered_adapter(adap);
 	if (ret < 0) {
diff --git a/drivers/i2c/busses/i2c-sis5595.c b/drivers/i2c/busses/i2c-sis5595.c
index dfc2d5eb6a68..8ce2daff985c 100644
--- a/drivers/i2c/busses/i2c-sis5595.c
+++ b/drivers/i2c/busses/i2c-sis5595.c
@@ -389,8 +389,8 @@ static int __devinit sis5595_probe(struct pci_dev *dev, const struct pci_device_
 	/* set up the sysfs linkage to our parent device */
 	sis5595_adapter.dev.parent = &dev->dev;
 
-	sprintf(sis5595_adapter.name, "SMBus SIS5595 adapter at %04x",
-		sis5595_base + SMB_INDEX);
+	snprintf(sis5595_adapter.name, sizeof(sis5595_adapter.name),
+		 "SMBus SIS5595 adapter at %04x", sis5595_base + SMB_INDEX);
 	err = i2c_add_adapter(&sis5595_adapter);
 	if (err) {
 		release_region(sis5595_base + SMB_INDEX, 2);
diff --git a/drivers/i2c/busses/i2c-sis630.c b/drivers/i2c/busses/i2c-sis630.c
index e7c4b790da54..9c9c016ff2b5 100644
--- a/drivers/i2c/busses/i2c-sis630.c
+++ b/drivers/i2c/busses/i2c-sis630.c
@@ -487,8 +487,8 @@ static int __devinit sis630_probe(struct pci_dev *dev, const struct pci_device_i
 	/* set up the sysfs linkage to our parent device */
 	sis630_adapter.dev.parent = &dev->dev;
 
-	sprintf(sis630_adapter.name, "SMBus SIS630 adapter at %04x",
-		acpi_base + SMB_STS);
+	snprintf(sis630_adapter.name, sizeof(sis630_adapter.name),
+		 "SMBus SIS630 adapter at %04x", acpi_base + SMB_STS);
 
 	return i2c_add_adapter(&sis630_adapter);
 }
diff --git a/drivers/i2c/chips/Kconfig b/drivers/i2c/chips/Kconfig
index 4c35702830ce..b2ea73150b9a 100644
--- a/drivers/i2c/chips/Kconfig
+++ b/drivers/i2c/chips/Kconfig
@@ -114,18 +114,6 @@ config SENSORS_PCF8591
 	  These devices are hard to detect and rarely found on mainstream
 	  hardware.  If unsure, say N.
 
-config ISP1301_OMAP
-	tristate "Philips ISP1301 with OMAP OTG"
-	depends on ARCH_OMAP_OTG
-	help
-	  If you say yes here you get support for the Philips ISP1301
-	  USB-On-The-Go transceiver working with the OMAP OTG controller.
-	  The ISP1301 is used in products including H2 and H3 development
-	  boards for Texas Instruments OMAP processors.
-	  
-	  This driver can also be built as a module.  If so, the module
-	  will be called isp1301_omap.
-
 config TPS65010
 	tristate "TPS6501x Power Management chips"
 	depends on GPIOLIB
diff --git a/drivers/i2c/chips/Makefile b/drivers/i2c/chips/Makefile
index 23d2a31b0a64..aa7552d5b6bf 100644
--- a/drivers/i2c/chips/Makefile
+++ b/drivers/i2c/chips/Makefile
@@ -18,7 +18,6 @@ obj-$(CONFIG_SENSORS_PCA9539)	+= pca9539.o
 obj-$(CONFIG_SENSORS_PCF8574)	+= pcf8574.o
 obj-$(CONFIG_PCF8575)		+= pcf8575.o
 obj-$(CONFIG_SENSORS_PCF8591)	+= pcf8591.o
-obj-$(CONFIG_ISP1301_OMAP)	+= isp1301_omap.o
 obj-$(CONFIG_TPS65010)		+= tps65010.o
 obj-$(CONFIG_MENELAUS)		+= menelaus.o
 obj-$(CONFIG_SENSORS_TSL2550)	+= tsl2550.o
diff --git a/drivers/i2c/i2c-core.c b/drivers/i2c/i2c-core.c
index c6a63f46bc15..b1c9abe24c7b 100644
--- a/drivers/i2c/i2c-core.c
+++ b/drivers/i2c/i2c-core.c
@@ -459,7 +459,7 @@ static int i2c_register_adapter(struct i2c_adapter *adap)
 		pr_debug("I2C adapter driver [%s] forgot to specify "
 			 "physical device\n", adap->name);
 	}
-	sprintf(adap->dev.bus_id, "i2c-%d", adap->nr);
+	dev_set_name(&adap->dev, "i2c-%d", adap->nr);
 	adap->dev.release = &i2c_adapter_dev_release;
 	adap->dev.class = &i2c_adapter_class;
 	res = device_register(&adap->dev);
@@ -845,8 +845,8 @@ int i2c_attach_client(struct i2c_client *client)
 	} else
 		client->dev.release = i2c_client_dev_release;
 
-	snprintf(&client->dev.bus_id[0], sizeof(client->dev.bus_id),
-		"%d-%04x", i2c_adapter_id(adapter), client->addr);
+	dev_set_name(&client->dev, "%d-%04x", i2c_adapter_id(adapter),
+		     client->addr);
 	res = device_register(&client->dev);
 	if (res)
 		goto out_err;
@@ -856,7 +856,7 @@ int i2c_attach_client(struct i2c_client *client)
 	mutex_unlock(&adapter->clist_lock);
 
 	dev_dbg(&adapter->dev, "client [%s] registered with bus id %s\n",
-		client->name, client->dev.bus_id);
+		client->name, dev_name(&client->dev));
 
 	if (adapter->client_register)  {
 		if (adapter->client_register(client)) {
diff --git a/drivers/ide/Kconfig b/drivers/ide/Kconfig
index 6d7401772a8f..57630402ea67 100644
--- a/drivers/ide/Kconfig
+++ b/drivers/ide/Kconfig
@@ -732,7 +732,7 @@ config BLK_DEV_IDE_TX4939
 
 config IDE_ARM
 	tristate "ARM IDE support"
-	depends on ARM && (ARCH_CLPS7500 || ARCH_RPC || ARCH_SHARK)
+	depends on ARM && (ARCH_RPC || ARCH_SHARK)
 	default y
 
 config BLK_DEV_IDE_ICSIDE
diff --git a/drivers/ide/ide_arm.c b/drivers/ide/ide_arm.c
index f728f2927b5a..bdcac94d7c1f 100644
--- a/drivers/ide/ide_arm.c
+++ b/drivers/ide/ide_arm.c
@@ -15,15 +15,8 @@
 
 #define DRV_NAME "ide_arm"
 
-#ifdef CONFIG_ARCH_CLPS7500
-# include <mach/hardware.h>
-#
-# define IDE_ARM_IO	(ISASLOT_IO + 0x1f0)
-# define IDE_ARM_IRQ	IRQ_ISA_14
-#else
-# define IDE_ARM_IO	0x1f0
-# define IDE_ARM_IRQ	IRQ_HARDDISK
-#endif
+#define IDE_ARM_IO	0x1f0
+#define IDE_ARM_IRQ	IRQ_HARDDISK
 
 static int __init ide_arm_init(void)
 {
diff --git a/drivers/ide/macide.c b/drivers/ide/macide.c
index 43f97cc1d30e..3c60064f1d4f 100644
--- a/drivers/ide/macide.c
+++ b/drivers/ide/macide.c
@@ -18,7 +18,6 @@
 #include <linux/delay.h>
 #include <linux/ide.h>
 
-#include <asm/machw.h>
 #include <asm/macintosh.h>
 #include <asm/macints.h>
 #include <asm/mac_baboon.h>
diff --git a/drivers/idle/i7300_idle.c b/drivers/idle/i7300_idle.c
index fb176f6ef9f8..17e8ddd01334 100644
--- a/drivers/idle/i7300_idle.c
+++ b/drivers/idle/i7300_idle.c
@@ -177,7 +177,7 @@ static int __init i7300_idle_ioat_selftest(u8 *ctl,
 }
 
 static struct device dummy_dma_dev = {
-	.bus_id = "fallback device",
+	.init_name = "fallback device",
 	.coherent_dma_mask = DMA_64BIT_MASK,
 	.dma_mask = &dummy_dma_dev.coherent_dma_mask,
 };
diff --git a/drivers/ieee1394/csr.c b/drivers/ieee1394/csr.c
index c90be4070e40..9029b6839f0b 100644
--- a/drivers/ieee1394/csr.c
+++ b/drivers/ieee1394/csr.c
@@ -68,22 +68,22 @@ static struct hpsb_highlevel csr_highlevel = {
 	.host_reset =	host_reset,
 };
 
-static struct hpsb_address_ops map_ops = {
+const static struct hpsb_address_ops map_ops = {
 	.read = read_maps,
 };
 
-static struct hpsb_address_ops fcp_ops = {
+const static struct hpsb_address_ops fcp_ops = {
 	.write = write_fcp,
 };
 
-static struct hpsb_address_ops reg_ops = {
+const static struct hpsb_address_ops reg_ops = {
 	.read = read_regs,
 	.write = write_regs,
 	.lock = lock_regs,
 	.lock64 = lock64_regs,
 };
 
-static struct hpsb_address_ops config_rom_ops = {
+const static struct hpsb_address_ops config_rom_ops = {
 	.read = read_config_rom,
 };
 
diff --git a/drivers/ieee1394/dma.h b/drivers/ieee1394/dma.h
index 2727bcd24194..467373cab8e5 100644
--- a/drivers/ieee1394/dma.h
+++ b/drivers/ieee1394/dma.h
@@ -12,6 +12,7 @@
 
 #include <asm/types.h>
 
+struct file;
 struct pci_dev;
 struct scatterlist;
 struct vm_area_struct;
diff --git a/drivers/ieee1394/eth1394.c b/drivers/ieee1394/eth1394.c
index 20128692b339..7ae8bce27569 100644
--- a/drivers/ieee1394/eth1394.c
+++ b/drivers/ieee1394/eth1394.c
@@ -181,7 +181,7 @@ static void ether1394_remove_host(struct hpsb_host *host);
 static void ether1394_host_reset(struct hpsb_host *host);
 
 /* Function for incoming 1394 packets */
-static struct hpsb_address_ops addr_ops = {
+const static struct hpsb_address_ops addr_ops = {
 	.write =	ether1394_write,
 };
 
diff --git a/drivers/ieee1394/highlevel.c b/drivers/ieee1394/highlevel.c
index 272543a42a43..600e391c8fe7 100644
--- a/drivers/ieee1394/highlevel.c
+++ b/drivers/ieee1394/highlevel.c
@@ -320,7 +320,7 @@ void hpsb_unregister_highlevel(struct hpsb_highlevel *hl)
  */
 u64 hpsb_allocate_and_register_addrspace(struct hpsb_highlevel *hl,
 					 struct hpsb_host *host,
-					 struct hpsb_address_ops *ops,
+					 const struct hpsb_address_ops *ops,
 					 u64 size, u64 alignment,
 					 u64 start, u64 end)
 {
@@ -407,7 +407,8 @@ u64 hpsb_allocate_and_register_addrspace(struct hpsb_highlevel *hl,
  * are automatically deallocated together with the hpsb_highlevel @hl.
  */
 int hpsb_register_addrspace(struct hpsb_highlevel *hl, struct hpsb_host *host,
-			    struct hpsb_address_ops *ops, u64 start, u64 end)
+			    const struct hpsb_address_ops *ops,
+			    u64 start, u64 end)
 {
 	struct hpsb_address_serve *as;
 	struct list_head *lh;
@@ -420,7 +421,7 @@ int hpsb_register_addrspace(struct hpsb_highlevel *hl, struct hpsb_host *host,
 		return 0;
 	}
 
-	as = kmalloc(sizeof(*as), GFP_ATOMIC);
+	as = kmalloc(sizeof(*as), GFP_KERNEL);
 	if (!as)
 		return 0;
 
@@ -477,7 +478,7 @@ int hpsb_unregister_addrspace(struct hpsb_highlevel *hl, struct hpsb_host *host,
 	return retval;
 }
 
-static struct hpsb_address_ops dummy_ops;
+const static struct hpsb_address_ops dummy_ops;
 
 /* dummy address spaces as lower and upper bounds of the host's a.s. list */
 static void init_hpsb_highlevel(struct hpsb_host *host)
diff --git a/drivers/ieee1394/highlevel.h b/drivers/ieee1394/highlevel.h
index bc5d0854c17e..9dba89fc60ad 100644
--- a/drivers/ieee1394/highlevel.h
+++ b/drivers/ieee1394/highlevel.h
@@ -15,7 +15,7 @@ struct hpsb_host;
 struct hpsb_address_serve {
 	struct list_head host_list;	/* per host list */
 	struct list_head hl_list;	/* hpsb_highlevel list */
-	struct hpsb_address_ops *op;
+	const struct hpsb_address_ops *op;
 	struct hpsb_host *host;
 	u64 start;	/* first address handled, quadlet aligned */
 	u64 end;	/* first address behind, quadlet aligned */
@@ -119,11 +119,12 @@ void hpsb_unregister_highlevel(struct hpsb_highlevel *hl);
 
 u64 hpsb_allocate_and_register_addrspace(struct hpsb_highlevel *hl,
 					 struct hpsb_host *host,
-					 struct hpsb_address_ops *ops,
+					 const struct hpsb_address_ops *ops,
 					 u64 size, u64 alignment,
 					 u64 start, u64 end);
 int hpsb_register_addrspace(struct hpsb_highlevel *hl, struct hpsb_host *host,
-			    struct hpsb_address_ops *ops, u64 start, u64 end);
+			    const struct hpsb_address_ops *ops,
+			    u64 start, u64 end);
 int hpsb_unregister_addrspace(struct hpsb_highlevel *hl, struct hpsb_host *host,
 			      u64 start);
 
diff --git a/drivers/ieee1394/ieee1394_core.c b/drivers/ieee1394/ieee1394_core.c
index dcdb71a7718d..9ee0a97329bf 100644
--- a/drivers/ieee1394/ieee1394_core.c
+++ b/drivers/ieee1394/ieee1394_core.c
@@ -1314,6 +1314,7 @@ EXPORT_SYMBOL(hpsb_make_lock64packet);
 EXPORT_SYMBOL(hpsb_make_phypacket);
 EXPORT_SYMBOL(hpsb_read);
 EXPORT_SYMBOL(hpsb_write);
+EXPORT_SYMBOL(hpsb_lock);
 EXPORT_SYMBOL(hpsb_packet_success);
 
 /** highlevel.c **/
diff --git a/drivers/ieee1394/ieee1394_transactions.c b/drivers/ieee1394/ieee1394_transactions.c
index 10c3d9f8c038..24021d2f0a75 100644
--- a/drivers/ieee1394/ieee1394_transactions.c
+++ b/drivers/ieee1394/ieee1394_transactions.c
@@ -570,3 +570,32 @@ int hpsb_write(struct hpsb_host *host, nodeid_t node, unsigned int generation,
 
 	return retval;
 }
+
+int hpsb_lock(struct hpsb_host *host, nodeid_t node, unsigned int generation,
+	      u64 addr, int extcode, quadlet_t *data, quadlet_t arg)
+{
+	struct hpsb_packet *packet;
+	int retval = 0;
+
+	BUG_ON(in_interrupt());
+
+	packet = hpsb_make_lockpacket(host, node, addr, extcode, data, arg);
+	if (!packet)
+		return -ENOMEM;
+
+	packet->generation = generation;
+	retval = hpsb_send_packet_and_wait(packet);
+	if (retval < 0)
+		goto hpsb_lock_fail;
+
+	retval = hpsb_packet_success(packet);
+
+	if (retval == 0)
+		*data = packet->data[0];
+
+hpsb_lock_fail:
+	hpsb_free_tlabel(packet);
+	hpsb_free_packet(packet);
+
+	return retval;
+}
diff --git a/drivers/ieee1394/ieee1394_transactions.h b/drivers/ieee1394/ieee1394_transactions.h
index d2d5bc3546d7..20b693be14b2 100644
--- a/drivers/ieee1394/ieee1394_transactions.h
+++ b/drivers/ieee1394/ieee1394_transactions.h
@@ -30,6 +30,8 @@ int hpsb_read(struct hpsb_host *host, nodeid_t node, unsigned int generation,
 	      u64 addr, quadlet_t *buffer, size_t length);
 int hpsb_write(struct hpsb_host *host, nodeid_t node, unsigned int generation,
 	       u64 addr, quadlet_t *buffer, size_t length);
+int hpsb_lock(struct hpsb_host *host, nodeid_t node, unsigned int generation,
+	      u64 addr, int extcode, quadlet_t *data, quadlet_t arg);
 
 #ifdef HPSB_DEBUG_TLABELS
 extern spinlock_t hpsb_tlabel_lock;
diff --git a/drivers/ieee1394/iso.h b/drivers/ieee1394/iso.h
index b5de5f21ef78..c2089c093aa7 100644
--- a/drivers/ieee1394/iso.h
+++ b/drivers/ieee1394/iso.h
@@ -13,6 +13,7 @@
 #define IEEE1394_ISO_H
 
 #include <linux/spinlock_types.h>
+#include <linux/wait.h>
 #include <asm/atomic.h>
 #include <asm/types.h>
 
diff --git a/drivers/ieee1394/nodemgr.c b/drivers/ieee1394/nodemgr.c
index 9e39f73282ee..bf2904a48407 100644
--- a/drivers/ieee1394/nodemgr.c
+++ b/drivers/ieee1394/nodemgr.c
@@ -977,6 +977,9 @@ static struct unit_directory *nodemgr_process_unit_directory
 	ud->ud_kv = ud_kv;
 	ud->id = (*id)++;
 
+	/* inherit vendor_id from root directory if none exists in unit dir */
+	ud->vendor_id = ne->vendor_id;
+
 	csr1212_for_each_dir_entry(ne->csr, kv, ud_kv, dentry) {
 		switch (kv->key.id) {
 		case CSR1212_KV_ID_VENDOR:
@@ -1271,7 +1274,8 @@ static void nodemgr_update_node(struct node_entry *ne, struct csr1212_csr *csr,
 		csr1212_destroy_csr(csr);
 	}
 
-	/* Mark the node current */
+	/* Finally, mark the node current */
+	smp_wmb();
 	ne->generation = generation;
 
 	if (ne->in_limbo) {
@@ -1802,7 +1806,7 @@ void hpsb_node_fill_packet(struct node_entry *ne, struct hpsb_packet *packet)
 {
 	packet->host = ne->host;
 	packet->generation = ne->generation;
-	barrier();
+	smp_rmb();
 	packet->node_id = ne->nodeid;
 }
 
@@ -1811,7 +1815,7 @@ int hpsb_node_write(struct node_entry *ne, u64 addr,
 {
 	unsigned int generation = ne->generation;
 
-	barrier();
+	smp_rmb();
 	return hpsb_write(ne->host, ne->nodeid, generation,
 			  addr, buffer, length);
 }
diff --git a/drivers/ieee1394/nodemgr.h b/drivers/ieee1394/nodemgr.h
index 4f287a3561ba..d9391efdab28 100644
--- a/drivers/ieee1394/nodemgr.h
+++ b/drivers/ieee1394/nodemgr.h
@@ -21,9 +21,11 @@
 #define _IEEE1394_NODEMGR_H
 
 #include <linux/device.h>
+#include <asm/system.h>
 #include <asm/types.h>
 
 #include "ieee1394_core.h"
+#include "ieee1394_transactions.h"
 #include "ieee1394_types.h"
 
 struct csr1212_csr;
@@ -157,6 +159,22 @@ static inline int hpsb_node_entry_valid(struct node_entry *ne)
 void hpsb_node_fill_packet(struct node_entry *ne, struct hpsb_packet *packet);
 int hpsb_node_write(struct node_entry *ne, u64 addr,
 		    quadlet_t *buffer, size_t length);
+static inline int hpsb_node_read(struct node_entry *ne, u64 addr,
+				 quadlet_t *buffer, size_t length)
+{
+	unsigned int g = ne->generation;
+
+	smp_rmb();
+	return hpsb_read(ne->host, ne->nodeid, g, addr, buffer, length);
+}
+static inline int hpsb_node_lock(struct node_entry *ne, u64 addr, int extcode,
+				 quadlet_t *buffer, quadlet_t arg)
+{
+	unsigned int g = ne->generation;
+
+	smp_rmb();
+	return hpsb_lock(ne->host, ne->nodeid, g, addr, extcode, buffer, arg);
+}
 int nodemgr_for_each_host(void *data, int (*cb)(struct hpsb_host *, void *));
 
 int init_ieee1394_nodemgr(void);
diff --git a/drivers/ieee1394/ohci1394.c b/drivers/ieee1394/ohci1394.c
index e509e13cb7a7..066726bcb0ee 100644
--- a/drivers/ieee1394/ohci1394.c
+++ b/drivers/ieee1394/ohci1394.c
@@ -3381,6 +3381,7 @@ static int ohci1394_pci_suspend(struct pci_dev *dev, pm_message_t state)
 	ohci_devctl(ohci->host, RESET_BUS, LONG_RESET_NO_FORCE_ROOT);
 	ohci_soft_reset(ohci);
 
+	free_irq(dev->irq, ohci);
 	err = pci_save_state(dev);
 	if (err) {
 		PRINT(KERN_ERR, "pci_save_state failed with %d", err);
@@ -3421,6 +3422,13 @@ static int ohci1394_pci_resume(struct pci_dev *dev)
 	reg_write(ohci, OHCI1394_IntEventClear, 0xffffffff);
 	reg_write(ohci, OHCI1394_IntMaskClear, 0xffffffff);
 	mdelay(50);
+
+	if (request_irq(dev->irq, ohci_irq_handler, IRQF_SHARED,
+			OHCI1394_DRIVER_NAME, ohci)) {
+		PRINT_G(KERN_ERR, "Failed to allocate interrupt %d", dev->irq);
+		return -EIO;
+	}
+
 	ohci_initialize(ohci);
 
 	hpsb_resume_host(ohci->host);
diff --git a/drivers/ieee1394/raw1394.c b/drivers/ieee1394/raw1394.c
index bf7e761c12b1..bad66c65b0d6 100644
--- a/drivers/ieee1394/raw1394.c
+++ b/drivers/ieee1394/raw1394.c
@@ -90,7 +90,7 @@ static int arm_lock(struct hpsb_host *host, int nodeid, quadlet_t * store,
 static int arm_lock64(struct hpsb_host *host, int nodeid, octlet_t * store,
 		      u64 addr, octlet_t data, octlet_t arg, int ext_tcode,
 		      u16 flags);
-static struct hpsb_address_ops arm_ops = {
+const static struct hpsb_address_ops arm_ops = {
 	.read = arm_read,
 	.write = arm_write,
 	.lock = arm_lock,
diff --git a/drivers/ieee1394/sbp2.c b/drivers/ieee1394/sbp2.c
index a373c18cf7b8..ab1034ccb7fb 100644
--- a/drivers/ieee1394/sbp2.c
+++ b/drivers/ieee1394/sbp2.c
@@ -265,7 +265,7 @@ static struct hpsb_highlevel sbp2_highlevel = {
 	.host_reset	= sbp2_host_reset,
 };
 
-static struct hpsb_address_ops sbp2_ops = {
+const static struct hpsb_address_ops sbp2_ops = {
 	.write		= sbp2_handle_status_write
 };
 
@@ -275,7 +275,7 @@ static int sbp2_handle_physdma_write(struct hpsb_host *, int, int, quadlet_t *,
 static int sbp2_handle_physdma_read(struct hpsb_host *, int, quadlet_t *, u64,
 				    size_t, u16);
 
-static struct hpsb_address_ops sbp2_physdma_ops = {
+const static struct hpsb_address_ops sbp2_physdma_ops = {
 	.read		= sbp2_handle_physdma_read,
 	.write		= sbp2_handle_physdma_write,
 };
diff --git a/drivers/infiniband/core/sysfs.c b/drivers/infiniband/core/sysfs.c
index 4d1042115598..6167649376a8 100644
--- a/drivers/infiniband/core/sysfs.c
+++ b/drivers/infiniband/core/sysfs.c
@@ -786,7 +786,7 @@ int ib_device_register_sysfs(struct ib_device *device)
 	class_dev->class      = &ib_class;
 	class_dev->driver_data = device;
 	class_dev->parent     = device->dma_device;
-	strlcpy(class_dev->bus_id, device->name, BUS_ID_SIZE);
+	dev_set_name(class_dev, device->name);
 
 	INIT_LIST_HEAD(&device->port_list);
 
diff --git a/drivers/infiniband/core/ucm.c b/drivers/infiniband/core/ucm.c
index e603736682bf..51bd9669cb1f 100644
--- a/drivers/infiniband/core/ucm.c
+++ b/drivers/infiniband/core/ucm.c
@@ -1266,8 +1266,7 @@ static void ib_ucm_add_one(struct ib_device *device)
 	ucm_dev->dev.parent = device->dma_device;
 	ucm_dev->dev.devt = ucm_dev->cdev.dev;
 	ucm_dev->dev.release = ib_ucm_release_dev;
-	snprintf(ucm_dev->dev.bus_id, BUS_ID_SIZE, "ucm%d",
-		 ucm_dev->devnum);
+	dev_set_name(&ucm_dev->dev, "ucm%d", ucm_dev->devnum);
 	if (device_register(&ucm_dev->dev))
 		goto err_cdev;
 
diff --git a/drivers/infiniband/hw/ehca/ehca_classes.h b/drivers/infiniband/hw/ehca/ehca_classes.h
index 7fc35cf0cddf..c825142a2fb7 100644
--- a/drivers/infiniband/hw/ehca/ehca_classes.h
+++ b/drivers/infiniband/hw/ehca/ehca_classes.h
@@ -175,6 +175,13 @@ struct ehca_queue_map {
 	unsigned int next_wqe_idx;   /* Idx to first wqe to be flushed */
 };
 
+/* function to calculate the next index for the qmap */
+static inline unsigned int next_index(unsigned int cur_index, unsigned int limit)
+{
+	unsigned int temp = cur_index + 1;
+	return (temp == limit) ? 0 : temp;
+}
+
 struct ehca_qp {
 	union {
 		struct ib_qp ib_qp;
diff --git a/drivers/infiniband/hw/ehca/ehca_main.c b/drivers/infiniband/hw/ehca/ehca_main.c
index bec7e0249358..3b77b674cbf6 100644
--- a/drivers/infiniband/hw/ehca/ehca_main.c
+++ b/drivers/infiniband/hw/ehca/ehca_main.c
@@ -717,6 +717,7 @@ static int __devinit ehca_probe(struct of_device *dev,
 	const u64 *handle;
 	struct ib_pd *ibpd;
 	int ret, i, eq_size;
+	unsigned long flags;
 
 	handle = of_get_property(dev->node, "ibm,hca-handle", NULL);
 	if (!handle) {
@@ -830,9 +831,9 @@ static int __devinit ehca_probe(struct of_device *dev,
 		ehca_err(&shca->ib_device,
 			 "Cannot create device attributes  ret=%d", ret);
 
-	spin_lock(&shca_list_lock);
+	spin_lock_irqsave(&shca_list_lock, flags);
 	list_add(&shca->shca_list, &shca_list);
-	spin_unlock(&shca_list_lock);
+	spin_unlock_irqrestore(&shca_list_lock, flags);
 
 	return 0;
 
@@ -878,6 +879,7 @@ probe1:
 static int __devexit ehca_remove(struct of_device *dev)
 {
 	struct ehca_shca *shca = dev->dev.driver_data;
+	unsigned long flags;
 	int ret;
 
 	sysfs_remove_group(&dev->dev.kobj, &ehca_dev_attr_grp);
@@ -915,9 +917,9 @@ static int __devexit ehca_remove(struct of_device *dev)
 
 	ib_dealloc_device(&shca->ib_device);
 
-	spin_lock(&shca_list_lock);
+	spin_lock_irqsave(&shca_list_lock, flags);
 	list_del(&shca->shca_list);
-	spin_unlock(&shca_list_lock);
+	spin_unlock_irqrestore(&shca_list_lock, flags);
 
 	return ret;
 }
@@ -975,6 +977,7 @@ static int ehca_mem_notifier(struct notifier_block *nb,
 			     unsigned long action, void *data)
 {
 	static unsigned long ehca_dmem_warn_time;
+	unsigned long flags;
 
 	switch (action) {
 	case MEM_CANCEL_OFFLINE:
@@ -985,12 +988,12 @@ static int ehca_mem_notifier(struct notifier_block *nb,
 	case MEM_GOING_ONLINE:
 	case MEM_GOING_OFFLINE:
 		/* only ok if no hca is attached to the lpar */
-		spin_lock(&shca_list_lock);
+		spin_lock_irqsave(&shca_list_lock, flags);
 		if (list_empty(&shca_list)) {
-			spin_unlock(&shca_list_lock);
+			spin_unlock_irqrestore(&shca_list_lock, flags);
 			return NOTIFY_OK;
 		} else {
-			spin_unlock(&shca_list_lock);
+			spin_unlock_irqrestore(&shca_list_lock, flags);
 			if (printk_timed_ratelimit(&ehca_dmem_warn_time,
 						   30 * 1000))
 				ehca_gen_err("DMEM operations are not allowed"
diff --git a/drivers/infiniband/hw/ehca/ehca_qp.c b/drivers/infiniband/hw/ehca/ehca_qp.c
index cadbf0cdd910..f161cf173dbe 100644
--- a/drivers/infiniband/hw/ehca/ehca_qp.c
+++ b/drivers/infiniband/hw/ehca/ehca_qp.c
@@ -1138,14 +1138,14 @@ static int calc_left_cqes(u64 wqe_p, struct ipz_queue *ipz_queue,
 		return -EFAULT;
 	}
 
-	tail_idx = (qmap->tail + 1) % qmap->entries;
+	tail_idx = next_index(qmap->tail, qmap->entries);
 	wqe_idx = q_ofs / ipz_queue->qe_size;
 
 	/* check all processed wqes, whether a cqe is requested or not */
 	while (tail_idx != wqe_idx) {
 		if (qmap->map[tail_idx].cqe_req)
 			qmap->left_to_poll++;
-		tail_idx = (tail_idx + 1) % qmap->entries;
+		tail_idx = next_index(tail_idx, qmap->entries);
 	}
 	/* save index in queue, where we have to start flushing */
 	qmap->next_wqe_idx = wqe_idx;
@@ -1195,14 +1195,14 @@ static int check_for_left_cqes(struct ehca_qp *my_qp, struct ehca_shca *shca)
 	} else {
 		spin_lock_irqsave(&my_qp->send_cq->spinlock, flags);
 		my_qp->sq_map.left_to_poll = 0;
-		my_qp->sq_map.next_wqe_idx = (my_qp->sq_map.tail + 1) %
-						my_qp->sq_map.entries;
+		my_qp->sq_map.next_wqe_idx = next_index(my_qp->sq_map.tail,
+							my_qp->sq_map.entries);
 		spin_unlock_irqrestore(&my_qp->send_cq->spinlock, flags);
 
 		spin_lock_irqsave(&my_qp->recv_cq->spinlock, flags);
 		my_qp->rq_map.left_to_poll = 0;
-		my_qp->rq_map.next_wqe_idx = (my_qp->rq_map.tail + 1) %
-						my_qp->rq_map.entries;
+		my_qp->rq_map.next_wqe_idx = next_index(my_qp->rq_map.tail,
+							my_qp->rq_map.entries);
 		spin_unlock_irqrestore(&my_qp->recv_cq->spinlock, flags);
 	}
 
diff --git a/drivers/infiniband/hw/ehca/ehca_reqs.c b/drivers/infiniband/hw/ehca/ehca_reqs.c
index 00a648f4316c..c7112686782f 100644
--- a/drivers/infiniband/hw/ehca/ehca_reqs.c
+++ b/drivers/infiniband/hw/ehca/ehca_reqs.c
@@ -726,13 +726,13 @@ repoll:
 		 * set left_to_poll to 0 because in error state, we will not
 		 * get any additional CQEs
 		 */
-		my_qp->sq_map.next_wqe_idx = (my_qp->sq_map.tail + 1) %
-						my_qp->sq_map.entries;
+		my_qp->sq_map.next_wqe_idx = next_index(my_qp->sq_map.tail,
+							my_qp->sq_map.entries);
 		my_qp->sq_map.left_to_poll = 0;
 		ehca_add_to_err_list(my_qp, 1);
 
-		my_qp->rq_map.next_wqe_idx = (my_qp->rq_map.tail + 1) %
-						my_qp->rq_map.entries;
+		my_qp->rq_map.next_wqe_idx = next_index(my_qp->rq_map.tail,
+							my_qp->rq_map.entries);
 		my_qp->rq_map.left_to_poll = 0;
 		if (HAS_RQ(my_qp))
 			ehca_add_to_err_list(my_qp, 0);
@@ -860,9 +860,8 @@ static int generate_flush_cqes(struct ehca_qp *my_qp, struct ib_cq *cq,
 
 		/* mark as reported and advance next_wqe pointer */
 		qmap_entry->reported = 1;
-		qmap->next_wqe_idx++;
-		if (qmap->next_wqe_idx == qmap->entries)
-			qmap->next_wqe_idx = 0;
+		qmap->next_wqe_idx = next_index(qmap->next_wqe_idx,
+						qmap->entries);
 		qmap_entry = &qmap->map[qmap->next_wqe_idx];
 
 		wc++; nr++;
diff --git a/drivers/infiniband/hw/ipath/ipath_driver.c b/drivers/infiniband/hw/ipath/ipath_driver.c
index ad0aab60b051..69c0ce321b4e 100644
--- a/drivers/infiniband/hw/ipath/ipath_driver.c
+++ b/drivers/infiniband/hw/ipath/ipath_driver.c
@@ -661,6 +661,8 @@ bail:
 static void __devexit cleanup_device(struct ipath_devdata *dd)
 {
 	int port;
+	struct ipath_portdata **tmp;
+	unsigned long flags;
 
 	if (*dd->ipath_statusp & IPATH_STATUS_CHIP_PRESENT) {
 		/* can't do anything more with chip; needs re-init */
@@ -742,20 +744,21 @@ static void __devexit cleanup_device(struct ipath_devdata *dd)
 
 	/*
 	 * free any resources still in use (usually just kernel ports)
-	 * at unload; we do for portcnt, not cfgports, because cfgports
-	 * could have changed while we were loaded.
+	 * at unload; we do for portcnt, because that's what we allocate.
+	 * We acquire lock to be really paranoid that ipath_pd isn't being
+	 * accessed from some interrupt-related code (that should not happen,
+	 * but best to be sure).
 	 */
+	spin_lock_irqsave(&dd->ipath_uctxt_lock, flags);
+	tmp = dd->ipath_pd;
+	dd->ipath_pd = NULL;
+	spin_unlock_irqrestore(&dd->ipath_uctxt_lock, flags);
 	for (port = 0; port < dd->ipath_portcnt; port++) {
-		struct ipath_portdata *pd = dd->ipath_pd[port];
-		dd->ipath_pd[port] = NULL;
+		struct ipath_portdata *pd = tmp[port];
+		tmp[port] = NULL; /* debugging paranoia */
 		ipath_free_pddata(dd, pd);
 	}
-	kfree(dd->ipath_pd);
-	/*
-	 * debuggability, in case some cleanup path tries to use it
-	 * after this
-	 */
-	dd->ipath_pd = NULL;
+	kfree(tmp);
 }
 
 static void __devexit ipath_remove_one(struct pci_dev *pdev)
@@ -2586,6 +2589,7 @@ int ipath_reset_device(int unit)
 {
 	int ret, i;
 	struct ipath_devdata *dd = ipath_lookup(unit);
+	unsigned long flags;
 
 	if (!dd) {
 		ret = -ENODEV;
@@ -2611,18 +2615,21 @@ int ipath_reset_device(int unit)
 		goto bail;
 	}
 
+	spin_lock_irqsave(&dd->ipath_uctxt_lock, flags);
 	if (dd->ipath_pd)
 		for (i = 1; i < dd->ipath_cfgports; i++) {
-			if (dd->ipath_pd[i] && dd->ipath_pd[i]->port_cnt) {
-				ipath_dbg("unit %u port %d is in use "
-					  "(PID %u cmd %s), can't reset\n",
-					  unit, i,
-					  pid_nr(dd->ipath_pd[i]->port_pid),
-					  dd->ipath_pd[i]->port_comm);
-				ret = -EBUSY;
-				goto bail;
-			}
+			if (!dd->ipath_pd[i] || !dd->ipath_pd[i]->port_cnt)
+				continue;
+			spin_unlock_irqrestore(&dd->ipath_uctxt_lock, flags);
+			ipath_dbg("unit %u port %d is in use "
+				  "(PID %u cmd %s), can't reset\n",
+				  unit, i,
+				  pid_nr(dd->ipath_pd[i]->port_pid),
+				  dd->ipath_pd[i]->port_comm);
+			ret = -EBUSY;
+			goto bail;
 		}
+	spin_unlock_irqrestore(&dd->ipath_uctxt_lock, flags);
 
 	if (dd->ipath_flags & IPATH_HAS_SEND_DMA)
 		teardown_sdma(dd);
@@ -2656,9 +2663,12 @@ static int ipath_signal_procs(struct ipath_devdata *dd, int sig)
 {
 	int i, sub, any = 0;
 	struct pid *pid;
+	unsigned long flags;
 
 	if (!dd->ipath_pd)
 		return 0;
+
+	spin_lock_irqsave(&dd->ipath_uctxt_lock, flags);
 	for (i = 1; i < dd->ipath_cfgports; i++) {
 		if (!dd->ipath_pd[i] || !dd->ipath_pd[i]->port_cnt)
 			continue;
@@ -2682,6 +2692,7 @@ static int ipath_signal_procs(struct ipath_devdata *dd, int sig)
 			any++;
 		}
 	}
+	spin_unlock_irqrestore(&dd->ipath_uctxt_lock, flags);
 	return any;
 }
 
diff --git a/drivers/infiniband/hw/ipath/ipath_file_ops.c b/drivers/infiniband/hw/ipath/ipath_file_ops.c
index 1af1f3a907c6..239d4e8068ac 100644
--- a/drivers/infiniband/hw/ipath/ipath_file_ops.c
+++ b/drivers/infiniband/hw/ipath/ipath_file_ops.c
@@ -223,8 +223,13 @@ static int ipath_get_base_info(struct file *fp,
 			(unsigned long long) kinfo->spi_subport_rcvhdr_base);
 	}
 
-	kinfo->spi_pioindex = (kinfo->spi_piobufbase - dd->ipath_piobufbase) /
-		dd->ipath_palign;
+	/*
+	 * All user buffers are 2KB buffers.  If we ever support
+	 * giving 4KB buffers to user processes, this will need some
+	 * work.
+	 */
+	kinfo->spi_pioindex = (kinfo->spi_piobufbase -
+		(dd->ipath_piobufbase & 0xffffffff)) / dd->ipath_palign;
 	kinfo->spi_pioalign = dd->ipath_palign;
 
 	kinfo->spi_qpair = IPATH_KD_QP;
@@ -2041,7 +2046,9 @@ static int ipath_close(struct inode *in, struct file *fp)
 	struct ipath_filedata *fd;
 	struct ipath_portdata *pd;
 	struct ipath_devdata *dd;
+	unsigned long flags;
 	unsigned port;
+	struct pid *pid;
 
 	ipath_cdbg(VERBOSE, "close on dev %lx, private data %p\n",
 		   (long)in->i_rdev, fp->private_data);
@@ -2074,14 +2081,13 @@ static int ipath_close(struct inode *in, struct file *fp)
 		mutex_unlock(&ipath_mutex);
 		goto bail;
 	}
+	/* early; no interrupt users after this */
+	spin_lock_irqsave(&dd->ipath_uctxt_lock, flags);
 	port = pd->port_port;
-
-	if (pd->port_hdrqfull) {
-		ipath_cdbg(PROC, "%s[%u] had %u rcvhdrqfull errors "
-			   "during run\n", pd->port_comm, pid_nr(pd->port_pid),
-			   pd->port_hdrqfull);
-		pd->port_hdrqfull = 0;
-	}
+	dd->ipath_pd[port] = NULL;
+	pid = pd->port_pid;
+	pd->port_pid = NULL;
+	spin_unlock_irqrestore(&dd->ipath_uctxt_lock, flags);
 
 	if (pd->port_rcvwait_to || pd->port_piowait_to
 	    || pd->port_rcvnowait || pd->port_pionowait) {
@@ -2138,13 +2144,11 @@ static int ipath_close(struct inode *in, struct file *fp)
 			unlock_expected_tids(pd);
 		ipath_stats.sps_ports--;
 		ipath_cdbg(PROC, "%s[%u] closed port %u:%u\n",
-			   pd->port_comm, pid_nr(pd->port_pid),
+			   pd->port_comm, pid_nr(pid),
 			   dd->ipath_unit, port);
 	}
 
-	put_pid(pd->port_pid);
-	pd->port_pid = NULL;
-	dd->ipath_pd[pd->port_port] = NULL; /* before releasing mutex */
+	put_pid(pid);
 	mutex_unlock(&ipath_mutex);
 	ipath_free_pddata(dd, pd); /* after releasing the mutex */
 
diff --git a/drivers/infiniband/hw/ipath/ipath_fs.c b/drivers/infiniband/hw/ipath/ipath_fs.c
index 8bb5170b4e41..53912c327bfe 100644
--- a/drivers/infiniband/hw/ipath/ipath_fs.c
+++ b/drivers/infiniband/hw/ipath/ipath_fs.c
@@ -86,7 +86,7 @@ static int create_file(const char *name, mode_t mode,
 	*dentry = NULL;
 	mutex_lock(&parent->d_inode->i_mutex);
 	*dentry = lookup_one_len(name, parent, strlen(name));
-	if (!IS_ERR(dentry))
+	if (!IS_ERR(*dentry))
 		error = ipathfs_mknod(parent->d_inode, *dentry,
 				      mode, fops, data);
 	else
diff --git a/drivers/infiniband/hw/ipath/ipath_iba6120.c b/drivers/infiniband/hw/ipath/ipath_iba6120.c
index 421cc2af891f..fbf8c5379ea8 100644
--- a/drivers/infiniband/hw/ipath/ipath_iba6120.c
+++ b/drivers/infiniband/hw/ipath/ipath_iba6120.c
@@ -721,6 +721,12 @@ static int ipath_pe_bringup_serdes(struct ipath_devdata *dd)
 				 INFINIPATH_HWE_SERDESPLLFAILED);
 	}
 
+	dd->ibdeltainprog = 1;
+	dd->ibsymsnap =
+	     ipath_read_creg32(dd, dd->ipath_cregs->cr_ibsymbolerrcnt);
+	dd->iblnkerrsnap =
+	     ipath_read_creg32(dd, dd->ipath_cregs->cr_iblinkerrrecovcnt);
+
 	val = ipath_read_kreg64(dd, dd->ipath_kregs->kr_serdesconfig0);
 	config1 = ipath_read_kreg64(dd, dd->ipath_kregs->kr_serdesconfig1);
 
@@ -810,6 +816,36 @@ static void ipath_pe_quiet_serdes(struct ipath_devdata *dd)
 {
 	u64 val = ipath_read_kreg64(dd, dd->ipath_kregs->kr_serdesconfig0);
 
+	if (dd->ibsymdelta || dd->iblnkerrdelta ||
+	    dd->ibdeltainprog) {
+		u64 diagc;
+		/* enable counter writes */
+		diagc = ipath_read_kreg64(dd, dd->ipath_kregs->kr_hwdiagctrl);
+		ipath_write_kreg(dd, dd->ipath_kregs->kr_hwdiagctrl,
+				 diagc | INFINIPATH_DC_COUNTERWREN);
+
+		if (dd->ibsymdelta || dd->ibdeltainprog) {
+			val = ipath_read_creg32(dd,
+					dd->ipath_cregs->cr_ibsymbolerrcnt);
+			if (dd->ibdeltainprog)
+				val -= val - dd->ibsymsnap;
+			val -= dd->ibsymdelta;
+			ipath_write_creg(dd,
+				  dd->ipath_cregs->cr_ibsymbolerrcnt, val);
+		}
+		if (dd->iblnkerrdelta || dd->ibdeltainprog) {
+			val = ipath_read_creg32(dd,
+					dd->ipath_cregs->cr_iblinkerrrecovcnt);
+			if (dd->ibdeltainprog)
+				val -= val - dd->iblnkerrsnap;
+			val -= dd->iblnkerrdelta;
+			ipath_write_creg(dd,
+				   dd->ipath_cregs->cr_iblinkerrrecovcnt, val);
+	     }
+
+	     /* and disable counter writes */
+	     ipath_write_kreg(dd, dd->ipath_kregs->kr_hwdiagctrl, diagc);
+	}
 	val |= INFINIPATH_SERDC0_TXIDLE;
 	ipath_dbg("Setting TxIdleEn on serdes (config0 = %llx)\n",
 		  (unsigned long long) val);
@@ -1749,6 +1785,31 @@ static void ipath_pe_config_jint(struct ipath_devdata *dd, u16 a, u16 b)
 
 static int ipath_pe_ib_updown(struct ipath_devdata *dd, int ibup, u64 ibcs)
 {
+	if (ibup) {
+		if (dd->ibdeltainprog) {
+			dd->ibdeltainprog = 0;
+			dd->ibsymdelta +=
+				ipath_read_creg32(dd,
+				  dd->ipath_cregs->cr_ibsymbolerrcnt) -
+				dd->ibsymsnap;
+			dd->iblnkerrdelta +=
+				ipath_read_creg32(dd,
+				  dd->ipath_cregs->cr_iblinkerrrecovcnt) -
+				dd->iblnkerrsnap;
+		}
+	} else {
+		dd->ipath_lli_counter = 0;
+		if (!dd->ibdeltainprog) {
+			dd->ibdeltainprog = 1;
+			dd->ibsymsnap =
+				ipath_read_creg32(dd,
+				  dd->ipath_cregs->cr_ibsymbolerrcnt);
+			dd->iblnkerrsnap =
+				ipath_read_creg32(dd,
+				  dd->ipath_cregs->cr_iblinkerrrecovcnt);
+		}
+	}
+
 	ipath_setup_pe_setextled(dd, ipath_ib_linkstate(dd, ibcs),
 		ipath_ib_linktrstate(dd, ibcs));
 	return 0;
diff --git a/drivers/infiniband/hw/ipath/ipath_iba7220.c b/drivers/infiniband/hw/ipath/ipath_iba7220.c
index 9839e20119bc..b2a9d4c155d1 100644
--- a/drivers/infiniband/hw/ipath/ipath_iba7220.c
+++ b/drivers/infiniband/hw/ipath/ipath_iba7220.c
@@ -951,6 +951,12 @@ static int ipath_7220_bringup_serdes(struct ipath_devdata *dd)
 				 INFINIPATH_HWE_SERDESPLLFAILED);
 	}
 
+	dd->ibdeltainprog = 1;
+	dd->ibsymsnap =
+	     ipath_read_creg32(dd, dd->ipath_cregs->cr_ibsymbolerrcnt);
+	dd->iblnkerrsnap =
+	     ipath_read_creg32(dd, dd->ipath_cregs->cr_iblinkerrrecovcnt);
+
 	if (!dd->ipath_ibcddrctrl) {
 		/* not on re-init after reset */
 		dd->ipath_ibcddrctrl =
@@ -1084,6 +1090,37 @@ static void ipath_7220_config_jint(struct ipath_devdata *dd,
 static void ipath_7220_quiet_serdes(struct ipath_devdata *dd)
 {
 	u64 val;
+	if (dd->ibsymdelta || dd->iblnkerrdelta ||
+	    dd->ibdeltainprog) {
+		u64 diagc;
+		/* enable counter writes */
+		diagc = ipath_read_kreg64(dd, dd->ipath_kregs->kr_hwdiagctrl);
+		ipath_write_kreg(dd, dd->ipath_kregs->kr_hwdiagctrl,
+				 diagc | INFINIPATH_DC_COUNTERWREN);
+
+		if (dd->ibsymdelta || dd->ibdeltainprog) {
+			val = ipath_read_creg32(dd,
+					dd->ipath_cregs->cr_ibsymbolerrcnt);
+			if (dd->ibdeltainprog)
+				val -= val - dd->ibsymsnap;
+			val -= dd->ibsymdelta;
+			ipath_write_creg(dd,
+				  dd->ipath_cregs->cr_ibsymbolerrcnt, val);
+		}
+		if (dd->iblnkerrdelta || dd->ibdeltainprog) {
+			val = ipath_read_creg32(dd,
+					dd->ipath_cregs->cr_iblinkerrrecovcnt);
+			if (dd->ibdeltainprog)
+				val -= val - dd->iblnkerrsnap;
+			val -= dd->iblnkerrdelta;
+			ipath_write_creg(dd,
+				   dd->ipath_cregs->cr_iblinkerrrecovcnt, val);
+	     }
+
+	     /* and disable counter writes */
+	     ipath_write_kreg(dd, dd->ipath_kregs->kr_hwdiagctrl, diagc);
+	}
+
 	dd->ipath_flags &= ~IPATH_IB_AUTONEG_INPROG;
 	wake_up(&dd->ipath_autoneg_wait);
 	cancel_delayed_work(&dd->ipath_autoneg_work);
@@ -2325,7 +2362,7 @@ static void try_auto_neg(struct ipath_devdata *dd)
 
 static int ipath_7220_ib_updown(struct ipath_devdata *dd, int ibup, u64 ibcs)
 {
-	int ret = 0;
+	int ret = 0, symadj = 0;
 	u32 ltstate = ipath_ib_linkstate(dd, ibcs);
 
 	dd->ipath_link_width_active =
@@ -2368,6 +2405,13 @@ static int ipath_7220_ib_updown(struct ipath_devdata *dd, int ibup, u64 ibcs)
 			ipath_dbg("DDR negotiation try, %u/%u\n",
 				dd->ipath_autoneg_tries,
 				IPATH_AUTONEG_TRIES);
+			if (!dd->ibdeltainprog) {
+				dd->ibdeltainprog = 1;
+				dd->ibsymsnap = ipath_read_creg32(dd,
+					dd->ipath_cregs->cr_ibsymbolerrcnt);
+				dd->iblnkerrsnap = ipath_read_creg32(dd,
+					dd->ipath_cregs->cr_iblinkerrrecovcnt);
+			}
 			try_auto_neg(dd);
 			ret = 1; /* no other IB status change processing */
 		} else if ((dd->ipath_flags & IPATH_IB_AUTONEG_INPROG)
@@ -2388,6 +2432,7 @@ static int ipath_7220_ib_updown(struct ipath_devdata *dd, int ibup, u64 ibcs)
 				set_speed_fast(dd,
 					dd->ipath_link_speed_enabled);
 				wake_up(&dd->ipath_autoneg_wait);
+				symadj = 1;
 			} else if (dd->ipath_flags & IPATH_IB_AUTONEG_FAILED) {
 				/*
 				 * clear autoneg failure flag, and do setup
@@ -2403,22 +2448,28 @@ static int ipath_7220_ib_updown(struct ipath_devdata *dd, int ibup, u64 ibcs)
 					IBA7220_IBC_IBTA_1_2_MASK;
 				ipath_write_kreg(dd,
 					IPATH_KREG_OFFSET(IBNCModeCtrl), 0);
+				symadj = 1;
 			}
 		}
 		/*
-		 * if we are in 1X, and are in autoneg width, it
-		 * could be due to an xgxs problem, so if we haven't
+		 * if we are in 1X on rev1 only, and are in autoneg width,
+		 * it could be due to an xgxs problem, so if we haven't
 		 * already tried, try twice to get to 4X; if we
 		 * tried, and couldn't, report it, since it will
 		 * probably not be what is desired.
 		 */
-		if ((dd->ipath_link_width_enabled & (IB_WIDTH_1X |
+		if (dd->ipath_minrev == 1 &&
+		    (dd->ipath_link_width_enabled & (IB_WIDTH_1X |
 			IB_WIDTH_4X)) == (IB_WIDTH_1X | IB_WIDTH_4X)
 			&& dd->ipath_link_width_active == IB_WIDTH_1X
 			&& dd->ipath_x1_fix_tries < 3) {
-			if (++dd->ipath_x1_fix_tries == 3)
+		     if (++dd->ipath_x1_fix_tries == 3) {
 				dev_info(&dd->pcidev->dev,
 					"IB link is in 1X mode\n");
+				if (!(dd->ipath_flags &
+				      IPATH_IB_AUTONEG_INPROG))
+					symadj = 1;
+		     }
 			else {
 				ipath_cdbg(VERBOSE, "IB 1X in "
 					"auto-width, try %u to be "
@@ -2429,7 +2480,8 @@ static int ipath_7220_ib_updown(struct ipath_devdata *dd, int ibup, u64 ibcs)
 				dd->ipath_f_xgxs_reset(dd);
 				ret = 1; /* skip other processing */
 			}
-		}
+		} else if (!(dd->ipath_flags & IPATH_IB_AUTONEG_INPROG))
+			symadj = 1;
 
 		if (!ret) {
 			dd->delay_mult = rate_to_delay
@@ -2440,6 +2492,25 @@ static int ipath_7220_ib_updown(struct ipath_devdata *dd, int ibup, u64 ibcs)
 		}
 	}
 
+	if (symadj) {
+		if (dd->ibdeltainprog) {
+			dd->ibdeltainprog = 0;
+			dd->ibsymdelta += ipath_read_creg32(dd,
+				dd->ipath_cregs->cr_ibsymbolerrcnt) -
+				dd->ibsymsnap;
+			dd->iblnkerrdelta += ipath_read_creg32(dd,
+				dd->ipath_cregs->cr_iblinkerrrecovcnt) -
+				dd->iblnkerrsnap;
+		}
+	} else if (!ibup && !dd->ibdeltainprog
+		   && !(dd->ipath_flags & IPATH_IB_AUTONEG_INPROG)) {
+		dd->ibdeltainprog = 1;
+		dd->ibsymsnap =	ipath_read_creg32(dd,
+				     dd->ipath_cregs->cr_ibsymbolerrcnt);
+		dd->iblnkerrsnap = ipath_read_creg32(dd,
+				     dd->ipath_cregs->cr_iblinkerrrecovcnt);
+	}
+
 	if (!ret)
 		ipath_setup_7220_setextled(dd, ipath_ib_linkstate(dd, ibcs),
 			ltstate);
diff --git a/drivers/infiniband/hw/ipath/ipath_init_chip.c b/drivers/infiniband/hw/ipath/ipath_init_chip.c
index 3e5baa43fc82..64aeefbd2a5d 100644
--- a/drivers/infiniband/hw/ipath/ipath_init_chip.c
+++ b/drivers/infiniband/hw/ipath/ipath_init_chip.c
@@ -229,6 +229,7 @@ static int init_chip_first(struct ipath_devdata *dd)
 	spin_lock_init(&dd->ipath_kernel_tid_lock);
 	spin_lock_init(&dd->ipath_user_tid_lock);
 	spin_lock_init(&dd->ipath_sendctrl_lock);
+	spin_lock_init(&dd->ipath_uctxt_lock);
 	spin_lock_init(&dd->ipath_sdma_lock);
 	spin_lock_init(&dd->ipath_gpio_lock);
 	spin_lock_init(&dd->ipath_eep_st_lock);
diff --git a/drivers/infiniband/hw/ipath/ipath_kernel.h b/drivers/infiniband/hw/ipath/ipath_kernel.h
index 0bd8bcb184a1..6ba4861dd6ac 100644
--- a/drivers/infiniband/hw/ipath/ipath_kernel.h
+++ b/drivers/infiniband/hw/ipath/ipath_kernel.h
@@ -355,6 +355,19 @@ struct ipath_devdata {
 	/* errors masked because they occur too fast */
 	ipath_err_t ipath_maskederrs;
 	u64 ipath_lastlinkrecov; /* link recoveries at last ACTIVE */
+	/* these 5 fields are used to establish deltas for IB Symbol
+	 * errors and linkrecovery errors. They can be reported on
+	 * some chips during link negotiation prior to INIT, and with
+	 * DDR when faking DDR negotiations with non-IBTA switches.
+	 * The chip counters are adjusted at driver unload if there is
+	 * a non-zero delta.
+	 */
+	u64 ibdeltainprog;
+	u64 ibsymdelta;
+	u64 ibsymsnap;
+	u64 iblnkerrdelta;
+	u64 iblnkerrsnap;
+
 	/* time in jiffies at which to re-enable maskederrs */
 	unsigned long ipath_unmasktime;
 	/* count of egrfull errors, combined for all ports */
@@ -464,6 +477,8 @@ struct ipath_devdata {
 	spinlock_t ipath_kernel_tid_lock;
 	spinlock_t ipath_user_tid_lock;
 	spinlock_t ipath_sendctrl_lock;
+	/* around ipath_pd and (user ports) port_cnt use (intr vs free) */
+	spinlock_t ipath_uctxt_lock;
 
 	/*
 	 * IPATH_STATUS_*,
diff --git a/drivers/infiniband/hw/ipath/ipath_keys.c b/drivers/infiniband/hw/ipath/ipath_keys.c
index 8f32b17a5eed..c0e933fec218 100644
--- a/drivers/infiniband/hw/ipath/ipath_keys.c
+++ b/drivers/infiniband/hw/ipath/ipath_keys.c
@@ -132,6 +132,7 @@ int ipath_lkey_ok(struct ipath_qp *qp, struct ipath_sge *isge,
 	 * (see ipath_get_dma_mr and ipath_dma.c).
 	 */
 	if (sge->lkey == 0) {
+		/* always a kernel port, no locking needed */
 		struct ipath_pd *pd = to_ipd(qp->ibqp.pd);
 
 		if (pd->user) {
@@ -211,6 +212,7 @@ int ipath_rkey_ok(struct ipath_qp *qp, struct ipath_sge_state *ss,
 	 * (see ipath_get_dma_mr and ipath_dma.c).
 	 */
 	if (rkey == 0) {
+		/* always a kernel port, no locking needed */
 		struct ipath_pd *pd = to_ipd(qp->ibqp.pd);
 
 		if (pd->user) {
diff --git a/drivers/infiniband/hw/ipath/ipath_mad.c b/drivers/infiniband/hw/ipath/ipath_mad.c
index be4fc9ada8e7..17a123197477 100644
--- a/drivers/infiniband/hw/ipath/ipath_mad.c
+++ b/drivers/infiniband/hw/ipath/ipath_mad.c
@@ -348,6 +348,7 @@ bail:
  */
 static int get_pkeys(struct ipath_devdata *dd, u16 * pkeys)
 {
+	/* always a kernel port, no locking needed */
 	struct ipath_portdata *pd = dd->ipath_pd[0];
 
 	memcpy(pkeys, pd->port_pkeys, sizeof(pd->port_pkeys));
@@ -730,6 +731,7 @@ static int set_pkeys(struct ipath_devdata *dd, u16 *pkeys)
 	int i;
 	int changed = 0;
 
+	/* always a kernel port, no locking needed */
 	pd = dd->ipath_pd[0];
 
 	for (i = 0; i < ARRAY_SIZE(pd->port_pkeys); i++) {
diff --git a/drivers/infiniband/hw/ipath/ipath_qp.c b/drivers/infiniband/hw/ipath/ipath_qp.c
index 4715911101e4..3a5a89b609c4 100644
--- a/drivers/infiniband/hw/ipath/ipath_qp.c
+++ b/drivers/infiniband/hw/ipath/ipath_qp.c
@@ -745,6 +745,7 @@ struct ib_qp *ipath_create_qp(struct ib_pd *ibpd,
 	struct ipath_swqe *swq = NULL;
 	struct ipath_ibdev *dev;
 	size_t sz;
+	size_t sg_list_sz;
 	struct ib_qp *ret;
 
 	if (init_attr->create_flags) {
@@ -789,19 +790,31 @@ struct ib_qp *ipath_create_qp(struct ib_pd *ibpd,
 			goto bail;
 		}
 		sz = sizeof(*qp);
+		sg_list_sz = 0;
 		if (init_attr->srq) {
 			struct ipath_srq *srq = to_isrq(init_attr->srq);
 
-			sz += sizeof(*qp->r_sg_list) *
-				srq->rq.max_sge;
-		} else
-			sz += sizeof(*qp->r_sg_list) *
-				init_attr->cap.max_recv_sge;
-		qp = kmalloc(sz, GFP_KERNEL);
+			if (srq->rq.max_sge > 1)
+				sg_list_sz = sizeof(*qp->r_sg_list) *
+					(srq->rq.max_sge - 1);
+		} else if (init_attr->cap.max_recv_sge > 1)
+			sg_list_sz = sizeof(*qp->r_sg_list) *
+				(init_attr->cap.max_recv_sge - 1);
+		qp = kmalloc(sz + sg_list_sz, GFP_KERNEL);
 		if (!qp) {
 			ret = ERR_PTR(-ENOMEM);
 			goto bail_swq;
 		}
+		if (sg_list_sz && (init_attr->qp_type == IB_QPT_UD ||
+		    init_attr->qp_type == IB_QPT_SMI ||
+		    init_attr->qp_type == IB_QPT_GSI)) {
+			qp->r_ud_sg_list = kmalloc(sg_list_sz, GFP_KERNEL);
+			if (!qp->r_ud_sg_list) {
+				ret = ERR_PTR(-ENOMEM);
+				goto bail_qp;
+			}
+		} else
+			qp->r_ud_sg_list = NULL;
 		if (init_attr->srq) {
 			sz = 0;
 			qp->r_rq.size = 0;
@@ -818,7 +831,7 @@ struct ib_qp *ipath_create_qp(struct ib_pd *ibpd,
 					      qp->r_rq.size * sz);
 			if (!qp->r_rq.wq) {
 				ret = ERR_PTR(-ENOMEM);
-				goto bail_qp;
+				goto bail_sg_list;
 			}
 		}
 
@@ -848,7 +861,7 @@ struct ib_qp *ipath_create_qp(struct ib_pd *ibpd,
 		if (err) {
 			ret = ERR_PTR(err);
 			vfree(qp->r_rq.wq);
-			goto bail_qp;
+			goto bail_sg_list;
 		}
 		qp->ip = NULL;
 		qp->s_tx = NULL;
@@ -925,6 +938,8 @@ bail_ip:
 		vfree(qp->r_rq.wq);
 	ipath_free_qp(&dev->qp_table, qp);
 	free_qpn(&dev->qp_table, qp->ibqp.qp_num);
+bail_sg_list:
+	kfree(qp->r_ud_sg_list);
 bail_qp:
 	kfree(qp);
 bail_swq:
@@ -989,6 +1004,7 @@ int ipath_destroy_qp(struct ib_qp *ibqp)
 		kref_put(&qp->ip->ref, ipath_release_mmap_info);
 	else
 		vfree(qp->r_rq.wq);
+	kfree(qp->r_ud_sg_list);
 	vfree(qp->s_wq);
 	kfree(qp);
 	return 0;
diff --git a/drivers/infiniband/hw/ipath/ipath_rc.c b/drivers/infiniband/hw/ipath/ipath_rc.c
index 7b93cda1a4bd..9170710b950d 100644
--- a/drivers/infiniband/hw/ipath/ipath_rc.c
+++ b/drivers/infiniband/hw/ipath/ipath_rc.c
@@ -573,9 +573,8 @@ int ipath_make_rc_req(struct ipath_qp *qp)
 		ohdr->u.rc.reth.length = cpu_to_be32(qp->s_len);
 		qp->s_state = OP(RDMA_READ_REQUEST);
 		hwords += sizeof(ohdr->u.rc.reth) / sizeof(u32);
-		bth2 = qp->s_psn++ & IPATH_PSN_MASK;
-		if (ipath_cmp24(qp->s_psn, qp->s_next_psn) > 0)
-			qp->s_next_psn = qp->s_psn;
+		bth2 = qp->s_psn & IPATH_PSN_MASK;
+		qp->s_psn = wqe->lpsn + 1;
 		ss = NULL;
 		len = 0;
 		qp->s_cur++;
diff --git a/drivers/infiniband/hw/ipath/ipath_sdma.c b/drivers/infiniband/hw/ipath/ipath_sdma.c
index 284c9bca517e..8e255adf5d9b 100644
--- a/drivers/infiniband/hw/ipath/ipath_sdma.c
+++ b/drivers/infiniband/hw/ipath/ipath_sdma.c
@@ -698,10 +698,8 @@ retry:
 
 	addr = dma_map_single(&dd->pcidev->dev, tx->txreq.map_addr,
 			      tx->map_len, DMA_TO_DEVICE);
-	if (dma_mapping_error(&dd->pcidev->dev, addr)) {
-		ret = -EIO;
-		goto unlock;
-	}
+	if (dma_mapping_error(&dd->pcidev->dev, addr))
+		goto ioerr;
 
 	dwoffset = tx->map_len >> 2;
 	make_sdma_desc(dd, sdmadesc, (u64) addr, dwoffset, 0);
@@ -741,6 +739,8 @@ retry:
 		dw = (len + 3) >> 2;
 		addr = dma_map_single(&dd->pcidev->dev, sge->vaddr, dw << 2,
 				      DMA_TO_DEVICE);
+		if (dma_mapping_error(&dd->pcidev->dev, addr))
+			goto unmap;
 		make_sdma_desc(dd, sdmadesc, (u64) addr, dw, dwoffset);
 		/* SDmaUseLargeBuf has to be set in every descriptor */
 		if (tx->txreq.flags & IPATH_SDMA_TXREQ_F_USELARGEBUF)
@@ -798,7 +798,18 @@ retry:
 	list_add_tail(&tx->txreq.list, &dd->ipath_sdma_activelist);
 	if (tx->txreq.flags & IPATH_SDMA_TXREQ_F_VL15)
 		vl15_watchdog_enq(dd);
-
+	goto unlock;
+
+unmap:
+	while (tail != dd->ipath_sdma_descq_tail) {
+		if (!tail)
+			tail = dd->ipath_sdma_descq_cnt - 1;
+		else
+			tail--;
+		unmap_desc(dd, tail);
+	}
+ioerr:
+	ret = -EIO;
 unlock:
 	spin_unlock_irqrestore(&dd->ipath_sdma_lock, flags);
 fail:
diff --git a/drivers/infiniband/hw/ipath/ipath_stats.c b/drivers/infiniband/hw/ipath/ipath_stats.c
index c8e3d65f0de8..f63e143e3292 100644
--- a/drivers/infiniband/hw/ipath/ipath_stats.c
+++ b/drivers/infiniband/hw/ipath/ipath_stats.c
@@ -112,6 +112,14 @@ u64 ipath_snap_cntr(struct ipath_devdata *dd, ipath_creg creg)
 			dd->ipath_lastrpkts = val;
 		}
 		val64 = dd->ipath_rpkts;
+	} else if (creg == dd->ipath_cregs->cr_ibsymbolerrcnt) {
+		if (dd->ibdeltainprog)
+			val64 -= val64 - dd->ibsymsnap;
+		val64 -= dd->ibsymdelta;
+	} else if (creg == dd->ipath_cregs->cr_iblinkerrrecovcnt) {
+		if (dd->ibdeltainprog)
+			val64 -= val64 - dd->iblnkerrsnap;
+		val64 -= dd->iblnkerrdelta;
 	} else
 		val64 = (u64) val;
 
diff --git a/drivers/infiniband/hw/ipath/ipath_ud.c b/drivers/infiniband/hw/ipath/ipath_ud.c
index 729446f56aab..91c74cc797ae 100644
--- a/drivers/infiniband/hw/ipath/ipath_ud.c
+++ b/drivers/infiniband/hw/ipath/ipath_ud.c
@@ -70,8 +70,6 @@ static void ipath_ud_loopback(struct ipath_qp *sqp, struct ipath_swqe *swqe)
 		goto done;
 	}
 
-	rsge.sg_list = NULL;
-
 	/*
 	 * Check that the qkey matches (except for QP0, see 9.6.1.4.1).
 	 * Qkeys with the high order bit set mean use the
@@ -115,21 +113,6 @@ static void ipath_ud_loopback(struct ipath_qp *sqp, struct ipath_swqe *swqe)
 		rq = &qp->r_rq;
 	}
 
-	if (rq->max_sge > 1) {
-		/*
-		 * XXX We could use GFP_KERNEL if ipath_do_send()
-		 * was always called from the tasklet instead of
-		 * from ipath_post_send().
-		 */
-		rsge.sg_list = kmalloc((rq->max_sge - 1) *
-					sizeof(struct ipath_sge),
-				       GFP_ATOMIC);
-		if (!rsge.sg_list) {
-			dev->n_pkt_drops++;
-			goto drop;
-		}
-	}
-
 	/*
 	 * Get the next work request entry to find where to put the data.
 	 * Note that it is safe to drop the lock after changing rq->tail
@@ -147,6 +130,7 @@ static void ipath_ud_loopback(struct ipath_qp *sqp, struct ipath_swqe *swqe)
 		goto drop;
 	}
 	wqe = get_rwqe_ptr(rq, tail);
+	rsge.sg_list = qp->r_ud_sg_list;
 	if (!ipath_init_sge(qp, wqe, &rlen, &rsge)) {
 		spin_unlock_irqrestore(&rq->lock, flags);
 		dev->n_pkt_drops++;
@@ -242,7 +226,6 @@ static void ipath_ud_loopback(struct ipath_qp *sqp, struct ipath_swqe *swqe)
 	ipath_cq_enter(to_icq(qp->ibqp.recv_cq), &wc,
 		       swqe->wr.send_flags & IB_SEND_SOLICITED);
 drop:
-	kfree(rsge.sg_list);
 	if (atomic_dec_and_test(&qp->refcount))
 		wake_up(&qp->wait);
 done:;
diff --git a/drivers/infiniband/hw/ipath/ipath_verbs.c b/drivers/infiniband/hw/ipath/ipath_verbs.c
index eabc4247860b..cdf0e6abd34d 100644
--- a/drivers/infiniband/hw/ipath/ipath_verbs.c
+++ b/drivers/infiniband/hw/ipath/ipath_verbs.c
@@ -1852,7 +1852,7 @@ unsigned ipath_get_npkeys(struct ipath_devdata *dd)
 }
 
 /**
- * ipath_get_pkey - return the indexed PKEY from the port 0 PKEY table
+ * ipath_get_pkey - return the indexed PKEY from the port PKEY table
  * @dd: the infinipath device
  * @index: the PKEY index
  */
@@ -1860,6 +1860,7 @@ unsigned ipath_get_pkey(struct ipath_devdata *dd, unsigned index)
 {
 	unsigned ret;
 
+	/* always a kernel port, no locking needed */
 	if (index >= ARRAY_SIZE(dd->ipath_pd[0]->port_pkeys))
 		ret = 0;
 	else
diff --git a/drivers/infiniband/hw/ipath/ipath_verbs.h b/drivers/infiniband/hw/ipath/ipath_verbs.h
index 9d12ae8a778e..11e3f613df93 100644
--- a/drivers/infiniband/hw/ipath/ipath_verbs.h
+++ b/drivers/infiniband/hw/ipath/ipath_verbs.h
@@ -431,6 +431,7 @@ struct ipath_qp {
 	u32 s_lsn;		/* limit sequence number (credit) */
 	struct ipath_swqe *s_wq;	/* send work queue */
 	struct ipath_swqe *s_wqe;
+	struct ipath_sge *r_ud_sg_list;
 	struct ipath_rq r_rq;		/* receive work queue */
 	struct ipath_sge r_sg_list[0];	/* verified SGEs */
 };
diff --git a/drivers/infiniband/hw/nes/nes.h b/drivers/infiniband/hw/nes/nes.h
index 1595dc7bba9d..13a5bb1a7bcf 100644
--- a/drivers/infiniband/hw/nes/nes.h
+++ b/drivers/infiniband/hw/nes/nes.h
@@ -137,14 +137,18 @@
 
 #ifdef CONFIG_INFINIBAND_NES_DEBUG
 #define nes_debug(level, fmt, args...) \
+do { \
 	if (level & nes_debug_level) \
-		printk(KERN_ERR PFX "%s[%u]: " fmt, __func__, __LINE__, ##args)
-
-#define assert(expr)                                                \
-if (!(expr)) {                                                       \
-	printk(KERN_ERR PFX "Assertion failed! %s, %s, %s, line %d\n",  \
-		   #expr, __FILE__, __func__, __LINE__);                \
-}
+		printk(KERN_ERR PFX "%s[%u]: " fmt, __func__, __LINE__, ##args); \
+} while (0)
+
+#define assert(expr) \
+do { \
+	if (!(expr)) { \
+		printk(KERN_ERR PFX "Assertion failed! %s, %s, %s, line %d\n", \
+			   #expr, __FILE__, __func__, __LINE__); \
+	} \
+} while (0)
 
 #define NES_EVENT_TIMEOUT   1200000
 #else
diff --git a/drivers/infiniband/hw/nes/nes_cm.c b/drivers/infiniband/hw/nes/nes_cm.c
index 2caf9da81ad5..aa373c5f8d84 100644
--- a/drivers/infiniband/hw/nes/nes_cm.c
+++ b/drivers/infiniband/hw/nes/nes_cm.c
@@ -86,13 +86,13 @@ static int mini_cm_accept(struct nes_cm_core *, struct ietf_mpa_frame *,
 	struct nes_cm_node *);
 static int mini_cm_reject(struct nes_cm_core *, struct ietf_mpa_frame *,
 	struct nes_cm_node *);
-static void mini_cm_recv_pkt(struct nes_cm_core *, struct nes_vnic *,
+static int mini_cm_recv_pkt(struct nes_cm_core *, struct nes_vnic *,
 	struct sk_buff *);
 static int mini_cm_dealloc_core(struct nes_cm_core *);
 static int mini_cm_get(struct nes_cm_core *);
 static int mini_cm_set(struct nes_cm_core *, u32, u32);
 
-static struct sk_buff *form_cm_frame(struct sk_buff *, struct nes_cm_node *,
+static void form_cm_frame(struct sk_buff *, struct nes_cm_node *,
 	void *, u32, void *, u32, u8);
 static struct sk_buff *get_free_pkt(struct nes_cm_node *cm_node);
 static int add_ref_cm_node(struct nes_cm_node *);
@@ -251,7 +251,7 @@ static int parse_mpa(struct nes_cm_node *cm_node, u8 *buffer, u32 len)
  * form_cm_frame - get a free packet and build empty frame Use
  * node info to build.
  */
-static struct sk_buff *form_cm_frame(struct sk_buff *skb,
+static void form_cm_frame(struct sk_buff *skb,
 	struct nes_cm_node *cm_node, void *options, u32 optionsize,
 	void *data, u32 datasize, u8 flags)
 {
@@ -339,7 +339,6 @@ static struct sk_buff *form_cm_frame(struct sk_buff *skb,
 	skb_shinfo(skb)->nr_frags = 0;
 	cm_packets_created++;
 
-	return skb;
 }
 
 
@@ -381,8 +380,6 @@ int schedule_nes_timer(struct nes_cm_node *cm_node, struct sk_buff *skb,
 	int ret = 0;
 	u32 was_timer_set;
 
-	if (!cm_node)
-		return -EINVAL;
 	new_send = kzalloc(sizeof(*new_send), GFP_ATOMIC);
 	if (!new_send)
 		return -1;
@@ -459,13 +456,23 @@ static void nes_cm_timer_tick(unsigned long pass)
 	int ret = NETDEV_TX_OK;
 	enum nes_cm_node_state last_state;
 
+	struct list_head timer_list;
+	INIT_LIST_HEAD(&timer_list);
 	spin_lock_irqsave(&cm_core->ht_lock, flags);
 
 	list_for_each_safe(list_node, list_core_temp,
-		&cm_core->connected_nodes) {
+				&cm_core->connected_nodes) {
 		cm_node = container_of(list_node, struct nes_cm_node, list);
-		add_ref_cm_node(cm_node);
-		spin_unlock_irqrestore(&cm_core->ht_lock, flags);
+		if (!list_empty(&cm_node->recv_list) || (cm_node->send_entry)) {
+			add_ref_cm_node(cm_node);
+			list_add(&cm_node->timer_entry, &timer_list);
+		}
+	}
+	spin_unlock_irqrestore(&cm_core->ht_lock, flags);
+
+	list_for_each_safe(list_node, list_core_temp, &timer_list) {
+		cm_node = container_of(list_node, struct nes_cm_node,
+					timer_entry);
 		spin_lock_irqsave(&cm_node->recv_list_lock, flags);
 		list_for_each_safe(list_core, list_node_temp,
 			&cm_node->recv_list) {
@@ -519,7 +526,7 @@ static void nes_cm_timer_tick(unsigned long pass)
 		do {
 			send_entry = cm_node->send_entry;
 			if (!send_entry)
-				continue;
+				break;
 			if (time_after(send_entry->timetosend, jiffies)) {
 				if (cm_node->state != NES_CM_STATE_TSA) {
 					if ((nexttimeout >
@@ -528,18 +535,18 @@ static void nes_cm_timer_tick(unsigned long pass)
 						nexttimeout =
 							send_entry->timetosend;
 						settimer = 1;
-						continue;
+						break;
 					}
 				} else {
 					free_retrans_entry(cm_node);
-					continue;
+					break;
 				}
 			}
 
 			if ((cm_node->state == NES_CM_STATE_TSA) ||
 				(cm_node->state == NES_CM_STATE_CLOSED)) {
 				free_retrans_entry(cm_node);
-				continue;
+				break;
 			}
 
 			if (!send_entry->retranscount ||
@@ -557,7 +564,7 @@ static void nes_cm_timer_tick(unsigned long pass)
 						NES_CM_EVENT_ABORTED);
 				spin_lock_irqsave(&cm_node->retrans_list_lock,
 					flags);
-				continue;
+				break;
 			}
 			atomic_inc(&send_entry->skb->users);
 			cm_packets_retrans++;
@@ -583,7 +590,7 @@ static void nes_cm_timer_tick(unsigned long pass)
 				send_entry->retrycount--;
 				nexttimeout = jiffies + NES_SHORT_TIME;
 				settimer = 1;
-				continue;
+				break;
 			} else {
 				cm_packets_sent++;
 			}
@@ -615,14 +622,12 @@ static void nes_cm_timer_tick(unsigned long pass)
 
 		spin_unlock_irqrestore(&cm_node->retrans_list_lock, flags);
 		rem_ref_cm_node(cm_node->cm_core, cm_node);
-		spin_lock_irqsave(&cm_core->ht_lock, flags);
 		if (ret != NETDEV_TX_OK) {
 			nes_debug(NES_DBG_CM, "rexmit failed for cm_node=%p\n",
 				cm_node);
 			break;
 		}
 	}
-	spin_unlock_irqrestore(&cm_core->ht_lock, flags);
 
 	if (settimer) {
 		if (!timer_pending(&cm_core->tcp_timer)) {
@@ -925,28 +930,36 @@ static int mini_cm_dec_refcnt_listen(struct nes_cm_core *cm_core,
 	struct list_head *list_pos = NULL;
 	struct list_head *list_temp = NULL;
 	struct nes_cm_node *cm_node = NULL;
+	struct list_head reset_list;
 
 	nes_debug(NES_DBG_CM, "attempting listener= %p free_nodes= %d, "
 		"refcnt=%d\n", listener, free_hanging_nodes,
 		atomic_read(&listener->ref_count));
 	/* free non-accelerated child nodes for this listener */
+	INIT_LIST_HEAD(&reset_list);
 	if (free_hanging_nodes) {
 		spin_lock_irqsave(&cm_core->ht_lock, flags);
 		list_for_each_safe(list_pos, list_temp,
-			&g_cm_core->connected_nodes) {
+				   &g_cm_core->connected_nodes) {
 			cm_node = container_of(list_pos, struct nes_cm_node,
 				list);
 			if ((cm_node->listener == listener) &&
-				(!cm_node->accelerated)) {
-				cleanup_retrans_entry(cm_node);
-				spin_unlock_irqrestore(&cm_core->ht_lock,
-					flags);
-				send_reset(cm_node, NULL);
-				spin_lock_irqsave(&cm_core->ht_lock, flags);
+			    (!cm_node->accelerated)) {
+				add_ref_cm_node(cm_node);
+				list_add(&cm_node->reset_entry, &reset_list);
 			}
 		}
 		spin_unlock_irqrestore(&cm_core->ht_lock, flags);
 	}
+
+	list_for_each_safe(list_pos, list_temp, &reset_list) {
+		cm_node = container_of(list_pos, struct nes_cm_node,
+					reset_entry);
+		cleanup_retrans_entry(cm_node);
+		send_reset(cm_node, NULL);
+		rem_ref_cm_node(cm_node->cm_core, cm_node);
+	}
+
 	spin_lock_irqsave(&cm_core->listen_list_lock, flags);
 	if (!atomic_dec_return(&listener->ref_count)) {
 		list_del(&listener->list);
@@ -1126,7 +1139,10 @@ static struct nes_cm_node *make_cm_node(struct nes_cm_core *cm_core,
 
 	cm_node->loopbackpartner = NULL;
 	/* get the mac addr for the remote node */
-	arpindex = nes_arp_table(nesdev, cm_node->rem_addr, NULL, NES_ARP_RESOLVE);
+	if (ipv4_is_loopback(htonl(cm_node->rem_addr)))
+		arpindex = nes_arp_table(nesdev, ntohl(nesvnic->local_ipaddr), NULL, NES_ARP_RESOLVE);
+	else
+		arpindex = nes_arp_table(nesdev, cm_node->rem_addr, NULL, NES_ARP_RESOLVE);
 	if (arpindex < 0) {
 		arpindex = nes_addr_resolve_neigh(nesvnic, cm_info->rem_addr);
 		if (arpindex < 0) {
@@ -1306,7 +1322,6 @@ static void drop_packet(struct sk_buff *skb)
 static void handle_fin_pkt(struct nes_cm_node *cm_node, struct sk_buff *skb,
 	struct tcphdr *tcph)
 {
-	atomic_inc(&cm_resets_recvd);
 	nes_debug(NES_DBG_CM, "Received FIN, cm_node = %p, state = %u. "
 		"refcnt=%d\n", cm_node, cm_node->state,
 		atomic_read(&cm_node->ref_count));
@@ -1344,6 +1359,7 @@ static void handle_rst_pkt(struct nes_cm_node *cm_node, struct sk_buff *skb,
 {
 
 	int	reset = 0;	/* whether to send reset in case of err.. */
+	int	passive_state;
 	atomic_inc(&cm_resets_recvd);
 	nes_debug(NES_DBG_CM, "Received Reset, cm_node = %p, state = %u."
 			" refcnt=%d\n", cm_node, cm_node->state,
@@ -1357,7 +1373,14 @@ static void handle_rst_pkt(struct nes_cm_node *cm_node, struct sk_buff *skb,
 			cm_node->listener, cm_node->state);
 		active_open_err(cm_node, skb, reset);
 		break;
-	/* For PASSIVE open states, remove the cm_node event */
+	case NES_CM_STATE_MPAREQ_RCVD:
+		passive_state = atomic_add_return(1, &cm_node->passive_state);
+		if (passive_state ==  NES_SEND_RESET_EVENT)
+			create_event(cm_node, NES_CM_EVENT_RESET);
+		cleanup_retrans_entry(cm_node);
+		cm_node->state = NES_CM_STATE_CLOSED;
+		dev_kfree_skb_any(skb);
+		break;
 	case NES_CM_STATE_ESTABLISHED:
 	case NES_CM_STATE_SYN_RCVD:
 	case NES_CM_STATE_LISTENING:
@@ -1365,7 +1388,14 @@ static void handle_rst_pkt(struct nes_cm_node *cm_node, struct sk_buff *skb,
 		passive_open_err(cm_node, skb, reset);
 		break;
 	case NES_CM_STATE_TSA:
+		active_open_err(cm_node, skb, reset);
+		break;
+	case NES_CM_STATE_CLOSED:
+		cleanup_retrans_entry(cm_node);
+		drop_packet(skb);
+		break;
 	default:
+		drop_packet(skb);
 		break;
 	}
 }
@@ -1394,6 +1424,9 @@ static void handle_rcv_mpa(struct nes_cm_node *cm_node, struct sk_buff *skb,
 		dev_kfree_skb_any(skb);
 		if (type == NES_CM_EVENT_CONNECTED)
 			cm_node->state = NES_CM_STATE_TSA;
+		else
+			atomic_set(&cm_node->passive_state,
+					NES_PASSIVE_STATE_INDICATED);
 		create_event(cm_node, type);
 
 	}
@@ -1474,7 +1507,7 @@ static void handle_syn_pkt(struct nes_cm_node *cm_node, struct sk_buff *skb,
 	int optionsize;
 
 	optionsize = (tcph->doff << 2) - sizeof(struct tcphdr);
-	skb_pull(skb, tcph->doff << 2);
+	skb_trim(skb, 0);
 	inc_sequence = ntohl(tcph->seq);
 
 	switch (cm_node->state) {
@@ -1507,6 +1540,10 @@ static void handle_syn_pkt(struct nes_cm_node *cm_node, struct sk_buff *skb,
 		cm_node->state = NES_CM_STATE_SYN_RCVD;
 		send_syn(cm_node, 1, skb);
 		break;
+	case NES_CM_STATE_CLOSED:
+		cleanup_retrans_entry(cm_node);
+		send_reset(cm_node, skb);
+		break;
 	case NES_CM_STATE_TSA:
 	case NES_CM_STATE_ESTABLISHED:
 	case NES_CM_STATE_FIN_WAIT1:
@@ -1515,7 +1552,6 @@ static void handle_syn_pkt(struct nes_cm_node *cm_node, struct sk_buff *skb,
 	case NES_CM_STATE_LAST_ACK:
 	case NES_CM_STATE_CLOSING:
 	case NES_CM_STATE_UNKNOWN:
-	case NES_CM_STATE_CLOSED:
 	default:
 		drop_packet(skb);
 		break;
@@ -1531,7 +1567,7 @@ static void handle_synack_pkt(struct nes_cm_node *cm_node, struct sk_buff *skb,
 	int optionsize;
 
 	optionsize = (tcph->doff << 2) - sizeof(struct tcphdr);
-	skb_pull(skb, tcph->doff << 2);
+	skb_trim(skb, 0);
 	inc_sequence = ntohl(tcph->seq);
 	switch (cm_node->state) {
 	case NES_CM_STATE_SYN_SENT:
@@ -1555,6 +1591,12 @@ static void handle_synack_pkt(struct nes_cm_node *cm_node, struct sk_buff *skb,
 		/* passive open, so should not be here */
 		passive_open_err(cm_node, skb, 1);
 		break;
+	case NES_CM_STATE_LISTENING:
+	case NES_CM_STATE_CLOSED:
+		cm_node->tcp_cntxt.loc_seq_num = ntohl(tcph->ack_seq);
+		cleanup_retrans_entry(cm_node);
+		send_reset(cm_node, skb);
+		break;
 	case NES_CM_STATE_ESTABLISHED:
 	case NES_CM_STATE_FIN_WAIT1:
 	case NES_CM_STATE_FIN_WAIT2:
@@ -1562,7 +1604,6 @@ static void handle_synack_pkt(struct nes_cm_node *cm_node, struct sk_buff *skb,
 	case NES_CM_STATE_TSA:
 	case NES_CM_STATE_CLOSING:
 	case NES_CM_STATE_UNKNOWN:
-	case NES_CM_STATE_CLOSED:
 	case NES_CM_STATE_MPAREQ_SENT:
 	default:
 		drop_packet(skb);
@@ -1577,6 +1618,13 @@ static void handle_ack_pkt(struct nes_cm_node *cm_node, struct sk_buff *skb,
 	u32 inc_sequence;
 	u32 rem_seq_ack;
 	u32 rem_seq;
+	int ret;
+	int optionsize;
+	u32 temp_seq = cm_node->tcp_cntxt.loc_seq_num;
+
+	optionsize = (tcph->doff << 2) - sizeof(struct tcphdr);
+	cm_node->tcp_cntxt.loc_seq_num = ntohl(tcph->ack_seq);
+
 	if (check_seq(cm_node, tcph, skb))
 		return;
 
@@ -1589,7 +1637,18 @@ static void handle_ack_pkt(struct nes_cm_node *cm_node, struct sk_buff *skb,
 	switch (cm_node->state) {
 	case NES_CM_STATE_SYN_RCVD:
 		/* Passive OPEN */
+		ret = handle_tcp_options(cm_node, tcph, skb, optionsize, 1);
+		if (ret)
+			break;
 		cm_node->tcp_cntxt.rem_ack_num = ntohl(tcph->ack_seq);
+		cm_node->tcp_cntxt.loc_seq_num = temp_seq;
+		if (cm_node->tcp_cntxt.rem_ack_num !=
+		    cm_node->tcp_cntxt.loc_seq_num) {
+			nes_debug(NES_DBG_CM, "rem_ack_num != loc_seq_num\n");
+			cleanup_retrans_entry(cm_node);
+			send_reset(cm_node, skb);
+			return;
+		}
 		cm_node->state = NES_CM_STATE_ESTABLISHED;
 		if (datasize) {
 			cm_node->tcp_cntxt.rcv_nxt = inc_sequence + datasize;
@@ -1621,11 +1680,15 @@ static void handle_ack_pkt(struct nes_cm_node *cm_node, struct sk_buff *skb,
 			dev_kfree_skb_any(skb);
 		}
 		break;
+	case NES_CM_STATE_LISTENING:
+	case NES_CM_STATE_CLOSED:
+		cleanup_retrans_entry(cm_node);
+		send_reset(cm_node, skb);
+		break;
 	case NES_CM_STATE_FIN_WAIT1:
 	case NES_CM_STATE_SYN_SENT:
 	case NES_CM_STATE_FIN_WAIT2:
 	case NES_CM_STATE_TSA:
-	case NES_CM_STATE_CLOSED:
 	case NES_CM_STATE_MPAREQ_RCVD:
 	case NES_CM_STATE_LAST_ACK:
 	case NES_CM_STATE_CLOSING:
@@ -1648,9 +1711,9 @@ static int handle_tcp_options(struct nes_cm_node *cm_node, struct tcphdr *tcph,
 			nes_debug(NES_DBG_CM, "%s: Node %p, Sending RESET\n",
 				__func__, cm_node);
 			if (passive)
-				passive_open_err(cm_node, skb, 0);
+				passive_open_err(cm_node, skb, 1);
 			else
-				active_open_err(cm_node, skb, 0);
+				active_open_err(cm_node, skb, 1);
 			return 1;
 		}
 	}
@@ -1970,6 +2033,7 @@ static int mini_cm_reject(struct nes_cm_core *cm_core,
 	struct ietf_mpa_frame *mpa_frame, struct nes_cm_node *cm_node)
 {
 	int ret = 0;
+	int passive_state;
 
 	nes_debug(NES_DBG_CM, "%s cm_node=%p type=%d state=%d\n",
 		__func__, cm_node, cm_node->tcp_cntxt.client, cm_node->state);
@@ -1977,9 +2041,13 @@ static int mini_cm_reject(struct nes_cm_core *cm_core,
 	if (cm_node->tcp_cntxt.client)
 		return ret;
 	cleanup_retrans_entry(cm_node);
-	cm_node->state = NES_CM_STATE_CLOSED;
 
-	ret = send_reset(cm_node, NULL);
+	passive_state = atomic_add_return(1, &cm_node->passive_state);
+	cm_node->state = NES_CM_STATE_CLOSED;
+	if (passive_state == NES_SEND_RESET_EVENT)
+		rem_ref_cm_node(cm_core, cm_node);
+	else
+		ret = send_reset(cm_node, NULL);
 	return ret;
 }
 
@@ -2037,7 +2105,7 @@ static int mini_cm_close(struct nes_cm_core *cm_core, struct nes_cm_node *cm_nod
  * recv_pkt - recv an ETHERNET packet, and process it through CM
  * node state machine
  */
-static void mini_cm_recv_pkt(struct nes_cm_core *cm_core,
+static int mini_cm_recv_pkt(struct nes_cm_core *cm_core,
 	struct nes_vnic *nesvnic, struct sk_buff *skb)
 {
 	struct nes_cm_node *cm_node = NULL;
@@ -2045,23 +2113,16 @@ static void mini_cm_recv_pkt(struct nes_cm_core *cm_core,
 	struct iphdr *iph;
 	struct tcphdr *tcph;
 	struct nes_cm_info nfo;
+	int skb_handled = 1;
 
 	if (!skb)
-		return;
+		return 0;
 	if (skb->len < sizeof(struct iphdr) + sizeof(struct tcphdr)) {
-		dev_kfree_skb_any(skb);
-		return;
+		return 0;
 	}
 
 	iph = (struct iphdr *)skb->data;
 	tcph = (struct tcphdr *)(skb->data + sizeof(struct iphdr));
-	skb_reset_network_header(skb);
-	skb_set_transport_header(skb, sizeof(*tcph));
-	if (!tcph) {
-		dev_kfree_skb_any(skb);
-		return;
-	}
-	skb->len = ntohs(iph->tot_len);
 
 	nfo.loc_addr = ntohl(iph->daddr);
 	nfo.loc_port = ntohs(tcph->dest);
@@ -2082,23 +2143,21 @@ static void mini_cm_recv_pkt(struct nes_cm_core *cm_core,
 			/* Only type of packet accepted are for */
 			/* the PASSIVE open (syn only) */
 			if ((!tcph->syn) || (tcph->ack)) {
-				cm_packets_dropped++;
+				skb_handled = 0;
 				break;
 			}
 			listener = find_listener(cm_core, nfo.loc_addr,
 				nfo.loc_port,
 				NES_CM_LISTENER_ACTIVE_STATE);
-			if (listener) {
-				nfo.cm_id = listener->cm_id;
-				nfo.conn_type = listener->conn_type;
-			} else {
-				nes_debug(NES_DBG_CM, "Unable to find listener "
-					"for the pkt\n");
-				cm_packets_dropped++;
-				dev_kfree_skb_any(skb);
+			if (!listener) {
+				nfo.cm_id = NULL;
+				nfo.conn_type = 0;
+				nes_debug(NES_DBG_CM, "Unable to find listener for the pkt\n");
+				skb_handled = 0;
 				break;
 			}
-
+			nfo.cm_id = listener->cm_id;
+			nfo.conn_type = listener->conn_type;
 			cm_node = make_cm_node(cm_core, nesvnic, &nfo,
 				listener);
 			if (!cm_node) {
@@ -2124,9 +2183,13 @@ static void mini_cm_recv_pkt(struct nes_cm_core *cm_core,
 			dev_kfree_skb_any(skb);
 			break;
 		}
+		skb_reset_network_header(skb);
+		skb_set_transport_header(skb, sizeof(*tcph));
+		skb->len = ntohs(iph->tot_len);
 		process_packet(cm_node, skb, cm_core);
 		rem_ref_cm_node(cm_core, cm_node);
 	} while (0);
+	return skb_handled;
 }
 
 
@@ -2397,7 +2460,6 @@ static int nes_cm_disconn_true(struct nes_qp *nesqp)
 			atomic_inc(&cm_disconnects);
 			cm_event.event = IW_CM_EVENT_DISCONNECT;
 			if (last_ae == NES_AEQE_AEID_LLP_CONNECTION_RESET) {
-				issued_disconnect_reset = 1;
 				cm_event.status = IW_CM_EVENT_STATUS_RESET;
 				nes_debug(NES_DBG_CM, "Generating a CM "
 					"Disconnect Event (status reset) for "
@@ -2547,6 +2609,7 @@ int nes_accept(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param)
 	struct nes_v4_quad nes_quad;
 	u32 crc_value;
 	int ret;
+	int passive_state;
 
 	ibqp = nes_get_qp(cm_id->device, conn_param->qpn);
 	if (!ibqp)
@@ -2714,8 +2777,6 @@ int nes_accept(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param)
 			conn_param->private_data_len +
 			sizeof(struct ietf_mpa_frame));
 
-	attr.qp_state = IB_QPS_RTS;
-	nes_modify_qp(&nesqp->ibqp, &attr, IB_QP_STATE, NULL);
 
 	/* notify OF layer that accept event was successfull */
 	cm_id->add_ref(cm_id);
@@ -2728,6 +2789,8 @@ int nes_accept(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param)
 	cm_event.private_data = NULL;
 	cm_event.private_data_len = 0;
 	ret = cm_id->event_handler(cm_id, &cm_event);
+	attr.qp_state = IB_QPS_RTS;
+	nes_modify_qp(&nesqp->ibqp, &attr, IB_QP_STATE, NULL);
 	if (cm_node->loopbackpartner) {
 		cm_node->loopbackpartner->mpa_frame_size =
 			nesqp->private_data_len;
@@ -2740,6 +2803,9 @@ int nes_accept(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param)
 		printk(KERN_ERR "%s[%u] OFA CM event_handler returned, "
 			"ret=%d\n", __func__, __LINE__, ret);
 
+	passive_state = atomic_add_return(1, &cm_node->passive_state);
+	if (passive_state == NES_SEND_RESET_EVENT)
+		create_event(cm_node, NES_CM_EVENT_RESET);
 	return 0;
 }
 
@@ -2943,15 +3009,16 @@ int nes_destroy_listen(struct iw_cm_id *cm_id)
  */
 int nes_cm_recv(struct sk_buff *skb, struct net_device *netdevice)
 {
+	int rc = 0;
 	cm_packets_received++;
 	if ((g_cm_core) && (g_cm_core->api)) {
-		g_cm_core->api->recv_pkt(g_cm_core, netdev_priv(netdevice), skb);
+		rc = g_cm_core->api->recv_pkt(g_cm_core, netdev_priv(netdevice), skb);
 	} else {
 		nes_debug(NES_DBG_CM, "Unable to process packet for CM,"
 				" cm is not setup properly.\n");
 	}
 
-	return 0;
+	return rc;
 }
 
 
@@ -3222,6 +3289,18 @@ static void cm_event_reset(struct nes_cm_event *event)
 	cm_event.private_data_len = 0;
 
 	ret = cm_id->event_handler(cm_id, &cm_event);
+	cm_id->add_ref(cm_id);
+	atomic_inc(&cm_closes);
+	cm_event.event = IW_CM_EVENT_CLOSE;
+	cm_event.status = IW_CM_EVENT_STATUS_OK;
+	cm_event.provider_data = cm_id->provider_data;
+	cm_event.local_addr = cm_id->local_addr;
+	cm_event.remote_addr = cm_id->remote_addr;
+	cm_event.private_data = NULL;
+	cm_event.private_data_len = 0;
+	nes_debug(NES_DBG_CM, "NODE %p Generating CLOSE\n", event->cm_node);
+	ret = cm_id->event_handler(cm_id, &cm_event);
+
 	nes_debug(NES_DBG_CM, "OFA CM event_handler returned, ret=%d\n", ret);
 
 
diff --git a/drivers/infiniband/hw/nes/nes_cm.h b/drivers/infiniband/hw/nes/nes_cm.h
index 367b3d290140..3a20a7883976 100644
--- a/drivers/infiniband/hw/nes/nes_cm.h
+++ b/drivers/infiniband/hw/nes/nes_cm.h
@@ -76,6 +76,10 @@ enum nes_timer_type {
 	NES_TIMER_TYPE_CLOSE,
 };
 
+#define NES_PASSIVE_STATE_INDICATED	0
+#define NES_DO_NOT_SEND_RESET_EVENT	1
+#define NES_SEND_RESET_EVENT		2
+
 #define MAX_NES_IFS 4
 
 #define SET_ACK 1
@@ -292,7 +296,10 @@ struct nes_cm_node {
 	int                       apbvt_set;
 	int                       accept_pend;
 	int			freed;
+	struct list_head	timer_entry;
+	struct list_head	reset_entry;
 	struct nes_qp		*nesqp;
+	atomic_t 		passive_state;
 };
 
 /* structure for client or CM to fill when making CM api calls. */
@@ -390,7 +397,7 @@ struct nes_cm_ops {
 			struct nes_cm_node *);
 	int (*reject)(struct nes_cm_core *, struct ietf_mpa_frame *,
 			struct nes_cm_node *);
-	void (*recv_pkt)(struct nes_cm_core *, struct nes_vnic *,
+	int (*recv_pkt)(struct nes_cm_core *, struct nes_vnic *,
 			struct sk_buff *);
 	int (*destroy_cm_core)(struct nes_cm_core *);
 	int (*get)(struct nes_cm_core *);
diff --git a/drivers/infiniband/hw/nes/nes_hw.c b/drivers/infiniband/hw/nes/nes_hw.c
index 7c49cc882d75..8f70ff2dcc58 100644
--- a/drivers/infiniband/hw/nes/nes_hw.c
+++ b/drivers/infiniband/hw/nes/nes_hw.c
@@ -2700,27 +2700,33 @@ void nes_nic_ce_handler(struct nes_device *nesdev, struct nes_hw_nic_cq *cq)
 							pkt_type, (pkt_type & NES_PKT_TYPE_APBVT_MASK)); */
 
 				if ((pkt_type & NES_PKT_TYPE_APBVT_MASK) == NES_PKT_TYPE_APBVT_BITS) {
-					nes_cm_recv(rx_skb, nesvnic->netdev);
+					if (nes_cm_recv(rx_skb, nesvnic->netdev))
+						rx_skb = NULL;
+				}
+				if (rx_skb == NULL)
+					goto skip_rx_indicate0;
+
+
+				if ((cqe_misc & NES_NIC_CQE_TAG_VALID) &&
+				    (nesvnic->vlan_grp != NULL)) {
+					vlan_tag = (u16)(le32_to_cpu(
+							cq->cq_vbase[head].cqe_words[NES_NIC_CQE_TAG_PKT_TYPE_IDX])
+							>> 16);
+					nes_debug(NES_DBG_CQ, "%s: Reporting stripped VLAN packet. Tag = 0x%04X\n",
+							nesvnic->netdev->name, vlan_tag);
+					if (nes_use_lro)
+						lro_vlan_hwaccel_receive_skb(&nesvnic->lro_mgr, rx_skb,
+								nesvnic->vlan_grp, vlan_tag, NULL);
+					else
+						nes_vlan_rx(rx_skb, nesvnic->vlan_grp, vlan_tag);
 				} else {
-					if ((cqe_misc & NES_NIC_CQE_TAG_VALID) && (nesvnic->vlan_grp != NULL)) {
-						vlan_tag = (u16)(le32_to_cpu(
-								cq->cq_vbase[head].cqe_words[NES_NIC_CQE_TAG_PKT_TYPE_IDX])
-								>> 16);
-						nes_debug(NES_DBG_CQ, "%s: Reporting stripped VLAN packet. Tag = 0x%04X\n",
-								nesvnic->netdev->name, vlan_tag);
-						if (nes_use_lro)
-							lro_vlan_hwaccel_receive_skb(&nesvnic->lro_mgr, rx_skb,
-									nesvnic->vlan_grp, vlan_tag, NULL);
-						else
-							nes_vlan_rx(rx_skb, nesvnic->vlan_grp, vlan_tag);
-					} else {
-						if (nes_use_lro)
-							lro_receive_skb(&nesvnic->lro_mgr, rx_skb, NULL);
-						else
-							nes_netif_rx(rx_skb);
-					}
+					if (nes_use_lro)
+						lro_receive_skb(&nesvnic->lro_mgr, rx_skb, NULL);
+					else
+						nes_netif_rx(rx_skb);
 				}
 
+skip_rx_indicate0:
 				nesvnic->netdev->last_rx = jiffies;
 				/* nesvnic->netstats.rx_packets++; */
 				/* nesvnic->netstats.rx_bytes += rx_pkt_size; */
diff --git a/drivers/infiniband/hw/nes/nes_utils.c b/drivers/infiniband/hw/nes/nes_utils.c
index fb8cbd71a2ef..5611a73d5831 100644
--- a/drivers/infiniband/hw/nes/nes_utils.c
+++ b/drivers/infiniband/hw/nes/nes_utils.c
@@ -540,11 +540,14 @@ struct nes_cqp_request *nes_get_cqp_request(struct nes_device *nesdev)
 
 	if (!list_empty(&nesdev->cqp_avail_reqs)) {
 		spin_lock_irqsave(&nesdev->cqp.lock, flags);
-		cqp_request = list_entry(nesdev->cqp_avail_reqs.next,
+		if (!list_empty(&nesdev->cqp_avail_reqs)) {
+			cqp_request = list_entry(nesdev->cqp_avail_reqs.next,
 				struct nes_cqp_request, list);
-		list_del_init(&cqp_request->list);
+			list_del_init(&cqp_request->list);
+		}
 		spin_unlock_irqrestore(&nesdev->cqp.lock, flags);
-	} else {
+	}
+	if (cqp_request == NULL) {
 		cqp_request = kzalloc(sizeof(struct nes_cqp_request), GFP_KERNEL);
 		if (cqp_request) {
 			cqp_request->dynamic = 1;
diff --git a/drivers/infiniband/hw/nes/nes_verbs.c b/drivers/infiniband/hw/nes/nes_verbs.c
index d36c9a0bf1bb..4fdb72454f94 100644
--- a/drivers/infiniband/hw/nes/nes_verbs.c
+++ b/drivers/infiniband/hw/nes/nes_verbs.c
@@ -1695,13 +1695,8 @@ static struct ib_cq *nes_create_cq(struct ib_device *ibdev, int entries,
 			/* use 4k pbl */
 			nes_debug(NES_DBG_CQ, "pbl_entries=%u, use a 4k PBL\n", pbl_entries);
 			if (nesadapter->free_4kpbl == 0) {
-				if (cqp_request->dynamic) {
-					spin_unlock_irqrestore(&nesadapter->pbl_lock, flags);
-					kfree(cqp_request);
-				} else {
-					list_add_tail(&cqp_request->list, &nesdev->cqp_avail_reqs);
-					spin_unlock_irqrestore(&nesadapter->pbl_lock, flags);
-				}
+				spin_unlock_irqrestore(&nesadapter->pbl_lock, flags);
+				nes_free_cqp_request(nesdev, cqp_request);
 				if (!context)
 					pci_free_consistent(nesdev->pcidev, nescq->cq_mem_size, mem,
 							nescq->hw_cq.cq_pbase);
@@ -1717,13 +1712,8 @@ static struct ib_cq *nes_create_cq(struct ib_device *ibdev, int entries,
 			/* use 256 byte pbl */
 			nes_debug(NES_DBG_CQ, "pbl_entries=%u, use a 256 byte PBL\n", pbl_entries);
 			if (nesadapter->free_256pbl == 0) {
-				if (cqp_request->dynamic) {
-					spin_unlock_irqrestore(&nesadapter->pbl_lock, flags);
-					kfree(cqp_request);
-				} else {
-					list_add_tail(&cqp_request->list, &nesdev->cqp_avail_reqs);
-					spin_unlock_irqrestore(&nesadapter->pbl_lock, flags);
-				}
+				spin_unlock_irqrestore(&nesadapter->pbl_lock, flags);
+				nes_free_cqp_request(nesdev, cqp_request);
 				if (!context)
 					pci_free_consistent(nesdev->pcidev, nescq->cq_mem_size, mem,
 							nescq->hw_cq.cq_pbase);
@@ -1928,13 +1918,8 @@ static int nes_reg_mr(struct nes_device *nesdev, struct nes_pd *nespd,
 			/* Two level PBL */
 			if ((pbl_count+1) > nesadapter->free_4kpbl) {
 				nes_debug(NES_DBG_MR, "Out of 4KB Pbls for two level request.\n");
-				if (cqp_request->dynamic) {
-					spin_unlock_irqrestore(&nesadapter->pbl_lock, flags);
-					kfree(cqp_request);
-				} else {
-					list_add_tail(&cqp_request->list, &nesdev->cqp_avail_reqs);
-					spin_unlock_irqrestore(&nesadapter->pbl_lock, flags);
-				}
+				spin_unlock_irqrestore(&nesadapter->pbl_lock, flags);
+				nes_free_cqp_request(nesdev, cqp_request);
 				return -ENOMEM;
 			} else {
 				nesadapter->free_4kpbl -= pbl_count+1;
@@ -1942,13 +1927,8 @@ static int nes_reg_mr(struct nes_device *nesdev, struct nes_pd *nespd,
 		} else if (residual_page_count > 32) {
 			if (pbl_count > nesadapter->free_4kpbl) {
 				nes_debug(NES_DBG_MR, "Out of 4KB Pbls.\n");
-				if (cqp_request->dynamic) {
-					spin_unlock_irqrestore(&nesadapter->pbl_lock, flags);
-					kfree(cqp_request);
-				} else {
-					list_add_tail(&cqp_request->list, &nesdev->cqp_avail_reqs);
-					spin_unlock_irqrestore(&nesadapter->pbl_lock, flags);
-				}
+				spin_unlock_irqrestore(&nesadapter->pbl_lock, flags);
+				nes_free_cqp_request(nesdev, cqp_request);
 				return -ENOMEM;
 			} else {
 				nesadapter->free_4kpbl -= pbl_count;
@@ -1956,13 +1936,8 @@ static int nes_reg_mr(struct nes_device *nesdev, struct nes_pd *nespd,
 		} else {
 			if (pbl_count > nesadapter->free_256pbl) {
 				nes_debug(NES_DBG_MR, "Out of 256B Pbls.\n");
-				if (cqp_request->dynamic) {
-					spin_unlock_irqrestore(&nesadapter->pbl_lock, flags);
-					kfree(cqp_request);
-				} else {
-					list_add_tail(&cqp_request->list, &nesdev->cqp_avail_reqs);
-					spin_unlock_irqrestore(&nesadapter->pbl_lock, flags);
-				}
+				spin_unlock_irqrestore(&nesadapter->pbl_lock, flags);
+				nes_free_cqp_request(nesdev, cqp_request);
 				return -ENOMEM;
 			} else {
 				nesadapter->free_256pbl -= pbl_count;
diff --git a/drivers/infiniband/ulp/srp/ib_srp.c b/drivers/infiniband/ulp/srp/ib_srp.c
index 5b8b533f2908..e5ebcbea5907 100644
--- a/drivers/infiniband/ulp/srp/ib_srp.c
+++ b/drivers/infiniband/ulp/srp/ib_srp.c
@@ -1972,8 +1972,7 @@ static struct srp_host *srp_add_port(struct srp_device *device, u8 port)
 
 	host->dev.class = &srp_class;
 	host->dev.parent = device->dev->dma_device;
-	snprintf(host->dev.bus_id, BUS_ID_SIZE, "srp-%s-%d",
-		 device->dev->name, port);
+	dev_set_name(&host->dev, "srp-%s-%d", device->dev->name, port);
 
 	if (device_register(&host->dev))
 		goto free_host;
diff --git a/drivers/input/keyboard/pxa27x_keypad.c b/drivers/input/keyboard/pxa27x_keypad.c
index 6d30c6d334c3..0d2fc64a5e1c 100644
--- a/drivers/input/keyboard/pxa27x_keypad.c
+++ b/drivers/input/keyboard/pxa27x_keypad.c
@@ -475,7 +475,7 @@ static int __devinit pxa27x_keypad_probe(struct platform_device *pdev)
 		goto failed_free_mem;
 	}
 
-	keypad->clk = clk_get(&pdev->dev, "KBDCLK");
+	keypad->clk = clk_get(&pdev->dev, NULL);
 	if (IS_ERR(keypad->clk)) {
 		dev_err(&pdev->dev, "failed to get keypad clock\n");
 		error = PTR_ERR(keypad->clk);
diff --git a/drivers/input/keyboard/sh_keysc.c b/drivers/input/keyboard/sh_keysc.c
index c600ab7f93e8..5c8a1bcf7ca7 100644
--- a/drivers/input/keyboard/sh_keysc.c
+++ b/drivers/input/keyboard/sh_keysc.c
@@ -18,6 +18,7 @@
 #include <linux/delay.h>
 #include <linux/platform_device.h>
 #include <linux/input.h>
+#include <linux/clk.h>
 #include <linux/io.h>
 #include <asm/sh_keysc.h>
 
@@ -39,6 +40,7 @@ static const struct {
 
 struct sh_keysc_priv {
 	void __iomem *iomem_base;
+	struct clk *clk;
 	unsigned long last_keys;
 	struct input_dev *input;
 	struct sh_keysc_info pdata;
@@ -125,6 +127,7 @@ static int __devinit sh_keysc_probe(struct platform_device *pdev)
 	struct sh_keysc_info *pdata;
 	struct resource *res;
 	struct input_dev *input;
+	char clk_name[8];
 	int i, k;
 	int irq, error;
 
@@ -165,11 +168,19 @@ static int __devinit sh_keysc_probe(struct platform_device *pdev)
 		goto err1;
 	}
 
+	snprintf(clk_name, sizeof(clk_name), "keysc%d", pdev->id);
+	priv->clk = clk_get(&pdev->dev, clk_name);
+	if (IS_ERR(priv->clk)) {
+		dev_err(&pdev->dev, "cannot get clock \"%s\"\n", clk_name);
+		error = PTR_ERR(priv->clk);
+		goto err2;
+	}
+
 	priv->input = input_allocate_device();
 	if (!priv->input) {
 		dev_err(&pdev->dev, "failed to allocate input device\n");
 		error = -ENOMEM;
-		goto err2;
+		goto err3;
 	}
 
 	input = priv->input;
@@ -187,7 +198,7 @@ static int __devinit sh_keysc_probe(struct platform_device *pdev)
 	error = request_irq(irq, sh_keysc_isr, 0, pdev->name, pdev);
 	if (error) {
 		dev_err(&pdev->dev, "failed to request IRQ\n");
-		goto err3;
+		goto err4;
 	}
 
 	for (i = 0; i < SH_KEYSC_MAXKEYS; i++) {
@@ -199,18 +210,22 @@ static int __devinit sh_keysc_probe(struct platform_device *pdev)
 	error = input_register_device(input);
 	if (error) {
 		dev_err(&pdev->dev, "failed to register input device\n");
-		goto err4;
+		goto err5;
 	}
 
+	clk_enable(priv->clk);
+
 	iowrite16((sh_keysc_mode[pdata->mode].kymd << 8) |
 		  pdata->scan_timing, priv->iomem_base + KYCR1_OFFS);
 	iowrite16(0, priv->iomem_base + KYOUTDR_OFFS);
 	iowrite16(KYCR2_IRQ_LEVEL, priv->iomem_base + KYCR2_OFFS);
 	return 0;
- err4:
+ err5:
 	free_irq(irq, pdev);
- err3:
+ err4:
 	input_free_device(input);
+ err3:
+	clk_put(priv->clk);
  err2:
 	iounmap(priv->iomem_base);
  err1:
@@ -230,6 +245,9 @@ static int __devexit sh_keysc_remove(struct platform_device *pdev)
 	free_irq(platform_get_irq(pdev, 0), pdev);
 	iounmap(priv->iomem_base);
 
+	clk_disable(priv->clk);
+	clk_put(priv->clk);
+
 	platform_set_drvdata(pdev, NULL);
 	kfree(priv);
 	return 0;
diff --git a/drivers/input/misc/apanel.c b/drivers/input/misc/apanel.c
index d82f7f727f7a..71b82434264d 100644
--- a/drivers/input/misc/apanel.c
+++ b/drivers/input/misc/apanel.c
@@ -57,7 +57,7 @@ static enum apanel_chip device_chip[APANEL_DEV_MAX];
 
 struct apanel {
 	struct input_polled_dev *ipdev;
-	struct i2c_client client;
+	struct i2c_client *client;
 	unsigned short keymap[MAX_PANEL_KEYS];
 	u16    nkeys;
 	u16    led_bits;
@@ -66,16 +66,7 @@ struct apanel {
 };
 
 
-static int apanel_probe(struct i2c_adapter *, int, int);
-
-/* for now, we only support one address */
-static unsigned short normal_i2c[] = {0, I2C_CLIENT_END};
-static unsigned short ignore = I2C_CLIENT_END;
-static struct i2c_client_address_data addr_data = {
-	.normal_i2c	= normal_i2c,
-	.probe		= &ignore,
-	.ignore		= &ignore,
-};
+static int apanel_probe(struct i2c_client *, const struct i2c_device_id *);
 
 static void report_key(struct input_dev *input, unsigned keycode)
 {
@@ -103,12 +94,12 @@ static void apanel_poll(struct input_polled_dev *ipdev)
 	s32 data;
 	int i;
 
-	data = i2c_smbus_read_word_data(&ap->client, cmd);
+	data = i2c_smbus_read_word_data(ap->client, cmd);
 	if (data < 0)
 		return;	/* ignore errors (due to ACPI??) */
 
 	/* write back to clear latch */
-	i2c_smbus_write_word_data(&ap->client, cmd, 0);
+	i2c_smbus_write_word_data(ap->client, cmd, 0);
 
 	if (!data)
 		return;
@@ -124,7 +115,7 @@ static void led_update(struct work_struct *work)
 {
 	struct apanel *ap = container_of(work, struct apanel, led_work);
 
-	i2c_smbus_write_word_data(&ap->client, 0x10, ap->led_bits);
+	i2c_smbus_write_word_data(ap->client, 0x10, ap->led_bits);
 }
 
 static void mail_led_set(struct led_classdev *led,
@@ -140,7 +131,7 @@ static void mail_led_set(struct led_classdev *led,
 	schedule_work(&ap->led_work);
 }
 
-static int apanel_detach_client(struct i2c_client *client)
+static int apanel_remove(struct i2c_client *client)
 {
 	struct apanel *ap = i2c_get_clientdata(client);
 
@@ -148,43 +139,33 @@ static int apanel_detach_client(struct i2c_client *client)
 		led_classdev_unregister(&ap->mail_led);
 
 	input_unregister_polled_device(ap->ipdev);
-	i2c_detach_client(&ap->client);
 	input_free_polled_device(ap->ipdev);
 
 	return 0;
 }
 
-/* Function is invoked for every i2c adapter. */
-static int apanel_attach_adapter(struct i2c_adapter *adap)
-{
-	dev_dbg(&adap->dev, APANEL ": attach adapter id=%d\n", adap->id);
-
-	/* Our device is connected only to i801 on laptop */
-	if (adap->id != I2C_HW_SMBUS_I801)
-		return -ENODEV;
-
-	return i2c_probe(adap, &addr_data, apanel_probe);
-}
-
 static void apanel_shutdown(struct i2c_client *client)
 {
-	apanel_detach_client(client);
+	apanel_remove(client);
 }
 
+static struct i2c_device_id apanel_id[] = {
+	{ "fujitsu_apanel", 0 },
+	{ }
+};
+MODULE_DEVICE_TABLE(i2c, apanel_id);
+
 static struct i2c_driver apanel_driver = {
 	.driver = {
 		.name = APANEL,
 	},
-	.attach_adapter = &apanel_attach_adapter,
-	.detach_client  = &apanel_detach_client,
+	.probe		= &apanel_probe,
+	.remove		= &apanel_remove,
 	.shutdown	= &apanel_shutdown,
+	.id_table	= apanel_id,
 };
 
 static struct apanel apanel = {
-	.client = {
-		.driver = &apanel_driver,
-		.name   = APANEL,
-	},
 	.keymap = {
 		[0] = KEY_MAIL,
 		[1] = KEY_WWW,
@@ -204,7 +185,8 @@ static struct apanel apanel = {
 };
 
 /* NB: Only one panel on the i2c. */
-static int apanel_probe(struct i2c_adapter *bus, int address, int kind)
+static int apanel_probe(struct i2c_client *client,
+			const struct i2c_device_id *id)
 {
 	struct apanel *ap;
 	struct input_polled_dev *ipdev;
@@ -212,9 +194,6 @@ static int apanel_probe(struct i2c_adapter *bus, int address, int kind)
 	u8 cmd = device_chip[APANEL_DEV_APPBTN] == CHIP_OZ992C ? 0 : 8;
 	int i, err = -ENOMEM;
 
-	dev_dbg(&bus->dev, APANEL ": probe adapter %p addr %d kind %d\n",
-		bus, address, kind);
-
 	ap = &apanel;
 
 	ipdev = input_allocate_polled_device();
@@ -222,18 +201,13 @@ static int apanel_probe(struct i2c_adapter *bus, int address, int kind)
 		goto out1;
 
 	ap->ipdev = ipdev;
-	ap->client.adapter = bus;
-	ap->client.addr = address;
-
-	i2c_set_clientdata(&ap->client, ap);
+	ap->client = client;
 
-	err = i2c_attach_client(&ap->client);
-	if (err)
-		goto out2;
+	i2c_set_clientdata(client, ap);
 
-	err = i2c_smbus_write_word_data(&ap->client, cmd, 0);
+	err = i2c_smbus_write_word_data(client, cmd, 0);
 	if (err) {
-		dev_warn(&ap->client.dev, APANEL ": smbus write error %d\n",
+		dev_warn(&client->dev, APANEL ": smbus write error %d\n",
 			 err);
 		goto out3;
 	}
@@ -246,7 +220,7 @@ static int apanel_probe(struct i2c_adapter *bus, int address, int kind)
 	idev->name = APANEL_NAME " buttons";
 	idev->phys = "apanel/input0";
 	idev->id.bustype = BUS_HOST;
-	idev->dev.parent = &ap->client.dev;
+	idev->dev.parent = &client->dev;
 
 	set_bit(EV_KEY, idev->evbit);
 
@@ -264,7 +238,7 @@ static int apanel_probe(struct i2c_adapter *bus, int address, int kind)
 
 	INIT_WORK(&ap->led_work, led_update);
 	if (device_chip[APANEL_DEV_LED] != CHIP_NONE) {
-		err = led_classdev_register(&ap->client.dev, &ap->mail_led);
+		err = led_classdev_register(&client->dev, &ap->mail_led);
 		if (err)
 			goto out4;
 	}
@@ -273,8 +247,6 @@ static int apanel_probe(struct i2c_adapter *bus, int address, int kind)
 out4:
 	input_unregister_polled_device(ipdev);
 out3:
-	i2c_detach_client(&ap->client);
-out2:
 	input_free_polled_device(ipdev);
 out1:
 	return err;
@@ -301,6 +273,7 @@ static int __init apanel_init(void)
 	void __iomem *bios;
 	const void __iomem *p;
 	u8 devno;
+	unsigned char i2c_addr;
 	int found = 0;
 
 	bios = ioremap(0xF0000, 0x10000); /* Can't fail */
@@ -313,7 +286,7 @@ static int __init apanel_init(void)
 
 	/* just use the first address */
 	p += 8;
-	normal_i2c[0] = readb(p+3) >> 1;
+	i2c_addr = readb(p + 3) >> 1;
 
 	for ( ; (devno = readb(p)) & 0x7f; p += 4) {
 		unsigned char method, slave, chip;
@@ -322,7 +295,7 @@ static int __init apanel_init(void)
 		chip = readb(p + 2);
 		slave = readb(p + 3) >> 1;
 
-		if (slave != normal_i2c[0]) {
+		if (slave != i2c_addr) {
 			pr_notice(APANEL ": only one SMBus slave "
 				  "address supported, skiping device...\n");
 			continue;
diff --git a/drivers/input/serio/Kconfig b/drivers/input/serio/Kconfig
index 27d70d326ff3..da3c3a5d2689 100644
--- a/drivers/input/serio/Kconfig
+++ b/drivers/input/serio/Kconfig
@@ -79,7 +79,7 @@ config SERIO_PARKBD
 
 config SERIO_RPCKBD
 	tristate "Acorn RiscPC keyboard controller"
-	depends on ARCH_ACORN || ARCH_CLPS7500
+	depends on ARCH_ACORN
 	default y
 	help
 	  Say Y here if you have the Acorn RiscPC and want to use an AT
diff --git a/drivers/input/touchscreen/mainstone-wm97xx.c b/drivers/input/touchscreen/mainstone-wm97xx.c
index ba648750a8d9..1d11e2be9ef8 100644
--- a/drivers/input/touchscreen/mainstone-wm97xx.c
+++ b/drivers/input/touchscreen/mainstone-wm97xx.c
@@ -31,7 +31,7 @@
 #include <linux/interrupt.h>
 #include <linux/wm97xx.h>
 #include <linux/io.h>
-#include <mach/pxa-regs.h>
+#include <mach/regs-ac97.h>
 
 #define VERSION		"0.13"
 
diff --git a/drivers/isdn/hardware/avm/b1isa.c b/drivers/isdn/hardware/avm/b1isa.c
index 1e288eeb5e2a..6461a32bc838 100644
--- a/drivers/isdn/hardware/avm/b1isa.c
+++ b/drivers/isdn/hardware/avm/b1isa.c
@@ -233,10 +233,8 @@ static void __exit b1isa_exit(void)
 	int i;
 
 	for (i = 0; i < MAX_CARDS; i++) {
-		if (!io[i])
-			break;
-
-		b1isa_remove(&isa_dev[i]);
+		if (isa_dev[i].resource[0].start)
+			b1isa_remove(&isa_dev[i]);
 	}
 	unregister_capi_driver(&capi_driver_b1isa);
 }
diff --git a/drivers/isdn/hysdn/hysdn_net.c b/drivers/isdn/hysdn/hysdn_net.c
index cfa8fa5e44ab..3f2a0a20c19b 100644
--- a/drivers/isdn/hysdn/hysdn_net.c
+++ b/drivers/isdn/hysdn/hysdn_net.c
@@ -83,12 +83,12 @@ net_open(struct net_device *dev)
 
 	/* Fill in the MAC-level header (if not already set) */
 	if (!card->mac_addr[0]) {
-		for (i = 0; i < ETH_ALEN - sizeof(unsigned long); i++)
+		for (i = 0; i < ETH_ALEN; i++)
 			dev->dev_addr[i] = 0xfc;
 		if ((in_dev = dev->ip_ptr) != NULL) {
 			struct in_ifaddr *ifa = in_dev->ifa_list;
 			if (ifa != NULL)
-				memcpy(dev->dev_addr + (ETH_ALEN - sizeof(unsigned long)), &ifa->ifa_local, sizeof(unsigned long));
+				memcpy(dev->dev_addr + (ETH_ALEN - sizeof(ifa->ifa_local)), &ifa->ifa_local, sizeof(ifa->ifa_local));
 		}
 	} else
 		memcpy(dev->dev_addr, card->mac_addr, ETH_ALEN);
diff --git a/drivers/isdn/mISDN/dsp_pipeline.c b/drivers/isdn/mISDN/dsp_pipeline.c
index 850260ab57d0..fdc800bda617 100644
--- a/drivers/isdn/mISDN/dsp_pipeline.c
+++ b/drivers/isdn/mISDN/dsp_pipeline.c
@@ -91,7 +91,7 @@ int mISDN_dsp_element_register(struct mISDN_dsp_element *elem)
 
 	entry->dev.class = elements_class;
 	dev_set_drvdata(&entry->dev, elem);
-	snprintf(entry->dev.bus_id, BUS_ID_SIZE, elem->name);
+	dev_set_name(&entry->dev, elem->name);
 	ret = device_register(&entry->dev);
 	if (ret) {
 		printk(KERN_ERR "%s: failed to register %s\n",
diff --git a/drivers/macintosh/macio_asic.c b/drivers/macintosh/macio_asic.c
index ec9e5f32f0ae..6e149f4a1fff 100644
--- a/drivers/macintosh/macio_asic.c
+++ b/drivers/macintosh/macio_asic.c
@@ -33,7 +33,7 @@
 
 #undef DEBUG
 
-#define MAX_NODE_NAME_SIZE (BUS_ID_SIZE - 12)
+#define MAX_NODE_NAME_SIZE (20 - 12)
 
 static struct macio_chip      *macio_on_hold;
 
@@ -240,7 +240,7 @@ static void macio_create_fixup_irq(struct macio_dev *dev, int index,
 	if (irq != NO_IRQ) {
 		dev->interrupt[index].start = irq;
 		dev->interrupt[index].flags = IORESOURCE_IRQ;
-		dev->interrupt[index].name = dev->ofdev.dev.bus_id;
+		dev->interrupt[index].name = dev_name(&dev->ofdev.dev);
 	}
 	if (dev->n_interrupts <= index)
 		dev->n_interrupts = index + 1;
@@ -303,7 +303,7 @@ static void macio_setup_interrupts(struct macio_dev *dev)
 			break;
 		res->start = irq;
 		res->flags = IORESOURCE_IRQ;
-		res->name = dev->ofdev.dev.bus_id;
+		res->name = dev_name(&dev->ofdev.dev);
 		if (macio_resource_quirks(np, res, i - 1)) {
 			memset(res, 0, sizeof(struct resource));
 			continue;
@@ -325,7 +325,7 @@ static void macio_setup_resources(struct macio_dev *dev,
 		if (index >= MACIO_DEV_COUNT_RESOURCES)
 			break;
 		*res = r;
-		res->name = dev->ofdev.dev.bus_id;
+		res->name = dev_name(&dev->ofdev.dev);
 
 		if (macio_resource_quirks(np, res, index)) {
 			memset(res, 0, sizeof(struct resource));
@@ -338,7 +338,7 @@ static void macio_setup_resources(struct macio_dev *dev,
 		if (insert_resource(parent_res, res)) {
 			printk(KERN_WARNING "Can't request resource "
 			       "%d for MacIO device %s\n",
-			       index, dev->ofdev.dev.bus_id);
+			       index, dev_name(&dev->ofdev.dev));
 		}
 	}
 	dev->n_resources = index;
@@ -385,8 +385,8 @@ static struct macio_dev * macio_add_one_device(struct macio_chip *chip,
 
 	/* MacIO itself has a different reg, we use it's PCI base */
 	if (np == chip->of_node) {
-		sprintf(dev->ofdev.dev.bus_id, "%1d.%08x:%.*s",
-			chip->lbus.index,
+		dev_set_name(&dev->ofdev.dev, "%1d.%08x:%.*s",
+			     chip->lbus.index,
 #ifdef CONFIG_PCI
 			(unsigned int)pci_resource_start(chip->lbus.pdev, 0),
 #else
@@ -395,9 +395,9 @@ static struct macio_dev * macio_add_one_device(struct macio_chip *chip,
 			MAX_NODE_NAME_SIZE, np->name);
 	} else {
 		reg = of_get_property(np, "reg", NULL);
-		sprintf(dev->ofdev.dev.bus_id, "%1d.%08x:%.*s",
-			chip->lbus.index,
-			reg ? *reg : 0, MAX_NODE_NAME_SIZE, np->name);
+		dev_set_name(&dev->ofdev.dev, "%1d.%08x:%.*s",
+			     chip->lbus.index,
+			     reg ? *reg : 0, MAX_NODE_NAME_SIZE, np->name);
 	}
 
 	/* Setup interrupts & resources */
@@ -408,7 +408,7 @@ static struct macio_dev * macio_add_one_device(struct macio_chip *chip,
 	/* Register with core */
 	if (of_device_register(&dev->ofdev) != 0) {
 		printk(KERN_DEBUG"macio: device registration error for %s!\n",
-		       dev->ofdev.dev.bus_id);
+		       dev_name(&dev->ofdev.dev));
 		kfree(dev);
 		return NULL;
 	}
@@ -558,7 +558,7 @@ err_out:
 		resource_no,
 		macio_resource_len(dev, resource_no),
 		macio_resource_start(dev, resource_no),
-		dev->ofdev.dev.bus_id);
+		dev_name(&dev->ofdev.dev));
 	return -EBUSY;
 }
 
diff --git a/drivers/macintosh/via-cuda.c b/drivers/macintosh/via-cuda.c
index 741a93a3eb61..62dd1fdafecf 100644
--- a/drivers/macintosh/via-cuda.c
+++ b/drivers/macintosh/via-cuda.c
@@ -23,7 +23,6 @@
 #else
 #include <asm/macintosh.h>
 #include <asm/macints.h>
-#include <asm/machw.h>
 #include <asm/mac_via.h>
 #endif
 #include <asm/io.h>
diff --git a/drivers/macintosh/via-macii.c b/drivers/macintosh/via-macii.c
index 6e6dd17ab572..817f37a875c9 100644
--- a/drivers/macintosh/via-macii.c
+++ b/drivers/macintosh/via-macii.c
@@ -33,7 +33,6 @@
 #include <linux/init.h>
 #include <asm/macintosh.h>
 #include <asm/macints.h>
-#include <asm/machw.h>
 #include <asm/mac_via.h>
 #include <asm/system.h>
 
diff --git a/drivers/macintosh/via-maciisi.c b/drivers/macintosh/via-maciisi.c
index 2dc788042707..4d686c0bdea0 100644
--- a/drivers/macintosh/via-maciisi.c
+++ b/drivers/macintosh/via-maciisi.c
@@ -24,7 +24,6 @@
 #include <linux/interrupt.h>
 #include <asm/macintosh.h>
 #include <asm/macints.h>
-#include <asm/machw.h>
 #include <asm/mac_via.h>
 
 static volatile unsigned char *via;
diff --git a/drivers/macintosh/via-pmu68k.c b/drivers/macintosh/via-pmu68k.c
index b64741c95ac4..fb9fa614a0e8 100644
--- a/drivers/macintosh/via-pmu68k.c
+++ b/drivers/macintosh/via-pmu68k.c
@@ -35,7 +35,6 @@
 
 #include <asm/macintosh.h>
 #include <asm/macints.h>
-#include <asm/machw.h>
 #include <asm/mac_via.h>
 
 #include <asm/pgtable.h>
diff --git a/drivers/macintosh/windfarm_smu_sat.c b/drivers/macintosh/windfarm_smu_sat.c
index 7f2be4baaeda..7847e981ac33 100644
--- a/drivers/macintosh/windfarm_smu_sat.c
+++ b/drivers/macintosh/windfarm_smu_sat.c
@@ -87,11 +87,12 @@ struct smu_sdbp_header *smu_sat_get_sdb_partition(unsigned int sat_id, int id,
 		return NULL;
 	}
 
-	len = i2c_smbus_read_word_data(&sat->i2c, 9);
-	if (len < 0) {
+	err = i2c_smbus_read_word_data(&sat->i2c, 9);
+	if (err < 0) {
 		printk(KERN_ERR "smu_sat_get_sdb_part rd len error\n");
 		return NULL;
 	}
+	len = err;
 	if (len == 0) {
 		printk(KERN_ERR "smu_sat_get_sdb_part no partition %x\n", id);
 		return NULL;
diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c
index ce26c84af064..dbc03c67fe98 100644
--- a/drivers/md/dm-crypt.c
+++ b/drivers/md/dm-crypt.c
@@ -1322,11 +1322,7 @@ static int __init dm_crypt_init(void)
 
 static void __exit dm_crypt_exit(void)
 {
-	int r = dm_unregister_target(&crypt_target);
-
-	if (r < 0)
-		DMERR("unregister failed %d", r);
-
+	dm_unregister_target(&crypt_target);
 	kmem_cache_destroy(_crypt_io_pool);
 }
 
diff --git a/drivers/md/dm-delay.c b/drivers/md/dm-delay.c
index 848b381f1173..59ee1b015d2d 100644
--- a/drivers/md/dm-delay.c
+++ b/drivers/md/dm-delay.c
@@ -364,11 +364,7 @@ bad_queue:
 
 static void __exit dm_delay_exit(void)
 {
-	int r = dm_unregister_target(&delay_target);
-
-	if (r < 0)
-		DMERR("unregister failed %d", r);
-
+	dm_unregister_target(&delay_target);
 	kmem_cache_destroy(delayed_cache);
 	destroy_workqueue(kdelayd_wq);
 }
diff --git a/drivers/md/dm-linear.c b/drivers/md/dm-linear.c
index 44042becad8a..bfa107f59d96 100644
--- a/drivers/md/dm-linear.c
+++ b/drivers/md/dm-linear.c
@@ -142,6 +142,7 @@ static struct target_type linear_target = {
 	.status = linear_status,
 	.ioctl  = linear_ioctl,
 	.merge  = linear_merge,
+	.features = DM_TARGET_SUPPORTS_BARRIERS,
 };
 
 int __init dm_linear_init(void)
@@ -156,8 +157,5 @@ int __init dm_linear_init(void)
 
 void dm_linear_exit(void)
 {
-	int r = dm_unregister_target(&linear_target);
-
-	if (r < 0)
-		DMERR("unregister failed %d", r);
+	dm_unregister_target(&linear_target);
 }
diff --git a/drivers/md/dm-log.c b/drivers/md/dm-log.c
index a8c0fc79ca78..bc9bf01a5da4 100644
--- a/drivers/md/dm-log.c
+++ b/drivers/md/dm-log.c
@@ -326,8 +326,6 @@ static void header_from_disk(struct log_header *core, struct log_header *disk)
 static int rw_header(struct log_c *lc, int rw)
 {
 	lc->io_req.bi_rw = rw;
-	lc->io_req.mem.ptr.vma = lc->disk_header;
-	lc->io_req.notify.fn = NULL;
 
 	return dm_io(&lc->io_req, 1, &lc->header_location, NULL);
 }
@@ -362,12 +360,6 @@ static int read_header(struct log_c *log)
 	return 0;
 }
 
-static inline int write_header(struct log_c *log)
-{
-	header_to_disk(&log->header, log->disk_header);
-	return rw_header(log, WRITE);
-}
-
 /*----------------------------------------------------------------
  * core log constructor/destructor
  *
@@ -454,7 +446,10 @@ static int create_log_context(struct dm_dirty_log *log, struct dm_target *ti,
 		buf_size = dm_round_up((LOG_OFFSET << SECTOR_SHIFT) +
 				       bitset_size, ti->limits.hardsect_size);
 		lc->header_location.count = buf_size >> SECTOR_SHIFT;
+
 		lc->io_req.mem.type = DM_IO_VMA;
+		lc->io_req.mem.ptr.vma = lc->disk_header;
+		lc->io_req.notify.fn = NULL;
 		lc->io_req.client = dm_io_client_create(dm_div_up(buf_size,
 								   PAGE_SIZE));
 		if (IS_ERR(lc->io_req.client)) {
@@ -467,6 +462,7 @@ static int create_log_context(struct dm_dirty_log *log, struct dm_target *ti,
 		lc->disk_header = vmalloc(buf_size);
 		if (!lc->disk_header) {
 			DMWARN("couldn't allocate disk log buffer");
+			dm_io_client_destroy(lc->io_req.client);
 			kfree(lc);
 			return -ENOMEM;
 		}
@@ -482,6 +478,8 @@ static int create_log_context(struct dm_dirty_log *log, struct dm_target *ti,
 		DMWARN("couldn't allocate sync bitset");
 		if (!dev)
 			vfree(lc->clean_bits);
+		else
+			dm_io_client_destroy(lc->io_req.client);
 		vfree(lc->disk_header);
 		kfree(lc);
 		return -ENOMEM;
@@ -495,6 +493,8 @@ static int create_log_context(struct dm_dirty_log *log, struct dm_target *ti,
 		vfree(lc->sync_bits);
 		if (!dev)
 			vfree(lc->clean_bits);
+		else
+			dm_io_client_destroy(lc->io_req.client);
 		vfree(lc->disk_header);
 		kfree(lc);
 		return -ENOMEM;
@@ -631,8 +631,10 @@ static int disk_resume(struct dm_dirty_log *log)
 	/* set the correct number of regions in the header */
 	lc->header.nr_regions = lc->region_count;
 
+	header_to_disk(&lc->header, lc->disk_header);
+
 	/* write the new header */
-	r = write_header(lc);
+	r = rw_header(lc, WRITE);
 	if (r) {
 		DMWARN("%s: Failed to write header on dirty region log device",
 		       lc->log_dev->name);
@@ -682,7 +684,7 @@ static int disk_flush(struct dm_dirty_log *log)
 	if (!lc->touched)
 		return 0;
 
-	r = write_header(lc);
+	r = rw_header(lc, WRITE);
 	if (r)
 		fail_log_device(lc);
 	else
diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c
index 3d7f4923cd13..345a26047ae0 100644
--- a/drivers/md/dm-mpath.c
+++ b/drivers/md/dm-mpath.c
@@ -1495,14 +1495,10 @@ static int __init dm_multipath_init(void)
 
 static void __exit dm_multipath_exit(void)
 {
-	int r;
-
 	destroy_workqueue(kmpath_handlerd);
 	destroy_workqueue(kmultipathd);
 
-	r = dm_unregister_target(&multipath_target);
-	if (r < 0)
-		DMERR("target unregister failed %d", r);
+	dm_unregister_target(&multipath_target);
 	kmem_cache_destroy(_mpio_cache);
 }
 
diff --git a/drivers/md/dm-raid1.c b/drivers/md/dm-raid1.c
index ec43f9fa4b2a..a542ca4b1769 100644
--- a/drivers/md/dm-raid1.c
+++ b/drivers/md/dm-raid1.c
@@ -1300,11 +1300,7 @@ static int __init dm_mirror_init(void)
 
 static void __exit dm_mirror_exit(void)
 {
-	int r;
-
-	r = dm_unregister_target(&mirror_target);
-	if (r < 0)
-		DMERR("unregister failed %d", r);
+	dm_unregister_target(&mirror_target);
 }
 
 /* Module hooks */
diff --git a/drivers/md/dm-snap.c b/drivers/md/dm-snap.c
index 6c96db26b87c..a8005b43a06b 100644
--- a/drivers/md/dm-snap.c
+++ b/drivers/md/dm-snap.c
@@ -9,6 +9,7 @@
 #include <linux/blkdev.h>
 #include <linux/ctype.h>
 #include <linux/device-mapper.h>
+#include <linux/delay.h>
 #include <linux/fs.h>
 #include <linux/init.h>
 #include <linux/kdev_t.h>
@@ -735,7 +736,7 @@ static void snapshot_dtr(struct dm_target *ti)
 	unregister_snapshot(s);
 
 	while (atomic_read(&s->pending_exceptions_count))
-		yield();
+		msleep(1);
 	/*
 	 * Ensure instructions in mempool_destroy aren't reordered
 	 * before atomic_read.
@@ -888,10 +889,10 @@ static void pending_complete(struct dm_snap_pending_exception *pe, int success)
 
 	/*
 	 * Check for conflicting reads. This is extremely improbable,
-	 * so yield() is sufficient and there is no need for a wait queue.
+	 * so msleep(1) is sufficient and there is no need for a wait queue.
 	 */
 	while (__chunk_is_tracked(s, pe->e.old_chunk))
-		yield();
+		msleep(1);
 
 	/*
 	 * Add a proper exception, and remove the
@@ -1469,17 +1470,10 @@ static int __init dm_snapshot_init(void)
 
 static void __exit dm_snapshot_exit(void)
 {
-	int r;
-
 	destroy_workqueue(ksnapd);
 
-	r = dm_unregister_target(&snapshot_target);
-	if (r)
-		DMERR("snapshot unregister failed %d", r);
-
-	r = dm_unregister_target(&origin_target);
-	if (r)
-		DMERR("origin unregister failed %d", r);
+	dm_unregister_target(&snapshot_target);
+	dm_unregister_target(&origin_target);
 
 	exit_origin_hash();
 	kmem_cache_destroy(pending_cache);
diff --git a/drivers/md/dm-stripe.c b/drivers/md/dm-stripe.c
index 9e4ef88d421e..41569bc60abc 100644
--- a/drivers/md/dm-stripe.c
+++ b/drivers/md/dm-stripe.c
@@ -337,9 +337,7 @@ int __init dm_stripe_init(void)
 
 void dm_stripe_exit(void)
 {
-	if (dm_unregister_target(&stripe_target))
-		DMWARN("target unregistration failed");
-
+	dm_unregister_target(&stripe_target);
 	destroy_workqueue(kstriped);
 
 	return;
diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index a63161aec487..ebaaf72cd822 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -38,6 +38,8 @@ struct dm_table {
 	sector_t *highs;
 	struct dm_target *targets;
 
+	unsigned barriers_supported:1;
+
 	/*
 	 * Indicates the rw permissions for the new logical
 	 * device.  This should be a combination of FMODE_READ
@@ -227,6 +229,7 @@ int dm_table_create(struct dm_table **result, fmode_t mode,
 
 	INIT_LIST_HEAD(&t->devices);
 	atomic_set(&t->holders, 1);
+	t->barriers_supported = 1;
 
 	if (!num_targets)
 		num_targets = KEYS_PER_NODE;
@@ -668,7 +671,7 @@ static void check_for_valid_limits(struct io_restrictions *rs)
 	if (!rs->max_segment_size)
 		rs->max_segment_size = MAX_SEGMENT_SIZE;
 	if (!rs->seg_boundary_mask)
-		rs->seg_boundary_mask = -1;
+		rs->seg_boundary_mask = BLK_SEG_BOUNDARY_MASK;
 	if (!rs->bounce_pfn)
 		rs->bounce_pfn = -1;
 }
@@ -728,6 +731,10 @@ int dm_table_add_target(struct dm_table *t, const char *type,
 	/* FIXME: the plan is to combine high here and then have
 	 * the merge fn apply the target level restrictions. */
 	combine_restrictions_low(&t->limits, &tgt->limits);
+
+	if (!(tgt->type->features & DM_TARGET_SUPPORTS_BARRIERS))
+		t->barriers_supported = 0;
+
 	return 0;
 
  bad:
@@ -772,6 +779,12 @@ int dm_table_complete(struct dm_table *t)
 
 	check_for_valid_limits(&t->limits);
 
+	/*
+	 * We only support barriers if there is exactly one underlying device.
+	 */
+	if (!list_is_singular(&t->devices))
+		t->barriers_supported = 0;
+
 	/* how many indexes will the btree have ? */
 	leaf_nodes = dm_div_up(t->num_targets, KEYS_PER_NODE);
 	t->depth = 1 + int_log(leaf_nodes, CHILDREN_PER_NODE);
@@ -986,6 +999,12 @@ struct mapped_device *dm_table_get_md(struct dm_table *t)
 	return t->md;
 }
 
+int dm_table_barrier_ok(struct dm_table *t)
+{
+	return t->barriers_supported;
+}
+EXPORT_SYMBOL(dm_table_barrier_ok);
+
 EXPORT_SYMBOL(dm_vcalloc);
 EXPORT_SYMBOL(dm_get_device);
 EXPORT_SYMBOL(dm_put_device);
diff --git a/drivers/md/dm-target.c b/drivers/md/dm-target.c
index 835cf95b857f..7decf10006e4 100644
--- a/drivers/md/dm-target.c
+++ b/drivers/md/dm-target.c
@@ -130,26 +130,26 @@ int dm_register_target(struct target_type *t)
 	return rv;
 }
 
-int dm_unregister_target(struct target_type *t)
+void dm_unregister_target(struct target_type *t)
 {
 	struct tt_internal *ti;
 
 	down_write(&_lock);
 	if (!(ti = __find_target_type(t->name))) {
-		up_write(&_lock);
-		return -EINVAL;
+		DMCRIT("Unregistering unrecognised target: %s", t->name);
+		BUG();
 	}
 
 	if (ti->use) {
-		up_write(&_lock);
-		return -ETXTBSY;
+		DMCRIT("Attempt to unregister target still in use: %s",
+		       t->name);
+		BUG();
 	}
 
 	list_del(&ti->list);
 	kfree(ti);
 
 	up_write(&_lock);
-	return 0;
 }
 
 /*
@@ -187,8 +187,7 @@ int __init dm_target_init(void)
 
 void dm_target_exit(void)
 {
-	if (dm_unregister_target(&error_target))
-		DMWARN("error target unregistration failed");
+	dm_unregister_target(&error_target);
 }
 
 EXPORT_SYMBOL(dm_register_target);
diff --git a/drivers/md/dm-zero.c b/drivers/md/dm-zero.c
index cdbf126ec106..bbc97030c0c2 100644
--- a/drivers/md/dm-zero.c
+++ b/drivers/md/dm-zero.c
@@ -69,10 +69,7 @@ static int __init dm_zero_init(void)
 
 static void __exit dm_zero_exit(void)
 {
-	int r = dm_unregister_target(&zero_target);
-
-	if (r < 0)
-		DMERR("unregister failed %d", r);
+	dm_unregister_target(&zero_target);
 }
 
 module_init(dm_zero_init)
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index c99e4728ff41..50a1f10729d8 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -31,6 +31,7 @@ static unsigned int _major = 0;
 
 static DEFINE_SPINLOCK(_minor_lock);
 /*
+ * For bio-based dm.
  * One of these is allocated per bio.
  */
 struct dm_io {
@@ -42,6 +43,7 @@ struct dm_io {
 };
 
 /*
+ * For bio-based dm.
  * One of these is allocated per target within a bio.  Hopefully
  * this will be simplified out one day.
  */
@@ -51,6 +53,27 @@ struct dm_target_io {
 	union map_info info;
 };
 
+/*
+ * For request-based dm.
+ * One of these is allocated per request.
+ */
+struct dm_rq_target_io {
+	struct mapped_device *md;
+	struct dm_target *ti;
+	struct request *orig, clone;
+	int error;
+	union map_info info;
+};
+
+/*
+ * For request-based dm.
+ * One of these is allocated per bio.
+ */
+struct dm_rq_clone_bio_info {
+	struct bio *orig;
+	struct request *rq;
+};
+
 union map_info *dm_get_mapinfo(struct bio *bio)
 {
 	if (bio && bio->bi_private)
@@ -146,6 +169,8 @@ struct mapped_device {
 #define MIN_IOS 256
 static struct kmem_cache *_io_cache;
 static struct kmem_cache *_tio_cache;
+static struct kmem_cache *_rq_tio_cache;
+static struct kmem_cache *_rq_bio_info_cache;
 
 static int __init local_init(void)
 {
@@ -161,9 +186,17 @@ static int __init local_init(void)
 	if (!_tio_cache)
 		goto out_free_io_cache;
 
+	_rq_tio_cache = KMEM_CACHE(dm_rq_target_io, 0);
+	if (!_rq_tio_cache)
+		goto out_free_tio_cache;
+
+	_rq_bio_info_cache = KMEM_CACHE(dm_rq_clone_bio_info, 0);
+	if (!_rq_bio_info_cache)
+		goto out_free_rq_tio_cache;
+
 	r = dm_uevent_init();
 	if (r)
-		goto out_free_tio_cache;
+		goto out_free_rq_bio_info_cache;
 
 	_major = major;
 	r = register_blkdev(_major, _name);
@@ -177,6 +210,10 @@ static int __init local_init(void)
 
 out_uevent_exit:
 	dm_uevent_exit();
+out_free_rq_bio_info_cache:
+	kmem_cache_destroy(_rq_bio_info_cache);
+out_free_rq_tio_cache:
+	kmem_cache_destroy(_rq_tio_cache);
 out_free_tio_cache:
 	kmem_cache_destroy(_tio_cache);
 out_free_io_cache:
@@ -187,6 +224,8 @@ out_free_io_cache:
 
 static void local_exit(void)
 {
+	kmem_cache_destroy(_rq_bio_info_cache);
+	kmem_cache_destroy(_rq_tio_cache);
 	kmem_cache_destroy(_tio_cache);
 	kmem_cache_destroy(_io_cache);
 	unregister_blkdev(_major, _name);
@@ -794,7 +833,11 @@ static int __split_bio(struct mapped_device *md, struct bio *bio)
 	ci.map = dm_get_table(md);
 	if (unlikely(!ci.map))
 		return -EIO;
-
+	if (unlikely(bio_barrier(bio) && !dm_table_barrier_ok(ci.map))) {
+		dm_table_put(ci.map);
+		bio_endio(bio, -EOPNOTSUPP);
+		return 0;
+	}
 	ci.md = md;
 	ci.bio = bio;
 	ci.io = alloc_io(md);
@@ -878,15 +921,6 @@ static int dm_request(struct request_queue *q, struct bio *bio)
 	struct mapped_device *md = q->queuedata;
 	int cpu;
 
-	/*
-	 * There is no use in forwarding any barrier request since we can't
-	 * guarantee it is (or can be) handled by the targets correctly.
-	 */
-	if (unlikely(bio_barrier(bio))) {
-		bio_endio(bio, -EOPNOTSUPP);
-		return 0;
-	}
-
 	down_read(&md->io_lock);
 
 	cpu = part_stat_lock();
@@ -1328,8 +1362,8 @@ void dm_put(struct mapped_device *md)
 			dm_table_presuspend_targets(map);
 			dm_table_postsuspend_targets(map);
 		}
-		__unbind(md);
 		dm_table_put(map);
+		__unbind(md);
 		free_dev(md);
 	}
 }
diff --git a/drivers/md/dm.h b/drivers/md/dm.h
index 0ade60cdef42..5b5d08ba9e92 100644
--- a/drivers/md/dm.h
+++ b/drivers/md/dm.h
@@ -51,6 +51,7 @@ int dm_table_any_congested(struct dm_table *t, int bdi_bits);
  * To check the return value from dm_table_find_target().
  */
 #define dm_target_is_valid(t) ((t)->table)
+int dm_table_barrier_ok(struct dm_table *t);
 
 /*-----------------------------------------------------------------
  * A registry of target types.
diff --git a/drivers/media/dvb/Kconfig b/drivers/media/dvb/Kconfig
index 0bcd852576d6..e5cb1d791415 100644
--- a/drivers/media/dvb/Kconfig
+++ b/drivers/media/dvb/Kconfig
@@ -38,6 +38,8 @@ comment "Supported SDMC DM1105 Adapters"
 	depends on DVB_CORE && PCI && I2C
 source "drivers/media/dvb/dm1105/Kconfig"
 
+source "drivers/media/dvb/firesat/Kconfig"
+
 comment "Supported DVB Frontends"
 	depends on DVB_CORE
 source "drivers/media/dvb/frontends/Kconfig"
diff --git a/drivers/media/dvb/Makefile b/drivers/media/dvb/Makefile
index f91e9eb15e52..cb765816f76c 100644
--- a/drivers/media/dvb/Makefile
+++ b/drivers/media/dvb/Makefile
@@ -3,3 +3,5 @@
 #
 
 obj-y        := dvb-core/ frontends/ ttpci/ ttusb-dec/ ttusb-budget/ b2c2/ bt8xx/ dvb-usb/ pluto2/ siano/ dm1105/
+
+obj-$(CONFIG_DVB_FIREDTV)	+= firesat/
diff --git a/drivers/media/dvb/firesat/Kconfig b/drivers/media/dvb/firesat/Kconfig
new file mode 100644
index 000000000000..6aa5dce8040c
--- /dev/null
+++ b/drivers/media/dvb/firesat/Kconfig
@@ -0,0 +1,12 @@
+config DVB_FIREDTV
+	tristate "FireDTV (FireWire attached DVB receivers)"
+	depends on DVB_CORE && IEEE1394
+	help
+	  Support for DVB receivers from Digital Everywhere, known as FireDTV
+	  and FloppyDTV, which are connected via IEEE 1394 (FireWire).
+
+	  These devices don't have an MPEG decoder built in, so you need
+	  an external software decoder to watch TV.
+
+	  To compile this driver as a module, say M here: the module will be
+	  called firedtv.
diff --git a/drivers/media/dvb/firesat/Makefile b/drivers/media/dvb/firesat/Makefile
new file mode 100644
index 000000000000..9e49edc7c49d
--- /dev/null
+++ b/drivers/media/dvb/firesat/Makefile
@@ -0,0 +1,13 @@
+firedtv-objs := firesat_1394.o	\
+		firesat_dvb.o	\
+		firesat_fe.o	\
+		firesat_iso.o	\
+		avc_api.o	\
+		cmp.o		\
+		firesat-rc.o	\
+		firesat-ci.o
+
+obj-$(CONFIG_DVB_FIREDTV) += firedtv.o
+
+EXTRA_CFLAGS := -Idrivers/ieee1394
+EXTRA_CFLAGS += -Idrivers/media/dvb/dvb-core
diff --git a/drivers/media/dvb/firesat/avc_api.c b/drivers/media/dvb/firesat/avc_api.c
new file mode 100644
index 000000000000..3a4da73f0798
--- /dev/null
+++ b/drivers/media/dvb/firesat/avc_api.c
@@ -0,0 +1,1051 @@
+/*
+ * FireDTV driver (formerly known as FireSAT)
+ *
+ * Copyright (C) 2004 Andreas Monitzer <andy@monitzer.com>
+ * Copyright (C) 2008 Ben Backx <ben@bbackx.com>
+ * Copyright (C) 2008 Henrik Kurelid <henrik@kurelid.se>
+ *
+ *	This program is free software; you can redistribute it and/or
+ *	modify it under the terms of the GNU General Public License as
+ *	published by the Free Software Foundation; either version 2 of
+ *	the License, or (at your option) any later version.
+ */
+
+#include <linux/bug.h>
+#include <linux/crc32.h>
+#include <linux/delay.h>
+#include <linux/device.h>
+#include <linux/kernel.h>
+#include <linux/moduleparam.h>
+#include <linux/mutex.h>
+#include <linux/string.h>
+#include <linux/wait.h>
+#include <linux/workqueue.h>
+
+#include <ieee1394_transactions.h>
+#include <nodemgr.h>
+
+#include "avc_api.h"
+#include "firesat.h"
+#include "firesat-rc.h"
+
+#define FCP_COMMAND_REGISTER	0xfffff0000b00ULL
+
+static int __avc_write(struct firesat *firesat,
+		       const AVCCmdFrm *CmdFrm, AVCRspFrm *RspFrm)
+{
+	int err, retry;
+
+	if (RspFrm)
+		firesat->avc_reply_received = false;
+
+	for (retry = 0; retry < 6; retry++) {
+		err = hpsb_node_write(firesat->ud->ne, FCP_COMMAND_REGISTER,
+				      (quadlet_t *)CmdFrm, CmdFrm->length);
+		if (err) {
+			firesat->avc_reply_received = true;
+			dev_err(&firesat->ud->device,
+				"FCP command write failed\n");
+			return err;
+		}
+
+		if (!RspFrm)
+			return 0;
+
+		/*
+		 * AV/C specs say that answers should be sent within 150 ms.
+		 * Time out after 200 ms.
+		 */
+		if (wait_event_timeout(firesat->avc_wait,
+				       firesat->avc_reply_received,
+				       HZ / 5) != 0) {
+			memcpy(RspFrm, firesat->respfrm, firesat->resp_length);
+			RspFrm->length = firesat->resp_length;
+
+			return 0;
+		}
+	}
+	dev_err(&firesat->ud->device, "FCP response timed out\n");
+	return -ETIMEDOUT;
+}
+
+static int avc_write(struct firesat *firesat,
+		     const AVCCmdFrm *CmdFrm, AVCRspFrm *RspFrm)
+{
+	int ret;
+
+	if (mutex_lock_interruptible(&firesat->avc_mutex))
+		return -EINTR;
+
+	ret = __avc_write(firesat, CmdFrm, RspFrm);
+
+	mutex_unlock(&firesat->avc_mutex);
+	return ret;
+}
+
+int avc_recv(struct firesat *firesat, u8 *data, size_t length)
+{
+	AVCRspFrm *RspFrm = (AVCRspFrm *)data;
+
+	if (length >= 8 &&
+	    RspFrm->operand[0] == SFE_VENDOR_DE_COMPANYID_0 &&
+	    RspFrm->operand[1] == SFE_VENDOR_DE_COMPANYID_1 &&
+	    RspFrm->operand[2] == SFE_VENDOR_DE_COMPANYID_2 &&
+	    RspFrm->operand[3] == SFE_VENDOR_OPCODE_REGISTER_REMOTE_CONTROL) {
+		if (RspFrm->resp == CHANGED) {
+			firesat_handle_rc(firesat,
+			    RspFrm->operand[4] << 8 | RspFrm->operand[5]);
+			schedule_work(&firesat->remote_ctrl_work);
+		} else if (RspFrm->resp != INTERIM) {
+			dev_info(&firesat->ud->device,
+				 "remote control result = %d\n", RspFrm->resp);
+		}
+		return 0;
+	}
+
+	if (firesat->avc_reply_received) {
+		dev_err(&firesat->ud->device,
+			"received out-of-order AVC response, ignored\n");
+		return -EIO;
+	}
+
+	memcpy(firesat->respfrm, data, length);
+	firesat->resp_length = length;
+
+	firesat->avc_reply_received = true;
+	wake_up(&firesat->avc_wait);
+
+	return 0;
+}
+
+/*
+ * tuning command for setting the relative LNB frequency
+ * (not supported by the AVC standard)
+ */
+static void avc_tuner_tuneqpsk(struct firesat *firesat,
+		struct dvb_frontend_parameters *params, AVCCmdFrm *CmdFrm)
+{
+	CmdFrm->opcode = VENDOR;
+
+	CmdFrm->operand[0] = SFE_VENDOR_DE_COMPANYID_0;
+	CmdFrm->operand[1] = SFE_VENDOR_DE_COMPANYID_1;
+	CmdFrm->operand[2] = SFE_VENDOR_DE_COMPANYID_2;
+	CmdFrm->operand[3] = SFE_VENDOR_OPCODE_TUNE_QPSK;
+
+	CmdFrm->operand[4] = (params->frequency >> 24) & 0xff;
+	CmdFrm->operand[5] = (params->frequency >> 16) & 0xff;
+	CmdFrm->operand[6] = (params->frequency >> 8) & 0xff;
+	CmdFrm->operand[7] = params->frequency & 0xff;
+
+	CmdFrm->operand[8] = ((params->u.qpsk.symbol_rate / 1000) >> 8) & 0xff;
+	CmdFrm->operand[9] = (params->u.qpsk.symbol_rate / 1000) & 0xff;
+
+	switch(params->u.qpsk.fec_inner) {
+	case FEC_1_2:
+		CmdFrm->operand[10] = 0x1; break;
+	case FEC_2_3:
+		CmdFrm->operand[10] = 0x2; break;
+	case FEC_3_4:
+		CmdFrm->operand[10] = 0x3; break;
+	case FEC_5_6:
+		CmdFrm->operand[10] = 0x4; break;
+	case FEC_7_8:
+		CmdFrm->operand[10] = 0x5; break;
+	case FEC_4_5:
+	case FEC_8_9:
+	case FEC_AUTO:
+	default:
+		CmdFrm->operand[10] = 0x0;
+	}
+
+	if (firesat->voltage == 0xff)
+		CmdFrm->operand[11] = 0xff;
+	else if (firesat->voltage == SEC_VOLTAGE_18) /* polarisation */
+		CmdFrm->operand[11] = 0;
+	else
+		CmdFrm->operand[11] = 1;
+
+	if (firesat->tone == 0xff)
+		CmdFrm->operand[12] = 0xff;
+	else if (firesat->tone == SEC_TONE_ON) /* band */
+		CmdFrm->operand[12] = 1;
+	else
+		CmdFrm->operand[12] = 0;
+
+	if (firesat->type == FireSAT_DVB_S2) {
+		CmdFrm->operand[13] = 0x1;
+		CmdFrm->operand[14] = 0xff;
+		CmdFrm->operand[15] = 0xff;
+		CmdFrm->length = 20;
+	} else {
+		CmdFrm->length = 16;
+	}
+}
+
+static void avc_tuner_dsd_dvb_c(struct dvb_frontend_parameters *params,
+		AVCCmdFrm *CmdFrm)
+{
+	M_VALID_FLAGS flags;
+
+	flags.Bits.Modulation = params->u.qam.modulation != QAM_AUTO;
+	flags.Bits.FEC_inner = params->u.qam.fec_inner != FEC_AUTO;
+	flags.Bits.FEC_outer = 0;
+	flags.Bits.Symbol_Rate = 1;
+	flags.Bits.Frequency = 1;
+	flags.Bits.Orbital_Pos = 0;
+	flags.Bits.Polarisation = 0;
+	flags.Bits.reserved_fields = 0;
+	flags.Bits.reserved1 = 0;
+	flags.Bits.Network_ID = 0;
+
+	CmdFrm->opcode	= DSD;
+
+	CmdFrm->operand[0]  = 0;    /* source plug */
+	CmdFrm->operand[1]  = 0xd2; /* subfunction replace */
+	CmdFrm->operand[2]  = 0x20; /* system id = DVB */
+	CmdFrm->operand[3]  = 0x00; /* antenna number */
+	/* system_specific_multiplex selection_length */
+	CmdFrm->operand[4]  = 0x11;
+	CmdFrm->operand[5]  = flags.Valid_Word.ByteHi; /* valid_flags [0] */
+	CmdFrm->operand[6]  = flags.Valid_Word.ByteLo; /* valid_flags [1] */
+	CmdFrm->operand[7]  = 0x00;
+	CmdFrm->operand[8]  = 0x00;
+	CmdFrm->operand[9]  = 0x00;
+	CmdFrm->operand[10] = 0x00;
+
+	CmdFrm->operand[11] =
+		(((params->frequency / 4000) >> 16) & 0xff) | (2 << 6);
+	CmdFrm->operand[12] =
+		((params->frequency / 4000) >> 8) & 0xff;
+	CmdFrm->operand[13] = (params->frequency / 4000) & 0xff;
+	CmdFrm->operand[14] =
+		((params->u.qpsk.symbol_rate / 1000) >> 12) & 0xff;
+	CmdFrm->operand[15] =
+		((params->u.qpsk.symbol_rate / 1000) >> 4) & 0xff;
+	CmdFrm->operand[16] =
+		((params->u.qpsk.symbol_rate / 1000) << 4) & 0xf0;
+	CmdFrm->operand[17] = 0x00;
+
+	switch (params->u.qpsk.fec_inner) {
+	case FEC_1_2:
+		CmdFrm->operand[18] = 0x1; break;
+	case FEC_2_3:
+		CmdFrm->operand[18] = 0x2; break;
+	case FEC_3_4:
+		CmdFrm->operand[18] = 0x3; break;
+	case FEC_5_6:
+		CmdFrm->operand[18] = 0x4; break;
+	case FEC_7_8:
+		CmdFrm->operand[18] = 0x5; break;
+	case FEC_8_9:
+		CmdFrm->operand[18] = 0x6; break;
+	case FEC_4_5:
+		CmdFrm->operand[18] = 0x8; break;
+	case FEC_AUTO:
+	default:
+		CmdFrm->operand[18] = 0x0;
+	}
+	switch (params->u.qam.modulation) {
+	case QAM_16:
+		CmdFrm->operand[19] = 0x08; break;
+	case QAM_32:
+		CmdFrm->operand[19] = 0x10; break;
+	case QAM_64:
+		CmdFrm->operand[19] = 0x18; break;
+	case QAM_128:
+		CmdFrm->operand[19] = 0x20; break;
+	case QAM_256:
+		CmdFrm->operand[19] = 0x28; break;
+	case QAM_AUTO:
+	default:
+		CmdFrm->operand[19] = 0x00;
+	}
+	CmdFrm->operand[20] = 0x00;
+	CmdFrm->operand[21] = 0x00;
+	/* Nr_of_dsd_sel_specs = 0 -> no PIDs are transmitted */
+	CmdFrm->operand[22] = 0x00;
+
+	CmdFrm->length = 28;
+}
+
+static void avc_tuner_dsd_dvb_t(struct dvb_frontend_parameters *params,
+		AVCCmdFrm *CmdFrm)
+{
+	M_VALID_FLAGS flags;
+
+	flags.Bits_T.GuardInterval =
+		params->u.ofdm.guard_interval != GUARD_INTERVAL_AUTO;
+	flags.Bits_T.CodeRateLPStream =
+		params->u.ofdm.code_rate_LP != FEC_AUTO;
+	flags.Bits_T.CodeRateHPStream =
+		params->u.ofdm.code_rate_HP != FEC_AUTO;
+	flags.Bits_T.HierarchyInfo =
+		params->u.ofdm.hierarchy_information != HIERARCHY_AUTO;
+	flags.Bits_T.Constellation =
+		params->u.ofdm.constellation != QAM_AUTO;
+	flags.Bits_T.Bandwidth =
+		params->u.ofdm.bandwidth != BANDWIDTH_AUTO;
+	flags.Bits_T.CenterFrequency = 1;
+	flags.Bits_T.reserved1 = 0;
+	flags.Bits_T.reserved2 = 0;
+	flags.Bits_T.OtherFrequencyFlag = 0;
+	flags.Bits_T.TransmissionMode =
+		params->u.ofdm.transmission_mode != TRANSMISSION_MODE_AUTO;
+	flags.Bits_T.NetworkId = 0;
+
+	CmdFrm->opcode	= DSD;
+
+	CmdFrm->operand[0]  = 0;    /* source plug */
+	CmdFrm->operand[1]  = 0xd2; /* subfunction replace */
+	CmdFrm->operand[2]  = 0x20; /* system id = DVB */
+	CmdFrm->operand[3]  = 0x00; /* antenna number */
+	/* system_specific_multiplex selection_length */
+	CmdFrm->operand[4]  = 0x0c;
+	CmdFrm->operand[5]  = flags.Valid_Word.ByteHi; /* valid_flags [0] */
+	CmdFrm->operand[6]  = flags.Valid_Word.ByteLo; /* valid_flags [1] */
+	CmdFrm->operand[7]  = 0x0;
+	CmdFrm->operand[8]  = (params->frequency / 10) >> 24;
+	CmdFrm->operand[9]  = ((params->frequency / 10) >> 16) & 0xff;
+	CmdFrm->operand[10] = ((params->frequency / 10) >>  8) & 0xff;
+	CmdFrm->operand[11] = (params->frequency / 10) & 0xff;
+
+	switch (params->u.ofdm.bandwidth) {
+	case BANDWIDTH_7_MHZ:
+		CmdFrm->operand[12] = 0x20; break;
+	case BANDWIDTH_8_MHZ:
+	case BANDWIDTH_6_MHZ: /* not defined by AVC spec */
+	case BANDWIDTH_AUTO:
+	default:
+		CmdFrm->operand[12] = 0x00;
+	}
+	switch (params->u.ofdm.constellation) {
+	case QAM_16:
+		CmdFrm->operand[13] = 1 << 6; break;
+	case QAM_64:
+		CmdFrm->operand[13] = 2 << 6; break;
+	case QPSK:
+	default:
+		CmdFrm->operand[13] = 0x00;
+	}
+	switch (params->u.ofdm.hierarchy_information) {
+	case HIERARCHY_1:
+		CmdFrm->operand[13] |= 1 << 3; break;
+	case HIERARCHY_2:
+		CmdFrm->operand[13] |= 2 << 3; break;
+	case HIERARCHY_4:
+		CmdFrm->operand[13] |= 3 << 3; break;
+	case HIERARCHY_AUTO:
+	case HIERARCHY_NONE:
+	default:
+		break;
+	}
+	switch (params->u.ofdm.code_rate_HP) {
+	case FEC_2_3:
+		CmdFrm->operand[13] |= 1; break;
+	case FEC_3_4:
+		CmdFrm->operand[13] |= 2; break;
+	case FEC_5_6:
+		CmdFrm->operand[13] |= 3; break;
+	case FEC_7_8:
+		CmdFrm->operand[13] |= 4; break;
+	case FEC_1_2:
+	default:
+		break;
+	}
+	switch (params->u.ofdm.code_rate_LP) {
+	case FEC_2_3:
+		CmdFrm->operand[14] = 1 << 5; break;
+	case FEC_3_4:
+		CmdFrm->operand[14] = 2 << 5; break;
+	case FEC_5_6:
+		CmdFrm->operand[14] = 3 << 5; break;
+	case FEC_7_8:
+		CmdFrm->operand[14] = 4 << 5; break;
+	case FEC_1_2:
+	default:
+		CmdFrm->operand[14] = 0x00; break;
+	}
+	switch (params->u.ofdm.guard_interval) {
+	case GUARD_INTERVAL_1_16:
+		CmdFrm->operand[14] |= 1 << 3; break;
+	case GUARD_INTERVAL_1_8:
+		CmdFrm->operand[14] |= 2 << 3; break;
+	case GUARD_INTERVAL_1_4:
+		CmdFrm->operand[14] |= 3 << 3; break;
+	case GUARD_INTERVAL_1_32:
+	case GUARD_INTERVAL_AUTO:
+	default:
+		break;
+	}
+	switch (params->u.ofdm.transmission_mode) {
+	case TRANSMISSION_MODE_8K:
+		CmdFrm->operand[14] |= 1 << 1; break;
+	case TRANSMISSION_MODE_2K:
+	case TRANSMISSION_MODE_AUTO:
+	default:
+		break;
+	}
+
+	CmdFrm->operand[15] = 0x00; /* network_ID[0] */
+	CmdFrm->operand[16] = 0x00; /* network_ID[1] */
+	/* Nr_of_dsd_sel_specs = 0 -> no PIDs are transmitted */
+	CmdFrm->operand[17] = 0x00;
+
+	CmdFrm->length = 24;
+}
+
+int avc_tuner_dsd(struct firesat *firesat,
+		  struct dvb_frontend_parameters *params)
+{
+	AVCCmdFrm CmdFrm;
+	AVCRspFrm RspFrm;
+
+	memset(&CmdFrm, 0, sizeof(AVCCmdFrm));
+
+	CmdFrm.cts	= AVC;
+	CmdFrm.ctype	= CONTROL;
+	CmdFrm.sutyp	= 0x5;
+	CmdFrm.suid	= firesat->subunit;
+
+	switch (firesat->type) {
+	case FireSAT_DVB_S:
+	case FireSAT_DVB_S2:
+		avc_tuner_tuneqpsk(firesat, params, &CmdFrm); break;
+	case FireSAT_DVB_C:
+		avc_tuner_dsd_dvb_c(params, &CmdFrm); break;
+	case FireSAT_DVB_T:
+		avc_tuner_dsd_dvb_t(params, &CmdFrm); break;
+	default:
+		BUG();
+	}
+
+	if (avc_write(firesat, &CmdFrm, &RspFrm) < 0)
+		return -EIO;
+
+	msleep(500);
+#if 0
+	/* FIXME: */
+	/* u8 *status was an out-parameter of avc_tuner_dsd, unused by caller */
+	if(status)
+		*status=RspFrm.operand[2];
+#endif
+	return 0;
+}
+
+int avc_tuner_set_pids(struct firesat *firesat, unsigned char pidc, u16 pid[])
+{
+	AVCCmdFrm CmdFrm;
+	AVCRspFrm RspFrm;
+	int pos, k;
+
+	if (pidc > 16 && pidc != 0xff)
+		return -EINVAL;
+
+	memset(&CmdFrm, 0, sizeof(AVCCmdFrm));
+
+	CmdFrm.cts	= AVC;
+	CmdFrm.ctype	= CONTROL;
+	CmdFrm.sutyp	= 0x5;
+	CmdFrm.suid	= firesat->subunit;
+	CmdFrm.opcode	= DSD;
+
+	CmdFrm.operand[0]  = 0; // source plug
+	CmdFrm.operand[1]  = 0xD2; // subfunction replace
+	CmdFrm.operand[2]  = 0x20; // system id = DVB
+	CmdFrm.operand[3]  = 0x00; // antenna number
+	CmdFrm.operand[4]  = 0x00; // system_specific_multiplex selection_length
+	CmdFrm.operand[5]  = pidc; // Nr_of_dsd_sel_specs
+
+	pos = 6;
+	if (pidc != 0xff)
+		for (k = 0; k < pidc; k++) {
+			CmdFrm.operand[pos++] = 0x13; // flowfunction relay
+			CmdFrm.operand[pos++] = 0x80; // dsd_sel_spec_valid_flags -> PID
+			CmdFrm.operand[pos++] = (pid[k] >> 8) & 0x1F;
+			CmdFrm.operand[pos++] = pid[k] & 0xFF;
+			CmdFrm.operand[pos++] = 0x00; // tableID
+			CmdFrm.operand[pos++] = 0x00; // filter_length
+		}
+
+	CmdFrm.length = ALIGN(3 + pos, 4);
+
+	if (avc_write(firesat, &CmdFrm, &RspFrm) < 0)
+		return -EIO;
+
+	msleep(50);
+	return 0;
+}
+
+int avc_tuner_get_ts(struct firesat *firesat)
+{
+	AVCCmdFrm CmdFrm;
+	AVCRspFrm RspFrm;
+
+	memset(&CmdFrm, 0, sizeof(AVCCmdFrm));
+
+	CmdFrm.cts		= AVC;
+	CmdFrm.ctype	= CONTROL;
+	CmdFrm.sutyp	= 0x5;
+	CmdFrm.suid		= firesat->subunit;
+	CmdFrm.opcode	= DSIT;
+
+	CmdFrm.operand[0]  = 0; // source plug
+	CmdFrm.operand[1]  = 0xD2; // subfunction replace
+	CmdFrm.operand[2]  = 0xFF; //status
+	CmdFrm.operand[3]  = 0x20; // system id = DVB
+	CmdFrm.operand[4]  = 0x00; // antenna number
+	CmdFrm.operand[5]  = 0x0;  // system_specific_search_flags
+	CmdFrm.operand[6]  = (firesat->type == FireSAT_DVB_T)?0x0c:0x11; // system_specific_multiplex selection_length
+	CmdFrm.operand[7]  = 0x00; // valid_flags [0]
+	CmdFrm.operand[8]  = 0x00; // valid_flags [1]
+	CmdFrm.operand[7 + (firesat->type == FireSAT_DVB_T)?0x0c:0x11] = 0x00; // nr_of_dsit_sel_specs (always 0)
+
+	CmdFrm.length = (firesat->type == FireSAT_DVB_T)?24:28;
+
+	if (avc_write(firesat, &CmdFrm, &RspFrm) < 0)
+		return -EIO;
+
+	msleep(250);
+	return 0;
+}
+
+int avc_identify_subunit(struct firesat *firesat)
+{
+	AVCCmdFrm CmdFrm;
+	AVCRspFrm RspFrm;
+
+	memset(&CmdFrm,0,sizeof(AVCCmdFrm));
+
+	CmdFrm.cts = AVC;
+	CmdFrm.ctype = CONTROL;
+	CmdFrm.sutyp = 0x5; // tuner
+	CmdFrm.suid = firesat->subunit;
+	CmdFrm.opcode = READ_DESCRIPTOR;
+
+	CmdFrm.operand[0]=DESCRIPTOR_SUBUNIT_IDENTIFIER;
+	CmdFrm.operand[1]=0xff;
+	CmdFrm.operand[2]=0x00;
+	CmdFrm.operand[3]=0x00; // length highbyte
+	CmdFrm.operand[4]=0x08; // length lowbyte
+	CmdFrm.operand[5]=0x00; // offset highbyte
+	CmdFrm.operand[6]=0x0d; // offset lowbyte
+
+	CmdFrm.length=12;
+
+	if (avc_write(firesat, &CmdFrm, &RspFrm) < 0)
+		return -EIO;
+
+	if ((RspFrm.resp != STABLE && RspFrm.resp != ACCEPTED) ||
+	    (RspFrm.operand[3] << 8) + RspFrm.operand[4] != 8) {
+		dev_err(&firesat->ud->device,
+			"cannot read subunit identifier\n");
+		return -EINVAL;
+	}
+	return 0;
+}
+
+int avc_tuner_status(struct firesat *firesat,
+		     ANTENNA_INPUT_INFO *antenna_input_info)
+{
+	AVCCmdFrm CmdFrm;
+	AVCRspFrm RspFrm;
+	int length;
+
+	memset(&CmdFrm, 0, sizeof(AVCCmdFrm));
+
+	CmdFrm.cts=AVC;
+	CmdFrm.ctype=CONTROL;
+	CmdFrm.sutyp=0x05; // tuner
+	CmdFrm.suid=firesat->subunit;
+	CmdFrm.opcode=READ_DESCRIPTOR;
+
+	CmdFrm.operand[0]=DESCRIPTOR_TUNER_STATUS;
+	CmdFrm.operand[1]=0xff; //read_result_status
+	CmdFrm.operand[2]=0x00; // reserver
+	CmdFrm.operand[3]=0;//sizeof(ANTENNA_INPUT_INFO) >> 8;
+	CmdFrm.operand[4]=0;//sizeof(ANTENNA_INPUT_INFO) & 0xFF;
+	CmdFrm.operand[5]=0x00;
+	CmdFrm.operand[6]=0x00;
+	CmdFrm.length=12;
+
+	if (avc_write(firesat, &CmdFrm, &RspFrm) < 0)
+		return -EIO;
+
+	if (RspFrm.resp != STABLE && RspFrm.resp != ACCEPTED) {
+		dev_err(&firesat->ud->device, "cannot read tuner status\n");
+		return -EINVAL;
+	}
+
+	length = RspFrm.operand[9];
+	if (RspFrm.operand[1] != 0x10 || length != sizeof(ANTENNA_INPUT_INFO)) {
+		dev_err(&firesat->ud->device, "got invalid tuner status\n");
+		return -EINVAL;
+	}
+
+	memcpy(antenna_input_info, &RspFrm.operand[10], length);
+	return 0;
+}
+
+int avc_lnb_control(struct firesat *firesat, char voltage, char burst,
+		    char conttone, char nrdiseq,
+		    struct dvb_diseqc_master_cmd *diseqcmd)
+{
+	AVCCmdFrm CmdFrm;
+	AVCRspFrm RspFrm;
+	int i, j, k;
+
+	memset(&CmdFrm, 0, sizeof(AVCCmdFrm));
+
+	CmdFrm.cts=AVC;
+	CmdFrm.ctype=CONTROL;
+	CmdFrm.sutyp=0x05;
+	CmdFrm.suid=firesat->subunit;
+	CmdFrm.opcode=VENDOR;
+
+	CmdFrm.operand[0]=SFE_VENDOR_DE_COMPANYID_0;
+	CmdFrm.operand[1]=SFE_VENDOR_DE_COMPANYID_1;
+	CmdFrm.operand[2]=SFE_VENDOR_DE_COMPANYID_2;
+	CmdFrm.operand[3]=SFE_VENDOR_OPCODE_LNB_CONTROL;
+
+	CmdFrm.operand[4]=voltage;
+	CmdFrm.operand[5]=nrdiseq;
+
+	i=6;
+
+	for (j = 0; j < nrdiseq; j++) {
+		CmdFrm.operand[i++] = diseqcmd[j].msg_len;
+
+		for (k = 0; k < diseqcmd[j].msg_len; k++)
+			CmdFrm.operand[i++] = diseqcmd[j].msg[k];
+	}
+
+	CmdFrm.operand[i++]=burst;
+	CmdFrm.operand[i++]=conttone;
+
+	CmdFrm.length = ALIGN(3 + i, 4);
+
+	if (avc_write(firesat, &CmdFrm, &RspFrm) < 0)
+		return -EIO;
+
+	if (RspFrm.resp != ACCEPTED) {
+		dev_err(&firesat->ud->device, "LNB control failed\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+int avc_register_remote_control(struct firesat *firesat)
+{
+	AVCCmdFrm CmdFrm;
+
+	memset(&CmdFrm, 0, sizeof(AVCCmdFrm));
+
+	CmdFrm.cts = AVC;
+	CmdFrm.ctype = NOTIFY;
+	CmdFrm.sutyp = 0x1f;
+	CmdFrm.suid = 0x7;
+	CmdFrm.opcode = VENDOR;
+
+	CmdFrm.operand[0] = SFE_VENDOR_DE_COMPANYID_0;
+	CmdFrm.operand[1] = SFE_VENDOR_DE_COMPANYID_1;
+	CmdFrm.operand[2] = SFE_VENDOR_DE_COMPANYID_2;
+	CmdFrm.operand[3] = SFE_VENDOR_OPCODE_REGISTER_REMOTE_CONTROL;
+
+	CmdFrm.length = 8;
+
+	return avc_write(firesat, &CmdFrm, NULL);
+}
+
+void avc_remote_ctrl_work(struct work_struct *work)
+{
+	struct firesat *firesat =
+			container_of(work, struct firesat, remote_ctrl_work);
+
+	/* Should it be rescheduled in failure cases? */
+	avc_register_remote_control(firesat);
+}
+
+#if 0 /* FIXME: unused */
+int avc_tuner_host2ca(struct firesat *firesat)
+{
+	AVCCmdFrm CmdFrm;
+	AVCRspFrm RspFrm;
+
+	memset(&CmdFrm, 0, sizeof(AVCCmdFrm));
+	CmdFrm.cts = AVC;
+	CmdFrm.ctype = CONTROL;
+	CmdFrm.sutyp = 0x5;
+	CmdFrm.suid = firesat->subunit;
+	CmdFrm.opcode = VENDOR;
+
+	CmdFrm.operand[0]=SFE_VENDOR_DE_COMPANYID_0;
+	CmdFrm.operand[1]=SFE_VENDOR_DE_COMPANYID_1;
+	CmdFrm.operand[2]=SFE_VENDOR_DE_COMPANYID_2;
+	CmdFrm.operand[3]=SFE_VENDOR_OPCODE_HOST2CA;
+	CmdFrm.operand[4] = 0; // slot
+	CmdFrm.operand[5] = SFE_VENDOR_TAG_CA_APPLICATION_INFO; // ca tag
+	CmdFrm.operand[6] = 0; // more/last
+	CmdFrm.operand[7] = 0; // length
+	CmdFrm.length = 12;
+
+	if (avc_write(firesat, &CmdFrm, &RspFrm) < 0)
+		return -EIO;
+
+	return 0;
+}
+#endif
+
+static int get_ca_object_pos(AVCRspFrm *RspFrm)
+{
+	int length = 1;
+
+	/* Check length of length field */
+	if (RspFrm->operand[7] & 0x80)
+		length = (RspFrm->operand[7] & 0x7f) + 1;
+	return length + 7;
+}
+
+static int get_ca_object_length(AVCRspFrm *RspFrm)
+{
+#if 0 /* FIXME: unused */
+	int size = 0;
+	int i;
+
+	if (RspFrm->operand[7] & 0x80)
+		for (i = 0; i < (RspFrm->operand[7] & 0x7f); i++) {
+			size <<= 8;
+			size += RspFrm->operand[8 + i];
+		}
+#endif
+	return RspFrm->operand[7];
+}
+
+int avc_ca_app_info(struct firesat *firesat, char *app_info, unsigned int *len)
+{
+	AVCCmdFrm CmdFrm;
+	AVCRspFrm RspFrm;
+	int pos;
+
+	memset(&CmdFrm, 0, sizeof(AVCCmdFrm));
+	CmdFrm.cts = AVC;
+	CmdFrm.ctype = STATUS;
+	CmdFrm.sutyp = 0x5;
+	CmdFrm.suid = firesat->subunit;
+	CmdFrm.opcode = VENDOR;
+
+	CmdFrm.operand[0]=SFE_VENDOR_DE_COMPANYID_0;
+	CmdFrm.operand[1]=SFE_VENDOR_DE_COMPANYID_1;
+	CmdFrm.operand[2]=SFE_VENDOR_DE_COMPANYID_2;
+	CmdFrm.operand[3]=SFE_VENDOR_OPCODE_CA2HOST;
+	CmdFrm.operand[4] = 0; // slot
+	CmdFrm.operand[5] = SFE_VENDOR_TAG_CA_APPLICATION_INFO; // ca tag
+	CmdFrm.length = 12;
+
+	if (avc_write(firesat, &CmdFrm, &RspFrm) < 0)
+		return -EIO;
+
+	/* FIXME: check response code and validate response data */
+
+	pos = get_ca_object_pos(&RspFrm);
+	app_info[0] = (TAG_APP_INFO >> 16) & 0xFF;
+	app_info[1] = (TAG_APP_INFO >> 8) & 0xFF;
+	app_info[2] = (TAG_APP_INFO >> 0) & 0xFF;
+	app_info[3] = 6 + RspFrm.operand[pos + 4];
+	app_info[4] = 0x01;
+	memcpy(&app_info[5], &RspFrm.operand[pos], 5 + RspFrm.operand[pos + 4]);
+	*len = app_info[3] + 4;
+
+	return 0;
+}
+
+int avc_ca_info(struct firesat *firesat, char *app_info, unsigned int *len)
+{
+	AVCCmdFrm CmdFrm;
+	AVCRspFrm RspFrm;
+	int pos;
+
+	memset(&CmdFrm, 0, sizeof(AVCCmdFrm));
+	CmdFrm.cts = AVC;
+	CmdFrm.ctype = STATUS;
+	CmdFrm.sutyp = 0x5;
+	CmdFrm.suid = firesat->subunit;
+	CmdFrm.opcode = VENDOR;
+
+	CmdFrm.operand[0]=SFE_VENDOR_DE_COMPANYID_0;
+	CmdFrm.operand[1]=SFE_VENDOR_DE_COMPANYID_1;
+	CmdFrm.operand[2]=SFE_VENDOR_DE_COMPANYID_2;
+	CmdFrm.operand[3]=SFE_VENDOR_OPCODE_CA2HOST;
+	CmdFrm.operand[4] = 0; // slot
+	CmdFrm.operand[5] = SFE_VENDOR_TAG_CA_APPLICATION_INFO; // ca tag
+	CmdFrm.length = 12;
+
+	if (avc_write(firesat, &CmdFrm, &RspFrm) < 0)
+		return -EIO;
+
+	pos = get_ca_object_pos(&RspFrm);
+	app_info[0] = (TAG_CA_INFO >> 16) & 0xFF;
+	app_info[1] = (TAG_CA_INFO >> 8) & 0xFF;
+	app_info[2] = (TAG_CA_INFO >> 0) & 0xFF;
+	app_info[3] = 2;
+	app_info[4] = RspFrm.operand[pos + 0];
+	app_info[5] = RspFrm.operand[pos + 1];
+	*len = app_info[3] + 4;
+
+	return 0;
+}
+
+int avc_ca_reset(struct firesat *firesat)
+{
+	AVCCmdFrm CmdFrm;
+	AVCRspFrm RspFrm;
+
+	memset(&CmdFrm, 0, sizeof(AVCCmdFrm));
+	CmdFrm.cts = AVC;
+	CmdFrm.ctype = CONTROL;
+	CmdFrm.sutyp = 0x5;
+	CmdFrm.suid = firesat->subunit;
+	CmdFrm.opcode = VENDOR;
+
+	CmdFrm.operand[0]=SFE_VENDOR_DE_COMPANYID_0;
+	CmdFrm.operand[1]=SFE_VENDOR_DE_COMPANYID_1;
+	CmdFrm.operand[2]=SFE_VENDOR_DE_COMPANYID_2;
+	CmdFrm.operand[3]=SFE_VENDOR_OPCODE_HOST2CA;
+	CmdFrm.operand[4] = 0; // slot
+	CmdFrm.operand[5] = SFE_VENDOR_TAG_CA_RESET; // ca tag
+	CmdFrm.operand[6] = 0; // more/last
+	CmdFrm.operand[7] = 1; // length
+	CmdFrm.operand[8] = 0; // force hardware reset
+	CmdFrm.length = 12;
+
+	if (avc_write(firesat, &CmdFrm, &RspFrm) < 0)
+		return -EIO;
+
+	return 0;
+}
+
+int avc_ca_pmt(struct firesat *firesat, char *msg, int length)
+{
+	AVCCmdFrm CmdFrm;
+	AVCRspFrm RspFrm;
+	int list_management;
+	int program_info_length;
+	int pmt_cmd_id;
+	int read_pos;
+	int write_pos;
+	int es_info_length;
+	int crc32_csum;
+
+	memset(&CmdFrm, 0, sizeof(AVCCmdFrm));
+	CmdFrm.cts = AVC;
+	CmdFrm.ctype = CONTROL;
+	CmdFrm.sutyp = 0x5;
+	CmdFrm.suid = firesat->subunit;
+	CmdFrm.opcode = VENDOR;
+
+	if (msg[0] != LIST_MANAGEMENT_ONLY) {
+		dev_info(&firesat->ud->device,
+			 "forcing list_management to ONLY\n");
+		msg[0] = LIST_MANAGEMENT_ONLY;
+	}
+	// We take the cmd_id from the programme level only!
+	list_management = msg[0];
+	program_info_length = ((msg[4] & 0x0F) << 8) + msg[5];
+	if (program_info_length > 0)
+		program_info_length--; // Remove pmt_cmd_id
+	pmt_cmd_id = msg[6];
+
+	CmdFrm.operand[0]=SFE_VENDOR_DE_COMPANYID_0;
+	CmdFrm.operand[1]=SFE_VENDOR_DE_COMPANYID_1;
+	CmdFrm.operand[2]=SFE_VENDOR_DE_COMPANYID_2;
+	CmdFrm.operand[3]=SFE_VENDOR_OPCODE_HOST2CA;
+	CmdFrm.operand[4] = 0; // slot
+	CmdFrm.operand[5] = SFE_VENDOR_TAG_CA_PMT; // ca tag
+	CmdFrm.operand[6] = 0; // more/last
+	//CmdFrm.operand[7] = XXXprogram_info_length + 17; // length
+	CmdFrm.operand[8] = list_management;
+	CmdFrm.operand[9] = 0x01; // pmt_cmd=OK_descramble
+
+	// TS program map table
+
+	// Table id=2
+	CmdFrm.operand[10] = 0x02;
+	// Section syntax + length
+	CmdFrm.operand[11] = 0x80;
+	//CmdFrm.operand[12] = XXXprogram_info_length + 12;
+	// Program number
+	CmdFrm.operand[13] = msg[1];
+	CmdFrm.operand[14] = msg[2];
+	// Version number=0 + current/next=1
+	CmdFrm.operand[15] = 0x01;
+	// Section number=0
+	CmdFrm.operand[16] = 0x00;
+	// Last section number=0
+	CmdFrm.operand[17] = 0x00;
+	// PCR_PID=1FFF
+	CmdFrm.operand[18] = 0x1F;
+	CmdFrm.operand[19] = 0xFF;
+	// Program info length
+	CmdFrm.operand[20] = (program_info_length >> 8);
+	CmdFrm.operand[21] = (program_info_length & 0xFF);
+	// CA descriptors at programme level
+	read_pos = 6;
+	write_pos = 22;
+	if (program_info_length > 0) {
+		pmt_cmd_id = msg[read_pos++];
+		if (pmt_cmd_id != 1 && pmt_cmd_id != 4)
+			dev_err(&firesat->ud->device,
+				"invalid pmt_cmd_id %d\n", pmt_cmd_id);
+
+		memcpy(&CmdFrm.operand[write_pos], &msg[read_pos],
+		       program_info_length);
+		read_pos += program_info_length;
+		write_pos += program_info_length;
+	}
+	while (read_pos < length) {
+		CmdFrm.operand[write_pos++] = msg[read_pos++];
+		CmdFrm.operand[write_pos++] = msg[read_pos++];
+		CmdFrm.operand[write_pos++] = msg[read_pos++];
+		es_info_length =
+			((msg[read_pos] & 0x0F) << 8) + msg[read_pos + 1];
+		read_pos += 2;
+		if (es_info_length > 0)
+			es_info_length--; // Remove pmt_cmd_id
+		CmdFrm.operand[write_pos++] = es_info_length >> 8;
+		CmdFrm.operand[write_pos++] = es_info_length & 0xFF;
+		if (es_info_length > 0) {
+			pmt_cmd_id = msg[read_pos++];
+			if (pmt_cmd_id != 1 && pmt_cmd_id != 4)
+				dev_err(&firesat->ud->device,
+					"invalid pmt_cmd_id %d "
+					"at stream level\n", pmt_cmd_id);
+
+			memcpy(&CmdFrm.operand[write_pos], &msg[read_pos],
+			       es_info_length);
+			read_pos += es_info_length;
+			write_pos += es_info_length;
+		}
+	}
+
+	// CRC
+	CmdFrm.operand[write_pos++] = 0x00;
+	CmdFrm.operand[write_pos++] = 0x00;
+	CmdFrm.operand[write_pos++] = 0x00;
+	CmdFrm.operand[write_pos++] = 0x00;
+
+	CmdFrm.operand[7] = write_pos - 8;
+	CmdFrm.operand[12] = write_pos - 13;
+
+	crc32_csum = crc32_be(0, &CmdFrm.operand[10],
+			   CmdFrm.operand[12] - 1);
+	CmdFrm.operand[write_pos - 4] = (crc32_csum >> 24) & 0xFF;
+	CmdFrm.operand[write_pos - 3] = (crc32_csum >> 16) & 0xFF;
+	CmdFrm.operand[write_pos - 2] = (crc32_csum >>  8) & 0xFF;
+	CmdFrm.operand[write_pos - 1] = (crc32_csum >>  0) & 0xFF;
+
+	CmdFrm.length = ALIGN(3 + write_pos, 4);
+
+	if (avc_write(firesat, &CmdFrm, &RspFrm) < 0)
+		return -EIO;
+
+	if (RspFrm.resp != ACCEPTED) {
+		dev_err(&firesat->ud->device,
+			"CA PMT failed with response 0x%x\n", RspFrm.resp);
+		return -EFAULT;
+	}
+
+	return 0;
+}
+
+int avc_ca_get_time_date(struct firesat *firesat, int *interval)
+{
+	AVCCmdFrm CmdFrm;
+	AVCRspFrm RspFrm;
+
+	memset(&CmdFrm, 0, sizeof(AVCCmdFrm));
+	CmdFrm.cts = AVC;
+	CmdFrm.ctype = STATUS;
+	CmdFrm.sutyp = 0x5;
+	CmdFrm.suid = firesat->subunit;
+	CmdFrm.opcode = VENDOR;
+
+	CmdFrm.operand[0]=SFE_VENDOR_DE_COMPANYID_0;
+	CmdFrm.operand[1]=SFE_VENDOR_DE_COMPANYID_1;
+	CmdFrm.operand[2]=SFE_VENDOR_DE_COMPANYID_2;
+	CmdFrm.operand[3]=SFE_VENDOR_OPCODE_CA2HOST;
+	CmdFrm.operand[4] = 0; // slot
+	CmdFrm.operand[5] = SFE_VENDOR_TAG_CA_DATE_TIME; // ca tag
+	CmdFrm.operand[6] = 0; // more/last
+	CmdFrm.operand[7] = 0; // length
+	CmdFrm.length = 12;
+
+	if (avc_write(firesat, &CmdFrm, &RspFrm) < 0)
+		return -EIO;
+
+	/* FIXME: check response code and validate response data */
+
+	*interval = RspFrm.operand[get_ca_object_pos(&RspFrm)];
+
+	return 0;
+}
+
+int avc_ca_enter_menu(struct firesat *firesat)
+{
+	AVCCmdFrm CmdFrm;
+	AVCRspFrm RspFrm;
+
+	memset(&CmdFrm, 0, sizeof(AVCCmdFrm));
+	CmdFrm.cts = AVC;
+	CmdFrm.ctype = STATUS;
+	CmdFrm.sutyp = 0x5;
+	CmdFrm.suid = firesat->subunit;
+	CmdFrm.opcode = VENDOR;
+
+	CmdFrm.operand[0]=SFE_VENDOR_DE_COMPANYID_0;
+	CmdFrm.operand[1]=SFE_VENDOR_DE_COMPANYID_1;
+	CmdFrm.operand[2]=SFE_VENDOR_DE_COMPANYID_2;
+	CmdFrm.operand[3]=SFE_VENDOR_OPCODE_HOST2CA;
+	CmdFrm.operand[4] = 0; // slot
+	CmdFrm.operand[5] = SFE_VENDOR_TAG_CA_ENTER_MENU;
+	CmdFrm.operand[6] = 0; // more/last
+	CmdFrm.operand[7] = 0; // length
+	CmdFrm.length = 12;
+
+	if (avc_write(firesat, &CmdFrm, &RspFrm) < 0)
+		return -EIO;
+
+	return 0;
+}
+
+int avc_ca_get_mmi(struct firesat *firesat, char *mmi_object, unsigned int *len)
+{
+	AVCCmdFrm CmdFrm;
+	AVCRspFrm RspFrm;
+
+	memset(&CmdFrm, 0, sizeof(AVCCmdFrm));
+	CmdFrm.cts = AVC;
+	CmdFrm.ctype = STATUS;
+	CmdFrm.sutyp = 0x5;
+	CmdFrm.suid = firesat->subunit;
+	CmdFrm.opcode = VENDOR;
+
+	CmdFrm.operand[0]=SFE_VENDOR_DE_COMPANYID_0;
+	CmdFrm.operand[1]=SFE_VENDOR_DE_COMPANYID_1;
+	CmdFrm.operand[2]=SFE_VENDOR_DE_COMPANYID_2;
+	CmdFrm.operand[3]=SFE_VENDOR_OPCODE_CA2HOST;
+	CmdFrm.operand[4] = 0; // slot
+	CmdFrm.operand[5] = SFE_VENDOR_TAG_CA_MMI;
+	CmdFrm.operand[6] = 0; // more/last
+	CmdFrm.operand[7] = 0; // length
+	CmdFrm.length = 12;
+
+	if (avc_write(firesat, &CmdFrm, &RspFrm) < 0)
+		return -EIO;
+
+	/* FIXME: check response code and validate response data */
+
+	*len = get_ca_object_length(&RspFrm);
+	memcpy(mmi_object, &RspFrm.operand[get_ca_object_pos(&RspFrm)], *len);
+
+	return 0;
+}
diff --git a/drivers/media/dvb/firesat/avc_api.h b/drivers/media/dvb/firesat/avc_api.h
new file mode 100644
index 000000000000..9d2efd8ff17b
--- /dev/null
+++ b/drivers/media/dvb/firesat/avc_api.h
@@ -0,0 +1,432 @@
+/*
+ * AV/C API
+ *
+ * Copyright (C) 2000 Manfred Weihs
+ * Copyright (C) 2003 Philipp Gutgsell <0014guph@edu.fh-kaernten.ac.at>
+ * Copyright (C) 2004 Andreas Monitzer <andy@monitzer.com>
+ * Copyright (C) 2008 Ben Backx <ben@bbackx.com>
+ * Copyright (C) 2008 Henrik Kurelid <henrik@kurelid.se>
+ *
+ * This is based on code written by Peter Halwachs, Thomas Groiss and
+ * Andreas Monitzer.
+ *
+ *	This program is free software; you can redistribute it and/or
+ *	modify it under the terms of the GNU General Public License as
+ *	published by the Free Software Foundation; either version 2 of
+ *	the License, or (at your option) any later version.
+ */
+
+#ifndef _AVC_API_H
+#define _AVC_API_H
+
+#include <linux/types.h>
+
+/*************************************************************
+	Constants from EN510221
+**************************************************************/
+#define LIST_MANAGEMENT_ONLY 0x03
+
+/************************************************************
+	definition of structures
+*************************************************************/
+typedef struct {
+	   int           Nr_SourcePlugs;
+	   int 	         Nr_DestinationPlugs;
+} TunerInfo;
+
+
+/***********************************************
+
+         supported cts
+
+************************************************/
+
+#define AVC  0x0
+
+// FCP command frame with ctype = 0x0 is AVC command frame
+
+#ifdef __LITTLE_ENDIAN
+
+// Definition FCP Command Frame
+typedef struct _AVCCmdFrm
+{
+		// AV/C command frame
+	__u8 ctype  : 4 ;   // command type
+	__u8 cts    : 4 ;   // always 0x0 for AVC
+	__u8 suid   : 3 ;   // subunit ID
+	__u8 sutyp  : 5 ;   // subunit_typ
+	__u8 opcode : 8 ;   // opcode
+	__u8 operand[509] ; // array of operands [1-507]
+	int length;         //length of the command frame
+} AVCCmdFrm ;
+
+// Definition FCP Response Frame
+typedef struct _AVCRspFrm
+{
+        // AV/C response frame
+	__u8 resp		: 4 ;   // response type
+	__u8 cts		: 4 ;   // always 0x0 for AVC
+	__u8 suid		: 3 ;   // subunit ID
+	__u8 sutyp	: 5 ;   // subunit_typ
+	__u8 opcode	: 8 ;   // opcode
+	__u8 operand[509] ; // array of operands [1-507]
+	int length;         //length of the response frame
+} AVCRspFrm ;
+
+#else
+
+typedef struct _AVCCmdFrm
+{
+	__u8 cts:4;
+	__u8 ctype:4;
+	__u8 sutyp:5;
+	__u8 suid:3;
+	__u8 opcode;
+	__u8 operand[509];
+	int length;
+} AVCCmdFrm;
+
+typedef struct _AVCRspFrm
+{
+	__u8 cts:4;
+	__u8 resp:4;
+	__u8 sutyp:5;
+	__u8 suid:3;
+	__u8 opcode;
+	__u8 operand[509];
+	int length;
+} AVCRspFrm;
+
+#endif
+
+/*************************************************************
+	AVC command types (ctype)
+**************************************************************///
+#define CONTROL    0x00
+#define STATUS     0x01
+#define INQUIRY    0x02
+#define NOTIFY     0x03
+
+/*************************************************************
+	AVC respond types
+**************************************************************///
+#define NOT_IMPLEMENTED 0x8
+#define ACCEPTED        0x9
+#define REJECTED        0xA
+#define STABLE          0xC
+#define CHANGED         0xD
+#define INTERIM         0xF
+
+/*************************************************************
+	AVC opcodes
+**************************************************************///
+#define CONNECT			0x24
+#define DISCONNECT		0x25
+#define UNIT_INFO		0x30
+#define SUBUNIT_Info		0x31
+#define VENDOR			0x00
+
+#define PLUG_INFO		0x02
+#define OPEN_DESCRIPTOR		0x08
+#define READ_DESCRIPTOR		0x09
+#define OBJECT_NUMBER_SELECT	0x0D
+
+/*************************************************************
+	AVCTuner opcodes
+**************************************************************/
+
+#define DSIT				0xC8
+#define DSD				0xCB
+#define DESCRIPTOR_TUNER_STATUS 	0x80
+#define DESCRIPTOR_SUBUNIT_IDENTIFIER	0x00
+
+/*************************************************************
+	AVCTuner list types
+**************************************************************/
+#define Multiplex_List   0x80
+#define Service_List     0x82
+
+/*************************************************************
+	AVCTuner object entries
+**************************************************************/
+#define Multiplex	 			0x80
+#define Service 	 			0x82
+#define Service_with_specified_components	0x83
+#define Preferred_components			0x90
+#define Component				0x84
+
+/*************************************************************
+	Vendor-specific commands
+**************************************************************/
+
+// digital everywhere vendor ID
+#define SFE_VENDOR_DE_COMPANYID_0			0x00
+#define SFE_VENDOR_DE_COMPANYID_1			0x12
+#define SFE_VENDOR_DE_COMPANYID_2			0x87
+
+#define SFE_VENDOR_MAX_NR_COMPONENTS		0x4
+#define SFE_VENDOR_MAX_NR_SERVICES			0x3
+#define SFE_VENDOR_MAX_NR_DSD_ELEMENTS		0x10
+
+// vendor commands
+#define SFE_VENDOR_OPCODE_REGISTER_REMOTE_CONTROL	0x0A
+#define SFE_VENDOR_OPCODE_LNB_CONTROL		0x52
+#define SFE_VENDOR_OPCODE_TUNE_QPSK			0x58	// QPSK command for DVB-S
+
+// TODO: following vendor specific commands needs to be implemented
+#define SFE_VENDOR_OPCODE_GET_FIRMWARE_VERSION	0x00
+#define SFE_VENDOR_OPCODE_HOST2CA				0x56
+#define SFE_VENDOR_OPCODE_CA2HOST				0x57
+#define SFE_VENDOR_OPCODE_CISTATUS				0x59
+#define SFE_VENDOR_OPCODE_TUNE_QPSK2			0x60 // QPSK command for DVB-S2 devices
+
+// CA Tags
+#define SFE_VENDOR_TAG_CA_RESET			0x00
+#define SFE_VENDOR_TAG_CA_APPLICATION_INFO	0x01
+#define SFE_VENDOR_TAG_CA_PMT			0x02
+#define SFE_VENDOR_TAG_CA_DATE_TIME		0x04
+#define SFE_VENDOR_TAG_CA_MMI			0x05
+#define SFE_VENDOR_TAG_CA_ENTER_MENU		0x07
+
+
+//AVCTuner DVB identifier service_ID
+#define DVB 0x20
+
+/*************************************************************
+						AVC descriptor types
+**************************************************************/
+
+#define Subunit_Identifier_Descriptor		 0x00
+#define Tuner_Status_Descriptor				 0x80
+
+typedef struct {
+	__u8          Subunit_Type;
+	__u8          Max_Subunit_ID;
+} SUBUNIT_INFO;
+
+/*************************************************************
+
+		AVCTuner DVB object IDs are 6 byte long
+
+**************************************************************/
+
+typedef struct {
+	__u8  Byte0;
+	__u8  Byte1;
+	__u8  Byte2;
+	__u8  Byte3;
+	__u8  Byte4;
+	__u8  Byte5;
+}OBJECT_ID;
+
+/*************************************************************
+						MULIPLEX Structs
+**************************************************************/
+typedef struct
+{
+#ifdef __LITTLE_ENDIAN
+	__u8       RF_frequency_hByte:6;
+	__u8       raster_Frequency:2;//Bit7,6 raster frequency
+#else
+	__u8 raster_Frequency:2;
+	__u8 RF_frequency_hByte:6;
+#endif
+	__u8       RF_frequency_mByte;
+	__u8       RF_frequency_lByte;
+
+}FREQUENCY;
+
+#ifdef __LITTLE_ENDIAN
+
+typedef struct
+{
+		 __u8        Modulation	    :1;
+		 __u8        FEC_inner	    :1;
+		 __u8        FEC_outer	    :1;
+		 __u8        Symbol_Rate    :1;
+		 __u8        Frequency	    :1;
+		 __u8        Orbital_Pos	:1;
+		 __u8        Polarisation	:1;
+		 __u8        reserved_fields :1;
+		 __u8        reserved1		:7;
+		 __u8        Network_ID	:1;
+
+}MULTIPLEX_VALID_FLAGS;
+
+typedef struct
+{
+	__u8	GuardInterval:1;
+	__u8	CodeRateLPStream:1;
+	__u8	CodeRateHPStream:1;
+	__u8	HierarchyInfo:1;
+	__u8	Constellation:1;
+	__u8	Bandwidth:1;
+	__u8	CenterFrequency:1;
+	__u8	reserved1:1;
+	__u8	reserved2:5;
+	__u8	OtherFrequencyFlag:1;
+	__u8	TransmissionMode:1;
+	__u8	NetworkId:1;
+}MULTIPLEX_VALID_FLAGS_DVBT;
+
+#else
+
+typedef struct {
+	__u8 reserved_fields:1;
+	__u8 Polarisation:1;
+	__u8 Orbital_Pos:1;
+	__u8 Frequency:1;
+	__u8 Symbol_Rate:1;
+	__u8 FEC_outer:1;
+	__u8 FEC_inner:1;
+	__u8 Modulation:1;
+	__u8 Network_ID:1;
+	__u8 reserved1:7;
+}MULTIPLEX_VALID_FLAGS;
+
+typedef struct {
+	__u8 reserved1:1;
+	__u8 CenterFrequency:1;
+	__u8 Bandwidth:1;
+	__u8 Constellation:1;
+	__u8 HierarchyInfo:1;
+	__u8 CodeRateHPStream:1;
+	__u8 CodeRateLPStream:1;
+	__u8 GuardInterval:1;
+	__u8 NetworkId:1;
+	__u8 TransmissionMode:1;
+	__u8 OtherFrequencyFlag:1;
+	__u8 reserved2:5;
+}MULTIPLEX_VALID_FLAGS_DVBT;
+
+#endif
+
+typedef union {
+	MULTIPLEX_VALID_FLAGS Bits;
+	MULTIPLEX_VALID_FLAGS_DVBT Bits_T;
+	struct {
+		__u8	ByteHi;
+		__u8	ByteLo;
+	} Valid_Word;
+} M_VALID_FLAGS;
+
+typedef struct
+{
+#ifdef __LITTLE_ENDIAN
+  __u8      ActiveSystem;
+  __u8      reserved:5;
+  __u8      NoRF:1;
+  __u8      Moving:1;
+  __u8      Searching:1;
+
+  __u8      SelectedAntenna:7;
+  __u8      Input:1;
+
+  __u8      BER[4];
+
+  __u8      SignalStrength;
+  FREQUENCY Frequency;
+
+  __u8      ManDepInfoLength;
+
+  __u8 PowerSupply:1;
+  __u8 FrontEndPowerStatus:1;
+  __u8 reserved3:1;
+  __u8 AntennaError:1;
+  __u8 FrontEndError:1;
+  __u8 reserved2:3;
+
+  __u8 CarrierNoiseRatio[2];
+  __u8 reserved4[2];
+  __u8 PowerSupplyVoltage;
+  __u8 AntennaVoltage;
+  __u8 FirewireBusVoltage;
+
+  __u8 CaMmi:1;
+  __u8 reserved5:7;
+
+  __u8 reserved6:1;
+  __u8 CaInitializationStatus:1;
+  __u8 CaErrorFlag:1;
+  __u8 CaDvbFlag:1;
+  __u8 CaModulePresentStatus:1;
+  __u8 CaApplicationInfo:1;
+  __u8 CaDateTimeRequest:1;
+  __u8 CaPmtReply:1;
+
+#else
+  __u8 ActiveSystem;
+  __u8 Searching:1;
+  __u8 Moving:1;
+  __u8 NoRF:1;
+  __u8 reserved:5;
+
+  __u8 Input:1;
+  __u8 SelectedAntenna:7;
+
+  __u8 BER[4];
+
+  __u8 SignalStrength;
+  FREQUENCY Frequency;
+
+  __u8 ManDepInfoLength;
+
+  __u8 reserved2:3;
+  __u8 FrontEndError:1;
+  __u8 AntennaError:1;
+  __u8 reserved3:1;
+  __u8 FrontEndPowerStatus:1;
+  __u8 PowerSupply:1;
+
+  __u8 CarrierNoiseRatio[2];
+  __u8 reserved4[2];
+  __u8 PowerSupplyVoltage;
+  __u8 AntennaVoltage;
+  __u8 FirewireBusVoltage;
+
+  __u8 reserved5:7;
+  __u8 CaMmi:1;
+  __u8 CaPmtReply:1;
+  __u8 CaDateTimeRequest:1;
+  __u8 CaApplicationInfo:1;
+  __u8 CaModulePresentStatus:1;
+  __u8 CaDvbFlag:1;
+  __u8 CaErrorFlag:1;
+  __u8 CaInitializationStatus:1;
+  __u8 reserved6:1;
+
+#endif
+} ANTENNA_INPUT_INFO; // 22 Byte
+
+#define LNBCONTROL_DONTCARE 0xff
+
+struct dvb_diseqc_master_cmd;
+struct dvb_frontend_parameters;
+struct firesat;
+
+int avc_recv(struct firesat *firesat, u8 *data, size_t length);
+
+int AVCTuner_DSIT(struct firesat *firesat, int Source_Plug,
+		struct dvb_frontend_parameters *params, __u8 *status);
+
+int avc_tuner_status(struct firesat *firesat,
+		ANTENNA_INPUT_INFO *antenna_input_info);
+int avc_tuner_dsd(struct firesat *firesat,
+		struct dvb_frontend_parameters *params);
+int avc_tuner_set_pids(struct firesat *firesat, unsigned char pidc, u16 pid[]);
+int avc_tuner_get_ts(struct firesat *firesat);
+int avc_identify_subunit(struct firesat *firesat);
+int avc_lnb_control(struct firesat *firesat, char voltage, char burst,
+		char conttone, char nrdiseq,
+		struct dvb_diseqc_master_cmd *diseqcmd);
+void avc_remote_ctrl_work(struct work_struct *work);
+int avc_register_remote_control(struct firesat *firesat);
+int avc_ca_app_info(struct firesat *firesat, char *app_info, unsigned int *len);
+int avc_ca_info(struct firesat *firesat, char *app_info, unsigned int *len);
+int avc_ca_reset(struct firesat *firesat);
+int avc_ca_pmt(struct firesat *firesat, char *app_info, int length);
+int avc_ca_get_time_date(struct firesat *firesat, int *interval);
+int avc_ca_enter_menu(struct firesat *firesat);
+int avc_ca_get_mmi(struct firesat *firesat, char *mmi_object, unsigned int *len);
+
+#endif /* _AVC_API_H */
diff --git a/drivers/media/dvb/firesat/cmp.c b/drivers/media/dvb/firesat/cmp.c
new file mode 100644
index 000000000000..8e98b814e430
--- /dev/null
+++ b/drivers/media/dvb/firesat/cmp.c
@@ -0,0 +1,171 @@
+/*
+ * FireDTV driver (formerly known as FireSAT)
+ *
+ * Copyright (C) 2004 Andreas Monitzer <andy@monitzer.com>
+ * Copyright (C) 2008 Henrik Kurelid <henrik@kurelid.se>
+ *
+ *	This program is free software; you can redistribute it and/or
+ *	modify it under the terms of the GNU General Public License as
+ *	published by the Free Software Foundation; either version 2 of
+ *	the License, or (at your option) any later version.
+ */
+
+#include <linux/device.h>
+#include <linux/kernel.h>
+#include <linux/mutex.h>
+#include <linux/types.h>
+
+#include <asm/byteorder.h>
+
+#include <ieee1394.h>
+#include <nodemgr.h>
+
+#include "avc_api.h"
+#include "cmp.h"
+#include "firesat.h"
+
+#define CMP_OUTPUT_PLUG_CONTROL_REG_0	0xfffff0000904ULL
+
+static int cmp_read(struct firesat *firesat, void *buf, u64 addr, size_t len)
+{
+	int ret;
+
+	if (mutex_lock_interruptible(&firesat->avc_mutex))
+		return -EINTR;
+
+	ret = hpsb_node_read(firesat->ud->ne, addr, buf, len);
+	if (ret < 0)
+		dev_err(&firesat->ud->device, "CMP: read I/O error\n");
+
+	mutex_unlock(&firesat->avc_mutex);
+	return ret;
+}
+
+static int cmp_lock(struct firesat *firesat, void *data, u64 addr, __be32 arg,
+		    int ext_tcode)
+{
+	int ret;
+
+	if (mutex_lock_interruptible(&firesat->avc_mutex))
+		return -EINTR;
+
+	ret = hpsb_node_lock(firesat->ud->ne, addr, ext_tcode, data,
+			     (__force quadlet_t)arg);
+	if (ret < 0)
+		dev_err(&firesat->ud->device, "CMP: lock I/O error\n");
+
+	mutex_unlock(&firesat->avc_mutex);
+	return ret;
+}
+
+static inline u32 get_opcr(__be32 opcr, u32 mask, u32 shift)
+{
+	return (be32_to_cpu(opcr) >> shift) & mask;
+}
+
+static inline void set_opcr(__be32 *opcr, u32 value, u32 mask, u32 shift)
+{
+	*opcr &= ~cpu_to_be32(mask << shift);
+	*opcr |= cpu_to_be32((value & mask) << shift);
+}
+
+#define get_opcr_online(v)		get_opcr((v), 0x1, 31)
+#define get_opcr_p2p_connections(v)	get_opcr((v), 0x3f, 24)
+#define get_opcr_channel(v)		get_opcr((v), 0x3f, 16)
+
+#define set_opcr_p2p_connections(p, v)	set_opcr((p), (v), 0x3f, 24)
+#define set_opcr_channel(p, v)		set_opcr((p), (v), 0x3f, 16)
+#define set_opcr_data_rate(p, v)	set_opcr((p), (v), 0x3, 14)
+#define set_opcr_overhead_id(p, v)	set_opcr((p), (v), 0xf, 10)
+
+int cmp_establish_pp_connection(struct firesat *firesat, int plug, int channel)
+{
+	__be32 old_opcr, opcr;
+	u64 opcr_address = CMP_OUTPUT_PLUG_CONTROL_REG_0 + (plug << 2);
+	int attempts = 0;
+	int ret;
+
+	ret = cmp_read(firesat, &opcr, opcr_address, 4);
+	if (ret < 0)
+		return ret;
+
+repeat:
+	if (!get_opcr_online(opcr)) {
+		dev_err(&firesat->ud->device, "CMP: output offline\n");
+		return -EBUSY;
+	}
+
+	old_opcr = opcr;
+
+	if (get_opcr_p2p_connections(opcr)) {
+		if (get_opcr_channel(opcr) != channel) {
+			dev_err(&firesat->ud->device,
+				"CMP: cannot change channel\n");
+			return -EBUSY;
+		}
+		dev_info(&firesat->ud->device,
+			 "CMP: overlaying existing connection\n");
+
+		/* We don't allocate isochronous resources. */
+	} else {
+		set_opcr_channel(&opcr, channel);
+		set_opcr_data_rate(&opcr, IEEE1394_SPEED_400);
+
+		/* FIXME: this is for the worst case - optimize */
+		set_opcr_overhead_id(&opcr, 0);
+
+		/* FIXME: allocate isochronous channel and bandwidth at IRM */
+	}
+
+	set_opcr_p2p_connections(&opcr, get_opcr_p2p_connections(opcr) + 1);
+
+	ret = cmp_lock(firesat, &opcr, opcr_address, old_opcr, 2);
+	if (ret < 0)
+		return ret;
+
+	if (old_opcr != opcr) {
+		/*
+		 * FIXME: if old_opcr.P2P_Connections > 0,
+		 * deallocate isochronous channel and bandwidth at IRM
+		 */
+
+		if (++attempts < 6) /* arbitrary limit */
+			goto repeat;
+		return -EBUSY;
+	}
+
+	return 0;
+}
+
+void cmp_break_pp_connection(struct firesat *firesat, int plug, int channel)
+{
+	__be32 old_opcr, opcr;
+	u64 opcr_address = CMP_OUTPUT_PLUG_CONTROL_REG_0 + (plug << 2);
+	int attempts = 0;
+
+	if (cmp_read(firesat, &opcr, opcr_address, 4) < 0)
+		return;
+
+repeat:
+	if (!get_opcr_online(opcr) || !get_opcr_p2p_connections(opcr) ||
+	    get_opcr_channel(opcr) != channel) {
+		dev_err(&firesat->ud->device, "CMP: no connection to break\n");
+		return;
+	}
+
+	old_opcr = opcr;
+	set_opcr_p2p_connections(&opcr, get_opcr_p2p_connections(opcr) - 1);
+
+	if (cmp_lock(firesat, &opcr, opcr_address, old_opcr, 2) < 0)
+		return;
+
+	if (old_opcr != opcr) {
+		/*
+		 * FIXME: if old_opcr.P2P_Connections == 1, i.e. we were last
+		 * owner, deallocate isochronous channel and bandwidth at IRM
+		 */
+
+		if (++attempts < 6) /* arbitrary limit */
+			goto repeat;
+	}
+}
diff --git a/drivers/media/dvb/firesat/cmp.h b/drivers/media/dvb/firesat/cmp.h
new file mode 100644
index 000000000000..d92f6c7fb5d5
--- /dev/null
+++ b/drivers/media/dvb/firesat/cmp.h
@@ -0,0 +1,9 @@
+#ifndef _CMP_H
+#define _CMP_H
+
+struct firesat;
+
+int cmp_establish_pp_connection(struct firesat *firesat, int plug, int channel);
+void cmp_break_pp_connection(struct firesat *firesat, int plug, int channel);
+
+#endif /* _CMP_H */
diff --git a/drivers/media/dvb/firesat/firesat-ci.c b/drivers/media/dvb/firesat/firesat-ci.c
new file mode 100644
index 000000000000..783ed2000102
--- /dev/null
+++ b/drivers/media/dvb/firesat/firesat-ci.c
@@ -0,0 +1,261 @@
+/*
+ * FireDTV driver (formerly known as FireSAT)
+ *
+ * Copyright (C) 2004 Andreas Monitzer <andy@monitzer.com>
+ * Copyright (C) 2008 Henrik Kurelid <henrik@kurelid.se>
+ *
+ *	This program is free software; you can redistribute it and/or
+ *	modify it under the terms of the GNU General Public License as
+ *	published by the Free Software Foundation; either version 2 of
+ *	the License, or (at your option) any later version.
+ */
+
+#include <linux/dvb/ca.h>
+#include <linux/fs.h>
+#include <linux/module.h>
+
+#include <dvbdev.h>
+
+#include "avc_api.h"
+#include "firesat.h"
+#include "firesat-ci.h"
+
+static int firesat_ca_ready(ANTENNA_INPUT_INFO *info)
+{
+	return info->CaInitializationStatus == 1 &&
+	       info->CaErrorFlag == 0 &&
+	       info->CaDvbFlag == 1 &&
+	       info->CaModulePresentStatus == 1;
+}
+
+static int firesat_get_ca_flags(ANTENNA_INPUT_INFO *info)
+{
+	int flags = 0;
+
+	if (info->CaModulePresentStatus == 1)
+		flags |= CA_CI_MODULE_PRESENT;
+	if (info->CaInitializationStatus == 1 &&
+	    info->CaErrorFlag == 0 &&
+	    info->CaDvbFlag == 1)
+		flags |= CA_CI_MODULE_READY;
+	return flags;
+}
+
+static int firesat_ca_reset(struct firesat *firesat)
+{
+	return avc_ca_reset(firesat) ? -EFAULT : 0;
+}
+
+static int firesat_ca_get_caps(void *arg)
+{
+	struct ca_caps *cap = arg;
+
+	cap->slot_num = 1;
+	cap->slot_type = CA_CI;
+	cap->descr_num = 1;
+	cap->descr_type = CA_ECD;
+	return 0;
+}
+
+static int firesat_ca_get_slot_info(struct firesat *firesat, void *arg)
+{
+	ANTENNA_INPUT_INFO info;
+	struct ca_slot_info *slot = arg;
+
+	if (avc_tuner_status(firesat, &info))
+		return -EFAULT;
+
+	if (slot->num != 0)
+		return -EFAULT;
+
+	slot->type = CA_CI;
+	slot->flags = firesat_get_ca_flags(&info);
+	return 0;
+}
+
+static int firesat_ca_app_info(struct firesat *firesat, void *arg)
+{
+	struct ca_msg *reply = arg;
+
+	return
+	    avc_ca_app_info(firesat, reply->msg, &reply->length) ? -EFAULT : 0;
+}
+
+static int firesat_ca_info(struct firesat *firesat, void *arg)
+{
+	struct ca_msg *reply = arg;
+
+	return avc_ca_info(firesat, reply->msg, &reply->length) ? -EFAULT : 0;
+}
+
+static int firesat_ca_get_mmi(struct firesat *firesat, void *arg)
+{
+	struct ca_msg *reply = arg;
+
+	return
+	    avc_ca_get_mmi(firesat, reply->msg, &reply->length) ? -EFAULT : 0;
+}
+
+static int firesat_ca_get_msg(struct firesat *firesat, void *arg)
+{
+	ANTENNA_INPUT_INFO info;
+	int err;
+
+	switch (firesat->ca_last_command) {
+	case TAG_APP_INFO_ENQUIRY:
+		err = firesat_ca_app_info(firesat, arg);
+		break;
+	case TAG_CA_INFO_ENQUIRY:
+		err = firesat_ca_info(firesat, arg);
+		break;
+	default:
+		if (avc_tuner_status(firesat, &info))
+			err = -EFAULT;
+		else if (info.CaMmi == 1)
+			err = firesat_ca_get_mmi(firesat, arg);
+		else {
+			printk(KERN_INFO "%s: Unhandled message 0x%08X\n",
+			       __func__, firesat->ca_last_command);
+			err = -EFAULT;
+		}
+	}
+	firesat->ca_last_command = 0;
+	return err;
+}
+
+static int firesat_ca_pmt(struct firesat *firesat, void *arg)
+{
+	struct ca_msg *msg = arg;
+	int data_pos;
+	int data_length;
+	int i;
+
+	data_pos = 4;
+	if (msg->msg[3] & 0x80) {
+		data_length = 0;
+		for (i = 0; i < (msg->msg[3] & 0x7F); i++)
+			data_length = (data_length << 8) + msg->msg[data_pos++];
+	} else {
+		data_length = msg->msg[3];
+	}
+
+	return avc_ca_pmt(firesat, &msg->msg[data_pos], data_length) ?
+	       -EFAULT : 0;
+}
+
+static int firesat_ca_send_msg(struct firesat *firesat, void *arg)
+{
+	struct ca_msg *msg = arg;
+	int err;
+
+	/* Do we need a semaphore for this? */
+	firesat->ca_last_command =
+		(msg->msg[0] << 16) + (msg->msg[1] << 8) + msg->msg[2];
+	switch (firesat->ca_last_command) {
+	case TAG_CA_PMT:
+		err = firesat_ca_pmt(firesat, arg);
+		break;
+	case TAG_APP_INFO_ENQUIRY:
+		/* handled in ca_get_msg */
+		err = 0;
+		break;
+	case TAG_CA_INFO_ENQUIRY:
+		/* handled in ca_get_msg */
+		err = 0;
+		break;
+	case TAG_ENTER_MENU:
+		err = avc_ca_enter_menu(firesat);
+		break;
+	default:
+		printk(KERN_ERR "%s: Unhandled unknown message 0x%08X\n",
+		       __func__, firesat->ca_last_command);
+		err = -EFAULT;
+	}
+	return err;
+}
+
+static int firesat_ca_ioctl(struct inode *inode, struct file *file,
+			    unsigned int cmd, void *arg)
+{
+	struct dvb_device *dvbdev = file->private_data;
+	struct firesat *firesat = dvbdev->priv;
+	ANTENNA_INPUT_INFO info;
+	int err;
+
+	switch(cmd) {
+	case CA_RESET:
+		err = firesat_ca_reset(firesat);
+		break;
+	case CA_GET_CAP:
+		err = firesat_ca_get_caps(arg);
+		break;
+	case CA_GET_SLOT_INFO:
+		err = firesat_ca_get_slot_info(firesat, arg);
+		break;
+	case CA_GET_MSG:
+		err = firesat_ca_get_msg(firesat, arg);
+		break;
+	case CA_SEND_MSG:
+		err = firesat_ca_send_msg(firesat, arg);
+		break;
+	default:
+		printk(KERN_INFO "%s: Unhandled ioctl, command: %u\n",__func__,
+		       cmd);
+		err = -EOPNOTSUPP;
+	}
+
+	/* FIXME Is this necessary? */
+	avc_tuner_status(firesat, &info);
+
+	return err;
+}
+
+static unsigned int firesat_ca_io_poll(struct file *file, poll_table *wait)
+{
+	return POLLIN;
+}
+
+static struct file_operations firesat_ca_fops = {
+	.owner		= THIS_MODULE,
+	.ioctl		= dvb_generic_ioctl,
+	.open		= dvb_generic_open,
+	.release	= dvb_generic_release,
+	.poll		= firesat_ca_io_poll,
+};
+
+static struct dvb_device firesat_ca = {
+	.users		= 1,
+	.readers	= 1,
+	.writers	= 1,
+	.fops		= &firesat_ca_fops,
+	.kernel_ioctl	= firesat_ca_ioctl,
+};
+
+int firesat_ca_register(struct firesat *firesat)
+{
+	ANTENNA_INPUT_INFO info;
+	int err;
+
+	if (avc_tuner_status(firesat, &info))
+		return -EINVAL;
+
+	if (!firesat_ca_ready(&info))
+		return -EFAULT;
+
+	err = dvb_register_device(&firesat->adapter, &firesat->cadev,
+				  &firesat_ca, firesat, DVB_DEVICE_CA);
+
+	if (info.CaApplicationInfo == 0)
+		printk(KERN_ERR "%s: CaApplicationInfo is not set.\n",
+		       __func__);
+	if (info.CaDateTimeRequest == 1)
+		avc_ca_get_time_date(firesat, &firesat->ca_time_interval);
+
+	return err;
+}
+
+void firesat_ca_release(struct firesat *firesat)
+{
+	if (firesat->cadev)
+		dvb_unregister_device(firesat->cadev);
+}
diff --git a/drivers/media/dvb/firesat/firesat-ci.h b/drivers/media/dvb/firesat/firesat-ci.h
new file mode 100644
index 000000000000..9c68cd2246a7
--- /dev/null
+++ b/drivers/media/dvb/firesat/firesat-ci.h
@@ -0,0 +1,9 @@
+#ifndef _FIREDTV_CI_H
+#define _FIREDTV_CI_H
+
+struct firesat;
+
+int firesat_ca_register(struct firesat *firesat);
+void firesat_ca_release(struct firesat *firesat);
+
+#endif /* _FIREDTV_CI_H */
diff --git a/drivers/media/dvb/firesat/firesat-rc.c b/drivers/media/dvb/firesat/firesat-rc.c
new file mode 100644
index 000000000000..5f9de142ee3e
--- /dev/null
+++ b/drivers/media/dvb/firesat/firesat-rc.c
@@ -0,0 +1,191 @@
+/*
+ * FireDTV driver (formerly known as FireSAT)
+ *
+ * Copyright (C) 2004 Andreas Monitzer <andy@monitzer.com>
+ *
+ *	This program is free software; you can redistribute it and/or
+ *	modify it under the terms of the GNU General Public License as
+ *	published by the Free Software Foundation; either version 2 of
+ *	the License, or (at your option) any later version.
+ */
+
+#include <linux/bitops.h>
+#include <linux/input.h>
+#include <linux/kernel.h>
+#include <linux/string.h>
+#include <linux/types.h>
+
+#include "firesat-rc.h"
+#include "firesat.h"
+
+/* fixed table with older keycodes, geared towards MythTV */
+const static u16 oldtable[] = {
+
+	/* code from device: 0x4501...0x451f */
+
+	KEY_ESC,
+	KEY_F9,
+	KEY_1,
+	KEY_2,
+	KEY_3,
+	KEY_4,
+	KEY_5,
+	KEY_6,
+	KEY_7,
+	KEY_8,
+	KEY_9,
+	KEY_I,
+	KEY_0,
+	KEY_ENTER,
+	KEY_RED,
+	KEY_UP,
+	KEY_GREEN,
+	KEY_F10,
+	KEY_SPACE,
+	KEY_F11,
+	KEY_YELLOW,
+	KEY_DOWN,
+	KEY_BLUE,
+	KEY_Z,
+	KEY_P,
+	KEY_PAGEDOWN,
+	KEY_LEFT,
+	KEY_W,
+	KEY_RIGHT,
+	KEY_P,
+	KEY_M,
+
+	/* code from device: 0x4540...0x4542 */
+
+	KEY_R,
+	KEY_V,
+	KEY_C,
+};
+
+/* user-modifiable table for a remote as sold in 2008 */
+const static u16 keytable[] = {
+
+	/* code from device: 0x0300...0x031f */
+
+	[0x00] = KEY_POWER,
+	[0x01] = KEY_SLEEP,
+	[0x02] = KEY_STOP,
+	[0x03] = KEY_OK,
+	[0x04] = KEY_RIGHT,
+	[0x05] = KEY_1,
+	[0x06] = KEY_2,
+	[0x07] = KEY_3,
+	[0x08] = KEY_LEFT,
+	[0x09] = KEY_4,
+	[0x0a] = KEY_5,
+	[0x0b] = KEY_6,
+	[0x0c] = KEY_UP,
+	[0x0d] = KEY_7,
+	[0x0e] = KEY_8,
+	[0x0f] = KEY_9,
+	[0x10] = KEY_DOWN,
+	[0x11] = KEY_TITLE,	/* "OSD" - fixme */
+	[0x12] = KEY_0,
+	[0x13] = KEY_F20,	/* "16:9" - fixme */
+	[0x14] = KEY_SCREEN,	/* "FULL" - fixme */
+	[0x15] = KEY_MUTE,
+	[0x16] = KEY_SUBTITLE,
+	[0x17] = KEY_RECORD,
+	[0x18] = KEY_TEXT,
+	[0x19] = KEY_AUDIO,
+	[0x1a] = KEY_RED,
+	[0x1b] = KEY_PREVIOUS,
+	[0x1c] = KEY_REWIND,
+	[0x1d] = KEY_PLAYPAUSE,
+	[0x1e] = KEY_NEXT,
+	[0x1f] = KEY_VOLUMEUP,
+
+	/* code from device: 0x0340...0x0354 */
+
+	[0x20] = KEY_CHANNELUP,
+	[0x21] = KEY_F21,	/* "4:3" - fixme */
+	[0x22] = KEY_TV,
+	[0x23] = KEY_DVD,
+	[0x24] = KEY_VCR,
+	[0x25] = KEY_AUX,
+	[0x26] = KEY_GREEN,
+	[0x27] = KEY_YELLOW,
+	[0x28] = KEY_BLUE,
+	[0x29] = KEY_CHANNEL,	/* "CH.LIST" */
+	[0x2a] = KEY_VENDOR,	/* "CI" - fixme */
+	[0x2b] = KEY_VOLUMEDOWN,
+	[0x2c] = KEY_CHANNELDOWN,
+	[0x2d] = KEY_LAST,
+	[0x2e] = KEY_INFO,
+	[0x2f] = KEY_FORWARD,
+	[0x30] = KEY_LIST,
+	[0x31] = KEY_FAVORITES,
+	[0x32] = KEY_MENU,
+	[0x33] = KEY_EPG,
+	[0x34] = KEY_EXIT,
+};
+
+int firesat_register_rc(struct firesat *firesat, struct device *dev)
+{
+	struct input_dev *idev;
+	int i, err;
+
+	idev = input_allocate_device();
+	if (!idev)
+		return -ENOMEM;
+
+	firesat->remote_ctrl_dev = idev;
+	idev->name = "FireDTV remote control";
+	idev->dev.parent = dev;
+	idev->evbit[0] = BIT_MASK(EV_KEY);
+	idev->keycode = kmemdup(keytable, sizeof(keytable), GFP_KERNEL);
+	if (!idev->keycode) {
+		err = -ENOMEM;
+		goto fail;
+	}
+	idev->keycodesize = sizeof(keytable[0]);
+	idev->keycodemax = ARRAY_SIZE(keytable);
+
+	for (i = 0; i < ARRAY_SIZE(keytable); i++)
+		set_bit(keytable[i], idev->keybit);
+
+	err = input_register_device(idev);
+	if (err)
+		goto fail_free_keymap;
+
+	return 0;
+
+fail_free_keymap:
+	kfree(idev->keycode);
+fail:
+	input_free_device(idev);
+	return err;
+}
+
+void firesat_unregister_rc(struct firesat *firesat)
+{
+	kfree(firesat->remote_ctrl_dev->keycode);
+	input_unregister_device(firesat->remote_ctrl_dev);
+}
+
+void firesat_handle_rc(struct firesat *firesat, unsigned int code)
+{
+	u16 *keycode = firesat->remote_ctrl_dev->keycode;
+
+	if (code >= 0x0300 && code <= 0x031f)
+		code = keycode[code - 0x0300];
+	else if (code >= 0x0340 && code <= 0x0354)
+		code = keycode[code - 0x0320];
+	else if (code >= 0x4501 && code <= 0x451f)
+		code = oldtable[code - 0x4501];
+	else if (code >= 0x4540 && code <= 0x4542)
+		code = oldtable[code - 0x4521];
+	else {
+		printk(KERN_DEBUG "firedtv: invalid key code 0x%04x "
+		       "from remote control\n", code);
+		return;
+	}
+
+	input_report_key(firesat->remote_ctrl_dev, code, 1);
+	input_report_key(firesat->remote_ctrl_dev, code, 0);
+}
diff --git a/drivers/media/dvb/firesat/firesat-rc.h b/drivers/media/dvb/firesat/firesat-rc.h
new file mode 100644
index 000000000000..12c1c5c28b36
--- /dev/null
+++ b/drivers/media/dvb/firesat/firesat-rc.h
@@ -0,0 +1,11 @@
+#ifndef _FIREDTV_RC_H
+#define _FIREDTV_RC_H
+
+struct firesat;
+struct device;
+
+int firesat_register_rc(struct firesat *firesat, struct device *dev);
+void firesat_unregister_rc(struct firesat *firesat);
+void firesat_handle_rc(struct firesat *firesat, unsigned int code);
+
+#endif /* _FIREDTV_RC_H */
diff --git a/drivers/media/dvb/firesat/firesat.h b/drivers/media/dvb/firesat/firesat.h
new file mode 100644
index 000000000000..51f64c0afcdb
--- /dev/null
+++ b/drivers/media/dvb/firesat/firesat.h
@@ -0,0 +1,227 @@
+/*
+ * FireDTV driver (formerly known as FireSAT)
+ *
+ * Copyright (C) 2004 Andreas Monitzer <andy@monitzer.com>
+ * Copyright (C) 2008 Henrik Kurelid <henrik@kurelid.se>
+ *
+ *	This program is free software; you can redistribute it and/or
+ *	modify it under the terms of the GNU General Public License as
+ *	published by the Free Software Foundation; either version 2 of
+ *	the License, or (at your option) any later version.
+ */
+
+#ifndef _FIREDTV_H
+#define _FIREDTV_H
+
+#include <linux/dvb/dmx.h>
+#include <linux/dvb/frontend.h>
+#include <linux/list.h>
+#include <linux/mutex.h>
+#include <linux/spinlock_types.h>
+#include <linux/types.h>
+#include <linux/wait.h>
+#include <linux/workqueue.h>
+
+#include <demux.h>
+#include <dmxdev.h>
+#include <dvb_demux.h>
+#include <dvb_frontend.h>
+#include <dvb_net.h>
+#include <dvbdev.h>
+
+#include <linux/version.h>
+#if LINUX_VERSION_CODE > KERNEL_VERSION(2, 6, 25)
+#define DVB_REGISTER_ADAPTER(x, y, z, w, v) dvb_register_adapter(x, y, z, w, v)
+#else
+#define DVB_REGISTER_ADAPTER(x, y, z, w, v) dvb_register_adapter(x, y, z, w)
+#define DVB_DEFINE_MOD_OPT_ADAPTER_NR(x)
+#endif
+
+/*****************************************************************
+ * CA message command constants from en50221_app_tags.h of libdvb
+ *****************************************************************/
+/*	Resource Manager		*/
+#define TAG_PROFILE_ENQUIRY		0x9f8010
+#define TAG_PROFILE			0x9f8011
+#define TAG_PROFILE_CHANGE		0x9f8012
+
+/*	Application Info		*/
+#define TAG_APP_INFO_ENQUIRY		0x9f8020
+#define TAG_APP_INFO			0x9f8021
+#define TAG_ENTER_MENU			0x9f8022
+
+/*	CA Support			*/
+#define TAG_CA_INFO_ENQUIRY		0x9f8030
+#define TAG_CA_INFO			0x9f8031
+#define TAG_CA_PMT			0x9f8032
+#define TAG_CA_PMT_REPLY		0x9f8033
+
+/*	Host Control			*/
+#define TAG_TUNE			0x9f8400
+#define TAG_REPLACE			0x9f8401
+#define TAG_CLEAR_REPLACE		0x9f8402
+#define TAG_ASK_RELEASE			0x9f8403
+
+/*	Date and Time			*/
+#define TAG_DATE_TIME_ENQUIRY		0x9f8440
+#define TAG_DATE_TIME			0x9f8441
+
+/*	Man Machine Interface (MMI)	*/
+#define TAG_CLOSE_MMI			0x9f8800
+#define TAG_DISPLAY_CONTROL		0x9f8801
+#define TAG_DISPLAY_REPLY		0x9f8802
+#define TAG_TEXT_LAST			0x9f8803
+#define TAG_TEXT_MORE			0x9f8804
+#define TAG_KEYPAD_CONTROL		0x9f8805
+#define TAG_KEYPRESS			0x9f8806
+#define TAG_ENQUIRY			0x9f8807
+#define TAG_ANSWER			0x9f8808
+#define TAG_MENU_LAST			0x9f8809
+#define TAG_MENU_MORE			0x9f880a
+#define TAG_MENU_ANSWER			0x9f880b
+#define TAG_LIST_LAST			0x9f880c
+#define TAG_LIST_MORE			0x9f880d
+#define TAG_SUBTITLE_SEGMENT_LAST	0x9f880e
+#define TAG_SUBTITLE_SEGMENT_MORE	0x9f880f
+#define TAG_DISPLAY_MESSAGE		0x9f8810
+#define TAG_SCENE_END_MARK		0x9f8811
+#define TAG_SCENE_DONE			0x9f8812
+#define TAG_SCENE_CONTROL		0x9f8813
+#define TAG_SUBTITLE_DOWNLOAD_LAST	0x9f8814
+#define TAG_SUBTITLE_DOWNLOAD_MORE	0x9f8815
+#define TAG_FLUSH_DOWNLOAD		0x9f8816
+#define TAG_DOWNLOAD_REPLY		0x9f8817
+
+/*	Low Speed Communications	*/
+#define TAG_COMMS_COMMAND		0x9f8c00
+#define TAG_CONNECTION_DESCRIPTOR	0x9f8c01
+#define TAG_COMMS_REPLY			0x9f8c02
+#define TAG_COMMS_SEND_LAST		0x9f8c03
+#define TAG_COMMS_SEND_MORE		0x9f8c04
+#define TAG_COMMS_RECV_LAST		0x9f8c05
+#define TAG_COMMS_RECV_MORE		0x9f8c06
+
+/* Authentication */
+#define TAG_AUTH_REQ			0x9f8200
+#define TAG_AUTH_RESP			0x9f8201
+
+/* Teletext */
+#define TAG_TELETEXT_EBU		0x9f9000
+
+/* Smartcard */
+#define TAG_SMARTCARD_COMMAND		0x9f8e00
+#define TAG_SMARTCARD_REPLY		0x9f8e01
+#define TAG_SMARTCARD_SEND		0x9f8e02
+#define TAG_SMARTCARD_RCV		0x9f8e03
+
+/* EPG */
+#define TAG_EPG_ENQUIRY         	0x9f8f00
+#define TAG_EPG_REPLY           	0x9f8f01
+
+
+enum model_type {
+	FireSAT_UNKNOWN = 0,
+	FireSAT_DVB_S   = 1,
+	FireSAT_DVB_C   = 2,
+	FireSAT_DVB_T   = 3,
+	FireSAT_DVB_S2  = 4,
+};
+
+struct input_dev;
+struct hpsb_iso;
+struct unit_directory;
+
+struct firesat {
+	struct dvb_adapter	adapter;
+	struct dmxdev		dmxdev;
+	struct dvb_demux	demux;
+	struct dmx_frontend	frontend;
+	struct dvb_net		dvbnet;
+	struct dvb_frontend	fe;
+
+	struct dvb_device	*cadev;
+	int			ca_last_command;
+	int			ca_time_interval;
+
+	struct mutex		avc_mutex;
+	wait_queue_head_t	avc_wait;
+	bool			avc_reply_received;
+	struct work_struct	remote_ctrl_work;
+	struct input_dev	*remote_ctrl_dev;
+
+	struct firesat_channel {
+		bool active;
+		int pid;
+	} channel[16];
+	struct mutex demux_mutex;
+
+	struct unit_directory *ud;
+
+	enum model_type type;
+	char subunit;
+	fe_sec_voltage_t voltage;
+	fe_sec_tone_mode_t tone;
+
+	int isochannel;
+	struct hpsb_iso *iso_handle;
+
+	struct list_head list;
+
+	/* needed by avc_api */
+	int resp_length;
+	u8 respfrm[512];
+};
+
+struct firewireheader {
+	union {
+		struct {
+			__u8 tcode:4;
+			__u8 sy:4;
+			__u8 tag:2;
+			__u8 channel:6;
+
+			__u8 length_l;
+			__u8 length_h;
+		} hdr;
+		__u32 val;
+	};
+};
+
+struct CIPHeader {
+	union {
+		struct {
+			__u8 syncbits:2;
+			__u8 sid:6;
+			__u8 dbs;
+			__u8 fn:2;
+			__u8 qpc:3;
+			__u8 sph:1;
+			__u8 rsv:2;
+			__u8 dbc;
+			__u8 syncbits2:2;
+			__u8 fmt:6;
+			__u32 fdf:24;
+		} cip;
+		__u64 val;
+	};
+};
+
+extern const char *firedtv_model_names[];
+extern struct list_head firesat_list;
+extern spinlock_t firesat_list_lock;
+
+struct device;
+
+/* firesat_dvb.c */
+int firesat_start_feed(struct dvb_demux_feed *dvbdmxfeed);
+int firesat_stop_feed(struct dvb_demux_feed *dvbdmxfeed);
+int firesat_dvbdev_init(struct firesat *firesat, struct device *dev);
+
+/* firesat_fe.c */
+void firesat_frontend_init(struct firesat *firesat);
+
+/* firesat_iso.c */
+int setup_iso_channel(struct firesat *firesat);
+void tear_down_iso_channel(struct firesat *firesat);
+
+#endif /* _FIREDTV_H */
diff --git a/drivers/media/dvb/firesat/firesat_1394.c b/drivers/media/dvb/firesat/firesat_1394.c
new file mode 100644
index 000000000000..82bd9786571d
--- /dev/null
+++ b/drivers/media/dvb/firesat/firesat_1394.c
@@ -0,0 +1,291 @@
+/*
+ * FireDTV driver (formerly known as FireSAT)
+ *
+ * Copyright (C) 2004 Andreas Monitzer <andy@monitzer.com>
+ * Copyright (C) 2007-2008 Ben Backx <ben@bbackx.com>
+ * Copyright (C) 2008 Henrik Kurelid <henrik@kurelid.se>
+ *
+ *	This program is free software; you can redistribute it and/or
+ *	modify it under the terms of the GNU General Public License as
+ *	published by the Free Software Foundation; either version 2 of
+ *	the License, or (at your option) any later version.
+ */
+
+#include <linux/device.h>
+#include <linux/errno.h>
+#include <linux/kernel.h>
+#include <linux/list.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/string.h>
+#include <linux/types.h>
+
+#include <dmxdev.h>
+#include <dvb_demux.h>
+#include <dvb_frontend.h>
+#include <dvbdev.h>
+
+#include <csr1212.h>
+#include <highlevel.h>
+#include <hosts.h>
+#include <ieee1394_hotplug.h>
+#include <nodemgr.h>
+
+#include "avc_api.h"
+#include "cmp.h"
+#include "firesat.h"
+#include "firesat-ci.h"
+#include "firesat-rc.h"
+
+#define MATCH_FLAGS	IEEE1394_MATCH_VENDOR_ID | IEEE1394_MATCH_MODEL_ID | \
+			IEEE1394_MATCH_SPECIFIER_ID | IEEE1394_MATCH_VERSION
+#define DIGITAL_EVERYWHERE_OUI   0x001287
+
+static struct ieee1394_device_id firesat_id_table[] = {
+
+	{
+		/* FloppyDTV S/CI and FloppyDTV S2 */
+		.match_flags	= MATCH_FLAGS,
+		.vendor_id	= DIGITAL_EVERYWHERE_OUI,
+		.model_id	= 0x000024,
+		.specifier_id	= AVC_UNIT_SPEC_ID_ENTRY,
+		.version	= AVC_SW_VERSION_ENTRY,
+	},{
+		/* FloppyDTV T/CI */
+		.match_flags	= MATCH_FLAGS,
+		.vendor_id	= DIGITAL_EVERYWHERE_OUI,
+		.model_id	= 0x000025,
+		.specifier_id	= AVC_UNIT_SPEC_ID_ENTRY,
+		.version	= AVC_SW_VERSION_ENTRY,
+	},{
+		/* FloppyDTV C/CI */
+		.match_flags	= MATCH_FLAGS,
+		.vendor_id	= DIGITAL_EVERYWHERE_OUI,
+		.model_id	= 0x000026,
+		.specifier_id	= AVC_UNIT_SPEC_ID_ENTRY,
+		.version	= AVC_SW_VERSION_ENTRY,
+	},{
+		/* FireDTV S/CI and FloppyDTV S2 */
+		.match_flags	= MATCH_FLAGS,
+		.vendor_id	= DIGITAL_EVERYWHERE_OUI,
+		.model_id	= 0x000034,
+		.specifier_id	= AVC_UNIT_SPEC_ID_ENTRY,
+		.version	= AVC_SW_VERSION_ENTRY,
+	},{
+		/* FireDTV T/CI */
+		.match_flags	= MATCH_FLAGS,
+		.vendor_id	= DIGITAL_EVERYWHERE_OUI,
+		.model_id	= 0x000035,
+		.specifier_id	= AVC_UNIT_SPEC_ID_ENTRY,
+		.version	= AVC_SW_VERSION_ENTRY,
+	},{
+		/* FireDTV C/CI */
+		.match_flags	= MATCH_FLAGS,
+		.vendor_id	= DIGITAL_EVERYWHERE_OUI,
+		.model_id	= 0x000036,
+		.specifier_id	= AVC_UNIT_SPEC_ID_ENTRY,
+		.version	= AVC_SW_VERSION_ENTRY,
+	}, { }
+};
+
+MODULE_DEVICE_TABLE(ieee1394, firesat_id_table);
+
+/* list of all firesat devices */
+LIST_HEAD(firesat_list);
+spinlock_t firesat_list_lock = SPIN_LOCK_UNLOCKED;
+
+static void fcp_request(struct hpsb_host *host,
+			int nodeid,
+			int direction,
+			int cts,
+			u8 *data,
+			size_t length)
+{
+	struct firesat *firesat = NULL;
+	struct firesat *firesat_entry;
+	unsigned long flags;
+
+	if (length > 0 && ((data[0] & 0xf0) >> 4) == 0) {
+
+		spin_lock_irqsave(&firesat_list_lock, flags);
+		list_for_each_entry(firesat_entry,&firesat_list,list) {
+			if (firesat_entry->ud->ne->host == host &&
+			    firesat_entry->ud->ne->nodeid == nodeid &&
+			    (firesat_entry->subunit == (data[1]&0x7) ||
+			     (firesat_entry->subunit == 0 &&
+			      (data[1]&0x7) == 0x7))) {
+				firesat=firesat_entry;
+				break;
+			}
+		}
+		spin_unlock_irqrestore(&firesat_list_lock, flags);
+
+		if (firesat)
+			avc_recv(firesat, data, length);
+	}
+}
+
+const char *firedtv_model_names[] = {
+	[FireSAT_UNKNOWN] = "unknown type",
+	[FireSAT_DVB_S]   = "FireDTV S/CI",
+	[FireSAT_DVB_C]   = "FireDTV C/CI",
+	[FireSAT_DVB_T]   = "FireDTV T/CI",
+	[FireSAT_DVB_S2]  = "FireDTV S2  ",
+};
+
+static int firesat_probe(struct device *dev)
+{
+	struct unit_directory *ud =
+			container_of(dev, struct unit_directory, device);
+	struct firesat *firesat;
+	unsigned long flags;
+	int kv_len;
+	void *kv_str;
+	int i;
+	int err = -ENOMEM;
+
+	firesat = kzalloc(sizeof(*firesat), GFP_KERNEL);
+	if (!firesat)
+		return -ENOMEM;
+
+	dev->driver_data = firesat;
+	firesat->ud		= ud;
+	firesat->subunit	= 0;
+	firesat->isochannel	= -1;
+	firesat->tone		= 0xff;
+	firesat->voltage	= 0xff;
+
+	mutex_init(&firesat->avc_mutex);
+	init_waitqueue_head(&firesat->avc_wait);
+	firesat->avc_reply_received = true;
+	mutex_init(&firesat->demux_mutex);
+	INIT_WORK(&firesat->remote_ctrl_work, avc_remote_ctrl_work);
+
+	/* Reading device model from ROM */
+	kv_len = (ud->model_name_kv->value.leaf.len - 2) * sizeof(quadlet_t);
+	kv_str = CSR1212_TEXTUAL_DESCRIPTOR_LEAF_DATA(ud->model_name_kv);
+	for (i = ARRAY_SIZE(firedtv_model_names); --i;)
+		if (strlen(firedtv_model_names[i]) <= kv_len &&
+		    strncmp(kv_str, firedtv_model_names[i], kv_len) == 0)
+			break;
+	firesat->type = i;
+
+	/*
+	 * Work around a bug in udev's path_id script:  Use the fw-host's dev
+	 * instead of the unit directory's dev as parent of the input device.
+	 */
+	err = firesat_register_rc(firesat, dev->parent->parent);
+	if (err)
+		goto fail_free;
+
+	INIT_LIST_HEAD(&firesat->list);
+	spin_lock_irqsave(&firesat_list_lock, flags);
+	list_add_tail(&firesat->list, &firesat_list);
+	spin_unlock_irqrestore(&firesat_list_lock, flags);
+
+	err = avc_identify_subunit(firesat);
+	if (err)
+		goto fail;
+
+	err = firesat_dvbdev_init(firesat, dev);
+	if (err)
+		goto fail;
+
+	avc_register_remote_control(firesat);
+	return 0;
+
+fail:
+	spin_lock_irqsave(&firesat_list_lock, flags);
+	list_del(&firesat->list);
+	spin_unlock_irqrestore(&firesat_list_lock, flags);
+	firesat_unregister_rc(firesat);
+fail_free:
+	kfree(firesat);
+	return err;
+}
+
+static int firesat_remove(struct device *dev)
+{
+	struct firesat *firesat = dev->driver_data;
+	unsigned long flags;
+
+	firesat_ca_release(firesat);
+	dvb_unregister_frontend(&firesat->fe);
+	dvb_net_release(&firesat->dvbnet);
+	firesat->demux.dmx.close(&firesat->demux.dmx);
+	firesat->demux.dmx.remove_frontend(&firesat->demux.dmx,
+					   &firesat->frontend);
+	dvb_dmxdev_release(&firesat->dmxdev);
+	dvb_dmx_release(&firesat->demux);
+	dvb_unregister_adapter(&firesat->adapter);
+
+	spin_lock_irqsave(&firesat_list_lock, flags);
+	list_del(&firesat->list);
+	spin_unlock_irqrestore(&firesat_list_lock, flags);
+
+	cancel_work_sync(&firesat->remote_ctrl_work);
+	firesat_unregister_rc(firesat);
+
+	kfree(firesat);
+	return 0;
+}
+
+static int firesat_update(struct unit_directory *ud)
+{
+	struct firesat *firesat = ud->device.driver_data;
+
+	if (firesat->isochannel >= 0)
+		cmp_establish_pp_connection(firesat, firesat->subunit,
+					    firesat->isochannel);
+	return 0;
+}
+
+static struct hpsb_protocol_driver firesat_driver = {
+
+	.name		= "firedtv",
+	.id_table	= firesat_id_table,
+	.update		= firesat_update,
+
+	.driver         = {
+		//.name and .bus are filled in for us in more recent linux versions
+		//.name	= "FireSAT",
+		//.bus	= &ieee1394_bus_type,
+		.probe  = firesat_probe,
+		.remove = firesat_remove,
+	},
+};
+
+static struct hpsb_highlevel firesat_highlevel = {
+	.name		= "firedtv",
+	.fcp_request	= fcp_request,
+};
+
+static int __init firesat_init(void)
+{
+	int ret;
+
+	hpsb_register_highlevel(&firesat_highlevel);
+	ret = hpsb_register_protocol(&firesat_driver);
+	if (ret) {
+		printk(KERN_ERR "firedtv: failed to register protocol\n");
+		hpsb_unregister_highlevel(&firesat_highlevel);
+	}
+	return ret;
+}
+
+static void __exit firesat_exit(void)
+{
+	hpsb_unregister_protocol(&firesat_driver);
+	hpsb_unregister_highlevel(&firesat_highlevel);
+}
+
+module_init(firesat_init);
+module_exit(firesat_exit);
+
+MODULE_AUTHOR("Andreas Monitzer <andy@monitzer.com>");
+MODULE_AUTHOR("Ben Backx <ben@bbackx.com>");
+MODULE_DESCRIPTION("FireDTV DVB Driver");
+MODULE_LICENSE("GPL");
+MODULE_SUPPORTED_DEVICE("FireDTV DVB");
diff --git a/drivers/media/dvb/firesat/firesat_dvb.c b/drivers/media/dvb/firesat/firesat_dvb.c
new file mode 100644
index 000000000000..cfa3a2e8edd1
--- /dev/null
+++ b/drivers/media/dvb/firesat/firesat_dvb.c
@@ -0,0 +1,276 @@
+/*
+ * FireDTV driver (formerly known as FireSAT)
+ *
+ * Copyright (C) 2004 Andreas Monitzer <andy@monitzer.com>
+ * Copyright (C) 2008 Henrik Kurelid <henrik@kurelid.se>
+ *
+ *	This program is free software; you can redistribute it and/or
+ *	modify it under the terms of the GNU General Public License as
+ *	published by the Free Software Foundation; either version 2 of
+ *	the License, or (at your option) any later version.
+ */
+
+#include <linux/errno.h>
+#include <linux/kernel.h>
+#include <linux/mutex.h>
+#include <linux/types.h>
+
+#include <dvb_demux.h>
+#include <dvb_frontend.h>
+#include <dvbdev.h>
+
+#include "avc_api.h"
+#include "firesat.h"
+#include "firesat-ci.h"
+
+DVB_DEFINE_MOD_OPT_ADAPTER_NR(adapter_nr);
+
+static struct firesat_channel *firesat_channel_allocate(struct firesat *firesat)
+{
+	struct firesat_channel *c = NULL;
+	int k;
+
+	if (mutex_lock_interruptible(&firesat->demux_mutex))
+		return NULL;
+
+	for (k = 0; k < 16; k++)
+		if (!firesat->channel[k].active) {
+			firesat->channel[k].active = true;
+			c = &firesat->channel[k];
+			break;
+		}
+
+	mutex_unlock(&firesat->demux_mutex);
+	return c;
+}
+
+static int firesat_channel_collect(struct firesat *firesat, int *pidc, u16 pid[])
+{
+	int k, l = 0;
+
+	if (mutex_lock_interruptible(&firesat->demux_mutex))
+		return -EINTR;
+
+	for (k = 0; k < 16; k++)
+		if (firesat->channel[k].active)
+			pid[l++] = firesat->channel[k].pid;
+
+	mutex_unlock(&firesat->demux_mutex);
+
+	*pidc = l;
+
+	return 0;
+}
+
+static int firesat_channel_release(struct firesat *firesat,
+				   struct firesat_channel *channel)
+{
+	if (mutex_lock_interruptible(&firesat->demux_mutex))
+		return -EINTR;
+
+	channel->active = false;
+
+	mutex_unlock(&firesat->demux_mutex);
+	return 0;
+}
+
+int firesat_start_feed(struct dvb_demux_feed *dvbdmxfeed)
+{
+	struct firesat *firesat = (struct firesat*)dvbdmxfeed->demux->priv;
+	struct firesat_channel *channel;
+	int pidc,k;
+	u16 pids[16];
+
+	switch (dvbdmxfeed->type) {
+	case DMX_TYPE_TS:
+	case DMX_TYPE_SEC:
+		break;
+	default:
+		printk(KERN_ERR "%s: invalid type %u\n",
+		       __func__, dvbdmxfeed->type);
+		return -EINVAL;
+	}
+
+	if (dvbdmxfeed->type == DMX_TYPE_TS) {
+		switch (dvbdmxfeed->pes_type) {
+		case DMX_TS_PES_VIDEO:
+		case DMX_TS_PES_AUDIO:
+		case DMX_TS_PES_TELETEXT:
+		case DMX_TS_PES_PCR:
+		case DMX_TS_PES_OTHER:
+			//Dirty fix to keep firesat->channel pid-list up to date
+			for(k=0;k<16;k++){
+				if (!firesat->channel[k].active)
+					firesat->channel[k].pid =
+						dvbdmxfeed->pid;
+					break;
+			}
+			channel = firesat_channel_allocate(firesat);
+			break;
+		default:
+			printk(KERN_ERR "%s: invalid pes type %u\n",
+			       __func__, dvbdmxfeed->pes_type);
+			return -EINVAL;
+		}
+	} else {
+		channel = firesat_channel_allocate(firesat);
+	}
+
+	if (!channel) {
+		printk(KERN_ERR "%s: busy!\n", __func__);
+		return -EBUSY;
+	}
+
+	dvbdmxfeed->priv = channel;
+	channel->pid = dvbdmxfeed->pid;
+
+	if (firesat_channel_collect(firesat, &pidc, pids)) {
+		firesat_channel_release(firesat, channel);
+		printk(KERN_ERR "%s: could not collect pids!\n", __func__);
+		return -EINTR;
+	}
+
+	if (dvbdmxfeed->pid == 8192) {
+		k = avc_tuner_get_ts(firesat);
+		if (k) {
+			firesat_channel_release(firesat, channel);
+			printk("%s: AVCTuner_GetTS failed with error %d\n",
+			       __func__, k);
+			return k;
+		}
+	} else {
+		k = avc_tuner_set_pids(firesat, pidc, pids);
+		if (k) {
+			firesat_channel_release(firesat, channel);
+			printk("%s: AVCTuner_SetPIDs failed with error %d\n",
+			       __func__, k);
+			return k;
+		}
+	}
+
+	return 0;
+}
+
+int firesat_stop_feed(struct dvb_demux_feed *dvbdmxfeed)
+{
+	struct dvb_demux *demux = dvbdmxfeed->demux;
+	struct firesat *firesat = (struct firesat*)demux->priv;
+	struct firesat_channel *c = dvbdmxfeed->priv;
+	int k, l;
+	u16 pids[16];
+
+	if (dvbdmxfeed->type == DMX_TYPE_TS && !((dvbdmxfeed->ts_type & TS_PACKET) &&
+				(demux->dmx.frontend->source != DMX_MEMORY_FE))) {
+
+		if (dvbdmxfeed->ts_type & TS_DECODER) {
+
+			if (dvbdmxfeed->pes_type >= DMX_TS_PES_OTHER ||
+				!demux->pesfilter[dvbdmxfeed->pes_type])
+
+				return -EINVAL;
+
+			demux->pids[dvbdmxfeed->pes_type] |= 0x8000;
+			demux->pesfilter[dvbdmxfeed->pes_type] = NULL;
+		}
+
+		if (!(dvbdmxfeed->ts_type & TS_DECODER &&
+			dvbdmxfeed->pes_type < DMX_TS_PES_OTHER))
+
+			return 0;
+	}
+
+	if (mutex_lock_interruptible(&firesat->demux_mutex))
+		return -EINTR;
+
+	/* list except channel to be removed */
+	for (k = 0, l = 0; k < 16; k++)
+		if (firesat->channel[k].active) {
+			if (&firesat->channel[k] != c)
+				pids[l++] = firesat->channel[k].pid;
+			else
+				firesat->channel[k].active = false;
+		}
+
+	k = avc_tuner_set_pids(firesat, l, pids);
+	if (!k)
+		c->active = false;
+
+	mutex_unlock(&firesat->demux_mutex);
+	return k;
+}
+
+int firesat_dvbdev_init(struct firesat *firesat, struct device *dev)
+{
+	int err;
+
+	err = DVB_REGISTER_ADAPTER(&firesat->adapter,
+				   firedtv_model_names[firesat->type],
+				   THIS_MODULE, dev, adapter_nr);
+	if (err)
+		goto fail_log;
+
+	/*DMX_TS_FILTERING | DMX_SECTION_FILTERING*/
+	firesat->demux.dmx.capabilities = 0;
+
+	firesat->demux.priv		= (void *)firesat;
+	firesat->demux.filternum	= 16;
+	firesat->demux.feednum		= 16;
+	firesat->demux.start_feed	= firesat_start_feed;
+	firesat->demux.stop_feed	= firesat_stop_feed;
+	firesat->demux.write_to_decoder	= NULL;
+
+	err = dvb_dmx_init(&firesat->demux);
+	if (err)
+		goto fail_unreg_adapter;
+
+	firesat->dmxdev.filternum	= 16;
+	firesat->dmxdev.demux		= &firesat->demux.dmx;
+	firesat->dmxdev.capabilities	= 0;
+
+	err = dvb_dmxdev_init(&firesat->dmxdev, &firesat->adapter);
+	if (err)
+		goto fail_dmx_release;
+
+	firesat->frontend.source = DMX_FRONTEND_0;
+
+	err = firesat->demux.dmx.add_frontend(&firesat->demux.dmx,
+					      &firesat->frontend);
+	if (err)
+		goto fail_dmxdev_release;
+
+	err = firesat->demux.dmx.connect_frontend(&firesat->demux.dmx,
+						  &firesat->frontend);
+	if (err)
+		goto fail_rem_frontend;
+
+	dvb_net_init(&firesat->adapter, &firesat->dvbnet, &firesat->demux.dmx);
+
+	firesat_frontend_init(firesat);
+	err = dvb_register_frontend(&firesat->adapter, &firesat->fe);
+	if (err)
+		goto fail_net_release;
+
+	err = firesat_ca_register(firesat);
+	if (err)
+		dev_info(dev, "Conditional Access Module not enabled\n");
+
+	return 0;
+
+fail_net_release:
+	dvb_net_release(&firesat->dvbnet);
+	firesat->demux.dmx.close(&firesat->demux.dmx);
+fail_rem_frontend:
+	firesat->demux.dmx.remove_frontend(&firesat->demux.dmx,
+					   &firesat->frontend);
+fail_dmxdev_release:
+	dvb_dmxdev_release(&firesat->dmxdev);
+fail_dmx_release:
+	dvb_dmx_release(&firesat->demux);
+fail_unreg_adapter:
+	dvb_unregister_adapter(&firesat->adapter);
+fail_log:
+	dev_err(dev, "DVB initialization failed\n");
+	return err;
+}
+
+
diff --git a/drivers/media/dvb/firesat/firesat_fe.c b/drivers/media/dvb/firesat/firesat_fe.c
new file mode 100644
index 000000000000..1ed972b79573
--- /dev/null
+++ b/drivers/media/dvb/firesat/firesat_fe.c
@@ -0,0 +1,245 @@
+/*
+ * FireDTV driver (formerly known as FireSAT)
+ *
+ * Copyright (C) 2004 Andreas Monitzer <andy@monitzer.com>
+ * Copyright (C) 2008 Henrik Kurelid <henrik@kurelid.se>
+ *
+ *	This program is free software; you can redistribute it and/or
+ *	modify it under the terms of the GNU General Public License as
+ *	published by the Free Software Foundation; either version 2 of
+ *	the License, or (at your option) any later version.
+ */
+
+#include <linux/errno.h>
+#include <linux/kernel.h>
+#include <linux/string.h>
+#include <linux/types.h>
+
+#include <dvb_frontend.h>
+
+#include "avc_api.h"
+#include "cmp.h"
+#include "firesat.h"
+
+static int firesat_dvb_init(struct dvb_frontend *fe)
+{
+	struct firesat *firesat = fe->sec_priv;
+	int err;
+
+	/* FIXME - allocate free channel at IRM */
+	firesat->isochannel = firesat->adapter.num;
+
+	err = cmp_establish_pp_connection(firesat, firesat->subunit,
+					  firesat->isochannel);
+	if (err) {
+		printk(KERN_ERR "Could not establish point to point "
+		       "connection.\n");
+		return err;
+	}
+
+	return setup_iso_channel(firesat);
+}
+
+static int firesat_sleep(struct dvb_frontend *fe)
+{
+	struct firesat *firesat = fe->sec_priv;
+
+	tear_down_iso_channel(firesat);
+	cmp_break_pp_connection(firesat, firesat->subunit, firesat->isochannel);
+	firesat->isochannel = -1;
+	return 0;
+}
+
+static int firesat_diseqc_send_master_cmd(struct dvb_frontend *fe,
+					  struct dvb_diseqc_master_cmd *cmd)
+{
+	struct firesat *firesat = fe->sec_priv;
+
+	return avc_lnb_control(firesat, LNBCONTROL_DONTCARE,
+			LNBCONTROL_DONTCARE, LNBCONTROL_DONTCARE, 1, cmd);
+}
+
+static int firesat_diseqc_send_burst(struct dvb_frontend *fe,
+				     fe_sec_mini_cmd_t minicmd)
+{
+	return 0;
+}
+
+static int firesat_set_tone(struct dvb_frontend *fe, fe_sec_tone_mode_t tone)
+{
+	struct firesat *firesat = fe->sec_priv;
+
+	firesat->tone = tone;
+	return 0;
+}
+
+static int firesat_set_voltage(struct dvb_frontend *fe,
+			       fe_sec_voltage_t voltage)
+{
+	struct firesat *firesat = fe->sec_priv;
+
+	firesat->voltage = voltage;
+	return 0;
+}
+
+static int firesat_read_status(struct dvb_frontend *fe, fe_status_t *status)
+{
+	struct firesat *firesat = fe->sec_priv;
+	ANTENNA_INPUT_INFO info;
+
+	if (avc_tuner_status(firesat, &info))
+		return -EINVAL;
+
+	if (info.NoRF)
+		*status = 0;
+	else
+		*status = FE_HAS_SIGNAL | FE_HAS_VITERBI | FE_HAS_SYNC |
+			  FE_HAS_CARRIER | FE_HAS_LOCK;
+	return 0;
+}
+
+static int firesat_read_ber(struct dvb_frontend *fe, u32 *ber)
+{
+	struct firesat *firesat = fe->sec_priv;
+	ANTENNA_INPUT_INFO info;
+
+	if (avc_tuner_status(firesat, &info))
+		return -EINVAL;
+
+	*ber = info.BER[0] << 24 | info.BER[1] << 16 |
+	       info.BER[2] << 8 | info.BER[3];
+	return 0;
+}
+
+static int firesat_read_signal_strength (struct dvb_frontend *fe, u16 *strength)
+{
+	struct firesat *firesat = fe->sec_priv;
+	ANTENNA_INPUT_INFO info;
+
+	if (avc_tuner_status(firesat, &info))
+		return -EINVAL;
+
+	*strength = info.SignalStrength << 8;
+	return 0;
+}
+
+static int firesat_read_snr(struct dvb_frontend *fe, u16 *snr)
+{
+	struct firesat *firesat = fe->sec_priv;
+	ANTENNA_INPUT_INFO info;
+
+	if (avc_tuner_status(firesat, &info))
+		return -EINVAL;
+
+	/* C/N[dB] = -10 * log10(snr / 65535) */
+	*snr = (info.CarrierNoiseRatio[0] << 8) + info.CarrierNoiseRatio[1];
+	*snr *= 257;
+	return 0;
+}
+
+static int firesat_read_uncorrected_blocks(struct dvb_frontend *fe, u32 *ucblocks)
+{
+	return -EOPNOTSUPP;
+}
+
+static int firesat_set_frontend(struct dvb_frontend *fe,
+				struct dvb_frontend_parameters *params)
+{
+	struct firesat *firesat = fe->sec_priv;
+
+	/* FIXME: avc_tuner_dsd never returns ACCEPTED. Check status? */
+	if (avc_tuner_dsd(firesat, params) != ACCEPTED)
+		return -EINVAL;
+	else
+		return 0; /* not sure of this... */
+}
+
+static int firesat_get_frontend(struct dvb_frontend *fe,
+				struct dvb_frontend_parameters *params)
+{
+	return -EOPNOTSUPP;
+}
+
+void firesat_frontend_init(struct firesat *firesat)
+{
+	struct dvb_frontend_ops *ops = &firesat->fe.ops;
+	struct dvb_frontend_info *fi = &ops->info;
+
+	ops->init			= firesat_dvb_init;
+	ops->sleep			= firesat_sleep;
+
+	ops->set_frontend		= firesat_set_frontend;
+	ops->get_frontend		= firesat_get_frontend;
+
+	ops->read_status		= firesat_read_status;
+	ops->read_ber			= firesat_read_ber;
+	ops->read_signal_strength	= firesat_read_signal_strength;
+	ops->read_snr			= firesat_read_snr;
+	ops->read_ucblocks		= firesat_read_uncorrected_blocks;
+
+	ops->diseqc_send_master_cmd 	= firesat_diseqc_send_master_cmd;
+	ops->diseqc_send_burst		= firesat_diseqc_send_burst;
+	ops->set_tone			= firesat_set_tone;
+	ops->set_voltage		= firesat_set_voltage;
+
+	switch (firesat->type) {
+	case FireSAT_DVB_S:
+		fi->type		= FE_QPSK;
+
+		fi->frequency_min	= 950000;
+		fi->frequency_max	= 2150000;
+		fi->frequency_stepsize	= 125;
+		fi->symbol_rate_min	= 1000000;
+		fi->symbol_rate_max	= 40000000;
+
+		fi->caps 		= FE_CAN_INVERSION_AUTO	|
+					  FE_CAN_FEC_1_2	|
+					  FE_CAN_FEC_2_3	|
+					  FE_CAN_FEC_3_4	|
+					  FE_CAN_FEC_5_6	|
+					  FE_CAN_FEC_7_8	|
+					  FE_CAN_FEC_AUTO	|
+					  FE_CAN_QPSK;
+		break;
+
+	case FireSAT_DVB_C:
+		fi->type		= FE_QAM;
+
+		fi->frequency_min	= 47000000;
+		fi->frequency_max	= 866000000;
+		fi->frequency_stepsize	= 62500;
+		fi->symbol_rate_min	= 870000;
+		fi->symbol_rate_max	= 6900000;
+
+		fi->caps 		= FE_CAN_INVERSION_AUTO |
+					  FE_CAN_QAM_16		|
+					  FE_CAN_QAM_32		|
+					  FE_CAN_QAM_64		|
+					  FE_CAN_QAM_128	|
+					  FE_CAN_QAM_256	|
+					  FE_CAN_QAM_AUTO;
+		break;
+
+	case FireSAT_DVB_T:
+		fi->type		= FE_OFDM;
+
+		fi->frequency_min	= 49000000;
+		fi->frequency_max	= 861000000;
+		fi->frequency_stepsize	= 62500;
+
+		fi->caps 		= FE_CAN_INVERSION_AUTO		|
+					  FE_CAN_FEC_2_3		|
+					  FE_CAN_TRANSMISSION_MODE_AUTO |
+					  FE_CAN_GUARD_INTERVAL_AUTO	|
+					  FE_CAN_HIERARCHY_AUTO;
+		break;
+
+	default:
+		printk(KERN_ERR "FireDTV: no frontend for model type %d\n",
+		       firesat->type);
+	}
+	strcpy(fi->name, firedtv_model_names[firesat->type]);
+
+	firesat->fe.dvb = &firesat->adapter;
+	firesat->fe.sec_priv = firesat;
+}
diff --git a/drivers/media/dvb/firesat/firesat_iso.c b/drivers/media/dvb/firesat/firesat_iso.c
new file mode 100644
index 000000000000..b3c61f95fa94
--- /dev/null
+++ b/drivers/media/dvb/firesat/firesat_iso.c
@@ -0,0 +1,111 @@
+/*
+ * FireSAT DVB driver
+ *
+ * Copyright (C) 2008 Henrik Kurelid <henrik@kurelid.se>
+ *
+ *	This program is free software; you can redistribute it and/or
+ *	modify it under the terms of the GNU General Public License as
+ *	published by the Free Software Foundation; either version 2 of
+ *	the License, or (at your option) any later version.
+ */
+
+#include <linux/errno.h>
+#include <linux/kernel.h>
+#include <linux/list.h>
+#include <linux/spinlock.h>
+
+#include <dvb_demux.h>
+
+#include <dma.h>
+#include <iso.h>
+#include <nodemgr.h>
+
+#include "firesat.h"
+
+static void rawiso_activity_cb(struct hpsb_iso *iso);
+
+void tear_down_iso_channel(struct firesat *firesat)
+{
+	if (firesat->iso_handle != NULL) {
+		hpsb_iso_stop(firesat->iso_handle);
+		hpsb_iso_shutdown(firesat->iso_handle);
+	}
+	firesat->iso_handle = NULL;
+}
+
+int setup_iso_channel(struct firesat *firesat)
+{
+	int result;
+	firesat->iso_handle =
+		hpsb_iso_recv_init(firesat->ud->ne->host,
+				   256 * 200, //data_buf_size,
+				   256, //buf_packets,
+				   firesat->isochannel,
+				   HPSB_ISO_DMA_DEFAULT, //dma_mode,
+				   -1, //stat.config.irq_interval,
+				   rawiso_activity_cb);
+	if (firesat->iso_handle == NULL) {
+		printk(KERN_ERR "Cannot initialize iso receive.\n");
+		return -EINVAL;
+	}
+	result = hpsb_iso_recv_start(firesat->iso_handle, -1, -1, 0);
+	if (result != 0) {
+		printk(KERN_ERR "Cannot start iso receive.\n");
+		return -EINVAL;
+	}
+	return 0;
+}
+
+static void rawiso_activity_cb(struct hpsb_iso *iso)
+{
+	unsigned int num;
+	unsigned int i;
+	unsigned int packet;
+	unsigned long flags;
+	struct firesat *firesat = NULL;
+	struct firesat *firesat_iterator;
+
+	spin_lock_irqsave(&firesat_list_lock, flags);
+	list_for_each_entry(firesat_iterator, &firesat_list, list) {
+		if(firesat_iterator->iso_handle == iso) {
+			firesat = firesat_iterator;
+			break;
+		}
+	}
+	spin_unlock_irqrestore(&firesat_list_lock, flags);
+
+	if (firesat) {
+		packet = iso->first_packet;
+		num = hpsb_iso_n_ready(iso);
+		for (i = 0; i < num; i++,
+			     packet = (packet + 1) % iso->buf_packets) {
+			unsigned char *buf =
+				dma_region_i(&iso->data_buf, unsigned char,
+					     iso->infos[packet].offset +
+					     sizeof(struct CIPHeader));
+			int count = (iso->infos[packet].len -
+				     sizeof(struct CIPHeader)) /
+				(188 + sizeof(struct firewireheader));
+			if (iso->infos[packet].len <= sizeof(struct CIPHeader))
+				continue; // ignore empty packet
+
+			while (count --) {
+				if (buf[sizeof(struct firewireheader)] == 0x47)
+					dvb_dmx_swfilter_packets(&firesat->demux,
+								 &buf[sizeof(struct firewireheader)], 1);
+				else
+					printk("%s: invalid packet, skipping\n", __func__);
+				buf += 188 + sizeof(struct firewireheader);
+
+			}
+
+		}
+		hpsb_iso_recv_release_packets(iso, num);
+	}
+	else {
+		printk("%s: packets for unknown iso channel, skipping\n",
+		       __func__);
+		hpsb_iso_recv_release_packets(iso, hpsb_iso_n_ready(iso));
+	}
+}
+
diff --git a/drivers/media/video/Kconfig b/drivers/media/video/Kconfig
index 47102c2c8250..057fd7e160c4 100644
--- a/drivers/media/video/Kconfig
+++ b/drivers/media/video/Kconfig
@@ -759,7 +759,7 @@ config VIDEO_PXA27x
 
 config VIDEO_SH_MOBILE_CEU
 	tristate "SuperH Mobile CEU Interface driver"
-	depends on VIDEO_DEV && SOC_CAMERA && HAS_DMA
+	depends on VIDEO_DEV && SOC_CAMERA && HAS_DMA && HAVE_CLK
 	select VIDEOBUF_DMA_CONTIG
 	---help---
 	  This is a v4l2 driver for the SuperH Mobile CEU Interface
diff --git a/drivers/media/video/cafe_ccic.c b/drivers/media/video/cafe_ccic.c
index 1740b9ebdcef..87eef4be2070 100644
--- a/drivers/media/video/cafe_ccic.c
+++ b/drivers/media/video/cafe_ccic.c
@@ -569,7 +569,6 @@ static int cafe_smbus_setup(struct cafe_camera *cam)
 
 	cafe_smbus_enable_irq(cam);
 	adap->id = I2C_HW_SMBUS_CAFE;
-	adap->class = I2C_CLASS_CAM_DIGITAL;
 	adap->owner = THIS_MODULE;
 	adap->client_register = cafe_smbus_attach;
 	adap->client_unregister = cafe_smbus_detach;
diff --git a/drivers/media/video/ov7670.c b/drivers/media/video/ov7670.c
index ea032f5f2f41..39bfe5d097c9 100644
--- a/drivers/media/video/ov7670.c
+++ b/drivers/media/video/ov7670.c
@@ -1347,7 +1347,6 @@ static struct i2c_driver ov7670_driver = {
 		.name = "ov7670",
 	},
 	.id 		= I2C_DRIVERID_OV7670,
-	.class 		= I2C_CLASS_CAM_DIGITAL,
 	.attach_adapter = ov7670_attach,
 	.detach_client	= ov7670_detach,
 	.command	= ov7670_command,
diff --git a/drivers/media/video/ovcamchip/ovcamchip_core.c b/drivers/media/video/ovcamchip/ovcamchip_core.c
index 2c4acbf5a4fe..c841f4e4fbe4 100644
--- a/drivers/media/video/ovcamchip/ovcamchip_core.c
+++ b/drivers/media/video/ovcamchip/ovcamchip_core.c
@@ -405,7 +405,6 @@ static struct i2c_driver driver = {
 		.name =		"ovcamchip",
 	},
 	.id =			I2C_DRIVERID_OVCAMCHIP,
-	.class =		I2C_CLASS_CAM_DIGITAL,
 	.attach_adapter =	ovcamchip_attach,
 	.detach_client =	ovcamchip_detach,
 	.command =		ovcamchip_command,
diff --git a/drivers/media/video/pvrusb2/pvrusb2-hdw.c b/drivers/media/video/pvrusb2/pvrusb2-hdw.c
index 5b81ba469641..7b4bdadaa9cd 100644
--- a/drivers/media/video/pvrusb2/pvrusb2-hdw.c
+++ b/drivers/media/video/pvrusb2/pvrusb2-hdw.c
@@ -3655,7 +3655,7 @@ void pvr2_hdw_device_reset(struct pvr2_hdw *hdw)
 	int ret;
 	pvr2_trace(PVR2_TRACE_INIT,"Performing a device reset...");
 	ret = usb_lock_device_for_reset(hdw->usb_dev,NULL);
-	if (ret == 1) {
+	if (ret == 0) {
 		ret = usb_reset_device(hdw->usb_dev);
 		usb_unlock_device(hdw->usb_dev);
 	} else {
diff --git a/drivers/media/video/pxa_camera.c b/drivers/media/video/pxa_camera.c
index eb6be5802928..70a77625107d 100644
--- a/drivers/media/video/pxa_camera.c
+++ b/drivers/media/video/pxa_camera.c
@@ -39,6 +39,8 @@
 #include <mach/pxa-regs.h>
 #include <mach/camera.h>
 
+#include "pxa_camera.h"
+
 #define PXA_CAM_VERSION_CODE KERNEL_VERSION(0, 0, 5)
 #define PXA_CAM_DRV_NAME "pxa27x-camera"
 
@@ -1071,7 +1073,7 @@ static int pxa_camera_probe(struct platform_device *pdev)
 		goto exit;
 	}
 
-	pcdev->clk = clk_get(&pdev->dev, "CAMCLK");
+	pcdev->clk = clk_get(&pdev->dev, NULL);
 	if (IS_ERR(pcdev->clk)) {
 		err = PTR_ERR(pcdev->clk);
 		goto exit_kfree;
diff --git a/drivers/media/video/pxa_camera.h b/drivers/media/video/pxa_camera.h
new file mode 100644
index 000000000000..89cbfc9a35c5
--- /dev/null
+++ b/drivers/media/video/pxa_camera.h
@@ -0,0 +1,95 @@
+/* Camera Interface */
+#define CICR0		__REG(0x50000000)
+#define CICR1		__REG(0x50000004)
+#define CICR2		__REG(0x50000008)
+#define CICR3		__REG(0x5000000C)
+#define CICR4		__REG(0x50000010)
+#define CISR		__REG(0x50000014)
+#define CIFR		__REG(0x50000018)
+#define CITOR		__REG(0x5000001C)
+#define CIBR0		__REG(0x50000028)
+#define CIBR1		__REG(0x50000030)
+#define CIBR2		__REG(0x50000038)
+
+#define CICR0_DMAEN	(1 << 31)	/* DMA request enable */
+#define CICR0_PAR_EN	(1 << 30)	/* Parity enable */
+#define CICR0_SL_CAP_EN	(1 << 29)	/* Capture enable for slave mode */
+#define CICR0_ENB	(1 << 28)	/* Camera interface enable */
+#define CICR0_DIS	(1 << 27)	/* Camera interface disable */
+#define CICR0_SIM	(0x7 << 24)	/* Sensor interface mode mask */
+#define CICR0_TOM	(1 << 9)	/* Time-out mask */
+#define CICR0_RDAVM	(1 << 8)	/* Receive-data-available mask */
+#define CICR0_FEM	(1 << 7)	/* FIFO-empty mask */
+#define CICR0_EOLM	(1 << 6)	/* End-of-line mask */
+#define CICR0_PERRM	(1 << 5)	/* Parity-error mask */
+#define CICR0_QDM	(1 << 4)	/* Quick-disable mask */
+#define CICR0_CDM	(1 << 3)	/* Disable-done mask */
+#define CICR0_SOFM	(1 << 2)	/* Start-of-frame mask */
+#define CICR0_EOFM	(1 << 1)	/* End-of-frame mask */
+#define CICR0_FOM	(1 << 0)	/* FIFO-overrun mask */
+
+#define CICR1_TBIT	(1 << 31)	/* Transparency bit */
+#define CICR1_RGBT_CONV	(0x3 << 29)	/* RGBT conversion mask */
+#define CICR1_PPL	(0x7ff << 15)	/* Pixels per line mask */
+#define CICR1_RGB_CONV	(0x7 << 12)	/* RGB conversion mask */
+#define CICR1_RGB_F	(1 << 11)	/* RGB format */
+#define CICR1_YCBCR_F	(1 << 10)	/* YCbCr format */
+#define CICR1_RGB_BPP	(0x7 << 7)	/* RGB bis per pixel mask */
+#define CICR1_RAW_BPP	(0x3 << 5)	/* Raw bis per pixel mask */
+#define CICR1_COLOR_SP	(0x3 << 3)	/* Color space mask */
+#define CICR1_DW	(0x7 << 0)	/* Data width mask */
+
+#define CICR2_BLW	(0xff << 24)	/* Beginning-of-line pixel clock
+					   wait count mask */
+#define CICR2_ELW	(0xff << 16)	/* End-of-line pixel clock
+					   wait count mask */
+#define CICR2_HSW	(0x3f << 10)	/* Horizontal sync pulse width mask */
+#define CICR2_BFPW	(0x3f << 3)	/* Beginning-of-frame pixel clock
+					   wait count mask */
+#define CICR2_FSW	(0x7 << 0)	/* Frame stabilization
+					   wait count mask */
+
+#define CICR3_BFW	(0xff << 24)	/* Beginning-of-frame line clock
+					   wait count mask */
+#define CICR3_EFW	(0xff << 16)	/* End-of-frame line clock
+					   wait count mask */
+#define CICR3_VSW	(0x3f << 10)	/* Vertical sync pulse width mask */
+#define CICR3_BFPW	(0x3f << 3)	/* Beginning-of-frame pixel clock
+					   wait count mask */
+#define CICR3_LPF	(0x7ff << 0)	/* Lines per frame mask */
+
+#define CICR4_MCLK_DLY	(0x3 << 24)	/* MCLK Data Capture Delay mask */
+#define CICR4_PCLK_EN	(1 << 23)	/* Pixel clock enable */
+#define CICR4_PCP	(1 << 22)	/* Pixel clock polarity */
+#define CICR4_HSP	(1 << 21)	/* Horizontal sync polarity */
+#define CICR4_VSP	(1 << 20)	/* Vertical sync polarity */
+#define CICR4_MCLK_EN	(1 << 19)	/* MCLK enable */
+#define CICR4_FR_RATE	(0x7 << 8)	/* Frame rate mask */
+#define CICR4_DIV	(0xff << 0)	/* Clock divisor mask */
+
+#define CISR_FTO	(1 << 15)	/* FIFO time-out */
+#define CISR_RDAV_2	(1 << 14)	/* Channel 2 receive data available */
+#define CISR_RDAV_1	(1 << 13)	/* Channel 1 receive data available */
+#define CISR_RDAV_0	(1 << 12)	/* Channel 0 receive data available */
+#define CISR_FEMPTY_2	(1 << 11)	/* Channel 2 FIFO empty */
+#define CISR_FEMPTY_1	(1 << 10)	/* Channel 1 FIFO empty */
+#define CISR_FEMPTY_0	(1 << 9)	/* Channel 0 FIFO empty */
+#define CISR_EOL	(1 << 8)	/* End of line */
+#define CISR_PAR_ERR	(1 << 7)	/* Parity error */
+#define CISR_CQD	(1 << 6)	/* Camera interface quick disable */
+#define CISR_CDD	(1 << 5)	/* Camera interface disable done */
+#define CISR_SOF	(1 << 4)	/* Start of frame */
+#define CISR_EOF	(1 << 3)	/* End of frame */
+#define CISR_IFO_2	(1 << 2)	/* FIFO overrun for Channel 2 */
+#define CISR_IFO_1	(1 << 1)	/* FIFO overrun for Channel 1 */
+#define CISR_IFO_0	(1 << 0)	/* FIFO overrun for Channel 0 */
+
+#define CIFR_FLVL2	(0x7f << 23)	/* FIFO 2 level mask */
+#define CIFR_FLVL1	(0x7f << 16)	/* FIFO 1 level mask */
+#define CIFR_FLVL0	(0xff << 8)	/* FIFO 0 level mask */
+#define CIFR_THL_0	(0x3 << 4)	/* Threshold Level for Channel 0 FIFO */
+#define CIFR_RESET_F	(1 << 3)	/* Reset input FIFOs */
+#define CIFR_FEN2	(1 << 2)	/* FIFO enable for channel 2 */
+#define CIFR_FEN1	(1 << 1)	/* FIFO enable for channel 1 */
+#define CIFR_FEN0	(1 << 0)	/* FIFO enable for channel 0 */
+
diff --git a/drivers/media/video/sh_mobile_ceu_camera.c b/drivers/media/video/sh_mobile_ceu_camera.c
index 2407607f2eff..536b1a9b310c 100644
--- a/drivers/media/video/sh_mobile_ceu_camera.c
+++ b/drivers/media/video/sh_mobile_ceu_camera.c
@@ -31,6 +31,7 @@
 #include <linux/platform_device.h>
 #include <linux/mutex.h>
 #include <linux/videodev2.h>
+#include <linux/clk.h>
 
 #include <media/v4l2-common.h>
 #include <media/v4l2-dev.h>
@@ -89,6 +90,7 @@ struct sh_mobile_ceu_dev {
 
 	unsigned int irq;
 	void __iomem *base;
+	struct clk *clk;
 	unsigned long video_limit;
 
 	/* lock used to protect videobuf */
@@ -309,6 +311,8 @@ static int sh_mobile_ceu_add_device(struct soc_camera_device *icd)
 	if (ret)
 		goto err;
 
+	clk_enable(pcdev->clk);
+
 	ceu_write(pcdev, CAPSR, 1 << 16); /* reset */
 	while (ceu_read(pcdev, CSTSR) & 1)
 		msleep(1);
@@ -342,6 +346,8 @@ static void sh_mobile_ceu_remove_device(struct soc_camera_device *icd)
 	}
 	spin_unlock_irqrestore(&pcdev->lock, flags);
 
+	clk_disable(pcdev->clk);
+
 	icd->ops->release(icd);
 
 	dev_info(&icd->dev,
@@ -550,6 +556,7 @@ static int sh_mobile_ceu_probe(struct platform_device *pdev)
 	struct sh_mobile_ceu_dev *pcdev;
 	struct resource *res;
 	void __iomem *base;
+	char clk_name[8];
 	unsigned int irq;
 	int err = 0;
 
@@ -615,6 +622,14 @@ static int sh_mobile_ceu_probe(struct platform_device *pdev)
 		goto exit_release_mem;
 	}
 
+	snprintf(clk_name, sizeof(clk_name), "ceu%d", pdev->id);
+	pcdev->clk = clk_get(&pdev->dev, clk_name);
+	if (IS_ERR(pcdev->clk)) {
+		dev_err(&pdev->dev, "cannot get clock \"%s\"\n", clk_name);
+		err = PTR_ERR(pcdev->clk);
+		goto exit_free_irq;
+	}
+
 	pcdev->ici.priv = pcdev;
 	pcdev->ici.dev.parent = &pdev->dev;
 	pcdev->ici.nr = pdev->id;
@@ -623,10 +638,12 @@ static int sh_mobile_ceu_probe(struct platform_device *pdev)
 
 	err = soc_camera_host_register(&pcdev->ici);
 	if (err)
-		goto exit_free_irq;
+		goto exit_free_clk;
 
 	return 0;
 
+exit_free_clk:
+	clk_put(pcdev->clk);
 exit_free_irq:
 	free_irq(pcdev->irq, pcdev);
 exit_release_mem:
@@ -645,6 +662,7 @@ static int sh_mobile_ceu_remove(struct platform_device *pdev)
 	struct sh_mobile_ceu_dev *pcdev = platform_get_drvdata(pdev);
 
 	soc_camera_host_unregister(&pcdev->ici);
+	clk_put(pcdev->clk);
 	free_irq(pcdev->irq, pcdev);
 	if (platform_get_resource(pdev, IORESOURCE_MEM, 1))
 		dma_release_declared_memory(&pdev->dev);
diff --git a/drivers/media/video/w9968cf.c b/drivers/media/video/w9968cf.c
index 4dfb43bd1846..e4a6272bdbd5 100644
--- a/drivers/media/video/w9968cf.c
+++ b/drivers/media/video/w9968cf.c
@@ -1553,7 +1553,6 @@ static int w9968cf_i2c_init(struct w9968cf_device* cam)
 
 	static struct i2c_adapter adap = {
 		.id =                I2C_HW_SMBUS_W9968CF,
-		.class =             I2C_CLASS_CAM_DIGITAL,
 		.owner =             THIS_MODULE,
 		.client_register =   w9968cf_i2c_attach_inform,
 		.client_unregister = w9968cf_i2c_detach_inform,
diff --git a/drivers/memstick/core/memstick.c b/drivers/memstick/core/memstick.c
index cea46906408e..a5b448ea4eab 100644
--- a/drivers/memstick/core/memstick.c
+++ b/drivers/memstick/core/memstick.c
@@ -385,8 +385,7 @@ static struct memstick_dev *memstick_alloc_card(struct memstick_host *host)
 
 	if (card) {
 		card->host = host;
-		snprintf(card->dev.bus_id, sizeof(card->dev.bus_id),
-			 "%s", host->dev.bus_id);
+		dev_set_name(&card->dev, "%s", dev_name(&host->dev));
 		card->dev.parent = &host->dev;
 		card->dev.bus = &memstick_bus_type;
 		card->dev.release = memstick_free_card;
@@ -519,7 +518,7 @@ int memstick_add_host(struct memstick_host *host)
 	if (rc)
 		return rc;
 
-	snprintf(host->dev.bus_id, BUS_ID_SIZE, "memstick%u", host->id);
+	dev_set_name(&host->dev, "memstick%u", host->id);
 
 	rc = device_add(&host->dev);
 	if (rc) {
diff --git a/drivers/memstick/core/mspro_block.c b/drivers/memstick/core/mspro_block.c
index 7911151e56a3..1f1e3982b1aa 100644
--- a/drivers/memstick/core/mspro_block.c
+++ b/drivers/memstick/core/mspro_block.c
@@ -887,14 +887,14 @@ try_again:
 	if (rc) {
 		printk(KERN_WARNING
 		       "%s: could not switch to 4-bit mode, error %d\n",
-		       card->dev.bus_id, rc);
+		       dev_name(&card->dev), rc);
 		return 0;
 	}
 
 	msb->system = MEMSTICK_SYS_PAR4;
 	host->set_param(host, MEMSTICK_INTERFACE, MEMSTICK_PAR4);
 	printk(KERN_INFO "%s: switching to 4-bit parallel mode\n",
-	       card->dev.bus_id);
+	       dev_name(&card->dev));
 
 	if (msb->caps & MEMSTICK_CAP_PAR8) {
 		rc = mspro_block_set_interface(card, MEMSTICK_SYS_PAR8);
@@ -905,11 +905,11 @@ try_again:
 					MEMSTICK_PAR8);
 			printk(KERN_INFO
 			       "%s: switching to 8-bit parallel mode\n",
-			       card->dev.bus_id);
+			       dev_name(&card->dev));
 		} else
 			printk(KERN_WARNING
 			       "%s: could not switch to 8-bit mode, error %d\n",
-			       card->dev.bus_id, rc);
+			       dev_name(&card->dev), rc);
 	}
 
 	card->next_request = h_mspro_block_req_init;
@@ -922,7 +922,7 @@ try_again:
 	if (rc) {
 		printk(KERN_WARNING
 		       "%s: interface error, trying to fall back to serial\n",
-		       card->dev.bus_id);
+		       dev_name(&card->dev));
 		msb->system = MEMSTICK_SYS_SERIAL;
 		host->set_param(host, MEMSTICK_POWER, MEMSTICK_POWER_OFF);
 		msleep(10);
@@ -992,14 +992,14 @@ static int mspro_block_read_attributes(struct memstick_dev *card)
 
 	if (be16_to_cpu(attr->signature) != MSPRO_BLOCK_SIGNATURE) {
 		printk(KERN_ERR "%s: unrecognized device signature %x\n",
-		       card->dev.bus_id, be16_to_cpu(attr->signature));
+		       dev_name(&card->dev), be16_to_cpu(attr->signature));
 		rc = -ENODEV;
 		goto out_free_attr;
 	}
 
 	if (attr->count > MSPRO_BLOCK_MAX_ATTRIBUTES) {
 		printk(KERN_WARNING "%s: way too many attribute entries\n",
-		       card->dev.bus_id);
+		       dev_name(&card->dev));
 		attr_count = MSPRO_BLOCK_MAX_ATTRIBUTES;
 	} else
 		attr_count = attr->count;
diff --git a/drivers/memstick/host/tifm_ms.c b/drivers/memstick/host/tifm_ms.c
index d32d6ad8f3fc..03f71a431c82 100644
--- a/drivers/memstick/host/tifm_ms.c
+++ b/drivers/memstick/host/tifm_ms.c
@@ -546,7 +546,7 @@ static void tifm_ms_abort(unsigned long data)
 	printk(KERN_ERR
 	       "%s : card failed to respond for a long period of time "
 	       "(%x, %x)\n",
-	       host->dev->dev.bus_id, host->req ? host->req->tpc : 0,
+	       dev_name(&host->dev->dev), host->req ? host->req->tpc : 0,
 	       host->cmd_flags);
 
 	tifm_eject(host->dev);
@@ -561,7 +561,7 @@ static int tifm_ms_probe(struct tifm_dev *sock)
 	if (!(TIFM_SOCK_STATE_OCCUPIED
 	      & readl(sock->addr + SOCK_PRESENT_STATE))) {
 		printk(KERN_WARNING "%s : card gone, unexpectedly\n",
-		       sock->dev.bus_id);
+		       dev_name(&sock->dev));
 		return rc;
 	}
 
diff --git a/drivers/message/i2o/device.c b/drivers/message/i2o/device.c
index 54c2e9ae23e5..a7dd03e8d332 100644
--- a/drivers/message/i2o/device.c
+++ b/drivers/message/i2o/device.c
@@ -134,7 +134,7 @@ static void i2o_device_release(struct device *dev)
 {
 	struct i2o_device *i2o_dev = to_i2o_device(dev);
 
-	pr_debug("i2o: device %s released\n", dev->bus_id);
+	pr_debug("i2o: device %s released\n", dev_name(dev));
 
 	kfree(i2o_dev);
 }
@@ -229,8 +229,8 @@ static int i2o_device_add(struct i2o_controller *c, i2o_lct_entry *entry)
 
 	i2o_dev->lct_data = *entry;
 
-	snprintf(i2o_dev->device.bus_id, BUS_ID_SIZE, "%d:%03x", c->unit,
-		 i2o_dev->lct_data.tid);
+	dev_set_name(&i2o_dev->device, "%d:%03x", c->unit,
+		     i2o_dev->lct_data.tid);
 
 	i2o_dev->iop = c;
 	i2o_dev->device.parent = &c->device;
@@ -281,7 +281,7 @@ static int i2o_device_add(struct i2o_controller *c, i2o_lct_entry *entry)
 
 	i2o_driver_notify_device_add_all(i2o_dev);
 
-	pr_debug("i2o: device %s added\n", i2o_dev->device.bus_id);
+	pr_debug("i2o: device %s added\n", dev_name(&i2o_dev->device));
 
 	return 0;
 
diff --git a/drivers/message/i2o/i2o_block.c b/drivers/message/i2o/i2o_block.c
index 84bdc2ee69e6..a443e136dc41 100644
--- a/drivers/message/i2o/i2o_block.c
+++ b/drivers/message/i2o/i2o_block.c
@@ -354,7 +354,7 @@ static inline void i2o_block_sglist_free(struct i2o_block_request *ireq)
  *	@req: the request to prepare
  *
  *	Allocate the necessary i2o_block_request struct and connect it to
- *	the request. This is needed that we not loose the SG list later on.
+ *	the request. This is needed that we not lose the SG list later on.
  *
  *	Returns BLKPREP_OK on success or BLKPREP_DEFER on failure.
  */
diff --git a/drivers/message/i2o/i2o_proc.c b/drivers/message/i2o/i2o_proc.c
index 54a3016ff45d..9a36b5a7de57 100644
--- a/drivers/message/i2o/i2o_proc.c
+++ b/drivers/message/i2o/i2o_proc.c
@@ -1300,7 +1300,7 @@ static int i2o_seq_show_dev_name(struct seq_file *seq, void *v)
 {
 	struct i2o_device *d = (struct i2o_device *)seq->private;
 
-	seq_printf(seq, "%s\n", d->device.bus_id);
+	seq_printf(seq, "%s\n", dev_name(&d->device));
 
 	return 0;
 }
diff --git a/drivers/message/i2o/iop.c b/drivers/message/i2o/iop.c
index be2b5926d26c..a94ab60fe5fb 100644
--- a/drivers/message/i2o/iop.c
+++ b/drivers/message/i2o/iop.c
@@ -49,7 +49,6 @@ static int i2o_hrt_get(struct i2o_controller *c);
 /**
  *	i2o_msg_get_wait - obtain an I2O message from the IOP
  *	@c: I2O controller
- *	@msg: pointer to a I2O message pointer
  *	@wait: how long to wait until timeout
  *
  *	This function waits up to wait seconds for a message slot to be
@@ -1073,7 +1072,7 @@ struct i2o_controller *i2o_iop_alloc(void)
 
 	c->device.release = &i2o_iop_release;
 
-	snprintf(c->device.bus_id, BUS_ID_SIZE, "iop%d", c->unit);
+	dev_set_name(&c->device, "iop%d", c->unit);
 
 #if BITS_PER_LONG == 64
 	spin_lock_init(&c->context_list_lock);
diff --git a/drivers/mfd/asic3.c b/drivers/mfd/asic3.c
index e4c0db4dc7b1..9e485459f63b 100644
--- a/drivers/mfd/asic3.c
+++ b/drivers/mfd/asic3.c
@@ -474,9 +474,9 @@ static __init int asic3_gpio_probe(struct platform_device *pdev,
 	u16 dir_reg[ASIC3_NUM_GPIO_BANKS];
 	int i;
 
-	memzero(alt_reg, ASIC3_NUM_GPIO_BANKS * sizeof(u16));
-	memzero(out_reg, ASIC3_NUM_GPIO_BANKS * sizeof(u16));
-	memzero(dir_reg, ASIC3_NUM_GPIO_BANKS * sizeof(u16));
+	memset(alt_reg, 0, ASIC3_NUM_GPIO_BANKS * sizeof(u16));
+	memset(out_reg, 0, ASIC3_NUM_GPIO_BANKS * sizeof(u16));
+	memset(dir_reg, 0, ASIC3_NUM_GPIO_BANKS * sizeof(u16));
 
 	/* Enable all GPIOs */
 	asic3_write_register(asic, ASIC3_GPIO_OFFSET(A, MASK), 0xffff);
diff --git a/drivers/mfd/mcp-core.c b/drivers/mfd/mcp-core.c
index b4ed57e02729..6063dc2b52e8 100644
--- a/drivers/mfd/mcp-core.c
+++ b/drivers/mfd/mcp-core.c
@@ -18,7 +18,7 @@
 #include <linux/slab.h>
 #include <linux/string.h>
 
-#include <asm/dma.h>
+#include <mach/dma.h>
 #include <asm/system.h>
 
 #include "mcp.h"
diff --git a/drivers/mfd/mcp-sa11x0.c b/drivers/mfd/mcp-sa11x0.c
index 28380b20bc70..62b32dabf629 100644
--- a/drivers/mfd/mcp-sa11x0.c
+++ b/drivers/mfd/mcp-sa11x0.c
@@ -20,7 +20,7 @@
 #include <linux/slab.h>
 #include <linux/platform_device.h>
 
-#include <asm/dma.h>
+#include <mach/dma.h>
 #include <mach/hardware.h>
 #include <asm/mach-types.h>
 #include <asm/system.h>
diff --git a/drivers/mfd/ucb1x00-assabet.c b/drivers/mfd/ucb1x00-assabet.c
index 61aeaf79640d..86fed4870f93 100644
--- a/drivers/mfd/ucb1x00-assabet.c
+++ b/drivers/mfd/ucb1x00-assabet.c
@@ -15,7 +15,7 @@
 #include <linux/proc_fs.h>
 #include <linux/device.h>
 
-#include <asm/dma.h>
+#include <mach/dma.h>
 
 #include "ucb1x00.h"
 
diff --git a/drivers/mfd/ucb1x00-core.c b/drivers/mfd/ucb1x00-core.c
index a316f1b75933..6860c924f364 100644
--- a/drivers/mfd/ucb1x00-core.c
+++ b/drivers/mfd/ucb1x00-core.c
@@ -25,7 +25,7 @@
 #include <linux/device.h>
 #include <linux/mutex.h>
 
-#include <asm/dma.h>
+#include <mach/dma.h>
 #include <mach/hardware.h>
 
 #include "ucb1x00.h"
diff --git a/drivers/mfd/ucb1x00-ts.c b/drivers/mfd/ucb1x00-ts.c
index 44762ca86a8d..61b7d3eb9a2f 100644
--- a/drivers/mfd/ucb1x00-ts.c
+++ b/drivers/mfd/ucb1x00-ts.c
@@ -31,7 +31,7 @@
 #include <linux/slab.h>
 #include <linux/kthread.h>
 
-#include <asm/dma.h>
+#include <mach/dma.h>
 #include <mach/collie.h>
 #include <asm/mach-types.h>
 
diff --git a/drivers/misc/Kconfig b/drivers/misc/Kconfig
index fee7304102af..8574879fa63b 100644
--- a/drivers/misc/Kconfig
+++ b/drivers/misc/Kconfig
@@ -120,7 +120,7 @@ config TIFM_CORE
 	  cards are supported via 'MMC/SD Card support: TI Flash Media MMC/SD
 	  Interface support (MMC_TIFM_SD)'.
 
-          To compile this driver as a module, choose M here: the module will
+	  To compile this driver as a module, choose M here: the module will
 	  be called tifm_core.
 
 config TIFM_7XX1
@@ -133,100 +133,9 @@ config TIFM_7XX1
 	  To make actual use of the device, you will have to select some
 	  flash card format drivers, as outlined in the TIFM_CORE Help.
 
-          To compile this driver as a module, choose M here: the module will
+	  To compile this driver as a module, choose M here: the module will
 	  be called tifm_7xx1.
 
-config ACER_WMI
-        tristate "Acer WMI Laptop Extras (EXPERIMENTAL)"
-	depends on X86
-	depends on EXPERIMENTAL
-	depends on ACPI
-	depends on LEDS_CLASS
-	depends on NEW_LEDS
-	depends on BACKLIGHT_CLASS_DEVICE
-	depends on SERIO_I8042
-	depends on RFKILL
-	select ACPI_WMI
-	---help---
-	  This is a driver for newer Acer (and Wistron) laptops. It adds
-	  wireless radio and bluetooth control, and on some laptops,
-	  exposes the mail LED and LCD backlight.
-
-	  For more information about this driver see
-	  <file:Documentation/laptops/acer-wmi.txt>
-
-	  If you have an ACPI-WMI compatible Acer/ Wistron laptop, say Y or M
-	  here.
-
-config ASUS_LAPTOP
-        tristate "Asus Laptop Extras (EXPERIMENTAL)"
-        depends on X86
-        depends on ACPI
-	depends on EXPERIMENTAL && !ACPI_ASUS
-	depends on LEDS_CLASS
-	depends on NEW_LEDS
-	depends on BACKLIGHT_CLASS_DEVICE
-        ---help---
-	  This is the new Linux driver for Asus laptops. It may also support some
-	  MEDION, JVC or VICTOR laptops. It makes all the extra buttons generate
-	  standard ACPI events that go through /proc/acpi/events. It also adds
-	  support for video output switching, LCD backlight control, Bluetooth and
-	  Wlan control, and most importantly, allows you to blink those fancy LEDs.
-
-	  For more information and a userspace daemon for handling the extra
-	  buttons see <http://acpi4asus.sf.net/>.
-
-	  If you have an ACPI-compatible ASUS laptop, say Y or M here.
-
-config FUJITSU_LAPTOP
-        tristate "Fujitsu Laptop Extras"
-        depends on X86
-        depends on ACPI
-	depends on INPUT
-        depends on BACKLIGHT_CLASS_DEVICE
-        ---help---
-	  This is a driver for laptops built by Fujitsu:
-
-	    * P2xxx/P5xxx/S6xxx/S7xxx series Lifebooks
-	    * Possibly other Fujitsu laptop models
-	    * Tested with S6410 and S7020
-
-	  It adds support for LCD brightness control and some hotkeys.
-
-	  If you have a Fujitsu laptop, say Y or M here.
-
-config FUJITSU_LAPTOP_DEBUG
-	bool "Verbose debug mode for Fujitsu Laptop Extras"
-	depends on FUJITSU_LAPTOP
-	default n
-	---help---
-	  Enables extra debug output from the fujitsu extras driver, at the
-	  expense of a slight increase in driver size.
-
-	  If you are not sure, say N here.
-
-config TC1100_WMI
-	tristate "HP Compaq TC1100 Tablet WMI Extras (EXPERIMENTAL)"
-	depends on X86 && !X86_64
-	depends on EXPERIMENTAL
-	depends on ACPI
-	select ACPI_WMI
-	---help---
-	  This is a driver for the WMI extensions (wireless and bluetooth power
-	  control) of the HP Compaq TC1100 tablet.
-
-config HP_WMI
-       tristate "HP WMI extras"
-       depends on ACPI_WMI
-       depends on INPUT
-       depends on RFKILL
-       help
-         Say Y here if you want to support WMI-based hotkeys on HP laptops and
-	 to read data from WMI such as docking or ambient light sensor state.
-
-         To compile this driver as a module, choose M here: the module will
-         be called hp-wmi.
-
 config ICS932S401
 	tristate "Integrated Circuits ICS932S401"
 	depends on I2C && EXPERIMENTAL
@@ -237,170 +146,6 @@ config ICS932S401
 	  This driver can also be built as a module. If so, the module
 	  will be called ics932s401.
 
-config MSI_LAPTOP
-        tristate "MSI Laptop Extras"
-        depends on X86
-        depends on ACPI
-        depends on BACKLIGHT_CLASS_DEVICE
-        ---help---
-	  This is a driver for laptops built by MSI (MICRO-STAR
-	  INTERNATIONAL):
-
-	  MSI MegaBook S270 (MS-1013)
-	  Cytron/TCM/Medion/Tchibo MD96100/SAM2000
-
-	  It adds support for Bluetooth, WLAN and LCD brightness control.
-
-	  More information about this driver is available at
-	  <http://0pointer.de/lennart/tchibo.html>.
-
-	  If you have an MSI S270 laptop, say Y or M here.
-
-config PANASONIC_LAPTOP
-	tristate "Panasonic Laptop Extras"
-	depends on X86 && INPUT && ACPI
-        depends on BACKLIGHT_CLASS_DEVICE
-	---help---
-	  This driver adds support for access to backlight control and hotkeys
-	  on Panasonic Let's Note laptops.
-
-	  If you have a Panasonic Let's note laptop (such as the R1(N variant),
-	  R2, R3, R5, T2, W2 and Y2 series), say Y.
-
-config COMPAL_LAPTOP
-	tristate "Compal Laptop Extras"
-	depends on X86
-	depends on ACPI
-	depends on BACKLIGHT_CLASS_DEVICE
-	---help---
-	  This is a driver for laptops built by Compal:
-
-	  Compal FL90/IFL90
-	  Compal FL91/IFL91
-	  Compal FL92/JFL92
-	  Compal FT00/IFT00
-
-	  It adds support for Bluetooth, WLAN and LCD brightness control.
-
-	  If you have an Compal FL9x/IFL9x/FT00 laptop, say Y or M here.
-
-config SONY_LAPTOP
-	tristate "Sony Laptop Extras"
-	depends on X86 && ACPI
-	select BACKLIGHT_CLASS_DEVICE
-	depends on INPUT
-	  ---help---
-	  This mini-driver drives the SNC and SPIC devices present in the ACPI
-	  BIOS of the Sony Vaio laptops.
-
-	  It gives access to some extra laptop functionalities like Bluetooth,
-	  screen brightness control, Fn keys and allows powering on/off some
-	  devices.
-
-	  Read <file:Documentation/laptops/sony-laptop.txt> for more information.
-
-config SONYPI_COMPAT
-	bool "Sonypi compatibility"
-	depends on SONY_LAPTOP
-	  ---help---
-	  Build the sonypi driver compatibility code into the sony-laptop driver.
-
-config THINKPAD_ACPI
-	tristate "ThinkPad ACPI Laptop Extras"
-	depends on X86 && ACPI
-	select BACKLIGHT_LCD_SUPPORT
-	select BACKLIGHT_CLASS_DEVICE
-	select HWMON
-	select NVRAM
-	select INPUT
-	select NEW_LEDS
-	select LEDS_CLASS
-	select NET
-	select RFKILL
-	---help---
-	  This is a driver for the IBM and Lenovo ThinkPad laptops. It adds
-	  support for Fn-Fx key combinations, Bluetooth control, video
-	  output switching, ThinkLight control, UltraBay eject and more.
-	  For more information about this driver see
-	  <file:Documentation/laptops/thinkpad-acpi.txt> and
-	  <http://ibm-acpi.sf.net/> .
-
-	  This driver was formerly known as ibm-acpi.
-
-	  If you have an IBM or Lenovo ThinkPad laptop, say Y or M here.
-
-config THINKPAD_ACPI_DEBUG
-	bool "Verbose debug mode"
-	depends on THINKPAD_ACPI
-	default n
-	---help---
-	  Enables extra debugging information, at the expense of a slightly
-	  increase in driver size.
-
-	  If you are not sure, say N here.
-
-config THINKPAD_ACPI_DOCK
-	bool "Legacy Docking Station Support"
-	depends on THINKPAD_ACPI
-	depends on ACPI_DOCK=n
-	default n
-	---help---
-	  Allows the thinkpad_acpi driver to handle docking station events.
-	  This support was made obsolete by the generic ACPI docking station
-	  support (CONFIG_ACPI_DOCK).  It will allow locking and removing the
-	  laptop from the docking station, but will not properly connect PCI
-	  devices.
-
-	  If you are not sure, say N here.
-
-config THINKPAD_ACPI_BAY
-	bool "Legacy Removable Bay Support"
-	depends on THINKPAD_ACPI
-	default y
-	---help---
-	  Allows the thinkpad_acpi driver to handle removable bays.  It will
-	  electrically disable the device in the bay, and also generate
-	  notifications when the bay lever is ejected or inserted.
-
-	  If you are not sure, say Y here.
-
-config THINKPAD_ACPI_VIDEO
-	bool "Video output control support"
-	depends on THINKPAD_ACPI
-	default y
-	---help---
-	  Allows the thinkpad_acpi driver to provide an interface to control
-	  the various video output ports.
-
-	  This feature often won't work well, depending on ThinkPad model,
-	  display state, video output devices in use, whether there is a X
-	  server running, phase of the moon, and the current mood of
-	  Schroedinger's cat.  If you can use X.org's RandR to control
-	  your ThinkPad's video output ports instead of this feature,
-	  don't think twice: do it and say N here to save some memory.
-
-	  If you are not sure, say Y here.
-
-config THINKPAD_ACPI_HOTKEY_POLL
-	bool "Support NVRAM polling for hot keys"
-	depends on THINKPAD_ACPI
-	default y
-	---help---
-	  Some thinkpad models benefit from NVRAM polling to detect a few of
-	  the hot key press events.  If you know your ThinkPad model does not
-	  need to do NVRAM polling to support any of the hot keys you use,
-	  unselecting this option will save about 1kB of memory.
-
-	  ThinkPads T40 and newer, R52 and newer, and X31 and newer are
-	  unlikely to need NVRAM polling in their latest BIOS versions.
-
-	  NVRAM polling can detect at most the following keys: ThinkPad/Access
-	  IBM, Zoom, Switch Display (fn+F7), ThinkLight, Volume up/down/mute,
-	  Brightness up/down, Display Expand (fn+F8), Hibernate (fn+F12).
-
-	  If you are not sure, say Y here.  The driver enables polling only if
-	  it is strictly necessary to do so.
-
 config ATMEL_SSC
 	tristate "Device driver for Atmel SSC peripheral"
 	depends on AVR32 || ARCH_AT91
@@ -413,31 +158,6 @@ config ATMEL_SSC
 
 	  If unsure, say N.
 
-config INTEL_MENLOW
-	tristate "Thermal Management driver for Intel menlow platform"
-	depends on ACPI_THERMAL
-	select THERMAL
-	depends on X86
-	---help---
-	  ACPI thermal management enhancement driver on
-	  Intel Menlow platform.
-
-	  If unsure, say N.
-
-config EEEPC_LAPTOP
-	tristate "Eee PC Hotkey Driver (EXPERIMENTAL)"
-	depends on X86
-	depends on ACPI
-	depends on BACKLIGHT_CLASS_DEVICE
-	depends on HWMON
-	depends on EXPERIMENTAL
-	depends on RFKILL
-	---help---
-	  This driver supports the Fn-Fx keys on Eee PC laptops.
-	  It also adds the ability to switch camera/wlan on/off.
-
-	  If you have an Eee PC laptop, say Y or M here.
-
 config ENCLOSURE_SERVICES
 	tristate "Enclosure Services"
 	default n
diff --git a/drivers/misc/Makefile b/drivers/misc/Makefile
index 817f7f5ab3bd..5af17943b552 100644
--- a/drivers/misc/Makefile
+++ b/drivers/misc/Makefile
@@ -1,32 +1,17 @@
 #
 # Makefile for misc devices that really don't fit anywhere else.
 #
-obj- := misc.o	# Dummy rule to force built-in.o to be made
-
-obj-$(CONFIG_IBM_ASM)		+= ibmasm/
 obj-$(CONFIG_HDPU_FEATURES)	+= hdpuftrs/
-obj-$(CONFIG_ASUS_LAPTOP)	+= asus-laptop.o
-obj-$(CONFIG_EEEPC_LAPTOP)	+= eeepc-laptop.o
-obj-$(CONFIG_MSI_LAPTOP)	+= msi-laptop.o
-obj-$(CONFIG_COMPAL_LAPTOP)	+= compal-laptop.o
-obj-$(CONFIG_ACER_WMI)		+= acer-wmi.o
 obj-$(CONFIG_ATMEL_PWM)		+= atmel_pwm.o
 obj-$(CONFIG_ATMEL_SSC)		+= atmel-ssc.o
 obj-$(CONFIG_ATMEL_TCLIB)	+= atmel_tclib.o
-obj-$(CONFIG_HP_WMI)		+= hp-wmi.o
 obj-$(CONFIG_ICS932S401)	+= ics932s401.o
-obj-$(CONFIG_TC1100_WMI)	+= tc1100-wmi.o
 obj-$(CONFIG_LKDTM)		+= lkdtm.o
 obj-$(CONFIG_TIFM_CORE)       	+= tifm_core.o
 obj-$(CONFIG_TIFM_7XX1)       	+= tifm_7xx1.o
 obj-$(CONFIG_PHANTOM)		+= phantom.o
 obj-$(CONFIG_SGI_IOC4)		+= ioc4.o
-obj-$(CONFIG_SONY_LAPTOP)	+= sony-laptop.o
-obj-$(CONFIG_THINKPAD_ACPI)	+= thinkpad_acpi.o
-obj-$(CONFIG_FUJITSU_LAPTOP)	+= fujitsu-laptop.o
-obj-$(CONFIG_PANASONIC_LAPTOP)	+= panasonic-laptop.o
 obj-$(CONFIG_EEPROM_93CX6)	+= eeprom_93cx6.o
-obj-$(CONFIG_INTEL_MENLOW)	+= intel_menlow.o
 obj-$(CONFIG_ENCLOSURE_SERVICES) += enclosure.o
 obj-$(CONFIG_KGDB_TESTS)	+= kgdbts.o
 obj-$(CONFIG_SGI_XP)		+= sgi-xp/
diff --git a/drivers/misc/enclosure.c b/drivers/misc/enclosure.c
index 0736cff9d97a..3cf61ece71d7 100644
--- a/drivers/misc/enclosure.c
+++ b/drivers/misc/enclosure.c
@@ -119,7 +119,7 @@ enclosure_register(struct device *dev, const char *name, int components,
 	edev->edev.class = &enclosure_class;
 	edev->edev.parent = get_device(dev);
 	edev->cb = cb;
-	snprintf(edev->edev.bus_id, BUS_ID_SIZE, "%s", name);
+	dev_set_name(&edev->edev, name);
 	err = device_register(&edev->edev);
 	if (err)
 		goto err;
@@ -170,7 +170,7 @@ EXPORT_SYMBOL_GPL(enclosure_unregister);
 static void enclosure_link_name(struct enclosure_component *cdev, char *name)
 {
 	strcpy(name, "enclosure_device:");
-	strcat(name, cdev->cdev.bus_id);
+	strcat(name, dev_name(&cdev->cdev));
 }
 
 static void enclosure_remove_links(struct enclosure_component *cdev)
@@ -256,9 +256,9 @@ enclosure_component_register(struct enclosure_device *edev,
 	cdev = &ecomp->cdev;
 	cdev->parent = get_device(&edev->edev);
 	if (name)
-		snprintf(cdev->bus_id, BUS_ID_SIZE, "%s", name);
+		dev_set_name(cdev, name);
 	else
-		snprintf(cdev->bus_id, BUS_ID_SIZE, "%u", number);
+		dev_set_name(cdev, "%u", number);
 
 	cdev->release = enclosure_component_release;
 	cdev->groups = enclosure_groups;
diff --git a/drivers/misc/sgi-gru/grumain.c b/drivers/misc/sgi-gru/grumain.c
index e11e1ac50900..3d2fc216bae5 100644
--- a/drivers/misc/sgi-gru/grumain.c
+++ b/drivers/misc/sgi-gru/grumain.c
@@ -29,7 +29,7 @@ static struct device_driver gru_driver = {
 };
 
 static struct device gru_device = {
-	.bus_id = {0},
+	.init_name = "",
 	.driver = &gru_driver,
 };
 
diff --git a/drivers/misc/sgi-gru/gruprocfs.c b/drivers/misc/sgi-gru/gruprocfs.c
index 533923f83f1a..73b0ca061bb5 100644
--- a/drivers/misc/sgi-gru/gruprocfs.c
+++ b/drivers/misc/sgi-gru/gruprocfs.c
@@ -317,7 +317,6 @@ int gru_proc_init(void)
 {
 	struct proc_entry *p;
 
-	proc_mkdir("sgi_uv", NULL);
 	proc_gru = proc_mkdir("sgi_uv/gru", NULL);
 
 	for (p = proc_files; p->name; p++)
diff --git a/drivers/misc/sgi-xp/xp.h b/drivers/misc/sgi-xp/xp.h
index ed1722e50049..7b4cbd5e03e9 100644
--- a/drivers/misc/sgi-xp/xp.h
+++ b/drivers/misc/sgi-xp/xp.h
@@ -194,9 +194,10 @@ enum xp_retval {
 	xpGruSendMqError,	/* 59: gru send message queue related error */
 
 	xpBadChannelNumber,	/* 60: invalid channel number */
-	xpBadMsgType,		/* 60: invalid message type */
+	xpBadMsgType,		/* 61: invalid message type */
+	xpBiosError,		/* 62: BIOS error */
 
-	xpUnknownReason		/* 61: unknown reason - must be last in enum */
+	xpUnknownReason		/* 63: unknown reason - must be last in enum */
 };
 
 /*
@@ -345,6 +346,8 @@ extern unsigned long (*xp_pa) (void *);
 extern enum xp_retval (*xp_remote_memcpy) (unsigned long, const unsigned long,
 		       size_t);
 extern int (*xp_cpu_to_nasid) (int);
+extern enum xp_retval (*xp_expand_memprotect) (unsigned long, unsigned long);
+extern enum xp_retval (*xp_restrict_memprotect) (unsigned long, unsigned long);
 
 extern u64 xp_nofault_PIOR_target;
 extern int xp_nofault_PIOR(void *);
diff --git a/drivers/misc/sgi-xp/xp_main.c b/drivers/misc/sgi-xp/xp_main.c
index 66a1d19e08ad..16f8dcab2da4 100644
--- a/drivers/misc/sgi-xp/xp_main.c
+++ b/drivers/misc/sgi-xp/xp_main.c
@@ -25,7 +25,7 @@ struct device_driver xp_dbg_name = {
 };
 
 struct device xp_dbg_subname = {
-	.bus_id = {0},		/* set to "" */
+	.init_name = "",		/* set to "" */
 	.driver = &xp_dbg_name
 };
 
@@ -51,6 +51,13 @@ EXPORT_SYMBOL_GPL(xp_remote_memcpy);
 int (*xp_cpu_to_nasid) (int cpuid);
 EXPORT_SYMBOL_GPL(xp_cpu_to_nasid);
 
+enum xp_retval (*xp_expand_memprotect) (unsigned long phys_addr,
+					unsigned long size);
+EXPORT_SYMBOL_GPL(xp_expand_memprotect);
+enum xp_retval (*xp_restrict_memprotect) (unsigned long phys_addr,
+					  unsigned long size);
+EXPORT_SYMBOL_GPL(xp_restrict_memprotect);
+
 /*
  * xpc_registrations[] keeps track of xpc_connect()'s done by the kernel-level
  * users of XPC.
diff --git a/drivers/misc/sgi-xp/xp_sn2.c b/drivers/misc/sgi-xp/xp_sn2.c
index 1440134caf31..fb3ec9d735a9 100644
--- a/drivers/misc/sgi-xp/xp_sn2.c
+++ b/drivers/misc/sgi-xp/xp_sn2.c
@@ -120,6 +120,38 @@ xp_cpu_to_nasid_sn2(int cpuid)
 	return cpuid_to_nasid(cpuid);
 }
 
+static enum xp_retval
+xp_expand_memprotect_sn2(unsigned long phys_addr, unsigned long size)
+{
+	u64 nasid_array = 0;
+	int ret;
+
+	ret = sn_change_memprotect(phys_addr, size, SN_MEMPROT_ACCESS_CLASS_1,
+				   &nasid_array);
+	if (ret != 0) {
+		dev_err(xp, "sn_change_memprotect(,, "
+			"SN_MEMPROT_ACCESS_CLASS_1,) failed ret=%d\n", ret);
+		return xpSalError;
+	}
+	return xpSuccess;
+}
+
+static enum xp_retval
+xp_restrict_memprotect_sn2(unsigned long phys_addr, unsigned long size)
+{
+	u64 nasid_array = 0;
+	int ret;
+
+	ret = sn_change_memprotect(phys_addr, size, SN_MEMPROT_ACCESS_CLASS_0,
+				   &nasid_array);
+	if (ret != 0) {
+		dev_err(xp, "sn_change_memprotect(,, "
+			"SN_MEMPROT_ACCESS_CLASS_0,) failed ret=%d\n", ret);
+		return xpSalError;
+	}
+	return xpSuccess;
+}
+
 enum xp_retval
 xp_init_sn2(void)
 {
@@ -132,6 +164,8 @@ xp_init_sn2(void)
 	xp_pa = xp_pa_sn2;
 	xp_remote_memcpy = xp_remote_memcpy_sn2;
 	xp_cpu_to_nasid = xp_cpu_to_nasid_sn2;
+	xp_expand_memprotect = xp_expand_memprotect_sn2;
+	xp_restrict_memprotect = xp_restrict_memprotect_sn2;
 
 	return xp_register_nofault_code_sn2();
 }
diff --git a/drivers/misc/sgi-xp/xp_uv.c b/drivers/misc/sgi-xp/xp_uv.c
index d9f7ce2510bc..d238576b26fa 100644
--- a/drivers/misc/sgi-xp/xp_uv.c
+++ b/drivers/misc/sgi-xp/xp_uv.c
@@ -15,6 +15,11 @@
 
 #include <linux/device.h>
 #include <asm/uv/uv_hub.h>
+#if defined CONFIG_X86_64
+#include <asm/uv/bios.h>
+#elif defined CONFIG_IA64_GENERIC || defined CONFIG_IA64_SGI_UV
+#include <asm/sn/sn_sal.h>
+#endif
 #include "../sgi-gru/grukservices.h"
 #include "xp.h"
 
@@ -49,18 +54,79 @@ xp_cpu_to_nasid_uv(int cpuid)
 	return UV_PNODE_TO_NASID(uv_cpu_to_pnode(cpuid));
 }
 
+static enum xp_retval
+xp_expand_memprotect_uv(unsigned long phys_addr, unsigned long size)
+{
+	int ret;
+
+#if defined CONFIG_X86_64
+	ret = uv_bios_change_memprotect(phys_addr, size, UV_MEMPROT_ALLOW_RW);
+	if (ret != BIOS_STATUS_SUCCESS) {
+		dev_err(xp, "uv_bios_change_memprotect(,, "
+			"UV_MEMPROT_ALLOW_RW) failed, ret=%d\n", ret);
+		return xpBiosError;
+	}
+
+#elif defined CONFIG_IA64_GENERIC || defined CONFIG_IA64_SGI_UV
+	u64 nasid_array;
+
+	ret = sn_change_memprotect(phys_addr, size, SN_MEMPROT_ACCESS_CLASS_1,
+				   &nasid_array);
+	if (ret != 0) {
+		dev_err(xp, "sn_change_memprotect(,, "
+			"SN_MEMPROT_ACCESS_CLASS_1,) failed ret=%d\n", ret);
+		return xpSalError;
+	}
+#else
+	#error not a supported configuration
+#endif
+	return xpSuccess;
+}
+
+static enum xp_retval
+xp_restrict_memprotect_uv(unsigned long phys_addr, unsigned long size)
+{
+	int ret;
+
+#if defined CONFIG_X86_64
+	ret = uv_bios_change_memprotect(phys_addr, size,
+					UV_MEMPROT_RESTRICT_ACCESS);
+	if (ret != BIOS_STATUS_SUCCESS) {
+		dev_err(xp, "uv_bios_change_memprotect(,, "
+			"UV_MEMPROT_RESTRICT_ACCESS) failed, ret=%d\n", ret);
+		return xpBiosError;
+	}
+
+#elif defined CONFIG_IA64_GENERIC || defined CONFIG_IA64_SGI_UV
+	u64 nasid_array;
+
+	ret = sn_change_memprotect(phys_addr, size, SN_MEMPROT_ACCESS_CLASS_0,
+				   &nasid_array);
+	if (ret != 0) {
+		dev_err(xp, "sn_change_memprotect(,, "
+			"SN_MEMPROT_ACCESS_CLASS_0,) failed ret=%d\n", ret);
+		return xpSalError;
+	}
+#else
+	#error not a supported configuration
+#endif
+	return xpSuccess;
+}
+
 enum xp_retval
 xp_init_uv(void)
 {
 	BUG_ON(!is_uv());
 
 	xp_max_npartitions = XP_MAX_NPARTITIONS_UV;
-	xp_partition_id = 0;	/* !!! not correct value */
-	xp_region_size = 0;	/* !!! not correct value */
+	xp_partition_id = sn_partition_id;
+	xp_region_size = sn_region_size;
 
 	xp_pa = xp_pa_uv;
 	xp_remote_memcpy = xp_remote_memcpy_uv;
 	xp_cpu_to_nasid = xp_cpu_to_nasid_uv;
+	xp_expand_memprotect = xp_expand_memprotect_uv;
+	xp_restrict_memprotect = xp_restrict_memprotect_uv;
 
 	return xpSuccess;
 }
diff --git a/drivers/misc/sgi-xp/xpc.h b/drivers/misc/sgi-xp/xpc.h
index 619208d61862..a5bd658c2e83 100644
--- a/drivers/misc/sgi-xp/xpc.h
+++ b/drivers/misc/sgi-xp/xpc.h
@@ -181,6 +181,18 @@ struct xpc_vars_part_sn2 {
 				  xpc_nasid_mask_nlongs))
 
 /*
+ * Info pertinent to a GRU message queue using a watch list for irq generation.
+ */
+struct xpc_gru_mq_uv {
+	void *address;		/* address of GRU message queue */
+	unsigned int order;	/* size of GRU message queue as a power of 2 */
+	int irq;		/* irq raised when message is received in mq */
+	int mmr_blade;		/* blade where watchlist was allocated from */
+	unsigned long mmr_offset; /* offset of irq mmr located on mmr_blade */
+	int watchlist_num;	/* number of watchlist allocatd by BIOS */
+};
+
+/*
  * The activate_mq is used to send/receive GRU messages that affect XPC's
  * heartbeat, partition active state, and channel state. This is UV only.
  */
diff --git a/drivers/misc/sgi-xp/xpc_main.c b/drivers/misc/sgi-xp/xpc_main.c
index e8d5cfbd32c2..89218f7cfaa7 100644
--- a/drivers/misc/sgi-xp/xpc_main.c
+++ b/drivers/misc/sgi-xp/xpc_main.c
@@ -59,12 +59,12 @@ struct device_driver xpc_dbg_name = {
 };
 
 struct device xpc_part_dbg_subname = {
-	.bus_id = {0},		/* set to "part" at xpc_init() time */
+	.init_name = "",	/* set to "part" at xpc_init() time */
 	.driver = &xpc_dbg_name
 };
 
 struct device xpc_chan_dbg_subname = {
-	.bus_id = {0},		/* set to "chan" at xpc_init() time */
+	.init_name = "",	/* set to "chan" at xpc_init() time */
 	.driver = &xpc_dbg_name
 };
 
@@ -1258,8 +1258,8 @@ xpc_init(void)
 	int ret;
 	struct task_struct *kthread;
 
-	snprintf(xpc_part->bus_id, BUS_ID_SIZE, "part");
-	snprintf(xpc_chan->bus_id, BUS_ID_SIZE, "chan");
+	dev_set_name(xpc_part, "part");
+	dev_set_name(xpc_chan, "chan");
 
 	if (is_shub()) {
 		/*
diff --git a/drivers/misc/sgi-xp/xpc_sn2.c b/drivers/misc/sgi-xp/xpc_sn2.c
index b4882ccf6344..73b7fb8de47a 100644
--- a/drivers/misc/sgi-xp/xpc_sn2.c
+++ b/drivers/misc/sgi-xp/xpc_sn2.c
@@ -553,22 +553,17 @@ static u64 xpc_prot_vec_sn2[MAX_NUMNODES];
 static enum xp_retval
 xpc_allow_amo_ops_sn2(struct amo *amos_page)
 {
-	u64 nasid_array = 0;
-	int ret;
+	enum xp_retval ret = xpSuccess;
 
 	/*
 	 * On SHUB 1.1, we cannot call sn_change_memprotect() since the BIST
 	 * collides with memory operations. On those systems we call
 	 * xpc_allow_amo_ops_shub_wars_1_1_sn2() instead.
 	 */
-	if (!enable_shub_wars_1_1()) {
-		ret = sn_change_memprotect(ia64_tpa((u64)amos_page), PAGE_SIZE,
-					   SN_MEMPROT_ACCESS_CLASS_1,
-					   &nasid_array);
-		if (ret != 0)
-			return xpSalError;
-	}
-	return xpSuccess;
+	if (!enable_shub_wars_1_1())
+		ret = xp_expand_memprotect(ia64_tpa((u64)amos_page), PAGE_SIZE);
+
+	return ret;
 }
 
 /*
diff --git a/drivers/misc/sgi-xp/xpc_uv.c b/drivers/misc/sgi-xp/xpc_uv.c
index 1ac694c01623..684b2dd17583 100644
--- a/drivers/misc/sgi-xp/xpc_uv.c
+++ b/drivers/misc/sgi-xp/xpc_uv.c
@@ -18,7 +18,15 @@
 #include <linux/interrupt.h>
 #include <linux/delay.h>
 #include <linux/device.h>
+#include <linux/err.h>
 #include <asm/uv/uv_hub.h>
+#if defined CONFIG_X86_64
+#include <asm/uv/bios.h>
+#include <asm/uv/uv_irq.h>
+#elif defined CONFIG_IA64_GENERIC || defined CONFIG_IA64_SGI_UV
+#include <asm/sn/intr.h>
+#include <asm/sn/sn_sal.h>
+#endif
 #include "../sgi-gru/gru.h"
 #include "../sgi-gru/grukservices.h"
 #include "xpc.h"
@@ -27,15 +35,17 @@ static atomic64_t xpc_heartbeat_uv;
 static DECLARE_BITMAP(xpc_heartbeating_to_mask_uv, XP_MAX_NPARTITIONS_UV);
 
 #define XPC_ACTIVATE_MSG_SIZE_UV	(1 * GRU_CACHE_LINE_BYTES)
-#define XPC_NOTIFY_MSG_SIZE_UV		(2 * GRU_CACHE_LINE_BYTES)
+#define XPC_ACTIVATE_MQ_SIZE_UV		(4 * XP_MAX_NPARTITIONS_UV * \
+					 XPC_ACTIVATE_MSG_SIZE_UV)
+#define XPC_ACTIVATE_IRQ_NAME		"xpc_activate"
 
-#define XPC_ACTIVATE_MQ_SIZE_UV	(4 * XP_MAX_NPARTITIONS_UV * \
-				 XPC_ACTIVATE_MSG_SIZE_UV)
-#define XPC_NOTIFY_MQ_SIZE_UV	(4 * XP_MAX_NPARTITIONS_UV * \
-				 XPC_NOTIFY_MSG_SIZE_UV)
+#define XPC_NOTIFY_MSG_SIZE_UV		(2 * GRU_CACHE_LINE_BYTES)
+#define XPC_NOTIFY_MQ_SIZE_UV		(4 * XP_MAX_NPARTITIONS_UV * \
+					 XPC_NOTIFY_MSG_SIZE_UV)
+#define XPC_NOTIFY_IRQ_NAME		"xpc_notify"
 
-static void *xpc_activate_mq_uv;
-static void *xpc_notify_mq_uv;
+static struct xpc_gru_mq_uv *xpc_activate_mq_uv;
+static struct xpc_gru_mq_uv *xpc_notify_mq_uv;
 
 static int
 xpc_setup_partitions_sn_uv(void)
@@ -52,62 +62,209 @@ xpc_setup_partitions_sn_uv(void)
 	return 0;
 }
 
-static void *
-xpc_create_gru_mq_uv(unsigned int mq_size, int cpuid, unsigned int irq,
+static int
+xpc_get_gru_mq_irq_uv(struct xpc_gru_mq_uv *mq, int cpu, char *irq_name)
+{
+#if defined CONFIG_X86_64
+	mq->irq = uv_setup_irq(irq_name, cpu, mq->mmr_blade, mq->mmr_offset);
+	if (mq->irq < 0) {
+		dev_err(xpc_part, "uv_setup_irq() returned error=%d\n",
+			mq->irq);
+	}
+
+#elif defined CONFIG_IA64_GENERIC || defined CONFIG_IA64_SGI_UV
+	int mmr_pnode;
+	unsigned long mmr_value;
+
+	if (strcmp(irq_name, XPC_ACTIVATE_IRQ_NAME) == 0)
+		mq->irq = SGI_XPC_ACTIVATE;
+	else if (strcmp(irq_name, XPC_NOTIFY_IRQ_NAME) == 0)
+		mq->irq = SGI_XPC_NOTIFY;
+	else
+		return -EINVAL;
+
+	mmr_pnode = uv_blade_to_pnode(mq->mmr_blade);
+	mmr_value = (unsigned long)cpu_physical_id(cpu) << 32 | mq->irq;
+
+	uv_write_global_mmr64(mmr_pnode, mq->mmr_offset, mmr_value);
+#else
+	#error not a supported configuration
+#endif
+
+	return 0;
+}
+
+static void
+xpc_release_gru_mq_irq_uv(struct xpc_gru_mq_uv *mq)
+{
+#if defined CONFIG_X86_64
+	uv_teardown_irq(mq->irq, mq->mmr_blade, mq->mmr_offset);
+
+#elif defined CONFIG_IA64_GENERIC || defined CONFIG_IA64_SGI_UV
+	int mmr_pnode;
+	unsigned long mmr_value;
+
+	mmr_pnode = uv_blade_to_pnode(mq->mmr_blade);
+	mmr_value = 1UL << 16;
+
+	uv_write_global_mmr64(mmr_pnode, mq->mmr_offset, mmr_value);
+#else
+	#error not a supported configuration
+#endif
+}
+
+static int
+xpc_gru_mq_watchlist_alloc_uv(struct xpc_gru_mq_uv *mq)
+{
+	int ret;
+
+#if defined CONFIG_X86_64
+	ret = uv_bios_mq_watchlist_alloc(mq->mmr_blade, mq->address, mq->order,
+					 &mq->mmr_offset);
+	if (ret < 0) {
+		dev_err(xpc_part, "uv_bios_mq_watchlist_alloc() failed, "
+			"ret=%d\n", ret);
+		return ret;
+	}
+#elif defined CONFIG_IA64_GENERIC || defined CONFIG_IA64_SGI_UV
+	ret = sn_mq_watchlist_alloc(mq->mmr_blade, mq->address, mq->order,
+				    &mq->mmr_offset);
+	if (ret < 0) {
+		dev_err(xpc_part, "sn_mq_watchlist_alloc() failed, ret=%d\n",
+			ret);
+		return -EBUSY;
+	}
+#else
+	#error not a supported configuration
+#endif
+
+	mq->watchlist_num = ret;
+	return 0;
+}
+
+static void
+xpc_gru_mq_watchlist_free_uv(struct xpc_gru_mq_uv *mq)
+{
+	int ret;
+
+#if defined CONFIG_X86_64
+	ret = uv_bios_mq_watchlist_free(mq->mmr_blade, mq->watchlist_num);
+	BUG_ON(ret != BIOS_STATUS_SUCCESS);
+#elif defined CONFIG_IA64_GENERIC || defined CONFIG_IA64_SGI_UV
+	ret = sn_mq_watchlist_free(mq->mmr_blade, mq->watchlist_num);
+	BUG_ON(ret != SALRET_OK);
+#else
+	#error not a supported configuration
+#endif
+}
+
+static struct xpc_gru_mq_uv *
+xpc_create_gru_mq_uv(unsigned int mq_size, int cpu, char *irq_name,
 		     irq_handler_t irq_handler)
 {
+	enum xp_retval xp_ret;
 	int ret;
 	int nid;
-	int mq_order;
+	int pg_order;
 	struct page *page;
-	void *mq;
+	struct xpc_gru_mq_uv *mq;
+
+	mq = kmalloc(sizeof(struct xpc_gru_mq_uv), GFP_KERNEL);
+	if (mq == NULL) {
+		dev_err(xpc_part, "xpc_create_gru_mq_uv() failed to kmalloc() "
+			"a xpc_gru_mq_uv structure\n");
+		ret = -ENOMEM;
+		goto out_1;
+	}
+
+	pg_order = get_order(mq_size);
+	mq->order = pg_order + PAGE_SHIFT;
+	mq_size = 1UL << mq->order;
+
+	mq->mmr_blade = uv_cpu_to_blade_id(cpu);
 
-	nid = cpu_to_node(cpuid);
-	mq_order = get_order(mq_size);
+	nid = cpu_to_node(cpu);
 	page = alloc_pages_node(nid, GFP_KERNEL | __GFP_ZERO | GFP_THISNODE,
-				mq_order);
+				pg_order);
 	if (page == NULL) {
 		dev_err(xpc_part, "xpc_create_gru_mq_uv() failed to alloc %d "
 			"bytes of memory on nid=%d for GRU mq\n", mq_size, nid);
-		return NULL;
+		ret = -ENOMEM;
+		goto out_2;
 	}
+	mq->address = page_address(page);
 
-	mq = page_address(page);
-	ret = gru_create_message_queue(mq, mq_size);
+	ret = gru_create_message_queue(mq->address, mq_size);
 	if (ret != 0) {
 		dev_err(xpc_part, "gru_create_message_queue() returned "
 			"error=%d\n", ret);
-		free_pages((unsigned long)mq, mq_order);
-		return NULL;
+		ret = -EINVAL;
+		goto out_3;
 	}
 
-	/* !!! Need to do some other things to set up IRQ */
+	/* enable generation of irq when GRU mq operation occurs to this mq */
+	ret = xpc_gru_mq_watchlist_alloc_uv(mq);
+	if (ret != 0)
+		goto out_3;
 
-	ret = request_irq(irq, irq_handler, 0, "xpc", NULL);
+	ret = xpc_get_gru_mq_irq_uv(mq, cpu, irq_name);
+	if (ret != 0)
+		goto out_4;
+
+	ret = request_irq(mq->irq, irq_handler, 0, irq_name, NULL);
 	if (ret != 0) {
 		dev_err(xpc_part, "request_irq(irq=%d) returned error=%d\n",
-			irq, ret);
-		free_pages((unsigned long)mq, mq_order);
-		return NULL;
+			mq->irq, ret);
+		goto out_5;
 	}
 
-	/* !!! enable generation of irq when GRU mq op occurs to this mq */
-
-	/* ??? allow other partitions to access GRU mq? */
+	/* allow other partitions to access this GRU mq */
+	xp_ret = xp_expand_memprotect(xp_pa(mq->address), mq_size);
+	if (xp_ret != xpSuccess) {
+		ret = -EACCES;
+		goto out_6;
+	}
 
 	return mq;
+
+	/* something went wrong */
+out_6:
+	free_irq(mq->irq, NULL);
+out_5:
+	xpc_release_gru_mq_irq_uv(mq);
+out_4:
+	xpc_gru_mq_watchlist_free_uv(mq);
+out_3:
+	free_pages((unsigned long)mq->address, pg_order);
+out_2:
+	kfree(mq);
+out_1:
+	return ERR_PTR(ret);
 }
 
 static void
-xpc_destroy_gru_mq_uv(void *mq, unsigned int mq_size, unsigned int irq)
+xpc_destroy_gru_mq_uv(struct xpc_gru_mq_uv *mq)
 {
-	/* ??? disallow other partitions to access GRU mq? */
+	unsigned int mq_size;
+	int pg_order;
+	int ret;
+
+	/* disallow other partitions to access GRU mq */
+	mq_size = 1UL << mq->order;
+	ret = xp_restrict_memprotect(xp_pa(mq->address), mq_size);
+	BUG_ON(ret != xpSuccess);
 
-	/* !!! disable generation of irq when GRU mq op occurs to this mq */
+	/* unregister irq handler and release mq irq/vector mapping */
+	free_irq(mq->irq, NULL);
+	xpc_release_gru_mq_irq_uv(mq);
 
-	free_irq(irq, NULL);
+	/* disable generation of irq when GRU mq op occurs to this mq */
+	xpc_gru_mq_watchlist_free_uv(mq);
 
-	free_pages((unsigned long)mq, get_order(mq_size));
+	pg_order = mq->order - PAGE_SHIFT;
+	free_pages((unsigned long)mq->address, pg_order);
+
+	kfree(mq);
 }
 
 static enum xp_retval
@@ -402,7 +559,10 @@ xpc_handle_activate_IRQ_uv(int irq, void *dev_id)
 	struct xpc_partition *part;
 	int wakeup_hb_checker = 0;
 
-	while ((msg_hdr = gru_get_next_message(xpc_activate_mq_uv)) != NULL) {
+	while (1) {
+		msg_hdr = gru_get_next_message(xpc_activate_mq_uv->address);
+		if (msg_hdr == NULL)
+			break;
 
 		partid = msg_hdr->partid;
 		if (partid < 0 || partid >= XP_MAX_NPARTITIONS_UV) {
@@ -418,7 +578,7 @@ xpc_handle_activate_IRQ_uv(int irq, void *dev_id)
 			}
 		}
 
-		gru_free_message(xpc_activate_mq_uv, msg_hdr);
+		gru_free_message(xpc_activate_mq_uv->address, msg_hdr);
 	}
 
 	if (wakeup_hb_checker)
@@ -482,7 +642,7 @@ xpc_send_local_activate_IRQ_uv(struct xpc_partition *part, int act_state_req)
 	struct xpc_partition_uv *part_uv = &part->sn.uv;
 
 	/*
-	 * !!! Make our side think that the remote parition sent an activate
+	 * !!! Make our side think that the remote partition sent an activate
 	 * !!! message our way by doing what the activate IRQ handler would
 	 * !!! do had one really been sent.
 	 */
@@ -500,14 +660,39 @@ static enum xp_retval
 xpc_get_partition_rsvd_page_pa_uv(void *buf, u64 *cookie, unsigned long *rp_pa,
 				  size_t *len)
 {
-	/* !!! call the UV version of sn_partition_reserved_page_pa() */
-	return xpUnsupported;
+	s64 status;
+	enum xp_retval ret;
+
+#if defined CONFIG_X86_64
+	status = uv_bios_reserved_page_pa((u64)buf, cookie, (u64 *)rp_pa,
+					  (u64 *)len);
+	if (status == BIOS_STATUS_SUCCESS)
+		ret = xpSuccess;
+	else if (status == BIOS_STATUS_MORE_PASSES)
+		ret = xpNeedMoreInfo;
+	else
+		ret = xpBiosError;
+
+#elif defined CONFIG_IA64_GENERIC || defined CONFIG_IA64_SGI_UV
+	status = sn_partition_reserved_page_pa((u64)buf, cookie, rp_pa, len);
+	if (status == SALRET_OK)
+		ret = xpSuccess;
+	else if (status == SALRET_MORE_PASSES)
+		ret = xpNeedMoreInfo;
+	else
+		ret = xpSalError;
+
+#else
+	#error not a supported configuration
+#endif
+
+	return ret;
 }
 
 static int
 xpc_setup_rsvd_page_sn_uv(struct xpc_rsvd_page *rp)
 {
-	rp->sn.activate_mq_gpa = uv_gpa(xpc_activate_mq_uv);
+	rp->sn.activate_mq_gpa = uv_gpa(xpc_activate_mq_uv->address);
 	return 0;
 }
 
@@ -1411,22 +1596,18 @@ xpc_init_uv(void)
 		return -E2BIG;
 	}
 
-	/* ??? The cpuid argument's value is 0, is that what we want? */
-	/* !!! The irq argument's value isn't correct. */
-	xpc_activate_mq_uv = xpc_create_gru_mq_uv(XPC_ACTIVATE_MQ_SIZE_UV, 0, 0,
+	xpc_activate_mq_uv = xpc_create_gru_mq_uv(XPC_ACTIVATE_MQ_SIZE_UV, 0,
+						  XPC_ACTIVATE_IRQ_NAME,
 						  xpc_handle_activate_IRQ_uv);
-	if (xpc_activate_mq_uv == NULL)
-		return -ENOMEM;
+	if (IS_ERR(xpc_activate_mq_uv))
+		return PTR_ERR(xpc_activate_mq_uv);
 
-	/* ??? The cpuid argument's value is 0, is that what we want? */
-	/* !!! The irq argument's value isn't correct. */
-	xpc_notify_mq_uv = xpc_create_gru_mq_uv(XPC_NOTIFY_MQ_SIZE_UV, 0, 0,
+	xpc_notify_mq_uv = xpc_create_gru_mq_uv(XPC_NOTIFY_MQ_SIZE_UV, 0,
+						XPC_NOTIFY_IRQ_NAME,
 						xpc_handle_notify_IRQ_uv);
-	if (xpc_notify_mq_uv == NULL) {
-		/* !!! The irq argument's value isn't correct. */
-		xpc_destroy_gru_mq_uv(xpc_activate_mq_uv,
-				      XPC_ACTIVATE_MQ_SIZE_UV, 0);
-		return -ENOMEM;
+	if (IS_ERR(xpc_notify_mq_uv)) {
+		xpc_destroy_gru_mq_uv(xpc_activate_mq_uv);
+		return PTR_ERR(xpc_notify_mq_uv);
 	}
 
 	return 0;
@@ -1435,9 +1616,6 @@ xpc_init_uv(void)
 void
 xpc_exit_uv(void)
 {
-	/* !!! The irq argument's value isn't correct. */
-	xpc_destroy_gru_mq_uv(xpc_notify_mq_uv, XPC_NOTIFY_MQ_SIZE_UV, 0);
-
-	/* !!! The irq argument's value isn't correct. */
-	xpc_destroy_gru_mq_uv(xpc_activate_mq_uv, XPC_ACTIVATE_MQ_SIZE_UV, 0);
+	xpc_destroy_gru_mq_uv(xpc_notify_mq_uv);
+	xpc_destroy_gru_mq_uv(xpc_activate_mq_uv);
 }
diff --git a/drivers/misc/sgi-xp/xpnet.c b/drivers/misc/sgi-xp/xpnet.c
index 71513b3af708..234d7be6d812 100644
--- a/drivers/misc/sgi-xp/xpnet.c
+++ b/drivers/misc/sgi-xp/xpnet.c
@@ -138,7 +138,7 @@ struct device_driver xpnet_dbg_name = {
 };
 
 struct device xpnet_dbg_subname = {
-	.bus_id = {0},		/* set to "" */
+	.init_name = "",	/* set to "" */
 	.driver = &xpnet_dbg_name
 };
 
diff --git a/drivers/misc/tifm_7xx1.c b/drivers/misc/tifm_7xx1.c
index 67503ea71d21..e71eba31decb 100644
--- a/drivers/misc/tifm_7xx1.c
+++ b/drivers/misc/tifm_7xx1.c
@@ -164,7 +164,7 @@ static void tifm_7xx1_switch_media(struct work_struct *work)
 		if (sock) {
 			printk(KERN_INFO
 			       "%s : demand removing card from socket %u:%u\n",
-			       fm->dev.bus_id, fm->id, cnt);
+			       dev_name(&fm->dev), fm->id, cnt);
 			fm->sockets[cnt] = NULL;
 			sock_addr = sock->addr;
 			spin_unlock_irqrestore(&fm->lock, flags);
diff --git a/drivers/misc/tifm_core.c b/drivers/misc/tifm_core.c
index 82dc72a1484f..98bcba521da2 100644
--- a/drivers/misc/tifm_core.c
+++ b/drivers/misc/tifm_core.c
@@ -203,7 +203,7 @@ int tifm_add_adapter(struct tifm_adapter *fm)
 	if (rc)
 		return rc;
 
-	snprintf(fm->dev.bus_id, BUS_ID_SIZE, "tifm%u", fm->id);
+	dev_set_name(&fm->dev, "tifm%u", fm->id);
 	rc = device_add(&fm->dev);
 	if (rc) {
 		spin_lock(&tifm_adapter_lock);
@@ -266,9 +266,8 @@ struct tifm_dev *tifm_alloc_device(struct tifm_adapter *fm, unsigned int id,
 		sock->dev.dma_mask = fm->dev.parent->dma_mask;
 		sock->dev.release = tifm_free_device;
 
-		snprintf(sock->dev.bus_id, BUS_ID_SIZE,
-			 "tifm_%s%u:%u", tifm_media_type_name(type, 2),
-			 fm->id, id);
+		dev_set_name(&sock->dev, "tifm_%s%u:%u",
+			     tifm_media_type_name(type, 2), fm->id, id);
 		printk(KERN_INFO DRIVER_NAME
 		       ": %s card detected in socket %u:%u\n",
 		       tifm_media_type_name(type, 0), fm->id, id);
diff --git a/drivers/mmc/host/mmci.c b/drivers/mmc/host/mmci.c
index 2fadf323c696..1bcbdd6763ac 100644
--- a/drivers/mmc/host/mmci.c
+++ b/drivers/mmc/host/mmci.c
@@ -500,7 +500,7 @@ static int mmci_probe(struct amba_device *dev, void *id)
 	}
 
 	host = mmc_priv(mmc);
-	host->clk = clk_get(&dev->dev, "MCLK");
+	host->clk = clk_get(&dev->dev, NULL);
 	if (IS_ERR(host->clk)) {
 		ret = PTR_ERR(host->clk);
 		host->clk = NULL;
diff --git a/drivers/mmc/host/pxamci.c b/drivers/mmc/host/pxamci.c
index ebfaa9960939..f88cc7406354 100644
--- a/drivers/mmc/host/pxamci.c
+++ b/drivers/mmc/host/pxamci.c
@@ -26,11 +26,12 @@
 #include <linux/clk.h>
 #include <linux/err.h>
 #include <linux/mmc/host.h>
+#include <linux/io.h>
 
-#include <asm/dma.h>
-#include <asm/io.h>
 #include <asm/sizes.h>
 
+#include <mach/dma.h>
+#include <mach/hardware.h>
 #include <mach/pxa-regs.h>
 #include <mach/mmc.h>
 
@@ -533,7 +534,7 @@ static int pxamci_probe(struct platform_device *pdev)
 	host->pdata = pdev->dev.platform_data;
 	host->clkrt = CLKRT_OFF;
 
-	host->clk = clk_get(&pdev->dev, "MMCCLK");
+	host->clk = clk_get(&pdev->dev, NULL);
 	if (IS_ERR(host->clk)) {
 		ret = PTR_ERR(host->clk);
 		host->clk = NULL;
diff --git a/drivers/mmc/host/s3cmci.c b/drivers/mmc/host/s3cmci.c
index 3b2085b57769..fcc98a4cce3c 100644
--- a/drivers/mmc/host/s3cmci.c
+++ b/drivers/mmc/host/s3cmci.c
@@ -25,7 +25,7 @@
 #include <mach/regs-sdi.h>
 #include <mach/regs-gpio.h>
 
-#include <asm/plat-s3c24xx/mci.h>
+#include <plat/mci.h>
 
 #include "s3cmci.h"
 
diff --git a/drivers/mtd/devices/m25p80.c b/drivers/mtd/devices/m25p80.c
index 76a76751da36..798ae4c8ef31 100644
--- a/drivers/mtd/devices/m25p80.c
+++ b/drivers/mtd/devices/m25p80.c
@@ -170,7 +170,7 @@ static int wait_till_ready(struct m25p *flash)
 static int erase_block(struct m25p *flash)
 {
 	DEBUG(MTD_DEBUG_LEVEL3, "%s: %s %dKiB\n",
-			flash->spi->dev.bus_id, __func__,
+			dev_name(&flash->spi->dev), __func__,
 			flash->mtd.size / 1024);
 
 	/* Wait until finished previous write command. */
@@ -197,7 +197,7 @@ static int erase_block(struct m25p *flash)
 static int erase_sector(struct m25p *flash, u32 offset)
 {
 	DEBUG(MTD_DEBUG_LEVEL3, "%s: %s %dKiB at 0x%08x\n",
-			flash->spi->dev.bus_id, __func__,
+			dev_name(&flash->spi->dev), __func__,
 			flash->mtd.erasesize / 1024, offset);
 
 	/* Wait until finished previous write command. */
@@ -234,7 +234,7 @@ static int m25p80_erase(struct mtd_info *mtd, struct erase_info *instr)
 	u32 addr,len;
 
 	DEBUG(MTD_DEBUG_LEVEL2, "%s: %s %s 0x%08x, len %d\n",
-			flash->spi->dev.bus_id, __func__, "at",
+			dev_name(&flash->spi->dev), __func__, "at",
 			(u32)instr->addr, instr->len);
 
 	/* sanity checks */
@@ -292,7 +292,7 @@ static int m25p80_read(struct mtd_info *mtd, loff_t from, size_t len,
 	struct spi_message m;
 
 	DEBUG(MTD_DEBUG_LEVEL2, "%s: %s %s 0x%08x, len %zd\n",
-			flash->spi->dev.bus_id, __func__, "from",
+			dev_name(&flash->spi->dev), __func__, "from",
 			(u32)from, len);
 
 	/* sanity checks */
@@ -364,7 +364,7 @@ static int m25p80_write(struct mtd_info *mtd, loff_t to, size_t len,
 	struct spi_message m;
 
 	DEBUG(MTD_DEBUG_LEVEL2, "%s: %s %s 0x%08x, len %zd\n",
-			flash->spi->dev.bus_id, __func__, "to",
+			dev_name(&flash->spi->dev), __func__, "to",
 			(u32)to, len);
 
 	if (retlen)
@@ -560,7 +560,7 @@ static struct flash_info *__devinit jedec_probe(struct spi_device *spi)
 	tmp = spi_write_then_read(spi, &code, 1, id, 5);
 	if (tmp < 0) {
 		DEBUG(MTD_DEBUG_LEVEL0, "%s: error %d reading JEDEC ID\n",
-			spi->dev.bus_id, tmp);
+			dev_name(&spi->dev), tmp);
 		return NULL;
 	}
 	jedec = id[0];
@@ -613,7 +613,7 @@ static int __devinit m25p_probe(struct spi_device *spi)
 		/* unrecognized chip? */
 		if (i == ARRAY_SIZE(m25p_data)) {
 			DEBUG(MTD_DEBUG_LEVEL0, "%s: unrecognized id %s\n",
-					spi->dev.bus_id, data->type);
+					dev_name(&spi->dev), data->type);
 			info = NULL;
 
 		/* recognized; is that chip really what's there? */
@@ -654,7 +654,7 @@ static int __devinit m25p_probe(struct spi_device *spi)
 	if (data && data->name)
 		flash->mtd.name = data->name;
 	else
-		flash->mtd.name = spi->dev.bus_id;
+		flash->mtd.name = dev_name(&spi->dev);
 
 	flash->mtd.type = MTD_NORFLASH;
 	flash->mtd.writesize = 1;
diff --git a/drivers/mtd/devices/mtd_dataflash.c b/drivers/mtd/devices/mtd_dataflash.c
index 6dd9aff8bb2d..65126cd668ff 100644
--- a/drivers/mtd/devices/mtd_dataflash.c
+++ b/drivers/mtd/devices/mtd_dataflash.c
@@ -128,7 +128,7 @@ static int dataflash_waitready(struct spi_device *spi)
 		status = dataflash_status(spi);
 		if (status < 0) {
 			DEBUG(MTD_DEBUG_LEVEL1, "%s: status %d?\n",
-					spi->dev.bus_id, status);
+					dev_name(&spi->dev), status);
 			status = 0;
 		}
 
@@ -154,7 +154,7 @@ static int dataflash_erase(struct mtd_info *mtd, struct erase_info *instr)
 	uint8_t			*command;
 
 	DEBUG(MTD_DEBUG_LEVEL2, "%s: erase addr=0x%x len 0x%x\n",
-			spi->dev.bus_id,
+			dev_name(&spi->dev),
 			instr->addr, instr->len);
 
 	/* Sanity checks */
@@ -197,7 +197,7 @@ static int dataflash_erase(struct mtd_info *mtd, struct erase_info *instr)
 
 		if (status < 0) {
 			printk(KERN_ERR "%s: erase %x, err %d\n",
-				spi->dev.bus_id, pageaddr, status);
+				dev_name(&spi->dev), pageaddr, status);
 			/* REVISIT:  can retry instr->retries times; or
 			 * giveup and instr->fail_addr = instr->addr;
 			 */
@@ -239,7 +239,7 @@ static int dataflash_read(struct mtd_info *mtd, loff_t from, size_t len,
 	int			status;
 
 	DEBUG(MTD_DEBUG_LEVEL2, "%s: read 0x%x..0x%x\n",
-		priv->spi->dev.bus_id, (unsigned)from, (unsigned)(from + len));
+		dev_name(&priv->spi->dev), (unsigned)from, (unsigned)(from + len));
 
 	*retlen = 0;
 
@@ -288,7 +288,7 @@ static int dataflash_read(struct mtd_info *mtd, loff_t from, size_t len,
 		status = 0;
 	} else
 		DEBUG(MTD_DEBUG_LEVEL1, "%s: read %x..%x --> %d\n",
-			priv->spi->dev.bus_id,
+			dev_name(&priv->spi->dev),
 			(unsigned)from, (unsigned)(from + len),
 			status);
 	return status;
@@ -315,7 +315,7 @@ static int dataflash_write(struct mtd_info *mtd, loff_t to, size_t len,
 	uint8_t			*command;
 
 	DEBUG(MTD_DEBUG_LEVEL2, "%s: write 0x%x..0x%x\n",
-		spi->dev.bus_id, (unsigned)to, (unsigned)(to + len));
+		dev_name(&spi->dev), (unsigned)to, (unsigned)(to + len));
 
 	*retlen = 0;
 
@@ -374,7 +374,7 @@ static int dataflash_write(struct mtd_info *mtd, loff_t to, size_t len,
 			status = spi_sync(spi, &msg);
 			if (status < 0)
 				DEBUG(MTD_DEBUG_LEVEL1, "%s: xfer %u -> %d \n",
-					spi->dev.bus_id, addr, status);
+					dev_name(&spi->dev), addr, status);
 
 			(void) dataflash_waitready(priv->spi);
 		}
@@ -396,7 +396,7 @@ static int dataflash_write(struct mtd_info *mtd, loff_t to, size_t len,
 		spi_transfer_del(x + 1);
 		if (status < 0)
 			DEBUG(MTD_DEBUG_LEVEL1, "%s: pgm %u/%u -> %d \n",
-				spi->dev.bus_id, addr, writelen, status);
+				dev_name(&spi->dev), addr, writelen, status);
 
 		(void) dataflash_waitready(priv->spi);
 
@@ -416,14 +416,14 @@ static int dataflash_write(struct mtd_info *mtd, loff_t to, size_t len,
 		status = spi_sync(spi, &msg);
 		if (status < 0)
 			DEBUG(MTD_DEBUG_LEVEL1, "%s: compare %u -> %d \n",
-				spi->dev.bus_id, addr, status);
+				dev_name(&spi->dev), addr, status);
 
 		status = dataflash_waitready(priv->spi);
 
 		/* Check result of the compare operation */
 		if (status & (1 << 6)) {
 			printk(KERN_ERR "%s: compare page %u, err %d\n",
-				spi->dev.bus_id, pageaddr, status);
+				dev_name(&spi->dev), pageaddr, status);
 			remaining = 0;
 			status = -EIO;
 			break;
@@ -779,7 +779,7 @@ static struct flash_info *__devinit jedec_probe(struct spi_device *spi)
 	tmp = spi_write_then_read(spi, &code, 1, id, 3);
 	if (tmp < 0) {
 		DEBUG(MTD_DEBUG_LEVEL0, "%s: error %d reading JEDEC ID\n",
-			spi->dev.bus_id, tmp);
+			dev_name(&spi->dev), tmp);
 		return ERR_PTR(tmp);
 	}
 	if (id[0] != 0x1f)
@@ -869,7 +869,7 @@ static int __devinit dataflash_probe(struct spi_device *spi)
 	status = dataflash_status(spi);
 	if (status <= 0 || status == 0xff) {
 		DEBUG(MTD_DEBUG_LEVEL1, "%s: status error %d\n",
-				spi->dev.bus_id, status);
+				dev_name(&spi->dev), status);
 		if (status == 0 || status == 0xff)
 			status = -ENODEV;
 		return status;
@@ -905,13 +905,13 @@ static int __devinit dataflash_probe(struct spi_device *spi)
 	/* obsolete AT45DB1282 not (yet?) supported */
 	default:
 		DEBUG(MTD_DEBUG_LEVEL1, "%s: unsupported device (%x)\n",
-				spi->dev.bus_id, status & 0x3c);
+				dev_name(&spi->dev), status & 0x3c);
 		status = -ENODEV;
 	}
 
 	if (status < 0)
 		DEBUG(MTD_DEBUG_LEVEL1, "%s: add_dataflash --> %d\n",
-				spi->dev.bus_id, status);
+				dev_name(&spi->dev), status);
 
 	return status;
 }
@@ -921,7 +921,7 @@ static int __devexit dataflash_remove(struct spi_device *spi)
 	struct dataflash	*flash = dev_get_drvdata(&spi->dev);
 	int			status;
 
-	DEBUG(MTD_DEBUG_LEVEL1, "%s: remove\n", spi->dev.bus_id);
+	DEBUG(MTD_DEBUG_LEVEL1, "%s: remove\n", dev_name(&spi->dev));
 
 	if (mtd_has_partitions() && flash->partitioned)
 		status = del_mtd_partitions(&flash->mtd);
diff --git a/drivers/mtd/maps/dc21285.c b/drivers/mtd/maps/dc21285.c
index 3aa018c092f8..42969fe051b2 100644
--- a/drivers/mtd/maps/dc21285.c
+++ b/drivers/mtd/maps/dc21285.c
@@ -32,16 +32,15 @@ static struct mtd_info *dc21285_mtd;
  */
 static void nw_en_write(void)
 {
-	extern spinlock_t gpio_lock;
 	unsigned long flags;
 
 	/*
 	 * we want to write a bit pattern XXX1 to Xilinx to enable
 	 * the write gate, which will be open for about the next 2ms.
 	 */
-	spin_lock_irqsave(&gpio_lock, flags);
-	cpld_modify(1, 1);
-	spin_unlock_irqrestore(&gpio_lock, flags);
+	spin_lock_irqsave(&nw_gpio_lock, flags);
+	nw_cpld_modify(CPLD_FLASH_WR_ENABLE, CPLD_FLASH_WR_ENABLE);
+	spin_unlock_irqrestore(&nw_gpio_lock, flags);
 
 	/*
 	 * let the ISA bus to catch on...
diff --git a/drivers/mtd/maps/integrator-flash.c b/drivers/mtd/maps/integrator-flash.c
index 7100ee3c7b01..d2ec262666c7 100644
--- a/drivers/mtd/maps/integrator-flash.c
+++ b/drivers/mtd/maps/integrator-flash.c
@@ -105,7 +105,7 @@ static int armflash_probe(struct platform_device *dev)
 	info->map.bankwidth	= plat->width;
 	info->map.phys		= res->start;
 	info->map.virt		= base;
-	info->map.name		= dev->dev.bus_id;
+	info->map.name		= dev_name(&dev->dev);
 	info->map.set_vpp	= armflash_set_vpp;
 
 	simple_map_init(&info->map);
diff --git a/drivers/mtd/maps/ixp2000.c b/drivers/mtd/maps/ixp2000.c
index dcdb1f17577d..d4fb9a3ab4df 100644
--- a/drivers/mtd/maps/ixp2000.c
+++ b/drivers/mtd/maps/ixp2000.c
@@ -170,7 +170,7 @@ static int ixp2000_flash_probe(struct platform_device *dev)
 		err = -ENOMEM;
 		goto Error;
 	}
-	memzero(info, sizeof(struct ixp2000_flash_info));
+	memset(info, 0, sizeof(struct ixp2000_flash_info));
 
 	platform_set_drvdata(dev, info);
 
@@ -188,7 +188,7 @@ static int ixp2000_flash_probe(struct platform_device *dev)
  	 */
 	info->map.map_priv_2 = (unsigned long) ixp_data->bank_setup;
 
-	info->map.name = dev->dev.bus_id;
+	info->map.name = dev_name(&dev->dev);
 	info->map.read = ixp2000_flash_read8;
 	info->map.write = ixp2000_flash_write8;
 	info->map.copy_from = ixp2000_flash_copy_from;
@@ -196,7 +196,7 @@ static int ixp2000_flash_probe(struct platform_device *dev)
 
 	info->res = request_mem_region(dev->resource->start,
 			dev->resource->end - dev->resource->start + 1,
-			dev->dev.bus_id);
+			dev_name(&dev->dev));
 	if (!info->res) {
 		dev_err(&dev->dev, "Could not reserve memory region\n");
 		err = -ENOMEM;
diff --git a/drivers/mtd/maps/ixp4xx.c b/drivers/mtd/maps/ixp4xx.c
index 9c7a5fbd4e51..7214b876feba 100644
--- a/drivers/mtd/maps/ixp4xx.c
+++ b/drivers/mtd/maps/ixp4xx.c
@@ -201,7 +201,7 @@ static int ixp4xx_flash_probe(struct platform_device *dev)
 		err = -ENOMEM;
 		goto Error;
 	}
-	memzero(info, sizeof(struct ixp4xx_flash_info));
+	memset(info, 0, sizeof(struct ixp4xx_flash_info));
 
 	platform_set_drvdata(dev, info);
 
@@ -218,7 +218,7 @@ static int ixp4xx_flash_probe(struct platform_device *dev)
 	 * handle that.
 	 */
 	info->map.bankwidth = 2;
-	info->map.name = dev->dev.bus_id;
+	info->map.name = dev_name(&dev->dev);
 	info->map.read = ixp4xx_read16,
 	info->map.write = ixp4xx_probe_write16,
 	info->map.copy_from = ixp4xx_copy_from,
diff --git a/drivers/mtd/maps/omap_nor.c b/drivers/mtd/maps/omap_nor.c
index 05f276af15da..7e50e9b1b781 100644
--- a/drivers/mtd/maps/omap_nor.c
+++ b/drivers/mtd/maps/omap_nor.c
@@ -101,7 +101,7 @@ static int __init omapflash_probe(struct platform_device *pdev)
 		err = -ENOMEM;
 		goto out_release_mem_region;
 	}
-	info->map.name		= pdev->dev.bus_id;
+	info->map.name		= dev_name(&pdev->dev);
 	info->map.phys		= res->start;
 	info->map.size		= size;
 	info->map.bankwidth	= pdata->width;
diff --git a/drivers/mtd/maps/physmap.c b/drivers/mtd/maps/physmap.c
index 42d844f8f6bf..8e2ee92c949c 100644
--- a/drivers/mtd/maps/physmap.c
+++ b/drivers/mtd/maps/physmap.c
@@ -116,14 +116,14 @@ static int physmap_flash_probe(struct platform_device *dev)
 
 		info->res = request_mem_region(dev->resource[i].start,
 					       dev->resource[i].end - dev->resource[i].start + 1,
-					       dev->dev.bus_id);
+					       dev_name(&dev->dev));
 		if (info->res == NULL) {
 			dev_err(&dev->dev, "Could not reserve memory region\n");
 			err = -ENOMEM;
 			goto err_out;
 		}
 
-		info->map[i].name = dev->dev.bus_id;
+		info->map[i].name = dev_name(&dev->dev);
 		info->map[i].phys = dev->resource[i].start;
 		info->map[i].size = dev->resource[i].end - dev->resource[i].start + 1;
 		info->map[i].bankwidth = physmap_data->width;
@@ -158,7 +158,7 @@ static int physmap_flash_probe(struct platform_device *dev)
 		 * We detected multiple devices. Concatenate them together.
 		 */
 #ifdef CONFIG_MTD_CONCAT
-		info->cmtd = mtd_concat_create(info->mtd, devices_found, dev->dev.bus_id);
+		info->cmtd = mtd_concat_create(info->mtd, devices_found, dev_name(&dev->dev));
 		if (info->cmtd == NULL)
 			err = -ENXIO;
 #else
diff --git a/drivers/mtd/maps/physmap_of.c b/drivers/mtd/maps/physmap_of.c
index 5fcfec034a94..fbf0ca939d72 100644
--- a/drivers/mtd/maps/physmap_of.c
+++ b/drivers/mtd/maps/physmap_of.c
@@ -183,7 +183,7 @@ static int __devinit of_flash_probe(struct of_device *dev,
 
 	err = -EBUSY;
 	info->res = request_mem_region(res.start, res.end - res.start + 1,
-				       dev->dev.bus_id);
+				       dev_name(&dev->dev));
 	if (!info->res)
 		goto err_out;
 
@@ -194,7 +194,7 @@ static int __devinit of_flash_probe(struct of_device *dev,
 		goto err_out;
 	}
 
-	info->map.name = dev->dev.bus_id;
+	info->map.name = dev_name(&dev->dev);
 	info->map.phys = res.start;
 	info->map.size = res.end - res.start + 1;
 	info->map.bankwidth = *width;
diff --git a/drivers/mtd/mtdconcat.c b/drivers/mtd/mtdconcat.c
index 789842d0e6f2..1a05cf37851e 100644
--- a/drivers/mtd/mtdconcat.c
+++ b/drivers/mtd/mtdconcat.c
@@ -691,7 +691,7 @@ static int concat_block_markbad(struct mtd_info *mtd, loff_t ofs)
  */
 struct mtd_info *mtd_concat_create(struct mtd_info *subdev[],	/* subdevices to concatenate */
 				   int num_devs,	/* number of subdevices      */
-				   char *name)
+				   const char *name)
 {				/* name for the new device   */
 	int i;
 	size_t size;
diff --git a/drivers/mtd/nand/fsl_upm.c b/drivers/mtd/nand/fsl_upm.c
index 024e3fffd4bb..09c1fef5fd36 100644
--- a/drivers/mtd/nand/fsl_upm.c
+++ b/drivers/mtd/nand/fsl_upm.c
@@ -220,7 +220,7 @@ static int __devinit fun_probe(struct of_device *ofdev,
 
 	fun->rnb_gpio = of_get_gpio(ofdev->node, 0);
 	if (fun->rnb_gpio >= 0) {
-		ret = gpio_request(fun->rnb_gpio, ofdev->dev.bus_id);
+		ret = gpio_request(fun->rnb_gpio, dev_name(&ofdev->dev));
 		if (ret) {
 			dev_err(&ofdev->dev, "can't request RNB gpio\n");
 			goto err2;
diff --git a/drivers/mtd/nand/plat_nand.c b/drivers/mtd/nand/plat_nand.c
index f674c5427b17..75f9f4874ecf 100644
--- a/drivers/mtd/nand/plat_nand.c
+++ b/drivers/mtd/nand/plat_nand.c
@@ -54,7 +54,7 @@ static int __init plat_nand_probe(struct platform_device *pdev)
 	data->chip.priv = &data;
 	data->mtd.priv = &data->chip;
 	data->mtd.owner = THIS_MODULE;
-	data->mtd.name = pdev->dev.bus_id;
+	data->mtd.name = dev_name(&pdev->dev);
 
 	data->chip.IO_ADDR_R = data->io_base;
 	data->chip.IO_ADDR_W = data->io_base;
diff --git a/drivers/mtd/nand/pxa3xx_nand.c b/drivers/mtd/nand/pxa3xx_nand.c
index c0fa9c9edf08..ce5752ab579d 100644
--- a/drivers/mtd/nand/pxa3xx_nand.c
+++ b/drivers/mtd/nand/pxa3xx_nand.c
@@ -20,8 +20,8 @@
 #include <linux/mtd/partitions.h>
 #include <linux/io.h>
 #include <linux/irq.h>
-#include <asm/dma.h>
 
+#include <mach/dma.h>
 #include <mach/pxa-regs.h>
 #include <mach/pxa3xx_nand.h>
 
@@ -1079,7 +1079,7 @@ static int pxa3xx_nand_probe(struct platform_device *pdev)
 	this = &info->nand_chip;
 	mtd->priv = info;
 
-	info->clk = clk_get(&pdev->dev, "NANDCLK");
+	info->clk = clk_get(&pdev->dev, NULL);
 	if (IS_ERR(info->clk)) {
 		dev_err(&pdev->dev, "failed to get nand clock\n");
 		ret = PTR_ERR(info->clk);
diff --git a/drivers/mtd/nand/s3c2410.c b/drivers/mtd/nand/s3c2410.c
index 556139ed1fdf..8e375d5fe231 100644
--- a/drivers/mtd/nand/s3c2410.c
+++ b/drivers/mtd/nand/s3c2410.c
@@ -45,8 +45,8 @@
 
 #include <asm/io.h>
 
-#include <asm/plat-s3c/regs-nand.h>
-#include <asm/plat-s3c/nand.h>
+#include <plat/regs-nand.h>
+#include <plat/nand.h>
 
 #ifdef CONFIG_MTD_NAND_S3C2410_HWECC
 static int hardware_ecc = 1;
@@ -818,7 +818,7 @@ static int s3c24xx_nand_probe(struct platform_device *pdev,
 		goto exit_error;
 	}
 
-	memzero(info, sizeof(*info));
+	memset(info, 0, sizeof(*info));
 	platform_set_drvdata(pdev, info);
 
 	spin_lock_init(&info->controller.lock);
@@ -883,7 +883,7 @@ static int s3c24xx_nand_probe(struct platform_device *pdev,
 		goto exit_error;
 	}
 
-	memzero(info->mtds, size);
+	memset(info->mtds, 0, size);
 
 	/* initialise all possible chips */
 
diff --git a/drivers/mtd/nand/tmio_nand.c b/drivers/mtd/nand/tmio_nand.c
index edb1e322113d..daa6a4c3b8ce 100644
--- a/drivers/mtd/nand/tmio_nand.c
+++ b/drivers/mtd/nand/tmio_nand.c
@@ -433,7 +433,7 @@ static int tmio_probe(struct platform_device *dev)
 	nand_chip->chip_delay = 15;
 
 	retval = request_irq(irq, &tmio_irq,
-				IRQF_DISABLED, dev->dev.bus_id, tmio);
+				IRQF_DISABLED, dev_name(&dev->dev), tmio);
 	if (retval) {
 		dev_err(&dev->dev, "request_irq error %d\n", retval);
 		goto err_irq;
diff --git a/drivers/mtd/onenand/generic.c b/drivers/mtd/onenand/generic.c
index ad81ab8e95e2..5b69e7773c6c 100644
--- a/drivers/mtd/onenand/generic.c
+++ b/drivers/mtd/onenand/generic.c
@@ -63,7 +63,7 @@ static int __devinit generic_onenand_probe(struct device *dev)
 	info->onenand.mmcontrol = pdata->mmcontrol;
 	info->onenand.irq = platform_get_irq(pdev, 0);
 
-	info->mtd.name = pdev->dev.bus_id;
+	info->mtd.name = dev_name(&pdev->dev);
 	info->mtd.priv = &info->onenand;
 	info->mtd.owner = THIS_MODULE;
 
diff --git a/drivers/mtd/onenand/omap2.c b/drivers/mtd/onenand/omap2.c
index e39b21d3e168..4e5a6bcbe0d4 100644
--- a/drivers/mtd/onenand/omap2.c
+++ b/drivers/mtd/onenand/omap2.c
@@ -669,7 +669,7 @@ static int __devinit omap2_onenand_probe(struct platform_device *pdev)
 		 c->onenand.base);
 
 	c->pdev = pdev;
-	c->mtd.name = pdev->dev.bus_id;
+	c->mtd.name = dev_name(&pdev->dev);
 	c->mtd.priv = &c->onenand;
 	c->mtd.owner = THIS_MODULE;
 
diff --git a/drivers/mtd/ubi/build.c b/drivers/mtd/ubi/build.c
index c7630a228310..3a8a80cf2822 100644
--- a/drivers/mtd/ubi/build.c
+++ b/drivers/mtd/ubi/build.c
@@ -280,7 +280,7 @@ static int ubi_sysfs_init(struct ubi_device *ubi)
 	ubi->dev.release = dev_release;
 	ubi->dev.devt = ubi->cdev.dev;
 	ubi->dev.class = ubi_class;
-	sprintf(&ubi->dev.bus_id[0], UBI_NAME_STR"%d", ubi->ubi_num);
+	dev_set_name(&ubi->dev, UBI_NAME_STR"%d", ubi->ubi_num);
 	err = device_register(&ubi->dev);
 	if (err)
 		return err;
diff --git a/drivers/mtd/ubi/vmt.c b/drivers/mtd/ubi/vmt.c
index 3531ca9a1e24..22e1d7398fce 100644
--- a/drivers/mtd/ubi/vmt.c
+++ b/drivers/mtd/ubi/vmt.c
@@ -329,7 +329,7 @@ int ubi_create_volume(struct ubi_device *ubi, struct ubi_mkvol_req *req)
 	vol->dev.devt = dev;
 	vol->dev.class = ubi_class;
 
-	sprintf(&vol->dev.bus_id[0], "%s_%d", ubi->ubi_name, vol->vol_id);
+	dev_set_name(&vol->dev, "%s_%d", ubi->ubi_name, vol->vol_id);
 	err = device_register(&vol->dev);
 	if (err) {
 		ubi_err("cannot register device");
@@ -678,7 +678,7 @@ int ubi_add_volume(struct ubi_device *ubi, struct ubi_volume *vol)
 	vol->dev.parent = &ubi->dev;
 	vol->dev.devt = dev;
 	vol->dev.class = ubi_class;
-	sprintf(&vol->dev.bus_id[0], "%s_%d", ubi->ubi_name, vol->vol_id);
+	dev_set_name(&vol->dev, "%s_%d", ubi->ubi_name, vol->vol_id);
 	err = device_register(&vol->dev);
 	if (err)
 		goto out_gluebi;
diff --git a/drivers/net/bnx2.c b/drivers/net/bnx2.c
index d07e3f148951..a1a3d0e5d2b4 100644
--- a/drivers/net/bnx2.c
+++ b/drivers/net/bnx2.c
@@ -3144,6 +3144,28 @@ bnx2_has_work(struct bnx2_napi *bnapi)
 	return 0;
 }
 
+static void
+bnx2_chk_missed_msi(struct bnx2 *bp)
+{
+	struct bnx2_napi *bnapi = &bp->bnx2_napi[0];
+	u32 msi_ctrl;
+
+	if (bnx2_has_work(bnapi)) {
+		msi_ctrl = REG_RD(bp, BNX2_PCICFG_MSI_CONTROL);
+		if (!(msi_ctrl & BNX2_PCICFG_MSI_CONTROL_ENABLE))
+			return;
+
+		if (bnapi->last_status_idx == bp->idle_chk_status_idx) {
+			REG_WR(bp, BNX2_PCICFG_MSI_CONTROL, msi_ctrl &
+			       ~BNX2_PCICFG_MSI_CONTROL_ENABLE);
+			REG_WR(bp, BNX2_PCICFG_MSI_CONTROL, msi_ctrl);
+			bnx2_msi(bp->irq_tbl[0].vector, bnapi);
+		}
+	}
+
+	bp->idle_chk_status_idx = bnapi->last_status_idx;
+}
+
 static void bnx2_poll_link(struct bnx2 *bp, struct bnx2_napi *bnapi)
 {
 	struct status_block *sblk = bnapi->status_blk.msi;
@@ -3218,14 +3240,15 @@ static int bnx2_poll(struct napi_struct *napi, int budget)
 
 		work_done = bnx2_poll_work(bp, bnapi, work_done, budget);
 
-		if (unlikely(work_done >= budget))
-			break;
-
 		/* bnapi->last_status_idx is used below to tell the hw how
 		 * much work has been processed, so we must read it before
 		 * checking for more work.
 		 */
 		bnapi->last_status_idx = sblk->status_idx;
+
+		if (unlikely(work_done >= budget))
+			break;
+
 		rmb();
 		if (likely(!bnx2_has_work(bnapi))) {
 			netif_rx_complete(bp->dev, napi);
@@ -4570,6 +4593,8 @@ bnx2_init_chip(struct bnx2 *bp)
 	for (i = 0; i < BNX2_MAX_MSIX_VEC; i++)
 		bp->bnx2_napi[i].last_status_idx = 0;
 
+	bp->idle_chk_status_idx = 0xffff;
+
 	bp->rx_mode = BNX2_EMAC_RX_MODE_SORT_MODE;
 
 	/* Set up how to generate a link change interrupt. */
@@ -5718,6 +5743,10 @@ bnx2_timer(unsigned long data)
 	if (atomic_read(&bp->intr_sem) != 0)
 		goto bnx2_restart_timer;
 
+	if ((bp->flags & (BNX2_FLAG_USING_MSI | BNX2_FLAG_ONE_SHOT_MSI)) ==
+	     BNX2_FLAG_USING_MSI)
+		bnx2_chk_missed_msi(bp);
+
 	bnx2_send_heart_beat(bp);
 
 	bp->stats_blk->stat_FwRxDrop =
diff --git a/drivers/net/bnx2.h b/drivers/net/bnx2.h
index 617d95340160..0b032c3c7b61 100644
--- a/drivers/net/bnx2.h
+++ b/drivers/net/bnx2.h
@@ -378,6 +378,9 @@ struct l2_fhdr {
  *  pci_config_l definition
  *  offset: 0000
  */
+#define BNX2_PCICFG_MSI_CONTROL				0x00000058
+#define BNX2_PCICFG_MSI_CONTROL_ENABLE			 (1L<<16)
+
 #define BNX2_PCICFG_MISC_CONFIG				0x00000068
 #define BNX2_PCICFG_MISC_CONFIG_TARGET_BYTE_SWAP	 (1L<<2)
 #define BNX2_PCICFG_MISC_CONFIG_TARGET_MB_WORD_SWAP	 (1L<<3)
@@ -6863,6 +6866,9 @@ struct bnx2 {
 
 	u8			num_tx_rings;
 	u8			num_rx_rings;
+
+	u32			idle_chk_status_idx;
+
 };
 
 #define REG_RD(bp, offset)					\
diff --git a/drivers/net/cs89x0.c b/drivers/net/cs89x0.c
index 7107620f615d..0b729f7d91fc 100644
--- a/drivers/net/cs89x0.c
+++ b/drivers/net/cs89x0.c
@@ -170,11 +170,7 @@ static char version[] __initdata =
 /* The cs8900 has 4 IRQ pins, software selectable. cs8900_irq_map maps
    them to system IRQ numbers. This mapping is card specific and is set to
    the configuration of the Cirrus Eval board for this chip. */
-#ifdef CONFIG_ARCH_CLPS7500
-static unsigned int netcard_portlist[] __used __initdata =
-   { 0x80090303, 0x300, 0x320, 0x340, 0x360, 0x200, 0x220, 0x240, 0x260, 0x280, 0x2a0, 0x2c0, 0x2e0, 0};
-static unsigned int cs8900_irq_map[] = {12,0,0,0};
-#elif defined(CONFIG_SH_HICOSH4)
+#if defined(CONFIG_SH_HICOSH4)
 static unsigned int netcard_portlist[] __used __initdata =
    { 0x0300, 0};
 static unsigned int cs8900_irq_map[] = {1,0,0,0};
diff --git a/drivers/net/e1000e/netdev.c b/drivers/net/e1000e/netdev.c
index 122539a0e1fe..cab10122ebca 100644
--- a/drivers/net/e1000e/netdev.c
+++ b/drivers/net/e1000e/netdev.c
@@ -4759,7 +4759,7 @@ static int __devinit e1000_probe(struct pci_dev *pdev,
 		}
 	}
 
-	err = pci_request_selected_regions(pdev,
+	err = pci_request_selected_regions_exclusive(pdev,
 	                                  pci_select_bars(pdev, IORESOURCE_MEM),
 	                                  e1000e_driver_name);
 	if (err)
diff --git a/drivers/net/enc28j60.c b/drivers/net/enc28j60.c
index e1b441effbbe..c414554ac321 100644
--- a/drivers/net/enc28j60.c
+++ b/drivers/net/enc28j60.c
@@ -568,6 +568,17 @@ static u16 erxrdpt_workaround(u16 next_packet_ptr, u16 start, u16 end)
 	return erxrdpt;
 }
 
+/*
+ * Calculate wrap around when reading beyond the end of the RX buffer
+ */
+static u16 rx_packet_start(u16 ptr)
+{
+	if (ptr + RSV_SIZE > RXEND_INIT)
+		return (ptr + RSV_SIZE) - (RXEND_INIT - RXSTART_INIT + 1);
+	else
+		return ptr + RSV_SIZE;
+}
+
 static void nolock_rxfifo_init(struct enc28j60_net *priv, u16 start, u16 end)
 {
 	u16 erxrdpt;
@@ -938,8 +949,9 @@ static void enc28j60_hw_rx(struct net_device *ndev)
 			skb->dev = ndev;
 			skb_reserve(skb, NET_IP_ALIGN);
 			/* copy the packet from the receive buffer */
-			enc28j60_mem_read(priv, priv->next_pk_ptr + sizeof(rsv),
-					len, skb_put(skb, len));
+			enc28j60_mem_read(priv,
+				rx_packet_start(priv->next_pk_ptr),
+				len, skb_put(skb, len));
 			if (netif_msg_pktdata(priv))
 				dump_packet(__func__, skb->len, skb->data);
 			skb->protocol = eth_type_trans(skb, ndev);
diff --git a/drivers/net/irda/pxaficp_ir.c b/drivers/net/irda/pxaficp_ir.c
index c5b02b66f756..0e081292f4f7 100644
--- a/drivers/net/irda/pxaficp_ir.c
+++ b/drivers/net/irda/pxaficp_ir.c
@@ -22,9 +22,53 @@
 #include <net/irda/wrapper.h>
 #include <net/irda/irda_device.h>
 
-#include <asm/dma.h>
+#include <mach/dma.h>
 #include <mach/irda.h>
+#include <mach/hardware.h>
 #include <mach/pxa-regs.h>
+#include <mach/regs-uart.h>
+
+#define FICP		__REG(0x40800000)  /* Start of FICP area */
+#define ICCR0		__REG(0x40800000)  /* ICP Control Register 0 */
+#define ICCR1		__REG(0x40800004)  /* ICP Control Register 1 */
+#define ICCR2		__REG(0x40800008)  /* ICP Control Register 2 */
+#define ICDR		__REG(0x4080000c)  /* ICP Data Register */
+#define ICSR0		__REG(0x40800014)  /* ICP Status Register 0 */
+#define ICSR1		__REG(0x40800018)  /* ICP Status Register 1 */
+
+#define ICCR0_AME	(1 << 7)	/* Address match enable */
+#define ICCR0_TIE	(1 << 6)	/* Transmit FIFO interrupt enable */
+#define ICCR0_RIE	(1 << 5)	/* Recieve FIFO interrupt enable */
+#define ICCR0_RXE	(1 << 4)	/* Receive enable */
+#define ICCR0_TXE	(1 << 3)	/* Transmit enable */
+#define ICCR0_TUS	(1 << 2)	/* Transmit FIFO underrun select */
+#define ICCR0_LBM	(1 << 1)	/* Loopback mode */
+#define ICCR0_ITR	(1 << 0)	/* IrDA transmission */
+
+#define ICCR2_RXP       (1 << 3)	/* Receive Pin Polarity select */
+#define ICCR2_TXP       (1 << 2)	/* Transmit Pin Polarity select */
+#define ICCR2_TRIG	(3 << 0)	/* Receive FIFO Trigger threshold */
+#define ICCR2_TRIG_8    (0 << 0)	/* 	>= 8 bytes */
+#define ICCR2_TRIG_16   (1 << 0)	/*	>= 16 bytes */
+#define ICCR2_TRIG_32   (2 << 0)	/*	>= 32 bytes */
+
+#ifdef CONFIG_PXA27x
+#define ICSR0_EOC	(1 << 6)	/* DMA End of Descriptor Chain */
+#endif
+#define ICSR0_FRE	(1 << 5)	/* Framing error */
+#define ICSR0_RFS	(1 << 4)	/* Receive FIFO service request */
+#define ICSR0_TFS	(1 << 3)	/* Transnit FIFO service request */
+#define ICSR0_RAB	(1 << 2)	/* Receiver abort */
+#define ICSR0_TUR	(1 << 1)	/* Trunsmit FIFO underun */
+#define ICSR0_EIF	(1 << 0)	/* End/Error in FIFO */
+
+#define ICSR1_ROR	(1 << 6)	/* Receiver FIFO underrun  */
+#define ICSR1_CRE	(1 << 5)	/* CRC error */
+#define ICSR1_EOF	(1 << 4)	/* End of frame */
+#define ICSR1_TNF	(1 << 3)	/* Transmit FIFO not full */
+#define ICSR1_RNE	(1 << 2)	/* Receive FIFO not empty */
+#define ICSR1_TBY	(1 << 1)	/* Tramsmiter busy flag */
+#define ICSR1_RSY	(1 << 0)	/* Recevier synchronized flag */
 
 #define IrSR_RXPL_NEG_IS_ZERO (1<<4)
 #define IrSR_RXPL_POS_IS_ZERO 0x0
diff --git a/drivers/net/irda/sa1100_ir.c b/drivers/net/irda/sa1100_ir.c
index a95188948de7..0813b5295f52 100644
--- a/drivers/net/irda/sa1100_ir.c
+++ b/drivers/net/irda/sa1100_ir.c
@@ -36,7 +36,7 @@
 #include <net/irda/irda_device.h>
 
 #include <asm/irq.h>
-#include <asm/dma.h>
+#include <mach/dma.h>
 #include <mach/hardware.h>
 #include <asm/mach/irda.h>
 
diff --git a/drivers/net/netx-eth.c b/drivers/net/netx-eth.c
index b9bed82e1d21..b289a0a2b945 100644
--- a/drivers/net/netx-eth.c
+++ b/drivers/net/netx-eth.c
@@ -401,6 +401,8 @@ static int netx_eth_drv_probe(struct platform_device *pdev)
 	priv->xmac_base = priv->xc->xmac_base;
 	priv->sram_base = priv->xc->sram_base;
 
+	spin_lock_init(&priv->lock);
+
 	ret = pfifo_request(PFIFO_MASK(priv->id));
 	if (ret) {
 		printk("unable to request PFIFO\n");
diff --git a/drivers/net/smc911x.h b/drivers/net/smc911x.h
index cc7d85bdfb3e..870b4c33f108 100644
--- a/drivers/net/smc911x.h
+++ b/drivers/net/smc911x.h
@@ -200,6 +200,9 @@ static inline void SMC_outsl(struct smc911x_local *lp, int reg,
 
 
 #ifdef SMC_USE_PXA_DMA
+
+#include <mach/dma.h>
+
 /*
  * Define the request and free functions
  * These are unfortunately architecture specific as no generic allocation
diff --git a/drivers/net/smc91x.h b/drivers/net/smc91x.h
index a07cc9351c6b..37e2cb4f4f88 100644
--- a/drivers/net/smc91x.h
+++ b/drivers/net/smc91x.h
@@ -527,7 +527,8 @@ struct smc_local {
  * as RX which can overrun memory and lose packets.
  */
 #include <linux/dma-mapping.h>
-#include <asm/dma.h>
+#include <mach/dma.h>
+#include <mach/hardware.h>
 #include <mach/pxa-regs.h>
 
 #ifdef SMC_insl
diff --git a/drivers/net/usb/kaweth.c b/drivers/net/usb/kaweth.c
index fdbf3be24fda..92a0aee89a85 100644
--- a/drivers/net/usb/kaweth.c
+++ b/drivers/net/usb/kaweth.c
@@ -283,9 +283,9 @@ static int kaweth_control(struct kaweth_device *kaweth,
 
 	dr->bRequestType= requesttype;
 	dr->bRequest = request;
-	dr->wValue = cpu_to_le16p(&value);
-	dr->wIndex = cpu_to_le16p(&index);
-	dr->wLength = cpu_to_le16p(&size);
+	dr->wValue = cpu_to_le16(value);
+	dr->wIndex = cpu_to_le16(index);
+	dr->wLength = cpu_to_le16(size);
 
 	return kaweth_internal_control_msg(kaweth->dev,
 					pipe,
diff --git a/drivers/net/usb/pegasus.c b/drivers/net/usb/pegasus.c
index 7914867110ed..32cc6617cc71 100644
--- a/drivers/net/usb/pegasus.c
+++ b/drivers/net/usb/pegasus.c
@@ -149,8 +149,8 @@ static int get_registers(pegasus_t * pegasus, __u16 indx, __u16 size,
 	pegasus->dr.bRequestType = PEGASUS_REQT_READ;
 	pegasus->dr.bRequest = PEGASUS_REQ_GET_REGS;
 	pegasus->dr.wValue = cpu_to_le16(0);
-	pegasus->dr.wIndex = cpu_to_le16p(&indx);
-	pegasus->dr.wLength = cpu_to_le16p(&size);
+	pegasus->dr.wIndex = cpu_to_le16(indx);
+	pegasus->dr.wLength = cpu_to_le16(size);
 	pegasus->ctrl_urb->transfer_buffer_length = size;
 
 	usb_fill_control_urb(pegasus->ctrl_urb, pegasus->usb,
@@ -207,8 +207,8 @@ static int set_registers(pegasus_t * pegasus, __u16 indx, __u16 size,
 	pegasus->dr.bRequestType = PEGASUS_REQT_WRITE;
 	pegasus->dr.bRequest = PEGASUS_REQ_SET_REGS;
 	pegasus->dr.wValue = cpu_to_le16(0);
-	pegasus->dr.wIndex = cpu_to_le16p(&indx);
-	pegasus->dr.wLength = cpu_to_le16p(&size);
+	pegasus->dr.wIndex = cpu_to_le16(indx);
+	pegasus->dr.wLength = cpu_to_le16(size);
 	pegasus->ctrl_urb->transfer_buffer_length = size;
 
 	usb_fill_control_urb(pegasus->ctrl_urb, pegasus->usb,
@@ -260,7 +260,7 @@ static int set_register(pegasus_t * pegasus, __u16 indx, __u8 data)
 	pegasus->dr.bRequestType = PEGASUS_REQT_WRITE;
 	pegasus->dr.bRequest = PEGASUS_REQ_SET_REG;
 	pegasus->dr.wValue = cpu_to_le16(data);
-	pegasus->dr.wIndex = cpu_to_le16p(&indx);
+	pegasus->dr.wIndex = cpu_to_le16(indx);
 	pegasus->dr.wLength = cpu_to_le16(1);
 	pegasus->ctrl_urb->transfer_buffer_length = 1;
 
@@ -475,7 +475,7 @@ static inline void get_node_id(pegasus_t * pegasus, __u8 * id)
 
 	for (i = 0; i < 3; i++) {
 		read_eprom_word(pegasus, i, &w16);
-		((__le16 *) id)[i] = cpu_to_le16p(&w16);
+		((__le16 *) id)[i] = cpu_to_le16(w16);
 	}
 }
 
diff --git a/drivers/net/wireless/ipw2200.c b/drivers/net/wireless/ipw2200.c
index dcce3542d5a7..7a9f901d4ff6 100644
--- a/drivers/net/wireless/ipw2200.c
+++ b/drivers/net/wireless/ipw2200.c
@@ -3897,6 +3897,7 @@ static int ipw_disassociate(void *data)
 	if (!(priv->status & (STATUS_ASSOCIATED | STATUS_ASSOCIATING)))
 		return 0;
 	ipw_send_disassociate(data, 0);
+	netif_carrier_off(priv->net_dev);
 	return 1;
 }
 
@@ -10190,6 +10191,9 @@ static int ipw_tx_skb(struct ipw_priv *priv, struct ieee80211_txb *txb,
 	u16 remaining_bytes;
 	int fc;
 
+	if (!(priv->status & STATUS_ASSOCIATED))
+		goto drop;
+
 	hdr_len = ieee80211_get_hdrlen(le16_to_cpu(hdr->frame_ctl));
 	switch (priv->ieee->iw_mode) {
 	case IW_MODE_ADHOC:
diff --git a/drivers/net/wireless/iwlwifi/iwl-core.c b/drivers/net/wireless/iwlwifi/iwl-core.c
index 4c312c55f90c..01a845851338 100644
--- a/drivers/net/wireless/iwlwifi/iwl-core.c
+++ b/drivers/net/wireless/iwlwifi/iwl-core.c
@@ -290,6 +290,9 @@ void iwl_clear_stations_table(struct iwl_priv *priv)
 	priv->num_stations = 0;
 	memset(priv->stations, 0, sizeof(priv->stations));
 
+	/* clean ucode key table bit map */
+	priv->ucode_key_table = 0;
+
 	spin_unlock_irqrestore(&priv->sta_lock, flags);
 }
 EXPORT_SYMBOL(iwl_clear_stations_table);
diff --git a/drivers/net/wireless/iwlwifi/iwl-sta.c b/drivers/net/wireless/iwlwifi/iwl-sta.c
index 61797f3f8d5c..26f7084d3011 100644
--- a/drivers/net/wireless/iwlwifi/iwl-sta.c
+++ b/drivers/net/wireless/iwlwifi/iwl-sta.c
@@ -475,7 +475,7 @@ static int iwl_get_free_ucode_key_index(struct iwl_priv *priv)
 		if (!test_and_set_bit(i, &priv->ucode_key_table))
 			return i;
 
-	return -1;
+	return WEP_INVALID_OFFSET;
 }
 
 int iwl_send_static_wepkey_cmd(struct iwl_priv *priv, u8 send_if_empty)
@@ -620,6 +620,9 @@ static int iwl_set_wep_dynamic_key_info(struct iwl_priv *priv,
 	/* else, we are overriding an existing key => no need to allocated room
 	 * in uCode. */
 
+	WARN(priv->stations[sta_id].sta.key.key_offset == WEP_INVALID_OFFSET,
+		"no space for new kew");
+
 	priv->stations[sta_id].sta.key.key_flags = key_flags;
 	priv->stations[sta_id].sta.sta.modify_mask = STA_MODIFY_KEY_MASK;
 	priv->stations[sta_id].sta.mode = STA_CONTROL_MODIFY_MSK;
@@ -637,6 +640,7 @@ static int iwl_set_ccmp_dynamic_key_info(struct iwl_priv *priv,
 {
 	unsigned long flags;
 	__le16 key_flags = 0;
+	int ret;
 
 	key_flags |= (STA_KEY_FLG_CCMP | STA_KEY_FLG_MAP_KEY_MSK);
 	key_flags |= cpu_to_le16(keyconf->keyidx << STA_KEY_FLG_KEYID_POS);
@@ -664,14 +668,18 @@ static int iwl_set_ccmp_dynamic_key_info(struct iwl_priv *priv,
 	/* else, we are overriding an existing key => no need to allocated room
 	 * in uCode. */
 
+	WARN(priv->stations[sta_id].sta.key.key_offset == WEP_INVALID_OFFSET,
+		"no space for new kew");
+
 	priv->stations[sta_id].sta.key.key_flags = key_flags;
 	priv->stations[sta_id].sta.sta.modify_mask = STA_MODIFY_KEY_MASK;
 	priv->stations[sta_id].sta.mode = STA_CONTROL_MODIFY_MSK;
 
+	ret = iwl_send_add_sta(priv, &priv->stations[sta_id].sta, CMD_ASYNC);
+
 	spin_unlock_irqrestore(&priv->sta_lock, flags);
 
-	IWL_DEBUG_INFO("hwcrypto: modify ucode station key info\n");
-	return iwl_send_add_sta(priv, &priv->stations[sta_id].sta, CMD_ASYNC);
+	return ret;
 }
 
 static int iwl_set_tkip_dynamic_key_info(struct iwl_priv *priv,
@@ -696,6 +704,9 @@ static int iwl_set_tkip_dynamic_key_info(struct iwl_priv *priv,
 	/* else, we are overriding an existing key => no need to allocated room
 	 * in uCode. */
 
+	WARN(priv->stations[sta_id].sta.key.key_offset == WEP_INVALID_OFFSET,
+		"no space for new kew");
+
 	/* This copy is acutally not needed: we get the key with each TX */
 	memcpy(priv->stations[sta_id].keyinfo.key, keyconf->key, 16);
 
@@ -734,6 +745,13 @@ int iwl_remove_dynamic_key(struct iwl_priv *priv,
 		return 0;
 	}
 
+	if (priv->stations[sta_id].sta.key.key_offset == WEP_INVALID_OFFSET) {
+		IWL_WARNING("Removing wrong key %d 0x%x\n",
+			    keyconf->keyidx, key_flags);
+		spin_unlock_irqrestore(&priv->sta_lock, flags);
+		return 0;
+	}
+
 	if (!test_and_clear_bit(priv->stations[sta_id].sta.key.key_offset,
 		&priv->ucode_key_table))
 		IWL_ERROR("index %d not used in uCode key table.\n",
diff --git a/drivers/net/wireless/zd1211rw/zd_mac.c b/drivers/net/wireless/zd1211rw/zd_mac.c
index fe1867b25ff7..cac732f4047f 100644
--- a/drivers/net/wireless/zd1211rw/zd_mac.c
+++ b/drivers/net/wireless/zd1211rw/zd_mac.c
@@ -615,7 +615,7 @@ static int filter_ack(struct ieee80211_hw *hw, struct ieee80211_hdr *rx_hdr,
 		struct ieee80211_hdr *tx_hdr;
 
 		tx_hdr = (struct ieee80211_hdr *)skb->data;
-		if (likely(!compare_ether_addr(tx_hdr->addr2, rx_hdr->addr1)))
+		if (likely(!memcmp(tx_hdr->addr2, rx_hdr->addr1, ETH_ALEN)))
 		{
 			__skb_unlink(skb, q);
 			tx_status(hw, skb, IEEE80211_TX_STAT_ACK, stats->signal, 1);
diff --git a/drivers/of/base.c b/drivers/of/base.c
index 7c79e94a35ea..4f884a358a7b 100644
--- a/drivers/of/base.c
+++ b/drivers/of/base.c
@@ -329,6 +329,41 @@ struct device_node *of_find_compatible_node(struct device_node *from,
 EXPORT_SYMBOL(of_find_compatible_node);
 
 /**
+ *	of_find_node_with_property - Find a node which has a property with
+ *                                   the given name.
+ *	@from:		The node to start searching from or NULL, the node
+ *			you pass will not be searched, only the next one
+ *			will; typically, you pass what the previous call
+ *			returned. of_node_put() will be called on it
+ *	@prop_name:	The name of the property to look for.
+ *
+ *	Returns a node pointer with refcount incremented, use
+ *	of_node_put() on it when done.
+ */
+struct device_node *of_find_node_with_property(struct device_node *from,
+	const char *prop_name)
+{
+	struct device_node *np;
+	struct property *pp;
+
+	read_lock(&devtree_lock);
+	np = from ? from->allnext : allnodes;
+	for (; np; np = np->allnext) {
+		for (pp = np->properties; pp != 0; pp = pp->next) {
+			if (of_prop_cmp(pp->name, prop_name) == 0) {
+				of_node_get(np);
+				goto out;
+			}
+		}
+	}
+out:
+	of_node_put(from);
+	read_unlock(&devtree_lock);
+	return np;
+}
+EXPORT_SYMBOL(of_find_node_with_property);
+
+/**
  * of_match_node - Tell if an device_node has a matching of_match structure
  *	@matches:	array of of device match structures to search in
  *	@node:		the of device structure to match against
diff --git a/drivers/of/gpio.c b/drivers/of/gpio.c
index 7cd7301b5839..a4ba217116eb 100644
--- a/drivers/of/gpio.c
+++ b/drivers/of/gpio.c
@@ -19,14 +19,17 @@
 #include <asm/prom.h>
 
 /**
- * of_get_gpio - Get a GPIO number from the device tree to use with GPIO API
+ * of_get_gpio_flags - Get a GPIO number and flags to use with GPIO API
  * @np:		device node to get GPIO from
  * @index:	index of the GPIO
+ * @flags:	a flags pointer to fill in
  *
  * Returns GPIO number to use with Linux generic GPIO API, or one of the errno
- * value on the error condition.
+ * value on the error condition. If @flags is not NULL the function also fills
+ * in flags for the GPIO.
  */
-int of_get_gpio(struct device_node *np, int index)
+int of_get_gpio_flags(struct device_node *np, int index,
+		      enum of_gpio_flags *flags)
 {
 	int ret;
 	struct device_node *gc;
@@ -59,7 +62,11 @@ int of_get_gpio(struct device_node *np, int index)
 		goto err1;
 	}
 
-	ret = of_gc->xlate(of_gc, np, gpio_spec);
+	/* .xlate might decide to not fill in the flags, so clear it. */
+	if (flags)
+		*flags = 0;
+
+	ret = of_gc->xlate(of_gc, np, gpio_spec, flags);
 	if (ret < 0)
 		goto err1;
 
@@ -70,26 +77,41 @@ err0:
 	pr_debug("%s exited with status %d\n", __func__, ret);
 	return ret;
 }
-EXPORT_SYMBOL(of_get_gpio);
+EXPORT_SYMBOL(of_get_gpio_flags);
 
 /**
- * of_gpio_simple_xlate - translate gpio_spec to the GPIO number
+ * of_gpio_simple_xlate - translate gpio_spec to the GPIO number and flags
  * @of_gc:	pointer to the of_gpio_chip structure
  * @np:		device node of the GPIO chip
  * @gpio_spec:	gpio specifier as found in the device tree
+ * @flags:	a flags pointer to fill in
  *
  * This is simple translation function, suitable for the most 1:1 mapped
  * gpio chips. This function performs only one sanity check: whether gpio
  * is less than ngpios (that is specified in the gpio_chip).
  */
 int of_gpio_simple_xlate(struct of_gpio_chip *of_gc, struct device_node *np,
-			 const void *gpio_spec)
+			 const void *gpio_spec, enum of_gpio_flags *flags)
 {
 	const u32 *gpio = gpio_spec;
 
+	/*
+	 * We're discouraging gpio_cells < 2, since that way you'll have to
+	 * write your own xlate function (that will have to retrive the GPIO
+	 * number and the flags from a single gpio cell -- this is possible,
+	 * but not recommended).
+	 */
+	if (of_gc->gpio_cells < 2) {
+		WARN_ON(1);
+		return -EINVAL;
+	}
+
 	if (*gpio > of_gc->gc.ngpio)
 		return -EINVAL;
 
+	if (flags)
+		*flags = gpio[1];
+
 	return *gpio;
 }
 EXPORT_SYMBOL(of_gpio_simple_xlate);
diff --git a/drivers/of/of_i2c.c b/drivers/of/of_i2c.c
index 24bbef777c19..e1b0ad6e918f 100644
--- a/drivers/of/of_i2c.c
+++ b/drivers/of/of_i2c.c
@@ -24,6 +24,7 @@ void of_register_i2c_devices(struct i2c_adapter *adap,
 
 	for_each_child_of_node(adap_node, node) {
 		struct i2c_board_info info = {};
+		struct dev_archdata dev_ad = {};
 		const u32 *addr;
 		int len;
 
@@ -41,6 +42,9 @@ void of_register_i2c_devices(struct i2c_adapter *adap,
 
 		info.addr = *addr;
 
+		dev_archdata_set_node(&dev_ad, node);
+		info.archdata = &dev_ad;
+
 		request_module("%s", info.type);
 
 		result = i2c_new_device(adap, &info);
@@ -51,6 +55,13 @@ void of_register_i2c_devices(struct i2c_adapter *adap,
 			irq_dispose_mapping(info.irq);
 			continue;
 		}
+
+		/*
+		 * Get the node to not lose the dev_archdata->of_node.
+		 * Currently there is no way to put it back, as well as no
+		 * of_unregister_i2c_devices() call.
+		 */
+		of_node_get(node);
 	}
 }
 EXPORT_SYMBOL(of_register_i2c_devices);
diff --git a/drivers/pci/Kconfig b/drivers/pci/Kconfig
index e1ca42591ac4..2a4501dd2515 100644
--- a/drivers/pci/Kconfig
+++ b/drivers/pci/Kconfig
@@ -42,6 +42,15 @@ config PCI_DEBUG
 
 	  When in doubt, say N.
 
+config PCI_STUB
+	tristate "PCI Stub driver"
+	depends on PCI
+	help
+	  Say Y or M here if you want be able to reserve a PCI device
+	  when it is going to be assigned to a guest operating system.
+
+	  When in doubt, say N.
+
 config HT_IRQ
 	bool "Interrupts on hypertransport devices"
 	default y
diff --git a/drivers/pci/Makefile b/drivers/pci/Makefile
index af3bfe22847b..3d07ce24f6a8 100644
--- a/drivers/pci/Makefile
+++ b/drivers/pci/Makefile
@@ -53,6 +53,8 @@ obj-$(CONFIG_HOTPLUG) += setup-bus.o
 
 obj-$(CONFIG_PCI_SYSCALL) += syscall.o
 
+obj-$(CONFIG_PCI_STUB) += pci-stub.o
+
 ifeq ($(CONFIG_PCI_DEBUG),y)
 EXTRA_CFLAGS += -DDEBUG
 endif
diff --git a/drivers/pci/bus.c b/drivers/pci/bus.c
index 999cc4088b59..3e1c135b174a 100644
--- a/drivers/pci/bus.c
+++ b/drivers/pci/bus.c
@@ -158,6 +158,10 @@ void pci_bus_add_devices(struct pci_bus *bus)
 				dev_err(&dev->dev,
 					"Error creating cpulistaffinity"
 					" file, continuing...\n");
+
+			/* Create legacy_io and legacy_mem files for this bus */
+			pci_create_legacy_files(child_bus);
+
 		}
 	}
 }
diff --git a/drivers/pci/hotplug/acpiphp_glue.c b/drivers/pci/hotplug/acpiphp_glue.c
index 955aae4071f7..e8cef99abddb 100644
--- a/drivers/pci/hotplug/acpiphp_glue.c
+++ b/drivers/pci/hotplug/acpiphp_glue.c
@@ -74,7 +74,7 @@ static void handle_hotplug_event_func(acpi_handle handle, u32 type, void *contex
  * Ejectable slot should satisfy at least these conditions:
  *
  *  1. has _ADR method
- *  2. has _EJ0 method
+ *  2. has _EJ0 method or _RMV method
  *
  * optionally
  *
@@ -87,18 +87,25 @@ static int is_ejectable(acpi_handle handle)
 {
 	acpi_status status;
 	acpi_handle tmp;
+	unsigned long long removable;
 
 	status = acpi_get_handle(handle, "_ADR", &tmp);
-	if (ACPI_FAILURE(status)) {
+	if (ACPI_FAILURE(status))
 		return 0;
-	}
 
 	status = acpi_get_handle(handle, "_EJ0", &tmp);
-	if (ACPI_FAILURE(status)) {
-		return 0;
+	if (ACPI_SUCCESS(status))
+		return 1;
+
+	status = acpi_get_handle(handle, "_RMV", &tmp);
+	if (ACPI_SUCCESS(status)) {
+		status = acpi_evaluate_integer(handle, "_RMV", NULL,
+					       &removable);
+		if (ACPI_SUCCESS(status) && removable)
+			return 1;
 	}
 
-	return 1;
+	return 0;
 }
 
 
@@ -185,16 +192,10 @@ register_slot(acpi_handle handle, u32 lvl, void *context, void **rv)
 	unsigned long long adr, sun;
 	int device, function, retval;
 
-	status = acpi_evaluate_integer(handle, "_ADR", NULL, &adr);
-
-	if (ACPI_FAILURE(status))
-		return AE_OK;
-
-	status = acpi_get_handle(handle, "_EJ0", &tmp);
-
-	if (ACPI_FAILURE(status) && !(is_dock_device(handle)))
+	if (!is_ejectable(handle) && !is_dock_device(handle))
 		return AE_OK;
 
+	acpi_evaluate_integer(handle, "_ADR", NULL, &adr);
 	device = (adr >> 16) & 0xffff;
 	function = adr & 0xffff;
 
@@ -205,7 +206,8 @@ register_slot(acpi_handle handle, u32 lvl, void *context, void **rv)
 	INIT_LIST_HEAD(&newfunc->sibling);
 	newfunc->handle = handle;
 	newfunc->function = function;
-	if (ACPI_SUCCESS(status))
+
+	if (ACPI_SUCCESS(acpi_get_handle(handle, "_EJ0", &tmp)))
 		newfunc->flags = FUNC_HAS_EJ0;
 
 	if (ACPI_SUCCESS(acpi_get_handle(handle, "_STA", &tmp)))
diff --git a/drivers/pci/hotplug/acpiphp_ibm.c b/drivers/pci/hotplug/acpiphp_ibm.c
index 881fdd2b7313..5befa7e379b7 100644
--- a/drivers/pci/hotplug/acpiphp_ibm.c
+++ b/drivers/pci/hotplug/acpiphp_ibm.c
@@ -271,7 +271,7 @@ static void ibm_handle_events(acpi_handle handle, u32 event, void *context)
 		dbg("%s: generationg bus event\n", __func__);
 		acpi_bus_generate_proc_event(note->device, note->event, detail);
 		acpi_bus_generate_netlink_event(note->device->pnp.device_class,
-						  note->device->dev.bus_id,
+						  dev_name(&note->device->dev),
 						  note->event, detail);
 	} else
 		note->event = event;
diff --git a/drivers/pci/hotplug/fakephp.c b/drivers/pci/hotplug/fakephp.c
index 3a2637a00934..b0e7de9e536d 100644
--- a/drivers/pci/hotplug/fakephp.c
+++ b/drivers/pci/hotplug/fakephp.c
@@ -324,6 +324,7 @@ static int disable_slot(struct hotplug_slot *slot)
 
 		if (test_and_set_bit(0, &dslot->removed)) {
 			dbg("Slot already scheduled for removal\n");
+			pci_dev_put(dev);
 			return -ENODEV;
 		}
 
diff --git a/drivers/pci/hotplug/pciehp_ctrl.c b/drivers/pci/hotplug/pciehp_ctrl.c
index fead63c6b49e..ff4034502d24 100644
--- a/drivers/pci/hotplug/pciehp_ctrl.c
+++ b/drivers/pci/hotplug/pciehp_ctrl.c
@@ -178,15 +178,14 @@ static void set_slot_off(struct controller *ctrl, struct slot * pslot)
 				 "Issue of Slot Power Off command failed\n");
 			return;
 		}
+		/*
+		 * After turning power off, we must wait for at least 1 second
+		 * before taking any action that relies on power having been
+		 * removed from the slot/adapter.
+		 */
+		msleep(1000);
 	}
 
-	/*
-	 * After turning power off, we must wait for at least 1 second
-	 * before taking any action that relies on power having been
-	 * removed from the slot/adapter.
-	 */
-	msleep(1000);
-
 	if (PWR_LED(ctrl))
 		pslot->hpc_ops->green_led_off(pslot);
 
@@ -286,15 +285,14 @@ static int remove_board(struct slot *p_slot)
 				 "Issue of Slot Disable command failed\n");
 			return retval;
 		}
+		/*
+		 * After turning power off, we must wait for at least 1 second
+		 * before taking any action that relies on power having been
+		 * removed from the slot/adapter.
+		 */
+		msleep(1000);
 	}
 
-	/*
-	 * After turning power off, we must wait for at least 1 second
-	 * before taking any action that relies on power having been
-	 * removed from the slot/adapter.
-	 */
-	msleep(1000);
-
 	if (PWR_LED(ctrl))
 		/* turn off Green LED */
 		p_slot->hpc_ops->green_led_off(p_slot);
diff --git a/drivers/pci/hotplug/rpadlpar_core.c b/drivers/pci/hotplug/rpadlpar_core.c
index 9c2a22fed18b..4e3e0382c16e 100644
--- a/drivers/pci/hotplug/rpadlpar_core.c
+++ b/drivers/pci/hotplug/rpadlpar_core.c
@@ -14,6 +14,9 @@
  *      as published by the Free Software Foundation; either version
  *      2 of the License, or (at your option) any later version.
  */
+
+#undef DEBUG
+
 #include <linux/init.h>
 #include <linux/pci.h>
 #include <linux/string.h>
@@ -151,20 +154,20 @@ static void dlpar_pci_add_bus(struct device_node *dn)
 		return;
 	}
 
+	/* Scan below the new bridge */
 	if (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE ||
 	    dev->hdr_type == PCI_HEADER_TYPE_CARDBUS)
 		of_scan_pci_bridge(dn, dev);
 
-	pcibios_fixup_new_pci_devices(dev->subordinate);
-
-	/* Claim new bus resources */
-	pcibios_claim_one_bus(dev->bus);
-
 	/* Map IO space for child bus, which may or may not succeed */
 	pcibios_map_io_space(dev->subordinate);
 
-	/* Add new devices to global lists.  Register in proc, sysfs. */
-	pci_bus_add_devices(phb->bus);
+	/* Finish adding it : resource allocation, adding devices, etc...
+	 * Note that we need to perform the finish pass on the -parent-
+	 * bus of the EADS bridge so the bridge device itself gets
+	 * properly added
+	 */
+	pcibios_finish_adding_to_bus(phb->bus);
 }
 
 static int dlpar_add_pci_slot(char *drc_name, struct device_node *dn)
@@ -203,27 +206,6 @@ static int dlpar_add_pci_slot(char *drc_name, struct device_node *dn)
 	return 0;
 }
 
-static int dlpar_remove_root_bus(struct pci_controller *phb)
-{
-	struct pci_bus *phb_bus;
-	int rc;
-
-	phb_bus = phb->bus;
-	if (!(list_empty(&phb_bus->children) &&
-	      list_empty(&phb_bus->devices))) {
-		return -EBUSY;
-	}
-
-	rc = pcibios_remove_root_bus(phb);
-	if (rc)
-		return -EIO;
-
-	device_unregister(phb_bus->bridge);
-	pci_remove_bus(phb_bus);
-
-	return 0;
-}
-
 static int dlpar_remove_phb(char *drc_name, struct device_node *dn)
 {
 	struct slot *slot;
@@ -235,18 +217,15 @@ static int dlpar_remove_phb(char *drc_name, struct device_node *dn)
 
 	/* If pci slot is hotplugable, use hotplug to remove it */
 	slot = find_php_slot(dn);
-	if (slot) {
-		if (rpaphp_deregister_slot(slot)) {
-			printk(KERN_ERR
-				"%s: unable to remove hotplug slot %s\n",
-				__func__, drc_name);
-			return -EIO;
-		}
+	if (slot && rpaphp_deregister_slot(slot)) {
+		printk(KERN_ERR "%s: unable to remove hotplug slot %s\n",
+		       __func__, drc_name);
+		return -EIO;
 	}
 
 	pdn = dn->data;
 	BUG_ON(!pdn || !pdn->phb);
-	rc = dlpar_remove_root_bus(pdn->phb);
+	rc = remove_phb_dynamic(pdn->phb);
 	if (rc < 0)
 		return rc;
 
@@ -378,26 +357,38 @@ int dlpar_remove_pci_slot(char *drc_name, struct device_node *dn)
 	if (!bus)
 		return -EINVAL;
 
-	/* If pci slot is hotplugable, use hotplug to remove it */
+	pr_debug("PCI: Removing PCI slot below EADS bridge %s\n",
+		 bus->self ? pci_name(bus->self) : "<!PHB!>");
+
 	slot = find_php_slot(dn);
 	if (slot) {
+		pr_debug("PCI: Removing hotplug slot for %04x:%02x...\n",
+			 pci_domain_nr(bus), bus->number);
+
 		if (rpaphp_deregister_slot(slot)) {
 			printk(KERN_ERR
 				"%s: unable to remove hotplug slot %s\n",
 				__func__, drc_name);
 			return -EIO;
 		}
-	} else
-		pcibios_remove_pci_devices(bus);
+	}
+
+	/* Remove all devices below slot */
+	pcibios_remove_pci_devices(bus);
 
+	/* Unmap PCI IO space */
 	if (pcibios_unmap_io_space(bus)) {
 		printk(KERN_ERR "%s: failed to unmap bus range\n",
 			__func__);
 		return -ERANGE;
 	}
 
+	/* Remove the EADS bridge device itself */
 	BUG_ON(!bus->self);
+	pr_debug("PCI: Now removing bridge device %s\n", pci_name(bus->self));
+	eeh_remove_bus_device(bus->self);
 	pci_remove_bus_device(bus->self);
+
 	return 0;
 }
 
diff --git a/drivers/pci/irq.c b/drivers/pci/irq.c
index 6441dfa969a3..de01174aff06 100644
--- a/drivers/pci/irq.c
+++ b/drivers/pci/irq.c
@@ -15,7 +15,7 @@ static void pci_note_irq_problem(struct pci_dev *pdev, const char *reason)
 
 	dev_printk(KERN_ERR, &pdev->dev,
 		   "Potentially misrouted IRQ (Bridge %s %04x:%04x)\n",
-		   parent->dev.bus_id, parent->vendor, parent->device);
+		   dev_name(&parent->dev), parent->vendor, parent->device);
 	dev_printk(KERN_ERR, &pdev->dev, "%s\n", reason);
 	dev_printk(KERN_ERR, &pdev->dev, "Please report to linux-kernel@vger.kernel.org\n");
 	WARN_ON(1);
diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c
index 74801f7df9c9..0e8dae10d6a7 100644
--- a/drivers/pci/msi.c
+++ b/drivers/pci/msi.c
@@ -755,28 +755,19 @@ void pci_no_msi(void)
 	pci_msi_enable = 0;
 }
 
-void pci_msi_init_pci_dev(struct pci_dev *dev)
-{
-	INIT_LIST_HEAD(&dev->msi_list);
-}
-
-#ifdef CONFIG_ACPI
-#include <linux/acpi.h>
-#include <linux/pci-acpi.h>
-static void __devinit msi_acpi_init(void)
+/**
+ * pci_msi_enabled - is MSI enabled?
+ *
+ * Returns true if MSI has not been disabled by the command-line option
+ * pci=nomsi.
+ **/
+int pci_msi_enabled(void)
 {
-	if (acpi_pci_disabled)
-		return;
-	pci_osc_support_set(OSC_MSI_SUPPORT);
-	pcie_osc_support_set(OSC_MSI_SUPPORT);
+	return pci_msi_enable;
 }
-#else
-static inline void msi_acpi_init(void) { }
-#endif /* CONFIG_ACPI */
+EXPORT_SYMBOL(pci_msi_enabled);
 
-void __devinit msi_init(void)
+void pci_msi_init_pci_dev(struct pci_dev *dev)
 {
-	if (!pci_msi_enable)
-		return;
-	msi_acpi_init();
+	INIT_LIST_HEAD(&dev->msi_list);
 }
diff --git a/drivers/pci/pci-acpi.c b/drivers/pci/pci-acpi.c
index ae5ec76dca77..3582512e7226 100644
--- a/drivers/pci/pci-acpi.c
+++ b/drivers/pci/pci-acpi.c
@@ -24,13 +24,14 @@ struct acpi_osc_data {
 	acpi_handle handle;
 	u32 support_set;
 	u32 control_set;
+	u32 control_query;
+	int is_queried;
 	struct list_head sibiling;
 };
 static LIST_HEAD(acpi_osc_data_list);
 
 struct acpi_osc_args {
 	u32 capbuf[3];
-	u32 ctrl_result;
 };
 
 static DEFINE_MUTEX(pci_acpi_lock);
@@ -56,7 +57,7 @@ static u8 OSC_UUID[16] = {0x5B, 0x4D, 0xDB, 0x33, 0xF7, 0x1F, 0x1C, 0x40,
 			  0x96, 0x57, 0x74, 0x41, 0xC0, 0x3D, 0xD7, 0x66};
 
 static acpi_status acpi_run_osc(acpi_handle handle,
-				struct acpi_osc_args *osc_args)
+				struct acpi_osc_args *osc_args, u32 *retval)
 {
 	acpi_status status;
 	struct acpi_object_list input;
@@ -112,8 +113,7 @@ static acpi_status acpi_run_osc(acpi_handle handle,
 		goto out_kfree;
 	}
 out_success:
-	osc_args->ctrl_result =
-		*((u32 *)(out_obj->buffer.pointer + 8));
+	*retval = *((u32 *)(out_obj->buffer.pointer + 8));
 	status = AE_OK;
 
 out_kfree:
@@ -121,11 +121,10 @@ out_kfree:
 	return status;
 }
 
-static acpi_status __acpi_query_osc(u32 flags, struct acpi_osc_data *osc_data,
-				    u32 *result)
+static acpi_status __acpi_query_osc(u32 flags, struct acpi_osc_data *osc_data)
 {
 	acpi_status status;
-	u32 support_set;
+	u32 support_set, result;
 	struct acpi_osc_args osc_args;
 
 	/* do _OSC query for all possible controls */
@@ -134,56 +133,45 @@ static acpi_status __acpi_query_osc(u32 flags, struct acpi_osc_data *osc_data,
 	osc_args.capbuf[OSC_SUPPORT_TYPE] = support_set;
 	osc_args.capbuf[OSC_CONTROL_TYPE] = OSC_CONTROL_MASKS;
 
-	status = acpi_run_osc(osc_data->handle, &osc_args);
+	status = acpi_run_osc(osc_data->handle, &osc_args, &result);
 	if (ACPI_SUCCESS(status)) {
 		osc_data->support_set = support_set;
-		*result = osc_args.ctrl_result;
+		osc_data->control_query = result;
+		osc_data->is_queried = 1;
 	}
 
 	return status;
 }
 
-static acpi_status acpi_query_osc(acpi_handle handle,
-				  u32 level, void *context, void **retval)
+/*
+ * pci_acpi_osc_support: Invoke _OSC indicating support for the given feature
+ * @flags: Bitmask of flags to support
+ *
+ * See the ACPI spec for the definition of the flags
+ */
+int pci_acpi_osc_support(acpi_handle handle, u32 flags)
 {
 	acpi_status status;
-	struct acpi_osc_data *osc_data;
-	u32 flags = (unsigned long)context, dummy;
 	acpi_handle tmp;
+	struct acpi_osc_data *osc_data;
+	int rc = 0;
 
 	status = acpi_get_handle(handle, "_OSC", &tmp);
 	if (ACPI_FAILURE(status))
-		return AE_OK;
+		return -ENOTTY;
 
 	mutex_lock(&pci_acpi_lock);
 	osc_data = acpi_get_osc_data(handle);
 	if (!osc_data) {
 		printk(KERN_ERR "acpi osc data array is full\n");
+		rc = -ENOMEM;
 		goto out;
 	}
 
-	__acpi_query_osc(flags, osc_data, &dummy);
+	__acpi_query_osc(flags, osc_data);
 out:
 	mutex_unlock(&pci_acpi_lock);
-	return AE_OK;
-}
-
-/**
- * __pci_osc_support_set - register OS support to Firmware
- * @flags: OS support bits
- * @hid: hardware ID
- *
- * Update OS support fields and doing a _OSC Query to obtain an update
- * from Firmware on supported control bits.
- **/
-acpi_status __pci_osc_support_set(u32 flags, const char *hid)
-{
-	if (!(flags & OSC_SUPPORT_MASKS))
-		return AE_TYPE;
-
-	acpi_get_devices(hid, acpi_query_osc,
-			 (void *)(unsigned long)flags, NULL);
-	return AE_OK;
+	return rc;
 }
 
 /**
@@ -196,7 +184,7 @@ acpi_status __pci_osc_support_set(u32 flags, const char *hid)
 acpi_status pci_osc_control_set(acpi_handle handle, u32 flags)
 {
 	acpi_status status;
-	u32 ctrlset, control_set, result;
+	u32 control_req, control_set, result;
 	acpi_handle tmp;
 	struct acpi_osc_data *osc_data;
 	struct acpi_osc_args osc_args;
@@ -213,28 +201,34 @@ acpi_status pci_osc_control_set(acpi_handle handle, u32 flags)
 		goto out;
 	}
 
-	ctrlset = (flags & OSC_CONTROL_MASKS);
-	if (!ctrlset) {
+	control_req = (flags & OSC_CONTROL_MASKS);
+	if (!control_req) {
 		status = AE_TYPE;
 		goto out;
 	}
 
-	status = __acpi_query_osc(osc_data->support_set, osc_data, &result);
-	if (ACPI_FAILURE(status))
+	/* No need to evaluate _OSC if the control was already granted. */
+	if ((osc_data->control_set & control_req) == control_req)
 		goto out;
 
-	if ((result & ctrlset) != ctrlset) {
+	if (!osc_data->is_queried) {
+		status = __acpi_query_osc(osc_data->support_set, osc_data);
+		if (ACPI_FAILURE(status))
+			goto out;
+	}
+
+	if ((osc_data->control_query & control_req) != control_req) {
 		status = AE_SUPPORT;
 		goto out;
 	}
 
-	control_set = osc_data->control_set | ctrlset;
+	control_set = osc_data->control_set | control_req;
 	osc_args.capbuf[OSC_QUERY_TYPE] = 0;
 	osc_args.capbuf[OSC_SUPPORT_TYPE] = osc_data->support_set;
 	osc_args.capbuf[OSC_CONTROL_TYPE] = control_set;
-	status = acpi_run_osc(handle, &osc_args);
+	status = acpi_run_osc(handle, &osc_args, &result);
 	if (ACPI_SUCCESS(status))
-		osc_data->control_set = control_set;
+		osc_data->control_set = result;
 out:
 	mutex_unlock(&pci_acpi_lock);
 	return status;
@@ -375,7 +369,7 @@ static int acpi_pci_find_root_bridge(struct device *dev, acpi_handle *handle)
 	 * The string should be the same as root bridge's name
 	 * Please look at 'pci_scan_bus_parented'
 	 */
-	num = sscanf(dev->bus_id, "pci%04x:%02x", &seg, &bus);
+	num = sscanf(dev_name(dev), "pci%04x:%02x", &seg, &bus);
 	if (num != 2)
 		return -ENODEV;
 	*handle = acpi_get_pci_rootbridge_handle(seg, bus);
diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c
index b4cdd690ae71..19f924429591 100644
--- a/drivers/pci/pci-driver.c
+++ b/drivers/pci/pci-driver.c
@@ -48,7 +48,7 @@ store_new_id(struct device_driver *driver, const char *buf, size_t count)
 		subdevice=PCI_ANY_ID, class=0, class_mask=0;
 	unsigned long driver_data=0;
 	int fields=0;
-	int retval;
+	int retval=0;
 
 	fields = sscanf(buf, "%x %x %x %x %x %x %lx",
 			&vendor, &device, &subvendor, &subdevice,
@@ -58,16 +58,18 @@ store_new_id(struct device_driver *driver, const char *buf, size_t count)
 
 	/* Only accept driver_data values that match an existing id_table
 	   entry */
-	retval = -EINVAL;
-	while (ids->vendor || ids->subvendor || ids->class_mask) {
-		if (driver_data == ids->driver_data) {
-			retval = 0;
-			break;
+	if (ids) {
+		retval = -EINVAL;
+		while (ids->vendor || ids->subvendor || ids->class_mask) {
+			if (driver_data == ids->driver_data) {
+				retval = 0;
+				break;
+			}
+			ids++;
 		}
-		ids++;
+		if (retval)	/* No match */
+			return retval;
 	}
-	if (retval)	/* No match */
-		return retval;
 
 	dynid = kzalloc(sizeof(*dynid), GFP_KERNEL);
 	if (!dynid)
@@ -433,8 +435,7 @@ static int pci_pm_suspend(struct device *dev)
 
 static int pci_pm_suspend_noirq(struct device *dev)
 {
-	struct pci_dev *pci_dev = to_pci_dev(dev);
-	struct pci_driver *drv = pci_dev->driver;
+	struct device_driver *drv = dev->driver;
 	int error = 0;
 
 	if (drv && drv->pm) {
@@ -469,11 +470,10 @@ static int pci_pm_resume(struct device *dev)
 
 static int pci_pm_resume_noirq(struct device *dev)
 {
-	struct pci_dev *pci_dev = to_pci_dev(dev);
-	struct pci_driver *drv = pci_dev->driver;
+	struct device_driver *drv = dev->driver;
 	int error = 0;
 
-	pci_fixup_device(pci_fixup_resume_early, pci_dev);
+	pci_fixup_device(pci_fixup_resume_early, to_pci_dev(dev));
 
 	if (drv && drv->pm) {
 		if (drv->pm->resume_noirq)
@@ -519,8 +519,7 @@ static int pci_pm_freeze(struct device *dev)
 
 static int pci_pm_freeze_noirq(struct device *dev)
 {
-	struct pci_dev *pci_dev = to_pci_dev(dev);
-	struct pci_driver *drv = pci_dev->driver;
+	struct device_driver *drv = dev->driver;
 	int error = 0;
 
 	if (drv && drv->pm) {
@@ -553,15 +552,14 @@ static int pci_pm_thaw(struct device *dev)
 
 static int pci_pm_thaw_noirq(struct device *dev)
 {
-	struct pci_dev *pci_dev = to_pci_dev(dev);
-	struct pci_driver *drv = pci_dev->driver;
+	struct device_driver *drv = dev->driver;
 	int error = 0;
 
 	if (drv && drv->pm) {
 		if (drv->pm->thaw_noirq)
 			error = drv->pm->thaw_noirq(dev);
 	} else {
-		pci_fixup_device(pci_fixup_resume_early, pci_dev);
+		pci_fixup_device(pci_fixup_resume_early, to_pci_dev(dev));
 		error = pci_legacy_resume_early(dev);
 	}
 
@@ -589,8 +587,7 @@ static int pci_pm_poweroff(struct device *dev)
 
 static int pci_pm_poweroff_noirq(struct device *dev)
 {
-	struct pci_dev *pci_dev = to_pci_dev(dev);
-	struct pci_driver *drv = pci_dev->driver;
+	struct device_driver *drv = dev->driver;
 	int error = 0;
 
 	if (drv && drv->pm) {
@@ -625,7 +622,7 @@ static int pci_pm_restore(struct device *dev)
 static int pci_pm_restore_noirq(struct device *dev)
 {
 	struct pci_dev *pci_dev = to_pci_dev(dev);
-	struct pci_driver *drv = pci_dev->driver;
+	struct device_driver *drv = dev->driver;
 	int error = 0;
 
 	pci_fixup_device(pci_fixup_resume, pci_dev);
@@ -654,17 +651,15 @@ static int pci_pm_restore_noirq(struct device *dev)
 
 #endif /* !CONFIG_HIBERNATION */
 
-struct pm_ext_ops pci_pm_ops = {
-	.base = {
-		.prepare = pci_pm_prepare,
-		.complete = pci_pm_complete,
-		.suspend = pci_pm_suspend,
-		.resume = pci_pm_resume,
-		.freeze = pci_pm_freeze,
-		.thaw = pci_pm_thaw,
-		.poweroff = pci_pm_poweroff,
-		.restore = pci_pm_restore,
-	},
+struct dev_pm_ops pci_dev_pm_ops = {
+	.prepare = pci_pm_prepare,
+	.complete = pci_pm_complete,
+	.suspend = pci_pm_suspend,
+	.resume = pci_pm_resume,
+	.freeze = pci_pm_freeze,
+	.thaw = pci_pm_thaw,
+	.poweroff = pci_pm_poweroff,
+	.restore = pci_pm_restore,
 	.suspend_noirq = pci_pm_suspend_noirq,
 	.resume_noirq = pci_pm_resume_noirq,
 	.freeze_noirq = pci_pm_freeze_noirq,
@@ -673,7 +668,7 @@ struct pm_ext_ops pci_pm_ops = {
 	.restore_noirq = pci_pm_restore_noirq,
 };
 
-#define PCI_PM_OPS_PTR	&pci_pm_ops
+#define PCI_PM_OPS_PTR	(&pci_dev_pm_ops)
 
 #else /* !CONFIG_PM_SLEEP */
 
@@ -703,9 +698,6 @@ int __pci_register_driver(struct pci_driver *drv, struct module *owner,
 	drv->driver.owner = owner;
 	drv->driver.mod_name = mod_name;
 
-	if (drv->pm)
-		drv->driver.pm = &drv->pm->base;
-
 	spin_lock_init(&drv->dynids.lock);
 	INIT_LIST_HEAD(&drv->dynids.list);
 
diff --git a/drivers/pci/pci-stub.c b/drivers/pci/pci-stub.c
new file mode 100644
index 000000000000..74fbec0bf6cb
--- /dev/null
+++ b/drivers/pci/pci-stub.c
@@ -0,0 +1,47 @@
+/* pci-stub - simple stub driver to reserve a pci device
+ *
+ * Copyright (C) 2008 Red Hat, Inc.
+ * Author:
+ * 	Chris Wright
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.
+ *
+ * Usage is simple, allocate a new id to the stub driver and bind the
+ * device to it.  For example:
+ * 
+ * # echo "8086 10f5" > /sys/bus/pci/drivers/pci-stub/new_id
+ * # echo -n 0000:00:19.0 > /sys/bus/pci/drivers/e1000e/unbind
+ * # echo -n 0000:00:19.0 > /sys/bus/pci/drivers/pci-stub/bind
+ * # ls -l /sys/bus/pci/devices/0000:00:19.0/driver
+ * .../0000:00:19.0/driver -> ../../../bus/pci/drivers/pci-stub
+ */
+
+#include <linux/module.h>
+#include <linux/pci.h>
+
+static int pci_stub_probe(struct pci_dev *dev, const struct pci_device_id *id)
+{
+	return 0;
+}
+
+static struct pci_driver stub_driver = {
+	.name		= "pci-stub",
+	.id_table	= NULL,	/* only dynamic id's */
+	.probe		= pci_stub_probe,
+};
+
+static int __init pci_stub_init(void)
+{
+	return pci_register_driver(&stub_driver);
+}
+
+static void __exit pci_stub_exit(void)
+{
+	pci_unregister_driver(&stub_driver);
+}
+
+module_init(pci_stub_init);
+module_exit(pci_stub_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Chris Wright <chrisw@sous-sol.org>");
diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c
index 5d72866897a8..c53631c565ef 100644
--- a/drivers/pci/pci-sysfs.c
+++ b/drivers/pci/pci-sysfs.c
@@ -569,7 +569,7 @@ void pci_remove_legacy_files(struct pci_bus *b)
 
 #ifdef HAVE_PCI_MMAP
 
-static int pci_mmap_fits(struct pci_dev *pdev, int resno, struct vm_area_struct *vma)
+int pci_mmap_fits(struct pci_dev *pdev, int resno, struct vm_area_struct *vma)
 {
 	unsigned long nr, start, size;
 
@@ -620,6 +620,9 @@ pci_mmap_resource(struct kobject *kobj, struct bin_attribute *attr,
 	vma->vm_pgoff += start >> PAGE_SHIFT;
 	mmap_type = res->flags & IORESOURCE_MEM ? pci_mmap_mem : pci_mmap_io;
 
+	if (res->flags & IORESOURCE_MEM && iomem_is_exclusive(start))
+		return -EINVAL;
+
 	return pci_mmap_page_range(pdev, vma, mmap_type, write_combine);
 }
 
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index 061d1ee0046a..3222f9022707 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -640,19 +640,14 @@ static int pci_save_pcie_state(struct pci_dev *dev)
 	int pos, i = 0;
 	struct pci_cap_saved_state *save_state;
 	u16 *cap;
-	int found = 0;
 
 	pos = pci_find_capability(dev, PCI_CAP_ID_EXP);
 	if (pos <= 0)
 		return 0;
 
 	save_state = pci_find_saved_cap(dev, PCI_CAP_ID_EXP);
-	if (!save_state)
-		save_state = kzalloc(sizeof(*save_state) + sizeof(u16) * 4, GFP_KERNEL);
-	else
-		found = 1;
 	if (!save_state) {
-		dev_err(&dev->dev, "out of memory in pci_save_pcie_state\n");
+		dev_err(&dev->dev, "buffer not found in %s\n", __FUNCTION__);
 		return -ENOMEM;
 	}
 	cap = (u16 *)&save_state->data[0];
@@ -661,9 +656,7 @@ static int pci_save_pcie_state(struct pci_dev *dev)
 	pci_read_config_word(dev, pos + PCI_EXP_LNKCTL, &cap[i++]);
 	pci_read_config_word(dev, pos + PCI_EXP_SLTCTL, &cap[i++]);
 	pci_read_config_word(dev, pos + PCI_EXP_RTCTL, &cap[i++]);
-	save_state->cap_nr = PCI_CAP_ID_EXP;
-	if (!found)
-		pci_add_saved_cap(dev, save_state);
+
 	return 0;
 }
 
@@ -688,30 +681,21 @@ static void pci_restore_pcie_state(struct pci_dev *dev)
 
 static int pci_save_pcix_state(struct pci_dev *dev)
 {
-	int pos, i = 0;
+	int pos;
 	struct pci_cap_saved_state *save_state;
-	u16 *cap;
-	int found = 0;
 
 	pos = pci_find_capability(dev, PCI_CAP_ID_PCIX);
 	if (pos <= 0)
 		return 0;
 
 	save_state = pci_find_saved_cap(dev, PCI_CAP_ID_PCIX);
-	if (!save_state)
-		save_state = kzalloc(sizeof(*save_state) + sizeof(u16), GFP_KERNEL);
-	else
-		found = 1;
 	if (!save_state) {
-		dev_err(&dev->dev, "out of memory in pci_save_pcie_state\n");
+		dev_err(&dev->dev, "buffer not found in %s\n", __FUNCTION__);
 		return -ENOMEM;
 	}
-	cap = (u16 *)&save_state->data[0];
 
-	pci_read_config_word(dev, pos + PCI_X_CMD, &cap[i++]);
-	save_state->cap_nr = PCI_CAP_ID_PCIX;
-	if (!found)
-		pci_add_saved_cap(dev, save_state);
+	pci_read_config_word(dev, pos + PCI_X_CMD, (u16 *)save_state->data);
+
 	return 0;
 }
 
@@ -1301,6 +1285,51 @@ void pci_pm_init(struct pci_dev *dev)
 }
 
 /**
+ * pci_add_save_buffer - allocate buffer for saving given capability registers
+ * @dev: the PCI device
+ * @cap: the capability to allocate the buffer for
+ * @size: requested size of the buffer
+ */
+static int pci_add_cap_save_buffer(
+	struct pci_dev *dev, char cap, unsigned int size)
+{
+	int pos;
+	struct pci_cap_saved_state *save_state;
+
+	pos = pci_find_capability(dev, cap);
+	if (pos <= 0)
+		return 0;
+
+	save_state = kzalloc(sizeof(*save_state) + size, GFP_KERNEL);
+	if (!save_state)
+		return -ENOMEM;
+
+	save_state->cap_nr = cap;
+	pci_add_saved_cap(dev, save_state);
+
+	return 0;
+}
+
+/**
+ * pci_allocate_cap_save_buffers - allocate buffers for saving capabilities
+ * @dev: the PCI device
+ */
+void pci_allocate_cap_save_buffers(struct pci_dev *dev)
+{
+	int error;
+
+	error = pci_add_cap_save_buffer(dev, PCI_CAP_ID_EXP, 4 * sizeof(u16));
+	if (error)
+		dev_err(&dev->dev,
+			"unable to preallocate PCI Express save buffer\n");
+
+	error = pci_add_cap_save_buffer(dev, PCI_CAP_ID_PCIX, sizeof(u16));
+	if (error)
+		dev_err(&dev->dev,
+			"unable to preallocate PCI-X save buffer\n");
+}
+
+/**
  * pci_enable_ari - enable ARI forwarding if hardware support it
  * @dev: the PCI device
  */
@@ -1395,7 +1424,8 @@ void pci_release_region(struct pci_dev *pdev, int bar)
  *	Returns 0 on success, or %EBUSY on error.  A warning
  *	message is also printed on failure.
  */
-int pci_request_region(struct pci_dev *pdev, int bar, const char *res_name)
+static int __pci_request_region(struct pci_dev *pdev, int bar, const char *res_name,
+									int exclusive)
 {
 	struct pci_devres *dr;
 
@@ -1408,8 +1438,9 @@ int pci_request_region(struct pci_dev *pdev, int bar, const char *res_name)
 			goto err_out;
 	}
 	else if (pci_resource_flags(pdev, bar) & IORESOURCE_MEM) {
-		if (!request_mem_region(pci_resource_start(pdev, bar),
-				        pci_resource_len(pdev, bar), res_name))
+		if (!__request_mem_region(pci_resource_start(pdev, bar),
+					pci_resource_len(pdev, bar), res_name,
+					exclusive))
 			goto err_out;
 	}
 
@@ -1428,6 +1459,47 @@ err_out:
 }
 
 /**
+ *	pci_request_region - Reserved PCI I/O and memory resource
+ *	@pdev: PCI device whose resources are to be reserved
+ *	@bar: BAR to be reserved
+ *	@res_name: Name to be associated with resource.
+ *
+ *	Mark the PCI region associated with PCI device @pdev BR @bar as
+ *	being reserved by owner @res_name.  Do not access any
+ *	address inside the PCI regions unless this call returns
+ *	successfully.
+ *
+ *	Returns 0 on success, or %EBUSY on error.  A warning
+ *	message is also printed on failure.
+ */
+int pci_request_region(struct pci_dev *pdev, int bar, const char *res_name)
+{
+	return __pci_request_region(pdev, bar, res_name, 0);
+}
+
+/**
+ *	pci_request_region_exclusive - Reserved PCI I/O and memory resource
+ *	@pdev: PCI device whose resources are to be reserved
+ *	@bar: BAR to be reserved
+ *	@res_name: Name to be associated with resource.
+ *
+ *	Mark the PCI region associated with PCI device @pdev BR @bar as
+ *	being reserved by owner @res_name.  Do not access any
+ *	address inside the PCI regions unless this call returns
+ *	successfully.
+ *
+ *	Returns 0 on success, or %EBUSY on error.  A warning
+ *	message is also printed on failure.
+ *
+ *	The key difference that _exclusive makes it that userspace is
+ *	explicitly not allowed to map the resource via /dev/mem or
+ * 	sysfs.
+ */
+int pci_request_region_exclusive(struct pci_dev *pdev, int bar, const char *res_name)
+{
+	return __pci_request_region(pdev, bar, res_name, IORESOURCE_EXCLUSIVE);
+}
+/**
  * pci_release_selected_regions - Release selected PCI I/O and memory resources
  * @pdev: PCI device whose resources were previously reserved
  * @bars: Bitmask of BARs to be released
@@ -1444,20 +1516,14 @@ void pci_release_selected_regions(struct pci_dev *pdev, int bars)
 			pci_release_region(pdev, i);
 }
 
-/**
- * pci_request_selected_regions - Reserve selected PCI I/O and memory resources
- * @pdev: PCI device whose resources are to be reserved
- * @bars: Bitmask of BARs to be requested
- * @res_name: Name to be associated with resource
- */
-int pci_request_selected_regions(struct pci_dev *pdev, int bars,
-				 const char *res_name)
+int __pci_request_selected_regions(struct pci_dev *pdev, int bars,
+				 const char *res_name, int excl)
 {
 	int i;
 
 	for (i = 0; i < 6; i++)
 		if (bars & (1 << i))
-			if(pci_request_region(pdev, i, res_name))
+			if (__pci_request_region(pdev, i, res_name, excl))
 				goto err_out;
 	return 0;
 
@@ -1469,6 +1535,26 @@ err_out:
 	return -EBUSY;
 }
 
+
+/**
+ * pci_request_selected_regions - Reserve selected PCI I/O and memory resources
+ * @pdev: PCI device whose resources are to be reserved
+ * @bars: Bitmask of BARs to be requested
+ * @res_name: Name to be associated with resource
+ */
+int pci_request_selected_regions(struct pci_dev *pdev, int bars,
+				 const char *res_name)
+{
+	return __pci_request_selected_regions(pdev, bars, res_name, 0);
+}
+
+int pci_request_selected_regions_exclusive(struct pci_dev *pdev,
+				 int bars, const char *res_name)
+{
+	return __pci_request_selected_regions(pdev, bars, res_name,
+			IORESOURCE_EXCLUSIVE);
+}
+
 /**
  *	pci_release_regions - Release reserved PCI I/O and memory resources
  *	@pdev: PCI device whose resources were previously reserved by pci_request_regions
@@ -1502,6 +1588,29 @@ int pci_request_regions(struct pci_dev *pdev, const char *res_name)
 }
 
 /**
+ *	pci_request_regions_exclusive - Reserved PCI I/O and memory resources
+ *	@pdev: PCI device whose resources are to be reserved
+ *	@res_name: Name to be associated with resource.
+ *
+ *	Mark all PCI regions associated with PCI device @pdev as
+ *	being reserved by owner @res_name.  Do not access any
+ *	address inside the PCI regions unless this call returns
+ *	successfully.
+ *
+ *	pci_request_regions_exclusive() will mark the region so that
+ * 	/dev/mem and the sysfs MMIO access will not be allowed.
+ *
+ *	Returns 0 on success, or %EBUSY on error.  A warning
+ *	message is also printed on failure.
+ */
+int pci_request_regions_exclusive(struct pci_dev *pdev, const char *res_name)
+{
+	return pci_request_selected_regions_exclusive(pdev,
+					((1 << 6) - 1), res_name);
+}
+
+
+/**
  * pci_set_master - enables bus-mastering for device dev
  * @dev: the PCI device to enable
  *
@@ -1751,24 +1860,7 @@ int pci_set_dma_seg_boundary(struct pci_dev *dev, unsigned long mask)
 EXPORT_SYMBOL(pci_set_dma_seg_boundary);
 #endif
 
-/**
- * pci_execute_reset_function() - Reset a PCI device function
- * @dev: Device function to reset
- *
- * Some devices allow an individual function to be reset without affecting
- * other functions in the same device.  The PCI device must be responsive
- * to PCI config space in order to use this function.
- *
- * The device function is presumed to be unused when this function is called.
- * Resetting the device will make the contents of PCI configuration space
- * random, so any caller of this must be prepared to reinitialise the
- * device including MSI, bus mastering, BARs, decoding IO and memory spaces,
- * etc.
- *
- * Returns 0 if the device function was successfully reset or -ENOTTY if the
- * device doesn't support resetting a single function.
- */
-int pci_execute_reset_function(struct pci_dev *dev)
+static int __pcie_flr(struct pci_dev *dev, int probe)
 {
 	u16 status;
 	u32 cap;
@@ -1780,6 +1872,9 @@ int pci_execute_reset_function(struct pci_dev *dev)
 	if (!(cap & PCI_EXP_DEVCAP_FLR))
 		return -ENOTTY;
 
+	if (probe)
+		return 0;
+
 	pci_block_user_cfg_access(dev);
 
 	/* Wait for Transaction Pending bit clean */
@@ -1802,6 +1897,80 @@ int pci_execute_reset_function(struct pci_dev *dev)
 	pci_unblock_user_cfg_access(dev);
 	return 0;
 }
+
+static int __pci_af_flr(struct pci_dev *dev, int probe)
+{
+	int cappos = pci_find_capability(dev, PCI_CAP_ID_AF);
+	u8 status;
+	u8 cap;
+
+	if (!cappos)
+		return -ENOTTY;
+	pci_read_config_byte(dev, cappos + PCI_AF_CAP, &cap);
+	if (!(cap & PCI_AF_CAP_TP) || !(cap & PCI_AF_CAP_FLR))
+		return -ENOTTY;
+
+	if (probe)
+		return 0;
+
+	pci_block_user_cfg_access(dev);
+
+	/* Wait for Transaction Pending bit clean */
+	msleep(100);
+	pci_read_config_byte(dev, cappos + PCI_AF_STATUS, &status);
+	if (status & PCI_AF_STATUS_TP) {
+		dev_info(&dev->dev, "Busy after 100ms while trying to"
+				" reset; sleeping for 1 second\n");
+		ssleep(1);
+		pci_read_config_byte(dev,
+				cappos + PCI_AF_STATUS, &status);
+		if (status & PCI_AF_STATUS_TP)
+			dev_info(&dev->dev, "Still busy after 1s; "
+					"proceeding with reset anyway\n");
+	}
+	pci_write_config_byte(dev, cappos + PCI_AF_CTRL, PCI_AF_CTRL_FLR);
+	mdelay(100);
+
+	pci_unblock_user_cfg_access(dev);
+	return 0;
+}
+
+static int __pci_reset_function(struct pci_dev *pdev, int probe)
+{
+	int res;
+
+	res = __pcie_flr(pdev, probe);
+	if (res != -ENOTTY)
+		return res;
+
+	res = __pci_af_flr(pdev, probe);
+	if (res != -ENOTTY)
+		return res;
+
+	return res;
+}
+
+/**
+ * pci_execute_reset_function() - Reset a PCI device function
+ * @dev: Device function to reset
+ *
+ * Some devices allow an individual function to be reset without affecting
+ * other functions in the same device.  The PCI device must be responsive
+ * to PCI config space in order to use this function.
+ *
+ * The device function is presumed to be unused when this function is called.
+ * Resetting the device will make the contents of PCI configuration space
+ * random, so any caller of this must be prepared to reinitialise the
+ * device including MSI, bus mastering, BARs, decoding IO and memory spaces,
+ * etc.
+ *
+ * Returns 0 if the device function was successfully reset or -ENOTTY if the
+ * device doesn't support resetting a single function.
+ */
+int pci_execute_reset_function(struct pci_dev *dev)
+{
+	return __pci_reset_function(dev, 0);
+}
 EXPORT_SYMBOL_GPL(pci_execute_reset_function);
 
 /**
@@ -1822,15 +1991,10 @@ EXPORT_SYMBOL_GPL(pci_execute_reset_function);
  */
 int pci_reset_function(struct pci_dev *dev)
 {
-	u32 cap;
-	int exppos = pci_find_capability(dev, PCI_CAP_ID_EXP);
-	int r;
+	int r = __pci_reset_function(dev, 1);
 
-	if (!exppos)
-		return -ENOTTY;
-	pci_read_config_dword(dev, exppos + PCI_EXP_DEVCAP, &cap);
-	if (!(cap & PCI_EXP_DEVCAP_FLR))
-		return -ENOTTY;
+	if (r < 0)
+		return r;
 
 	if (!dev->msi_enabled && !dev->msix_enabled && dev->irq != 0)
 		disable_irq(dev->irq);
@@ -2029,6 +2193,19 @@ static void __devinit pci_no_domains(void)
 #endif
 }
 
+/**
+ * pci_ext_cfg_enabled - can we access extended PCI config space?
+ * @dev: The PCI device of the root bridge.
+ *
+ * Returns 1 if we can access PCI extended config space (offsets
+ * greater than 0xff). This is the default implementation. Architecture
+ * implementations can override this.
+ */
+int __attribute__ ((weak)) pci_ext_cfg_avail(struct pci_dev *dev)
+{
+	return 1;
+}
+
 static int __devinit pci_init(void)
 {
 	struct pci_dev *dev = NULL;
@@ -2037,8 +2214,6 @@ static int __devinit pci_init(void)
 		pci_fixup_device(pci_fixup_final, dev);
 	}
 
-	msi_init();
-
 	return 0;
 }
 
@@ -2083,10 +2258,13 @@ EXPORT_SYMBOL(pci_find_capability);
 EXPORT_SYMBOL(pci_bus_find_capability);
 EXPORT_SYMBOL(pci_release_regions);
 EXPORT_SYMBOL(pci_request_regions);
+EXPORT_SYMBOL(pci_request_regions_exclusive);
 EXPORT_SYMBOL(pci_release_region);
 EXPORT_SYMBOL(pci_request_region);
+EXPORT_SYMBOL(pci_request_region_exclusive);
 EXPORT_SYMBOL(pci_release_selected_regions);
 EXPORT_SYMBOL(pci_request_selected_regions);
+EXPORT_SYMBOL(pci_request_selected_regions_exclusive);
 EXPORT_SYMBOL(pci_set_master);
 EXPORT_SYMBOL(pci_set_mwi);
 EXPORT_SYMBOL(pci_try_set_mwi);
diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index 9de87e9f98f5..7242b511a93f 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -10,6 +10,10 @@ extern int pci_uevent(struct device *dev, struct kobj_uevent_env *env);
 extern int pci_create_sysfs_dev_files(struct pci_dev *pdev);
 extern void pci_remove_sysfs_dev_files(struct pci_dev *pdev);
 extern void pci_cleanup_rom(struct pci_dev *dev);
+#ifdef HAVE_PCI_MMAP
+extern int pci_mmap_fits(struct pci_dev *pdev, int resno,
+			 struct vm_area_struct *vma);
+#endif
 
 /**
  * Firmware PM callbacks
@@ -41,6 +45,7 @@ struct pci_platform_pm_ops {
 
 extern int pci_set_platform_pm(struct pci_platform_pm_ops *ops);
 extern void pci_pm_init(struct pci_dev *dev);
+extern void pci_allocate_cap_save_buffers(struct pci_dev *dev);
 
 extern int pci_user_read_config_byte(struct pci_dev *dev, int where, u8 *val);
 extern int pci_user_read_config_word(struct pci_dev *dev, int where, u16 *val);
@@ -98,11 +103,9 @@ extern unsigned int pci_pm_d3_delay;
 #ifdef CONFIG_PCI_MSI
 void pci_no_msi(void);
 extern void pci_msi_init_pci_dev(struct pci_dev *dev);
-extern void __devinit msi_init(void);
 #else
 static inline void pci_no_msi(void) { }
 static inline void pci_msi_init_pci_dev(struct pci_dev *dev) { }
-static inline void msi_init(void) { }
 #endif
 
 #ifdef CONFIG_PCIEAER
diff --git a/drivers/pci/pcie/aer/aerdrv_acpi.c b/drivers/pci/pcie/aer/aerdrv_acpi.c
index 6dd7b13e9808..ebce26c37049 100644
--- a/drivers/pci/pcie/aer/aerdrv_acpi.c
+++ b/drivers/pci/pcie/aer/aerdrv_acpi.c
@@ -38,7 +38,6 @@ int aer_osc_setup(struct pcie_device *pciedev)
 
 	handle = acpi_find_root_bridge_handle(pdev);
 	if (handle) {
-		pcie_osc_support_set(OSC_EXT_PCI_CONFIG_SUPPORT);
 		status = pci_osc_control_set(handle,
 					OSC_PCI_EXPRESS_AER_CONTROL |
 					OSC_PCI_EXPRESS_CAP_STRUCTURE_CONTROL);
diff --git a/drivers/pci/pcie/aspm.c b/drivers/pci/pcie/aspm.c
index 8f63f4c6b85f..1089f8653d5a 100644
--- a/drivers/pci/pcie/aspm.c
+++ b/drivers/pci/pcie/aspm.c
@@ -834,24 +834,15 @@ void pcie_no_aspm(void)
 		aspm_disabled = 1;
 }
 
-#ifdef CONFIG_ACPI
-#include <acpi/acpi_bus.h>
-#include <linux/pci-acpi.h>
-static void pcie_aspm_platform_init(void)
-{
-	pcie_osc_support_set(OSC_ACTIVE_STATE_PWR_SUPPORT|
-		OSC_CLOCK_PWR_CAPABILITY_SUPPORT);
-}
-#else
-static inline void pcie_aspm_platform_init(void) { }
-#endif
-
-static int __init pcie_aspm_init(void)
+/**
+ * pcie_aspm_enabled - is PCIe ASPM enabled?
+ *
+ * Returns true if ASPM has not been disabled by the command-line option
+ * pcie_aspm=off.
+ **/
+int pcie_aspm_enabled(void)
 {
-	if (aspm_disabled)
-		return 0;
-	pcie_aspm_platform_init();
-	return 0;
+       return !aspm_disabled;
 }
+EXPORT_SYMBOL(pcie_aspm_enabled);
 
-fs_initcall(pcie_aspm_init);
diff --git a/drivers/pci/pcie/portdrv_core.c b/drivers/pci/pcie/portdrv_core.c
index 2e091e014829..75f501ab6468 100644
--- a/drivers/pci/pcie/portdrv_core.c
+++ b/drivers/pci/pcie/portdrv_core.c
@@ -224,7 +224,7 @@ static void pcie_device_init(struct pci_dev *parent, struct pcie_device *dev,
 	device->driver = NULL;
 	device->driver_data = NULL;
 	device->release = release_pcie_device;	/* callback to free pcie dev */
-	snprintf(device->bus_id, sizeof(device->bus_id), "%s:pcie%02x",
+	dev_set_name(device, "%s:pcie%02x",
 		 pci_name(parent), get_descriptor_id(port_type, service_type));
 	device->parent = &parent->dev;
 }
diff --git a/drivers/pci/pcie/portdrv_pci.c b/drivers/pci/pcie/portdrv_pci.c
index 584422da8d8b..0549fe2bdac9 100644
--- a/drivers/pci/pcie/portdrv_pci.c
+++ b/drivers/pci/pcie/portdrv_pci.c
@@ -50,7 +50,7 @@ static int pcie_portdrv_restore_config(struct pci_dev *dev)
 }
 
 #ifdef CONFIG_PM
-static int pcie_portdrv_suspend(struct pci_dev *dev, pm_message_t state)
+static int pcie_portdrv_suspend_late(struct pci_dev *dev, pm_message_t state)
 {
 	int ret = pcie_port_device_suspend(dev, state);
 
@@ -59,14 +59,14 @@ static int pcie_portdrv_suspend(struct pci_dev *dev, pm_message_t state)
 	return ret;
 }
 
-static int pcie_portdrv_resume(struct pci_dev *dev)
+static int pcie_portdrv_resume_early(struct pci_dev *dev)
 {
 	pcie_portdrv_restore_config(dev);
 	return pcie_port_device_resume(dev);
 }
 #else
-#define pcie_portdrv_suspend NULL
-#define pcie_portdrv_resume NULL
+#define pcie_portdrv_suspend_late NULL
+#define pcie_portdrv_resume_early NULL
 #endif
 
 /*
@@ -282,8 +282,8 @@ static struct pci_driver pcie_portdriver = {
 	.probe		= pcie_portdrv_probe,
 	.remove		= pcie_portdrv_remove,
 
-	.suspend	= pcie_portdrv_suspend,
-	.resume		= pcie_portdrv_resume,
+	.suspend_late	= pcie_portdrv_suspend_late,
+	.resume_early	= pcie_portdrv_resume_early,
 
 	.err_handler 	= &pcie_portdrv_err_handler,
 };
diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index 003a9b3c293f..4160069b7d39 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -412,7 +412,7 @@ static struct pci_bus *pci_alloc_child_bus(struct pci_bus *parent,
 	 * registered later in pci_bus_add_devices()
 	 */
 	child->dev.class = &pcibus_class;
-	sprintf(child->dev.bus_id, "%04x:%02x", pci_domain_nr(child), busnr);
+	dev_set_name(&child->dev, "%04x:%02x", pci_domain_nr(child), busnr);
 
 	/*
 	 * Set up the primary, secondary and subordinate
@@ -958,6 +958,9 @@ static void pci_init_capabilities(struct pci_dev *dev)
 	/* MSI/MSI-X list */
 	pci_msi_init_pci_dev(dev);
 
+	/* Buffers for saving PCIe and PCI-X capabilities */
+	pci_allocate_cap_save_buffers(dev);
+
 	/* Power Management */
 	pci_pm_init(dev);
 
@@ -1130,7 +1133,7 @@ struct pci_bus * pci_create_bus(struct device *parent,
 	memset(dev, 0, sizeof(*dev));
 	dev->parent = parent;
 	dev->release = pci_release_bus_bridge_dev;
-	sprintf(dev->bus_id, "pci%04x:%02x", pci_domain_nr(b), bus);
+	dev_set_name(dev, "pci%04x:%02x", pci_domain_nr(b), bus);
 	error = device_register(dev);
 	if (error)
 		goto dev_reg_err;
@@ -1141,7 +1144,7 @@ struct pci_bus * pci_create_bus(struct device *parent,
 
 	b->dev.class = &pcibus_class;
 	b->dev.parent = b->bridge;
-	sprintf(b->dev.bus_id, "%04x:%02x", pci_domain_nr(b), bus);
+	dev_set_name(&b->dev, "%04x:%02x", pci_domain_nr(b), bus);
 	error = device_register(&b->dev);
 	if (error)
 		goto class_dev_reg_err;
diff --git a/drivers/pci/proc.c b/drivers/pci/proc.c
index e1098c302c45..7fb086d39617 100644
--- a/drivers/pci/proc.c
+++ b/drivers/pci/proc.c
@@ -252,11 +252,20 @@ static int proc_bus_pci_mmap(struct file *file, struct vm_area_struct *vma)
 	const struct proc_dir_entry *dp = PDE(inode);
 	struct pci_dev *dev = dp->data;
 	struct pci_filp_private *fpriv = file->private_data;
-	int ret;
+	int i, ret;
 
 	if (!capable(CAP_SYS_RAWIO))
 		return -EPERM;
 
+	/* Make sure the caller is mapping a real resource for this device */
+	for (i = 0; i < PCI_ROM_RESOURCE; i++) {
+		if (pci_mmap_fits(dev, i, vma))
+			break;
+	}
+
+	if (i >= PCI_ROM_RESOURCE)
+		return -ENODEV;
+
 	ret = pci_mmap_page_range(dev, vma,
 				  fpriv->mmap_state,
 				  fpriv->write_combine);
diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
index 5f4f85f56cb7..d3a9e0f38682 100644
--- a/drivers/pci/quirks.c
+++ b/drivers/pci/quirks.c
@@ -449,7 +449,7 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL,    PCI_DEVICE_ID_INTEL_82801DB_12,
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL,    PCI_DEVICE_ID_INTEL_82801EB_0,		quirk_ich4_lpc_acpi);
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL,    PCI_DEVICE_ID_INTEL_ESB_1,		quirk_ich4_lpc_acpi);
 
-static void __devinit quirk_ich6_lpc_acpi(struct pci_dev *dev)
+static void __devinit ich6_lpc_acpi_gpio(struct pci_dev *dev)
 {
 	u32 region;
 
@@ -459,20 +459,95 @@ static void __devinit quirk_ich6_lpc_acpi(struct pci_dev *dev)
 	pci_read_config_dword(dev, 0x48, &region);
 	quirk_io_region(dev, region, 64, PCI_BRIDGE_RESOURCES+1, "ICH6 GPIO");
 }
-DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_ICH6_0, quirk_ich6_lpc_acpi);
-DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_ICH6_1, quirk_ich6_lpc_acpi);
-DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_ICH7_0, quirk_ich6_lpc_acpi);
-DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_ICH7_1, quirk_ich6_lpc_acpi);
-DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_ICH7_31, quirk_ich6_lpc_acpi);
-DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_ICH8_0, quirk_ich6_lpc_acpi);
-DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_ICH8_2, quirk_ich6_lpc_acpi);
-DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_ICH8_3, quirk_ich6_lpc_acpi);
-DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_ICH8_1, quirk_ich6_lpc_acpi);
-DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_ICH8_4, quirk_ich6_lpc_acpi);
-DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_ICH9_2, quirk_ich6_lpc_acpi);
-DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_ICH9_4, quirk_ich6_lpc_acpi);
-DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_ICH9_7, quirk_ich6_lpc_acpi);
-DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_ICH9_8, quirk_ich6_lpc_acpi);
+
+static void __devinit ich6_lpc_generic_decode(struct pci_dev *dev, unsigned reg, const char *name, int dynsize)
+{
+	u32 val;
+	u32 size, base;
+
+	pci_read_config_dword(dev, reg, &val);
+
+	/* Enabled? */
+	if (!(val & 1))
+		return;
+	base = val & 0xfffc;
+	if (dynsize) {
+		/*
+		 * This is not correct. It is 16, 32 or 64 bytes depending on
+		 * register D31:F0:ADh bits 5:4.
+		 *
+		 * But this gets us at least _part_ of it.
+		 */
+		size = 16;
+	} else {
+		size = 128;
+	}
+	base &= ~(size-1);
+
+	/* Just print it out for now. We should reserve it after more debugging */
+	dev_info(&dev->dev, "%s PIO at %04x-%04x\n", name, base, base+size-1);
+}
+
+static void __devinit quirk_ich6_lpc(struct pci_dev *dev)
+{
+	/* Shared ACPI/GPIO decode with all ICH6+ */
+	ich6_lpc_acpi_gpio(dev);
+
+	/* ICH6-specific generic IO decode */
+	ich6_lpc_generic_decode(dev, 0x84, "LPC Generic IO decode 1", 0);
+	ich6_lpc_generic_decode(dev, 0x88, "LPC Generic IO decode 2", 1);
+}
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_ICH6_0, quirk_ich6_lpc);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_ICH6_1, quirk_ich6_lpc);
+
+static void __devinit ich7_lpc_generic_decode(struct pci_dev *dev, unsigned reg, const char *name)
+{
+	u32 val;
+	u32 mask, base;
+
+	pci_read_config_dword(dev, reg, &val);
+
+	/* Enabled? */
+	if (!(val & 1))
+		return;
+
+	/*
+	 * IO base in bits 15:2, mask in bits 23:18, both
+	 * are dword-based
+	 */
+	base = val & 0xfffc;
+	mask = (val >> 16) & 0xfc;
+	mask |= 3;
+
+	/* Just print it out for now. We should reserve it after more debugging */
+	dev_info(&dev->dev, "%s PIO at %04x (mask %04x)\n", name, base, mask);
+}
+
+/* ICH7-10 has the same common LPC generic IO decode registers */
+static void __devinit quirk_ich7_lpc(struct pci_dev *dev)
+{
+	/* We share the common ACPI/DPIO decode with ICH6 */
+	ich6_lpc_acpi_gpio(dev);
+
+	/* And have 4 ICH7+ generic decodes */
+	ich7_lpc_generic_decode(dev, 0x84, "ICH7 LPC Generic IO decode 1");
+	ich7_lpc_generic_decode(dev, 0x88, "ICH7 LPC Generic IO decode 2");
+	ich7_lpc_generic_decode(dev, 0x8c, "ICH7 LPC Generic IO decode 3");
+	ich7_lpc_generic_decode(dev, 0x90, "ICH7 LPC Generic IO decode 4");
+}
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_ICH7_0, quirk_ich7_lpc);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_ICH7_1, quirk_ich7_lpc);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_ICH7_31, quirk_ich7_lpc);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_ICH8_0, quirk_ich7_lpc);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_ICH8_2, quirk_ich7_lpc);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_ICH8_3, quirk_ich7_lpc);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_ICH8_1, quirk_ich7_lpc);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_ICH8_4, quirk_ich7_lpc);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_ICH9_2, quirk_ich7_lpc);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_ICH9_4, quirk_ich7_lpc);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_ICH9_7, quirk_ich7_lpc);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_ICH9_8, quirk_ich7_lpc);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL,   PCI_DEVICE_ID_INTEL_ICH10_1, quirk_ich7_lpc);
 
 /*
  * VIA ACPI: One IO region pointed to by longword at
@@ -606,27 +681,6 @@ static void __init quirk_ioapic_rmw(struct pci_dev *dev)
 		sis_apic_bug = 1;
 }
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_SI,	PCI_ANY_ID,			quirk_ioapic_rmw);
-
-#define AMD8131_revA0        0x01
-#define AMD8131_revB0        0x11
-#define AMD8131_MISC         0x40
-#define AMD8131_NIOAMODE_BIT 0
-static void quirk_amd_8131_ioapic(struct pci_dev *dev)
-{ 
-        unsigned char tmp;
-        
-        if (nr_ioapics == 0) 
-                return;
-
-        if (dev->revision == AMD8131_revA0 || dev->revision == AMD8131_revB0) {
-                dev_info(&dev->dev, "Fixing up AMD8131 IOAPIC mode\n");
-                pci_read_config_byte( dev, AMD8131_MISC, &tmp);
-                tmp &= ~(1 << AMD8131_NIOAMODE_BIT);
-                pci_write_config_byte( dev, AMD8131_MISC, tmp);
-        }
-} 
-DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_8131_BRIDGE, quirk_amd_8131_ioapic);
-DECLARE_PCI_FIXUP_RESUME_EARLY(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_8131_BRIDGE, quirk_amd_8131_ioapic);
 #endif /* CONFIG_X86_IO_APIC */
 
 /*
@@ -1423,6 +1477,155 @@ DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL,	0x2609, quirk_intel_pcie_pm);
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL,	0x260a, quirk_intel_pcie_pm);
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL,	0x260b, quirk_intel_pcie_pm);
 
+#ifdef CONFIG_X86_IO_APIC
+/*
+ * Boot interrupts on some chipsets cannot be turned off. For these chipsets,
+ * remap the original interrupt in the linux kernel to the boot interrupt, so
+ * that a PCI device's interrupt handler is installed on the boot interrupt
+ * line instead.
+ */
+static void quirk_reroute_to_boot_interrupts_intel(struct pci_dev *dev)
+{
+	if (noioapicquirk || noioapicreroute)
+		return;
+
+	dev->irq_reroute_variant = INTEL_IRQ_REROUTE_VARIANT;
+
+	printk(KERN_INFO "PCI quirk: reroute interrupts for 0x%04x:0x%04x\n",
+			dev->vendor, dev->device);
+	return;
+}
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_80333_0,	quirk_reroute_to_boot_interrupts_intel);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_80333_1,	quirk_reroute_to_boot_interrupts_intel);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_ESB2_0,	quirk_reroute_to_boot_interrupts_intel);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_PXH_0,	quirk_reroute_to_boot_interrupts_intel);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_PXH_1,	quirk_reroute_to_boot_interrupts_intel);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_PXHV,	quirk_reroute_to_boot_interrupts_intel);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_80332_0,	quirk_reroute_to_boot_interrupts_intel);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_80332_1,	quirk_reroute_to_boot_interrupts_intel);
+DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_80333_0,	quirk_reroute_to_boot_interrupts_intel);
+DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_80333_1,	quirk_reroute_to_boot_interrupts_intel);
+DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_ESB2_0,	quirk_reroute_to_boot_interrupts_intel);
+DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_PXH_0,	quirk_reroute_to_boot_interrupts_intel);
+DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_PXH_1,	quirk_reroute_to_boot_interrupts_intel);
+DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_PXHV,	quirk_reroute_to_boot_interrupts_intel);
+DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_80332_0,	quirk_reroute_to_boot_interrupts_intel);
+DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_80332_1,	quirk_reroute_to_boot_interrupts_intel);
+
+/*
+ * On some chipsets we can disable the generation of legacy INTx boot
+ * interrupts.
+ */
+
+/*
+ * IO-APIC1 on 6300ESB generates boot interrupts, see intel order no
+ * 300641-004US, section 5.7.3.
+ */
+#define INTEL_6300_IOAPIC_ABAR		0x40
+#define INTEL_6300_DISABLE_BOOT_IRQ	(1<<14)
+
+static void quirk_disable_intel_boot_interrupt(struct pci_dev *dev)
+{
+	u16 pci_config_word;
+
+	if (noioapicquirk)
+		return;
+
+	pci_read_config_word(dev, INTEL_6300_IOAPIC_ABAR, &pci_config_word);
+	pci_config_word |= INTEL_6300_DISABLE_BOOT_IRQ;
+	pci_write_config_word(dev, INTEL_6300_IOAPIC_ABAR, pci_config_word);
+
+	printk(KERN_INFO "disabled boot interrupt on device 0x%04x:0x%04x\n",
+		dev->vendor, dev->device);
+}
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL,   PCI_DEVICE_ID_INTEL_ESB_10, 	quirk_disable_intel_boot_interrupt);
+DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_INTEL,   PCI_DEVICE_ID_INTEL_ESB_10, 	quirk_disable_intel_boot_interrupt);
+
+/*
+ * disable boot interrupts on HT-1000
+ */
+#define BC_HT1000_FEATURE_REG		0x64
+#define BC_HT1000_PIC_REGS_ENABLE	(1<<0)
+#define BC_HT1000_MAP_IDX		0xC00
+#define BC_HT1000_MAP_DATA		0xC01
+
+static void quirk_disable_broadcom_boot_interrupt(struct pci_dev *dev)
+{
+	u32 pci_config_dword;
+	u8 irq;
+
+	if (noioapicquirk)
+		return;
+
+	pci_read_config_dword(dev, BC_HT1000_FEATURE_REG, &pci_config_dword);
+	pci_write_config_dword(dev, BC_HT1000_FEATURE_REG, pci_config_dword |
+			BC_HT1000_PIC_REGS_ENABLE);
+
+	for (irq = 0x10; irq < 0x10 + 32; irq++) {
+		outb(irq, BC_HT1000_MAP_IDX);
+		outb(0x00, BC_HT1000_MAP_DATA);
+	}
+
+	pci_write_config_dword(dev, BC_HT1000_FEATURE_REG, pci_config_dword);
+
+	printk(KERN_INFO "disabled boot interrupts on PCI device"
+			"0x%04x:0x%04x\n", dev->vendor, dev->device);
+}
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_SERVERWORKS,   PCI_DEVICE_ID_SERVERWORKS_HT1000SB, 	quirk_disable_broadcom_boot_interrupt);
+DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_SERVERWORKS,   PCI_DEVICE_ID_SERVERWORKS_HT1000SB, 	quirk_disable_broadcom_boot_interrupt);
+
+/*
+ * disable boot interrupts on AMD and ATI chipsets
+ */
+/*
+ * NOIOAMODE needs to be disabled to disable "boot interrupts". For AMD 8131
+ * rev. A0 and B0, NOIOAMODE needs to be disabled anyway to fix IO-APIC mode
+ * (due to an erratum).
+ */
+#define AMD_813X_MISC			0x40
+#define AMD_813X_NOIOAMODE		(1<<0)
+
+static void quirk_disable_amd_813x_boot_interrupt(struct pci_dev *dev)
+{
+	u32 pci_config_dword;
+
+	if (noioapicquirk)
+		return;
+
+	pci_read_config_dword(dev, AMD_813X_MISC, &pci_config_dword);
+	pci_config_dword &= ~AMD_813X_NOIOAMODE;
+	pci_write_config_dword(dev, AMD_813X_MISC, pci_config_dword);
+
+	printk(KERN_INFO "disabled boot interrupts on PCI device "
+			"0x%04x:0x%04x\n", dev->vendor, dev->device);
+}
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD,   PCI_DEVICE_ID_AMD_8131_BRIDGE, 	quirk_disable_amd_813x_boot_interrupt);
+DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_AMD,   PCI_DEVICE_ID_AMD_8132_BRIDGE, 	quirk_disable_amd_813x_boot_interrupt);
+
+#define AMD_8111_PCI_IRQ_ROUTING	0x56
+
+static void quirk_disable_amd_8111_boot_interrupt(struct pci_dev *dev)
+{
+	u16 pci_config_word;
+
+	if (noioapicquirk)
+		return;
+
+	pci_read_config_word(dev, AMD_8111_PCI_IRQ_ROUTING, &pci_config_word);
+	if (!pci_config_word) {
+		printk(KERN_INFO "boot interrupts on PCI device 0x%04x:0x%04x "
+				"already disabled\n",
+				dev->vendor, dev->device);
+		return;
+	}
+	pci_write_config_word(dev, AMD_8111_PCI_IRQ_ROUTING, 0);
+	printk(KERN_INFO "disabled boot interrupts on PCI device "
+			"0x%04x:0x%04x\n", dev->vendor, dev->device);
+}
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD,   PCI_DEVICE_ID_AMD_8111_SMBUS, 	quirk_disable_amd_8111_boot_interrupt);
+DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_AMD,   PCI_DEVICE_ID_AMD_8111_SMBUS, 	quirk_disable_amd_8111_boot_interrupt);
+#endif /* CONFIG_X86_IO_APIC */
+
 /*
  * Toshiba TC86C001 IDE controller reports the standard 8-byte BAR0 size
  * but the PIO transfers won't work if BAR0 falls at the odd 8 bytes.
@@ -1946,11 +2149,12 @@ DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x4375,
 
 #endif /* CONFIG_PCI_MSI */
 
-static void pci_do_fixups(struct pci_dev *dev, struct pci_fixup *f, struct pci_fixup *end)
+static void pci_do_fixups(struct pci_dev *dev, struct pci_fixup *f,
+			  struct pci_fixup *end)
 {
 	while (f < end) {
 		if ((f->vendor == dev->vendor || f->vendor == (u16) PCI_ANY_ID) &&
- 		    (f->device == dev->device || f->device == (u16) PCI_ANY_ID)) {
+		    (f->device == dev->device || f->device == (u16) PCI_ANY_ID)) {
 			dev_dbg(&dev->dev, "calling %pF\n", f->hook);
 			f->hook(dev);
 		}
diff --git a/drivers/platform/Kconfig b/drivers/platform/Kconfig
new file mode 100644
index 000000000000..9652c3fe7f5e
--- /dev/null
+++ b/drivers/platform/Kconfig
@@ -0,0 +1,5 @@
+# drivers/platform/Kconfig
+
+if X86
+source "drivers/platform/x86/Kconfig"
+endif
diff --git a/drivers/platform/Makefile b/drivers/platform/Makefile
new file mode 100644
index 000000000000..782953ae4c03
--- /dev/null
+++ b/drivers/platform/Makefile
@@ -0,0 +1,5 @@
+#
+# Makefile for linux/drivers/platform
+#
+
+obj-$(CONFIG_X86)		+= x86/
diff --git a/drivers/platform/x86/Kconfig b/drivers/platform/x86/Kconfig
new file mode 100644
index 000000000000..0a9a5b9440af
--- /dev/null
+++ b/drivers/platform/x86/Kconfig
@@ -0,0 +1,290 @@
+#
+# X86 Platform Specific Drivers
+#
+
+menuconfig X86_PLATFORM_DEVICES
+	bool "X86 Platform Specific Device Drivers"
+	default y
+	---help---
+	  Say Y here to get to see options for device drivers for various
+	  x86 platforms, including vendor-specific laptop extension drivers.
+	  This option alone does not add any kernel code.
+
+	  If you say N, all options in this submenu will be skipped and disabled.
+
+if X86_PLATFORM_DEVICES
+
+config ACER_WMI
+	tristate "Acer WMI Laptop Extras (EXPERIMENTAL)"
+	depends on EXPERIMENTAL
+	depends on ACPI
+	depends on LEDS_CLASS
+	depends on NEW_LEDS
+	depends on BACKLIGHT_CLASS_DEVICE
+	depends on SERIO_I8042
+	depends on RFKILL
+	select ACPI_WMI
+	---help---
+	  This is a driver for newer Acer (and Wistron) laptops. It adds
+	  wireless radio and bluetooth control, and on some laptops,
+	  exposes the mail LED and LCD backlight.
+
+	  For more information about this driver see
+	  <file:Documentation/laptops/acer-wmi.txt>
+
+	  If you have an ACPI-WMI compatible Acer/ Wistron laptop, say Y or M
+	  here.
+
+config ASUS_LAPTOP
+	tristate "Asus Laptop Extras (EXPERIMENTAL)"
+	depends on ACPI
+	depends on EXPERIMENTAL && !ACPI_ASUS
+	depends on LEDS_CLASS
+	depends on NEW_LEDS
+	depends on BACKLIGHT_CLASS_DEVICE
+	---help---
+	  This is the new Linux driver for Asus laptops. It may also support some
+	  MEDION, JVC or VICTOR laptops. It makes all the extra buttons generate
+	  standard ACPI events that go through /proc/acpi/events. It also adds
+	  support for video output switching, LCD backlight control, Bluetooth and
+	  Wlan control, and most importantly, allows you to blink those fancy LEDs.
+
+	  For more information and a userspace daemon for handling the extra
+	  buttons see <http://acpi4asus.sf.net/>.
+
+	  If you have an ACPI-compatible ASUS laptop, say Y or M here.
+
+config FUJITSU_LAPTOP
+	tristate "Fujitsu Laptop Extras"
+	depends on ACPI
+	depends on INPUT
+	depends on BACKLIGHT_CLASS_DEVICE
+	---help---
+	  This is a driver for laptops built by Fujitsu:
+
+	    * P2xxx/P5xxx/S6xxx/S7xxx series Lifebooks
+	    * Possibly other Fujitsu laptop models
+	    * Tested with S6410 and S7020
+
+	  It adds support for LCD brightness control and some hotkeys.
+
+	  If you have a Fujitsu laptop, say Y or M here.
+
+config FUJITSU_LAPTOP_DEBUG
+	bool "Verbose debug mode for Fujitsu Laptop Extras"
+	depends on FUJITSU_LAPTOP
+	default n
+	---help---
+	  Enables extra debug output from the fujitsu extras driver, at the
+	  expense of a slight increase in driver size.
+
+	  If you are not sure, say N here.
+
+config TC1100_WMI
+	tristate "HP Compaq TC1100 Tablet WMI Extras (EXPERIMENTAL)"
+	depends on !X86_64
+	depends on EXPERIMENTAL
+	depends on ACPI
+	select ACPI_WMI
+	---help---
+	  This is a driver for the WMI extensions (wireless and bluetooth power
+	  control) of the HP Compaq TC1100 tablet.
+
+config HP_WMI
+	tristate "HP WMI extras"
+	depends on ACPI_WMI
+	depends on INPUT
+	depends on RFKILL
+	help
+	 Say Y here if you want to support WMI-based hotkeys on HP laptops and
+	 to read data from WMI such as docking or ambient light sensor state.
+
+	 To compile this driver as a module, choose M here: the module will
+	 be called hp-wmi.
+
+config MSI_LAPTOP
+	tristate "MSI Laptop Extras"
+	depends on ACPI
+	depends on BACKLIGHT_CLASS_DEVICE
+	---help---
+	  This is a driver for laptops built by MSI (MICRO-STAR
+	  INTERNATIONAL):
+
+	  MSI MegaBook S270 (MS-1013)
+	  Cytron/TCM/Medion/Tchibo MD96100/SAM2000
+
+	  It adds support for Bluetooth, WLAN and LCD brightness control.
+
+	  More information about this driver is available at
+	  <http://0pointer.de/lennart/tchibo.html>.
+
+	  If you have an MSI S270 laptop, say Y or M here.
+
+config PANASONIC_LAPTOP
+	tristate "Panasonic Laptop Extras"
+	depends on INPUT && ACPI
+	depends on BACKLIGHT_CLASS_DEVICE
+	---help---
+	  This driver adds support for access to backlight control and hotkeys
+	  on Panasonic Let's Note laptops.
+
+	  If you have a Panasonic Let's note laptop (such as the R1(N variant),
+	  R2, R3, R5, T2, W2 and Y2 series), say Y.
+
+config COMPAL_LAPTOP
+	tristate "Compal Laptop Extras"
+	depends on ACPI
+	depends on BACKLIGHT_CLASS_DEVICE
+	---help---
+	  This is a driver for laptops built by Compal:
+
+	  Compal FL90/IFL90
+	  Compal FL91/IFL91
+	  Compal FL92/JFL92
+	  Compal FT00/IFT00
+
+	  It adds support for Bluetooth, WLAN and LCD brightness control.
+
+	  If you have an Compal FL9x/IFL9x/FT00 laptop, say Y or M here.
+
+config SONY_LAPTOP
+	tristate "Sony Laptop Extras"
+	depends on ACPI
+	select BACKLIGHT_CLASS_DEVICE
+	depends on INPUT
+	  ---help---
+	  This mini-driver drives the SNC and SPIC devices present in the ACPI
+	  BIOS of the Sony Vaio laptops.
+
+	  It gives access to some extra laptop functionalities like Bluetooth,
+	  screen brightness control, Fn keys and allows powering on/off some
+	  devices.
+
+	  Read <file:Documentation/laptops/sony-laptop.txt> for more information.
+
+config SONYPI_COMPAT
+	bool "Sonypi compatibility"
+	depends on SONY_LAPTOP
+	  ---help---
+	  Build the sonypi driver compatibility code into the sony-laptop driver.
+
+config THINKPAD_ACPI
+	tristate "ThinkPad ACPI Laptop Extras"
+	depends on ACPI
+	select BACKLIGHT_LCD_SUPPORT
+	select BACKLIGHT_CLASS_DEVICE
+	select HWMON
+	select NVRAM
+	select INPUT
+	select NEW_LEDS
+	select LEDS_CLASS
+	select NET
+	select RFKILL
+	---help---
+	  This is a driver for the IBM and Lenovo ThinkPad laptops. It adds
+	  support for Fn-Fx key combinations, Bluetooth control, video
+	  output switching, ThinkLight control, UltraBay eject and more.
+	  For more information about this driver see
+	  <file:Documentation/laptops/thinkpad-acpi.txt> and
+	  <http://ibm-acpi.sf.net/> .
+
+	  This driver was formerly known as ibm-acpi.
+
+	  If you have an IBM or Lenovo ThinkPad laptop, say Y or M here.
+
+config THINKPAD_ACPI_DEBUG
+	bool "Verbose debug mode"
+	depends on THINKPAD_ACPI
+	default n
+	---help---
+	  Enables extra debugging information, at the expense of a slightly
+	  increase in driver size.
+
+	  If you are not sure, say N here.
+
+config THINKPAD_ACPI_DOCK
+	bool "Legacy Docking Station Support"
+	depends on THINKPAD_ACPI
+	depends on ACPI_DOCK=n
+	default n
+	---help---
+	  Allows the thinkpad_acpi driver to handle docking station events.
+	  This support was made obsolete by the generic ACPI docking station
+	  support (CONFIG_ACPI_DOCK).  It will allow locking and removing the
+	  laptop from the docking station, but will not properly connect PCI
+	  devices.
+
+	  If you are not sure, say N here.
+
+config THINKPAD_ACPI_BAY
+	bool "Legacy Removable Bay Support"
+	depends on THINKPAD_ACPI
+	default y
+	---help---
+	  Allows the thinkpad_acpi driver to handle removable bays.  It will
+	  electrically disable the device in the bay, and also generate
+	  notifications when the bay lever is ejected or inserted.
+
+	  If you are not sure, say Y here.
+
+config THINKPAD_ACPI_VIDEO
+	bool "Video output control support"
+	depends on THINKPAD_ACPI
+	default y
+	---help---
+	  Allows the thinkpad_acpi driver to provide an interface to control
+	  the various video output ports.
+
+	  This feature often won't work well, depending on ThinkPad model,
+	  display state, video output devices in use, whether there is a X
+	  server running, phase of the moon, and the current mood of
+	  Schroedinger's cat.  If you can use X.org's RandR to control
+	  your ThinkPad's video output ports instead of this feature,
+	  don't think twice: do it and say N here to save some memory.
+
+	  If you are not sure, say Y here.
+
+config THINKPAD_ACPI_HOTKEY_POLL
+	bool "Support NVRAM polling for hot keys"
+	depends on THINKPAD_ACPI
+	default y
+	---help---
+	  Some thinkpad models benefit from NVRAM polling to detect a few of
+	  the hot key press events.  If you know your ThinkPad model does not
+	  need to do NVRAM polling to support any of the hot keys you use,
+	  unselecting this option will save about 1kB of memory.
+
+	  ThinkPads T40 and newer, R52 and newer, and X31 and newer are
+	  unlikely to need NVRAM polling in their latest BIOS versions.
+
+	  NVRAM polling can detect at most the following keys: ThinkPad/Access
+	  IBM, Zoom, Switch Display (fn+F7), ThinkLight, Volume up/down/mute,
+	  Brightness up/down, Display Expand (fn+F8), Hibernate (fn+F12).
+
+	  If you are not sure, say Y here.  The driver enables polling only if
+	  it is strictly necessary to do so.
+
+config INTEL_MENLOW
+	tristate "Thermal Management driver for Intel menlow platform"
+	depends on ACPI_THERMAL
+	select THERMAL
+	---help---
+	  ACPI thermal management enhancement driver on
+	  Intel Menlow platform.
+
+	  If unsure, say N.
+
+config EEEPC_LAPTOP
+	tristate "Eee PC Hotkey Driver (EXPERIMENTAL)"
+	depends on ACPI
+	depends on BACKLIGHT_CLASS_DEVICE
+	depends on HWMON
+	depends on EXPERIMENTAL
+	depends on RFKILL
+	---help---
+	  This driver supports the Fn-Fx keys on Eee PC laptops.
+	  It also adds the ability to switch camera/wlan on/off.
+
+	  If you have an Eee PC laptop, say Y or M here.
+
+endif # X86_PLATFORM_DEVICES
diff --git a/drivers/platform/x86/Makefile b/drivers/platform/x86/Makefile
new file mode 100644
index 000000000000..4d26b1bf22ae
--- /dev/null
+++ b/drivers/platform/x86/Makefile
@@ -0,0 +1,16 @@
+#
+# Makefile for linux/drivers/platform/x86
+# x86 Platform-Specific Drivers
+#
+obj-$(CONFIG_ASUS_LAPTOP)	+= asus-laptop.o
+obj-$(CONFIG_EEEPC_LAPTOP)	+= eeepc-laptop.o
+obj-$(CONFIG_MSI_LAPTOP)	+= msi-laptop.o
+obj-$(CONFIG_COMPAL_LAPTOP)	+= compal-laptop.o
+obj-$(CONFIG_ACER_WMI)		+= acer-wmi.o
+obj-$(CONFIG_HP_WMI)		+= hp-wmi.o
+obj-$(CONFIG_TC1100_WMI)	+= tc1100-wmi.o
+obj-$(CONFIG_SONY_LAPTOP)	+= sony-laptop.o
+obj-$(CONFIG_THINKPAD_ACPI)	+= thinkpad_acpi.o
+obj-$(CONFIG_FUJITSU_LAPTOP)	+= fujitsu-laptop.o
+obj-$(CONFIG_PANASONIC_LAPTOP)	+= panasonic-laptop.o
+obj-$(CONFIG_INTEL_MENLOW)	+= intel_menlow.o
diff --git a/drivers/misc/acer-wmi.c b/drivers/platform/x86/acer-wmi.c
index 94c9f911824e..94c9f911824e 100644
--- a/drivers/misc/acer-wmi.c
+++ b/drivers/platform/x86/acer-wmi.c
diff --git a/drivers/misc/asus-laptop.c b/drivers/platform/x86/asus-laptop.c
index 8fb8b3591048..8fb8b3591048 100644
--- a/drivers/misc/asus-laptop.c
+++ b/drivers/platform/x86/asus-laptop.c
diff --git a/drivers/misc/compal-laptop.c b/drivers/platform/x86/compal-laptop.c
index 11003bba10d3..11003bba10d3 100644
--- a/drivers/misc/compal-laptop.c
+++ b/drivers/platform/x86/compal-laptop.c
diff --git a/drivers/misc/eeepc-laptop.c b/drivers/platform/x86/eeepc-laptop.c
index 02fe2b8b8939..02fe2b8b8939 100644
--- a/drivers/misc/eeepc-laptop.c
+++ b/drivers/platform/x86/eeepc-laptop.c
diff --git a/drivers/misc/fujitsu-laptop.c b/drivers/platform/x86/fujitsu-laptop.c
index a7dd3e9fb79d..a7dd3e9fb79d 100644
--- a/drivers/misc/fujitsu-laptop.c
+++ b/drivers/platform/x86/fujitsu-laptop.c
diff --git a/drivers/misc/hp-wmi.c b/drivers/platform/x86/hp-wmi.c
index 4b7c24c519c3..4b7c24c519c3 100644
--- a/drivers/misc/hp-wmi.c
+++ b/drivers/platform/x86/hp-wmi.c
diff --git a/drivers/misc/intel_menlow.c b/drivers/platform/x86/intel_menlow.c
index 27b7662955bb..27b7662955bb 100644
--- a/drivers/misc/intel_menlow.c
+++ b/drivers/platform/x86/intel_menlow.c
diff --git a/drivers/misc/msi-laptop.c b/drivers/platform/x86/msi-laptop.c
index 759763d18e4c..759763d18e4c 100644
--- a/drivers/misc/msi-laptop.c
+++ b/drivers/platform/x86/msi-laptop.c
diff --git a/drivers/misc/panasonic-laptop.c b/drivers/platform/x86/panasonic-laptop.c
index 4a1bc64485d5..4a1bc64485d5 100644
--- a/drivers/misc/panasonic-laptop.c
+++ b/drivers/platform/x86/panasonic-laptop.c
diff --git a/drivers/misc/sony-laptop.c b/drivers/platform/x86/sony-laptop.c
index 571b211608d1..571b211608d1 100644
--- a/drivers/misc/sony-laptop.c
+++ b/drivers/platform/x86/sony-laptop.c
diff --git a/drivers/misc/tc1100-wmi.c b/drivers/platform/x86/tc1100-wmi.c
index f25e4c974dcf..f25e4c974dcf 100644
--- a/drivers/misc/tc1100-wmi.c
+++ b/drivers/platform/x86/tc1100-wmi.c
diff --git a/drivers/misc/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c
index 899766e16fa8..899766e16fa8 100644
--- a/drivers/misc/thinkpad_acpi.c
+++ b/drivers/platform/x86/thinkpad_acpi.c
diff --git a/drivers/pnp/card.c b/drivers/pnp/card.c
index e75b060daa95..efea128f02da 100644
--- a/drivers/pnp/card.c
+++ b/drivers/pnp/card.c
@@ -165,8 +165,7 @@ struct pnp_card *pnp_alloc_card(struct pnp_protocol *protocol, int id, char *pnp
 	card->number = id;
 
 	card->dev.parent = &card->protocol->dev;
-	sprintf(card->dev.bus_id, "%02x:%02x", card->protocol->number,
-		card->number);
+	dev_set_name(&card->dev, "%02x:%02x", card->protocol->number, card->number);
 
 	card->dev.coherent_dma_mask = DMA_24BIT_MASK;
 	card->dev.dma_mask = &card->dev.coherent_dma_mask;
@@ -295,8 +294,8 @@ int pnp_add_card_device(struct pnp_card *card, struct pnp_dev *dev)
 {
 	dev->dev.parent = &card->dev;
 	dev->card_link = NULL;
-	snprintf(dev->dev.bus_id, BUS_ID_SIZE, "%02x:%02x.%02x",
-		 dev->protocol->number, card->number, dev->number);
+	dev_set_name(&dev->dev, "%02x:%02x.%02x",
+		     dev->protocol->number, card->number, dev->number);
 	spin_lock(&pnp_lock);
 	dev->card = card;
 	list_add_tail(&dev->card_list, &card->devices);
diff --git a/drivers/pnp/core.c b/drivers/pnp/core.c
index 16c01c6fa7c5..14814f231739 100644
--- a/drivers/pnp/core.c
+++ b/drivers/pnp/core.c
@@ -70,7 +70,7 @@ int pnp_register_protocol(struct pnp_protocol *protocol)
 	spin_unlock(&pnp_lock);
 
 	protocol->number = nodenum;
-	sprintf(protocol->dev.bus_id, "pnp%d", nodenum);
+	dev_set_name(&protocol->dev, "pnp%d", nodenum);
 	return device_register(&protocol->dev);
 }
 
@@ -145,8 +145,7 @@ struct pnp_dev *pnp_alloc_dev(struct pnp_protocol *protocol, int id, char *pnpid
 	dev->dev.coherent_dma_mask = dev->dma_mask;
 	dev->dev.release = &pnp_release_device;
 
-	sprintf(dev->dev.bus_id, "%02x:%02x", dev->protocol->number,
-		dev->number);
+	dev_set_name(&dev->dev, "%02x:%02x", dev->protocol->number, dev->number);
 
 	dev_id = pnp_add_id(dev, pnpid);
 	if (!dev_id) {
diff --git a/drivers/pnp/system.c b/drivers/pnp/system.c
index 764f3a310685..59b90922da8c 100644
--- a/drivers/pnp/system.c
+++ b/drivers/pnp/system.c
@@ -26,7 +26,7 @@ static void reserve_range(struct pnp_dev *dev, resource_size_t start,
 			  resource_size_t end, int port)
 {
 	char *regionid;
-	const char *pnpid = dev->dev.bus_id;
+	const char *pnpid = dev_name(&dev->dev);
 	struct resource *res;
 
 	regionid = kmalloc(16, GFP_KERNEL);
diff --git a/drivers/power/ds2760_battery.c b/drivers/power/ds2760_battery.c
index 308ddb201b66..1d768928e0bb 100644
--- a/drivers/power/ds2760_battery.c
+++ b/drivers/power/ds2760_battery.c
@@ -354,7 +354,7 @@ static int ds2760_battery_probe(struct platform_device *pdev)
 	pdata = pdev->dev.platform_data;
 	di->dev		= &pdev->dev;
 	di->w1_dev	     = pdev->dev.parent;
-	di->bat.name	   = pdev->dev.bus_id;
+	di->bat.name	   = dev_name(&pdev->dev);
 	di->bat.type	   = POWER_SUPPLY_TYPE_BATTERY;
 	di->bat.properties     = ds2760_battery_props;
 	di->bat.num_properties = ARRAY_SIZE(ds2760_battery_props);
@@ -371,7 +371,7 @@ static int ds2760_battery_probe(struct platform_device *pdev)
 	}
 
 	INIT_DELAYED_WORK(&di->monitor_work, ds2760_battery_work);
-	di->monitor_wqueue = create_singlethread_workqueue(pdev->dev.bus_id);
+	di->monitor_wqueue = create_singlethread_workqueue(dev_name(&pdev->dev));
 	if (!di->monitor_wqueue) {
 		retval = -ESRCH;
 		goto workqueue_failed;
diff --git a/drivers/ps3/ps3av.c b/drivers/ps3/ps3av.c
index 06848b254d57..5324978b73fb 100644
--- a/drivers/ps3/ps3av.c
+++ b/drivers/ps3/ps3av.c
@@ -59,8 +59,6 @@ static struct ps3av {
 		struct ps3av_reply_hdr reply_hdr;
 		u8 raw[PS3AV_BUF_SIZE];
 	} recv_buf;
-	void (*flip_ctl)(int on, void *data);
-	void *flip_data;
 } *ps3av;
 
 /* color space */
@@ -939,24 +937,6 @@ int ps3av_audio_mute(int mute)
 
 EXPORT_SYMBOL_GPL(ps3av_audio_mute);
 
-void ps3av_register_flip_ctl(void (*flip_ctl)(int on, void *data),
-			     void *flip_data)
-{
-	mutex_lock(&ps3av->mutex);
-	ps3av->flip_ctl = flip_ctl;
-	ps3av->flip_data = flip_data;
-	mutex_unlock(&ps3av->mutex);
-}
-EXPORT_SYMBOL_GPL(ps3av_register_flip_ctl);
-
-void ps3av_flip_ctl(int on)
-{
-	mutex_lock(&ps3av->mutex);
-	if (ps3av->flip_ctl)
-		ps3av->flip_ctl(on, ps3av->flip_data);
-	mutex_unlock(&ps3av->mutex);
-}
-
 static int ps3av_probe(struct ps3_system_bus_device *dev)
 {
 	int res;
diff --git a/drivers/ps3/ps3av_cmd.c b/drivers/ps3/ps3av_cmd.c
index 11eb50318fec..716596e8e5b0 100644
--- a/drivers/ps3/ps3av_cmd.c
+++ b/drivers/ps3/ps3av_cmd.c
@@ -864,7 +864,7 @@ int ps3av_cmd_avb_param(struct ps3av_pkt_avb_param *avb, u32 send_len)
 {
 	int res;
 
-	ps3av_flip_ctl(0);	/* flip off */
+	mutex_lock(&ps3_gpu_mutex);
 
 	/* avb packet */
 	res = ps3av_do_pkt(PS3AV_CID_AVB_PARAM, send_len, sizeof(*avb),
@@ -878,7 +878,7 @@ int ps3av_cmd_avb_param(struct ps3av_pkt_avb_param *avb, u32 send_len)
 			 res);
 
       out:
-	ps3av_flip_ctl(1);	/* flip on */
+	mutex_unlock(&ps3_gpu_mutex);
 	return res;
 }
 
diff --git a/drivers/rapidio/rio-scan.c b/drivers/rapidio/rio-scan.c
index 643a6b98462b..5c13f61bfb1b 100644
--- a/drivers/rapidio/rio-scan.c
+++ b/drivers/rapidio/rio-scan.c
@@ -365,15 +365,15 @@ static struct rio_dev *rio_setup_device(struct rio_net *net,
 				rdid++)
 			rswitch->route_table[rdid] = RIO_INVALID_ROUTE;
 		rdev->rswitch = rswitch;
-		sprintf(rio_name(rdev), "%02x:s:%04x", rdev->net->id,
-			rdev->rswitch->switchid);
+		dev_set_name(&rdev->dev, "%02x:s:%04x", rdev->net->id,
+			     rdev->rswitch->switchid);
 		rio_route_set_ops(rdev);
 
 		list_add_tail(&rswitch->node, &rio_switches);
 
 	} else
-		sprintf(rio_name(rdev), "%02x:e:%04x", rdev->net->id,
-			rdev->destid);
+		dev_set_name(&rdev->dev, "%02x:e:%04x", rdev->net->id,
+			     rdev->destid);
 
 	rdev->dev.bus = &rio_bus_type;
 
diff --git a/drivers/rtc/rtc-at91sam9.c b/drivers/rtc/rtc-at91sam9.c
index 2133f37906f2..d5e4e637ddec 100644
--- a/drivers/rtc/rtc-at91sam9.c
+++ b/drivers/rtc/rtc-at91sam9.c
@@ -21,6 +21,7 @@
 
 #include <mach/board.h>
 #include <mach/at91_rtt.h>
+#include <mach/cpu.h>
 
 
 /*
diff --git a/drivers/rtc/rtc-s3c.c b/drivers/rtc/rtc-s3c.c
index f59277bbedaa..7a568beba3f0 100644
--- a/drivers/rtc/rtc-s3c.c
+++ b/drivers/rtc/rtc-s3c.c
@@ -26,7 +26,7 @@
 #include <asm/uaccess.h>
 #include <asm/io.h>
 #include <asm/irq.h>
-#include <asm/plat-s3c/regs-rtc.h>
+#include <plat/regs-rtc.h>
 
 /* I have yet to find an S3C implementation with more than one
  * of these rtc blocks in */
diff --git a/drivers/s390/block/dasd_devmap.c b/drivers/s390/block/dasd_devmap.c
index 921443b01d16..2ef25731d197 100644
--- a/drivers/s390/block/dasd_devmap.c
+++ b/drivers/s390/block/dasd_devmap.c
@@ -23,6 +23,7 @@
 
 /* This is ugly... */
 #define PRINTK_HEADER "dasd_devmap:"
+#define DASD_BUS_ID_SIZE 20
 
 #include "dasd_int.h"
 
@@ -41,7 +42,7 @@ EXPORT_SYMBOL_GPL(dasd_page_cache);
  */
 struct dasd_devmap {
 	struct list_head list;
-	char bus_id[BUS_ID_SIZE];
+	char bus_id[DASD_BUS_ID_SIZE];
         unsigned int devindex;
         unsigned short features;
 	struct dasd_device *device;
@@ -94,7 +95,7 @@ dasd_hash_busid(const char *bus_id)
 	int hash, i;
 
 	hash = 0;
-	for (i = 0; (i < BUS_ID_SIZE) && *bus_id; i++, bus_id++)
+	for (i = 0; (i < DASD_BUS_ID_SIZE) && *bus_id; i++, bus_id++)
 		hash += *bus_id;
 	return hash & 0xff;
 }
@@ -301,7 +302,7 @@ dasd_parse_range( char *parsestring ) {
 	int from, from_id0, from_id1;
 	int to, to_id0, to_id1;
 	int features, rc;
-	char bus_id[BUS_ID_SIZE+1], *str;
+	char bus_id[DASD_BUS_ID_SIZE+1], *str;
 
 	str = parsestring;
 	rc = dasd_busid(&str, &from_id0, &from_id1, &from);
@@ -407,14 +408,14 @@ dasd_add_busid(const char *bus_id, int features)
 	devmap = NULL;
 	hash = dasd_hash_busid(bus_id);
 	list_for_each_entry(tmp, &dasd_hashlists[hash], list)
-		if (strncmp(tmp->bus_id, bus_id, BUS_ID_SIZE) == 0) {
+		if (strncmp(tmp->bus_id, bus_id, DASD_BUS_ID_SIZE) == 0) {
 			devmap = tmp;
 			break;
 		}
 	if (!devmap) {
 		/* This bus_id is new. */
 		new->devindex = dasd_max_devindex++;
-		strncpy(new->bus_id, bus_id, BUS_ID_SIZE);
+		strncpy(new->bus_id, bus_id, DASD_BUS_ID_SIZE);
 		new->features = features;
 		new->device = NULL;
 		list_add(&new->list, &dasd_hashlists[hash]);
@@ -439,7 +440,7 @@ dasd_find_busid(const char *bus_id)
 	devmap = ERR_PTR(-ENODEV);
 	hash = dasd_hash_busid(bus_id);
 	list_for_each_entry(tmp, &dasd_hashlists[hash], list) {
-		if (strncmp(tmp->bus_id, bus_id, BUS_ID_SIZE) == 0) {
+		if (strncmp(tmp->bus_id, bus_id, DASD_BUS_ID_SIZE) == 0) {
 			devmap = tmp;
 			break;
 		}
@@ -561,7 +562,7 @@ dasd_create_device(struct ccw_device *cdev)
 	}
 
 	spin_lock_irqsave(get_ccwdev_lock(cdev), flags);
-	cdev->dev.driver_data = device;
+	dev_set_drvdata(&cdev->dev, device);
 	spin_unlock_irqrestore(get_ccwdev_lock(cdev), flags);
 
 	return device;
@@ -597,7 +598,7 @@ dasd_delete_device(struct dasd_device *device)
 
 	/* Disconnect dasd_device structure from ccw_device structure. */
 	spin_lock_irqsave(get_ccwdev_lock(device->cdev), flags);
-	device->cdev->dev.driver_data = NULL;
+	dev_set_drvdata(&device->cdev->dev, NULL);
 	spin_unlock_irqrestore(get_ccwdev_lock(device->cdev), flags);
 
 	/*
@@ -638,7 +639,7 @@ dasd_put_device_wake(struct dasd_device *device)
 struct dasd_device *
 dasd_device_from_cdev_locked(struct ccw_device *cdev)
 {
-	struct dasd_device *device = cdev->dev.driver_data;
+	struct dasd_device *device = dev_get_drvdata(&cdev->dev);
 
 	if (!device)
 		return ERR_PTR(-ENODEV);
diff --git a/drivers/s390/block/dasd_proc.c b/drivers/s390/block/dasd_proc.c
index 9088de84b45d..bf6fd348f20e 100644
--- a/drivers/s390/block/dasd_proc.c
+++ b/drivers/s390/block/dasd_proc.c
@@ -180,12 +180,12 @@ dasd_calc_metrics(char *page, char **start, off_t off,
 
 #ifdef CONFIG_DASD_PROFILE
 static char *
-dasd_statistics_array(char *str, unsigned int *array, int shift)
+dasd_statistics_array(char *str, unsigned int *array, int factor)
 {
 	int i;
 
 	for (i = 0; i < 32; i++) {
-		str += sprintf(str, "%7d ", array[i] >> shift);
+		str += sprintf(str, "%7d ", array[i] / factor);
 		if (i == 15)
 			str += sprintf(str, "\n");
 	}
@@ -202,7 +202,7 @@ dasd_statistics_read(char *page, char **start, off_t off,
 #ifdef CONFIG_DASD_PROFILE
 	struct dasd_profile_info_t *prof;
 	char *str;
-	int shift;
+	int factor;
 
 	/* check for active profiling */
 	if (dasd_profile_level == DASD_PROFILE_OFF) {
@@ -214,12 +214,14 @@ dasd_statistics_read(char *page, char **start, off_t off,
 
 	prof = &dasd_global_profile;
 	/* prevent couter 'overflow' on output */
-	for (shift = 0; (prof->dasd_io_reqs >> shift) > 9999999; shift++);
+	for (factor = 1; (prof->dasd_io_reqs / factor) > 9999999;
+	     factor *= 10);
 
 	str = page;
 	str += sprintf(str, "%d dasd I/O requests\n", prof->dasd_io_reqs);
-	str += sprintf(str, "with %d sectors(512B each)\n",
+	str += sprintf(str, "with %u sectors(512B each)\n",
 		       prof->dasd_io_sects);
+	str += sprintf(str, "Scale Factor is  %d\n", factor);
 	str += sprintf(str,
 		       "   __<4	   ___8	   __16	   __32	   __64	   _128	"
 		       "   _256	   _512	   __1k	   __2k	   __4k	   __8k	"
@@ -230,22 +232,22 @@ dasd_statistics_read(char *page, char **start, off_t off,
 		       "   __1G	   __2G	   __4G " "   _>4G\n");
 
 	str += sprintf(str, "Histogram of sizes (512B secs)\n");
-	str = dasd_statistics_array(str, prof->dasd_io_secs, shift);
+	str = dasd_statistics_array(str, prof->dasd_io_secs, factor);
 	str += sprintf(str, "Histogram of I/O times (microseconds)\n");
-	str = dasd_statistics_array(str, prof->dasd_io_times, shift);
+	str = dasd_statistics_array(str, prof->dasd_io_times, factor);
 	str += sprintf(str, "Histogram of I/O times per sector\n");
-	str = dasd_statistics_array(str, prof->dasd_io_timps, shift);
+	str = dasd_statistics_array(str, prof->dasd_io_timps, factor);
 	str += sprintf(str, "Histogram of I/O time till ssch\n");
-	str = dasd_statistics_array(str, prof->dasd_io_time1, shift);
+	str = dasd_statistics_array(str, prof->dasd_io_time1, factor);
 	str += sprintf(str, "Histogram of I/O time between ssch and irq\n");
-	str = dasd_statistics_array(str, prof->dasd_io_time2, shift);
+	str = dasd_statistics_array(str, prof->dasd_io_time2, factor);
 	str += sprintf(str, "Histogram of I/O time between ssch "
 			    "and irq per sector\n");
-	str = dasd_statistics_array(str, prof->dasd_io_time2ps, shift);
+	str = dasd_statistics_array(str, prof->dasd_io_time2ps, factor);
 	str += sprintf(str, "Histogram of I/O time between irq and end\n");
-	str = dasd_statistics_array(str, prof->dasd_io_time3, shift);
+	str = dasd_statistics_array(str, prof->dasd_io_time3, factor);
 	str += sprintf(str, "# of req in chanq at enqueuing (1..32) \n");
-	str = dasd_statistics_array(str, prof->dasd_io_nr_req, shift);
+	str = dasd_statistics_array(str, prof->dasd_io_nr_req, factor);
 	len = str - page;
 #else
 	len = sprintf(page, "Statistics are not activated in this kernel\n");
diff --git a/drivers/s390/block/dcssblk.c b/drivers/s390/block/dcssblk.c
index 63f26a135fe5..26ffc6ab441d 100644
--- a/drivers/s390/block/dcssblk.c
+++ b/drivers/s390/block/dcssblk.c
@@ -4,6 +4,9 @@
  * Authors: Carsten Otte, Stefan Weinhuber, Gerald Schaefer
  */
 
+#define KMSG_COMPONENT "dcssblk"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
 #include <linux/module.h>
 #include <linux/moduleparam.h>
 #include <linux/ctype.h>
@@ -17,19 +20,10 @@
 #include <linux/interrupt.h>
 #include <asm/s390_rdev.h>
 
-//#define DCSSBLK_DEBUG		/* Debug messages on/off */
 #define DCSSBLK_NAME "dcssblk"
 #define DCSSBLK_MINORS_PER_DISK 1
 #define DCSSBLK_PARM_LEN 400
-
-#ifdef DCSSBLK_DEBUG
-#define PRINT_DEBUG(x...) printk(KERN_DEBUG DCSSBLK_NAME " debug: " x)
-#else
-#define PRINT_DEBUG(x...) do {} while (0)
-#endif
-#define PRINT_INFO(x...)  printk(KERN_INFO DCSSBLK_NAME " info: " x)
-#define PRINT_WARN(x...)  printk(KERN_WARNING DCSSBLK_NAME " warning: " x)
-#define PRINT_ERR(x...)	  printk(KERN_ERR DCSSBLK_NAME " error: " x)
+#define DCSS_BUS_ID_SIZE 20
 
 static int dcssblk_open(struct block_device *bdev, fmode_t mode);
 static int dcssblk_release(struct gendisk *disk, fmode_t mode);
@@ -50,7 +44,7 @@ static struct block_device_operations dcssblk_devops = {
 struct dcssblk_dev_info {
 	struct list_head lh;
 	struct device dev;
-	char segment_name[BUS_ID_SIZE];
+	char segment_name[DCSS_BUS_ID_SIZE];
 	atomic_t use_count;
 	struct gendisk *gd;
 	unsigned long start;
@@ -65,7 +59,7 @@ struct dcssblk_dev_info {
 
 struct segment_info {
 	struct list_head lh;
-	char segment_name[BUS_ID_SIZE];
+	char segment_name[DCSS_BUS_ID_SIZE];
 	unsigned long start;
 	unsigned long end;
 	int segment_type;
@@ -261,10 +255,9 @@ dcssblk_is_continuous(struct dcssblk_dev_info *dev_info)
 	/* check continuity */
 	for (i = 0; i < dev_info->num_of_segments - 1; i++) {
 		if ((sort_list[i].end + 1) != sort_list[i+1].start) {
-			PRINT_ERR("Segment %s is not contiguous with "
-				"segment %s\n",
-				sort_list[i].segment_name,
-				sort_list[i+1].segment_name);
+			pr_err("Adjacent DCSSs %s and %s are not "
+			       "contiguous\n", sort_list[i].segment_name,
+			       sort_list[i+1].segment_name);
 			rc = -EINVAL;
 			goto out;
 		}
@@ -275,10 +268,10 @@ dcssblk_is_continuous(struct dcssblk_dev_info *dev_info)
 				!(sort_list[i+1].segment_type &
 				SEGMENT_EXCLUSIVE) ||
 				(sort_list[i+1].segment_type == SEG_TYPE_ER)) {
-				PRINT_ERR("Segment %s has different type from "
-					"segment %s\n",
-					sort_list[i].segment_name,
-					sort_list[i+1].segment_name);
+				pr_err("DCSS %s and DCSS %s have "
+				       "incompatible types\n",
+				       sort_list[i].segment_name,
+				       sort_list[i+1].segment_name);
 				rc = -EINVAL;
 				goto out;
 			}
@@ -380,8 +373,9 @@ dcssblk_shared_store(struct device *dev, struct device_attribute *attr, const ch
 	} else if (inbuf[0] == '0') {
 		/* reload segments in exclusive mode */
 		if (dev_info->segment_type == SEG_TYPE_SC) {
-			PRINT_ERR("Segment type SC (%s) cannot be loaded in "
-				"non-shared mode\n", dev_info->segment_name);
+			pr_err("DCSS %s is of type SC and cannot be "
+			       "loaded as exclusive-writable\n",
+			       dev_info->segment_name);
 			rc = -EINVAL;
 			goto out;
 		}
@@ -404,9 +398,8 @@ dcssblk_shared_store(struct device *dev, struct device_attribute *attr, const ch
 	goto out;
 
 removeseg:
-	PRINT_ERR("Could not reload segment(s) of the device %s, removing "
-		"segment(s) now!\n",
-		dev_info->segment_name);
+	pr_err("DCSS device %s is removed after a failed access mode "
+	       "change\n", dev_info->segment_name);
 	temp = entry;
 	list_for_each_entry(entry, &dev_info->seg_list, lh) {
 		if (entry != temp)
@@ -454,17 +447,17 @@ dcssblk_save_store(struct device *dev, struct device_attribute *attr, const char
 	if (inbuf[0] == '1') {
 		if (atomic_read(&dev_info->use_count) == 0) {
 			// device is idle => we save immediately
-			PRINT_INFO("Saving segment(s) of the device %s\n",
-				   dev_info->segment_name);
+			pr_info("All DCSSs that map to device %s are "
+				"saved\n", dev_info->segment_name);
 			list_for_each_entry(entry, &dev_info->seg_list, lh) {
 				segment_save(entry->segment_name);
 			}
 		}  else {
 			// device is busy => we save it when it becomes
 			// idle in dcssblk_release
-			PRINT_INFO("Device %s is currently busy, segment(s) "
-				   "will be saved when it becomes idle...\n",
-				   dev_info->segment_name);
+			pr_info("Device %s is in use, its DCSSs will be "
+				"saved when it becomes idle\n",
+				dev_info->segment_name);
 			dev_info->save_pending = 1;
 		}
 	} else if (inbuf[0] == '0') {
@@ -472,9 +465,9 @@ dcssblk_save_store(struct device *dev, struct device_attribute *attr, const char
 			// device is busy & the user wants to undo his save
 			// request
 			dev_info->save_pending = 0;
-			PRINT_INFO("Pending save for segment(s) of the device "
-					"%s deactivated\n",
-					dev_info->segment_name);
+			pr_info("A pending save request for device %s "
+				"has been canceled\n",
+				dev_info->segment_name);
 		}
 	} else {
 		up_write(&dcssblk_devices_sem);
@@ -614,9 +607,8 @@ dcssblk_add_store(struct device *dev, struct device_attribute *attr, const char
 
 	seg_byte_size = (dev_info->end - dev_info->start + 1);
 	set_capacity(dev_info->gd, seg_byte_size >> 9); // size in sectors
-	PRINT_INFO("Loaded segment(s) %s, size = %lu Byte, "
-		   "capacity = %lu (512 Byte) sectors\n", local_buf,
-		   seg_byte_size, seg_byte_size >> 9);
+	pr_info("Loaded %s with total size %lu bytes and capacity %lu "
+		"sectors\n", local_buf, seg_byte_size, seg_byte_size >> 9);
 
 	dev_info->save_pending = 0;
 	dev_info->is_shared = 1;
@@ -744,13 +736,15 @@ dcssblk_remove_store(struct device *dev, struct device_attribute *attr, const ch
 	dev_info = dcssblk_get_device_by_name(local_buf);
 	if (dev_info == NULL) {
 		up_write(&dcssblk_devices_sem);
-		PRINT_WARN("Device %s is not loaded!\n", local_buf);
+		pr_warning("Device %s cannot be removed because it is not a "
+			   "known device\n", local_buf);
 		rc = -ENODEV;
 		goto out_buf;
 	}
 	if (atomic_read(&dev_info->use_count) != 0) {
 		up_write(&dcssblk_devices_sem);
-		PRINT_WARN("Device %s is in use!\n", local_buf);
+		pr_warning("Device %s cannot be removed while it is in "
+			   "use\n", local_buf);
 		rc = -EBUSY;
 		goto out_buf;
 	}
@@ -807,8 +801,8 @@ dcssblk_release(struct gendisk *disk, fmode_t mode)
 	down_write(&dcssblk_devices_sem);
 	if (atomic_dec_and_test(&dev_info->use_count)
 	    && (dev_info->save_pending)) {
-		PRINT_INFO("Device %s became idle and is being saved now\n",
-			    dev_info->segment_name);
+		pr_info("Device %s has become idle and is being saved "
+			"now\n", dev_info->segment_name);
 		list_for_each_entry(entry, &dev_info->seg_list, lh) {
 			segment_save(entry->segment_name);
 		}
@@ -851,7 +845,8 @@ dcssblk_make_request(struct request_queue *q, struct bio *bio)
 		case SEG_TYPE_SC:
 			/* cannot write to these segments */
 			if (bio_data_dir(bio) == WRITE) {
-				PRINT_WARN("rejecting write to ro device %s\n",
+				pr_warning("Writing to %s failed because it "
+					   "is a read-only device\n",
 					   dev_name(&dev_info->dev));
 				goto fail;
 			}
diff --git a/drivers/s390/block/xpram.c b/drivers/s390/block/xpram.c
index 03916989ed2d..76814f3e898a 100644
--- a/drivers/s390/block/xpram.c
+++ b/drivers/s390/block/xpram.c
@@ -25,6 +25,9 @@
  *   generic hard disk support to replace ad-hoc partitioning
  */
 
+#define KMSG_COMPONENT "xpram"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
 #include <linux/module.h>
 #include <linux/moduleparam.h>
 #include <linux/ctype.h>  /* isdigit, isxdigit */
@@ -42,12 +45,6 @@
 #define XPRAM_DEVS	1	/* one partition */
 #define XPRAM_MAX_DEVS	32	/* maximal number of devices (partitions) */
 
-#define PRINT_DEBUG(x...)	printk(KERN_DEBUG XPRAM_NAME " debug:" x)
-#define PRINT_INFO(x...)	printk(KERN_INFO XPRAM_NAME " info:" x)
-#define PRINT_WARN(x...)	printk(KERN_WARNING XPRAM_NAME " warning:" x)
-#define PRINT_ERR(x...)		printk(KERN_ERR XPRAM_NAME " error:" x)
-
-
 typedef struct {
 	unsigned int	size;		/* size of xpram segment in pages */
 	unsigned int	offset;		/* start page of xpram segment */
@@ -264,7 +261,7 @@ static int __init xpram_setup_sizes(unsigned long pages)
 
 	/* Check number of devices. */
 	if (devs <= 0 || devs > XPRAM_MAX_DEVS) {
-		PRINT_ERR("invalid number %d of devices\n",devs);
+		pr_err("%d is not a valid number of XPRAM devices\n",devs);
 		return -EINVAL;
 	}
 	xpram_devs = devs;
@@ -295,22 +292,22 @@ static int __init xpram_setup_sizes(unsigned long pages)
 			mem_auto_no++;
 	}
 	
-	PRINT_INFO("  number of devices (partitions): %d \n", xpram_devs);
+	pr_info("  number of devices (partitions): %d \n", xpram_devs);
 	for (i = 0; i < xpram_devs; i++) {
 		if (xpram_sizes[i])
-			PRINT_INFO("  size of partition %d: %u kB\n",
-				   i, xpram_sizes[i]);
+			pr_info("  size of partition %d: %u kB\n",
+				i, xpram_sizes[i]);
 		else
-			PRINT_INFO("  size of partition %d to be set "
-				   "automatically\n",i);
+			pr_info("  size of partition %d to be set "
+				"automatically\n",i);
 	}
-	PRINT_DEBUG("  memory needed (for sized partitions): %lu kB\n",
-		    mem_needed);
-	PRINT_DEBUG("  partitions to be sized automatically: %d\n",
-		    mem_auto_no);
+	pr_info("  memory needed (for sized partitions): %lu kB\n",
+		mem_needed);
+	pr_info("  partitions to be sized automatically: %d\n",
+		mem_auto_no);
 
 	if (mem_needed > pages * 4) {
-		PRINT_ERR("Not enough expanded memory available\n");
+		pr_err("Not enough expanded memory available\n");
 		return -EINVAL;
 	}
 
@@ -322,8 +319,8 @@ static int __init xpram_setup_sizes(unsigned long pages)
 	 */
 	if (mem_auto_no) {
 		mem_auto = ((pages - mem_needed / 4) / mem_auto_no) * 4;
-		PRINT_INFO("  automatically determined "
-			   "partition size: %lu kB\n", mem_auto);
+		pr_info("  automatically determined "
+			"partition size: %lu kB\n", mem_auto);
 		for (i = 0; i < xpram_devs; i++)
 			if (xpram_sizes[i] == 0)
 				xpram_sizes[i] = mem_auto;
@@ -405,12 +402,12 @@ static int __init xpram_init(void)
 
 	/* Find out size of expanded memory. */
 	if (xpram_present() != 0) {
-		PRINT_WARN("No expanded memory available\n");
+		pr_err("No expanded memory available\n");
 		return -ENODEV;
 	}
 	xpram_pages = xpram_highest_page_index() + 1;
-	PRINT_INFO("  %u pages expanded memory found (%lu KB).\n",
-		   xpram_pages, (unsigned long) xpram_pages*4);
+	pr_info("  %u pages expanded memory found (%lu KB).\n",
+		xpram_pages, (unsigned long) xpram_pages*4);
 	rc = xpram_setup_sizes(xpram_pages);
 	if (rc)
 		return rc;
diff --git a/drivers/s390/char/monreader.c b/drivers/s390/char/monreader.c
index 35fd8dfcaaa6..97e63cf46944 100644
--- a/drivers/s390/char/monreader.c
+++ b/drivers/s390/char/monreader.c
@@ -7,6 +7,9 @@
  *   Author: Gerald Schaefer <gerald.schaefer@de.ibm.com>
  */
 
+#define KMSG_COMPONENT "monreader"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
 #include <linux/module.h>
 #include <linux/moduleparam.h>
 #include <linux/init.h>
@@ -24,19 +27,6 @@
 #include <asm/ebcdic.h>
 #include <asm/extmem.h>
 
-//#define MON_DEBUG			/* Debug messages on/off */
-
-#define MON_NAME "monreader"
-
-#define P_INFO(x...)	printk(KERN_INFO MON_NAME " info: " x)
-#define P_ERROR(x...)	printk(KERN_ERR MON_NAME " error: " x)
-#define P_WARNING(x...)	printk(KERN_WARNING MON_NAME " warning: " x)
-
-#ifdef MON_DEBUG
-#define P_DEBUG(x...)   printk(KERN_DEBUG MON_NAME " debug: " x)
-#else
-#define P_DEBUG(x...)   do {} while (0)
-#endif
 
 #define MON_COLLECT_SAMPLE 0x80
 #define MON_COLLECT_EVENT  0x40
@@ -172,7 +162,7 @@ static int mon_send_reply(struct mon_msg *monmsg,
 	} else
 		monmsg->replied_msglim = 1;
 	if (rc) {
-		P_ERROR("read, IUCV reply failed with rc = %i\n\n", rc);
+		pr_err("Reading monitor data failed with rc=%i\n", rc);
 		return -EIO;
 	}
 	return 0;
@@ -251,7 +241,8 @@ static void mon_iucv_path_severed(struct iucv_path *path, u8 ipuser[16])
 {
 	struct mon_private *monpriv = path->private;
 
-	P_ERROR("IUCV connection severed with rc = 0x%X\n", ipuser[0]);
+	pr_err("z/VM *MONITOR system service disconnected with rc=%i\n",
+	       ipuser[0]);
 	iucv_path_sever(path, NULL);
 	atomic_set(&monpriv->iucv_severed, 1);
 	wake_up(&mon_conn_wait_queue);
@@ -266,8 +257,7 @@ static void mon_iucv_message_pending(struct iucv_path *path,
 	memcpy(&monpriv->msg_array[monpriv->write_index]->msg,
 	       msg, sizeof(*msg));
 	if (atomic_inc_return(&monpriv->msglim_count) == MON_MSGLIM) {
-		P_WARNING("IUCV message pending, message limit (%i) reached\n",
-			  MON_MSGLIM);
+		pr_warning("The read queue for monitor data is full\n");
 		monpriv->msg_array[monpriv->write_index]->msglim_reached = 1;
 	}
 	monpriv->write_index = (monpriv->write_index + 1) % MON_MSGLIM;
@@ -311,8 +301,8 @@ static int mon_open(struct inode *inode, struct file *filp)
 	rc = iucv_path_connect(monpriv->path, &monreader_iucv_handler,
 			       MON_SERVICE, NULL, user_data_connect, monpriv);
 	if (rc) {
-		P_ERROR("iucv connection to *MONITOR failed with "
-			"IPUSER SEVER code = %i\n", rc);
+		pr_err("Connecting to the z/VM *MONITOR system service "
+		       "failed with rc=%i\n", rc);
 		rc = -EIO;
 		goto out_path;
 	}
@@ -353,7 +343,8 @@ static int mon_close(struct inode *inode, struct file *filp)
 	 */
 	rc = iucv_path_sever(monpriv->path, user_data_sever);
 	if (rc)
-		P_ERROR("close, iucv_sever failed with rc = %i\n", rc);
+		pr_warning("Disconnecting the z/VM *MONITOR system service "
+			   "failed with rc=%i\n", rc);
 
 	atomic_set(&monpriv->iucv_severed, 0);
 	atomic_set(&monpriv->iucv_connected, 0);
@@ -469,7 +460,8 @@ static int __init mon_init(void)
 	int rc;
 
 	if (!MACHINE_IS_VM) {
-		P_ERROR("not running under z/VM, driver not loaded\n");
+		pr_err("The z/VM *MONITOR record device driver cannot be "
+		       "loaded without z/VM\n");
 		return -ENODEV;
 	}
 
@@ -478,7 +470,8 @@ static int __init mon_init(void)
 	 */
 	rc = iucv_register(&monreader_iucv_handler, 1);
 	if (rc) {
-		P_ERROR("failed to register with iucv driver\n");
+		pr_err("The z/VM *MONITOR record device driver failed to "
+		       "register with IUCV\n");
 		return rc;
 	}
 
@@ -488,8 +481,8 @@ static int __init mon_init(void)
 		goto out_iucv;
 	}
 	if (rc != SEG_TYPE_SC) {
-		P_ERROR("segment %s has unsupported type, should be SC\n",
-			mon_dcss_name);
+		pr_err("The specified *MONITOR DCSS %s does not have the "
+		       "required type SC\n", mon_dcss_name);
 		rc = -EINVAL;
 		goto out_iucv;
 	}
diff --git a/drivers/s390/char/monwriter.c b/drivers/s390/char/monwriter.c
index 4d71aa8c1a79..c7d7483bab9a 100644
--- a/drivers/s390/char/monwriter.c
+++ b/drivers/s390/char/monwriter.c
@@ -8,6 +8,9 @@
  * Author(s): Melissa Howland <Melissa.Howland@us.ibm.com>
  */
 
+#define KMSG_COMPONENT "monwriter"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
 #include <linux/module.h>
 #include <linux/moduleparam.h>
 #include <linux/init.h>
@@ -64,9 +67,9 @@ static int monwrite_diag(struct monwrite_hdr *myhdr, char *buffer, int fcn)
 	rc = appldata_asm(&id, fcn, (void *) buffer, myhdr->datalen);
 	if (rc <= 0)
 		return rc;
+	pr_err("Writing monitor data failed with rc=%i\n", rc);
 	if (rc == 5)
 		return -EPERM;
-	printk("DIAG X'DC' error with return code: %i\n", rc);
 	return -EINVAL;
 }
 
diff --git a/drivers/s390/char/sclp_cmd.c b/drivers/s390/char/sclp_cmd.c
index ec9c0bcf66ee..506390496416 100644
--- a/drivers/s390/char/sclp_cmd.c
+++ b/drivers/s390/char/sclp_cmd.c
@@ -6,6 +6,9 @@
  *		 Peter Oberparleiter <peter.oberparleiter@de.ibm.com>
  */
 
+#define KMSG_COMPONENT "sclp_cmd"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
 #include <linux/completion.h>
 #include <linux/init.h>
 #include <linux/errno.h>
@@ -16,9 +19,8 @@
 #include <linux/memory.h>
 #include <asm/chpid.h>
 #include <asm/sclp.h>
-#include "sclp.h"
 
-#define TAG	"sclp_cmd: "
+#include "sclp.h"
 
 #define SCLP_CMDW_READ_SCP_INFO		0x00020001
 #define SCLP_CMDW_READ_SCP_INFO_FORCED	0x00120001
@@ -169,8 +171,8 @@ static int do_sync_request(sclp_cmdw_t cmd, void *sccb)
 
 	/* Check response. */
 	if (request->status != SCLP_REQ_DONE) {
-		printk(KERN_WARNING TAG "sync request failed "
-		       "(cmd=0x%08x, status=0x%02x)\n", cmd, request->status);
+		pr_warning("sync request failed (cmd=0x%08x, "
+			   "status=0x%02x)\n", cmd, request->status);
 		rc = -EIO;
 	}
 out:
@@ -224,8 +226,8 @@ int sclp_get_cpu_info(struct sclp_cpu_info *info)
 	if (rc)
 		goto out;
 	if (sccb->header.response_code != 0x0010) {
-		printk(KERN_WARNING TAG "readcpuinfo failed "
-		       "(response=0x%04x)\n", sccb->header.response_code);
+		pr_warning("readcpuinfo failed (response=0x%04x)\n",
+			   sccb->header.response_code);
 		rc = -EIO;
 		goto out;
 	}
@@ -262,8 +264,9 @@ static int do_cpu_configure(sclp_cmdw_t cmd)
 	case 0x0120:
 		break;
 	default:
-		printk(KERN_WARNING TAG "configure cpu failed (cmd=0x%08x, "
-		       "response=0x%04x)\n", cmd, sccb->header.response_code);
+		pr_warning("configure cpu failed (cmd=0x%08x, "
+			   "response=0x%04x)\n", cmd,
+			   sccb->header.response_code);
 		rc = -EIO;
 		break;
 	}
@@ -626,9 +629,9 @@ static int do_chp_configure(sclp_cmdw_t cmd)
 	case 0x0450:
 		break;
 	default:
-		printk(KERN_WARNING TAG "configure channel-path failed "
-		       "(cmd=0x%08x, response=0x%04x)\n", cmd,
-		       sccb->header.response_code);
+		pr_warning("configure channel-path failed "
+			   "(cmd=0x%08x, response=0x%04x)\n", cmd,
+			   sccb->header.response_code);
 		rc = -EIO;
 		break;
 	}
@@ -695,8 +698,8 @@ int sclp_chp_read_info(struct sclp_chp_info *info)
 	if (rc)
 		goto out;
 	if (sccb->header.response_code != 0x0010) {
-		printk(KERN_WARNING TAG "read channel-path info failed "
-		       "(response=0x%04x)\n", sccb->header.response_code);
+		pr_warning("read channel-path info failed "
+			   "(response=0x%04x)\n", sccb->header.response_code);
 		rc = -EIO;
 		goto out;
 	}
diff --git a/drivers/s390/char/sclp_config.c b/drivers/s390/char/sclp_config.c
index 4cebd6ee6d27..b497afe061cc 100644
--- a/drivers/s390/char/sclp_config.c
+++ b/drivers/s390/char/sclp_config.c
@@ -5,15 +5,17 @@
  *    Author(s): Heiko Carstens <heiko.carstens@de.ibm.com>
  */
 
+#define KMSG_COMPONENT "sclp_config"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
 #include <linux/init.h>
 #include <linux/errno.h>
 #include <linux/cpu.h>
 #include <linux/sysdev.h>
 #include <linux/workqueue.h>
 #include <asm/smp.h>
-#include "sclp.h"
 
-#define TAG	"sclp_config: "
+#include "sclp.h"
 
 struct conf_mgm_data {
 	u8 reserved;
@@ -31,7 +33,7 @@ static void sclp_cpu_capability_notify(struct work_struct *work)
 	int cpu;
 	struct sys_device *sysdev;
 
-	printk(KERN_WARNING TAG "cpu capability changed.\n");
+	pr_warning("cpu capability changed.\n");
 	get_online_cpus();
 	for_each_online_cpu(cpu) {
 		sysdev = get_cpu_sysdev(cpu);
@@ -78,7 +80,7 @@ static int __init sclp_conf_init(void)
 		return rc;
 
 	if (!(sclp_conf_register.sclp_send_mask & EVTYP_CONFMGMDATA_MASK)) {
-		printk(KERN_WARNING TAG "no configuration management.\n");
+		pr_warning("no configuration management.\n");
 		sclp_unregister(&sclp_conf_register);
 		rc = -ENOSYS;
 	}
diff --git a/drivers/s390/char/sclp_cpi_sys.c b/drivers/s390/char/sclp_cpi_sys.c
index d887bd261d28..62c2647f37f4 100644
--- a/drivers/s390/char/sclp_cpi_sys.c
+++ b/drivers/s390/char/sclp_cpi_sys.c
@@ -7,6 +7,9 @@
  *		 Michael Ernst <mernst@de.ibm.com>
  */
 
+#define KMSG_COMPONENT "sclp_cpi"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
 #include <linux/kernel.h>
 #include <linux/init.h>
 #include <linux/stat.h>
@@ -20,6 +23,7 @@
 #include <linux/completion.h>
 #include <asm/ebcdic.h>
 #include <asm/sclp.h>
+
 #include "sclp.h"
 #include "sclp_rw.h"
 #include "sclp_cpi_sys.h"
@@ -150,16 +154,16 @@ static int cpi_req(void)
 	wait_for_completion(&completion);
 
 	if (req->status != SCLP_REQ_DONE) {
-		printk(KERN_WARNING "cpi: request failed (status=0x%02x)\n",
-			req->status);
+		pr_warning("request failed (status=0x%02x)\n",
+			   req->status);
 		rc = -EIO;
 		goto out_free_req;
 	}
 
 	response = ((struct cpi_sccb *) req->sccb)->header.response_code;
 	if (response != 0x0020) {
-		printk(KERN_WARNING "cpi: failed with "
-			"response code 0x%x\n", response);
+		pr_warning("request failed with response code 0x%x\n",
+			   response);
 		rc = -EIO;
 	}
 
diff --git a/drivers/s390/char/sclp_sdias.c b/drivers/s390/char/sclp_sdias.c
index 8b854857ba07..6a1c58dc61a7 100644
--- a/drivers/s390/char/sclp_sdias.c
+++ b/drivers/s390/char/sclp_sdias.c
@@ -5,15 +5,18 @@
  * Author(s): Michael Holzheu
  */
 
+#define KMSG_COMPONENT "sclp_sdias"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
 #include <linux/sched.h>
 #include <asm/sclp.h>
 #include <asm/debug.h>
 #include <asm/ipl.h>
+
 #include "sclp.h"
 #include "sclp_rw.h"
 
 #define TRACE(x...) debug_sprintf_event(sdias_dbf, 1, x)
-#define ERROR_MSG(x...) printk ( KERN_ALERT "SDIAS: " x )
 
 #define SDIAS_RETRIES 300
 #define SDIAS_SLEEP_TICKS 50
@@ -131,7 +134,7 @@ int sclp_sdias_blk_count(void)
 
 	rc = sdias_sclp_send(&request);
 	if (rc) {
-		ERROR_MSG("sclp_send failed for get_nr_blocks\n");
+		pr_err("sclp_send failed for get_nr_blocks\n");
 		goto out;
 	}
 	if (sccb.hdr.response_code != 0x0020) {
@@ -145,7 +148,8 @@ int sclp_sdias_blk_count(void)
 			rc = sccb.evbuf.blk_cnt;
 			break;
 		default:
-			ERROR_MSG("SCLP error: %x\n", sccb.evbuf.event_status);
+			pr_err("SCLP error: %x\n",
+			       sccb.evbuf.event_status);
 			rc = -EIO;
 			goto out;
 	}
@@ -201,7 +205,7 @@ int sclp_sdias_copy(void *dest, int start_blk, int nr_blks)
 
 	rc = sdias_sclp_send(&request);
 	if (rc) {
-		ERROR_MSG("sclp_send failed: %x\n", rc);
+		pr_err("sclp_send failed: %x\n", rc);
 		goto out;
 	}
 	if (sccb.hdr.response_code != 0x0020) {
@@ -219,9 +223,9 @@ int sclp_sdias_copy(void *dest, int start_blk, int nr_blks)
 		case EVSTATE_NO_DATA:
 			TRACE("no data\n");
 		default:
-			ERROR_MSG("Error from SCLP while copying hsa. "
-				  "Event status = %x\n",
-				sccb.evbuf.event_status);
+			pr_err("Error from SCLP while copying hsa. "
+			       "Event status = %x\n",
+			       sccb.evbuf.event_status);
 			rc = -EIO;
 	}
 out:
diff --git a/drivers/s390/char/sclp_vt220.c b/drivers/s390/char/sclp_vt220.c
index 9854f19f5e62..a839aa531d7c 100644
--- a/drivers/s390/char/sclp_vt220.c
+++ b/drivers/s390/char/sclp_vt220.c
@@ -583,23 +583,6 @@ sclp_vt220_chars_in_buffer(struct tty_struct *tty)
 	return count;
 }
 
-static void
-__sclp_vt220_flush_buffer(void)
-{
-	unsigned long flags;
-
-	sclp_vt220_emit_current();
-	spin_lock_irqsave(&sclp_vt220_lock, flags);
-	if (timer_pending(&sclp_vt220_timer))
-		del_timer(&sclp_vt220_timer);
-	while (sclp_vt220_outqueue_count > 0) {
-		spin_unlock_irqrestore(&sclp_vt220_lock, flags);
-		sclp_sync_wait();
-		spin_lock_irqsave(&sclp_vt220_lock, flags);
-	}
-	spin_unlock_irqrestore(&sclp_vt220_lock, flags);
-}
-
 /*
  * Pass on all buffers to the hardware. Return only when there are no more
  * buffers pending.
@@ -745,6 +728,22 @@ sclp_vt220_con_device(struct console *c, int *index)
 	return sclp_vt220_driver;
 }
 
+static void __sclp_vt220_flush_buffer(void)
+{
+	unsigned long flags;
+
+	sclp_vt220_emit_current();
+	spin_lock_irqsave(&sclp_vt220_lock, flags);
+	if (timer_pending(&sclp_vt220_timer))
+		del_timer(&sclp_vt220_timer);
+	while (sclp_vt220_outqueue_count > 0) {
+		spin_unlock_irqrestore(&sclp_vt220_lock, flags);
+		sclp_sync_wait();
+		spin_lock_irqsave(&sclp_vt220_lock, flags);
+	}
+	spin_unlock_irqrestore(&sclp_vt220_lock, flags);
+}
+
 static int
 sclp_vt220_notify(struct notifier_block *self,
 			  unsigned long event, void *data)
diff --git a/drivers/s390/char/tape.h b/drivers/s390/char/tape.h
index d0d565a05dfe..c07809c8016a 100644
--- a/drivers/s390/char/tape.h
+++ b/drivers/s390/char/tape.h
@@ -324,8 +324,6 @@ static inline void tape_proc_cleanup (void) {;}
 #endif
 
 /* a function for dumping device sense info */
-extern void tape_dump_sense(struct tape_device *, struct tape_request *,
-			    struct irb *);
 extern void tape_dump_sense_dbf(struct tape_device *, struct tape_request *,
 				struct irb *);
 
diff --git a/drivers/s390/char/tape_34xx.c b/drivers/s390/char/tape_34xx.c
index 22ca34361ed7..6d0d4abdb3e2 100644
--- a/drivers/s390/char/tape_34xx.c
+++ b/drivers/s390/char/tape_34xx.c
@@ -8,6 +8,8 @@
  *		 Martin Schwidefsky <schwidefsky@de.ibm.com>
  */
 
+#define KMSG_COMPONENT "tape"
+
 #include <linux/module.h>
 #include <linux/init.h>
 #include <linux/bio.h>
@@ -18,8 +20,6 @@
 #include "tape.h"
 #include "tape_std.h"
 
-#define PRINTK_HEADER "TAPE_34XX: "
-
 /*
  * Pointer to debug area.
  */
@@ -203,8 +203,7 @@ tape_34xx_unsolicited_irq(struct tape_device *device, struct irb *irb)
 		tape_34xx_schedule_work(device, TO_MSEN);
 	} else {
 		DBF_EVENT(3, "unsol.irq! dev end: %08x\n", device->cdev_id);
-		PRINT_WARN("Unsolicited IRQ (Device End) caught.\n");
-		tape_dump_sense(device, NULL, irb);
+		tape_dump_sense_dbf(device, NULL, irb);
 	}
 	return TAPE_IO_SUCCESS;
 }
@@ -226,9 +225,7 @@ tape_34xx_erp_read_opposite(struct tape_device *device,
 		tape_std_read_backward(device, request);
 		return tape_34xx_erp_retry(request);
 	}
-	if (request->op != TO_RBA)
-		PRINT_ERR("read_opposite called with state:%s\n",
-			  tape_op_verbose[request->op]);
+
 	/*
 	 * We tried to read forward and backward, but hat no
 	 * success -> failed.
@@ -241,13 +238,10 @@ tape_34xx_erp_bug(struct tape_device *device, struct tape_request *request,
 		  struct irb *irb, int no)
 {
 	if (request->op != TO_ASSIGN) {
-		PRINT_WARN("An unexpected condition #%d was caught in "
-			   "tape error recovery.\n", no);
-		PRINT_WARN("Please report this incident.\n");
-		if (request)
-			PRINT_WARN("Operation of tape:%s\n",
-				   tape_op_verbose[request->op]);
-		tape_dump_sense(device, request, irb);
+		dev_err(&device->cdev->dev, "An unexpected condition %d was "
+			"caught in tape error recovery. Please report this "
+			"incident", no);
+		tape_dump_sense_dbf(device, request, irb);
 	}
 	return tape_34xx_erp_failed(request, -EIO);
 }
@@ -261,9 +255,9 @@ tape_34xx_erp_overrun(struct tape_device *device, struct tape_request *request,
 		      struct irb *irb)
 {
 	if (irb->ecw[3] == 0x40) {
-		PRINT_WARN ("Data overrun error between control-unit "
-			    "and drive. Use a faster channel connection, "
-			    "if possible! \n");
+		dev_warn (&device->cdev->dev, "Data overrun error between "
+			"control-unit and drive. Use a faster channel "
+			"connection, if possible!");
 		return tape_34xx_erp_failed(request, -EIO);
 	}
 	return tape_34xx_erp_bug(device, request, irb, -1);
@@ -280,7 +274,8 @@ tape_34xx_erp_sequence(struct tape_device *device,
 		/*
 		 * cu detected incorrect block-id sequence on tape.
 		 */
-		PRINT_WARN("Illegal block-id sequence found!\n");
+		dev_warn (&device->cdev->dev, "Illegal block-id sequence "
+			"found!");
 		return tape_34xx_erp_failed(request, -EIO);
 	}
 	/*
@@ -393,8 +388,6 @@ tape_34xx_unit_check(struct tape_device *device, struct tape_request *request,
 			/* Writing at physical end of volume */
 			return tape_34xx_erp_failed(request, -ENOSPC);
 		default:
-			PRINT_ERR("Invalid op in %s:%i\n",
-				  __func__, __LINE__);
 			return tape_34xx_erp_failed(request, 0);
 		}
 	}
@@ -420,7 +413,7 @@ tape_34xx_unit_check(struct tape_device *device, struct tape_request *request,
 							 irb, -4);
 
 			/* data check is permanent, CU recovery has failed */
-			PRINT_WARN("Permanent read error\n");
+			dev_warn (&device->cdev->dev, "Permanent read error");
 			return tape_34xx_erp_failed(request, -EIO);
 		case 0x25:
 			// a write data check occurred
@@ -433,22 +426,25 @@ tape_34xx_unit_check(struct tape_device *device, struct tape_request *request,
 							 irb, -5);
 
 			// data check is permanent, cu-recovery has failed
-			PRINT_WARN("Permanent write error\n");
+			dev_warn (&device->cdev->dev, "Permanent write error");
 			return tape_34xx_erp_failed(request, -EIO);
 		case 0x26:
 			/* Data Check (read opposite) occurred. */
 			return tape_34xx_erp_read_opposite(device, request);
 		case 0x28:
 			/* ID-Mark at tape start couldn't be written */
-			PRINT_WARN("ID-Mark could not be written.\n");
+			dev_warn (&device->cdev->dev, "ID-Mark could not be "
+				"written.");
 			return tape_34xx_erp_failed(request, -EIO);
 		case 0x31:
 			/* Tape void. Tried to read beyond end of device. */
-			PRINT_WARN("Read beyond end of recorded area.\n");
+			dev_warn (&device->cdev->dev, "Read beyond end of "
+				"recorded area.");
 			return tape_34xx_erp_failed(request, -ENOSPC);
 		case 0x41:
 			/* Record sequence error. */
-			PRINT_WARN("Invalid block-id sequence found.\n");
+			dev_warn (&device->cdev->dev, "Invalid block-id "
+				"sequence found.");
 			return tape_34xx_erp_failed(request, -EIO);
 		default:
 			/* all data checks for 3480 should result in one of
@@ -470,16 +466,12 @@ tape_34xx_unit_check(struct tape_device *device, struct tape_request *request,
 	switch (sense[3]) {
 	case 0x00:
 		/* Unit check with erpa code 0. Report and ignore. */
-		PRINT_WARN("Non-error sense was found. "
-			   "Unit-check will be ignored.\n");
 		return TAPE_IO_SUCCESS;
 	case 0x21:
 		/*
 		 * Data streaming not operational. CU will switch to
 		 * interlock mode. Reissue the command.
 		 */
-		PRINT_WARN("Data streaming not operational. "
-			   "Switching to interlock-mode.\n");
 		return tape_34xx_erp_retry(request);
 	case 0x22:
 		/*
@@ -487,11 +479,7 @@ tape_34xx_unit_check(struct tape_device *device, struct tape_request *request,
 		 * error on the lower interface, internal path not usable,
 		 * or error during cartridge load.
 		 */
-		PRINT_WARN("A path equipment check occurred. One of the "
-			   "following conditions occurred:\n");
-		PRINT_WARN("drive adapter error, buffer error on the lower "
-			   "interface, internal path not usable, error "
-			   "during cartridge load.\n");
+		dev_warn (&device->cdev->dev, "path equipment check occurred.");
 		return tape_34xx_erp_failed(request, -EIO);
 	case 0x24:
 		/*
@@ -514,7 +502,6 @@ tape_34xx_unit_check(struct tape_device *device, struct tape_request *request,
 		 * but the hardware isn't capable to do idrc, or a perform
 		 * subsystem func is issued and the CU is not on-line.
 		 */
-		PRINT_WARN ("Function incompatible. Try to switch off idrc\n");
 		return tape_34xx_erp_failed(request, -EIO);
 	case 0x2a:
 		/*
@@ -552,23 +539,24 @@ tape_34xx_unit_check(struct tape_device *device, struct tape_request *request,
 		 * reading the format id mark or that that format specified
 		 * is not supported by the drive.
 		 */
-		PRINT_WARN("Drive not capable processing the tape format!\n");
+		dev_warn (&device->cdev->dev, "Drive not capable processing "
+			"the tape format!");
 		return tape_34xx_erp_failed(request, -EMEDIUMTYPE);
 	case 0x30:
 		/* The medium is write protected. */
-		PRINT_WARN("Medium is write protected!\n");
+		dev_warn (&device->cdev->dev, "Medium is write protected!");
 		return tape_34xx_erp_failed(request, -EACCES);
 	case 0x32:
 		// Tension loss. We cannot recover this, it's an I/O error.
-		PRINT_WARN("The drive lost tape tension.\n");
+		dev_warn (&device->cdev->dev, "The drive lost tape tension.");
 		return tape_34xx_erp_failed(request, -EIO);
 	case 0x33:
 		/*
 		 * Load Failure. The cartridge was not inserted correctly or
 		 * the tape is not threaded correctly.
 		 */
-		PRINT_WARN("Cartridge load failure. Reload the cartridge "
-			   "and try again.\n");
+		dev_warn (&device->cdev->dev, "Cartridge load failure. Reload "
+			"the cartridge and try again.");
 		tape_34xx_delete_sbid_from(device, 0);
 		return tape_34xx_erp_failed(request, -EIO);
 	case 0x34:
@@ -576,8 +564,8 @@ tape_34xx_unit_check(struct tape_device *device, struct tape_request *request,
 		 * Unload failure. The drive cannot maintain tape tension
 		 * and control tape movement during an unload operation.
 		 */
-		PRINT_WARN("Failure during cartridge unload. "
-			   "Please try manually.\n");
+		dev_warn (&device->cdev->dev, "Failure during cartridge "
+			"unload, try manually.");
 		if (request->op == TO_RUN)
 			return tape_34xx_erp_failed(request, -EIO);
 		return tape_34xx_erp_bug(device, request, irb, sense[3]);
@@ -589,8 +577,8 @@ tape_34xx_unit_check(struct tape_device *device, struct tape_request *request,
 		 * - the cartridge loader does not respond correctly
 		 * - a failure occurs during an index, load, or unload cycle
 		 */
-		PRINT_WARN("Equipment check! Please check the drive and "
-			   "the cartridge loader.\n");
+		dev_warn (&device->cdev->dev, "Equipment check! Please check "
+			"the drive and the cartridge loader.");
 		return tape_34xx_erp_failed(request, -EIO);
 	case 0x36:
 		if (device->cdev->id.driver_info == tape_3490)
@@ -603,7 +591,7 @@ tape_34xx_unit_check(struct tape_device *device, struct tape_request *request,
 		 * Tape length error. The tape is shorter than reported in
 		 * the beginning-of-tape data.
 		 */
-		PRINT_WARN("Tape length error.\n");
+		dev_warn (&device->cdev->dev, "Tape length error.");
 		return tape_34xx_erp_failed(request, -EIO);
 	case 0x38:
 		/*
@@ -620,12 +608,14 @@ tape_34xx_unit_check(struct tape_device *device, struct tape_request *request,
 		return tape_34xx_erp_failed(request, -EIO);
 	case 0x3a:
 		/* Drive switched to not ready. */
-		PRINT_WARN("Drive not ready. Turn the ready/not ready switch "
-			   "to ready position and try again.\n");
+		dev_warn (&device->cdev->dev, "Drive not ready. Turn the "
+			"ready/not ready switch to ready position and try "
+			"again.");
 		return tape_34xx_erp_failed(request, -EIO);
 	case 0x3b:
 		/* Manual rewind or unload. This causes an I/O error. */
-		PRINT_WARN("Medium was rewound or unloaded manually.\n");
+		dev_warn (&device->cdev->dev, "Medium was rewound or unloaded"
+			" manually.");
 		tape_34xx_delete_sbid_from(device, 0);
 		return tape_34xx_erp_failed(request, -EIO);
 	case 0x42:
@@ -633,7 +623,8 @@ tape_34xx_unit_check(struct tape_device *device, struct tape_request *request,
 		 * Degraded mode. A condition that can cause degraded
 		 * performance is detected.
 		 */
-		PRINT_WARN("Subsystem is running in degraded mode.\n");
+		dev_warn (&device->cdev->dev, "Subsystem is running in "
+			"degraded mode.");
 		return tape_34xx_erp_retry(request);
 	case 0x43:
 		/* Drive not ready. */
@@ -652,7 +643,6 @@ tape_34xx_unit_check(struct tape_device *device, struct tape_request *request,
 					break;
 			}
 		}
-		PRINT_WARN("The drive is not ready.\n");
 		return tape_34xx_erp_failed(request, -ENOMEDIUM);
 	case 0x44:
 		/* Locate Block unsuccessful. */
@@ -663,7 +653,8 @@ tape_34xx_unit_check(struct tape_device *device, struct tape_request *request,
 		return tape_34xx_erp_failed(request, -EIO);
 	case 0x45:
 		/* The drive is assigned to a different channel path. */
-		PRINT_WARN("The drive is assigned elsewhere.\n");
+		dev_warn (&device->cdev->dev, "The drive is assigned "
+			"elsewhere.");
 		return tape_34xx_erp_failed(request, -EIO);
 	case 0x46:
 		/*
@@ -671,11 +662,12 @@ tape_34xx_unit_check(struct tape_device *device, struct tape_request *request,
 		 * the power supply may be switched off or
 		 * the drive address may not be set correctly.
 		 */
-		PRINT_WARN("The drive is not on-line.");
+		dev_warn (&device->cdev->dev, "The drive is not on-line.");
 		return tape_34xx_erp_failed(request, -EIO);
 	case 0x47:
 		/* Volume fenced. CU reports volume integrity is lost. */
-		PRINT_WARN("Volume fenced. The volume integrity is lost.\n");
+		dev_warn (&device->cdev->dev, "Volume fenced. The volume "
+			"integrity is lost.");
 		tape_34xx_delete_sbid_from(device, 0);
 		return tape_34xx_erp_failed(request, -EIO);
 	case 0x48:
@@ -683,20 +675,21 @@ tape_34xx_unit_check(struct tape_device *device, struct tape_request *request,
 		return tape_34xx_erp_retry(request);
 	case 0x49:
 		/* Bus out check. A parity check error on the bus was found. */
-		PRINT_WARN("Bus out check. A data transfer over the bus "
-			   "has been corrupted.\n");
+		dev_warn (&device->cdev->dev, "Bus out check. A data transfer"
+			   "over the bus has been corrupted.");
 		return tape_34xx_erp_failed(request, -EIO);
 	case 0x4a:
 		/* Control unit erp failed. */
-		PRINT_WARN("The control unit I/O error recovery failed.\n");
+		dev_warn (&device->cdev->dev, "The control unit I/O error "
+			"recovery failed.");
 		return tape_34xx_erp_failed(request, -EIO);
 	case 0x4b:
 		/*
 		 * CU and drive incompatible. The drive requests micro-program
 		 * patches, which are not available on the CU.
 		 */
-		PRINT_WARN("The drive needs microprogram patches from the "
-			   "control unit, which are not available.\n");
+		dev_warn (&device->cdev->dev, "The drive needs microprogram "
+			"patches from the control unit, which are not available.");
 		return tape_34xx_erp_failed(request, -EIO);
 	case 0x4c:
 		/*
@@ -721,8 +714,8 @@ tape_34xx_unit_check(struct tape_device *device, struct tape_request *request,
 			 * the block to be written is larger than allowed for
 			 * buffered mode.
 			 */
-			PRINT_WARN("Maximum block size for buffered "
-				   "mode exceeded.\n");
+			dev_warn (&device->cdev->dev, "Maximum block size for"
+				" buffered mode exceeded.");
 			return tape_34xx_erp_failed(request, -ENOBUFS);
 		}
 		/* This erpa is reserved for 3480. */
@@ -759,22 +752,20 @@ tape_34xx_unit_check(struct tape_device *device, struct tape_request *request,
 		return tape_34xx_erp_retry(request);
 	case 0x55:
 		/* Channel interface recovery (permanent). */
-		PRINT_WARN("A permanent channel interface error occurred.\n");
+		dev_warn (&device->cdev->dev, "A permanent channel interface "
+			"error occurred.");
 		return tape_34xx_erp_failed(request, -EIO);
 	case 0x56:
 		/* Channel protocol error. */
-		PRINT_WARN("A channel protocol error occurred.\n");
+		dev_warn (&device->cdev->dev, "A channel protocol error "
+			"occurred.");
 		return tape_34xx_erp_failed(request, -EIO);
 	case 0x57:
 		if (device->cdev->id.driver_info == tape_3480) {
 			/* Attention intercept. */
-			PRINT_WARN("An attention intercept occurred, "
-				   "which will be recovered.\n");
 			return tape_34xx_erp_retry(request);
 		} else {
 			/* Global status intercept. */
-			PRINT_WARN("An global status intercept was received, "
-				   "which will be recovered.\n");
 			return tape_34xx_erp_retry(request);
 		}
 	case 0x5a:
@@ -782,42 +773,27 @@ tape_34xx_unit_check(struct tape_device *device, struct tape_request *request,
 		 * Tape length incompatible. The tape inserted is too long,
 		 * which could cause damage to the tape or the drive.
 		 */
-		PRINT_WARN("Tape Length Incompatible\n");
-		PRINT_WARN("Tape length exceeds IBM enhanced capacity "
-			"cartdridge length or a medium\n");
-		PRINT_WARN("with EC-CST identification mark has been mounted "
-			"in a device that writes\n");
-		PRINT_WARN("3480 or 3480 XF format.\n");
+		dev_warn (&device->cdev->dev, "Tape Length Incompatible");
 		return tape_34xx_erp_failed(request, -EIO);
 	case 0x5b:
 		/* Format 3480 XF incompatible */
 		if (sense[1] & SENSE_BEGINNING_OF_TAPE)
 			/* The tape will get overwritten. */
 			return tape_34xx_erp_retry(request);
-		PRINT_WARN("Format 3480 XF Incompatible\n");
-		PRINT_WARN("Medium has been created in 3480 format. "
-			"To change the format writes\n");
-		PRINT_WARN("must be issued at BOT.\n");
+		dev_warn (&device->cdev->dev, "Format 3480 XF Incompatible");
 		return tape_34xx_erp_failed(request, -EIO);
 	case 0x5c:
 		/* Format 3480-2 XF incompatible */
-		PRINT_WARN("Format 3480-2 XF Incompatible\n");
-		PRINT_WARN("Device can only read 3480 or 3480 XF format.\n");
+		dev_warn (&device->cdev->dev, "Format 3480-2 XF Incompatible");
 		return tape_34xx_erp_failed(request, -EIO);
 	case 0x5d:
 		/* Tape length violation. */
-		PRINT_WARN("Tape Length Violation\n");
-		PRINT_WARN("The mounted tape exceeds IBM Enhanced Capacity "
-			"Cartdridge System Tape length.\n");
-		PRINT_WARN("This may cause damage to the drive or tape when "
-			"processing to the EOV\n");
+		dev_warn (&device->cdev->dev, "Tape Length Violation");
 		return tape_34xx_erp_failed(request, -EMEDIUMTYPE);
 	case 0x5e:
 		/* Compaction algorithm incompatible. */
-		PRINT_WARN("Compaction Algorithm Incompatible\n");
-		PRINT_WARN("The volume is recorded using an incompatible "
-			"compaction algorithm,\n");
-		PRINT_WARN("which is not supported by the device.\n");
+		dev_warn (&device->cdev->dev, "Compaction Algorithm "
+			"Incompatible");
 		return tape_34xx_erp_failed(request, -EMEDIUMTYPE);
 
 		/* The following erpas should have been covered earlier. */
@@ -848,7 +824,6 @@ tape_34xx_irq(struct tape_device *device, struct tape_request *request,
 	    (irb->scsw.cmd.dstat & DEV_STAT_DEV_END) &&
 	    (request->op == TO_WRI)) {
 		/* Write at end of volume */
-		PRINT_INFO("End of volume\n"); /* XXX */
 		return tape_34xx_erp_failed(request, -ENOSPC);
 	}
 
@@ -869,9 +844,7 @@ tape_34xx_irq(struct tape_device *device, struct tape_request *request,
 	}
 
 	DBF_EVENT(6, "xunknownirq\n");
-	PRINT_ERR("Unexpected interrupt.\n");
-	PRINT_ERR("Current op is: %s", tape_op_verbose[request->op]);
-	tape_dump_sense(device, request, irb);
+	tape_dump_sense_dbf(device, request, irb);
 	return TAPE_IO_STOP;
 }
 
diff --git a/drivers/s390/char/tape_3590.c b/drivers/s390/char/tape_3590.c
index 4005c44a404c..77e9e430a1b8 100644
--- a/drivers/s390/char/tape_3590.c
+++ b/drivers/s390/char/tape_3590.c
@@ -8,12 +8,15 @@
  *		 Martin Schwidefsky <schwidefsky@de.ibm.com>
  */
 
+#define KMSG_COMPONENT "tape"
+
 #include <linux/module.h>
 #include <linux/init.h>
 #include <linux/bio.h>
 #include <asm/ebcdic.h>
 
 #define TAPE_DBF_AREA	tape_3590_dbf
+#define BUFSIZE 512	/* size of buffers for dynamic generated messages */
 
 #include "tape.h"
 #include "tape_std.h"
@@ -36,7 +39,7 @@ EXPORT_SYMBOL(TAPE_DBF_AREA);
  * - Read Alternate:		 implemented
  *******************************************************************/
 
-#define PRINTK_HEADER "TAPE_3590: "
+#define KMSG_COMPONENT "tape"
 
 static const char *tape_3590_msg[TAPE_3590_MAX_MSG] = {
 	[0x00] = "",
@@ -726,7 +729,7 @@ static void tape_3590_med_state_set(struct tape_device *device,
 	}
 	c_info->medium_status |= TAPE390_MEDIUM_LOADED_MASK;
 	if (sense->flags & MSENSE_CRYPT_MASK) {
-		PRINT_INFO("Medium is encrypted (%04x)\n", sense->flags);
+		DBF_EVENT(6, "Medium is encrypted (%04x)\n", sense->flags);
 		c_info->medium_status |= TAPE390_MEDIUM_ENCRYPTED_MASK;
 	} else	{
 		DBF_EVENT(6, "Medium is not encrypted %04x\n", sense->flags);
@@ -847,8 +850,7 @@ tape_3590_unsolicited_irq(struct tape_device *device, struct irb *irb)
 		tape_3590_schedule_work(device, TO_READ_ATTMSG);
 	} else {
 		DBF_EVENT(3, "unsol.irq! dev end: %08x\n", device->cdev_id);
-		PRINT_WARN("Unsolicited IRQ (Device End) caught.\n");
-		tape_dump_sense(device, NULL, irb);
+		tape_dump_sense_dbf(device, NULL, irb);
 	}
 	/* check medium state */
 	tape_3590_schedule_work(device, TO_MSEN);
@@ -876,8 +878,6 @@ tape_3590_erp_basic(struct tape_device *device, struct tape_request *request,
 	case SENSE_BRA_DRE:
 		return tape_3590_erp_failed(device, request, irb, rc);
 	default:
-		PRINT_ERR("Unknown BRA %x - This should not happen!\n",
-			  sense->bra);
 		BUG();
 		return TAPE_IO_STOP;
 	}
@@ -910,7 +910,7 @@ tape_3590_erp_swap(struct tape_device *device, struct tape_request *request,
 	 * should proceed with the new tape... this
 	 * should probably be done in user space!
 	 */
-	PRINT_WARN("(%s): Swap Tape Device!\n", dev_name(&device->cdev->dev));
+	dev_warn (&device->cdev->dev, "Swap Tape Device!");
 	return tape_3590_erp_basic(device, request, irb, -EIO);
 }
 
@@ -985,8 +985,6 @@ tape_3590_erp_read_opposite(struct tape_device *device,
 		return tape_3590_erp_failed(device, request, irb, -EIO);
 		break;
 	default:
-		PRINT_WARN("read_opposite_recovery_called_with_op: %s\n",
-			   tape_op_verbose[request->op]);
 		return tape_3590_erp_failed(device, request, irb, -EIO);
 	}
 }
@@ -998,50 +996,61 @@ static void
 tape_3590_print_mim_msg_f0(struct tape_device *device, struct irb *irb)
 {
 	struct tape_3590_sense *sense;
+	char *exception, *service;
+
+	exception = kmalloc(BUFSIZE, GFP_ATOMIC);
+	service = kmalloc(BUFSIZE, GFP_ATOMIC);
+
+	if (!exception || !service)
+		goto out_nomem;
 
 	sense = (struct tape_3590_sense *) irb->ecw;
 	/* Exception Message */
 	switch (sense->fmt.f70.emc) {
 	case 0x02:
-		PRINT_WARN("(%s): Data degraded\n",
-			   dev_name(&device->cdev->dev));
+		snprintf(exception, BUFSIZE, "Data degraded");
 		break;
 	case 0x03:
-		PRINT_WARN("(%s): Data degraded in partion %i\n",
-			   dev_name(&device->cdev->dev), sense->fmt.f70.mp);
+		snprintf(exception, BUFSIZE, "Data degraded in partion %i",
+			sense->fmt.f70.mp);
 		break;
 	case 0x04:
-		PRINT_WARN("(%s): Medium degraded\n",
-			   dev_name(&device->cdev->dev));
+		snprintf(exception, BUFSIZE, "Medium degraded");
 		break;
 	case 0x05:
-		PRINT_WARN("(%s): Medium degraded in partition %i\n",
-			   dev_name(&device->cdev->dev), sense->fmt.f70.mp);
+		snprintf(exception, BUFSIZE, "Medium degraded in partition %i",
+			sense->fmt.f70.mp);
 		break;
 	case 0x06:
-		PRINT_WARN("(%s): Block 0 Error\n",
-			   dev_name(&device->cdev->dev));
+		snprintf(exception, BUFSIZE, "Block 0 Error");
 		break;
 	case 0x07:
-		PRINT_WARN("(%s): Medium Exception 0x%02x\n",
-			   dev_name(&device->cdev->dev), sense->fmt.f70.md);
+		snprintf(exception, BUFSIZE, "Medium Exception 0x%02x",
+			sense->fmt.f70.md);
 		break;
 	default:
-		PRINT_WARN("(%s): MIM ExMsg: 0x%02x\n",
-			   dev_name(&device->cdev->dev), sense->fmt.f70.emc);
+		snprintf(exception, BUFSIZE, "0x%02x",
+			sense->fmt.f70.emc);
 		break;
 	}
 	/* Service Message */
 	switch (sense->fmt.f70.smc) {
 	case 0x02:
-		PRINT_WARN("(%s): Reference Media maintenance procedure %i\n",
-			   dev_name(&device->cdev->dev), sense->fmt.f70.md);
+		snprintf(service, BUFSIZE, "Reference Media maintenance "
+			"procedure %i", sense->fmt.f70.md);
 		break;
 	default:
-		PRINT_WARN("(%s): MIM ServiceMsg: 0x%02x\n",
-			   dev_name(&device->cdev->dev), sense->fmt.f70.smc);
+		snprintf(service, BUFSIZE, "0x%02x",
+			sense->fmt.f70.smc);
 		break;
 	}
+
+	dev_warn (&device->cdev->dev, "Media information: exception %s, "
+		"service %s", exception, service);
+
+out_nomem:
+	kfree(exception);
+	kfree(service);
 }
 
 /*
@@ -1051,108 +1060,108 @@ static void
 tape_3590_print_io_sim_msg_f1(struct tape_device *device, struct irb *irb)
 {
 	struct tape_3590_sense *sense;
+	char *exception, *service;
+
+	exception = kmalloc(BUFSIZE, GFP_ATOMIC);
+	service = kmalloc(BUFSIZE, GFP_ATOMIC);
+
+	if (!exception || !service)
+		goto out_nomem;
 
 	sense = (struct tape_3590_sense *) irb->ecw;
 	/* Exception Message */
 	switch (sense->fmt.f71.emc) {
 	case 0x01:
-		PRINT_WARN("(%s): Effect of failure is unknown\n",
-			   dev_name(&device->cdev->dev));
+		snprintf(exception, BUFSIZE, "Effect of failure is unknown");
 		break;
 	case 0x02:
-		PRINT_WARN("(%s): CU Exception - no performance impact\n",
-			   dev_name(&device->cdev->dev));
+		snprintf(exception, BUFSIZE, "CU Exception - no performance "
+			"impact");
 		break;
 	case 0x03:
-		PRINT_WARN("(%s): CU Exception on channel interface 0x%02x\n",
-			   dev_name(&device->cdev->dev), sense->fmt.f71.md[0]);
+		snprintf(exception, BUFSIZE, "CU Exception on channel "
+			"interface 0x%02x", sense->fmt.f71.md[0]);
 		break;
 	case 0x04:
-		PRINT_WARN("(%s): CU Exception on device path 0x%02x\n",
-			   dev_name(&device->cdev->dev), sense->fmt.f71.md[0]);
+		snprintf(exception, BUFSIZE, "CU Exception on device path "
+			"0x%02x", sense->fmt.f71.md[0]);
 		break;
 	case 0x05:
-		PRINT_WARN("(%s): CU Exception on library path 0x%02x\n",
-			   dev_name(&device->cdev->dev), sense->fmt.f71.md[0]);
+		snprintf(exception, BUFSIZE, "CU Exception on library path "
+			"0x%02x", sense->fmt.f71.md[0]);
 		break;
 	case 0x06:
-		PRINT_WARN("(%s): CU Exception on node 0x%02x\n",
-			   dev_name(&device->cdev->dev), sense->fmt.f71.md[0]);
+		snprintf(exception, BUFSIZE, "CU Exception on node 0x%02x",
+			sense->fmt.f71.md[0]);
 		break;
 	case 0x07:
-		PRINT_WARN("(%s): CU Exception on partition 0x%02x\n",
-			   dev_name(&device->cdev->dev), sense->fmt.f71.md[0]);
+		snprintf(exception, BUFSIZE, "CU Exception on partition "
+			"0x%02x", sense->fmt.f71.md[0]);
 		break;
 	default:
-		PRINT_WARN("(%s): SIM ExMsg: 0x%02x\n",
-			   dev_name(&device->cdev->dev), sense->fmt.f71.emc);
+		snprintf(exception, BUFSIZE, "0x%02x",
+			sense->fmt.f71.emc);
 	}
 	/* Service Message */
 	switch (sense->fmt.f71.smc) {
 	case 0x01:
-		PRINT_WARN("(%s): Repair impact is unknown\n",
-			   dev_name(&device->cdev->dev));
+		snprintf(service, BUFSIZE, "Repair impact is unknown");
 		break;
 	case 0x02:
-		PRINT_WARN("(%s): Repair will not impact cu performance\n",
-			   dev_name(&device->cdev->dev));
+		snprintf(service, BUFSIZE, "Repair will not impact cu "
+			"performance");
 		break;
 	case 0x03:
 		if (sense->fmt.f71.mdf == 0)
-			PRINT_WARN("(%s): Repair will disable node "
-				   "0x%x on CU\n",
-				   dev_name(&device->cdev->dev),
-				   sense->fmt.f71.md[1]);
+			snprintf(service, BUFSIZE, "Repair will disable node "
+				"0x%x on CU", sense->fmt.f71.md[1]);
 		else
-			PRINT_WARN("(%s): Repair will disable nodes "
-				   "(0x%x-0x%x) on CU\n",
-				   dev_name(&device->cdev->dev),
-				   sense->fmt.f71.md[1], sense->fmt.f71.md[2]);
+			snprintf(service, BUFSIZE, "Repair will disable "
+				"nodes (0x%x-0x%x) on CU", sense->fmt.f71.md[1],
+				sense->fmt.f71.md[2]);
 		break;
 	case 0x04:
 		if (sense->fmt.f71.mdf == 0)
-			PRINT_WARN("(%s): Repair will disable cannel path "
-				   "0x%x on CU\n",
-				   dev_name(&device->cdev->dev),
-				   sense->fmt.f71.md[1]);
+			snprintf(service, BUFSIZE, "Repair will disable "
+				"channel path 0x%x on CU",
+				sense->fmt.f71.md[1]);
 		else
-			PRINT_WARN("(%s): Repair will disable cannel paths "
-				   "(0x%x-0x%x) on CU\n",
-				   dev_name(&device->cdev->dev),
-				   sense->fmt.f71.md[1], sense->fmt.f71.md[2]);
+			snprintf(service, BUFSIZE, "Repair will disable cannel"
+				" paths (0x%x-0x%x) on CU",
+				sense->fmt.f71.md[1], sense->fmt.f71.md[2]);
 		break;
 	case 0x05:
 		if (sense->fmt.f71.mdf == 0)
-			PRINT_WARN("(%s): Repair will disable device path "
-				   "0x%x on CU\n",
-				   dev_name(&device->cdev->dev),
-				   sense->fmt.f71.md[1]);
+			snprintf(service, BUFSIZE, "Repair will disable device"
+				" path 0x%x on CU", sense->fmt.f71.md[1]);
 		else
-			PRINT_WARN("(%s): Repair will disable device paths "
-				   "(0x%x-0x%x) on CU\n",
-				   dev_name(&device->cdev->dev),
-				   sense->fmt.f71.md[1], sense->fmt.f71.md[2]);
+			snprintf(service, BUFSIZE, "Repair will disable device"
+				" paths (0x%x-0x%x) on CU",
+				sense->fmt.f71.md[1], sense->fmt.f71.md[2]);
 		break;
 	case 0x06:
 		if (sense->fmt.f71.mdf == 0)
-			PRINT_WARN("(%s): Repair will disable library path "
-				   "0x%x on CU\n",
-				   dev_name(&device->cdev->dev),
-				   sense->fmt.f71.md[1]);
+			snprintf(service, BUFSIZE, "Repair will disable "
+				"library path 0x%x on CU",
+				sense->fmt.f71.md[1]);
 		else
-			PRINT_WARN("(%s): Repair will disable library paths "
-				   "(0x%x-0x%x) on CU\n",
-				   dev_name(&device->cdev->dev),
-				   sense->fmt.f71.md[1], sense->fmt.f71.md[2]);
+			snprintf(service, BUFSIZE, "Repair will disable "
+				"library paths (0x%x-0x%x) on CU",
+				sense->fmt.f71.md[1], sense->fmt.f71.md[2]);
 		break;
 	case 0x07:
-		PRINT_WARN("(%s): Repair will disable access to CU\n",
-			   dev_name(&device->cdev->dev));
+		snprintf(service, BUFSIZE, "Repair will disable access to CU");
 		break;
 	default:
-		PRINT_WARN("(%s): SIM ServiceMsg: 0x%02x\n",
-			   dev_name(&device->cdev->dev), sense->fmt.f71.smc);
+		snprintf(service, BUFSIZE, "0x%02x",
+			sense->fmt.f71.smc);
 	}
+
+	dev_warn (&device->cdev->dev, "I/O subsystem information: exception"
+		" %s, service %s", exception, service);
+out_nomem:
+	kfree(exception);
+	kfree(service);
 }
 
 /*
@@ -1162,111 +1171,109 @@ static void
 tape_3590_print_dev_sim_msg_f2(struct tape_device *device, struct irb *irb)
 {
 	struct tape_3590_sense *sense;
+	char *exception, *service;
+
+	exception = kmalloc(BUFSIZE, GFP_ATOMIC);
+	service = kmalloc(BUFSIZE, GFP_ATOMIC);
+
+	if (!exception || !service)
+		goto out_nomem;
 
 	sense = (struct tape_3590_sense *) irb->ecw;
 	/* Exception Message */
 	switch (sense->fmt.f71.emc) {
 	case 0x01:
-		PRINT_WARN("(%s): Effect of failure is unknown\n",
-			   dev_name(&device->cdev->dev));
+		snprintf(exception, BUFSIZE, "Effect of failure is unknown");
 		break;
 	case 0x02:
-		PRINT_WARN("(%s): DV Exception - no performance impact\n",
-			   dev_name(&device->cdev->dev));
+		snprintf(exception, BUFSIZE, "DV Exception - no performance"
+			" impact");
 		break;
 	case 0x03:
-		PRINT_WARN("(%s): DV Exception on channel interface 0x%02x\n",
-			   dev_name(&device->cdev->dev), sense->fmt.f71.md[0]);
+		snprintf(exception, BUFSIZE, "DV Exception on channel "
+			"interface 0x%02x", sense->fmt.f71.md[0]);
 		break;
 	case 0x04:
-		PRINT_WARN("(%s): DV Exception on loader 0x%02x\n",
-			   dev_name(&device->cdev->dev), sense->fmt.f71.md[0]);
+		snprintf(exception, BUFSIZE, "DV Exception on loader 0x%02x",
+			sense->fmt.f71.md[0]);
 		break;
 	case 0x05:
-		PRINT_WARN("(%s): DV Exception on message display 0x%02x\n",
-			   dev_name(&device->cdev->dev), sense->fmt.f71.md[0]);
+		snprintf(exception, BUFSIZE, "DV Exception on message display"
+			" 0x%02x", sense->fmt.f71.md[0]);
 		break;
 	case 0x06:
-		PRINT_WARN("(%s): DV Exception in tape path\n",
-			   dev_name(&device->cdev->dev));
+		snprintf(exception, BUFSIZE, "DV Exception in tape path");
 		break;
 	case 0x07:
-		PRINT_WARN("(%s): DV Exception in drive\n",
-			   dev_name(&device->cdev->dev));
+		snprintf(exception, BUFSIZE, "DV Exception in drive");
 		break;
 	default:
-		PRINT_WARN("(%s): DSIM ExMsg: 0x%02x\n",
-			   dev_name(&device->cdev->dev), sense->fmt.f71.emc);
+		snprintf(exception, BUFSIZE, "0x%02x",
+			sense->fmt.f71.emc);
 	}
 	/* Service Message */
 	switch (sense->fmt.f71.smc) {
 	case 0x01:
-		PRINT_WARN("(%s): Repair impact is unknown\n",
-			   dev_name(&device->cdev->dev));
+		snprintf(service, BUFSIZE, "Repair impact is unknown");
 		break;
 	case 0x02:
-		PRINT_WARN("(%s): Repair will not impact device performance\n",
-			   dev_name(&device->cdev->dev));
+		snprintf(service, BUFSIZE, "Repair will not impact device "
+			"performance");
 		break;
 	case 0x03:
 		if (sense->fmt.f71.mdf == 0)
-			PRINT_WARN("(%s): Repair will disable channel path "
-				   "0x%x on DV\n",
-				   dev_name(&device->cdev->dev),
-				   sense->fmt.f71.md[1]);
+			snprintf(service, BUFSIZE, "Repair will disable "
+				"channel path 0x%x on DV",
+				sense->fmt.f71.md[1]);
 		else
-			PRINT_WARN("(%s): Repair will disable channel path "
-				   "(0x%x-0x%x) on DV\n",
-				   dev_name(&device->cdev->dev),
-				   sense->fmt.f71.md[1], sense->fmt.f71.md[2]);
+			snprintf(service, BUFSIZE, "Repair will disable "
+				"channel path (0x%x-0x%x) on DV",
+				sense->fmt.f71.md[1], sense->fmt.f71.md[2]);
 		break;
 	case 0x04:
 		if (sense->fmt.f71.mdf == 0)
-			PRINT_WARN("(%s): Repair will disable interface 0x%x "
-				   "on DV\n",
-				   dev_name(&device->cdev->dev),
-				   sense->fmt.f71.md[1]);
+			snprintf(service, BUFSIZE, "Repair will disable "
+				"interface 0x%x on DV", sense->fmt.f71.md[1]);
 		else
-			PRINT_WARN("(%s): Repair will disable interfaces "
-				   "(0x%x-0x%x) on DV\n",
-				   dev_name(&device->cdev->dev),
-				   sense->fmt.f71.md[1], sense->fmt.f71.md[2]);
+			snprintf(service, BUFSIZE, "Repair will disable "
+				"interfaces (0x%x-0x%x) on DV",
+				sense->fmt.f71.md[1], sense->fmt.f71.md[2]);
 		break;
 	case 0x05:
 		if (sense->fmt.f71.mdf == 0)
-			PRINT_WARN("(%s): Repair will disable loader 0x%x "
-				   "on DV\n",
-				   dev_name(&device->cdev->dev),
-				   sense->fmt.f71.md[1]);
+			snprintf(service, BUFSIZE, "Repair will disable loader"
+				" 0x%x on DV", sense->fmt.f71.md[1]);
 		else
-			PRINT_WARN("(%s): Repair will disable loader "
-				   "(0x%x-0x%x) on DV\n",
-				   dev_name(&device->cdev->dev),
-				   sense->fmt.f71.md[1], sense->fmt.f71.md[2]);
+			snprintf(service, BUFSIZE, "Repair will disable loader"
+				" (0x%x-0x%x) on DV",
+				sense->fmt.f71.md[1], sense->fmt.f71.md[2]);
 		break;
 	case 0x07:
-		PRINT_WARN("(%s): Repair will disable access to DV\n",
-			   dev_name(&device->cdev->dev));
+		snprintf(service, BUFSIZE, "Repair will disable access to DV");
 		break;
 	case 0x08:
 		if (sense->fmt.f71.mdf == 0)
-			PRINT_WARN("(%s): Repair will disable message "
-				   "display 0x%x on DV\n",
-				   dev_name(&device->cdev->dev),
-				   sense->fmt.f71.md[1]);
+			snprintf(service, BUFSIZE, "Repair will disable "
+				"message display 0x%x on DV",
+				sense->fmt.f71.md[1]);
 		else
-			PRINT_WARN("(%s): Repair will disable message "
-				   "displays (0x%x-0x%x) on DV\n",
-				   dev_name(&device->cdev->dev),
-				   sense->fmt.f71.md[1], sense->fmt.f71.md[2]);
+			snprintf(service, BUFSIZE, "Repair will disable "
+				"message displays (0x%x-0x%x) on DV",
+				 sense->fmt.f71.md[1], sense->fmt.f71.md[2]);
 		break;
 	case 0x09:
-		PRINT_WARN("(%s): Clean DV\n", dev_name(&device->cdev->dev));
+		snprintf(service, BUFSIZE, "Clean DV");
 		break;
 	default:
-		PRINT_WARN("(%s): DSIM ServiceMsg: 0x%02x\n",
-			   dev_name(&device->cdev->dev), sense->fmt.f71.smc);
+		snprintf(service, BUFSIZE, "0x%02x",
+			sense->fmt.f71.smc);
 	}
+
+	dev_warn (&device->cdev->dev, "Device subsystem information: exception"
+		" %s, service %s", exception, service);
+out_nomem:
+	kfree(exception);
+	kfree(service);
 }
 
 /*
@@ -1282,46 +1289,42 @@ tape_3590_print_era_msg(struct tape_device *device, struct irb *irb)
 		return;
 	if ((sense->mc > 0) && (sense->mc < TAPE_3590_MAX_MSG)) {
 		if (tape_3590_msg[sense->mc] != NULL)
-			PRINT_WARN("(%s): %s\n", dev_name(&device->cdev->dev),
-				   tape_3590_msg[sense->mc]);
-		else {
-			PRINT_WARN("(%s): Message Code 0x%x\n",
-				   dev_name(&device->cdev->dev), sense->mc);
-		}
+			dev_warn (&device->cdev->dev, "Tape sense message: %s",
+				tape_3590_msg[sense->mc]);
+		else
+			dev_warn (&device->cdev->dev, "Tape sense message code"
+				" 0x%x", sense->mc);
 		return;
 	}
 	if (sense->mc == 0xf0) {
 		/* Standard Media Information Message */
-		PRINT_WARN("(%s): MIM SEV=%i, MC=%02x, ES=%x/%x, "
-			   "RC=%02x-%04x-%02x\n", dev_name(&device->cdev->dev),
-			   sense->fmt.f70.sev, sense->mc,
-			   sense->fmt.f70.emc, sense->fmt.f70.smc,
-			   sense->fmt.f70.refcode, sense->fmt.f70.mid,
-			   sense->fmt.f70.fid);
+		dev_warn (&device->cdev->dev, "MIM SEV=%i, MC=%02x, ES=%x/%x, "
+			"RC=%02x-%04x-%02x", sense->fmt.f70.sev, sense->mc,
+			sense->fmt.f70.emc, sense->fmt.f70.smc,
+			sense->fmt.f70.refcode, sense->fmt.f70.mid,
+			sense->fmt.f70.fid);
 		tape_3590_print_mim_msg_f0(device, irb);
 		return;
 	}
 	if (sense->mc == 0xf1) {
 		/* Standard I/O Subsystem Service Information Message */
-		PRINT_WARN("(%s): IOSIM SEV=%i, DEVTYPE=3590/%02x, "
-			   "MC=%02x, ES=%x/%x, REF=0x%04x-0x%04x-0x%04x\n",
-			   dev_name(&device->cdev->dev), sense->fmt.f71.sev,
-			   device->cdev->id.dev_model,
-			   sense->mc, sense->fmt.f71.emc,
-			   sense->fmt.f71.smc, sense->fmt.f71.refcode1,
-			   sense->fmt.f71.refcode2, sense->fmt.f71.refcode3);
+		dev_warn (&device->cdev->dev, "IOSIM SEV=%i, DEVTYPE=3590/%02x,"
+			" MC=%02x, ES=%x/%x, REF=0x%04x-0x%04x-0x%04x",
+			sense->fmt.f71.sev, device->cdev->id.dev_model,
+			sense->mc, sense->fmt.f71.emc, sense->fmt.f71.smc,
+			sense->fmt.f71.refcode1, sense->fmt.f71.refcode2,
+			sense->fmt.f71.refcode3);
 		tape_3590_print_io_sim_msg_f1(device, irb);
 		return;
 	}
 	if (sense->mc == 0xf2) {
 		/* Standard Device Service Information Message */
-		PRINT_WARN("(%s): DEVSIM SEV=%i, DEVTYPE=3590/%02x, "
-			   "MC=%02x, ES=%x/%x, REF=0x%04x-0x%04x-0x%04x\n",
-			   dev_name(&device->cdev->dev), sense->fmt.f71.sev,
-			   device->cdev->id.dev_model,
-			   sense->mc, sense->fmt.f71.emc,
-			   sense->fmt.f71.smc, sense->fmt.f71.refcode1,
-			   sense->fmt.f71.refcode2, sense->fmt.f71.refcode3);
+		dev_warn (&device->cdev->dev, "DEVSIM SEV=%i, DEVTYPE=3590/%02x"
+			", MC=%02x, ES=%x/%x, REF=0x%04x-0x%04x-0x%04x",
+			sense->fmt.f71.sev, device->cdev->id.dev_model,
+			sense->mc, sense->fmt.f71.emc, sense->fmt.f71.smc,
+			sense->fmt.f71.refcode1, sense->fmt.f71.refcode2,
+			sense->fmt.f71.refcode3);
 		tape_3590_print_dev_sim_msg_f2(device, irb);
 		return;
 	}
@@ -1329,8 +1332,7 @@ tape_3590_print_era_msg(struct tape_device *device, struct irb *irb)
 		/* Standard Library Service Information Message */
 		return;
 	}
-	PRINT_WARN("(%s): Device Message(%x)\n",
-		   dev_name(&device->cdev->dev), sense->mc);
+	dev_warn (&device->cdev->dev, "Device Message(%x)", sense->mc);
 }
 
 static int tape_3590_crypt_error(struct tape_device *device,
@@ -1355,9 +1357,7 @@ static int tape_3590_crypt_error(struct tape_device *device,
 		/* No connection to EKM */
 		return tape_3590_erp_basic(device, request, irb, -ENOTCONN);
 
-	PRINT_ERR("(%s): Unable to get encryption key from EKM\n", bus_id);
-	PRINT_ERR("(%s): CU=%02X DRIVE=%06X EKM=%02X:%04X\n", bus_id, cu_rc,
-		drv_rc, ekm_rc1, ekm_rc2);
+	dev_err (&device->cdev->dev, "Unable to get encryption key from EKM");
 
 	return tape_3590_erp_basic(device, request, irb, -ENOKEY);
 }
@@ -1443,8 +1443,6 @@ tape_3590_unit_check(struct tape_device *device, struct tape_request *request,
 		 * print additional msg since default msg
 		 * "device intervention" is not very meaningfull
 		 */
-		PRINT_WARN("(%s): Tape operation when medium not loaded\n",
-			   dev_name(&device->cdev->dev));
 		tape_med_state_set(device, MS_UNLOADED);
 		tape_3590_schedule_work(device, TO_CRYPT_OFF);
 		return tape_3590_erp_basic(device, request, irb, -ENOMEDIUM);
@@ -1490,19 +1488,14 @@ tape_3590_unit_check(struct tape_device *device, struct tape_request *request,
 		return tape_3590_erp_basic(device, request, irb, -ENOMEDIUM);
 
 	case 0x6020:
-		PRINT_WARN("(%s): Cartridge of wrong type ?\n",
-			   dev_name(&device->cdev->dev));
 		return tape_3590_erp_basic(device, request, irb, -EMEDIUMTYPE);
 
 	case 0x8011:
-		PRINT_WARN("(%s): Another host has reserved the tape device\n",
-			   dev_name(&device->cdev->dev));
 		return tape_3590_erp_basic(device, request, irb, -EPERM);
 	case 0x8013:
-		PRINT_WARN("(%s): Another host has privileged access to the "
-			   "tape device\n", dev_name(&device->cdev->dev));
-		PRINT_WARN("(%s): To solve the problem unload the current "
-			   "cartridge!\n", dev_name(&device->cdev->dev));
+		dev_warn (&device->cdev->dev, "Another host has privileged "
+			"access to the tape device, To solve the problem "
+			"unload the current cartridge!");
 		return tape_3590_erp_basic(device, request, irb, -EPERM);
 	default:
 		return tape_3590_erp_basic(device, request, irb, -EIO);
@@ -1552,9 +1545,7 @@ tape_3590_irq(struct tape_device *device, struct tape_request *request,
 	}
 
 	DBF_EVENT(6, "xunknownirq\n");
-	PRINT_ERR("Unexpected interrupt.\n");
-	PRINT_ERR("Current op is: %s", tape_op_verbose[request->op]);
-	tape_dump_sense(device, request, irb);
+	tape_dump_sense_dbf(device, request, irb);
 	return TAPE_IO_STOP;
 }
 
@@ -1609,7 +1600,6 @@ tape_3590_setup_device(struct tape_device *device)
 	if (rc)
 		goto fail_rdc_data;
 	if (rdc_data->data[31] == 0x13) {
-		PRINT_INFO("Device has crypto support\n");
 		data->crypt_info.capability |= TAPE390_CRYPT_SUPPORTED_MASK;
 		tape_3592_disable_crypt(device);
 	} else {
diff --git a/drivers/s390/char/tape_block.c b/drivers/s390/char/tape_block.c
index ae18baf59f06..feb23be5ce53 100644
--- a/drivers/s390/char/tape_block.c
+++ b/drivers/s390/char/tape_block.c
@@ -10,6 +10,8 @@
  *		 Stefan Bader <shbader@de.ibm.com>
  */
 
+#define KMSG_COMPONENT "tape_block"
+
 #include <linux/fs.h>
 #include <linux/module.h>
 #include <linux/blkdev.h>
@@ -23,8 +25,6 @@
 
 #include "tape.h"
 
-#define PRINTK_HEADER "TAPE_BLOCK: "
-
 #define TAPEBLOCK_MAX_SEC	100
 #define TAPEBLOCK_MIN_REQUEUE	3
 
@@ -279,8 +279,6 @@ tapeblock_cleanup_device(struct tape_device *device)
 	tape_put_device(device);
 
 	if (!device->blk_data.disk) {
-		PRINT_ERR("(%s): No gendisk to clean up!\n",
-			dev_name(&device->cdev->dev));
 		goto cleanup_queue;
 	}
 
@@ -314,7 +312,7 @@ tapeblock_revalidate_disk(struct gendisk *disk)
 	if (!device->blk_data.medium_changed)
 		return 0;
 
-	PRINT_INFO("Detecting media size...\n");
+	dev_info(&device->cdev->dev, "Detecting media size...");
 	rc = tape_mtop(device, MTFSFM, 1);
 	if (rc)
 		return rc;
@@ -341,7 +339,8 @@ tapeblock_revalidate_disk(struct gendisk *disk)
 	device->bof = rc;
 	nr_of_blks -= rc;
 
-	PRINT_INFO("Found %i blocks on media\n", nr_of_blks);
+	dev_info(&device->cdev->dev, "Found %i blocks on media",
+		nr_of_blks);
 	set_capacity(device->blk_data.disk,
 		nr_of_blks*(TAPEBLOCK_HSEC_SIZE/512));
 
@@ -376,8 +375,8 @@ tapeblock_open(struct block_device *bdev, fmode_t mode)
 
 	if (device->required_tapemarks) {
 		DBF_EVENT(2, "TBLOCK: missing tapemarks\n");
-		PRINT_ERR("TBLOCK: Refusing to open tape with missing"
-			" end of file marks.\n");
+		dev_warn(&device->cdev->dev, "Refusing to open tape with"
+			" missing end of file marks.");
 		rc = -EPERM;
 		goto put_device;
 	}
@@ -452,7 +451,6 @@ tapeblock_ioctl(
 			rc = -EINVAL;
 			break;
 		default:
-			PRINT_WARN("invalid ioctl 0x%x\n", command);
 			rc = -EINVAL;
 	}
 
@@ -474,7 +472,6 @@ tapeblock_init(void)
 
 	if (tapeblock_major == 0)
 		tapeblock_major = rc;
-	PRINT_INFO("tape gets major %d for block device\n", tapeblock_major);
 	return 0;
 }
 
diff --git a/drivers/s390/char/tape_char.c b/drivers/s390/char/tape_char.c
index be0ce2215c8d..31566c55adfe 100644
--- a/drivers/s390/char/tape_char.c
+++ b/drivers/s390/char/tape_char.c
@@ -24,8 +24,6 @@
 #include "tape_std.h"
 #include "tape_class.h"
 
-#define PRINTK_HEADER "TAPE_CHAR: "
-
 #define TAPECHAR_MAJOR		0	/* get dynamic major */
 
 /*
@@ -102,8 +100,6 @@ tapechar_check_idalbuffer(struct tape_device *device, size_t block_size)
 	if (block_size > MAX_BLOCKSIZE) {
 		DBF_EVENT(3, "Invalid blocksize (%zd > %d)\n",
 			block_size, MAX_BLOCKSIZE);
-		PRINT_ERR("Invalid blocksize (%zd> %d)\n",
-			block_size, MAX_BLOCKSIZE);
 		return -EINVAL;
 	}
 
@@ -485,7 +481,6 @@ tapechar_init (void)
 		return -1;
 
 	tapechar_major = MAJOR(dev);
-	PRINT_INFO("tape gets major %d for character devices\n", MAJOR(dev));
 
 	return 0;
 }
@@ -496,7 +491,5 @@ tapechar_init (void)
 void
 tapechar_exit(void)
 {
-	PRINT_INFO("tape releases major %d for character devices\n",
-		tapechar_major);
 	unregister_chrdev_region(MKDEV(tapechar_major, 0), 256);
 }
diff --git a/drivers/s390/char/tape_core.c b/drivers/s390/char/tape_core.c
index f9bb51fa7f5b..e00a6a61bba8 100644
--- a/drivers/s390/char/tape_core.c
+++ b/drivers/s390/char/tape_core.c
@@ -11,6 +11,7 @@
  *		 Stefan Bader <shbader@de.ibm.com>
  */
 
+#define KMSG_COMPONENT "tape"
 #include <linux/module.h>
 #include <linux/init.h>	     // for kernel parameters
 #include <linux/kmod.h>	     // for requesting modules
@@ -25,7 +26,6 @@
 #include "tape.h"
 #include "tape_std.h"
 
-#define PRINTK_HEADER "TAPE_CORE: "
 #define LONG_BUSY_TIMEOUT 180 /* seconds */
 
 static void __tape_do_irq (struct ccw_device *, unsigned long, struct irb *);
@@ -214,13 +214,11 @@ tape_med_state_set(struct tape_device *device, enum tape_medium_state newstate)
 	switch(newstate){
 	case MS_UNLOADED:
 		device->tape_generic_status |= GMT_DR_OPEN(~0);
-		PRINT_INFO("(%s): Tape is unloaded\n",
-			   dev_name(&device->cdev->dev));
+		dev_info(&device->cdev->dev, "Tape is unloaded");
 		break;
 	case MS_LOADED:
 		device->tape_generic_status &= ~GMT_DR_OPEN(~0);
-		PRINT_INFO("(%s): Tape has been mounted\n",
-			   dev_name(&device->cdev->dev));
+		dev_info(&device->cdev->dev, "Tape has been mounted");
 		break;
 	default:
 		// print nothing
@@ -333,7 +331,6 @@ tape_generic_online(struct tape_device *device,
 	/* Let the discipline have a go at the device. */
 	device->discipline = discipline;
 	if (!try_module_get(discipline->owner)) {
-		PRINT_ERR("Cannot get module. Module gone.\n");
 		return -EINVAL;
 	}
 
@@ -391,7 +388,6 @@ int
 tape_generic_offline(struct tape_device *device)
 {
 	if (!device) {
-		PRINT_ERR("tape_generic_offline: no such device\n");
 		return -ENODEV;
 	}
 
@@ -413,9 +409,6 @@ tape_generic_offline(struct tape_device *device)
 			DBF_EVENT(3, "(%08x): Set offline failed "
 				"- drive in use.\n",
 				device->cdev_id);
-			PRINT_WARN("(%s): Set offline failed "
-				"- drive in use.\n",
-				dev_name(&device->cdev->dev));
 			spin_unlock_irq(get_ccwdev_lock(device->cdev));
 			return -EBUSY;
 	}
@@ -435,14 +428,11 @@ tape_alloc_device(void)
 	device = kzalloc(sizeof(struct tape_device), GFP_KERNEL);
 	if (device == NULL) {
 		DBF_EXCEPTION(2, "ti:no mem\n");
-		PRINT_INFO ("can't allocate memory for "
-			    "tape info structure\n");
 		return ERR_PTR(-ENOMEM);
 	}
 	device->modeset_byte = kmalloc(1, GFP_KERNEL | GFP_DMA);
 	if (device->modeset_byte == NULL) {
 		DBF_EXCEPTION(2, "ti:no mem\n");
-		PRINT_INFO("can't allocate memory for modeset byte\n");
 		kfree(device);
 		return ERR_PTR(-ENOMEM);
 	}
@@ -490,7 +480,6 @@ tape_put_device(struct tape_device *device)
 	} else {
 		if (remain < 0) {
 			DBF_EVENT(4, "put device without reference\n");
-			PRINT_ERR("put device without reference\n");
 		} else {
 			DBF_EVENT(4, "tape_free_device(%p)\n", device);
 			kfree(device->modeset_byte);
@@ -538,8 +527,6 @@ tape_generic_probe(struct ccw_device *cdev)
 	ret = sysfs_create_group(&cdev->dev.kobj, &tape_attr_group);
 	if (ret) {
 		tape_put_device(device);
-		PRINT_ERR("probe failed for tape device %s\n",
-			  dev_name(&cdev->dev));
 		return ret;
 	}
 	cdev->dev.driver_data = device;
@@ -547,7 +534,6 @@ tape_generic_probe(struct ccw_device *cdev)
 	device->cdev = cdev;
 	ccw_device_get_id(cdev, &dev_id);
 	device->cdev_id = devid_to_int(&dev_id);
-	PRINT_INFO("tape device %s found\n", dev_name(&cdev->dev));
 	return ret;
 }
 
@@ -584,7 +570,6 @@ tape_generic_remove(struct ccw_device *cdev)
 
 	device = cdev->dev.driver_data;
 	if (!device) {
-		PRINT_ERR("No device pointer in tape_generic_remove!\n");
 		return;
 	}
 	DBF_LH(3, "(%08x): tape_generic_remove(%p)\n", device->cdev_id, cdev);
@@ -615,10 +600,8 @@ tape_generic_remove(struct ccw_device *cdev)
 			 */
 			DBF_EVENT(3, "(%08x): Drive in use vanished!\n",
 				device->cdev_id);
-			PRINT_WARN("(%s): Drive in use vanished - "
-				"expect trouble!\n",
-				dev_name(&device->cdev->dev));
-			PRINT_WARN("State was %i\n", device->tape_state);
+			dev_warn(&device->cdev->dev, "Drive in use vanished - "
+				"expect trouble!");
 			tape_state_set(device, TS_NOT_OPER);
 			__tape_discard_requests(device);
 			spin_unlock_irq(get_ccwdev_lock(device->cdev));
@@ -830,30 +813,6 @@ __tape_end_request(
 }
 
 /*
- * Write sense data to console/dbf
- */
-void
-tape_dump_sense(struct tape_device* device, struct tape_request *request,
-		struct irb *irb)
-{
-	unsigned int *sptr;
-
-	PRINT_INFO("-------------------------------------------------\n");
-	PRINT_INFO("DSTAT : %02x  CSTAT: %02x	CPA: %04x\n",
-		   irb->scsw.cmd.dstat, irb->scsw.cmd.cstat, irb->scsw.cmd.cpa);
-	PRINT_INFO("DEVICE: %s\n", dev_name(&device->cdev->dev));
-	if (request != NULL)
-		PRINT_INFO("OP	  : %s\n", tape_op_verbose[request->op]);
-
-	sptr = (unsigned int *) irb->ecw;
-	PRINT_INFO("Sense data: %08X %08X %08X %08X \n",
-		   sptr[0], sptr[1], sptr[2], sptr[3]);
-	PRINT_INFO("Sense data: %08X %08X %08X %08X \n",
-		   sptr[4], sptr[5], sptr[6], sptr[7]);
-	PRINT_INFO("--------------------------------------------------\n");
-}
-
-/*
  * Write sense data to dbf
  */
 void
@@ -1051,8 +1010,6 @@ __tape_do_irq (struct ccw_device *cdev, unsigned long intparm, struct irb *irb)
 
 	device = (struct tape_device *) cdev->dev.driver_data;
 	if (device == NULL) {
-		PRINT_ERR("could not get device structure for %s "
-			  "in interrupt\n", dev_name(&cdev->dev));
 		return;
 	}
 	request = (struct tape_request *) intparm;
@@ -1064,13 +1021,13 @@ __tape_do_irq (struct ccw_device *cdev, unsigned long intparm, struct irb *irb)
 		/* FIXME: What to do with the request? */
 		switch (PTR_ERR(irb)) {
 			case -ETIMEDOUT:
-				PRINT_WARN("(%s): Request timed out\n",
+				DBF_LH(1, "(%s): Request timed out\n",
 					dev_name(&cdev->dev));
 			case -EIO:
 				__tape_end_request(device, request, -EIO);
 				break;
 			default:
-				PRINT_ERR("(%s): Unexpected i/o error %li\n",
+				DBF_LH(1, "(%s): Unexpected i/o error %li\n",
 					dev_name(&cdev->dev),
 					PTR_ERR(irb));
 		}
@@ -1182,8 +1139,6 @@ __tape_do_irq (struct ccw_device *cdev, unsigned long intparm, struct irb *irb)
 		default:
 			if (rc > 0) {
 				DBF_EVENT(6, "xunknownrc\n");
-				PRINT_ERR("Invalid return code from discipline "
-				  	"interrupt function.\n");
 				__tape_end_request(device, request, -EIO);
 			} else {
 				__tape_end_request(device, request, rc);
@@ -1323,7 +1278,6 @@ EXPORT_SYMBOL(tape_state_set);
 EXPORT_SYMBOL(tape_med_state_set);
 EXPORT_SYMBOL(tape_alloc_request);
 EXPORT_SYMBOL(tape_free_request);
-EXPORT_SYMBOL(tape_dump_sense);
 EXPORT_SYMBOL(tape_dump_sense_dbf);
 EXPORT_SYMBOL(tape_do_io);
 EXPORT_SYMBOL(tape_do_io_async);
diff --git a/drivers/s390/char/tape_proc.c b/drivers/s390/char/tape_proc.c
index 8a376af926a7..202f42132939 100644
--- a/drivers/s390/char/tape_proc.c
+++ b/drivers/s390/char/tape_proc.c
@@ -20,8 +20,6 @@
 
 #include "tape.h"
 
-#define PRINTK_HEADER "TAPE_PROC: "
-
 static const char *tape_med_st_verbose[MS_SIZE] =
 {
 	[MS_UNKNOWN] = "UNKNOWN ",
@@ -128,7 +126,6 @@ tape_proc_init(void)
 		proc_create("tapedevices", S_IFREG | S_IRUGO | S_IWUSR, NULL,
 			    &tape_proc_ops);
 	if (tape_proc_devices == NULL) {
-		PRINT_WARN("tape: Cannot register procfs entry tapedevices\n");
 		return;
 	}
 }
diff --git a/drivers/s390/char/tape_std.c b/drivers/s390/char/tape_std.c
index 5bd573d144d6..44dd0f80c847 100644
--- a/drivers/s390/char/tape_std.c
+++ b/drivers/s390/char/tape_std.c
@@ -26,8 +26,6 @@
 #include "tape.h"
 #include "tape_std.h"
 
-#define PRINTK_HEADER "TAPE_STD: "
-
 /*
  * tape_std_assign
  */
@@ -46,9 +44,8 @@ tape_std_assign_timeout(unsigned long data)
 			device->cdev_id);
 	rc = tape_cancel_io(device, request);
 	if(rc)
-		PRINT_ERR("(%s): Assign timeout: Cancel failed with rc = %i\n",
+		DBF_EVENT(3, "(%s): Assign timeout: Cancel failed with rc = %i\n",
 			dev_name(&device->cdev->dev), rc);
-
 }
 
 int
@@ -82,8 +79,6 @@ tape_std_assign(struct tape_device *device)
 	del_timer(&timeout);
 
 	if (rc != 0) {
-		PRINT_WARN("%s: assign failed - device might be busy\n",
-			dev_name(&device->cdev->dev));
 		DBF_EVENT(3, "%08x: assign failed - device might be busy\n",
 			device->cdev_id);
 	} else {
@@ -105,8 +100,6 @@ tape_std_unassign (struct tape_device *device)
 	if (device->tape_state == TS_NOT_OPER) {
 		DBF_EVENT(3, "(%08x): Can't unassign device\n",
 			device->cdev_id);
-		PRINT_WARN("(%s): Can't unassign device - device gone\n",
-			dev_name(&device->cdev->dev));
 		return -EIO;
 	}
 
@@ -120,8 +113,6 @@ tape_std_unassign (struct tape_device *device)
 
 	if ((rc = tape_do_io(device, request)) != 0) {
 		DBF_EVENT(3, "%08x: Unassign failed\n", device->cdev_id);
-		PRINT_WARN("%s: Unassign failed\n",
-			   dev_name(&device->cdev->dev));
 	} else {
 		DBF_EVENT(3, "%08x: Tape unassigned\n", device->cdev_id);
 	}
@@ -242,8 +233,6 @@ tape_std_mtsetblk(struct tape_device *device, int count)
 	if (count > MAX_BLOCKSIZE) {
 		DBF_EVENT(3, "Invalid block size (%d > %d) given.\n",
 			count, MAX_BLOCKSIZE);
-		PRINT_ERR("Invalid block size (%d > %d) given.\n",
-			count, MAX_BLOCKSIZE);
 		return -EINVAL;
 	}
 
@@ -633,14 +622,6 @@ tape_std_mtcompression(struct tape_device *device, int mt_count)
 
 	if (mt_count < 0 || mt_count > 1) {
 		DBF_EXCEPTION(6, "xcom parm\n");
-		if (*device->modeset_byte & 0x08)
-			PRINT_INFO("(%s) Compression is currently on\n",
-				   dev_name(&device->cdev->dev));
-		else
-			PRINT_INFO("(%s) Compression is currently off\n",
-				   dev_name(&device->cdev->dev));
-		PRINT_INFO("Use 1 to switch compression on, 0 to "
-			   "switch it off\n");
 		return -EINVAL;
 	}
 	request = tape_alloc_request(2, 0);
diff --git a/drivers/s390/char/vmcp.c b/drivers/s390/char/vmcp.c
index 09e7d9bf438b..a6087cec55b4 100644
--- a/drivers/s390/char/vmcp.c
+++ b/drivers/s390/char/vmcp.c
@@ -11,12 +11,14 @@
  * The idea of this driver is based on cpint from Neale Ferguson and #CP in CMS
  */
 
+#define KMSG_COMPONENT "vmcp"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
 #include <linux/fs.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/miscdevice.h>
 #include <linux/module.h>
-#include <linux/smp_lock.h>
 #include <asm/cpcmd.h>
 #include <asm/debug.h>
 #include <asm/uaccess.h>
@@ -26,8 +28,6 @@ MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Christian Borntraeger <borntraeger@de.ibm.com>");
 MODULE_DESCRIPTION("z/VM CP interface");
 
-#define PRINTK_HEADER "vmcp: "
-
 static debug_info_t *vmcp_debug;
 
 static int vmcp_open(struct inode *inode, struct file *file)
@@ -41,13 +41,11 @@ static int vmcp_open(struct inode *inode, struct file *file)
 	if (!session)
 		return -ENOMEM;
 
-	lock_kernel();
 	session->bufsize = PAGE_SIZE;
 	session->response = NULL;
 	session->resp_size = 0;
 	mutex_init(&session->mutex);
 	file->private_data = session;
-	unlock_kernel();
 	return nonseekable_open(inode, file);
 }
 
@@ -193,7 +191,8 @@ static int __init vmcp_init(void)
 	int ret;
 
 	if (!MACHINE_IS_VM) {
-		PRINT_WARN("z/VM CP interface is only available under z/VM\n");
+		pr_warning("The z/VM CP interface device driver cannot be "
+			   "loaded without z/VM\n");
 		return -ENODEV;
 	}
 
diff --git a/drivers/s390/char/vmlogrdr.c b/drivers/s390/char/vmlogrdr.c
index 24762727bc27..aabbeb909cc6 100644
--- a/drivers/s390/char/vmlogrdr.c
+++ b/drivers/s390/char/vmlogrdr.c
@@ -10,6 +10,10 @@
  *		   Stefan Weinhuber <wein@de.ibm.com>
  *
  */
+
+#define KMSG_COMPONENT "vmlogrdr"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
 #include <linux/module.h>
 #include <linux/init.h>
 #include <linux/errno.h>
@@ -28,8 +32,6 @@
 #include <linux/smp_lock.h>
 #include <linux/string.h>
 
-
-
 MODULE_AUTHOR
 	("(C) 2004 IBM Corporation by Xenia Tkatschow (xenia@us.ibm.com)\n"
 	 "                            Stefan Weinhuber (wein@de.ibm.com)");
@@ -174,8 +176,7 @@ static void vmlogrdr_iucv_path_severed(struct iucv_path *path, u8 ipuser[16])
 	struct vmlogrdr_priv_t * logptr = path->private;
 	u8 reason = (u8) ipuser[8];
 
-	printk (KERN_ERR "vmlogrdr: connection severed with"
-		" reason %i\n", reason);
+	pr_err("vmlogrdr: connection severed with reason %i\n", reason);
 
 	iucv_path_sever(path, NULL);
 	kfree(path);
@@ -333,8 +334,8 @@ static int vmlogrdr_open (struct inode *inode, struct file *filp)
 	if (logptr->autorecording) {
 		ret = vmlogrdr_recording(logptr,1,logptr->autopurge);
 		if (ret)
-			printk (KERN_WARNING "vmlogrdr: failed to start "
-				"recording automatically\n");
+			pr_warning("vmlogrdr: failed to start "
+				   "recording automatically\n");
 	}
 
 	/* create connection to the system service */
@@ -345,9 +346,9 @@ static int vmlogrdr_open (struct inode *inode, struct file *filp)
 				       logptr->system_service, NULL, NULL,
 				       logptr);
 	if (connect_rc) {
-		printk (KERN_ERR "vmlogrdr: iucv connection to %s "
-			"failed with rc %i \n", logptr->system_service,
-			connect_rc);
+		pr_err("vmlogrdr: iucv connection to %s "
+		       "failed with rc %i \n",
+		       logptr->system_service, connect_rc);
 		goto out_path;
 	}
 
@@ -388,8 +389,8 @@ static int vmlogrdr_release (struct inode *inode, struct file *filp)
 	if (logptr->autorecording) {
 		ret = vmlogrdr_recording(logptr,0,logptr->autopurge);
 		if (ret)
-			printk (KERN_WARNING "vmlogrdr: failed to stop "
-				"recording automatically\n");
+			pr_warning("vmlogrdr: failed to stop "
+				   "recording automatically\n");
 	}
 	logptr->dev_in_use = 0;
 
@@ -823,8 +824,7 @@ static int __init vmlogrdr_init(void)
 	dev_t dev;
 
 	if (! MACHINE_IS_VM) {
-		printk (KERN_ERR "vmlogrdr: not running under VM, "
-				"driver not loaded.\n");
+		pr_err("not running under VM, driver not loaded.\n");
 		return -ENODEV;
 	}
 
diff --git a/drivers/s390/char/vmur.c b/drivers/s390/char/vmur.c
index 9020eba620ee..5dcef81fc9d9 100644
--- a/drivers/s390/char/vmur.c
+++ b/drivers/s390/char/vmur.c
@@ -8,6 +8,9 @@
  *	    Frank Munzert <munzert@de.ibm.com>
  */
 
+#define KMSG_COMPONENT "vmur"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
 #include <linux/cdev.h>
 #include <linux/smp_lock.h>
 
@@ -40,8 +43,6 @@ MODULE_AUTHOR("IBM Corporation");
 MODULE_DESCRIPTION("s390 z/VM virtual unit record device driver");
 MODULE_LICENSE("GPL");
 
-#define PRINTK_HEADER "vmur: "
-
 static dev_t ur_first_dev_maj_min;
 static struct class *vmur_class;
 static struct debug_info *vmur_dbf;
@@ -987,7 +988,8 @@ static int __init ur_init(void)
 	dev_t dev;
 
 	if (!MACHINE_IS_VM) {
-		PRINT_ERR("%s is only available under z/VM.\n", ur_banner);
+		pr_err("The %s cannot be loaded without z/VM\n",
+		       ur_banner);
 		return -ENODEV;
 	}
 
@@ -1006,7 +1008,8 @@ static int __init ur_init(void)
 
 	rc = alloc_chrdev_region(&dev, 0, NUM_MINORS, "vmur");
 	if (rc) {
-		PRINT_ERR("alloc_chrdev_region failed: err = %d\n", rc);
+		pr_err("Kernel function alloc_chrdev_region failed with "
+		       "error code %d\n", rc);
 		goto fail_unregister_driver;
 	}
 	ur_first_dev_maj_min = MKDEV(MAJOR(dev), 0);
@@ -1016,7 +1019,7 @@ static int __init ur_init(void)
 		rc = PTR_ERR(vmur_class);
 		goto fail_unregister_region;
 	}
-	PRINT_INFO("%s loaded.\n", ur_banner);
+	pr_info("%s loaded.\n", ur_banner);
 	return 0;
 
 fail_unregister_region:
@@ -1034,7 +1037,7 @@ static void __exit ur_exit(void)
 	unregister_chrdev_region(ur_first_dev_maj_min, NUM_MINORS);
 	ccw_driver_unregister(&ur_driver);
 	debug_unregister(vmur_dbf);
-	PRINT_INFO("%s unloaded.\n", ur_banner);
+	pr_info("%s unloaded.\n", ur_banner);
 }
 
 module_init(ur_init);
diff --git a/drivers/s390/char/zcore.c b/drivers/s390/char/zcore.c
index 7fd84be11931..eefc6611412e 100644
--- a/drivers/s390/char/zcore.c
+++ b/drivers/s390/char/zcore.c
@@ -9,6 +9,9 @@
  * Author(s): Michael Holzheu
  */
 
+#define KMSG_COMPONENT "zdump"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
 #include <linux/init.h>
 #include <linux/miscdevice.h>
 #include <linux/utsname.h>
@@ -24,8 +27,6 @@
 #include "sclp.h"
 
 #define TRACE(x...) debug_sprintf_event(zcore_dbf, 1, x)
-#define MSG(x...) printk( KERN_ALERT x )
-#define ERROR_MSG(x...) printk ( KERN_ALERT "DUMP: " x )
 
 #define TO_USER		0
 #define TO_KERNEL	1
@@ -563,19 +564,19 @@ static int __init sys_info_init(enum arch_id arch)
 
 	switch (arch) {
 	case ARCH_S390X:
-		MSG("DETECTED 'S390X (64 bit) OS'\n");
+		pr_alert("DETECTED 'S390X (64 bit) OS'\n");
 		sys_info.sa_base = SAVE_AREA_BASE_S390X;
 		sys_info.sa_size = sizeof(struct save_area_s390x);
 		set_s390x_lc_mask(&sys_info.lc_mask);
 		break;
 	case ARCH_S390:
-		MSG("DETECTED 'S390 (32 bit) OS'\n");
+		pr_alert("DETECTED 'S390 (32 bit) OS'\n");
 		sys_info.sa_base = SAVE_AREA_BASE_S390;
 		sys_info.sa_size = sizeof(struct save_area_s390);
 		set_s390_lc_mask(&sys_info.lc_mask);
 		break;
 	default:
-		ERROR_MSG("unknown architecture 0x%x.\n",arch);
+		pr_alert("0x%x is an unknown architecture.\n",arch);
 		return -EINVAL;
 	}
 	sys_info.arch = arch;
@@ -674,7 +675,8 @@ static int __init zcore_init(void)
 
 #ifndef __s390x__
 	if (arch == ARCH_S390X) {
-		ERROR_MSG("32 bit dumper can't dump 64 bit system!\n");
+		pr_alert("The 32-bit dump tool cannot be used for a "
+			 "64-bit system\n");
 		rc = -EINVAL;
 		goto fail;
 	}
diff --git a/drivers/s390/cio/blacklist.c b/drivers/s390/cio/blacklist.c
index 2f547b840ef0..fe00be3675cd 100644
--- a/drivers/s390/cio/blacklist.c
+++ b/drivers/s390/cio/blacklist.c
@@ -9,6 +9,9 @@
  *		 Arnd Bergmann (arndb@de.ibm.com)
  */
 
+#define KMSG_COMPONENT "cio"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
 #include <linux/init.h>
 #include <linux/vmalloc.h>
 #include <linux/slab.h>
@@ -50,9 +53,10 @@ static int blacklist_range(range_action action, unsigned int from_ssid,
 {
 	if ((from_ssid > to_ssid) || ((from_ssid == to_ssid) && (from > to))) {
 		if (msgtrigger)
-			printk(KERN_WARNING "cio: Invalid cio_ignore range "
-			       "0.%x.%04x-0.%x.%04x\n", from_ssid, from,
-			       to_ssid, to);
+			pr_warning("0.%x.%04x to 0.%x.%04x is not a valid "
+				   "range for cio_ignore\n", from_ssid, from,
+				   to_ssid, to);
+
 		return 1;
 	}
 
@@ -140,8 +144,8 @@ static int parse_busid(char *str, unsigned int *cssid, unsigned int *ssid,
 	rc = 0;
 out:
 	if (rc && msgtrigger)
-		printk(KERN_WARNING "cio: Invalid cio_ignore device '%s'\n",
-		       str);
+		pr_warning("%s is not a valid device for the cio_ignore "
+			   "kernel parameter\n", str);
 
 	return rc;
 }
diff --git a/drivers/s390/cio/ccwgroup.c b/drivers/s390/cio/ccwgroup.c
index 3ac2c2019f5e..17fa009d9959 100644
--- a/drivers/s390/cio/ccwgroup.c
+++ b/drivers/s390/cio/ccwgroup.c
@@ -19,6 +19,8 @@
 #include <asm/ccwdev.h>
 #include <asm/ccwgroup.h>
 
+#define CCW_BUS_ID_SIZE		20
+
 /* In Linux 2.4, we had a channel device layer called "chandev"
  * that did all sorts of obscure stuff for networking devices.
  * This is another driver that serves as a replacement for just
@@ -172,7 +174,7 @@ static int __get_next_bus_id(const char **buf, char *bus_id)
 		len = end - start + 1;
 		end++;
 	}
-	if (len < BUS_ID_SIZE) {
+	if (len < CCW_BUS_ID_SIZE) {
 		strlcpy(bus_id, start, len);
 		rc = 0;
 	} else
@@ -181,7 +183,7 @@ static int __get_next_bus_id(const char **buf, char *bus_id)
 	return rc;
 }
 
-static int __is_valid_bus_id(char bus_id[BUS_ID_SIZE])
+static int __is_valid_bus_id(char bus_id[CCW_BUS_ID_SIZE])
 {
 	int cssid, ssid, devno;
 
@@ -213,7 +215,7 @@ int ccwgroup_create_from_string(struct device *root, unsigned int creator_id,
 {
 	struct ccwgroup_device *gdev;
 	int rc, i;
-	char tmp_bus_id[BUS_ID_SIZE];
+	char tmp_bus_id[CCW_BUS_ID_SIZE];
 	const char *curr_buf;
 
 	gdev = kzalloc(sizeof(*gdev) + num_devices * sizeof(gdev->cdev[0]),
diff --git a/drivers/s390/cio/chsc.c b/drivers/s390/cio/chsc.c
index 29826fdd47b8..ebab6ea4659b 100644
--- a/drivers/s390/cio/chsc.c
+++ b/drivers/s390/cio/chsc.c
@@ -8,6 +8,9 @@
  *		 Arnd Bergmann (arndb@de.ibm.com)
  */
 
+#define KMSG_COMPONENT "cio"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
 #include <linux/module.h>
 #include <linux/slab.h>
 #include <linux/init.h>
@@ -333,6 +336,7 @@ static void chsc_process_sei_chp_config(struct chsc_sei_area *sei_area)
 	struct chp_config_data *data;
 	struct chp_id chpid;
 	int num;
+	char *events[3] = {"configure", "deconfigure", "cancel deconfigure"};
 
 	CIO_CRW_EVENT(4, "chsc: channel-path-configuration notification\n");
 	if (sei_area->rs != 0)
@@ -343,8 +347,8 @@ static void chsc_process_sei_chp_config(struct chsc_sei_area *sei_area)
 		if (!chp_test_bit(data->map, num))
 			continue;
 		chpid.id = num;
-		printk(KERN_WARNING "cio: processing configure event %d for "
-		       "chpid %x.%02x\n", data->op, chpid.cssid, chpid.id);
+		pr_notice("Processing %s for channel path %x.%02x\n",
+			  events[data->op], chpid.cssid, chpid.id);
 		switch (data->op) {
 		case 0:
 			chp_cfg_schedule(chpid, 1);
diff --git a/drivers/s390/cio/cio.c b/drivers/s390/cio/cio.c
index 3db2c386546f..36af2636d910 100644
--- a/drivers/s390/cio/cio.c
+++ b/drivers/s390/cio/cio.c
@@ -9,6 +9,9 @@
  *		 Martin Schwidefsky (schwidefsky@de.ibm.com)
  */
 
+#define KMSG_COMPONENT "cio"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
 #include <linux/module.h>
 #include <linux/init.h>
 #include <linux/slab.h>
@@ -104,44 +107,6 @@ cio_get_options (struct subchannel *sch)
        return flags;
 }
 
-/*
- * Use tpi to get a pending interrupt, call the interrupt handler and
- * return a pointer to the subchannel structure.
- */
-static int
-cio_tpi(void)
-{
-	struct tpi_info *tpi_info;
-	struct subchannel *sch;
-	struct irb *irb;
-	int irq_context;
-
-	tpi_info = (struct tpi_info *) __LC_SUBCHANNEL_ID;
-	if (tpi (NULL) != 1)
-		return 0;
-	irb = (struct irb *) __LC_IRB;
-	/* Store interrupt response block to lowcore. */
-	if (tsch (tpi_info->schid, irb) != 0)
-		/* Not status pending or not operational. */
-		return 1;
-	sch = (struct subchannel *)(unsigned long)tpi_info->intparm;
-	if (!sch)
-		return 1;
-	irq_context = in_interrupt();
-	if (!irq_context)
-		local_bh_disable();
-	irq_enter ();
-	spin_lock(sch->lock);
-	memcpy(&sch->schib.scsw, &irb->scsw, sizeof(union scsw));
-	if (sch->driver && sch->driver->irq)
-		sch->driver->irq(sch);
-	spin_unlock(sch->lock);
-	irq_exit ();
-	if (!irq_context)
-		_local_bh_enable();
-	return 1;
-}
-
 static int
 cio_start_handle_notoper(struct subchannel *sch, __u8 lpm)
 {
@@ -687,6 +652,43 @@ static char console_sch_name[10] = "0.x.xxxx";
 static struct io_subchannel_private console_priv;
 static int console_subchannel_in_use;
 
+/*
+ * Use tpi to get a pending interrupt, call the interrupt handler and
+ * return a pointer to the subchannel structure.
+ */
+static int cio_tpi(void)
+{
+	struct tpi_info *tpi_info;
+	struct subchannel *sch;
+	struct irb *irb;
+	int irq_context;
+
+	tpi_info = (struct tpi_info *) __LC_SUBCHANNEL_ID;
+	if (tpi(NULL) != 1)
+		return 0;
+	irb = (struct irb *) __LC_IRB;
+	/* Store interrupt response block to lowcore. */
+	if (tsch(tpi_info->schid, irb) != 0)
+		/* Not status pending or not operational. */
+		return 1;
+	sch = (struct subchannel *)(unsigned long)tpi_info->intparm;
+	if (!sch)
+		return 1;
+	irq_context = in_interrupt();
+	if (!irq_context)
+		local_bh_disable();
+	irq_enter();
+	spin_lock(sch->lock);
+	memcpy(&sch->schib.scsw, &irb->scsw, sizeof(union scsw));
+	if (sch->driver && sch->driver->irq)
+		sch->driver->irq(sch);
+	spin_unlock(sch->lock);
+	irq_exit();
+	if (!irq_context)
+		_local_bh_enable();
+	return 1;
+}
+
 void *cio_get_console_priv(void)
 {
 	return &console_priv;
@@ -780,7 +782,7 @@ cio_probe_console(void)
 	sch_no = cio_get_console_sch_no();
 	if (sch_no == -1) {
 		console_subchannel_in_use = 0;
-		printk(KERN_WARNING "cio: No ccw console found!\n");
+		pr_warning("No CCW console was found\n");
 		return ERR_PTR(-ENODEV);
 	}
 	memset(&console_subchannel, 0, sizeof(struct subchannel));
diff --git a/drivers/s390/cio/cmf.c b/drivers/s390/cio/cmf.c
index a90b28c0be57..12643a815848 100644
--- a/drivers/s390/cio/cmf.c
+++ b/drivers/s390/cio/cmf.c
@@ -25,6 +25,9 @@
  * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
+#define KMSG_COMPONENT "cio"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
 #include <linux/bootmem.h>
 #include <linux/device.h>
 #include <linux/init.h>
@@ -1359,9 +1362,8 @@ static int __init init_cmf(void)
 	default:
 		return 1;
 	}
-
-	printk(KERN_INFO "cio: Channel measurement facility using %s "
-	       "format (%s)\n", format_string, detect_string);
+	pr_info("Channel measurement facility initialized using format "
+		"%s (mode %s)\n", format_string, detect_string);
 	return 0;
 }
 
diff --git a/drivers/s390/cio/css.c b/drivers/s390/cio/css.c
index 76bbb1e74c29..d744aa1981db 100644
--- a/drivers/s390/cio/css.c
+++ b/drivers/s390/cio/css.c
@@ -6,6 +6,10 @@
  *    Author(s): Arnd Bergmann (arndb@de.ibm.com)
  *		 Cornelia Huck (cornelia.huck@de.ibm.com)
  */
+
+#define KMSG_COMPONENT "cio"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
 #include <linux/module.h>
 #include <linux/init.h>
 #include <linux/device.h>
@@ -844,8 +848,8 @@ out:
 	s390_unregister_crw_handler(CRW_RSC_CSS);
 	chsc_free_sei_area();
 	kfree(slow_subchannel_set);
-	printk(KERN_WARNING"cio: failed to initialize css driver (%d)!\n",
-	       ret);
+	pr_alert("The CSS device driver initialization failed with "
+		 "errno=%d\n", ret);
 	return ret;
 }
 
diff --git a/drivers/s390/cio/device.c b/drivers/s390/cio/device.c
index 4e4008325e28..fc0c0abd1271 100644
--- a/drivers/s390/cio/device.c
+++ b/drivers/s390/cio/device.c
@@ -1179,12 +1179,6 @@ static int io_subchannel_probe(struct subchannel *sch)
 		return 0;
 	}
 	io_subchannel_init_fields(sch);
-	/*
-	 * First check if a fitting device may be found amongst the
-	 * disconnected devices or in the orphanage.
-	 */
-	dev_id.devno = sch->schib.pmcw.dev;
-	dev_id.ssid = sch->schid.ssid;
 	rc = sysfs_create_group(&sch->dev.kobj,
 				&io_subchannel_attr_group);
 	if (rc)
@@ -1196,6 +1190,12 @@ static int io_subchannel_probe(struct subchannel *sch)
 		rc = -ENOMEM;
 		goto out_err;
 	}
+	/*
+	 * First check if a fitting device may be found amongst the
+	 * disconnected devices or in the orphanage.
+	 */
+	dev_id.devno = sch->schib.pmcw.dev;
+	dev_id.ssid = sch->schid.ssid;
 	cdev = get_disc_ccwdev_by_dev_id(&dev_id, NULL);
 	if (!cdev)
 		cdev = get_orphaned_ccwdev_by_dev_id(to_css(sch->dev.parent),
@@ -1723,7 +1723,7 @@ __ccwdev_check_busid(struct device *dev, void *id)
 
 	bus_id = id;
 
-	return (strncmp(bus_id, dev_name(dev), BUS_ID_SIZE) == 0);
+	return (strcmp(bus_id, dev_name(dev)) == 0);
 }
 
 
diff --git a/drivers/s390/cio/qdio.h b/drivers/s390/cio/qdio.h
index e3ea1d5f2810..c60f2566d28c 100644
--- a/drivers/s390/cio/qdio.h
+++ b/drivers/s390/cio/qdio.h
@@ -10,6 +10,7 @@
 
 #include <asm/page.h>
 #include <asm/schid.h>
+#include <asm/debug.h>
 #include "chsc.h"
 
 #define QDIO_BUSY_BIT_PATIENCE		100	/* 100 microseconds */
@@ -111,12 +112,12 @@ static inline int do_sqbs(u64 token, unsigned char state, int queue,
 }
 
 static inline int do_eqbs(u64 token, unsigned char *state, int queue,
-			  int *start, int *count)
+			  int *start, int *count, int ack)
 {
 	register unsigned long _ccq asm ("0") = *count;
 	register unsigned long _token asm ("1") = token;
 	unsigned long _queuestart = ((unsigned long)queue << 32) | *start;
-	unsigned long _state = 0;
+	unsigned long _state = (unsigned long)ack << 63;
 
 	asm volatile(
 		"	.insn	rrf,0xB99c0000,%1,%2,0,0"
@@ -133,7 +134,7 @@ static inline int do_eqbs(u64 token, unsigned char *state, int queue,
 static inline int do_sqbs(u64 token, unsigned char state, int queue,
 			  int *start, int *count) { return 0; }
 static inline int do_eqbs(u64 token, unsigned char *state, int queue,
-			  int *start, int *count) { return 0; }
+			  int *start, int *count, int ack) { return 0; }
 #endif /* CONFIG_64BIT */
 
 struct qdio_irq;
@@ -186,11 +187,11 @@ struct qdio_input_q {
 	/* input buffer acknowledgement flag */
 	int polling;
 
+	/* how much sbals are acknowledged with qebsm */
+	int ack_count;
+
 	/* last time of noticing incoming data */
 	u64 timestamp;
-
-	/* lock for clearing the acknowledgement */
-	spinlock_t lock;
 };
 
 struct qdio_output_q {
@@ -300,11 +301,13 @@ struct qdio_irq {
 	struct qdio_q *input_qs[QDIO_MAX_QUEUES_PER_IRQ];
 	struct qdio_q *output_qs[QDIO_MAX_QUEUES_PER_IRQ];
 
+	debug_info_t *debug_area;
 	struct mutex setup_mutex;
 };
 
 /* helper functions */
 #define queue_type(q)	q->irq_ptr->qib.qfmt
+#define SCH_NO(q)	(q->irq_ptr->schid.sch_no)
 
 #define is_thinint_irq(irq) \
 	(irq->qib.qfmt == QDIO_IQDIO_QFMT || \
@@ -348,10 +351,13 @@ static inline unsigned long long get_usecs(void)
 	((bufnr + 1) & QDIO_MAX_BUFFERS_MASK)
 #define add_buf(bufnr, inc) \
 	((bufnr + inc) & QDIO_MAX_BUFFERS_MASK)
+#define sub_buf(bufnr, dec) \
+	((bufnr - dec) & QDIO_MAX_BUFFERS_MASK)
 
 /* prototypes for thin interrupt */
 void qdio_sync_after_thinint(struct qdio_q *q);
-int get_buf_state(struct qdio_q *q, unsigned int bufnr, unsigned char *state);
+int get_buf_state(struct qdio_q *q, unsigned int bufnr, unsigned char *state,
+		  int auto_ack);
 void qdio_check_outbound_after_thinint(struct qdio_q *q);
 int qdio_inbound_q_moved(struct qdio_q *q);
 void qdio_kick_inbound_handler(struct qdio_q *q);
@@ -378,10 +384,15 @@ void qdio_int_handler(struct ccw_device *cdev, unsigned long intparm,
 int qdio_allocate_qs(struct qdio_irq *irq_ptr, int nr_input_qs,
 		     int nr_output_qs);
 void qdio_setup_ssqd_info(struct qdio_irq *irq_ptr);
+int qdio_setup_get_ssqd(struct qdio_irq *irq_ptr,
+			struct subchannel_id *schid,
+			struct qdio_ssqd_desc *data);
 int qdio_setup_irq(struct qdio_initialize *init_data);
 void qdio_print_subchannel_info(struct qdio_irq *irq_ptr,
 				struct ccw_device *cdev);
 void qdio_release_memory(struct qdio_irq *irq_ptr);
+int qdio_setup_create_sysfs(struct ccw_device *cdev);
+void qdio_setup_destroy_sysfs(struct ccw_device *cdev);
 int qdio_setup_init(void);
 void qdio_setup_exit(void);
 
diff --git a/drivers/s390/cio/qdio_debug.c b/drivers/s390/cio/qdio_debug.c
index f05590355be8..f8a3b6967f69 100644
--- a/drivers/s390/cio/qdio_debug.c
+++ b/drivers/s390/cio/qdio_debug.c
@@ -14,7 +14,7 @@
 #include "qdio.h"
 
 debug_info_t *qdio_dbf_setup;
-debug_info_t *qdio_dbf_trace;
+debug_info_t *qdio_dbf_error;
 
 static struct dentry *debugfs_root;
 #define MAX_DEBUGFS_QUEUES	32
@@ -22,59 +22,33 @@ static struct dentry *debugfs_queues[MAX_DEBUGFS_QUEUES] = { NULL };
 static DEFINE_MUTEX(debugfs_mutex);
 #define QDIO_DEBUGFS_NAME_LEN	40
 
-void qdio_allocate_do_dbf(struct qdio_initialize *init_data)
+void qdio_allocate_dbf(struct qdio_initialize *init_data,
+		       struct qdio_irq *irq_ptr)
 {
-	char dbf_text[20];
-
-	sprintf(dbf_text, "qfmt:%x", init_data->q_format);
-	QDIO_DBF_TEXT0(0, setup, dbf_text);
-	QDIO_DBF_HEX0(0, setup, init_data->adapter_name, 8);
-	sprintf(dbf_text, "qpff%4x", init_data->qib_param_field_format);
-	QDIO_DBF_TEXT0(0, setup, dbf_text);
-	QDIO_DBF_HEX0(0, setup, &init_data->qib_param_field, sizeof(void *));
-	QDIO_DBF_HEX0(0, setup, &init_data->input_slib_elements, sizeof(void *));
-	QDIO_DBF_HEX0(0, setup, &init_data->output_slib_elements, sizeof(void *));
-	sprintf(dbf_text, "niq:%4x", init_data->no_input_qs);
-	QDIO_DBF_TEXT0(0, setup, dbf_text);
-	sprintf(dbf_text, "noq:%4x", init_data->no_output_qs);
-	QDIO_DBF_TEXT0(0, setup, dbf_text);
-	QDIO_DBF_HEX0(0, setup, &init_data->input_handler, sizeof(void *));
-	QDIO_DBF_HEX0(0, setup, &init_data->output_handler, sizeof(void *));
-	QDIO_DBF_HEX0(0, setup, &init_data->int_parm, sizeof(long));
-	QDIO_DBF_HEX0(0, setup, &init_data->flags, sizeof(long));
-	QDIO_DBF_HEX0(0, setup, &init_data->input_sbal_addr_array, sizeof(void *));
-	QDIO_DBF_HEX0(0, setup, &init_data->output_sbal_addr_array, sizeof(void *));
-}
-
-static void qdio_unregister_dbf_views(void)
-{
-	if (qdio_dbf_setup)
-		debug_unregister(qdio_dbf_setup);
-	if (qdio_dbf_trace)
-		debug_unregister(qdio_dbf_trace);
-}
-
-static int qdio_register_dbf_views(void)
-{
-	qdio_dbf_setup = debug_register("qdio_setup", QDIO_DBF_SETUP_PAGES,
-					QDIO_DBF_SETUP_NR_AREAS,
-					QDIO_DBF_SETUP_LEN);
-	if (!qdio_dbf_setup)
-		goto oom;
-	debug_register_view(qdio_dbf_setup, &debug_hex_ascii_view);
-	debug_set_level(qdio_dbf_setup, QDIO_DBF_SETUP_LEVEL);
-
-	qdio_dbf_trace = debug_register("qdio_trace", QDIO_DBF_TRACE_PAGES,
-					QDIO_DBF_TRACE_NR_AREAS,
-					QDIO_DBF_TRACE_LEN);
-	if (!qdio_dbf_trace)
-		goto oom;
-	debug_register_view(qdio_dbf_trace, &debug_hex_ascii_view);
-	debug_set_level(qdio_dbf_trace, QDIO_DBF_TRACE_LEVEL);
-	return 0;
-oom:
-	qdio_unregister_dbf_views();
-	return -ENOMEM;
+	char text[20];
+
+	DBF_EVENT("qfmt:%1d", init_data->q_format);
+	DBF_HEX(init_data->adapter_name, 8);
+	DBF_EVENT("qpff%4x", init_data->qib_param_field_format);
+	DBF_HEX(&init_data->qib_param_field, sizeof(void *));
+	DBF_HEX(&init_data->input_slib_elements, sizeof(void *));
+	DBF_HEX(&init_data->output_slib_elements, sizeof(void *));
+	DBF_EVENT("niq:%1d noq:%1d", init_data->no_input_qs,
+		  init_data->no_output_qs);
+	DBF_HEX(&init_data->input_handler, sizeof(void *));
+	DBF_HEX(&init_data->output_handler, sizeof(void *));
+	DBF_HEX(&init_data->int_parm, sizeof(long));
+	DBF_HEX(&init_data->flags, sizeof(long));
+	DBF_HEX(&init_data->input_sbal_addr_array, sizeof(void *));
+	DBF_HEX(&init_data->output_sbal_addr_array, sizeof(void *));
+	DBF_EVENT("irq:%8lx", (unsigned long)irq_ptr);
+
+	/* allocate trace view for the interface */
+	snprintf(text, 20, "qdio_%s", dev_name(&init_data->cdev->dev));
+	irq_ptr->debug_area = debug_register(text, 2, 1, 16);
+	debug_register_view(irq_ptr->debug_area, &debug_hex_ascii_view);
+	debug_set_level(irq_ptr->debug_area, DBF_WARN);
+	DBF_DEV_EVENT(DBF_ERR, irq_ptr, "dbf created");
 }
 
 static int qstat_show(struct seq_file *m, void *v)
@@ -86,16 +60,18 @@ static int qstat_show(struct seq_file *m, void *v)
 	if (!q)
 		return 0;
 
-	seq_printf(m, "device state indicator: %d\n", *q->irq_ptr->dsci);
+	seq_printf(m, "device state indicator: %d\n", *(u32 *)q->irq_ptr->dsci);
 	seq_printf(m, "nr_used: %d\n", atomic_read(&q->nr_buf_used));
 	seq_printf(m, "ftc: %d\n", q->first_to_check);
 	seq_printf(m, "last_move_ftc: %d\n", q->last_move_ftc);
 	seq_printf(m, "polling: %d\n", q->u.in.polling);
+	seq_printf(m, "ack count: %d\n", q->u.in.ack_count);
 	seq_printf(m, "slsb buffer states:\n");
+	seq_printf(m, "|0      |8      |16     |24     |32     |40     |48     |56  63|\n");
 
 	qdio_siga_sync_q(q);
 	for (i = 0; i < QDIO_MAX_BUFFERS_PER_Q; i++) {
-		get_buf_state(q, i, &state);
+		get_buf_state(q, i, &state, 0);
 		switch (state) {
 		case SLSB_P_INPUT_NOT_INIT:
 		case SLSB_P_OUTPUT_NOT_INIT:
@@ -127,6 +103,7 @@ static int qstat_show(struct seq_file *m, void *v)
 			seq_printf(m, "\n");
 	}
 	seq_printf(m, "\n");
+	seq_printf(m, "|64     |72     |80     |88     |96     |104    |112    |   127|\n");
 	return 0;
 }
 
@@ -223,11 +200,24 @@ void qdio_shutdown_debug_entries(struct qdio_irq *irq_ptr, struct ccw_device *cd
 int __init qdio_debug_init(void)
 {
 	debugfs_root = debugfs_create_dir("qdio_queues", NULL);
-	return qdio_register_dbf_views();
+
+	qdio_dbf_setup = debug_register("qdio_setup", 16, 1, 16);
+	debug_register_view(qdio_dbf_setup, &debug_hex_ascii_view);
+	debug_set_level(qdio_dbf_setup, DBF_INFO);
+	DBF_EVENT("dbf created\n");
+
+	qdio_dbf_error = debug_register("qdio_error", 4, 1, 16);
+	debug_register_view(qdio_dbf_error, &debug_hex_ascii_view);
+	debug_set_level(qdio_dbf_error, DBF_INFO);
+	DBF_ERROR("dbf created\n");
+	return 0;
 }
 
 void qdio_debug_exit(void)
 {
 	debugfs_remove(debugfs_root);
-	qdio_unregister_dbf_views();
+	if (qdio_dbf_setup)
+		debug_unregister(qdio_dbf_setup);
+	if (qdio_dbf_error)
+		debug_unregister(qdio_dbf_error);
 }
diff --git a/drivers/s390/cio/qdio_debug.h b/drivers/s390/cio/qdio_debug.h
index 5a4d85b829ad..5d70bd162ae9 100644
--- a/drivers/s390/cio/qdio_debug.h
+++ b/drivers/s390/cio/qdio_debug.h
@@ -12,80 +12,72 @@
 #include <asm/qdio.h>
 #include "qdio.h"
 
-#define QDIO_DBF_HEX(ex, name, level, addr, len) \
+/* that gives us 15 characters in the text event views */
+#define QDIO_DBF_LEN	16
+
+extern debug_info_t *qdio_dbf_setup;
+extern debug_info_t *qdio_dbf_error;
+
+/* sort out low debug levels early to avoid wasted sprints */
+static inline int qdio_dbf_passes(debug_info_t *dbf_grp, int level)
+{
+	return (level <= dbf_grp->level);
+}
+
+#define DBF_ERR		3	/* error conditions	*/
+#define DBF_WARN	4	/* warning conditions	*/
+#define DBF_INFO	6	/* informational	*/
+
+#undef DBF_EVENT
+#undef DBF_ERROR
+#undef DBF_DEV_EVENT
+
+#define DBF_EVENT(text...) \
 	do { \
-	if (ex) \
-		debug_exception(qdio_dbf_##name, level, (void *)(addr), len); \
-	else \
-		debug_event(qdio_dbf_##name, level, (void *)(addr), len); \
+		char debug_buffer[QDIO_DBF_LEN]; \
+		snprintf(debug_buffer, QDIO_DBF_LEN, text); \
+		debug_text_event(qdio_dbf_setup, DBF_ERR, debug_buffer); \
 	} while (0)
-#define QDIO_DBF_TEXT(ex, name, level, text) \
+
+#define DBF_HEX(addr, len) \
 	do { \
-	if (ex) \
-		debug_text_exception(qdio_dbf_##name, level, text); \
-	else \
-		debug_text_event(qdio_dbf_##name, level, text); \
+		debug_event(qdio_dbf_setup, DBF_ERR, (void*)(addr), len); \
 	} while (0)
 
-#define QDIO_DBF_HEX0(ex, name, addr, len) QDIO_DBF_HEX(ex, name, 0, addr, len)
-#define QDIO_DBF_HEX1(ex, name, addr, len) QDIO_DBF_HEX(ex, name, 1, addr, len)
-#define QDIO_DBF_HEX2(ex, name, addr, len) QDIO_DBF_HEX(ex, name, 2, addr, len)
-
-#ifdef CONFIG_QDIO_DEBUG
-#define QDIO_DBF_HEX3(ex, name, addr, len) QDIO_DBF_HEX(ex, name, 3, addr, len)
-#define QDIO_DBF_HEX4(ex, name, addr, len) QDIO_DBF_HEX(ex, name, 4, addr, len)
-#define QDIO_DBF_HEX5(ex, name, addr, len) QDIO_DBF_HEX(ex, name, 5, addr, len)
-#define QDIO_DBF_HEX6(ex, name, addr, len) QDIO_DBF_HEX(ex, name, 6, addr, len)
-#else
-#define QDIO_DBF_HEX3(ex, name, addr, len) do {} while (0)
-#define QDIO_DBF_HEX4(ex, name, addr, len) do {} while (0)
-#define QDIO_DBF_HEX5(ex, name, addr, len) do {} while (0)
-#define QDIO_DBF_HEX6(ex, name, addr, len) do {} while (0)
-#endif /* CONFIG_QDIO_DEBUG */
-
-#define QDIO_DBF_TEXT0(ex, name, text) QDIO_DBF_TEXT(ex, name, 0, text)
-#define QDIO_DBF_TEXT1(ex, name, text) QDIO_DBF_TEXT(ex, name, 1, text)
-#define QDIO_DBF_TEXT2(ex, name, text) QDIO_DBF_TEXT(ex, name, 2, text)
-
-#ifdef CONFIG_QDIO_DEBUG
-#define QDIO_DBF_TEXT3(ex, name, text) QDIO_DBF_TEXT(ex, name, 3, text)
-#define QDIO_DBF_TEXT4(ex, name, text) QDIO_DBF_TEXT(ex, name, 4, text)
-#define QDIO_DBF_TEXT5(ex, name, text) QDIO_DBF_TEXT(ex, name, 5, text)
-#define QDIO_DBF_TEXT6(ex, name, text) QDIO_DBF_TEXT(ex, name, 6, text)
-#else
-#define QDIO_DBF_TEXT3(ex, name, text) do {} while (0)
-#define QDIO_DBF_TEXT4(ex, name, text) do {} while (0)
-#define QDIO_DBF_TEXT5(ex, name, text) do {} while (0)
-#define QDIO_DBF_TEXT6(ex, name, text) do {} while (0)
-#endif /* CONFIG_QDIO_DEBUG */
+#define DBF_ERROR(text...) \
+	do { \
+		char debug_buffer[QDIO_DBF_LEN]; \
+		snprintf(debug_buffer, QDIO_DBF_LEN, text); \
+		debug_text_event(qdio_dbf_error, DBF_ERR, debug_buffer); \
+	} while (0)
 
-/* s390dbf views */
-#define QDIO_DBF_SETUP_LEN		8
-#define QDIO_DBF_SETUP_PAGES		8
-#define QDIO_DBF_SETUP_NR_AREAS		1
+#define DBF_ERROR_HEX(addr, len) \
+	do { \
+		debug_event(qdio_dbf_error, DBF_ERR, (void*)(addr), len); \
+	} while (0)
 
-#define QDIO_DBF_TRACE_LEN		8
-#define QDIO_DBF_TRACE_NR_AREAS		2
 
-#ifdef CONFIG_QDIO_DEBUG
-#define QDIO_DBF_TRACE_PAGES		32
-#define QDIO_DBF_SETUP_LEVEL		6
-#define QDIO_DBF_TRACE_LEVEL		4
-#else /* !CONFIG_QDIO_DEBUG */
-#define QDIO_DBF_TRACE_PAGES		8
-#define QDIO_DBF_SETUP_LEVEL		2
-#define QDIO_DBF_TRACE_LEVEL		2
-#endif /* CONFIG_QDIO_DEBUG */
+#define DBF_DEV_EVENT(level, device, text...) \
+	do { \
+		char debug_buffer[QDIO_DBF_LEN]; \
+		if (qdio_dbf_passes(device->debug_area, level)) { \
+			snprintf(debug_buffer, QDIO_DBF_LEN, text); \
+			debug_text_event(device->debug_area, level, debug_buffer); \
+		} \
+	} while (0)
 
-extern debug_info_t *qdio_dbf_setup;
-extern debug_info_t *qdio_dbf_trace;
+#define DBF_DEV_HEX(level, device, addr, len) \
+	do { \
+		debug_event(device->debug_area, level, (void*)(addr), len); \
+	} while (0)
 
-void qdio_allocate_do_dbf(struct qdio_initialize *init_data);
-void debug_print_bstat(struct qdio_q *q);
+void qdio_allocate_dbf(struct qdio_initialize *init_data,
+		       struct qdio_irq *irq_ptr);
 void qdio_setup_debug_entries(struct qdio_irq *irq_ptr,
 			      struct ccw_device *cdev);
 void qdio_shutdown_debug_entries(struct qdio_irq *irq_ptr,
 				 struct ccw_device *cdev);
 int qdio_debug_init(void);
 void qdio_debug_exit(void);
+
 #endif
diff --git a/drivers/s390/cio/qdio_main.c b/drivers/s390/cio/qdio_main.c
index 7c8659151993..584f8498e3b3 100644
--- a/drivers/s390/cio/qdio_main.c
+++ b/drivers/s390/cio/qdio_main.c
@@ -95,8 +95,6 @@ static inline int do_siga_output(unsigned long schid, unsigned long mask,
 
 static inline int qdio_check_ccq(struct qdio_q *q, unsigned int ccq)
 {
-	char dbf_text[15];
-
 	/* all done or next buffer state different */
 	if (ccq == 0 || ccq == 32)
 		return 0;
@@ -104,8 +102,7 @@ static inline int qdio_check_ccq(struct qdio_q *q, unsigned int ccq)
 	if (ccq == 96 || ccq == 97)
 		return 1;
 	/* notify devices immediately */
-	sprintf(dbf_text, "%d", ccq);
-	QDIO_DBF_TEXT2(1, trace, dbf_text);
+	DBF_ERROR("%4x ccq:%3d", SCH_NO(q), ccq);
 	return -EIO;
 }
 
@@ -115,41 +112,45 @@ static inline int qdio_check_ccq(struct qdio_q *q, unsigned int ccq)
  * @state: state of the extracted buffers
  * @start: buffer number to start at
  * @count: count of buffers to examine
+ * @auto_ack: automatically acknowledge buffers
  *
  * Returns the number of successfull extracted equal buffer states.
  * Stops processing if a state is different from the last buffers state.
  */
 static int qdio_do_eqbs(struct qdio_q *q, unsigned char *state,
-			int start, int count)
+			int start, int count, int auto_ack)
 {
 	unsigned int ccq = 0;
 	int tmp_count = count, tmp_start = start;
 	int nr = q->nr;
 	int rc;
-	char dbf_text[15];
 
 	BUG_ON(!q->irq_ptr->sch_token);
+	qdio_perf_stat_inc(&perf_stats.debug_eqbs_all);
 
 	if (!q->is_input_q)
 		nr += q->irq_ptr->nr_input_qs;
 again:
-	ccq = do_eqbs(q->irq_ptr->sch_token, state, nr, &tmp_start, &tmp_count);
+	ccq = do_eqbs(q->irq_ptr->sch_token, state, nr, &tmp_start, &tmp_count,
+		      auto_ack);
 	rc = qdio_check_ccq(q, ccq);
 
 	/* At least one buffer was processed, return and extract the remaining
 	 * buffers later.
 	 */
-	if ((ccq == 96) && (count != tmp_count))
+	if ((ccq == 96) && (count != tmp_count)) {
+		qdio_perf_stat_inc(&perf_stats.debug_eqbs_incomplete);
 		return (count - tmp_count);
+	}
+
 	if (rc == 1) {
-		QDIO_DBF_TEXT5(1, trace, "eqAGAIN");
+		DBF_DEV_EVENT(DBF_WARN, q->irq_ptr, "EQBS again:%2d", ccq);
 		goto again;
 	}
 
 	if (rc < 0) {
-		QDIO_DBF_TEXT2(1, trace, "eqberr");
-		sprintf(dbf_text, "%2x,%2x,%d,%d", count, tmp_count, ccq, nr);
-		QDIO_DBF_TEXT2(1, trace, dbf_text);
+		DBF_ERROR("%4x EQBS ERROR", SCH_NO(q));
+		DBF_ERROR("%3d%3d%2d", count, tmp_count, nr);
 		q->handler(q->irq_ptr->cdev,
 			   QDIO_ERROR_ACTIVATE_CHECK_CONDITION,
 			   0, -1, -1, q->irq_ptr->int_parm);
@@ -176,9 +177,12 @@ static int qdio_do_sqbs(struct qdio_q *q, unsigned char state, int start,
 	int tmp_count = count, tmp_start = start;
 	int nr = q->nr;
 	int rc;
-	char dbf_text[15];
+
+	if (!count)
+		return 0;
 
 	BUG_ON(!q->irq_ptr->sch_token);
+	qdio_perf_stat_inc(&perf_stats.debug_sqbs_all);
 
 	if (!q->is_input_q)
 		nr += q->irq_ptr->nr_input_qs;
@@ -186,16 +190,13 @@ again:
 	ccq = do_sqbs(q->irq_ptr->sch_token, state, nr, &tmp_start, &tmp_count);
 	rc = qdio_check_ccq(q, ccq);
 	if (rc == 1) {
-		QDIO_DBF_TEXT5(1, trace, "sqAGAIN");
+		DBF_DEV_EVENT(DBF_INFO, q->irq_ptr, "SQBS again:%2d", ccq);
+		qdio_perf_stat_inc(&perf_stats.debug_sqbs_incomplete);
 		goto again;
 	}
 	if (rc < 0) {
-		QDIO_DBF_TEXT3(1, trace, "sqberr");
-		sprintf(dbf_text, "%2x,%2x", count, tmp_count);
-		QDIO_DBF_TEXT3(1, trace, dbf_text);
-		sprintf(dbf_text, "%d,%d", ccq, nr);
-		QDIO_DBF_TEXT3(1, trace, dbf_text);
-
+		DBF_ERROR("%4x SQBS ERROR", SCH_NO(q));
+		DBF_ERROR("%3d%3d%2d", count, tmp_count, nr);
 		q->handler(q->irq_ptr->cdev,
 			   QDIO_ERROR_ACTIVATE_CHECK_CONDITION,
 			   0, -1, -1, q->irq_ptr->int_parm);
@@ -207,7 +208,8 @@ again:
 
 /* returns number of examined buffers and their common state in *state */
 static inline int get_buf_states(struct qdio_q *q, unsigned int bufnr,
-				 unsigned char *state, unsigned int count)
+				 unsigned char *state, unsigned int count,
+				 int auto_ack)
 {
 	unsigned char __state = 0;
 	int i;
@@ -216,7 +218,7 @@ static inline int get_buf_states(struct qdio_q *q, unsigned int bufnr,
 	BUG_ON(count > QDIO_MAX_BUFFERS_PER_Q);
 
 	if (is_qebsm(q))
-		return qdio_do_eqbs(q, state, bufnr, count);
+		return qdio_do_eqbs(q, state, bufnr, count, auto_ack);
 
 	for (i = 0; i < count; i++) {
 		if (!__state)
@@ -230,9 +232,9 @@ static inline int get_buf_states(struct qdio_q *q, unsigned int bufnr,
 }
 
 inline int get_buf_state(struct qdio_q *q, unsigned int bufnr,
-		  unsigned char *state)
+		  unsigned char *state, int auto_ack)
 {
-	return get_buf_states(q, bufnr, state, 1);
+	return get_buf_states(q, bufnr, state, 1, auto_ack);
 }
 
 /* wrap-around safe setting of slsb states, returns number of changed buffers */
@@ -282,14 +284,13 @@ static int qdio_siga_sync(struct qdio_q *q, unsigned int output,
 	if (!need_siga_sync(q))
 		return 0;
 
+	DBF_DEV_EVENT(DBF_INFO, q->irq_ptr, "siga-s:");
+	DBF_DEV_HEX(DBF_INFO, q->irq_ptr, q, sizeof(void *));
 	qdio_perf_stat_inc(&perf_stats.siga_sync);
 
 	cc = do_siga_sync(q->irq_ptr->schid, output, input);
-	if (cc) {
-		QDIO_DBF_TEXT4(0, trace, "sigasync");
-		QDIO_DBF_HEX4(0, trace, &q, sizeof(void *));
-		QDIO_DBF_HEX3(0, trace, &cc, sizeof(int *));
-	}
+	if (cc)
+		DBF_ERROR("%4x SIGA-S:%2d", SCH_NO(q), cc);
 	return cc;
 }
 
@@ -333,17 +334,13 @@ static int qdio_siga_output(struct qdio_q *q)
 	int cc;
 	u32 busy_bit;
 	u64 start_time = 0;
-	char dbf_text[15];
-
-	QDIO_DBF_TEXT5(0, trace, "sigaout");
-	QDIO_DBF_HEX5(0, trace, &q, sizeof(void *));
 
+	DBF_DEV_EVENT(DBF_INFO, q->irq_ptr, "siga-w:%1d", q->nr);
 	qdio_perf_stat_inc(&perf_stats.siga_out);
 again:
 	cc = qdio_do_siga_output(q, &busy_bit);
 	if (queue_type(q) == QDIO_IQDIO_QFMT && cc == 2 && busy_bit) {
-		sprintf(dbf_text, "bb%4x%2x", q->irq_ptr->schid.sch_no, q->nr);
-		QDIO_DBF_TEXT3(0, trace, dbf_text);
+		DBF_DEV_EVENT(DBF_INFO, q->irq_ptr, "siga-w bb:%2d", q->nr);
 
 		if (!start_time)
 			start_time = get_usecs();
@@ -354,7 +351,7 @@ again:
 	if (cc == 2 && busy_bit)
 		cc |= QDIO_ERROR_SIGA_BUSY;
 	if (cc)
-		QDIO_DBF_HEX3(0, trace, &cc, sizeof(int *));
+		DBF_ERROR("%4x SIGA-W:%2d", SCH_NO(q), cc);
 	return cc;
 }
 
@@ -362,14 +359,12 @@ static inline int qdio_siga_input(struct qdio_q *q)
 {
 	int cc;
 
-	QDIO_DBF_TEXT4(0, trace, "sigain");
-	QDIO_DBF_HEX4(0, trace, &q, sizeof(void *));
-
+	DBF_DEV_EVENT(DBF_INFO, q->irq_ptr, "siga-r:%1d", q->nr);
 	qdio_perf_stat_inc(&perf_stats.siga_in);
 
 	cc = do_siga_input(q->irq_ptr->schid, q->mask);
 	if (cc)
-		QDIO_DBF_HEX3(0, trace, &cc, sizeof(int *));
+		DBF_ERROR("%4x SIGA-R:%2d", SCH_NO(q), cc);
 	return cc;
 }
 
@@ -387,35 +382,91 @@ void qdio_sync_after_thinint(struct qdio_q *q)
 
 inline void qdio_stop_polling(struct qdio_q *q)
 {
-	spin_lock_bh(&q->u.in.lock);
-	if (!q->u.in.polling) {
-		spin_unlock_bh(&q->u.in.lock);
+	if (!q->u.in.polling)
 		return;
-	}
+
 	q->u.in.polling = 0;
 	qdio_perf_stat_inc(&perf_stats.debug_stop_polling);
 
 	/* show the card that we are not polling anymore */
-	set_buf_state(q, q->last_move_ftc, SLSB_P_INPUT_NOT_INIT);
-	spin_unlock_bh(&q->u.in.lock);
+	if (is_qebsm(q)) {
+		set_buf_states(q, q->last_move_ftc, SLSB_P_INPUT_NOT_INIT,
+			       q->u.in.ack_count);
+		q->u.in.ack_count = 0;
+	} else
+		set_buf_state(q, q->last_move_ftc, SLSB_P_INPUT_NOT_INIT);
 }
 
-static void announce_buffer_error(struct qdio_q *q)
+static void announce_buffer_error(struct qdio_q *q, int count)
 {
-	char dbf_text[15];
+	q->qdio_error = QDIO_ERROR_SLSB_STATE;
 
-	if (q->is_input_q)
-		QDIO_DBF_TEXT3(1, trace, "inperr");
-	else
-		QDIO_DBF_TEXT3(0, trace, "outperr");
+	/* special handling for no target buffer empty */
+	if ((!q->is_input_q &&
+	    (q->sbal[q->first_to_check]->element[15].flags & 0xff) == 0x10)) {
+		qdio_perf_stat_inc(&perf_stats.outbound_target_full);
+		DBF_DEV_EVENT(DBF_INFO, q->irq_ptr, "OUTFULL FTC:%3d",
+			      q->first_to_check);
+		return;
+	}
 
-	sprintf(dbf_text, "%x-%x-%x", q->first_to_check,
-		q->sbal[q->first_to_check]->element[14].flags,
-		q->sbal[q->first_to_check]->element[15].flags);
-	QDIO_DBF_TEXT3(1, trace, dbf_text);
-	QDIO_DBF_HEX2(1, trace, q->sbal[q->first_to_check], 256);
+	DBF_ERROR("%4x BUF ERROR", SCH_NO(q));
+	DBF_ERROR((q->is_input_q) ? "IN:%2d" : "OUT:%2d", q->nr);
+	DBF_ERROR("FTC:%3d C:%3d", q->first_to_check, count);
+	DBF_ERROR("F14:%2x F15:%2x",
+		  q->sbal[q->first_to_check]->element[14].flags & 0xff,
+		  q->sbal[q->first_to_check]->element[15].flags & 0xff);
+}
 
-	q->qdio_error = QDIO_ERROR_SLSB_STATE;
+static inline void inbound_primed(struct qdio_q *q, int count)
+{
+	int new;
+
+	DBF_DEV_EVENT(DBF_INFO, q->irq_ptr, "in prim: %3d", count);
+
+	/* for QEBSM the ACK was already set by EQBS */
+	if (is_qebsm(q)) {
+		if (!q->u.in.polling) {
+			q->u.in.polling = 1;
+			q->u.in.ack_count = count;
+			q->last_move_ftc = q->first_to_check;
+			return;
+		}
+
+		/* delete the previous ACK's */
+		set_buf_states(q, q->last_move_ftc, SLSB_P_INPUT_NOT_INIT,
+			       q->u.in.ack_count);
+		q->u.in.ack_count = count;
+		q->last_move_ftc = q->first_to_check;
+		return;
+	}
+
+	/*
+	 * ACK the newest buffer. The ACK will be removed in qdio_stop_polling
+	 * or by the next inbound run.
+	 */
+	new = add_buf(q->first_to_check, count - 1);
+	if (q->u.in.polling) {
+		/* reset the previous ACK but first set the new one */
+		set_buf_state(q, new, SLSB_P_INPUT_ACK);
+		set_buf_state(q, q->last_move_ftc, SLSB_P_INPUT_NOT_INIT);
+	}
+	else {
+		q->u.in.polling = 1;
+		set_buf_state(q, q->first_to_check, SLSB_P_INPUT_ACK);
+	}
+
+	q->last_move_ftc = new;
+	count--;
+	if (!count)
+		return;
+
+	/*
+	 * Need to change all PRIMED buffers to NOT_INIT, otherwise
+	 * we're loosing initiative in the thinint code.
+	 */
+	set_buf_states(q, next_buf(q->first_to_check), SLSB_P_INPUT_NOT_INIT,
+		       count);
 }
 
 static int get_inbound_buffer_frontier(struct qdio_q *q)
@@ -424,13 +475,6 @@ static int get_inbound_buffer_frontier(struct qdio_q *q)
 	unsigned char state;
 
 	/*
-	 * If we still poll don't update last_move_ftc, keep the
-	 * previously ACK buffer there.
-	 */
-	if (!q->u.in.polling)
-		q->last_move_ftc = q->first_to_check;
-
-	/*
 	 * Don't check 128 buffers, as otherwise qdio_inbound_q_moved
 	 * would return 0.
 	 */
@@ -450,34 +494,13 @@ check_next:
 	if (q->first_to_check == stop)
 		goto out;
 
-	count = get_buf_states(q, q->first_to_check, &state, count);
+	count = get_buf_states(q, q->first_to_check, &state, count, 1);
 	if (!count)
 		goto out;
 
 	switch (state) {
 	case SLSB_P_INPUT_PRIMED:
-		QDIO_DBF_TEXT5(0, trace, "inptprim");
-
-		/*
-		 * Only ACK the first buffer. The ACK will be removed in
-		 * qdio_stop_polling.
-		 */
-		if (q->u.in.polling)
-			state = SLSB_P_INPUT_NOT_INIT;
-		else {
-			q->u.in.polling = 1;
-			state = SLSB_P_INPUT_ACK;
-		}
-		set_buf_state(q, q->first_to_check, state);
-
-		/*
-		 * Need to change all PRIMED buffers to NOT_INIT, otherwise
-		 * we're loosing initiative in the thinint code.
-		 */
-		if (count > 1)
-			set_buf_states(q, next_buf(q->first_to_check),
-				       SLSB_P_INPUT_NOT_INIT, count - 1);
-
+		inbound_primed(q, count);
 		/*
 		 * No siga-sync needed for non-qebsm here, as the inbound queue
 		 * will be synced on the next siga-r, resp.
@@ -487,21 +510,23 @@ check_next:
 		atomic_sub(count, &q->nr_buf_used);
 		goto check_next;
 	case SLSB_P_INPUT_ERROR:
-		announce_buffer_error(q);
+		announce_buffer_error(q, count);
 		/* process the buffer, the upper layer will take care of it */
 		q->first_to_check = add_buf(q->first_to_check, count);
 		atomic_sub(count, &q->nr_buf_used);
 		break;
 	case SLSB_CU_INPUT_EMPTY:
+		DBF_DEV_EVENT(DBF_INFO, q->irq_ptr, "in nop");
+		break;
 	case SLSB_P_INPUT_NOT_INIT:
 	case SLSB_P_INPUT_ACK:
-		QDIO_DBF_TEXT5(0, trace, "inpnipro");
+		WARN_ON(1);
+		q->first_to_check++;
 		break;
 	default:
 		BUG();
 	}
 out:
-	QDIO_DBF_HEX4(0, trace, &q->first_to_check, sizeof(int));
 	return q->first_to_check;
 }
 
@@ -515,8 +540,7 @@ int qdio_inbound_q_moved(struct qdio_q *q)
 		if (!need_siga_sync(q) && !pci_out_supported(q))
 			q->u.in.timestamp = get_usecs();
 
-		QDIO_DBF_TEXT4(0, trace, "inhasmvd");
-		QDIO_DBF_HEX4(0, trace, &q, sizeof(void *));
+		DBF_DEV_EVENT(DBF_INFO, q->irq_ptr, "in moved");
 		return 1;
 	} else
 		return 0;
@@ -524,10 +548,7 @@ int qdio_inbound_q_moved(struct qdio_q *q)
 
 static int qdio_inbound_q_done(struct qdio_q *q)
 {
-	unsigned char state;
-#ifdef CONFIG_QDIO_DEBUG
-	char dbf_text[15];
-#endif
+	unsigned char state = 0;
 
 	if (!atomic_read(&q->nr_buf_used))
 		return 1;
@@ -538,7 +559,7 @@ static int qdio_inbound_q_done(struct qdio_q *q)
 	 */
 	qdio_siga_sync_q(q);
 
-	get_buf_state(q, q->first_to_check, &state);
+	get_buf_state(q, q->first_to_check, &state, 0);
 	if (state == SLSB_P_INPUT_PRIMED)
 		/* we got something to do */
 		return 0;
@@ -552,20 +573,12 @@ static int qdio_inbound_q_done(struct qdio_q *q)
 	 * has (probably) not moved (see qdio_inbound_processing).
 	 */
 	if (get_usecs() > q->u.in.timestamp + QDIO_INPUT_THRESHOLD) {
-#ifdef CONFIG_QDIO_DEBUG
-		QDIO_DBF_TEXT4(0, trace, "inqisdon");
-		QDIO_DBF_HEX4(0, trace, &q, sizeof(void *));
-		sprintf(dbf_text, "pf%02x", q->first_to_check);
-		QDIO_DBF_TEXT4(0, trace, dbf_text);
-#endif /* CONFIG_QDIO_DEBUG */
+		DBF_DEV_EVENT(DBF_INFO, q->irq_ptr, "in done:%3d",
+			      q->first_to_check);
 		return 1;
 	} else {
-#ifdef CONFIG_QDIO_DEBUG
-		QDIO_DBF_TEXT4(0, trace, "inqisntd");
-		QDIO_DBF_HEX4(0, trace, &q, sizeof(void *));
-		sprintf(dbf_text, "pf%02x", q->first_to_check);
-		QDIO_DBF_TEXT4(0, trace, dbf_text);
-#endif /* CONFIG_QDIO_DEBUG */
+		DBF_DEV_EVENT(DBF_INFO, q->irq_ptr, "in notd:%3d",
+			      q->first_to_check);
 		return 0;
 	}
 }
@@ -573,9 +586,6 @@ static int qdio_inbound_q_done(struct qdio_q *q)
 void qdio_kick_inbound_handler(struct qdio_q *q)
 {
 	int count, start, end;
-#ifdef CONFIG_QDIO_DEBUG
-	char dbf_text[15];
-#endif
 
 	qdio_perf_stat_inc(&perf_stats.inbound_handler);
 
@@ -586,10 +596,7 @@ void qdio_kick_inbound_handler(struct qdio_q *q)
 	else
 		count = end + QDIO_MAX_BUFFERS_PER_Q - start;
 
-#ifdef CONFIG_QDIO_DEBUG
-	sprintf(dbf_text, "s=%2xc=%2x", start, count);
-	QDIO_DBF_TEXT4(0, trace, dbf_text);
-#endif /* CONFIG_QDIO_DEBUG */
+	DBF_DEV_EVENT(DBF_INFO, q->irq_ptr, "kih s:%3d c:%3d", start, count);
 
 	if (unlikely(q->irq_ptr->state != QDIO_IRQ_STATE_ACTIVE))
 		return;
@@ -655,14 +662,14 @@ check_next:
 	if (q->first_to_check == stop)
 		return q->first_to_check;
 
-	count = get_buf_states(q, q->first_to_check, &state, count);
+	count = get_buf_states(q, q->first_to_check, &state, count, 0);
 	if (!count)
 		return q->first_to_check;
 
 	switch (state) {
 	case SLSB_P_OUTPUT_EMPTY:
 		/* the adapter got it */
-		QDIO_DBF_TEXT5(0, trace, "outpempt");
+		DBF_DEV_EVENT(DBF_INFO, q->irq_ptr, "out empty:%1d %3d", q->nr, count);
 
 		atomic_sub(count, &q->nr_buf_used);
 		q->first_to_check = add_buf(q->first_to_check, count);
@@ -674,16 +681,19 @@ check_next:
 			break;
 		goto check_next;
 	case SLSB_P_OUTPUT_ERROR:
-		announce_buffer_error(q);
+		announce_buffer_error(q, count);
 		/* process the buffer, the upper layer will take care of it */
 		q->first_to_check = add_buf(q->first_to_check, count);
 		atomic_sub(count, &q->nr_buf_used);
 		break;
 	case SLSB_CU_OUTPUT_PRIMED:
 		/* the adapter has not fetched the output yet */
-		QDIO_DBF_TEXT5(0, trace, "outpprim");
+		DBF_DEV_EVENT(DBF_INFO, q->irq_ptr, "out primed:%1d", q->nr);
 		break;
 	case SLSB_P_OUTPUT_NOT_INIT:
+		WARN_ON(1);
+		q->first_to_check++;
+		break;
 	case SLSB_P_OUTPUT_HALTED:
 		break;
 	default:
@@ -706,8 +716,7 @@ static inline int qdio_outbound_q_moved(struct qdio_q *q)
 
 	if ((bufnr != q->last_move_ftc) || q->qdio_error) {
 		q->last_move_ftc = bufnr;
-		QDIO_DBF_TEXT4(0, trace, "oqhasmvd");
-		QDIO_DBF_HEX4(0, trace, &q, sizeof(void *));
+		DBF_DEV_EVENT(DBF_INFO, q->irq_ptr, "out moved:%1d", q->nr);
 		return 1;
 	} else
 		return 0;
@@ -742,12 +751,8 @@ static inline int qdio_outbound_q_moved(struct qdio_q *q)
 static void qdio_kick_outbound_q(struct qdio_q *q)
 {
 	int rc;
-#ifdef CONFIG_QDIO_DEBUG
-	char dbf_text[15];
 
-	QDIO_DBF_TEXT5(0, trace, "kickoutq");
-	QDIO_DBF_HEX5(0, trace, &q, sizeof(void *));
-#endif /* CONFIG_QDIO_DEBUG */
+	DBF_DEV_EVENT(DBF_INFO, q->irq_ptr, "kickoutq:%1d", q->nr);
 
 	if (!need_siga_out(q))
 		return;
@@ -756,15 +761,9 @@ static void qdio_kick_outbound_q(struct qdio_q *q)
 	switch (rc) {
 	case 0:
 		/* TODO: improve error handling for CC=0 case */
-#ifdef CONFIG_QDIO_DEBUG
-		if (q->u.out.timestamp) {
-			QDIO_DBF_TEXT3(0, trace, "cc2reslv");
-			sprintf(dbf_text, "%4x%2x%2x", q->irq_ptr->schid.sch_no,
-				q->nr,
-				atomic_read(&q->u.out.busy_siga_counter));
-			QDIO_DBF_TEXT3(0, trace, dbf_text);
-		}
-#endif /* CONFIG_QDIO_DEBUG */
+		if (q->u.out.timestamp)
+			DBF_DEV_EVENT(DBF_INFO, q->irq_ptr, "cc2 rslv:%4x",
+				      atomic_read(&q->u.out.busy_siga_counter));
 		/* went smooth this time, reset timestamp */
 		q->u.out.timestamp = 0;
 		break;
@@ -781,12 +780,7 @@ static void qdio_kick_outbound_q(struct qdio_q *q)
 			tasklet_schedule(&q->tasklet);
 			break;
 		}
-		QDIO_DBF_TEXT2(0, trace, "cc2REPRT");
-#ifdef CONFIG_QDIO_DEBUG
-		sprintf(dbf_text, "%4x%2x%2x", q->irq_ptr->schid.sch_no, q->nr,
-			atomic_read(&q->u.out.busy_siga_counter));
-		QDIO_DBF_TEXT3(0, trace, dbf_text);
-#endif /* CONFIG_QDIO_DEBUG */
+		DBF_ERROR("%4x cc2 REP:%1d", SCH_NO(q), q->nr);
 	default:
 		/* for plain cc=1, 2 or 3 */
 		q->qdio_error = rc;
@@ -796,9 +790,6 @@ static void qdio_kick_outbound_q(struct qdio_q *q)
 static void qdio_kick_outbound_handler(struct qdio_q *q)
 {
 	int start, end, count;
-#ifdef CONFIG_QDIO_DEBUG
-	char dbf_text[15];
-#endif
 
 	start = q->first_to_kick;
 	end = q->last_move_ftc;
@@ -807,13 +798,8 @@ static void qdio_kick_outbound_handler(struct qdio_q *q)
 	else
 		count = end + QDIO_MAX_BUFFERS_PER_Q - start;
 
-#ifdef CONFIG_QDIO_DEBUG
-	QDIO_DBF_TEXT4(0, trace, "kickouth");
-	QDIO_DBF_HEX4(0, trace, &q, sizeof(void *));
-
-	sprintf(dbf_text, "s=%2xc=%2x", start, count);
-	QDIO_DBF_TEXT4(0, trace, dbf_text);
-#endif /* CONFIG_QDIO_DEBUG */
+	DBF_DEV_EVENT(DBF_INFO, q->irq_ptr, "kickouth: %1d", q->nr);
+	DBF_DEV_EVENT(DBF_INFO, q->irq_ptr, "s:%3d c:%3d", start, count);
 
 	if (unlikely(q->irq_ptr->state != QDIO_IRQ_STATE_ACTIVE))
 		return;
@@ -908,27 +894,18 @@ void qdio_check_outbound_after_thinint(struct qdio_q *q)
 static inline void qdio_set_state(struct qdio_irq *irq_ptr,
 				  enum qdio_irq_states state)
 {
-#ifdef CONFIG_QDIO_DEBUG
-	char dbf_text[15];
-
-	QDIO_DBF_TEXT5(0, trace, "newstate");
-	sprintf(dbf_text, "%4x%4x", irq_ptr->schid.sch_no, state);
-	QDIO_DBF_TEXT5(0, trace, dbf_text);
-#endif /* CONFIG_QDIO_DEBUG */
+	DBF_DEV_EVENT(DBF_INFO, irq_ptr, "newstate: %1d", state);
 
 	irq_ptr->state = state;
 	mb();
 }
 
-static void qdio_irq_check_sense(struct subchannel_id schid, struct irb *irb)
+static void qdio_irq_check_sense(struct qdio_irq *irq_ptr, struct irb *irb)
 {
-	char dbf_text[15];
-
 	if (irb->esw.esw0.erw.cons) {
-		sprintf(dbf_text, "sens%4x", schid.sch_no);
-		QDIO_DBF_TEXT2(1, trace, dbf_text);
-		QDIO_DBF_HEX0(0, trace, irb, 64);
-		QDIO_DBF_HEX0(0, trace, irb->ecw, 64);
+		DBF_ERROR("%4x sense:", irq_ptr->schid.sch_no);
+		DBF_ERROR_HEX(irb, 64);
+		DBF_ERROR_HEX(irb->ecw, 64);
 	}
 }
 
@@ -962,14 +939,10 @@ static void qdio_handle_activate_check(struct ccw_device *cdev,
 {
 	struct qdio_irq *irq_ptr = cdev->private->qdio_data;
 	struct qdio_q *q;
-	char dbf_text[15];
 
-	QDIO_DBF_TEXT2(1, trace, "ick2");
-	sprintf(dbf_text, "%s", dev_name(&cdev->dev));
-	QDIO_DBF_TEXT2(1, trace, dbf_text);
-	QDIO_DBF_HEX2(0, trace, &intparm, sizeof(int));
-	QDIO_DBF_HEX2(0, trace, &dstat, sizeof(int));
-	QDIO_DBF_HEX2(0, trace, &cstat, sizeof(int));
+	DBF_ERROR("%4x ACT CHECK", irq_ptr->schid.sch_no);
+	DBF_ERROR("intp :%lx", intparm);
+	DBF_ERROR("ds: %2x cs:%2x", dstat, cstat);
 
 	if (irq_ptr->nr_input_qs) {
 		q = irq_ptr->input_qs[0];
@@ -1022,28 +995,29 @@ static void qdio_int_error(struct ccw_device *cdev)
 }
 
 static int qdio_establish_check_errors(struct ccw_device *cdev, int cstat,
-					   int dstat)
+				       int dstat)
 {
 	struct qdio_irq *irq_ptr = cdev->private->qdio_data;
 
 	if (cstat || (dstat & ~(DEV_STAT_CHN_END | DEV_STAT_DEV_END))) {
-		QDIO_DBF_TEXT2(1, setup, "eq:ckcon");
+		DBF_ERROR("EQ:ck con");
 		goto error;
 	}
 
 	if (!(dstat & DEV_STAT_DEV_END)) {
-		QDIO_DBF_TEXT2(1, setup, "eq:no de");
+		DBF_ERROR("EQ:no dev");
 		goto error;
 	}
 
 	if (dstat & ~(DEV_STAT_CHN_END | DEV_STAT_DEV_END)) {
-		QDIO_DBF_TEXT2(1, setup, "eq:badio");
+		DBF_ERROR("EQ: bad io");
 		goto error;
 	}
 	return 0;
 error:
-	QDIO_DBF_HEX2(0, trace, &cstat, sizeof(int));
-	QDIO_DBF_HEX2(0, trace, &dstat, sizeof(int));
+	DBF_ERROR("%4x EQ:error", irq_ptr->schid.sch_no);
+	DBF_ERROR("ds: %2x cs:%2x", dstat, cstat);
+
 	qdio_set_state(irq_ptr, QDIO_IRQ_STATE_ERR);
 	return 1;
 }
@@ -1052,12 +1026,8 @@ static void qdio_establish_handle_irq(struct ccw_device *cdev, int cstat,
 				      int dstat)
 {
 	struct qdio_irq *irq_ptr = cdev->private->qdio_data;
-	char dbf_text[15];
-
-	sprintf(dbf_text, "qehi%4x", cdev->private->schid.sch_no);
-	QDIO_DBF_TEXT0(0, setup, dbf_text);
-	QDIO_DBF_TEXT0(0, trace, dbf_text);
 
+	DBF_DEV_EVENT(DBF_INFO, irq_ptr, "qest irq");
 	if (!qdio_establish_check_errors(cdev, cstat, dstat))
 		qdio_set_state(irq_ptr, QDIO_IRQ_STATE_ESTABLISHED);
 }
@@ -1068,25 +1038,21 @@ void qdio_int_handler(struct ccw_device *cdev, unsigned long intparm,
 {
 	struct qdio_irq *irq_ptr = cdev->private->qdio_data;
 	int cstat, dstat;
-	char dbf_text[15];
 
 	qdio_perf_stat_inc(&perf_stats.qdio_int);
 
 	if (!intparm || !irq_ptr) {
-		sprintf(dbf_text, "qihd%4x", cdev->private->schid.sch_no);
-		QDIO_DBF_TEXT2(1, setup, dbf_text);
+		DBF_ERROR("qint:%4x", cdev->private->schid.sch_no);
 		return;
 	}
 
 	if (IS_ERR(irb)) {
 		switch (PTR_ERR(irb)) {
 		case -EIO:
-			sprintf(dbf_text, "ierr%4x", irq_ptr->schid.sch_no);
-			QDIO_DBF_TEXT2(1, setup, dbf_text);
+			DBF_ERROR("%4x IO error", irq_ptr->schid.sch_no);
 			return;
 		case -ETIMEDOUT:
-			sprintf(dbf_text, "qtoh%4x", irq_ptr->schid.sch_no);
-			QDIO_DBF_TEXT2(1, setup, dbf_text);
+			DBF_ERROR("%4x IO timeout", irq_ptr->schid.sch_no);
 			qdio_int_error(cdev);
 			return;
 		default:
@@ -1094,7 +1060,7 @@ void qdio_int_handler(struct ccw_device *cdev, unsigned long intparm,
 			return;
 		}
 	}
-	qdio_irq_check_sense(irq_ptr->schid, irb);
+	qdio_irq_check_sense(irq_ptr, irb);
 
 	cstat = irb->scsw.cmd.cstat;
 	dstat = irb->scsw.cmd.dstat;
@@ -1129,23 +1095,20 @@ void qdio_int_handler(struct ccw_device *cdev, unsigned long intparm,
 /**
  * qdio_get_ssqd_desc - get qdio subchannel description
  * @cdev: ccw device to get description for
+ * @data: where to store the ssqd
  *
- * Returns a pointer to the saved qdio subchannel description,
- * or NULL for not setup qdio devices.
+ * Returns 0 or an error code. The results of the chsc are stored in the
+ * specified structure.
  */
-struct qdio_ssqd_desc *qdio_get_ssqd_desc(struct ccw_device *cdev)
+int qdio_get_ssqd_desc(struct ccw_device *cdev,
+		       struct qdio_ssqd_desc *data)
 {
-	struct qdio_irq *irq_ptr;
-	char dbf_text[15];
 
-	sprintf(dbf_text, "qssq%4x", cdev->private->schid.sch_no);
-	QDIO_DBF_TEXT0(0, setup, dbf_text);
-
-	irq_ptr = cdev->private->qdio_data;
-	if (!irq_ptr)
-		return NULL;
+	if (!cdev || !cdev->private)
+		return -EINVAL;
 
-	return &irq_ptr->ssqd_desc;
+	DBF_EVENT("get ssqd:%4x", cdev->private->schid.sch_no);
+	return qdio_setup_get_ssqd(NULL, &cdev->private->schid, data);
 }
 EXPORT_SYMBOL_GPL(qdio_get_ssqd_desc);
 
@@ -1159,14 +1122,9 @@ EXPORT_SYMBOL_GPL(qdio_get_ssqd_desc);
  */
 int qdio_cleanup(struct ccw_device *cdev, int how)
 {
-	struct qdio_irq *irq_ptr;
-	char dbf_text[15];
+	struct qdio_irq *irq_ptr = cdev->private->qdio_data;
 	int rc;
 
-	sprintf(dbf_text, "qcln%4x", cdev->private->schid.sch_no);
-	QDIO_DBF_TEXT0(0, setup, dbf_text);
-
-	irq_ptr = cdev->private->qdio_data;
 	if (!irq_ptr)
 		return -ENODEV;
 
@@ -1199,18 +1157,15 @@ static void qdio_shutdown_queues(struct ccw_device *cdev)
  */
 int qdio_shutdown(struct ccw_device *cdev, int how)
 {
-	struct qdio_irq *irq_ptr;
+	struct qdio_irq *irq_ptr = cdev->private->qdio_data;
 	int rc;
 	unsigned long flags;
-	char dbf_text[15];
-
-	sprintf(dbf_text, "qshu%4x", cdev->private->schid.sch_no);
-	QDIO_DBF_TEXT0(0, setup, dbf_text);
 
-	irq_ptr = cdev->private->qdio_data;
 	if (!irq_ptr)
 		return -ENODEV;
 
+	DBF_EVENT("qshutdown:%4x", cdev->private->schid.sch_no);
+
 	mutex_lock(&irq_ptr->setup_mutex);
 	/*
 	 * Subchannel was already shot down. We cannot prevent being called
@@ -1234,10 +1189,8 @@ int qdio_shutdown(struct ccw_device *cdev, int how)
 		/* default behaviour is halt */
 		rc = ccw_device_halt(cdev, QDIO_DOING_CLEANUP);
 	if (rc) {
-		sprintf(dbf_text, "sher%4x", irq_ptr->schid.sch_no);
-		QDIO_DBF_TEXT0(0, setup, dbf_text);
-		sprintf(dbf_text, "rc=%d", rc);
-		QDIO_DBF_TEXT0(0, setup, dbf_text);
+		DBF_ERROR("%4x SHUTD ERR", irq_ptr->schid.sch_no);
+		DBF_ERROR("rc:%4d", rc);
 		goto no_cleanup;
 	}
 
@@ -1271,17 +1224,18 @@ EXPORT_SYMBOL_GPL(qdio_shutdown);
  */
 int qdio_free(struct ccw_device *cdev)
 {
-	struct qdio_irq *irq_ptr;
-	char dbf_text[15];
-
-	sprintf(dbf_text, "qfre%4x", cdev->private->schid.sch_no);
-	QDIO_DBF_TEXT0(0, setup, dbf_text);
+	struct qdio_irq *irq_ptr = cdev->private->qdio_data;
 
-	irq_ptr = cdev->private->qdio_data;
 	if (!irq_ptr)
 		return -ENODEV;
 
+	DBF_EVENT("qfree:%4x", cdev->private->schid.sch_no);
 	mutex_lock(&irq_ptr->setup_mutex);
+
+	if (irq_ptr->debug_area != NULL) {
+		debug_unregister(irq_ptr->debug_area);
+		irq_ptr->debug_area = NULL;
+	}
 	cdev->private->qdio_data = NULL;
 	mutex_unlock(&irq_ptr->setup_mutex);
 
@@ -1300,10 +1254,6 @@ EXPORT_SYMBOL_GPL(qdio_free);
 int qdio_initialize(struct qdio_initialize *init_data)
 {
 	int rc;
-	char dbf_text[15];
-
-	sprintf(dbf_text, "qini%4x", init_data->cdev->private->schid.sch_no);
-	QDIO_DBF_TEXT0(0, setup, dbf_text);
 
 	rc = qdio_allocate(init_data);
 	if (rc)
@@ -1323,10 +1273,8 @@ EXPORT_SYMBOL_GPL(qdio_initialize);
 int qdio_allocate(struct qdio_initialize *init_data)
 {
 	struct qdio_irq *irq_ptr;
-	char dbf_text[15];
 
-	sprintf(dbf_text, "qalc%4x", init_data->cdev->private->schid.sch_no);
-	QDIO_DBF_TEXT0(0, setup, dbf_text);
+	DBF_EVENT("qallocate:%4x", init_data->cdev->private->schid.sch_no);
 
 	if ((init_data->no_input_qs && !init_data->input_handler) ||
 	    (init_data->no_output_qs && !init_data->output_handler))
@@ -1340,16 +1288,13 @@ int qdio_allocate(struct qdio_initialize *init_data)
 	    (!init_data->output_sbal_addr_array))
 		return -EINVAL;
 
-	qdio_allocate_do_dbf(init_data);
-
 	/* irq_ptr must be in GFP_DMA since it contains ccw1.cda */
 	irq_ptr = (void *) get_zeroed_page(GFP_KERNEL | GFP_DMA);
 	if (!irq_ptr)
 		goto out_err;
-	QDIO_DBF_TEXT0(0, setup, "irq_ptr:");
-	QDIO_DBF_HEX0(0, setup, &irq_ptr, sizeof(void *));
 
 	mutex_init(&irq_ptr->setup_mutex);
+	qdio_allocate_dbf(init_data, irq_ptr);
 
 	/*
 	 * Allocate a page for the chsc calls in qdio_establish.
@@ -1367,9 +1312,6 @@ int qdio_allocate(struct qdio_initialize *init_data)
 		goto out_rel;
 	WARN_ON((unsigned long)irq_ptr->qdr & 0xfff);
 
-	QDIO_DBF_TEXT0(0, setup, "qdr:");
-	QDIO_DBF_HEX0(0, setup, &irq_ptr->qdr, sizeof(void *));
-
 	if (qdio_allocate_qs(irq_ptr, init_data->no_input_qs,
 			     init_data->no_output_qs))
 		goto out_rel;
@@ -1390,14 +1332,12 @@ EXPORT_SYMBOL_GPL(qdio_allocate);
  */
 int qdio_establish(struct qdio_initialize *init_data)
 {
-	char dbf_text[20];
 	struct qdio_irq *irq_ptr;
 	struct ccw_device *cdev = init_data->cdev;
 	unsigned long saveflags;
 	int rc;
 
-	sprintf(dbf_text, "qest%4x", cdev->private->schid.sch_no);
-	QDIO_DBF_TEXT0(0, setup, dbf_text);
+	DBF_EVENT("qestablish:%4x", cdev->private->schid.sch_no);
 
 	irq_ptr = cdev->private->qdio_data;
 	if (!irq_ptr)
@@ -1427,10 +1367,8 @@ int qdio_establish(struct qdio_initialize *init_data)
 
 	rc = ccw_device_start(cdev, &irq_ptr->ccw, QDIO_DOING_ESTABLISH, 0, 0);
 	if (rc) {
-		sprintf(dbf_text, "eq:io%4x", irq_ptr->schid.sch_no);
-		QDIO_DBF_TEXT2(1, setup, dbf_text);
-		sprintf(dbf_text, "eq:rc%4x", rc);
-		QDIO_DBF_TEXT2(1, setup, dbf_text);
+		DBF_ERROR("%4x est IO ERR", irq_ptr->schid.sch_no);
+		DBF_ERROR("rc:%4x", rc);
 	}
 	spin_unlock_irqrestore(get_ccwdev_lock(cdev), saveflags);
 
@@ -1451,10 +1389,8 @@ int qdio_establish(struct qdio_initialize *init_data)
 	}
 
 	qdio_setup_ssqd_info(irq_ptr);
-	sprintf(dbf_text, "qDmmwc%2x", irq_ptr->ssqd_desc.mmwc);
-	QDIO_DBF_TEXT2(0, setup, dbf_text);
-	sprintf(dbf_text, "qib ac%2x", irq_ptr->qib.ac);
-	QDIO_DBF_TEXT2(0, setup, dbf_text);
+	DBF_EVENT("qDmmwc:%2x", irq_ptr->ssqd_desc.mmwc);
+	DBF_EVENT("qib ac:%4x", irq_ptr->qib.ac);
 
 	/* qebsm is now setup if available, initialize buffer states */
 	qdio_init_buf_states(irq_ptr);
@@ -1475,10 +1411,8 @@ int qdio_activate(struct ccw_device *cdev)
 	struct qdio_irq *irq_ptr;
 	int rc;
 	unsigned long saveflags;
-	char dbf_text[20];
 
-	sprintf(dbf_text, "qact%4x", cdev->private->schid.sch_no);
-	QDIO_DBF_TEXT0(0, setup, dbf_text);
+	DBF_EVENT("qactivate:%4x", cdev->private->schid.sch_no);
 
 	irq_ptr = cdev->private->qdio_data;
 	if (!irq_ptr)
@@ -1504,10 +1438,8 @@ int qdio_activate(struct ccw_device *cdev)
 	rc = ccw_device_start(cdev, &irq_ptr->ccw, QDIO_DOING_ACTIVATE,
 			      0, DOIO_DENY_PREFETCH);
 	if (rc) {
-		sprintf(dbf_text, "aq:io%4x", irq_ptr->schid.sch_no);
-		QDIO_DBF_TEXT2(1, setup, dbf_text);
-		sprintf(dbf_text, "aq:rc%4x", rc);
-		QDIO_DBF_TEXT2(1, setup, dbf_text);
+		DBF_ERROR("%4x act IO ERR", irq_ptr->schid.sch_no);
+		DBF_ERROR("rc:%4x", rc);
 	}
 	spin_unlock_irqrestore(get_ccwdev_lock(cdev), saveflags);
 
@@ -1565,23 +1497,38 @@ static inline int buf_in_between(int bufnr, int start, int count)
 static void handle_inbound(struct qdio_q *q, unsigned int callflags,
 			   int bufnr, int count)
 {
-	unsigned long flags;
-	int used, rc;
+	int used, rc, diff;
 
-	/*
-	 * do_QDIO could run in parallel with the queue tasklet so the
-	 * upper-layer programm could empty the ACK'ed buffer here.
-	 * If that happens we must clear the polling flag, otherwise
-	 * qdio_stop_polling() could set the buffer to NOT_INIT after
-	 * it was set to EMPTY which would kill us.
-	 */
-	spin_lock_irqsave(&q->u.in.lock, flags);
-	if (q->u.in.polling)
-		if (buf_in_between(q->last_move_ftc, bufnr, count))
+	if (!q->u.in.polling)
+		goto set;
+
+	/* protect against stop polling setting an ACK for an emptied slsb */
+	if (count == QDIO_MAX_BUFFERS_PER_Q) {
+		/* overwriting everything, just delete polling status */
+		q->u.in.polling = 0;
+		q->u.in.ack_count = 0;
+		goto set;
+	} else if (buf_in_between(q->last_move_ftc, bufnr, count)) {
+		if (is_qebsm(q)) {
+			/* partial overwrite, just update last_move_ftc */
+			diff = add_buf(bufnr, count);
+			diff = sub_buf(diff, q->last_move_ftc);
+			q->u.in.ack_count -= diff;
+			if (q->u.in.ack_count <= 0) {
+				q->u.in.polling = 0;
+				q->u.in.ack_count = 0;
+				/* TODO: must we set last_move_ftc to something meaningful? */
+				goto set;
+			}
+			q->last_move_ftc = add_buf(q->last_move_ftc, diff);
+		}
+		else
+			/* the only ACK will be deleted, so stop polling */
 			q->u.in.polling = 0;
+	}
 
+set:
 	count = set_buf_states(q, bufnr, SLSB_CU_INPUT_EMPTY, count);
-	spin_unlock_irqrestore(&q->u.in.lock, flags);
 
 	used = atomic_add_return(count, &q->nr_buf_used) - count;
 	BUG_ON(used + count > QDIO_MAX_BUFFERS_PER_Q);
@@ -1649,11 +1596,11 @@ static void handle_outbound(struct qdio_q *q, unsigned int callflags,
 	}
 
 	/* try to fast requeue buffers */
-	get_buf_state(q, prev_buf(bufnr), &state);
+	get_buf_state(q, prev_buf(bufnr), &state, 0);
 	if (state != SLSB_CU_OUTPUT_PRIMED)
 		qdio_kick_outbound_q(q);
 	else {
-		QDIO_DBF_TEXT5(0, trace, "fast-req");
+		DBF_DEV_EVENT(DBF_INFO, q->irq_ptr, "fast-req");
 		qdio_perf_stat_inc(&perf_stats.fast_requeue);
 	}
 out:
@@ -1673,12 +1620,6 @@ int do_QDIO(struct ccw_device *cdev, unsigned int callflags,
 	    int q_nr, int bufnr, int count)
 {
 	struct qdio_irq *irq_ptr;
-#ifdef CONFIG_QDIO_DEBUG
-	char dbf_text[20];
-
-	sprintf(dbf_text, "doQD%4x", cdev->private->schid.sch_no);
-	QDIO_DBF_TEXT3(0, trace, dbf_text);
-#endif /* CONFIG_QDIO_DEBUG */
 
 	if ((bufnr > QDIO_MAX_BUFFERS_PER_Q) ||
 	    (count > QDIO_MAX_BUFFERS_PER_Q) ||
@@ -1692,33 +1633,24 @@ int do_QDIO(struct ccw_device *cdev, unsigned int callflags,
 	if (!irq_ptr)
 		return -ENODEV;
 
-#ifdef CONFIG_QDIO_DEBUG
 	if (callflags & QDIO_FLAG_SYNC_INPUT)
-		QDIO_DBF_HEX3(0, trace, &irq_ptr->input_qs[q_nr],
-			      sizeof(void *));
+		DBF_DEV_EVENT(DBF_INFO, irq_ptr, "doQDIO input");
 	else
-		QDIO_DBF_HEX3(0, trace, &irq_ptr->output_qs[q_nr],
-			      sizeof(void *));
-
-	sprintf(dbf_text, "flag%04x", callflags);
-	QDIO_DBF_TEXT3(0, trace, dbf_text);
-	sprintf(dbf_text, "qi%02xct%02x", bufnr, count);
-	QDIO_DBF_TEXT3(0, trace, dbf_text);
-#endif /* CONFIG_QDIO_DEBUG */
+		DBF_DEV_EVENT(DBF_INFO, irq_ptr, "doQDIO output");
+	DBF_DEV_EVENT(DBF_INFO, irq_ptr, "q:%1d flag:%4x", q_nr, callflags);
+	DBF_DEV_EVENT(DBF_INFO, irq_ptr, "buf:%2d cnt:%3d", bufnr, count);
 
 	if (irq_ptr->state != QDIO_IRQ_STATE_ACTIVE)
 		return -EBUSY;
 
 	if (callflags & QDIO_FLAG_SYNC_INPUT)
-		handle_inbound(irq_ptr->input_qs[q_nr],
-			       callflags, bufnr, count);
+		handle_inbound(irq_ptr->input_qs[q_nr], callflags, bufnr,
+			       count);
 	else if (callflags & QDIO_FLAG_SYNC_OUTPUT)
-		handle_outbound(irq_ptr->output_qs[q_nr],
-				callflags, bufnr, count);
-	else {
-		QDIO_DBF_TEXT3(1, trace, "doQD:inv");
+		handle_outbound(irq_ptr->output_qs[q_nr], callflags, bufnr,
+				count);
+	else
 		return -EINVAL;
-	}
 	return 0;
 }
 EXPORT_SYMBOL_GPL(do_QDIO);
diff --git a/drivers/s390/cio/qdio_perf.c b/drivers/s390/cio/qdio_perf.c
index ec5c4a414235..136d0f0b1e93 100644
--- a/drivers/s390/cio/qdio_perf.c
+++ b/drivers/s390/cio/qdio_perf.c
@@ -74,12 +74,20 @@ static int qdio_perf_proc_show(struct seq_file *m, void *v)
 	seq_printf(m, "\n");
 	seq_printf(m, "Number of fast requeues (outg. SBAL w/o SIGA)\t: %li\n",
 		   (long)atomic_long_read(&perf_stats.fast_requeue));
+	seq_printf(m, "Number of outbound target full condition\t: %li\n",
+		   (long)atomic_long_read(&perf_stats.outbound_target_full));
 	seq_printf(m, "Number of outbound tasklet mod_timer calls\t: %li\n",
 		   (long)atomic_long_read(&perf_stats.debug_tl_out_timer));
 	seq_printf(m, "Number of stop polling calls\t\t\t: %li\n",
 		   (long)atomic_long_read(&perf_stats.debug_stop_polling));
 	seq_printf(m, "AI inbound tasklet loops after stop polling\t: %li\n",
 		   (long)atomic_long_read(&perf_stats.thinint_inbound_loop2));
+	seq_printf(m, "QEBSM EQBS total/incomplete\t\t\t: %li/%li\n",
+		   (long)atomic_long_read(&perf_stats.debug_eqbs_all),
+		   (long)atomic_long_read(&perf_stats.debug_eqbs_incomplete));
+	seq_printf(m, "QEBSM SQBS total/incomplete\t\t\t: %li/%li\n",
+		   (long)atomic_long_read(&perf_stats.debug_sqbs_all),
+		   (long)atomic_long_read(&perf_stats.debug_sqbs_incomplete));
 	seq_printf(m, "\n");
 	return 0;
 }
diff --git a/drivers/s390/cio/qdio_perf.h b/drivers/s390/cio/qdio_perf.h
index 5c406a8b7387..7821ac4fa517 100644
--- a/drivers/s390/cio/qdio_perf.h
+++ b/drivers/s390/cio/qdio_perf.h
@@ -36,10 +36,15 @@ struct qdio_perf_stats {
 	atomic_long_t inbound_handler;
 	atomic_long_t outbound_handler;
 	atomic_long_t fast_requeue;
+	atomic_long_t outbound_target_full;
 
 	/* for debugging */
 	atomic_long_t debug_tl_out_timer;
 	atomic_long_t debug_stop_polling;
+	atomic_long_t debug_eqbs_all;
+	atomic_long_t debug_eqbs_incomplete;
+	atomic_long_t debug_sqbs_all;
+	atomic_long_t debug_sqbs_incomplete;
 };
 
 extern struct qdio_perf_stats perf_stats;
diff --git a/drivers/s390/cio/qdio_setup.c b/drivers/s390/cio/qdio_setup.c
index a0b6b46e7466..18d54fc21ce9 100644
--- a/drivers/s390/cio/qdio_setup.c
+++ b/drivers/s390/cio/qdio_setup.c
@@ -120,14 +120,12 @@ static void setup_queues_misc(struct qdio_q *q, struct qdio_irq *irq_ptr,
 }
 
 static void setup_storage_lists(struct qdio_q *q, struct qdio_irq *irq_ptr,
-				void **sbals_array, char *dbf_text, int i)
+				void **sbals_array, int i)
 {
 	struct qdio_q *prev;
 	int j;
 
-	QDIO_DBF_TEXT0(0, setup, dbf_text);
-	QDIO_DBF_HEX0(0, setup, &q, sizeof(void *));
-
+	DBF_HEX(&q, sizeof(void *));
 	q->sl = (struct sl *)((char *)q->slib + PAGE_SIZE / 2);
 
 	/* fill in sbal */
@@ -150,31 +148,26 @@ static void setup_storage_lists(struct qdio_q *q, struct qdio_irq *irq_ptr,
 	for (j = 0; j < QDIO_MAX_BUFFERS_PER_Q; j++)
 		q->sl->element[j].sbal = (unsigned long)q->sbal[j];
 
-	QDIO_DBF_TEXT2(0, setup, "sl-sb-b0");
-	QDIO_DBF_HEX2(0, setup, q->sl, sizeof(void *));
-	QDIO_DBF_HEX2(0, setup, &q->slsb, sizeof(void *));
-	QDIO_DBF_HEX2(0, setup, q->sbal, sizeof(void *));
+	DBF_EVENT("sl-slsb-sbal");
+	DBF_HEX(q->sl, sizeof(void *));
+	DBF_HEX(&q->slsb, sizeof(void *));
+	DBF_HEX(q->sbal, sizeof(void *));
 }
 
 static void setup_queues(struct qdio_irq *irq_ptr,
 			 struct qdio_initialize *qdio_init)
 {
-	char dbf_text[20];
 	struct qdio_q *q;
 	void **input_sbal_array = qdio_init->input_sbal_addr_array;
 	void **output_sbal_array = qdio_init->output_sbal_addr_array;
 	int i;
 
-	sprintf(dbf_text, "qset%4x", qdio_init->cdev->private->schid.sch_no);
-	QDIO_DBF_TEXT0(0, setup, dbf_text);
-
 	for_each_input_queue(irq_ptr, q, i) {
-		sprintf(dbf_text, "in-q%4x", i);
+		DBF_EVENT("in-q:%1d", i);
 		setup_queues_misc(q, irq_ptr, qdio_init->input_handler, i);
 
 		q->is_input_q = 1;
-		spin_lock_init(&q->u.in.lock);
-		setup_storage_lists(q, irq_ptr, input_sbal_array, dbf_text, i);
+		setup_storage_lists(q, irq_ptr, input_sbal_array, i);
 		input_sbal_array += QDIO_MAX_BUFFERS_PER_Q;
 
 		if (is_thinint_irq(irq_ptr))
@@ -186,12 +179,11 @@ static void setup_queues(struct qdio_irq *irq_ptr,
 	}
 
 	for_each_output_queue(irq_ptr, q, i) {
-		sprintf(dbf_text, "outq%4x", i);
+		DBF_EVENT("outq:%1d", i);
 		setup_queues_misc(q, irq_ptr, qdio_init->output_handler, i);
 
 		q->is_input_q = 0;
-		setup_storage_lists(q, irq_ptr, output_sbal_array,
-				    dbf_text, i);
+		setup_storage_lists(q, irq_ptr, output_sbal_array, i);
 		output_sbal_array += QDIO_MAX_BUFFERS_PER_Q;
 
 		tasklet_init(&q->tasklet, qdio_outbound_processing,
@@ -222,8 +214,6 @@ static void process_ac_flags(struct qdio_irq *irq_ptr, unsigned char qdioac)
 static void check_and_setup_qebsm(struct qdio_irq *irq_ptr,
 				  unsigned char qdioac, unsigned long token)
 {
-	char dbf_text[15];
-
 	if (!(irq_ptr->qib.rflags & QIB_RFLAGS_ENABLE_QEBSM))
 		goto no_qebsm;
 	if (!(qdioac & AC1_SC_QEBSM_AVAILABLE) ||
@@ -232,33 +222,41 @@ static void check_and_setup_qebsm(struct qdio_irq *irq_ptr,
 
 	irq_ptr->sch_token = token;
 
-	QDIO_DBF_TEXT0(0, setup, "V=V:1");
-	sprintf(dbf_text, "%8lx", irq_ptr->sch_token);
-	QDIO_DBF_TEXT0(0, setup, dbf_text);
+	DBF_EVENT("V=V:1");
+	DBF_EVENT("%8lx", irq_ptr->sch_token);
 	return;
 
 no_qebsm:
 	irq_ptr->sch_token = 0;
 	irq_ptr->qib.rflags &= ~QIB_RFLAGS_ENABLE_QEBSM;
-	QDIO_DBF_TEXT0(0, setup, "noV=V");
+	DBF_EVENT("noV=V");
 }
 
-static int __get_ssqd_info(struct qdio_irq *irq_ptr)
+/*
+ * If there is a qdio_irq we use the chsc_page and store the information
+ * in the qdio_irq, otherwise we copy it to the specified structure.
+ */
+int qdio_setup_get_ssqd(struct qdio_irq *irq_ptr,
+			struct subchannel_id *schid,
+			struct qdio_ssqd_desc *data)
 {
 	struct chsc_ssqd_area *ssqd;
 	int rc;
 
-	QDIO_DBF_TEXT0(0, setup, "getssqd");
-	ssqd = (struct chsc_ssqd_area *)irq_ptr->chsc_page;
+	DBF_EVENT("getssqd:%4x", schid->sch_no);
+	if (irq_ptr != NULL)
+		ssqd = (struct chsc_ssqd_area *)irq_ptr->chsc_page;
+	else
+		ssqd = (struct chsc_ssqd_area *)__get_free_page(GFP_KERNEL);
 	memset(ssqd, 0, PAGE_SIZE);
 
 	ssqd->request = (struct chsc_header) {
 		.length = 0x0010,
 		.code	= 0x0024,
 	};
-	ssqd->first_sch = irq_ptr->schid.sch_no;
-	ssqd->last_sch = irq_ptr->schid.sch_no;
-	ssqd->ssid = irq_ptr->schid.ssid;
+	ssqd->first_sch = schid->sch_no;
+	ssqd->last_sch = schid->sch_no;
+	ssqd->ssid = schid->ssid;
 
 	if (chsc(ssqd))
 		return -EIO;
@@ -268,27 +266,29 @@ static int __get_ssqd_info(struct qdio_irq *irq_ptr)
 
 	if (!(ssqd->qdio_ssqd.flags & CHSC_FLAG_QDIO_CAPABILITY) ||
 	    !(ssqd->qdio_ssqd.flags & CHSC_FLAG_VALIDITY) ||
-	    (ssqd->qdio_ssqd.sch != irq_ptr->schid.sch_no))
+	    (ssqd->qdio_ssqd.sch != schid->sch_no))
 		return -EINVAL;
 
-	memcpy(&irq_ptr->ssqd_desc, &ssqd->qdio_ssqd,
-	       sizeof(struct qdio_ssqd_desc));
+	if (irq_ptr != NULL)
+		memcpy(&irq_ptr->ssqd_desc, &ssqd->qdio_ssqd,
+		       sizeof(struct qdio_ssqd_desc));
+	else {
+		memcpy(data, &ssqd->qdio_ssqd,
+		       sizeof(struct qdio_ssqd_desc));
+		free_page((unsigned long)ssqd);
+	}
 	return 0;
 }
 
 void qdio_setup_ssqd_info(struct qdio_irq *irq_ptr)
 {
 	unsigned char qdioac;
-	char dbf_text[15];
 	int rc;
 
-	rc = __get_ssqd_info(irq_ptr);
+	rc = qdio_setup_get_ssqd(irq_ptr, &irq_ptr->schid, NULL);
 	if (rc) {
-		QDIO_DBF_TEXT2(0, setup, "ssqdasig");
-		sprintf(dbf_text, "schn%4x", irq_ptr->schid.sch_no);
-		QDIO_DBF_TEXT2(0, setup, dbf_text);
-		sprintf(dbf_text, "rc:%d", rc);
-		QDIO_DBF_TEXT2(0, setup, dbf_text);
+		DBF_ERROR("%4x ssqd ERR", irq_ptr->schid.sch_no);
+		DBF_ERROR("rc:%x", rc);
 		/* all flags set, worst case */
 		qdioac = AC1_SIGA_INPUT_NEEDED | AC1_SIGA_OUTPUT_NEEDED |
 			 AC1_SIGA_SYNC_NEEDED;
@@ -297,9 +297,7 @@ void qdio_setup_ssqd_info(struct qdio_irq *irq_ptr)
 
 	check_and_setup_qebsm(irq_ptr, qdioac, irq_ptr->ssqd_desc.sch_token);
 	process_ac_flags(irq_ptr, qdioac);
-
-	sprintf(dbf_text, "qdioac%2x", qdioac);
-	QDIO_DBF_TEXT2(0, setup, dbf_text);
+	DBF_EVENT("qdioac:%4x", qdioac);
 }
 
 void qdio_release_memory(struct qdio_irq *irq_ptr)
@@ -419,7 +417,7 @@ int qdio_setup_irq(struct qdio_initialize *init_data)
 	/* get qdio commands */
 	ciw = ccw_device_get_ciw(init_data->cdev, CIW_TYPE_EQUEUE);
 	if (!ciw) {
-		QDIO_DBF_TEXT2(1, setup, "no eq");
+		DBF_ERROR("%4x NO EQ", irq_ptr->schid.sch_no);
 		rc = -EINVAL;
 		goto out_err;
 	}
@@ -427,7 +425,7 @@ int qdio_setup_irq(struct qdio_initialize *init_data)
 
 	ciw = ccw_device_get_ciw(init_data->cdev, CIW_TYPE_AQUEUE);
 	if (!ciw) {
-		QDIO_DBF_TEXT2(1, setup, "no aq");
+		DBF_ERROR("%4x NO AQ", irq_ptr->schid.sch_no);
 		rc = -EINVAL;
 		goto out_err;
 	}
@@ -447,56 +445,38 @@ void qdio_print_subchannel_info(struct qdio_irq *irq_ptr,
 {
 	char s[80];
 
-	sprintf(s, "qdio: %s ", dev_name(&cdev->dev));
-	switch (irq_ptr->qib.qfmt) {
-	case QDIO_QETH_QFMT:
-		sprintf(s + strlen(s), "OSA ");
-		break;
-	case QDIO_ZFCP_QFMT:
-		sprintf(s + strlen(s), "ZFCP ");
-		break;
-	case QDIO_IQDIO_QFMT:
-		sprintf(s + strlen(s), "HS ");
-		break;
-	}
-	sprintf(s + strlen(s), "on SC %x using ", irq_ptr->schid.sch_no);
-	sprintf(s + strlen(s), "AI:%d ", is_thinint_irq(irq_ptr));
-	sprintf(s + strlen(s), "QEBSM:%d ", (irq_ptr->sch_token) ? 1 : 0);
-	sprintf(s + strlen(s), "PCI:%d ",
-		(irq_ptr->qib.ac & QIB_AC_OUTBOUND_PCI_SUPPORTED) ? 1 : 0);
-	sprintf(s + strlen(s), "TDD:%d ", css_general_characteristics.aif_tdd);
-	sprintf(s + strlen(s), "SIGA:");
-	sprintf(s + strlen(s), "%s", (irq_ptr->siga_flag.input) ? "R" : " ");
-	sprintf(s + strlen(s), "%s", (irq_ptr->siga_flag.output) ? "W" : " ");
-	sprintf(s + strlen(s), "%s", (irq_ptr->siga_flag.sync) ? "S" : " ");
-	sprintf(s + strlen(s), "%s",
-		(!irq_ptr->siga_flag.no_sync_ti) ? "A" : " ");
-	sprintf(s + strlen(s), "%s",
-		(!irq_ptr->siga_flag.no_sync_out_ti) ? "O" : " ");
-	sprintf(s + strlen(s), "%s",
-		(!irq_ptr->siga_flag.no_sync_out_pci) ? "P" : " ");
-	sprintf(s + strlen(s), "\n");
+	snprintf(s, 80, "qdio: %s %s on SC %x using "
+		 "AI:%d QEBSM:%d PCI:%d TDD:%d SIGA:%s%s%s%s%s%s\n",
+		 dev_name(&cdev->dev),
+		 (irq_ptr->qib.qfmt == QDIO_QETH_QFMT) ? "OSA" :
+			((irq_ptr->qib.qfmt == QDIO_ZFCP_QFMT) ? "ZFCP" : "HS"),
+		 irq_ptr->schid.sch_no,
+		 is_thinint_irq(irq_ptr),
+		 (irq_ptr->sch_token) ? 1 : 0,
+		 (irq_ptr->qib.ac & QIB_AC_OUTBOUND_PCI_SUPPORTED) ? 1 : 0,
+		 css_general_characteristics.aif_tdd,
+		 (irq_ptr->siga_flag.input) ? "R" : " ",
+		 (irq_ptr->siga_flag.output) ? "W" : " ",
+		 (irq_ptr->siga_flag.sync) ? "S" : " ",
+		 (!irq_ptr->siga_flag.no_sync_ti) ? "A" : " ",
+		 (!irq_ptr->siga_flag.no_sync_out_ti) ? "O" : " ",
+		 (!irq_ptr->siga_flag.no_sync_out_pci) ? "P" : " ");
 	printk(KERN_INFO "%s", s);
 }
 
 int __init qdio_setup_init(void)
 {
-	char dbf_text[15];
-
 	qdio_q_cache = kmem_cache_create("qdio_q", sizeof(struct qdio_q),
 					 256, 0, NULL);
 	if (!qdio_q_cache)
 		return -ENOMEM;
 
 	/* Check for OSA/FCP thin interrupts (bit 67). */
-	sprintf(dbf_text, "thini%1x",
-		(css_general_characteristics.aif_osa) ? 1 : 0);
-	QDIO_DBF_TEXT0(0, setup, dbf_text);
+	DBF_EVENT("thinint:%1d",
+		  (css_general_characteristics.aif_osa) ? 1 : 0);
 
 	/* Check for QEBSM support in general (bit 58). */
-	sprintf(dbf_text, "cssQBS:%1x",
-		(qebsm_possible()) ? 1 : 0);
-	QDIO_DBF_TEXT0(0, setup, dbf_text);
+	DBF_EVENT("cssQEBSM:%1d", (qebsm_possible()) ? 1 : 0);
 	return 0;
 }
 
diff --git a/drivers/s390/cio/qdio_thinint.c b/drivers/s390/cio/qdio_thinint.c
index ea7f61400267..8e90e147b746 100644
--- a/drivers/s390/cio/qdio_thinint.c
+++ b/drivers/s390/cio/qdio_thinint.c
@@ -125,13 +125,13 @@ void tiqdio_remove_input_queues(struct qdio_irq *irq_ptr)
 
 static inline int tiqdio_inbound_q_done(struct qdio_q *q)
 {
-	unsigned char state;
+	unsigned char state = 0;
 
 	if (!atomic_read(&q->nr_buf_used))
 		return 1;
 
 	qdio_siga_sync_q(q);
-	get_buf_state(q, q->first_to_check, &state);
+	get_buf_state(q, q->first_to_check, &state, 0);
 
 	if (state == SLSB_P_INPUT_PRIMED)
 		/* more work coming */
@@ -258,8 +258,6 @@ static void tiqdio_thinint_handler(void *ind, void *drv_data)
 static int set_subchannel_ind(struct qdio_irq *irq_ptr, int reset)
 {
 	struct scssc_area *scssc_area;
-	char dbf_text[15];
-	void *ptr;
 	int rc;
 
 	scssc_area = (struct scssc_area *)irq_ptr->chsc_page;
@@ -294,19 +292,15 @@ static int set_subchannel_ind(struct qdio_irq *irq_ptr, int reset)
 
 	rc = chsc_error_from_response(scssc_area->response.code);
 	if (rc) {
-		sprintf(dbf_text, "sidR%4x", scssc_area->response.code);
-		QDIO_DBF_TEXT1(0, trace, dbf_text);
-		QDIO_DBF_TEXT1(0, setup, dbf_text);
-		ptr = &scssc_area->response;
-		QDIO_DBF_HEX2(1, setup, &ptr, QDIO_DBF_SETUP_LEN);
+		DBF_ERROR("%4x SSI r:%4x", irq_ptr->schid.sch_no,
+			  scssc_area->response.code);
+		DBF_ERROR_HEX(&scssc_area->response, sizeof(void *));
 		return rc;
 	}
 
-	QDIO_DBF_TEXT2(0, setup, "setscind");
-	QDIO_DBF_HEX2(0, setup, &scssc_area->summary_indicator_addr,
-		      sizeof(unsigned long));
-	QDIO_DBF_HEX2(0, setup, &scssc_area->subchannel_indicator_addr,
-		      sizeof(unsigned long));
+	DBF_EVENT("setscind");
+	DBF_HEX(&scssc_area->summary_indicator_addr, sizeof(unsigned long));
+	DBF_HEX(&scssc_area->subchannel_indicator_addr,	sizeof(unsigned long));
 	return 0;
 }
 
@@ -327,14 +321,11 @@ void tiqdio_free_memory(void)
 
 int __init tiqdio_register_thinints(void)
 {
-	char dbf_text[20];
-
 	isc_register(QDIO_AIRQ_ISC);
 	tiqdio_alsi = s390_register_adapter_interrupt(&tiqdio_thinint_handler,
 						      NULL, QDIO_AIRQ_ISC);
 	if (IS_ERR(tiqdio_alsi)) {
-		sprintf(dbf_text, "regthn%lx", PTR_ERR(tiqdio_alsi));
-		QDIO_DBF_TEXT0(0, setup, dbf_text);
+		DBF_EVENT("RTI:%lx", PTR_ERR(tiqdio_alsi));
 		tiqdio_alsi = NULL;
 		isc_unregister(QDIO_AIRQ_ISC);
 		return -ENOMEM;
@@ -360,7 +351,7 @@ void qdio_setup_thinint(struct qdio_irq *irq_ptr)
 	if (!is_thinint_irq(irq_ptr))
 		return;
 	irq_ptr->dsci = get_indicator();
-	QDIO_DBF_HEX1(0, setup, &irq_ptr->dsci, sizeof(void *));
+	DBF_HEX(&irq_ptr->dsci, sizeof(void *));
 }
 
 void qdio_shutdown_thinint(struct qdio_irq *irq_ptr)
diff --git a/drivers/s390/crypto/ap_bus.c b/drivers/s390/crypto/ap_bus.c
index e3fe6838293a..1f5f5d2d87d9 100644
--- a/drivers/s390/crypto/ap_bus.c
+++ b/drivers/s390/crypto/ap_bus.c
@@ -5,6 +5,7 @@
  * Author(s): Cornelia Huck <cornelia.huck@de.ibm.com>
  *	      Martin Schwidefsky <schwidefsky@de.ibm.com>
  *	      Ralph Wuerthner <rwuerthn@de.ibm.com>
+ *	      Felix Beck <felix.beck@de.ibm.com>
  *
  * Adjunct processor bus.
  *
@@ -23,6 +24,9 @@
  * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
+#define KMSG_COMPONENT "ap"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
 #include <linux/module.h>
 #include <linux/init.h>
 #include <linux/delay.h>
@@ -34,6 +38,10 @@
 #include <linux/mutex.h>
 #include <asm/s390_rdev.h>
 #include <asm/reset.h>
+#include <asm/airq.h>
+#include <asm/atomic.h>
+#include <asm/system.h>
+#include <asm/isc.h>
 #include <linux/hrtimer.h>
 #include <linux/ktime.h>
 
@@ -46,6 +54,7 @@ static enum hrtimer_restart ap_poll_timeout(struct hrtimer *);
 static int ap_poll_thread_start(void);
 static void ap_poll_thread_stop(void);
 static void ap_request_timeout(unsigned long);
+static inline void ap_schedule_poll_timer(void);
 
 /*
  * Module description.
@@ -68,7 +77,7 @@ module_param_named(poll_thread, ap_thread_flag, int, 0000);
 MODULE_PARM_DESC(poll_thread, "Turn on/off poll thread, default is 0 (off).");
 
 static struct device *ap_root_device = NULL;
-static DEFINE_SPINLOCK(ap_device_lock);
+static DEFINE_SPINLOCK(ap_device_list_lock);
 static LIST_HEAD(ap_device_list);
 
 /*
@@ -80,19 +89,29 @@ static int ap_config_time = AP_CONFIG_TIME;
 static DECLARE_WORK(ap_config_work, ap_scan_bus);
 
 /*
- * Tasklet & timer for AP request polling.
+ * Tasklet & timer for AP request polling and interrupts
  */
 static DECLARE_TASKLET(ap_tasklet, ap_poll_all, 0);
 static atomic_t ap_poll_requests = ATOMIC_INIT(0);
 static DECLARE_WAIT_QUEUE_HEAD(ap_poll_wait);
 static struct task_struct *ap_poll_kthread = NULL;
 static DEFINE_MUTEX(ap_poll_thread_mutex);
+static void *ap_interrupt_indicator;
 static struct hrtimer ap_poll_timer;
 /* In LPAR poll with 4kHz frequency. Poll every 250000 nanoseconds.
  * If z/VM change to 1500000 nanoseconds to adjust to z/VM polling.*/
 static unsigned long long poll_timeout = 250000;
 
 /**
+ * ap_using_interrupts() - Returns non-zero if interrupt support is
+ * available.
+ */
+static inline int ap_using_interrupts(void)
+{
+	return ap_interrupt_indicator != NULL;
+}
+
+/**
  * ap_intructions_available() - Test if AP instructions are available.
  *
  * Returns 0 if the AP instructions are installed.
@@ -113,6 +132,23 @@ static inline int ap_instructions_available(void)
 }
 
 /**
+ * ap_interrupts_available(): Test if AP interrupts are available.
+ *
+ * Returns 1 if AP interrupts are available.
+ */
+static int ap_interrupts_available(void)
+{
+	unsigned long long facility_bits[2];
+
+	if (stfle(facility_bits, 2) <= 1)
+		return 0;
+	if (!(facility_bits[0] & (1ULL << 61)) ||
+	    !(facility_bits[1] & (1ULL << 62)))
+		return 0;
+	return 1;
+}
+
+/**
  * ap_test_queue(): Test adjunct processor queue.
  * @qid: The AP queue number
  * @queue_depth: Pointer to queue depth value
@@ -152,6 +188,80 @@ static inline struct ap_queue_status ap_reset_queue(ap_qid_t qid)
 	return reg1;
 }
 
+#ifdef CONFIG_64BIT
+/**
+ * ap_queue_interruption_control(): Enable interruption for a specific AP.
+ * @qid: The AP queue number
+ * @ind: The notification indicator byte
+ *
+ * Returns AP queue status.
+ */
+static inline struct ap_queue_status
+ap_queue_interruption_control(ap_qid_t qid, void *ind)
+{
+	register unsigned long reg0 asm ("0") = qid | 0x03000000UL;
+	register unsigned long reg1_in asm ("1") = 0x0000800000000000UL | AP_ISC;
+	register struct ap_queue_status reg1_out asm ("1");
+	register void *reg2 asm ("2") = ind;
+	asm volatile(
+		".long 0xb2af0000"		/* PQAP(RAPQ) */
+		: "+d" (reg0), "+d" (reg1_in), "=d" (reg1_out), "+d" (reg2)
+		:
+		: "cc" );
+	return reg1_out;
+}
+#endif
+
+/**
+ * ap_queue_enable_interruption(): Enable interruption on an AP.
+ * @qid: The AP queue number
+ * @ind: the notification indicator byte
+ *
+ * Enables interruption on AP queue via ap_queue_interruption_control(). Based
+ * on the return value it waits a while and tests the AP queue if interrupts
+ * have been switched on using ap_test_queue().
+ */
+static int ap_queue_enable_interruption(ap_qid_t qid, void *ind)
+{
+#ifdef CONFIG_64BIT
+	struct ap_queue_status status;
+	int t_depth, t_device_type, rc, i;
+
+	rc = -EBUSY;
+	status = ap_queue_interruption_control(qid, ind);
+
+	for (i = 0; i < AP_MAX_RESET; i++) {
+		switch (status.response_code) {
+		case AP_RESPONSE_NORMAL:
+			if (status.int_enabled)
+				return 0;
+			break;
+		case AP_RESPONSE_RESET_IN_PROGRESS:
+		case AP_RESPONSE_BUSY:
+			break;
+		case AP_RESPONSE_Q_NOT_AVAIL:
+		case AP_RESPONSE_DECONFIGURED:
+		case AP_RESPONSE_CHECKSTOPPED:
+		case AP_RESPONSE_INVALID_ADDRESS:
+			return -ENODEV;
+		case AP_RESPONSE_OTHERWISE_CHANGED:
+			if (status.int_enabled)
+				return 0;
+			break;
+		default:
+			break;
+		}
+		if (i < AP_MAX_RESET - 1) {
+			udelay(5);
+			status = ap_test_queue(qid, &t_depth, &t_device_type);
+		}
+	}
+	return rc;
+#else
+	return -EINVAL;
+#endif
+}
+
 /**
  * __ap_send(): Send message to adjunct processor queue.
  * @qid: The AP queue number
@@ -295,6 +405,11 @@ static int ap_query_queue(ap_qid_t qid, int *queue_depth, int *device_type)
 		case AP_RESPONSE_CHECKSTOPPED:
 			rc = -ENODEV;
 			break;
+		case AP_RESPONSE_INVALID_ADDRESS:
+			rc = -ENODEV;
+			break;
+		case AP_RESPONSE_OTHERWISE_CHANGED:
+			break;
 		case AP_RESPONSE_BUSY:
 			break;
 		default:
@@ -345,6 +460,15 @@ static int ap_init_queue(ap_qid_t qid)
 			status = ap_test_queue(qid, &dummy, &dummy);
 		}
 	}
+	if (rc == 0 && ap_using_interrupts()) {
+		rc = ap_queue_enable_interruption(qid, ap_interrupt_indicator);
+		/* If interruption mode is supported by the machine,
+		* but an AP can not be enabled for interruption then
+		* the AP will be discarded.    */
+		if (rc)
+			pr_err("Registering adapter interrupts for "
+			       "AP %d failed\n", AP_QID_DEVICE(qid));
+	}
 	return rc;
 }
 
@@ -397,16 +521,16 @@ static ssize_t ap_hwtype_show(struct device *dev,
 	struct ap_device *ap_dev = to_ap_dev(dev);
 	return snprintf(buf, PAGE_SIZE, "%d\n", ap_dev->device_type);
 }
-static DEVICE_ATTR(hwtype, 0444, ap_hwtype_show, NULL);
 
+static DEVICE_ATTR(hwtype, 0444, ap_hwtype_show, NULL);
 static ssize_t ap_depth_show(struct device *dev, struct device_attribute *attr,
 			     char *buf)
 {
 	struct ap_device *ap_dev = to_ap_dev(dev);
 	return snprintf(buf, PAGE_SIZE, "%d\n", ap_dev->queue_depth);
 }
-static DEVICE_ATTR(depth, 0444, ap_depth_show, NULL);
 
+static DEVICE_ATTR(depth, 0444, ap_depth_show, NULL);
 static ssize_t ap_request_count_show(struct device *dev,
 				     struct device_attribute *attr,
 				     char *buf)
@@ -509,9 +633,9 @@ static int ap_device_probe(struct device *dev)
 	ap_dev->drv = ap_drv;
 	rc = ap_drv->probe ? ap_drv->probe(ap_dev) : -ENODEV;
 	if (!rc) {
-		spin_lock_bh(&ap_device_lock);
+		spin_lock_bh(&ap_device_list_lock);
 		list_add(&ap_dev->list, &ap_device_list);
-		spin_unlock_bh(&ap_device_lock);
+		spin_unlock_bh(&ap_device_list_lock);
 	}
 	return rc;
 }
@@ -553,9 +677,9 @@ static int ap_device_remove(struct device *dev)
 
 	ap_flush_queue(ap_dev);
 	del_timer_sync(&ap_dev->timeout);
-	spin_lock_bh(&ap_device_lock);
+	spin_lock_bh(&ap_device_list_lock);
 	list_del_init(&ap_dev->list);
-	spin_unlock_bh(&ap_device_lock);
+	spin_unlock_bh(&ap_device_list_lock);
 	if (ap_drv->remove)
 		ap_drv->remove(ap_dev);
 	spin_lock_bh(&ap_dev->lock);
@@ -599,6 +723,14 @@ static ssize_t ap_config_time_show(struct bus_type *bus, char *buf)
 	return snprintf(buf, PAGE_SIZE, "%d\n", ap_config_time);
 }
 
+static ssize_t ap_interrupts_show(struct bus_type *bus, char *buf)
+{
+	return snprintf(buf, PAGE_SIZE, "%d\n",
+			ap_using_interrupts() ? 1 : 0);
+}
+
+static BUS_ATTR(ap_interrupts, 0444, ap_interrupts_show, NULL);
+
 static ssize_t ap_config_time_store(struct bus_type *bus,
 				    const char *buf, size_t count)
 {
@@ -653,7 +785,8 @@ static ssize_t poll_timeout_store(struct bus_type *bus, const char *buf,
 	ktime_t hr_time;
 
 	/* 120 seconds = maximum poll interval */
-	if (sscanf(buf, "%llu\n", &time) != 1 || time < 1 || time > 120000000000)
+	if (sscanf(buf, "%llu\n", &time) != 1 || time < 1 ||
+	    time > 120000000000ULL)
 		return -EINVAL;
 	poll_timeout = time;
 	hr_time = ktime_set(0, poll_timeout);
@@ -672,6 +805,7 @@ static struct bus_attribute *const ap_bus_attrs[] = {
 	&bus_attr_ap_domain,
 	&bus_attr_config_time,
 	&bus_attr_poll_thread,
+	&bus_attr_ap_interrupts,
 	&bus_attr_poll_timeout,
 	NULL,
 };
@@ -814,6 +948,11 @@ out:
 	return rc;
 }
 
+static void ap_interrupt_handler(void *unused1, void *unused2)
+{
+	tasklet_schedule(&ap_tasklet);
+}
+
 /**
  * __ap_scan_bus(): Scan the AP bus.
  * @dev: Pointer to device
@@ -928,6 +1067,8 @@ ap_config_timeout(unsigned long ptr)
  */
 static inline void ap_schedule_poll_timer(void)
 {
+	if (ap_using_interrupts())
+		return;
 	if (hrtimer_is_queued(&ap_poll_timer))
 		return;
 	hrtimer_start(&ap_poll_timer, ktime_set(0, poll_timeout),
@@ -1181,7 +1322,7 @@ static void ap_reset(struct ap_device *ap_dev)
 		ap_dev->unregistered = 1;
 }
 
-static int __ap_poll_all(struct ap_device *ap_dev, unsigned long *flags)
+static int __ap_poll_device(struct ap_device *ap_dev, unsigned long *flags)
 {
 	spin_lock(&ap_dev->lock);
 	if (!ap_dev->unregistered) {
@@ -1207,13 +1348,19 @@ static void ap_poll_all(unsigned long dummy)
 	unsigned long flags;
 	struct ap_device *ap_dev;
 
+	/* Reset the indicator if interrupts are used. Thus new interrupts can
+	 * be received. Doing it in the beginning of the tasklet is therefor
+	 * important that no requests on any AP get lost.
+	 */
+	if (ap_using_interrupts())
+		xchg((u8 *)ap_interrupt_indicator, 0);
 	do {
 		flags = 0;
-		spin_lock(&ap_device_lock);
+		spin_lock(&ap_device_list_lock);
 		list_for_each_entry(ap_dev, &ap_device_list, list) {
-			__ap_poll_all(ap_dev, &flags);
+			__ap_poll_device(ap_dev, &flags);
 		}
-		spin_unlock(&ap_device_lock);
+		spin_unlock(&ap_device_list_lock);
 	} while (flags & 1);
 	if (flags & 2)
 		ap_schedule_poll_timer();
@@ -1253,11 +1400,11 @@ static int ap_poll_thread(void *data)
 		remove_wait_queue(&ap_poll_wait, &wait);
 
 		flags = 0;
-		spin_lock_bh(&ap_device_lock);
+		spin_lock_bh(&ap_device_list_lock);
 		list_for_each_entry(ap_dev, &ap_device_list, list) {
-			__ap_poll_all(ap_dev, &flags);
+			__ap_poll_device(ap_dev, &flags);
 		}
-		spin_unlock_bh(&ap_device_lock);
+		spin_unlock_bh(&ap_device_list_lock);
 	}
 	set_current_state(TASK_RUNNING);
 	remove_wait_queue(&ap_poll_wait, &wait);
@@ -1268,6 +1415,8 @@ static int ap_poll_thread_start(void)
 {
 	int rc;
 
+	if (ap_using_interrupts())
+		return 0;
 	mutex_lock(&ap_poll_thread_mutex);
 	if (!ap_poll_kthread) {
 		ap_poll_kthread = kthread_run(ap_poll_thread, NULL, "appoll");
@@ -1301,8 +1450,12 @@ static void ap_request_timeout(unsigned long data)
 {
 	struct ap_device *ap_dev = (struct ap_device *) data;
 
-	if (ap_dev->reset == AP_RESET_ARMED)
+	if (ap_dev->reset == AP_RESET_ARMED) {
 		ap_dev->reset = AP_RESET_DO;
+
+		if (ap_using_interrupts())
+			tasklet_schedule(&ap_tasklet);
+	}
 }
 
 static void ap_reset_domain(void)
@@ -1337,14 +1490,25 @@ int __init ap_module_init(void)
 	int rc, i;
 
 	if (ap_domain_index < -1 || ap_domain_index >= AP_DOMAINS) {
-		printk(KERN_WARNING "Invalid param: domain = %d. "
-		       " Not loading.\n", ap_domain_index);
+		pr_warning("%d is not a valid cryptographic domain\n",
+			   ap_domain_index);
 		return -EINVAL;
 	}
 	if (ap_instructions_available() != 0) {
-		printk(KERN_WARNING "AP instructions not installed.\n");
+		pr_warning("The hardware system does not support "
+			   "AP instructions\n");
 		return -ENODEV;
 	}
+	if (ap_interrupts_available()) {
+		isc_register(AP_ISC);
+		ap_interrupt_indicator = s390_register_adapter_interrupt(
+			&ap_interrupt_handler, NULL, AP_ISC);
+		if (IS_ERR(ap_interrupt_indicator)) {
+			ap_interrupt_indicator = NULL;
+			isc_unregister(AP_ISC);
+		}
+	}
+
 	register_reset_call(&ap_reset_call);
 
 	/* Create /sys/bus/ap. */
@@ -1408,6 +1572,10 @@ out_bus:
 	bus_unregister(&ap_bus_type);
 out:
 	unregister_reset_call(&ap_reset_call);
+	if (ap_using_interrupts()) {
+		s390_unregister_adapter_interrupt(ap_interrupt_indicator, AP_ISC);
+		isc_unregister(AP_ISC);
+	}
 	return rc;
 }
 
@@ -1443,6 +1611,10 @@ void ap_module_exit(void)
 		bus_remove_file(&ap_bus_type, ap_bus_attrs[i]);
 	bus_unregister(&ap_bus_type);
 	unregister_reset_call(&ap_reset_call);
+	if (ap_using_interrupts()) {
+		s390_unregister_adapter_interrupt(ap_interrupt_indicator, AP_ISC);
+		isc_unregister(AP_ISC);
+	}
 }
 
 #ifndef CONFIG_ZCRYPT_MONOLITHIC
diff --git a/drivers/s390/crypto/ap_bus.h b/drivers/s390/crypto/ap_bus.h
index 446378b308fc..a35362241805 100644
--- a/drivers/s390/crypto/ap_bus.h
+++ b/drivers/s390/crypto/ap_bus.h
@@ -5,6 +5,7 @@
  * Author(s): Cornelia Huck <cornelia.huck@de.ibm.com>
  *	      Martin Schwidefsky <schwidefsky@de.ibm.com>
  *	      Ralph Wuerthner <rwuerthn@de.ibm.com>
+ *	      Felix Beck <felix.beck@de.ibm.com>
  *
  * Adjunct processor bus header file.
  *
@@ -67,7 +68,8 @@ struct ap_queue_status {
 	unsigned int queue_empty	: 1;
 	unsigned int replies_waiting	: 1;
 	unsigned int queue_full		: 1;
-	unsigned int pad1		: 5;
+	unsigned int pad1		: 4;
+	unsigned int int_enabled	: 1;
 	unsigned int response_code	: 8;
 	unsigned int pad2		: 16;
 };
@@ -78,6 +80,8 @@ struct ap_queue_status {
 #define AP_RESPONSE_DECONFIGURED	0x03
 #define AP_RESPONSE_CHECKSTOPPED	0x04
 #define AP_RESPONSE_BUSY		0x05
+#define AP_RESPONSE_INVALID_ADDRESS	0x06
+#define AP_RESPONSE_OTHERWISE_CHANGED	0x07
 #define AP_RESPONSE_Q_FULL		0x10
 #define AP_RESPONSE_NO_PENDING_REPLY	0x10
 #define AP_RESPONSE_INDEX_TOO_BIG	0x11
diff --git a/drivers/s390/net/ctcm_fsms.c b/drivers/s390/net/ctcm_fsms.c
index 42776550acfd..f29c7086fc19 100644
--- a/drivers/s390/net/ctcm_fsms.c
+++ b/drivers/s390/net/ctcm_fsms.c
@@ -13,6 +13,9 @@
 #undef DEBUGDATA
 #undef DEBUGCCW
 
+#define KMSG_COMPONENT "ctcm"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
 #include <linux/module.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
@@ -190,21 +193,22 @@ static void ctcmpc_chx_send_sweep(fsm_instance *fsm, int event, void *arg);
 void ctcm_ccw_check_rc(struct channel *ch, int rc, char *msg)
 {
 	CTCM_DBF_TEXT_(ERROR, CTC_DBF_ERROR,
-			"%s(%s): %s: %04x\n",
-				CTCM_FUNTAIL, ch->id, msg, rc);
+		"%s(%s): %s: %04x\n",
+		CTCM_FUNTAIL, ch->id, msg, rc);
 	switch (rc) {
 	case -EBUSY:
-		ctcm_pr_warn("%s (%s): Busy !\n", ch->id, msg);
+		pr_info("%s: The communication peer is busy\n",
+			ch->id);
 		fsm_event(ch->fsm, CTC_EVENT_IO_EBUSY, ch);
 		break;
 	case -ENODEV:
-		ctcm_pr_emerg("%s (%s): Invalid device called for IO\n",
-			     ch->id, msg);
+		pr_err("%s: The specified target device is not valid\n",
+		       ch->id);
 		fsm_event(ch->fsm, CTC_EVENT_IO_ENODEV, ch);
 		break;
 	default:
-		ctcm_pr_emerg("%s (%s): Unknown error in do_IO %04x\n",
-			     ch->id, msg, rc);
+		pr_err("An I/O operation resulted in error %04x\n",
+		       rc);
 		fsm_event(ch->fsm, CTC_EVENT_IO_UNKNOWN, ch);
 	}
 }
@@ -886,8 +890,15 @@ static void ctcm_chx_rxiniterr(fsm_instance *fi, int event, void *arg)
 			fsm_newstate(fi, CTC_STATE_RXERR);
 			fsm_event(priv->fsm, DEV_EVENT_RXDOWN, dev);
 		}
-	} else
-		ctcm_pr_warn("%s: Error during RX init handshake\n", dev->name);
+	} else {
+		CTCM_DBF_TEXT_(ERROR, CTC_DBF_ERROR,
+			"%s(%s): %s in %s", CTCM_FUNTAIL, ch->id,
+			ctc_ch_event_names[event], fsm_getstate_str(fi));
+
+		dev_warn(&dev->dev,
+			"Initialization failed with RX/TX init handshake "
+			"error %s\n", ctc_ch_event_names[event]);
+	}
 }
 
 /**
@@ -969,7 +980,9 @@ static void ctcm_chx_txiniterr(fsm_instance *fi, int event, void *arg)
 			"%s(%s): %s in %s", CTCM_FUNTAIL, ch->id,
 			ctc_ch_event_names[event], fsm_getstate_str(fi));
 
-		ctcm_pr_warn("%s: Error during TX init handshake\n", dev->name);
+		dev_warn(&dev->dev,
+			"Initialization failed with RX/TX init handshake "
+			"error %s\n", ctc_ch_event_names[event]);
 	}
 }
 
@@ -2101,14 +2114,11 @@ static void dev_action_restart(fsm_instance *fi, int event, void *arg)
 	CTCMY_DBF_DEV_NAME(TRACE, dev, "");
 
 	if (IS_MPC(priv)) {
-		ctcm_pr_info("ctcm: %s Restarting Device and "
-		       "MPC Group in 5 seconds\n",
-		       dev->name);
 		restart_timer = CTCM_TIME_1_SEC;
 	} else {
-		ctcm_pr_info("%s: Restarting\n", dev->name);
 		restart_timer = CTCM_TIME_5_SEC;
 	}
+	dev_info(&dev->dev, "Restarting device\n");
 
 	dev_action_stop(fi, event, arg);
 	fsm_event(priv->fsm, DEV_EVENT_STOP, dev);
@@ -2150,16 +2160,16 @@ static void dev_action_chup(fsm_instance *fi, int event, void *arg)
 	case DEV_STATE_STARTWAIT_RX:
 		if (event == DEV_EVENT_RXUP) {
 			fsm_newstate(fi, DEV_STATE_RUNNING);
-			ctcm_pr_info("%s: connected with remote side\n",
-				    dev->name);
+			dev_info(&dev->dev,
+				"Connected with remote side\n");
 			ctcm_clear_busy(dev);
 		}
 		break;
 	case DEV_STATE_STARTWAIT_TX:
 		if (event == DEV_EVENT_TXUP) {
 			fsm_newstate(fi, DEV_STATE_RUNNING);
-			ctcm_pr_info("%s: connected with remote side\n",
-				    dev->name);
+			dev_info(&dev->dev,
+				"Connected with remote side\n");
 			ctcm_clear_busy(dev);
 		}
 		break;
diff --git a/drivers/s390/net/ctcm_main.c b/drivers/s390/net/ctcm_main.c
index a4e29836a2aa..2678573becec 100644
--- a/drivers/s390/net/ctcm_main.c
+++ b/drivers/s390/net/ctcm_main.c
@@ -21,6 +21,9 @@
 #undef DEBUGDATA
 #undef DEBUGCCW
 
+#define KMSG_COMPONENT "ctcm"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
 #include <linux/module.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
@@ -281,14 +284,16 @@ static long ctcm_check_irb_error(struct ccw_device *cdev, struct irb *irb)
 
 	switch (PTR_ERR(irb)) {
 	case -EIO:
-		ctcm_pr_warn("i/o-error on device %s\n", dev_name(&cdev->dev));
+		dev_err(&cdev->dev,
+			"An I/O-error occurred on the CTCM device\n");
 		break;
 	case -ETIMEDOUT:
-		ctcm_pr_warn("timeout on device %s\n", dev_name(&cdev->dev));
+		dev_err(&cdev->dev,
+			"An adapter hardware operation timed out\n");
 		break;
 	default:
-		ctcm_pr_warn("unknown error %ld on device %s\n",
-				PTR_ERR(irb), dev_name(&cdev->dev));
+		dev_err(&cdev->dev,
+			"An error occurred on the adapter hardware\n");
 	}
 	return PTR_ERR(irb);
 }
@@ -309,15 +314,17 @@ static inline void ccw_unit_check(struct channel *ch, __u8 sense)
 	if (sense & SNS0_INTERVENTION_REQ) {
 		if (sense & 0x01) {
 			if (ch->sense_rc != 0x01) {
-				ctcm_pr_debug("%s: Interface disc. or Sel. "
-					      "reset (remote)\n", ch->id);
+				pr_notice(
+					"%s: The communication peer has "
+					"disconnected\n", ch->id);
 				ch->sense_rc = 0x01;
 			}
 			fsm_event(ch->fsm, CTC_EVENT_UC_RCRESET, ch);
 		} else {
 			if (ch->sense_rc != SNS0_INTERVENTION_REQ) {
-				ctcm_pr_debug("%s: System reset (remote)\n",
-					      ch->id);
+				pr_notice(
+					"%s: The remote operating system is "
+					"not available\n", ch->id);
 				ch->sense_rc = SNS0_INTERVENTION_REQ;
 			}
 			fsm_event(ch->fsm, CTC_EVENT_UC_RSRESET, ch);
@@ -1194,8 +1201,11 @@ static void ctcm_irq_handler(struct ccw_device *cdev,
 
 	/* Check for unsolicited interrupts. */
 	if (cgdev == NULL) {
-		ctcm_pr_warn("ctcm: Got unsolicited irq: c-%02x d-%02x\n",
-			     cstat, dstat);
+		CTCM_DBF_TEXT_(TRACE, CTC_DBF_ERROR,
+			"%s(%s) unsolicited irq: c-%02x d-%02x\n",
+			CTCM_FUNTAIL, dev_name(&cdev->dev), cstat, dstat);
+		dev_warn(&cdev->dev,
+			"The adapter received a non-specific IRQ\n");
 		return;
 	}
 
@@ -1207,31 +1217,34 @@ static void ctcm_irq_handler(struct ccw_device *cdev,
 	else if (priv->channel[WRITE]->cdev == cdev)
 		ch = priv->channel[WRITE];
 	else {
-		ctcm_pr_err("ctcm: Can't determine channel for interrupt, "
-			   "device %s\n", dev_name(&cdev->dev));
+		dev_err(&cdev->dev,
+			"%s: Internal error: Can't determine channel for "
+			"interrupt device %s\n",
+			__func__, dev_name(&cdev->dev));
+			/* Explain: inconsistent internal structures */
 		return;
 	}
 
 	dev = ch->netdev;
 	if (dev == NULL) {
-		ctcm_pr_crit("ctcm: %s dev=NULL bus_id=%s, ch=0x%p\n",
-				__func__, dev_name(&cdev->dev), ch);
+		dev_err(&cdev->dev,
+			"%s Internal error: net_device is NULL, ch = 0x%p\n",
+			__func__, ch);
+			/* Explain: inconsistent internal structures */
 		return;
 	}
 
-	CTCM_DBF_TEXT_(TRACE, CTC_DBF_DEBUG,
-		"%s(%s): int. for %s: cstat=%02x dstat=%02x",
-			CTCM_FUNTAIL, dev->name, ch->id, cstat, dstat);
-
 	/* Copy interruption response block. */
 	memcpy(ch->irb, irb, sizeof(struct irb));
 
+	/* Issue error message and return on subchannel error code */
 	if (irb->scsw.cmd.cstat) {
-	/* Check for good subchannel return code, otherwise error message */
 		fsm_event(ch->fsm, CTC_EVENT_SC_UNKNOWN, ch);
-		ctcm_pr_warn("%s: subchannel check for dev: %s - %02x %02x\n",
-			    dev->name, ch->id, irb->scsw.cmd.cstat,
-			    irb->scsw.cmd.dstat);
+		CTCM_DBF_TEXT_(TRACE, CTC_DBF_WARN,
+			"%s(%s): sub-ch check %s: cs=%02x ds=%02x",
+				CTCM_FUNTAIL, dev->name, ch->id, cstat, dstat);
+		dev_warn(&cdev->dev,
+				"A check occurred on the subchannel\n");
 		return;
 	}
 
@@ -1239,7 +1252,7 @@ static void ctcm_irq_handler(struct ccw_device *cdev,
 	if (irb->scsw.cmd.dstat & DEV_STAT_UNIT_CHECK) {
 		if ((irb->ecw[0] & ch->sense_rc) == 0)
 			/* print it only once */
-			CTCM_DBF_TEXT_(TRACE, CTC_DBF_INFO,
+			CTCM_DBF_TEXT_(TRACE, CTC_DBF_WARN,
 				"%s(%s): sense=%02x, ds=%02x",
 				CTCM_FUNTAIL, ch->id, irb->ecw[0], dstat);
 		ccw_unit_check(ch, irb->ecw[0]);
@@ -1574,6 +1587,11 @@ static int ctcm_new_device(struct ccwgroup_device *cgdev)
 
 	strlcpy(priv->fsm->name, dev->name, sizeof(priv->fsm->name));
 
+	dev_info(&dev->dev,
+		"setup OK : r/w = %s/%s, protocol : %d\n",
+			priv->channel[READ]->id,
+			priv->channel[WRITE]->id, priv->protocol);
+
 	CTCM_DBF_TEXT_(SETUP, CTC_DBF_INFO,
 		"setup(%s) OK : r/w = %s/%s, protocol : %d", dev->name,
 			priv->channel[READ]->id,
@@ -1687,7 +1705,7 @@ static void __exit ctcm_exit(void)
 {
 	unregister_cu3088_discipline(&ctcm_group_driver);
 	ctcm_unregister_dbf_views();
-	ctcm_pr_info("CTCM driver unloaded\n");
+	pr_info("CTCM driver unloaded\n");
 }
 
 /*
@@ -1695,7 +1713,7 @@ static void __exit ctcm_exit(void)
  */
 static void print_banner(void)
 {
-	printk(KERN_INFO "CTCM driver initialized\n");
+	pr_info("CTCM driver initialized\n");
 }
 
 /**
@@ -1717,8 +1735,8 @@ static int __init ctcm_init(void)
 	ret = register_cu3088_discipline(&ctcm_group_driver);
 	if (ret) {
 		ctcm_unregister_dbf_views();
-		ctcm_pr_crit("ctcm_init failed with register_cu3088_discipline "
-				"(rc = %d)\n", ret);
+		pr_err("%s / register_cu3088_discipline failed, ret = %d\n",
+			__func__, ret);
 		return ret;
 	}
 	print_banner();
diff --git a/drivers/s390/net/ctcm_main.h b/drivers/s390/net/ctcm_main.h
index d77cce3fe4d4..d925e732b7d8 100644
--- a/drivers/s390/net/ctcm_main.h
+++ b/drivers/s390/net/ctcm_main.h
@@ -41,12 +41,6 @@
 #define LOG_FLAG_NOMEM		8
 
 #define ctcm_pr_debug(fmt, arg...) printk(KERN_DEBUG fmt, ##arg)
-#define ctcm_pr_info(fmt, arg...) printk(KERN_INFO fmt, ##arg)
-#define ctcm_pr_notice(fmt, arg...) printk(KERN_NOTICE fmt, ##arg)
-#define ctcm_pr_warn(fmt, arg...) printk(KERN_WARNING fmt, ##arg)
-#define ctcm_pr_emerg(fmt, arg...) printk(KERN_EMERG fmt, ##arg)
-#define ctcm_pr_err(fmt, arg...) printk(KERN_ERR fmt, ##arg)
-#define ctcm_pr_crit(fmt, arg...) printk(KERN_CRIT fmt, ##arg)
 
 #define CTCM_PR_DEBUG(fmt, arg...) \
 	do { \
diff --git a/drivers/s390/net/ctcm_mpc.c b/drivers/s390/net/ctcm_mpc.c
index 19f5d5ed85e0..3db5f846bbf6 100644
--- a/drivers/s390/net/ctcm_mpc.c
+++ b/drivers/s390/net/ctcm_mpc.c
@@ -19,6 +19,9 @@
 #undef DEBUGDATA
 #undef DEBUGCCW
 
+#define KMSG_COMPONENT "ctcm"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
 #include <linux/module.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
@@ -386,7 +389,7 @@ int ctc_mpc_alloc_channel(int port_num, void (*callback)(int, int))
 		if (grp->allocchan_callback_retries < 4) {
 			if (grp->allochanfunc)
 				grp->allochanfunc(grp->port_num,
-					      grp->group_max_buflen);
+						  grp->group_max_buflen);
 		} else {
 			/* there are problems...bail out	    */
 			/* there may be a state mismatch so restart */
@@ -1232,8 +1235,9 @@ done:
 
 	dev_kfree_skb_any(pskb);
 	if (sendrc == NET_RX_DROP) {
-		printk(KERN_WARNING "%s %s() NETWORK BACKLOG EXCEEDED"
-		       " - PACKET DROPPED\n", dev->name, __func__);
+		dev_warn(&dev->dev,
+			"The network backlog for %s is exceeded, "
+			"package dropped\n", __func__);
 		fsm_event(grp->fsm, MPCG_EVENT_INOP, dev);
 	}
 
@@ -1670,10 +1674,11 @@ static int mpc_validate_xid(struct mpcg_info *mpcginfo)
 					CTCM_FUNTAIL, ch->id);
 		}
 	}
-
 done:
 	if (rc) {
-		ctcm_pr_info("ctcmpc	   :  %s() failed\n", __func__);
+		dev_warn(&dev->dev,
+			"The XID used in the MPC protocol is not valid, "
+			"rc = %d\n", rc);
 		priv->xid->xid2_flag2 = 0x40;
 		grp->saved_xid2->xid2_flag2 = 0x40;
 	}
diff --git a/drivers/s390/net/ctcm_sysfs.c b/drivers/s390/net/ctcm_sysfs.c
index bb2d13721d34..8452bb052d68 100644
--- a/drivers/s390/net/ctcm_sysfs.c
+++ b/drivers/s390/net/ctcm_sysfs.c
@@ -10,6 +10,9 @@
 #undef DEBUGDATA
 #undef DEBUGCCW
 
+#define KMSG_COMPONENT "ctcm"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
 #include <linux/sysfs.h>
 #include "ctcm_main.h"
 
diff --git a/drivers/s390/net/lcs.c b/drivers/s390/net/lcs.c
index 0825be87e5a0..afa8337734d1 100644
--- a/drivers/s390/net/lcs.c
+++ b/drivers/s390/net/lcs.c
@@ -26,6 +26,9 @@
  * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
+#define KMSG_COMPONENT		"lcs"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
 #include <linux/module.h>
 #include <linux/if.h>
 #include <linux/netdevice.h>
@@ -54,8 +57,6 @@
 #error Cannot compile lcs.c without some net devices switched on.
 #endif
 
-#define PRINTK_HEADER		" lcs: "
-
 /**
  * initialization string for output
  */
@@ -96,7 +97,7 @@ lcs_register_debug_facility(void)
 	lcs_dbf_setup = debug_register("lcs_setup", 2, 1, 8);
 	lcs_dbf_trace = debug_register("lcs_trace", 4, 1, 8);
 	if (lcs_dbf_setup == NULL || lcs_dbf_trace == NULL) {
-		PRINT_ERR("Not enough memory for debug facility.\n");
+		pr_err("Not enough memory for debug facility.\n");
 		lcs_unregister_debug_facility();
 		return -ENOMEM;
 	}
@@ -503,7 +504,9 @@ lcs_start_channel(struct lcs_channel *channel)
 	if (rc) {
 		LCS_DBF_TEXT_(4,trace,"essh%s",
 			      dev_name(&channel->ccwdev->dev));
-		PRINT_ERR("Error in starting channel, rc=%d!\n", rc);
+		dev_err(&channel->ccwdev->dev,
+			"Starting an LCS device resulted in an error,"
+			" rc=%d!\n", rc);
 	}
 	return rc;
 }
@@ -640,7 +643,9 @@ __lcs_resume_channel(struct lcs_channel *channel)
 	if (rc) {
 		LCS_DBF_TEXT_(4, trace, "ersc%s",
 			      dev_name(&channel->ccwdev->dev));
-		PRINT_ERR("Error in lcs_resume_channel: rc=%d\n",rc);
+		dev_warn(&channel->ccwdev->dev,
+			"Sending data from the LCS device to the LAN failed"
+			" with rc=%d\n",rc);
 	} else
 		channel->state = LCS_CH_STATE_RUNNING;
 	return rc;
@@ -1086,7 +1091,7 @@ lcs_check_multicast_support(struct lcs_card *card)
 	cmd->cmd.lcs_qipassist.num_ip_pairs = 1;
 	rc = lcs_send_lancmd(card, buffer, __lcs_check_multicast_cb);
 	if (rc != 0) {
-		PRINT_ERR("Query IPAssist failed. Assuming unsupported!\n");
+		pr_err("Query IPAssist failed. Assuming unsupported!\n");
 		return -EOPNOTSUPP;
 	}
 	if (card->ip_assists_supported & LCS_IPASS_MULTICAST_SUPPORT)
@@ -1119,8 +1124,8 @@ list_modified:
 			rc = lcs_send_setipm(card, ipm);
 			spin_lock_irqsave(&card->ipm_lock, flags);
 			if (rc) {
-				PRINT_INFO("Adding multicast address failed. "
-					   "Table possibly full!\n");
+				pr_info("Adding multicast address failed."
+					" Table possibly full!\n");
 				/* store ipm in failed list -> will be added
 				 * to ipm_list again, so a retry will be done
 				 * during the next call of this function */
@@ -1231,8 +1236,8 @@ lcs_set_mc_addresses(struct lcs_card *card, struct in_device *in4_dev)
 		ipm = (struct lcs_ipm_list *)
 			kzalloc(sizeof(struct lcs_ipm_list), GFP_ATOMIC);
 		if (ipm == NULL) {
-			PRINT_INFO("Not enough memory to add "
-				   "new multicast entry!\n");
+			pr_info("Not enough memory to add"
+				" new multicast entry!\n");
 			break;
 		}
 		memcpy(&ipm->ipm.mac_addr, buf, LCS_MAC_LENGTH);
@@ -1306,18 +1311,21 @@ lcs_check_irb_error(struct ccw_device *cdev, struct irb *irb)
 
 	switch (PTR_ERR(irb)) {
 	case -EIO:
-		PRINT_WARN("i/o-error on device %s\n", dev_name(&cdev->dev));
+		dev_warn(&cdev->dev,
+			"An I/O-error occurred on the LCS device\n");
 		LCS_DBF_TEXT(2, trace, "ckirberr");
 		LCS_DBF_TEXT_(2, trace, "  rc%d", -EIO);
 		break;
 	case -ETIMEDOUT:
-		PRINT_WARN("timeout on device %s\n", dev_name(&cdev->dev));
+		dev_warn(&cdev->dev,
+			"A command timed out on the LCS device\n");
 		LCS_DBF_TEXT(2, trace, "ckirberr");
 		LCS_DBF_TEXT_(2, trace, "  rc%d", -ETIMEDOUT);
 		break;
 	default:
-		PRINT_WARN("unknown error %ld on device %s\n", PTR_ERR(irb),
-			   dev_name(&cdev->dev));
+		dev_warn(&cdev->dev,
+			"An error occurred on the LCS device, rc=%ld\n",
+			PTR_ERR(irb));
 		LCS_DBF_TEXT(2, trace, "ckirberr");
 		LCS_DBF_TEXT(2, trace, "  rc???");
 	}
@@ -1403,8 +1411,10 @@ lcs_irq(struct ccw_device *cdev, unsigned long intparm, struct irb *irb)
 	/* Check for channel and device errors presented */
 	rc = lcs_get_problem(cdev, irb);
 	if (rc || (dstat & DEV_STAT_UNIT_EXCEP)) {
-		PRINT_WARN("check on device %s, dstat=0x%X, cstat=0x%X \n",
-			    dev_name(&cdev->dev), dstat, cstat);
+		dev_warn(&cdev->dev,
+			"The LCS device stopped because of an error,"
+			" dstat=0x%X, cstat=0x%X \n",
+			    dstat, cstat);
 		if (rc) {
 			channel->state = LCS_CH_STATE_ERROR;
 		}
@@ -1761,8 +1771,8 @@ lcs_get_control(struct lcs_card *card, struct lcs_cmd *cmd)
 			lcs_schedule_recovery(card);
 			break;
 		case LCS_CMD_STOPLAN:
-			PRINT_WARN("Stoplan for %s initiated by LGW.\n",
-					card->dev->name);
+			pr_warning("Stoplan for %s initiated by LGW.\n",
+				   card->dev->name);
 			if (card->dev)
 				netif_carrier_off(card->dev);
 			break;
@@ -1790,7 +1800,8 @@ lcs_get_skb(struct lcs_card *card, char *skb_data, unsigned int skb_len)
 
 	skb = dev_alloc_skb(skb_len);
 	if (skb == NULL) {
-		PRINT_ERR("LCS: alloc_skb failed for device=%s\n",
+		dev_err(&card->dev->dev,
+			" Allocating a socket buffer to interface %s failed\n",
 			  card->dev->name);
 		card->stats.rx_dropped++;
 		return;
@@ -1886,7 +1897,8 @@ lcs_stop_device(struct net_device *dev)
 		(card->write.state != LCS_CH_STATE_RUNNING));
 	rc = lcs_stopcard(card);
 	if (rc)
-		PRINT_ERR("Try it again!\n ");
+		dev_err(&card->dev->dev,
+			" Shutting down the LCS device failed\n ");
 	return rc;
 }
 
@@ -1905,7 +1917,7 @@ lcs_open_device(struct net_device *dev)
 	/* initialize statistics */
 	rc = lcs_detect(card);
 	if (rc) {
-		PRINT_ERR("LCS:Error in opening device!\n");
+		pr_err("Error in opening device!\n");
 
 	} else {
 		dev->flags |= IFF_UP;
@@ -2113,8 +2125,9 @@ lcs_new_device(struct ccwgroup_device *ccwgdev)
 	rc = lcs_detect(card);
 	if (rc) {
 		LCS_DBF_TEXT(2, setup, "dtctfail");
-		PRINT_WARN("Detection of LCS card failed with return code "
-			   "%d (0x%x)\n", rc, rc);
+		dev_warn(&card->dev->dev,
+			"Detecting a network adapter for LCS devices"
+			" failed with rc=%d (0x%x)\n", rc, rc);
 		lcs_stopcard(card);
 		goto out;
 	}
@@ -2144,7 +2157,7 @@ lcs_new_device(struct ccwgroup_device *ccwgdev)
 #endif
 	default:
 		LCS_DBF_TEXT(3, setup, "errinit");
-		PRINT_ERR("LCS: Initialization failed\n");
+		pr_err(" Initialization failed\n");
 		goto out;
 	}
 	if (!dev)
@@ -2176,13 +2189,13 @@ netdev_out:
 		goto out;
 
 	/* Print out supported assists: IPv6 */
-	PRINT_INFO("LCS device %s %s IPv6 support\n", card->dev->name,
-		   (card->ip_assists_supported & LCS_IPASS_IPV6_SUPPORT) ?
-		   "with" : "without");
+	pr_info("LCS device %s %s IPv6 support\n", card->dev->name,
+		(card->ip_assists_supported & LCS_IPASS_IPV6_SUPPORT) ?
+		"with" : "without");
 	/* Print out supported assist: Multicast */
-	PRINT_INFO("LCS device %s %s Multicast support\n", card->dev->name,
-		   (card->ip_assists_supported & LCS_IPASS_MULTICAST_SUPPORT) ?
-		   "with" : "without");
+	pr_info("LCS device %s %s Multicast support\n", card->dev->name,
+		(card->ip_assists_supported & LCS_IPASS_MULTICAST_SUPPORT) ?
+		"with" : "without");
 	return 0;
 out:
 
@@ -2248,15 +2261,16 @@ lcs_recovery(void *ptr)
 		return 0;
 	LCS_DBF_TEXT(4, trace, "recover2");
 	gdev = card->gdev;
-	PRINT_WARN("Recovery of device %s started...\n", dev_name(&gdev->dev));
+	dev_warn(&gdev->dev,
+		"A recovery process has been started for the LCS device\n");
 	rc = __lcs_shutdown_device(gdev, 1);
 	rc = lcs_new_device(gdev);
 	if (!rc)
-		PRINT_INFO("Device %s successfully recovered!\n",
-				card->dev->name);
+		pr_info("Device %s successfully recovered!\n",
+			card->dev->name);
 	else
-		PRINT_INFO("Device %s could not be recovered!\n",
-				card->dev->name);
+		pr_info("Device %s could not be recovered!\n",
+			card->dev->name);
 	lcs_clear_thread_running_bit(card, LCS_RECOVERY_THREAD);
 	return 0;
 }
@@ -2308,17 +2322,17 @@ __init lcs_init_module(void)
 {
 	int rc;
 
-	PRINT_INFO("Loading %s\n",version);
+	pr_info("Loading %s\n", version);
 	rc = lcs_register_debug_facility();
 	LCS_DBF_TEXT(0, setup, "lcsinit");
 	if (rc) {
-		PRINT_ERR("Initialization failed\n");
+		pr_err("Initialization failed\n");
 		return rc;
 	}
 
 	rc = register_cu3088_discipline(&lcs_group_driver);
 	if (rc) {
-		PRINT_ERR("Initialization failed\n");
+		pr_err("Initialization failed\n");
 		return rc;
 	}
 	return 0;
@@ -2331,7 +2345,7 @@ __init lcs_init_module(void)
 static void
 __exit lcs_cleanup_module(void)
 {
-	PRINT_INFO("Terminating lcs module.\n");
+	pr_info("Terminating lcs module.\n");
 	LCS_DBF_TEXT(0, trace, "cleanup");
 	unregister_cu3088_discipline(&lcs_group_driver);
 	lcs_unregister_debug_facility();
diff --git a/drivers/s390/net/netiucv.c b/drivers/s390/net/netiucv.c
index 0fea51e34b57..930e2fc2a011 100644
--- a/drivers/s390/net/netiucv.c
+++ b/drivers/s390/net/netiucv.c
@@ -31,6 +31,9 @@
  *
  */
 
+#define KMSG_COMPONENT "netiucv"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
 #undef DEBUG
 
 #include <linux/module.h>
@@ -846,7 +849,8 @@ static void conn_action_connsever(fsm_instance *fi, int event, void *arg)
 
 	fsm_deltimer(&conn->timer);
 	iucv_path_sever(conn->path, NULL);
-	PRINT_INFO("%s: Remote dropped connection\n", netdev->name);
+	dev_info(privptr->dev, "The peer interface of the IUCV device"
+		" has closed the connection\n");
 	IUCV_DBF_TEXT(data, 2,
 		      "conn_action_connsever: Remote dropped connection\n");
 	fsm_newstate(fi, CONN_STATE_STARTWAIT);
@@ -856,13 +860,15 @@ static void conn_action_connsever(fsm_instance *fi, int event, void *arg)
 static void conn_action_start(fsm_instance *fi, int event, void *arg)
 {
 	struct iucv_connection *conn = arg;
+	struct net_device *netdev = conn->netdev;
+	struct netiucv_priv *privptr = netdev_priv(netdev);
 	int rc;
 
 	IUCV_DBF_TEXT(trace, 3, __func__);
 
 	fsm_newstate(fi, CONN_STATE_STARTWAIT);
 	IUCV_DBF_TEXT_(setup, 2, "%s('%s'): connecting ...\n",
-		    conn->netdev->name, conn->userid);
+		netdev->name, conn->userid);
 
 	/*
 	 * We must set the state before calling iucv_connect because the
@@ -876,41 +882,45 @@ static void conn_action_start(fsm_instance *fi, int event, void *arg)
 			       NULL, iucvMagic, conn);
 	switch (rc) {
 	case 0:
-		conn->netdev->tx_queue_len = conn->path->msglim;
+		netdev->tx_queue_len = conn->path->msglim;
 		fsm_addtimer(&conn->timer, NETIUCV_TIMEOUT_5SEC,
 			     CONN_EVENT_TIMER, conn);
 		return;
 	case 11:
-		PRINT_INFO("%s: User %s is currently not available.\n",
-			   conn->netdev->name,
-			   netiucv_printname(conn->userid));
+		dev_warn(privptr->dev,
+			"The IUCV device failed to connect to z/VM guest %s\n",
+			netiucv_printname(conn->userid));
 		fsm_newstate(fi, CONN_STATE_STARTWAIT);
 		break;
 	case 12:
-		PRINT_INFO("%s: User %s is currently not ready.\n",
-			   conn->netdev->name,
-			   netiucv_printname(conn->userid));
+		dev_warn(privptr->dev,
+			"The IUCV device failed to connect to the peer on z/VM"
+			" guest %s\n", netiucv_printname(conn->userid));
 		fsm_newstate(fi, CONN_STATE_STARTWAIT);
 		break;
 	case 13:
-		PRINT_WARN("%s: Too many IUCV connections.\n",
-			   conn->netdev->name);
+		dev_err(privptr->dev,
+			"Connecting the IUCV device would exceed the maximum"
+			" number of IUCV connections\n");
 		fsm_newstate(fi, CONN_STATE_CONNERR);
 		break;
 	case 14:
-		PRINT_WARN("%s: User %s has too many IUCV connections.\n",
-			   conn->netdev->name,
-			   netiucv_printname(conn->userid));
+		dev_err(privptr->dev,
+			"z/VM guest %s has too many IUCV connections"
+			" to connect with the IUCV device\n",
+			netiucv_printname(conn->userid));
 		fsm_newstate(fi, CONN_STATE_CONNERR);
 		break;
 	case 15:
-		PRINT_WARN("%s: No IUCV authorization in CP directory.\n",
-			   conn->netdev->name);
+		dev_err(privptr->dev,
+			"The IUCV device cannot connect to a z/VM guest with no"
+			" IUCV authorization\n");
 		fsm_newstate(fi, CONN_STATE_CONNERR);
 		break;
 	default:
-		PRINT_WARN("%s: iucv_connect returned error %d\n",
-			   conn->netdev->name, rc);
+		dev_err(privptr->dev,
+			"Connecting the IUCV device failed with error %d\n",
+			rc);
 		fsm_newstate(fi, CONN_STATE_CONNERR);
 		break;
 	}
@@ -1059,8 +1069,9 @@ dev_action_connup(fsm_instance *fi, int event, void *arg)
 	switch (fsm_getstate(fi)) {
 		case DEV_STATE_STARTWAIT:
 			fsm_newstate(fi, DEV_STATE_RUNNING);
-			PRINT_INFO("%s: connected with remote side %s\n",
-			       dev->name, privptr->conn->userid);
+			dev_info(privptr->dev,
+				"The IUCV device has been connected"
+				" successfully to %s\n", privptr->conn->userid);
 			IUCV_DBF_TEXT(setup, 3,
 				"connection is up and running\n");
 			break;
@@ -1982,6 +1993,8 @@ static ssize_t conn_write(struct device_driver *drv,
 	if (rc)
 		goto out_unreg;
 
+	dev_info(priv->dev, "The IUCV interface to %s has been"
+		" established successfully\n", netiucv_printname(username));
 
 	return count;
 
@@ -2027,10 +2040,9 @@ static ssize_t remove_write (struct device_driver *drv,
 			continue;
 		read_unlock_bh(&iucv_connection_rwlock);
                 if (ndev->flags & (IFF_UP | IFF_RUNNING)) {
-			PRINT_WARN("netiucv: net device %s active with peer "
-				   "%s\n", ndev->name, priv->conn->userid);
-                        PRINT_WARN("netiucv: %s cannot be removed\n",
-				   ndev->name);
+			dev_warn(dev, "The IUCV device is connected"
+				" to %s and cannot be removed\n",
+				priv->conn->userid);
 			IUCV_DBF_TEXT(data, 2, "remove_write: still active\n");
 			return -EPERM;
                 }
@@ -2062,7 +2074,7 @@ static struct attribute_group *netiucv_drv_attr_groups[] = {
 
 static void netiucv_banner(void)
 {
-	PRINT_INFO("NETIUCV driver initialized\n");
+	pr_info("driver initialized\n");
 }
 
 static void __exit netiucv_exit(void)
@@ -2088,7 +2100,7 @@ static void __exit netiucv_exit(void)
 	iucv_unregister(&netiucv_handler, 1);
 	iucv_unregister_dbf_views();
 
-	PRINT_INFO("NETIUCV driver unloaded\n");
+	pr_info("driver unloaded\n");
 	return;
 }
 
diff --git a/drivers/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h
index af6d60458513..d5ccce1643e4 100644
--- a/drivers/s390/net/qeth_core.h
+++ b/drivers/s390/net/qeth_core.h
@@ -31,11 +31,10 @@
 #include <asm/qdio.h>
 #include <asm/ccwdev.h>
 #include <asm/ccwgroup.h>
+#include <asm/sysinfo.h>
 
 #include "qeth_core_mpc.h"
 
-#define KMSG_COMPONENT "qeth"
-
 /**
  * Debug Facility stuff
  */
@@ -74,11 +73,6 @@ struct qeth_dbf_info {
 #define QETH_DBF_TEXT_(name, level, text...) \
 	qeth_dbf_longtext(QETH_DBF_##name, level, text)
 
-/**
- * some more debug stuff
- */
-#define PRINTK_HEADER	"qeth: "
-
 #define SENSE_COMMAND_REJECT_BYTE 0
 #define SENSE_COMMAND_REJECT_FLAG 0x80
 #define SENSE_RESETTING_EVENT_BYTE 1
@@ -733,6 +727,7 @@ struct qeth_card {
 	struct qeth_osn_info osn_info;
 	struct qeth_discipline discipline;
 	atomic_t force_alloc_skb;
+	struct service_level qeth_service_level;
 };
 
 struct qeth_card_list_struct {
diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index 52d26592c72c..bbd6788e8270 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -8,6 +8,9 @@
  *		 Frank Blaschka <frank.blaschka@de.ibm.com>
  */
 
+#define KMSG_COMPONENT "qeth"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
 #include <linux/module.h>
 #include <linux/moduleparam.h>
 #include <linux/string.h>
@@ -319,7 +322,10 @@ static int qeth_issue_next_read(struct qeth_card *card)
 		return -EIO;
 	iob = qeth_get_buffer(&card->read);
 	if (!iob) {
-		PRINT_WARN("issue_next_read failed: no iob available!\n");
+		dev_warn(&card->gdev->dev, "The qeth device driver "
+			"failed to recover an error on the device\n");
+		QETH_DBF_MESSAGE(2, "%s issue_next_read failed: no iob "
+			"available\n", dev_name(&card->gdev->dev));
 		return -ENOMEM;
 	}
 	qeth_setup_ccw(&card->read, iob->data, QETH_BUFSIZE);
@@ -327,7 +333,8 @@ static int qeth_issue_next_read(struct qeth_card *card)
 	rc = ccw_device_start(card->read.ccwdev, &card->read.ccw,
 			      (addr_t) iob, 0, 0);
 	if (rc) {
-		PRINT_ERR("Error in starting next read ccw! rc=%i\n", rc);
+		QETH_DBF_MESSAGE(2, "%s error in starting next read ccw! "
+			"rc=%i\n", dev_name(&card->gdev->dev), rc);
 		atomic_set(&card->read.irq_pending, 0);
 		qeth_schedule_recovery(card);
 		wake_up(&card->wait_q);
@@ -393,10 +400,9 @@ static struct qeth_ipa_cmd *qeth_check_ipa_data(struct qeth_card *card,
 		} else {
 			switch (cmd->hdr.command) {
 			case IPA_CMD_STOPLAN:
-				PRINT_WARN("Link failure on %s (CHPID 0x%X) - "
-					   "there is a network problem or "
-					   "someone pulled the cable or "
-					   "disabled the port.\n",
+				dev_warn(&card->gdev->dev,
+					   "The link for interface %s on CHPID"
+					   " 0x%X failed\n",
 					   QETH_CARD_IFNAME(card),
 					   card->info.chpid);
 				card->lan_online = 0;
@@ -404,9 +410,9 @@ static struct qeth_ipa_cmd *qeth_check_ipa_data(struct qeth_card *card,
 					netif_carrier_off(card->dev);
 				return NULL;
 			case IPA_CMD_STARTLAN:
-				PRINT_INFO("Link reestablished on %s "
-					   "(CHPID 0x%X). Scheduling "
-					   "IP address reset.\n",
+				dev_info(&card->gdev->dev,
+					   "The link for %s on CHPID 0x%X has"
+					   " been restored\n",
 					   QETH_CARD_IFNAME(card),
 					   card->info.chpid);
 				netif_carrier_on(card->dev);
@@ -458,7 +464,7 @@ static int qeth_check_idx_response(unsigned char *buffer)
 
 	QETH_DBF_HEX(CTRL, 2, buffer, QETH_DBF_CTRL_LEN);
 	if ((buffer[2] & 0xc0) == 0xc0) {
-		PRINT_WARN("received an IDX TERMINATE "
+		QETH_DBF_MESSAGE(2, "received an IDX TERMINATE "
 			   "with cause code 0x%02x%s\n",
 			   buffer[4],
 			   ((buffer[4] == 0x22) ?
@@ -744,8 +750,10 @@ static int qeth_get_problem(struct ccw_device *cdev, struct irb *irb)
 		     SCHN_STAT_CHN_DATA_CHK | SCHN_STAT_CHAIN_CHECK |
 		     SCHN_STAT_PROT_CHECK | SCHN_STAT_PROG_CHECK)) {
 		QETH_DBF_TEXT(TRACE, 2, "CGENCHK");
-		PRINT_WARN("check on device %s, dstat=x%x, cstat=x%x ",
-			   dev_name(&cdev->dev), dstat, cstat);
+		dev_warn(&cdev->dev, "The qeth device driver "
+			"failed to recover an error on the device\n");
+		QETH_DBF_MESSAGE(2, "%s check on device dstat=x%x, cstat=x%x ",
+			dev_name(&cdev->dev), dstat, cstat);
 		print_hex_dump(KERN_WARNING, "qeth: irb ", DUMP_PREFIX_OFFSET,
 				16, 1, irb, 64, 1);
 		return 1;
@@ -784,12 +792,14 @@ static long __qeth_check_irb_error(struct ccw_device *cdev,
 
 	switch (PTR_ERR(irb)) {
 	case -EIO:
-		PRINT_WARN("i/o-error on device %s\n", dev_name(&cdev->dev));
+		QETH_DBF_MESSAGE(2, "%s i/o-error on device\n",
+			dev_name(&cdev->dev));
 		QETH_DBF_TEXT(TRACE, 2, "ckirberr");
 		QETH_DBF_TEXT_(TRACE, 2, "  rc%d", -EIO);
 		break;
 	case -ETIMEDOUT:
-		PRINT_WARN("timeout on device %s\n", dev_name(&cdev->dev));
+		dev_warn(&cdev->dev, "A hardware operation timed out"
+			" on the device\n");
 		QETH_DBF_TEXT(TRACE, 2, "ckirberr");
 		QETH_DBF_TEXT_(TRACE, 2, "  rc%d", -ETIMEDOUT);
 		if (intparm == QETH_RCD_PARM) {
@@ -802,8 +812,8 @@ static long __qeth_check_irb_error(struct ccw_device *cdev,
 		}
 		break;
 	default:
-		PRINT_WARN("unknown error %ld on device %s\n", PTR_ERR(irb),
-			   dev_name(&cdev->dev));
+		QETH_DBF_MESSAGE(2, "%s unknown error %ld on device\n",
+			dev_name(&cdev->dev), PTR_ERR(irb));
 		QETH_DBF_TEXT(TRACE, 2, "ckirberr");
 		QETH_DBF_TEXT(TRACE, 2, "  rc???");
 	}
@@ -869,10 +879,12 @@ static void qeth_irq(struct ccw_device *cdev, unsigned long intparm,
 	    (dstat & DEV_STAT_UNIT_CHECK) ||
 	    (cstat)) {
 		if (irb->esw.esw0.erw.cons) {
-			/* TODO: we should make this s390dbf */
-			PRINT_WARN("sense data available on channel %s.\n",
-				   CHANNEL_ID(channel));
-			PRINT_WARN(" cstat 0x%X\n dstat 0x%X\n", cstat, dstat);
+			dev_warn(&channel->ccwdev->dev,
+				"The qeth device driver failed to recover "
+				"an error on the device\n");
+			QETH_DBF_MESSAGE(2, "%s sense data available. cstat "
+				"0x%X dstat 0x%X\n",
+				dev_name(&channel->ccwdev->dev), cstat, dstat);
 			print_hex_dump(KERN_WARNING, "qeth: irb ",
 				DUMP_PREFIX_OFFSET, 16, 1, irb, 32, 1);
 			print_hex_dump(KERN_WARNING, "qeth: sense data ",
@@ -1138,6 +1150,14 @@ static int qeth_setup_card(struct qeth_card *card)
 	return 0;
 }
 
+static void qeth_core_sl_print(struct seq_file *m, struct service_level *slr)
+{
+	struct qeth_card *card = container_of(slr, struct qeth_card,
+					qeth_service_level);
+	seq_printf(m, "qeth: %s firmware level %s\n", CARD_BUS_ID(card),
+			card->info.mcl_level);
+}
+
 static struct qeth_card *qeth_alloc_card(void)
 {
 	struct qeth_card *card;
@@ -1157,6 +1177,8 @@ static struct qeth_card *qeth_alloc_card(void)
 		return NULL;
 	}
 	card->options.layer2 = -1;
+	card->qeth_service_level.seq_print = qeth_core_sl_print;
+	register_service_level(&card->qeth_service_level);
 	return card;
 }
 
@@ -1175,8 +1197,8 @@ static int qeth_determine_card_type(struct qeth_card *card)
 			card->qdio.no_out_queues = known_devices[i][8];
 			card->info.is_multicast_different = known_devices[i][9];
 			if (qeth_is_1920_device(card)) {
-				PRINT_INFO("Priority Queueing not able "
-					   "due to hardware limitations!\n");
+				dev_info(&card->gdev->dev,
+					"Priority Queueing not supported\n");
 				card->qdio.no_out_queues = 1;
 				card->qdio.default_out_queue = 0;
 			}
@@ -1185,7 +1207,8 @@ static int qeth_determine_card_type(struct qeth_card *card)
 		i++;
 	}
 	card->info.type = QETH_CARD_TYPE_UNKNOWN;
-	PRINT_ERR("unknown card type on device %s\n", CARD_BUS_ID(card));
+	dev_err(&card->gdev->dev, "The adapter hardware is of an "
+		"unknown type\n");
 	return -ENOENT;
 }
 
@@ -1368,8 +1391,8 @@ static int qeth_get_unitaddr(struct qeth_card *card)
 	QETH_DBF_TEXT(SETUP, 2, "getunit");
 	rc = qeth_read_conf_data(card, (void **) &prcd, &length);
 	if (rc) {
-		PRINT_ERR("qeth_read_conf_data for device %s returned %i\n",
-			CARD_DDEV_ID(card), rc);
+		QETH_DBF_MESSAGE(2, "%s qeth_read_conf_data returned %i\n",
+			dev_name(&card->gdev->dev), rc);
 		return rc;
 	}
 	card->info.chpid = prcd[30];
@@ -1519,7 +1542,10 @@ static int qeth_idx_activate_channel(struct qeth_channel *channel,
 	if (rc == -ERESTARTSYS)
 		return rc;
 	if (channel->state != CH_STATE_ACTIVATING) {
-		PRINT_WARN("IDX activate timed out!\n");
+		dev_warn(&channel->ccwdev->dev, "The qeth device driver"
+			" failed to recover an error on the device\n");
+		QETH_DBF_MESSAGE(2, "%s IDX activate timed out\n",
+			dev_name(&channel->ccwdev->dev));
 		QETH_DBF_TEXT_(SETUP, 2, "2err%d", -ETIME);
 		qeth_clear_cmd_buffers(channel);
 		return -ETIME;
@@ -1552,20 +1578,21 @@ static void qeth_idx_write_cb(struct qeth_channel *channel,
 
 	if (!(QETH_IS_IDX_ACT_POS_REPLY(iob->data))) {
 		if (QETH_IDX_ACT_CAUSE_CODE(iob->data) == 0x19)
-			PRINT_ERR("IDX_ACTIVATE on write channel device %s: "
-				"adapter exclusively used by another host\n",
-			CARD_WDEV_ID(card));
+			dev_err(&card->write.ccwdev->dev,
+				"The adapter is used exclusively by another "
+				"host\n");
 		else
-			PRINT_ERR("IDX_ACTIVATE on write channel device %s: "
-				"negative reply\n", CARD_WDEV_ID(card));
+			QETH_DBF_MESSAGE(2, "%s IDX_ACTIVATE on write channel:"
+				" negative reply\n",
+				dev_name(&card->write.ccwdev->dev));
 		goto out;
 	}
 	memcpy(&temp, QETH_IDX_ACT_FUNC_LEVEL(iob->data), 2);
 	if ((temp & ~0x0100) != qeth_peer_func_level(card->info.func_level)) {
-		PRINT_WARN("IDX_ACTIVATE on write channel device %s: "
-			   "function level mismatch "
-			   "(sent: 0x%x, received: 0x%x)\n",
-			   CARD_WDEV_ID(card), card->info.func_level, temp);
+		QETH_DBF_MESSAGE(2, "%s IDX_ACTIVATE on write channel: "
+			"function level mismatch (sent: 0x%x, received: "
+			"0x%x)\n", dev_name(&card->write.ccwdev->dev),
+			card->info.func_level, temp);
 		goto out;
 	}
 	channel->state = CH_STATE_UP;
@@ -1591,12 +1618,13 @@ static void qeth_idx_read_cb(struct qeth_channel *channel,
 
 	if (!(QETH_IS_IDX_ACT_POS_REPLY(iob->data))) {
 		if (QETH_IDX_ACT_CAUSE_CODE(iob->data) == 0x19)
-			PRINT_ERR("IDX_ACTIVATE on read channel device %s: "
-				"adapter exclusively used by another host\n",
-				CARD_RDEV_ID(card));
+			dev_err(&card->write.ccwdev->dev,
+				"The adapter is used exclusively by another "
+				"host\n");
 		else
-			PRINT_ERR("IDX_ACTIVATE on read channel device %s: "
-				"negative reply\n", CARD_RDEV_ID(card));
+			QETH_DBF_MESSAGE(2, "%s IDX_ACTIVATE on read channel:"
+				" negative reply\n",
+				dev_name(&card->read.ccwdev->dev));
 		goto out;
 	}
 
@@ -1610,9 +1638,10 @@ static void qeth_idx_read_cb(struct qeth_channel *channel,
 
 	memcpy(&temp, QETH_IDX_ACT_FUNC_LEVEL(iob->data), 2);
 	if (temp != qeth_peer_func_level(card->info.func_level)) {
-		PRINT_WARN("IDX_ACTIVATE on read channel device %s: function "
-			   "level mismatch (sent: 0x%x, received: 0x%x)\n",
-			   CARD_RDEV_ID(card), card->info.func_level, temp);
+		QETH_DBF_MESSAGE(2, "%s IDX_ACTIVATE on read channel: function "
+			"level mismatch (sent: 0x%x, received: 0x%x)\n",
+			dev_name(&card->read.ccwdev->dev),
+			card->info.func_level, temp);
 		goto out;
 	}
 	memcpy(&card->token.issuer_rm_r,
@@ -1686,8 +1715,9 @@ int qeth_send_control_data(struct qeth_card *card, int len,
 			      (addr_t) iob, 0, 0);
 	spin_unlock_irqrestore(get_ccwdev_lock(card->write.ccwdev), flags);
 	if (rc) {
-		PRINT_WARN("qeth_send_control_data: "
-			   "ccw_device_start rc = %i\n", rc);
+		QETH_DBF_MESSAGE(2, "%s qeth_send_control_data: "
+			"ccw_device_start rc = %i\n",
+			dev_name(&card->write.ccwdev->dev), rc);
 		QETH_DBF_TEXT_(TRACE, 2, " err%d", rc);
 		spin_lock_irqsave(&card->lock, flags);
 		list_del_init(&reply->list);
@@ -2170,11 +2200,8 @@ static void qeth_print_status_with_portname(struct qeth_card *card)
 		dbf_text[i] =
 			(char) _ebcasc[(__u8) dbf_text[i]];
 	dbf_text[8] = 0;
-	PRINT_INFO("Device %s/%s/%s is a%s card%s%s%s\n"
+	dev_info(&card->gdev->dev, "Device is a%s card%s%s%s\n"
 	       "with link type %s (portname: %s)\n",
-	       CARD_RDEV_ID(card),
-	       CARD_WDEV_ID(card),
-	       CARD_DDEV_ID(card),
 	       qeth_get_cardname(card),
 	       (card->info.mcl_level[0]) ? " (level: " : "",
 	       (card->info.mcl_level[0]) ? card->info.mcl_level : "",
@@ -2187,23 +2214,17 @@ static void qeth_print_status_with_portname(struct qeth_card *card)
 static void qeth_print_status_no_portname(struct qeth_card *card)
 {
 	if (card->info.portname[0])
-		PRINT_INFO("Device %s/%s/%s is a%s "
+		dev_info(&card->gdev->dev, "Device is a%s "
 		       "card%s%s%s\nwith link type %s "
 		       "(no portname needed by interface).\n",
-		       CARD_RDEV_ID(card),
-		       CARD_WDEV_ID(card),
-		       CARD_DDEV_ID(card),
 		       qeth_get_cardname(card),
 		       (card->info.mcl_level[0]) ? " (level: " : "",
 		       (card->info.mcl_level[0]) ? card->info.mcl_level : "",
 		       (card->info.mcl_level[0]) ? ")" : "",
 		       qeth_get_cardname_short(card));
 	else
-		PRINT_INFO("Device %s/%s/%s is a%s "
+		dev_info(&card->gdev->dev, "Device is a%s "
 		       "card%s%s%s\nwith link type %s.\n",
-		       CARD_RDEV_ID(card),
-		       CARD_WDEV_ID(card),
-		       CARD_DDEV_ID(card),
 		       qeth_get_cardname(card),
 		       (card->info.mcl_level[0]) ? " (level: " : "",
 		       (card->info.mcl_level[0]) ? card->info.mcl_level : "",
@@ -2630,9 +2651,8 @@ void qeth_queue_input_buffer(struct qeth_card *card, int index)
 				qeth_get_micros() -
 				card->perf_stats.inbound_do_qdio_start_time;
 		if (rc) {
-			PRINT_WARN("qeth_queue_input_buffer's do_QDIO "
-				   "return %i (device %s).\n",
-				   rc, CARD_DDEV_ID(card));
+			dev_warn(&card->gdev->dev,
+				"QDIO reported an error, rc=%i\n", rc);
 			QETH_DBF_TEXT(TRACE, 2, "qinberr");
 			QETH_DBF_TEXT_(TRACE, 2, "%s", CARD_BUS_ID(card));
 		}
@@ -3730,6 +3750,7 @@ static void qeth_core_free_card(struct qeth_card *card)
 		free_netdev(card->dev);
 	kfree(card->ip_tbd_list);
 	qeth_free_qdio_buffers(card);
+	unregister_service_level(&card->qeth_service_level);
 	kfree(card);
 }
 
@@ -3757,7 +3778,7 @@ static int qeth_core_driver_group(const char *buf, struct device *root_dev,
 
 int qeth_core_hardsetup_card(struct qeth_card *card)
 {
-	struct qdio_ssqd_desc *qdio_ssqd;
+	struct qdio_ssqd_desc *ssqd;
 	int retries = 3;
 	int mpno = 0;
 	int rc;
@@ -3766,7 +3787,8 @@ int qeth_core_hardsetup_card(struct qeth_card *card)
 	atomic_set(&card->force_alloc_skb, 0);
 retry:
 	if (retries < 3) {
-		PRINT_WARN("Retrying to do IDX activates.\n");
+		QETH_DBF_MESSAGE(2, "%s Retrying to do IDX activates.\n",
+			dev_name(&card->gdev->dev));
 		ccw_device_set_offline(CARD_DDEV(card));
 		ccw_device_set_offline(CARD_WDEV(card));
 		ccw_device_set_offline(CARD_RDEV(card));
@@ -3792,9 +3814,16 @@ retry:
 		return rc;
 	}
 
-	qdio_ssqd = qdio_get_ssqd_desc(CARD_DDEV(card));
-	if (qdio_ssqd)
-		mpno = qdio_ssqd->pcnt;
+	ssqd = kmalloc(sizeof(struct qdio_ssqd_desc), GFP_KERNEL);
+	if (!ssqd) {
+		rc = -ENOMEM;
+		goto out;
+	}
+	rc = qdio_get_ssqd_desc(CARD_DDEV(card), ssqd);
+	if (rc == 0)
+		mpno = ssqd->pcnt;
+	kfree(ssqd);
+
 	if (mpno)
 		mpno = min(mpno - 1, QETH_MAX_PORTNO);
 	if (card->info.portno > mpno) {
@@ -3834,7 +3863,10 @@ retry:
 	}
 	return 0;
 out:
-	PRINT_ERR("Initialization in hardsetup failed! rc=%d\n", rc);
+	dev_warn(&card->gdev->dev, "The qeth device driver failed to recover "
+		"an error on the device\n");
+	QETH_DBF_MESSAGE(2, "%s Initialization in hardsetup failed! rc=%d\n",
+		dev_name(&card->gdev->dev), rc);
 	return rc;
 }
 EXPORT_SYMBOL_GPL(qeth_core_hardsetup_card);
@@ -4054,8 +4086,8 @@ int qeth_core_load_discipline(struct qeth_card *card,
 		break;
 	}
 	if (!card->discipline.ccwgdriver) {
-		PRINT_ERR("Support for discipline %d not present\n",
-				discipline);
+		dev_err(&card->gdev->dev, "There is no kernel module to "
+			"support discipline %d\n", discipline);
 		rc = -EINVAL;
 	}
 	return rc;
@@ -4448,7 +4480,7 @@ static int __init qeth_core_init(void)
 {
 	int rc;
 
-	PRINT_INFO("loading core functions\n");
+	pr_info("loading core functions\n");
 	INIT_LIST_HEAD(&qeth_core_card_list.list);
 	rwlock_init(&qeth_core_card_list.rwlock);
 
@@ -4488,9 +4520,10 @@ driver_err:
 ccwgroup_err:
 	ccw_driver_unregister(&qeth_ccw_driver);
 ccw_err:
+	QETH_DBF_MESSAGE(2, "Initialization failed with code %d\n", rc);
 	qeth_unregister_dbf_views();
 out_err:
-	PRINT_ERR("Initialization failed with code %d\n", rc);
+	pr_err("Initializing the qeth device driver failed\n");
 	return rc;
 }
 
@@ -4503,7 +4536,7 @@ static void __exit qeth_core_exit(void)
 	ccw_driver_unregister(&qeth_ccw_driver);
 	kmem_cache_destroy(qeth_core_header_cache);
 	qeth_unregister_dbf_views();
-	PRINT_INFO("core functions removed\n");
+	pr_info("core functions removed\n");
 }
 
 module_init(qeth_core_init);
diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c
index 1b1e80336d2c..af15bc648ba1 100644
--- a/drivers/s390/net/qeth_l2_main.c
+++ b/drivers/s390/net/qeth_l2_main.c
@@ -8,6 +8,9 @@
  *		 Frank Blaschka <frank.blaschka@de.ibm.com>
  */
 
+#define KMSG_COMPONENT "qeth"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
 #include <linux/module.h>
 #include <linux/moduleparam.h>
 #include <linux/string.h>
@@ -503,12 +506,13 @@ static int qeth_l2_send_setmac_cb(struct qeth_card *card,
 		card->info.mac_bits |= QETH_LAYER2_MAC_REGISTERED;
 		memcpy(card->dev->dev_addr, cmd->data.setdelmac.mac,
 		       OSA_ADDR_LEN);
-		PRINT_INFO("MAC address %2.2x:%2.2x:%2.2x:%2.2x:%2.2x:%2.2x "
-			   "successfully registered on device %s\n",
-			   card->dev->dev_addr[0], card->dev->dev_addr[1],
-			   card->dev->dev_addr[2], card->dev->dev_addr[3],
-			   card->dev->dev_addr[4], card->dev->dev_addr[5],
-			   card->dev->name);
+		dev_info(&card->gdev->dev,
+			"MAC address %2.2x:%2.2x:%2.2x:%2.2x:%2.2x:%2.2x "
+			"successfully registered on device %s\n",
+			card->dev->dev_addr[0], card->dev->dev_addr[1],
+			card->dev->dev_addr[2], card->dev->dev_addr[3],
+			card->dev->dev_addr[4], card->dev->dev_addr[5],
+			card->dev->name);
 	}
 	return 0;
 }
@@ -1015,9 +1019,8 @@ static int __qeth_l2_set_online(struct ccwgroup_device *gdev, int recovery_mode)
 	if (rc) {
 		QETH_DBF_TEXT_(SETUP, 2, "1err%d", rc);
 		if (rc == 0xe080) {
-			PRINT_WARN("LAN on card %s if offline! "
-				   "Waiting for STARTLAN from card.\n",
-				   CARD_BUS_ID(card));
+			dev_warn(&card->gdev->dev,
+				"The LAN is offline\n");
 			card->lan_online = 0;
 		}
 		return rc;
@@ -1117,8 +1120,8 @@ static int qeth_l2_recover(void *ptr)
 	if (!qeth_do_run_thread(card, QETH_RECOVER_THREAD))
 		return 0;
 	QETH_DBF_TEXT(TRACE, 2, "recover2");
-	PRINT_WARN("Recovery of device %s started ...\n",
-		   CARD_BUS_ID(card));
+	dev_warn(&card->gdev->dev,
+		"A recovery process has been started for the device\n");
 	card->use_hard_stop = 1;
 	__qeth_l2_set_offline(card->gdev, 1);
 	rc = __qeth_l2_set_online(card->gdev, 1);
@@ -1126,27 +1129,27 @@ static int qeth_l2_recover(void *ptr)
 	qeth_clear_thread_start_bit(card, QETH_RECOVER_THREAD);
 	qeth_clear_thread_running_bit(card, QETH_RECOVER_THREAD);
 	if (!rc)
-		PRINT_INFO("Device %s successfully recovered!\n",
-			   CARD_BUS_ID(card));
+		dev_info(&card->gdev->dev,
+			"Device successfully recovered!\n");
 	else {
 		rtnl_lock();
 		dev_close(card->dev);
 		rtnl_unlock();
-		PRINT_INFO("Device %s could not be recovered!\n",
-			   CARD_BUS_ID(card));
+		dev_warn(&card->gdev->dev, "The qeth device driver "
+			"failed to recover an error on the device\n");
 	}
 	return 0;
 }
 
 static int __init qeth_l2_init(void)
 {
-	PRINT_INFO("register layer 2 discipline\n");
+	pr_info("register layer 2 discipline\n");
 	return 0;
 }
 
 static void __exit qeth_l2_exit(void)
 {
-	PRINT_INFO("unregister layer 2 discipline\n");
+	pr_info("unregister layer 2 discipline\n");
 }
 
 static void qeth_l2_shutdown(struct ccwgroup_device *gdev)
diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c
index ed59fedd5922..c0b30b25a5f1 100644
--- a/drivers/s390/net/qeth_l3_main.c
+++ b/drivers/s390/net/qeth_l3_main.c
@@ -8,6 +8,9 @@
  *		 Frank Blaschka <frank.blaschka@de.ibm.com>
  */
 
+#define KMSG_COMPONENT "qeth"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
 #include <linux/module.h>
 #include <linux/moduleparam.h>
 #include <linux/string.h>
@@ -917,8 +920,8 @@ static int qeth_l3_register_addr_entry(struct qeth_card *card,
 	if (rc) {
 		QETH_DBF_TEXT(TRACE, 2, "FAILED");
 		qeth_l3_ipaddr_to_string(addr->proto, (u8 *)&addr->u, buf);
-		PRINT_WARN("Could not register IP address %s (rc=0x%x/%d)\n",
-			   buf, rc, rc);
+		dev_warn(&card->gdev->dev,
+			"Registering IP address %s failed\n", buf);
 	}
 	return rc;
 }
@@ -1029,24 +1032,22 @@ static int qeth_l3_setadapter_parms(struct qeth_card *card)
 	QETH_DBF_TEXT(SETUP, 2, "setadprm");
 
 	if (!qeth_is_supported(card, IPA_SETADAPTERPARMS)) {
-		PRINT_WARN("set adapter parameters not supported "
-			   "on device %s.\n",
-			   CARD_BUS_ID(card));
+		dev_info(&card->gdev->dev,
+			"set adapter parameters not supported.\n");
 		QETH_DBF_TEXT(SETUP, 2, " notsupp");
 		return 0;
 	}
 	rc = qeth_query_setadapterparms(card);
 	if (rc) {
-		PRINT_WARN("couldn't set adapter parameters on device %s: "
-			   "x%x\n", CARD_BUS_ID(card), rc);
+		QETH_DBF_MESSAGE(2, "%s couldn't set adapter parameters: "
+			"0x%x\n", card->gdev->dev.bus_id, rc);
 		return rc;
 	}
 	if (qeth_adp_supported(card, IPA_SETADP_ALTER_MAC_ADDRESS)) {
 		rc = qeth_setadpparms_change_macaddr(card);
 		if (rc)
-			PRINT_WARN("couldn't get MAC address on "
-				   "device %s: x%x\n",
-				   CARD_BUS_ID(card), rc);
+			dev_warn(&card->gdev->dev, "Reading the adapter MAC"
+				" address failed\n", rc);
 	}
 
 	if ((card->info.link_type == QETH_LINK_TYPE_HSTR) ||
@@ -1160,16 +1161,17 @@ static int qeth_l3_start_ipa_arp_processing(struct qeth_card *card)
 	QETH_DBF_TEXT(TRACE, 3, "ipaarp");
 
 	if (!qeth_is_supported(card, IPA_ARP_PROCESSING)) {
-		PRINT_WARN("ARP processing not supported "
-			   "on %s!\n", QETH_CARD_IFNAME(card));
+		dev_info(&card->gdev->dev,
+			"ARP processing not supported on %s!\n",
+			QETH_CARD_IFNAME(card));
 		return 0;
 	}
 	rc = qeth_l3_send_simple_setassparms(card, IPA_ARP_PROCESSING,
 					IPA_CMD_ASS_START, 0);
 	if (rc) {
-		PRINT_WARN("Could not start ARP processing "
-			   "assist on %s: 0x%x\n",
-			   QETH_CARD_IFNAME(card), rc);
+		dev_warn(&card->gdev->dev,
+			"Starting ARP processing support for %s failed\n",
+			QETH_CARD_IFNAME(card));
 	}
 	return rc;
 }
@@ -1181,19 +1183,21 @@ static int qeth_l3_start_ipa_ip_fragmentation(struct qeth_card *card)
 	QETH_DBF_TEXT(TRACE, 3, "ipaipfrg");
 
 	if (!qeth_is_supported(card, IPA_IP_FRAGMENTATION)) {
-		PRINT_INFO("Hardware IP fragmentation not supported on %s\n",
-			   QETH_CARD_IFNAME(card));
+		dev_info(&card->gdev->dev,
+			"Hardware IP fragmentation not supported on %s\n",
+			QETH_CARD_IFNAME(card));
 		return  -EOPNOTSUPP;
 	}
 
 	rc = qeth_l3_send_simple_setassparms(card, IPA_IP_FRAGMENTATION,
 					  IPA_CMD_ASS_START, 0);
 	if (rc) {
-		PRINT_WARN("Could not start Hardware IP fragmentation "
-			   "assist on %s: 0x%x\n",
-			   QETH_CARD_IFNAME(card), rc);
+		dev_warn(&card->gdev->dev,
+			"Starting IP fragmentation support for %s failed\n",
+			QETH_CARD_IFNAME(card));
 	} else
-		PRINT_INFO("Hardware IP fragmentation enabled \n");
+		dev_info(&card->gdev->dev,
+			"Hardware IP fragmentation enabled \n");
 	return rc;
 }
 
@@ -1207,17 +1211,18 @@ static int qeth_l3_start_ipa_source_mac(struct qeth_card *card)
 		return -EOPNOTSUPP;
 
 	if (!qeth_is_supported(card, IPA_SOURCE_MAC)) {
-		PRINT_INFO("Inbound source address not "
-			   "supported on %s\n", QETH_CARD_IFNAME(card));
+		dev_info(&card->gdev->dev,
+			"Inbound source address not supported on %s\n",
+			QETH_CARD_IFNAME(card));
 		return -EOPNOTSUPP;
 	}
 
 	rc = qeth_l3_send_simple_setassparms(card, IPA_SOURCE_MAC,
 					  IPA_CMD_ASS_START, 0);
 	if (rc)
-		PRINT_WARN("Could not start inbound source "
-			   "assist on %s: 0x%x\n",
-			   QETH_CARD_IFNAME(card), rc);
+		dev_warn(&card->gdev->dev,
+			"Starting proxy ARP support for %s failed\n",
+			QETH_CARD_IFNAME(card));
 	return rc;
 }
 
@@ -1228,19 +1233,19 @@ static int qeth_l3_start_ipa_vlan(struct qeth_card *card)
 	QETH_DBF_TEXT(TRACE, 3, "strtvlan");
 
 	if (!qeth_is_supported(card, IPA_FULL_VLAN)) {
-		PRINT_WARN("VLAN not supported on %s\n",
-				QETH_CARD_IFNAME(card));
+		dev_info(&card->gdev->dev,
+			"VLAN not supported on %s\n", QETH_CARD_IFNAME(card));
 		return -EOPNOTSUPP;
 	}
 
 	rc = qeth_l3_send_simple_setassparms(card, IPA_VLAN_PRIO,
 					  IPA_CMD_ASS_START, 0);
 	if (rc) {
-		PRINT_WARN("Could not start vlan "
-			   "assist on %s: 0x%x\n",
-			   QETH_CARD_IFNAME(card), rc);
+		dev_warn(&card->gdev->dev,
+			"Starting VLAN support for %s failed\n",
+			QETH_CARD_IFNAME(card));
 	} else {
-		PRINT_INFO("VLAN enabled \n");
+		dev_info(&card->gdev->dev, "VLAN enabled\n");
 	}
 	return rc;
 }
@@ -1252,19 +1257,20 @@ static int qeth_l3_start_ipa_multicast(struct qeth_card *card)
 	QETH_DBF_TEXT(TRACE, 3, "stmcast");
 
 	if (!qeth_is_supported(card, IPA_MULTICASTING)) {
-		PRINT_WARN("Multicast not supported on %s\n",
-			   QETH_CARD_IFNAME(card));
+		dev_info(&card->gdev->dev,
+			"Multicast not supported on %s\n",
+			QETH_CARD_IFNAME(card));
 		return -EOPNOTSUPP;
 	}
 
 	rc = qeth_l3_send_simple_setassparms(card, IPA_MULTICASTING,
 					  IPA_CMD_ASS_START, 0);
 	if (rc) {
-		PRINT_WARN("Could not start multicast "
-			   "assist on %s: rc=%i\n",
-			   QETH_CARD_IFNAME(card), rc);
+		dev_warn(&card->gdev->dev,
+			"Starting multicast support for %s failed\n",
+			QETH_CARD_IFNAME(card));
 	} else {
-		PRINT_INFO("Multicast enabled\n");
+		dev_info(&card->gdev->dev, "Multicast enabled\n");
 		card->dev->flags |= IFF_MULTICAST;
 	}
 	return rc;
@@ -1315,36 +1321,37 @@ static int qeth_l3_softsetup_ipv6(struct qeth_card *card)
 
 	rc = qeth_l3_query_ipassists(card, QETH_PROT_IPV6);
 	if (rc) {
-		PRINT_ERR("IPv6 query ipassist failed on %s\n",
-			  QETH_CARD_IFNAME(card));
+		dev_err(&card->gdev->dev,
+			"Activating IPv6 support for %s failed\n",
+			QETH_CARD_IFNAME(card));
 		return rc;
 	}
 	rc = qeth_l3_send_simple_setassparms(card, IPA_IPV6,
 					  IPA_CMD_ASS_START, 3);
 	if (rc) {
-		PRINT_WARN("IPv6 start assist (version 4) failed "
-			   "on %s: 0x%x\n",
-			   QETH_CARD_IFNAME(card), rc);
+		dev_err(&card->gdev->dev,
+			"Activating IPv6 support for %s failed\n",
+			QETH_CARD_IFNAME(card));
 		return rc;
 	}
 	rc = qeth_l3_send_simple_setassparms_ipv6(card, IPA_IPV6,
 					       IPA_CMD_ASS_START);
 	if (rc) {
-		PRINT_WARN("IPV6 start assist (version 6) failed  "
-			   "on %s: 0x%x\n",
-			   QETH_CARD_IFNAME(card), rc);
+		dev_err(&card->gdev->dev,
+			"Activating IPv6 support for %s failed\n",
+			 QETH_CARD_IFNAME(card));
 		return rc;
 	}
 	rc = qeth_l3_send_simple_setassparms_ipv6(card, IPA_PASSTHRU,
 					       IPA_CMD_ASS_START);
 	if (rc) {
-		PRINT_WARN("Could not enable passthrough "
-			   "on %s: 0x%x\n",
-			   QETH_CARD_IFNAME(card), rc);
+		dev_warn(&card->gdev->dev,
+			"Enabling the passthrough mode for %s failed\n",
+			QETH_CARD_IFNAME(card));
 		return rc;
 	}
 out:
-	PRINT_INFO("IPV6 enabled \n");
+	dev_info(&card->gdev->dev, "IPV6 enabled\n");
 	return 0;
 }
 #endif
@@ -1356,8 +1363,8 @@ static int qeth_l3_start_ipa_ipv6(struct qeth_card *card)
 	QETH_DBF_TEXT(TRACE, 3, "strtipv6");
 
 	if (!qeth_is_supported(card, IPA_IPV6)) {
-		PRINT_WARN("IPv6 not supported on %s\n",
-			   QETH_CARD_IFNAME(card));
+		dev_info(&card->gdev->dev,
+			"IPv6 not supported on %s\n", QETH_CARD_IFNAME(card));
 		return 0;
 	}
 #ifdef CONFIG_QETH_IPV6
@@ -1373,34 +1380,35 @@ static int qeth_l3_start_ipa_broadcast(struct qeth_card *card)
 	QETH_DBF_TEXT(TRACE, 3, "stbrdcst");
 	card->info.broadcast_capable = 0;
 	if (!qeth_is_supported(card, IPA_FILTERING)) {
-		PRINT_WARN("Broadcast not supported on %s\n",
-			   QETH_CARD_IFNAME(card));
+		dev_info(&card->gdev->dev,
+			"Broadcast not supported on %s\n",
+			QETH_CARD_IFNAME(card));
 		rc = -EOPNOTSUPP;
 		goto out;
 	}
 	rc = qeth_l3_send_simple_setassparms(card, IPA_FILTERING,
 					  IPA_CMD_ASS_START, 0);
 	if (rc) {
-		PRINT_WARN("Could not enable broadcasting filtering "
-			   "on %s: 0x%x\n",
-			   QETH_CARD_IFNAME(card), rc);
+		dev_warn(&card->gdev->dev, "Enabling broadcast filtering for "
+			"%s failed\n", QETH_CARD_IFNAME(card));
 		goto out;
 	}
 
 	rc = qeth_l3_send_simple_setassparms(card, IPA_FILTERING,
 					  IPA_CMD_ASS_CONFIGURE, 1);
 	if (rc) {
-		PRINT_WARN("Could not set up broadcast filtering on %s: 0x%x\n",
-			   QETH_CARD_IFNAME(card), rc);
+		dev_warn(&card->gdev->dev,
+			"Setting up broadcast filtering for %s failed\n",
+			QETH_CARD_IFNAME(card));
 		goto out;
 	}
 	card->info.broadcast_capable = QETH_BROADCAST_WITH_ECHO;
-	PRINT_INFO("Broadcast enabled \n");
+	dev_info(&card->gdev->dev, "Broadcast enabled\n");
 	rc = qeth_l3_send_simple_setassparms(card, IPA_FILTERING,
 					  IPA_CMD_ASS_ENABLE, 1);
 	if (rc) {
-		PRINT_WARN("Could not set up broadcast echo filtering on "
-			   "%s: 0x%x\n", QETH_CARD_IFNAME(card), rc);
+		dev_warn(&card->gdev->dev, "Setting up broadcast echo "
+			"filtering for %s failed\n", QETH_CARD_IFNAME(card));
 		goto out;
 	}
 	card->info.broadcast_capable = QETH_BROADCAST_WITHOUT_ECHO;
@@ -1419,18 +1427,18 @@ static int qeth_l3_send_checksum_command(struct qeth_card *card)
 	rc = qeth_l3_send_simple_setassparms(card, IPA_INBOUND_CHECKSUM,
 					  IPA_CMD_ASS_START, 0);
 	if (rc) {
-		PRINT_WARN("Starting Inbound HW Checksumming failed on %s: "
-			   "0x%x,\ncontinuing using Inbound SW Checksumming\n",
-			   QETH_CARD_IFNAME(card), rc);
+		dev_warn(&card->gdev->dev, "Starting HW checksumming for %s "
+			"failed, using SW checksumming\n",
+			QETH_CARD_IFNAME(card));
 		return rc;
 	}
 	rc = qeth_l3_send_simple_setassparms(card, IPA_INBOUND_CHECKSUM,
 					  IPA_CMD_ASS_ENABLE,
 					  card->info.csum_mask);
 	if (rc) {
-		PRINT_WARN("Enabling Inbound HW Checksumming failed on %s: "
-			   "0x%x,\ncontinuing using Inbound SW Checksumming\n",
-			   QETH_CARD_IFNAME(card), rc);
+		dev_warn(&card->gdev->dev, "Enabling HW checksumming for %s "
+			"failed, using SW checksumming\n",
+			QETH_CARD_IFNAME(card));
 		return rc;
 	}
 	return 0;
@@ -1443,26 +1451,30 @@ static int qeth_l3_start_ipa_checksum(struct qeth_card *card)
 	QETH_DBF_TEXT(TRACE, 3, "strtcsum");
 
 	if (card->options.checksum_type == NO_CHECKSUMMING) {
-		PRINT_WARN("Using no checksumming on %s.\n",
-			   QETH_CARD_IFNAME(card));
+		dev_info(&card->gdev->dev,
+			"Using no checksumming on %s.\n",
+			QETH_CARD_IFNAME(card));
 		return 0;
 	}
 	if (card->options.checksum_type == SW_CHECKSUMMING) {
-		PRINT_WARN("Using SW checksumming on %s.\n",
-			   QETH_CARD_IFNAME(card));
+		dev_info(&card->gdev->dev,
+			"Using SW checksumming on %s.\n",
+			QETH_CARD_IFNAME(card));
 		return 0;
 	}
 	if (!qeth_is_supported(card, IPA_INBOUND_CHECKSUM)) {
-		PRINT_WARN("Inbound HW Checksumming not "
-			   "supported on %s,\ncontinuing "
-			   "using Inbound SW Checksumming\n",
-			   QETH_CARD_IFNAME(card));
+		dev_info(&card->gdev->dev,
+			"Inbound HW Checksumming not "
+			"supported on %s,\ncontinuing "
+			"using Inbound SW Checksumming\n",
+			QETH_CARD_IFNAME(card));
 		card->options.checksum_type = SW_CHECKSUMMING;
 		return 0;
 	}
 	rc = qeth_l3_send_checksum_command(card);
 	if (!rc)
-		PRINT_INFO("HW Checksumming (inbound) enabled \n");
+		dev_info(&card->gdev->dev,
+			"HW Checksumming (inbound) enabled\n");
 
 	return rc;
 }
@@ -1474,18 +1486,20 @@ static int qeth_l3_start_ipa_tso(struct qeth_card *card)
 	QETH_DBF_TEXT(TRACE, 3, "sttso");
 
 	if (!qeth_is_supported(card, IPA_OUTBOUND_TSO)) {
-		PRINT_WARN("Outbound TSO not supported on %s\n",
-			   QETH_CARD_IFNAME(card));
+		dev_info(&card->gdev->dev,
+			"Outbound TSO not supported on %s\n",
+			QETH_CARD_IFNAME(card));
 		rc = -EOPNOTSUPP;
 	} else {
 		rc = qeth_l3_send_simple_setassparms(card, IPA_OUTBOUND_TSO,
 						IPA_CMD_ASS_START, 0);
 		if (rc)
-			PRINT_WARN("Could not start outbound TSO "
-				   "assist on %s: rc=%i\n",
-				   QETH_CARD_IFNAME(card), rc);
+			dev_warn(&card->gdev->dev, "Starting outbound TCP "
+				"segmentation offload for %s failed\n",
+				QETH_CARD_IFNAME(card));
 		else
-			PRINT_INFO("Outbound TSO enabled\n");
+			dev_info(&card->gdev->dev,
+				"Outbound TSO enabled\n");
 	}
 	if (rc && (card->options.large_send == QETH_LARGE_SEND_TSO)) {
 		card->options.large_send = QETH_LARGE_SEND_NO;
@@ -1578,12 +1592,8 @@ static int qeth_l3_get_unique_id_cb(struct qeth_card *card,
 	else {
 		card->info.unique_id =  UNIQUE_ID_IF_CREATE_ADDR_FAILED |
 					UNIQUE_ID_NOT_BY_CARD;
-		PRINT_WARN("couldn't get a unique id from the card on device "
-			   "%s (result=x%x), using default id. ipv6 "
-			   "autoconfig on other lpars may lead to duplicate "
-			   "ip addresses. please use manually "
-			   "configured ones.\n",
-			   CARD_BUS_ID(card), cmd->hdr.return_code);
+		dev_warn(&card->gdev->dev, "The network adapter failed to "
+			"generate a unique ID\n");
 	}
 	return 0;
 }
@@ -3086,9 +3096,8 @@ static int __qeth_l3_set_online(struct ccwgroup_device *gdev, int recovery_mode)
 	if (rc) {
 		QETH_DBF_TEXT_(SETUP, 2, "1err%d", rc);
 		if (rc == 0xe080) {
-			PRINT_WARN("LAN on card %s if offline! "
-				   "Waiting for STARTLAN from card.\n",
-				   CARD_BUS_ID(card));
+			dev_warn(&card->gdev->dev,
+				"The LAN is offline\n");
 			card->lan_online = 0;
 		}
 		return rc;
@@ -3194,8 +3203,8 @@ static int qeth_l3_recover(void *ptr)
 	if (!qeth_do_run_thread(card, QETH_RECOVER_THREAD))
 		return 0;
 	QETH_DBF_TEXT(TRACE, 2, "recover2");
-	PRINT_WARN("Recovery of device %s started ...\n",
-		   CARD_BUS_ID(card));
+	dev_warn(&card->gdev->dev,
+		"A recovery process has been started for the device\n");
 	card->use_hard_stop = 1;
 	__qeth_l3_set_offline(card->gdev, 1);
 	rc = __qeth_l3_set_online(card->gdev, 1);
@@ -3203,14 +3212,14 @@ static int qeth_l3_recover(void *ptr)
 	qeth_clear_thread_start_bit(card, QETH_RECOVER_THREAD);
 	qeth_clear_thread_running_bit(card, QETH_RECOVER_THREAD);
 	if (!rc)
-		PRINT_INFO("Device %s successfully recovered!\n",
-			   CARD_BUS_ID(card));
+		dev_info(&card->gdev->dev,
+			"Device successfully recovered!\n");
 	else {
 		rtnl_lock();
 		dev_close(card->dev);
 		rtnl_unlock();
-		PRINT_INFO("Device %s could not be recovered!\n",
-			   CARD_BUS_ID(card));
+		dev_warn(&card->gdev->dev, "The qeth device driver "
+			"failed to recover an error on the device\n");
 	}
 	return 0;
 }
@@ -3344,7 +3353,7 @@ static int qeth_l3_register_notifiers(void)
 		return rc;
 	}
 #else
-	PRINT_WARN("layer 3 discipline no IPv6 support\n");
+	pr_warning("There is no IPv6 support for the layer 3 discipline\n");
 #endif
 	return 0;
 }
@@ -3363,7 +3372,7 @@ static int __init qeth_l3_init(void)
 {
 	int rc = 0;
 
-	PRINT_INFO("register layer 3 discipline\n");
+	pr_info("register layer 3 discipline\n");
 	rc = qeth_l3_register_notifiers();
 	return rc;
 }
@@ -3371,7 +3380,7 @@ static int __init qeth_l3_init(void)
 static void __exit qeth_l3_exit(void)
 {
 	qeth_l3_unregister_notifiers();
-	PRINT_INFO("unregister layer 3 discipline\n");
+	pr_info("unregister layer 3 discipline\n");
 }
 
 module_init(qeth_l3_init);
diff --git a/drivers/s390/scsi/zfcp_aux.c b/drivers/s390/scsi/zfcp_aux.c
index 3d4e3e3f3fc0..e529b55b3ce9 100644
--- a/drivers/s390/scsi/zfcp_aux.c
+++ b/drivers/s390/scsi/zfcp_aux.c
@@ -25,9 +25,15 @@
  *            Sven Schuetz
  */
 
+#define KMSG_COMPONENT "zfcp"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
 #include <linux/miscdevice.h>
+#include <linux/seq_file.h>
 #include "zfcp_ext.h"
 
+#define ZFCP_BUS_ID_SIZE	20
+
 static char *device;
 
 MODULE_AUTHOR("IBM Deutschland Entwicklung GmbH - linux390@de.ibm.com");
@@ -83,9 +89,9 @@ static int __init zfcp_device_setup(char *devstr)
 	strcpy(str, devstr);
 
 	token = strsep(&str, ",");
-	if (!token || strlen(token) >= BUS_ID_SIZE)
+	if (!token || strlen(token) >= ZFCP_BUS_ID_SIZE)
 		goto err_out;
-	strncpy(zfcp_data.init_busid, token, BUS_ID_SIZE);
+	strncpy(zfcp_data.init_busid, token, ZFCP_BUS_ID_SIZE);
 
 	token = strsep(&str, ",");
 	if (!token || strict_strtoull(token, 0,
@@ -102,7 +108,7 @@ static int __init zfcp_device_setup(char *devstr)
 
  err_out:
 	kfree(str);
-	pr_err("zfcp: %s is not a valid SCSI device\n", devstr);
+	pr_err("%s is not a valid SCSI device\n", devstr);
 	return 0;
 }
 
@@ -186,13 +192,13 @@ static int __init zfcp_module_init(void)
 
 	retval = misc_register(&zfcp_cfdc_misc);
 	if (retval) {
-		pr_err("zfcp: Registering the misc device zfcp_cfdc failed\n");
+		pr_err("Registering the misc device zfcp_cfdc failed\n");
 		goto out_misc;
 	}
 
 	retval = zfcp_ccw_register();
 	if (retval) {
-		pr_err("zfcp: The zfcp device driver could not register with "
+		pr_err("The zfcp device driver could not register with "
 		       "the common I/O layer\n");
 		goto out_ccw_register;
 	}
@@ -436,6 +442,16 @@ static void _zfcp_status_read_scheduler(struct work_struct *work)
 					     stat_work));
 }
 
+static void zfcp_print_sl(struct seq_file *m, struct service_level *sl)
+{
+	struct zfcp_adapter *adapter =
+		container_of(sl, struct zfcp_adapter, service_level);
+
+	seq_printf(m, "zfcp: %s microcode level %x\n",
+		   dev_name(&adapter->ccw_device->dev),
+		   adapter->fsf_lic_version);
+}
+
 /**
  * zfcp_adapter_enqueue - enqueue a new adapter to the list
  * @ccw_device: pointer to the struct cc_device
@@ -500,6 +516,8 @@ int zfcp_adapter_enqueue(struct ccw_device *ccw_device)
 	INIT_WORK(&adapter->stat_work, _zfcp_status_read_scheduler);
 	INIT_WORK(&adapter->scan_work, _zfcp_scan_ports_later);
 
+	adapter->service_level.seq_print = zfcp_print_sl;
+
 	/* mark adapter unusable as long as sysfs registration is not complete */
 	atomic_set_mask(ZFCP_STATUS_COMMON_REMOVE, &adapter->status);
 
diff --git a/drivers/s390/scsi/zfcp_ccw.c b/drivers/s390/scsi/zfcp_ccw.c
index 951a8d409d1d..728147131e1d 100644
--- a/drivers/s390/scsi/zfcp_ccw.c
+++ b/drivers/s390/scsi/zfcp_ccw.c
@@ -6,6 +6,9 @@
  * Copyright IBM Corporation 2002, 2008
  */
 
+#define KMSG_COMPONENT "zfcp"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
 #include "zfcp_ext.h"
 
 /**
diff --git a/drivers/s390/scsi/zfcp_cfdc.c b/drivers/s390/scsi/zfcp_cfdc.c
index ec2abceca6dc..f1a7518e67ed 100644
--- a/drivers/s390/scsi/zfcp_cfdc.c
+++ b/drivers/s390/scsi/zfcp_cfdc.c
@@ -7,6 +7,9 @@
  * Copyright IBM Corporation 2008
  */
 
+#define KMSG_COMPONENT "zfcp"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
 #include <linux/types.h>
 #include <linux/miscdevice.h>
 #include <asm/ccwdev.h>
diff --git a/drivers/s390/scsi/zfcp_dbf.c b/drivers/s390/scsi/zfcp_dbf.c
index 31012d58cfb7..735d675623f8 100644
--- a/drivers/s390/scsi/zfcp_dbf.c
+++ b/drivers/s390/scsi/zfcp_dbf.c
@@ -6,6 +6,9 @@
  * Copyright IBM Corporation 2002, 2008
  */
 
+#define KMSG_COMPONENT "zfcp"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
 #include <linux/ctype.h>
 #include <asm/debug.h>
 #include "zfcp_ext.h"
diff --git a/drivers/s390/scsi/zfcp_def.h b/drivers/s390/scsi/zfcp_def.h
index 9ce4c75bd190..e19e46ae4a68 100644
--- a/drivers/s390/scsi/zfcp_def.h
+++ b/drivers/s390/scsi/zfcp_def.h
@@ -33,6 +33,7 @@
 #include <asm/qdio.h>
 #include <asm/debug.h>
 #include <asm/ebcdic.h>
+#include <asm/sysinfo.h>
 #include "zfcp_dbf.h"
 #include "zfcp_fsf.h"
 
@@ -515,6 +516,7 @@ struct zfcp_adapter {
 	struct fsf_qtcb_bottom_port *stats_reset_data;
 	unsigned long		stats_reset;
 	struct work_struct	scan_work;
+	struct service_level	service_level;
 	atomic_t		qdio_outb_full;	   /* queue full incidents */
 };
 
diff --git a/drivers/s390/scsi/zfcp_erp.c b/drivers/s390/scsi/zfcp_erp.c
index c557ba34e1aa..4ed4950d994b 100644
--- a/drivers/s390/scsi/zfcp_erp.c
+++ b/drivers/s390/scsi/zfcp_erp.c
@@ -6,6 +6,9 @@
  * Copyright IBM Corporation 2002, 2008
  */
 
+#define KMSG_COMPONENT "zfcp"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
 #include "zfcp_ext.h"
 
 #define ZFCP_MAX_ERPS                   3
@@ -1281,10 +1284,13 @@ static void zfcp_erp_action_cleanup(struct zfcp_erp_action *act, int result)
 		break;
 
 	case ZFCP_ERP_ACTION_REOPEN_ADAPTER:
-		if (result != ZFCP_ERP_SUCCEEDED)
+		if (result != ZFCP_ERP_SUCCEEDED) {
+			unregister_service_level(&adapter->service_level);
 			zfcp_erp_rports_del(adapter);
-		else
+		} else {
+			register_service_level(&adapter->service_level);
 			schedule_work(&adapter->scan_work);
+		}
 		zfcp_adapter_put(adapter);
 		break;
 	}
diff --git a/drivers/s390/scsi/zfcp_fc.c b/drivers/s390/scsi/zfcp_fc.c
index 8aab3091a7b1..f009f2a7ec3e 100644
--- a/drivers/s390/scsi/zfcp_fc.c
+++ b/drivers/s390/scsi/zfcp_fc.c
@@ -6,6 +6,9 @@
  * Copyright IBM Corporation 2008
  */
 
+#define KMSG_COMPONENT "zfcp"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
 #include "zfcp_ext.h"
 
 struct ct_iu_gpn_ft_req {
diff --git a/drivers/s390/scsi/zfcp_fsf.c b/drivers/s390/scsi/zfcp_fsf.c
index dc0367690405..9c72e083559d 100644
--- a/drivers/s390/scsi/zfcp_fsf.c
+++ b/drivers/s390/scsi/zfcp_fsf.c
@@ -6,6 +6,9 @@
  * Copyright IBM Corporation 2002, 2008
  */
 
+#define KMSG_COMPONENT "zfcp"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
 #include <linux/blktrace_api.h>
 #include "zfcp_ext.h"
 
diff --git a/drivers/s390/scsi/zfcp_qdio.c b/drivers/s390/scsi/zfcp_qdio.c
index 664752f90b20..d3b55fb66f13 100644
--- a/drivers/s390/scsi/zfcp_qdio.c
+++ b/drivers/s390/scsi/zfcp_qdio.c
@@ -6,6 +6,9 @@
  * Copyright IBM Corporation 2002, 2008
  */
 
+#define KMSG_COMPONENT "zfcp"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
 #include "zfcp_ext.h"
 
 /* FIXME(tune): free space should be one max. SBAL chain plus what? */
diff --git a/drivers/s390/scsi/zfcp_scsi.c b/drivers/s390/scsi/zfcp_scsi.c
index 468c880f8b6d..9dc42a68fbdd 100644
--- a/drivers/s390/scsi/zfcp_scsi.c
+++ b/drivers/s390/scsi/zfcp_scsi.c
@@ -6,6 +6,9 @@
  * Copyright IBM Corporation 2002, 2008
  */
 
+#define KMSG_COMPONENT "zfcp"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
 #include "zfcp_ext.h"
 #include <asm/atomic.h>
 
diff --git a/drivers/s390/scsi/zfcp_sysfs.c b/drivers/s390/scsi/zfcp_sysfs.c
index ca9293ba1766..899af2b45b1e 100644
--- a/drivers/s390/scsi/zfcp_sysfs.c
+++ b/drivers/s390/scsi/zfcp_sysfs.c
@@ -6,6 +6,9 @@
  * Copyright IBM Corporation 2008
  */
 
+#define KMSG_COMPONENT "zfcp"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
 #include "zfcp_ext.h"
 
 #define ZFCP_DEV_ATTR(_feat, _name, _mode, _show, _store) \
diff --git a/drivers/s390/sysinfo.c b/drivers/s390/sysinfo.c
index c3e4ab07b9cc..0eea90781385 100644
--- a/drivers/s390/sysinfo.c
+++ b/drivers/s390/sysinfo.c
@@ -1,17 +1,21 @@
 /*
  *  drivers/s390/sysinfo.c
  *
- *    Copyright (C) 2001 IBM Deutschland Entwicklung GmbH, IBM Corporation
- *    Author(s): Ulrich Weigand (Ulrich.Weigand@de.ibm.com)
+ *  Copyright IBM Corp. 2001, 2008
+ *  Author(s): Ulrich Weigand (Ulrich.Weigand@de.ibm.com)
+ *	       Martin Schwidefsky <schwidefsky@de.ibm.com>
  */
 
 #include <linux/kernel.h>
 #include <linux/mm.h>
 #include <linux/proc_fs.h>
+#include <linux/seq_file.h>
 #include <linux/init.h>
 #include <linux/delay.h>
+#include <linux/module.h>
 #include <asm/ebcdic.h>
 #include <asm/sysinfo.h>
+#include <asm/cpcmd.h>
 
 /* Sigh, math-emu. Don't ask. */
 #include <asm/sfp-util.h>
@@ -271,6 +275,125 @@ static __init int create_proc_sysinfo(void)
 
 __initcall(create_proc_sysinfo);
 
+/*
+ * Service levels interface.
+ */
+
+static DECLARE_RWSEM(service_level_sem);
+static LIST_HEAD(service_level_list);
+
+int register_service_level(struct service_level *slr)
+{
+	struct service_level *ptr;
+
+	down_write(&service_level_sem);
+	list_for_each_entry(ptr, &service_level_list, list)
+		if (ptr == slr) {
+			up_write(&service_level_sem);
+			return -EEXIST;
+		}
+	list_add_tail(&slr->list, &service_level_list);
+	up_write(&service_level_sem);
+	return 0;
+}
+EXPORT_SYMBOL(register_service_level);
+
+int unregister_service_level(struct service_level *slr)
+{
+	struct service_level *ptr, *next;
+	int rc = -ENOENT;
+
+	down_write(&service_level_sem);
+	list_for_each_entry_safe(ptr, next, &service_level_list, list) {
+		if (ptr != slr)
+			continue;
+		list_del(&ptr->list);
+		rc = 0;
+		break;
+	}
+	up_write(&service_level_sem);
+	return rc;
+}
+EXPORT_SYMBOL(unregister_service_level);
+
+static void *service_level_start(struct seq_file *m, loff_t *pos)
+{
+	down_read(&service_level_sem);
+	return seq_list_start(&service_level_list, *pos);
+}
+
+static void *service_level_next(struct seq_file *m, void *p, loff_t *pos)
+{
+	return seq_list_next(p, &service_level_list, pos);
+}
+
+static void service_level_stop(struct seq_file *m, void *p)
+{
+	up_read(&service_level_sem);
+}
+
+static int service_level_show(struct seq_file *m, void *p)
+{
+	struct service_level *slr;
+
+	slr = list_entry(p, struct service_level, list);
+	slr->seq_print(m, slr);
+	return 0;
+}
+
+static const struct seq_operations service_level_seq_ops = {
+	.start		= service_level_start,
+	.next		= service_level_next,
+	.stop		= service_level_stop,
+	.show		= service_level_show
+};
+
+static int service_level_open(struct inode *inode, struct file *file)
+{
+	return seq_open(file, &service_level_seq_ops);
+}
+
+static const struct file_operations service_level_ops = {
+	.open		= service_level_open,
+	.read		= seq_read,
+	.llseek 	= seq_lseek,
+	.release	= seq_release
+};
+
+static void service_level_vm_print(struct seq_file *m,
+				   struct service_level *slr)
+{
+	char *query_buffer, *str;
+
+	query_buffer = kmalloc(1024, GFP_KERNEL | GFP_DMA);
+	if (!query_buffer)
+		return;
+	cpcmd("QUERY CPLEVEL", query_buffer, 1024, NULL);
+	str = strchr(query_buffer, '\n');
+	if (str)
+		*str = 0;
+	seq_printf(m, "VM: %s\n", query_buffer);
+	kfree(query_buffer);
+}
+
+static struct service_level service_level_vm = {
+	.seq_print = service_level_vm_print
+};
+
+static __init int create_proc_service_level(void)
+{
+	proc_create("service_levels", 0, NULL, &service_level_ops);
+	if (MACHINE_IS_VM)
+		register_service_level(&service_level_vm);
+	return 0;
+}
+
+subsys_initcall(create_proc_service_level);
+
+/*
+ * Bogomips calculation based on cpu capability.
+ */
+
 int get_cpu_capability(unsigned int *capability)
 {
 	struct sysinfo_1_2_2 *info;
diff --git a/drivers/scsi/aacraid/linit.c b/drivers/scsi/aacraid/linit.c
index 162cd927d94b..94acbeed4e7c 100644
--- a/drivers/scsi/aacraid/linit.c
+++ b/drivers/scsi/aacraid/linit.c
@@ -175,8 +175,8 @@ static struct aac_driver_ident aac_drivers[] = {
 	{ aac_rx_init, "percraid", "DELL    ", "PERCRAID        ", 2, AAC_QUIRK_31BIT | AAC_QUIRK_34SG | AAC_QUIRK_SCSI_32 }, /* PERC 3/Di (Boxster/PERC3DiB) */
 	{ aac_rx_init, "aacraid",  "ADAPTEC ", "catapult        ", 2, AAC_QUIRK_31BIT | AAC_QUIRK_34SG | AAC_QUIRK_SCSI_32 }, /* catapult */
 	{ aac_rx_init, "aacraid",  "ADAPTEC ", "tomcat          ", 2, AAC_QUIRK_31BIT | AAC_QUIRK_34SG | AAC_QUIRK_SCSI_32 }, /* tomcat */
-	{ aac_rx_init, "aacraid",  "ADAPTEC ", "Adaptec 2120S   ", 1, AAC_QUIRK_31BIT | AAC_QUIRK_34SG | AAC_QUIRK_SCSI_32 }, /* Adaptec 2120S (Crusader) */
-	{ aac_rx_init, "aacraid",  "ADAPTEC ", "Adaptec 2200S   ", 2, AAC_QUIRK_31BIT | AAC_QUIRK_34SG | AAC_QUIRK_SCSI_32 }, /* Adaptec 2200S (Vulcan) */
+	{ aac_rx_init, "aacraid",  "ADAPTEC ", "Adaptec 2120S   ", 1, AAC_QUIRK_31BIT | AAC_QUIRK_34SG },		      /* Adaptec 2120S (Crusader) */
+	{ aac_rx_init, "aacraid",  "ADAPTEC ", "Adaptec 2200S   ", 2, AAC_QUIRK_31BIT | AAC_QUIRK_34SG },		      /* Adaptec 2200S (Vulcan) */
 	{ aac_rx_init, "aacraid",  "ADAPTEC ", "Adaptec 2200S   ", 2, AAC_QUIRK_31BIT | AAC_QUIRK_34SG | AAC_QUIRK_SCSI_32 }, /* Adaptec 2200S (Vulcan-2m) */
 	{ aac_rx_init, "aacraid",  "Legend  ", "Legend S220     ", 1, AAC_QUIRK_31BIT | AAC_QUIRK_34SG | AAC_QUIRK_SCSI_32 }, /* Legend S220 (Legend Crusader) */
 	{ aac_rx_init, "aacraid",  "Legend  ", "Legend S230     ", 2, AAC_QUIRK_31BIT | AAC_QUIRK_34SG | AAC_QUIRK_SCSI_32 }, /* Legend S230 (Legend Vulcan) */
diff --git a/drivers/scsi/aic94xx/aic94xx_tmf.c b/drivers/scsi/aic94xx/aic94xx_tmf.c
index d4640ef6d44f..78eb86fc6276 100644
--- a/drivers/scsi/aic94xx/aic94xx_tmf.c
+++ b/drivers/scsi/aic94xx/aic94xx_tmf.c
@@ -189,7 +189,7 @@ int asd_I_T_nexus_reset(struct domain_device *dev)
 	asd_clear_nexus_I_T(dev, NEXUS_PHASE_PRE);
 	/* send a hard reset */
 	ASD_DPRINTK("sending %s reset to %s\n",
-		    reset_type ? "hard" : "soft", phy->dev.bus_id);
+		    reset_type ? "hard" : "soft", dev_name(&phy->dev));
 	res = sas_phy_reset(phy, reset_type);
 	if (res == TMF_RESP_FUNC_COMPLETE) {
 		/* wait for the maximum settle time */
diff --git a/drivers/scsi/hosts.c b/drivers/scsi/hosts.c
index 3fdbb13e80a8..aa670a1d1513 100644
--- a/drivers/scsi/hosts.c
+++ b/drivers/scsi/hosts.c
@@ -388,8 +388,7 @@ struct Scsi_Host *scsi_host_alloc(struct scsi_host_template *sht, int privsize)
 		shost->dma_boundary = 0xffffffff;
 
 	device_initialize(&shost->shost_gendev);
-	snprintf(shost->shost_gendev.bus_id, BUS_ID_SIZE, "host%d",
-		shost->host_no);
+	dev_set_name(&shost->shost_gendev, "host%d", shost->host_no);
 #ifndef CONFIG_SYSFS_DEPRECATED
 	shost->shost_gendev.bus = &scsi_bus_type;
 #endif
@@ -398,8 +397,7 @@ struct Scsi_Host *scsi_host_alloc(struct scsi_host_template *sht, int privsize)
 	device_initialize(&shost->shost_dev);
 	shost->shost_dev.parent = &shost->shost_gendev;
 	shost->shost_dev.class = &shost_class;
-	snprintf(shost->shost_dev.bus_id, BUS_ID_SIZE, "host%d",
-		 shost->host_no);
+	dev_set_name(&shost->shost_dev, "host%d", shost->host_no);
 	shost->shost_dev.groups = scsi_sysfs_shost_attr_groups;
 
 	shost->ehandler = kthread_run(scsi_error_handler, shost,
diff --git a/drivers/scsi/ipr.c b/drivers/scsi/ipr.c
index ded854a6dd35..d773030c4194 100644
--- a/drivers/scsi/ipr.c
+++ b/drivers/scsi/ipr.c
@@ -2184,7 +2184,7 @@ static void ipr_dump_location_data(struct ipr_ioa_cfg *ioa_cfg,
 		sizeof(struct ipr_dump_entry_header);
 	driver_dump->location_entry.hdr.data_type = IPR_DUMP_DATA_TYPE_ASCII;
 	driver_dump->location_entry.hdr.id = IPR_DUMP_LOCATION_ID;
-	strcpy(driver_dump->location_entry.location, ioa_cfg->pdev->dev.bus_id);
+	strcpy(driver_dump->location_entry.location, dev_name(&ioa_cfg->pdev->dev));
 	driver_dump->hdr.num_entries++;
 }
 
diff --git a/drivers/scsi/ipr.h b/drivers/scsi/ipr.h
index 4871dd1f2582..d5723c92c322 100644
--- a/drivers/scsi/ipr.h
+++ b/drivers/scsi/ipr.h
@@ -1272,7 +1272,7 @@ struct ipr_dump_entry_header {
 
 struct ipr_dump_location_entry {
 	struct ipr_dump_entry_header hdr;
-	u8 location[BUS_ID_SIZE];
+	u8 location[20];
 }__attribute__((packed));
 
 struct ipr_dump_trace_entry {
diff --git a/drivers/scsi/libiscsi.c b/drivers/scsi/libiscsi.c
index 801c7cf54d2e..3fdee7370ccc 100644
--- a/drivers/scsi/libiscsi.c
+++ b/drivers/scsi/libiscsi.c
@@ -489,12 +489,6 @@ __iscsi_conn_send_pdu(struct iscsi_conn *conn, struct iscsi_hdr *hdr,
 		if (!__kfifo_get(session->cmdpool.queue,
 				 (void*)&task, sizeof(void*)))
 			return NULL;
-
-		if ((hdr->opcode == (ISCSI_OP_NOOP_OUT | ISCSI_OP_IMMEDIATE)) &&
-		     hdr->ttt == RESERVED_ITT) {
-			conn->ping_task = task;
-			conn->last_ping = jiffies;
-		}
 	}
 	/*
 	 * released in complete pdu for task we expect a response for, and
@@ -703,6 +697,11 @@ static void iscsi_send_nopout(struct iscsi_conn *conn, struct iscsi_nopin *rhdr)
 	task = __iscsi_conn_send_pdu(conn, (struct iscsi_hdr *)&hdr, NULL, 0);
 	if (!task)
 		iscsi_conn_printk(KERN_ERR, conn, "Could not send nopout\n");
+	else if (!rhdr) {
+		/* only track our nops */
+		conn->ping_task = task;
+		conn->last_ping = jiffies;
+	}
 }
 
 static int iscsi_handle_reject(struct iscsi_conn *conn, struct iscsi_hdr *hdr,
diff --git a/drivers/scsi/libsas/sas_discover.c b/drivers/scsi/libsas/sas_discover.c
index 709a6f75ca9d..facc5bfcf7db 100644
--- a/drivers/scsi/libsas/sas_discover.c
+++ b/drivers/scsi/libsas/sas_discover.c
@@ -169,7 +169,7 @@ int sas_notify_lldd_dev_found(struct domain_device *dev)
 		if (res) {
 			printk("sas: driver on pcidev %s cannot handle "
 			       "device %llx, error:%d\n",
-			       sas_ha->dev->bus_id,
+			       dev_name(sas_ha->dev),
 			       SAS_ADDR(dev->sas_addr), res);
 		}
 	}
diff --git a/drivers/scsi/libsas/sas_dump.c b/drivers/scsi/libsas/sas_dump.c
index bf34a236f946..c17c25030f1c 100644
--- a/drivers/scsi/libsas/sas_dump.c
+++ b/drivers/scsi/libsas/sas_dump.c
@@ -56,7 +56,7 @@ void sas_dprint_phye(int phyid, enum phy_event pe)
 
 void sas_dprint_hae(struct sas_ha_struct *sas_ha, enum ha_event he)
 {
-	SAS_DPRINTK("ha %s: %s event\n", sas_ha->dev->bus_id,
+	SAS_DPRINTK("ha %s: %s event\n", dev_name(sas_ha->dev),
 		    sas_hae_str[he]);
 }
 
diff --git a/drivers/scsi/libsas/sas_port.c b/drivers/scsi/libsas/sas_port.c
index 139935a121b4..e6ac59c023f1 100644
--- a/drivers/scsi/libsas/sas_port.c
+++ b/drivers/scsi/libsas/sas_port.c
@@ -113,7 +113,7 @@ static void sas_form_port(struct asd_sas_phy *phy)
 	sas_port_add_phy(port->port, phy->phy);
 
 	SAS_DPRINTK("%s added to %s, phy_mask:0x%x (%16llx)\n",
-		    phy->phy->dev.bus_id,port->port->dev.bus_id,
+		    dev_name(&phy->phy->dev), dev_name(&port->port->dev),
 		    port->phy_mask,
 		    SAS_ADDR(port->attached_sas_addr));
 
diff --git a/drivers/scsi/mac_esp.c b/drivers/scsi/mac_esp.c
index 887682a24e36..c24e86f07804 100644
--- a/drivers/scsi/mac_esp.c
+++ b/drivers/scsi/mac_esp.c
@@ -53,7 +53,8 @@ struct mac_esp_priv {
 	void __iomem *pdma_io;
 	int error;
 };
-static struct platform_device *internal_esp, *external_esp;
+static struct platform_device *internal_pdev, *external_pdev;
+static struct esp *esp_chips[2];
 
 #define MAC_ESP_GET_PRIV(esp) ((struct mac_esp_priv *) \
 			       platform_get_drvdata((struct platform_device *) \
@@ -170,7 +171,7 @@ static inline int mac_esp_wait_for_dreq(struct esp *esp)
 
 #define MAC_ESP_PDMA_LOOP(operands) \
 	asm volatile ( \
-	     "       tstw %2                   \n" \
+	     "       tstw %1                   \n" \
 	     "       jbeq 20f                  \n" \
 	     "1:     movew " operands "        \n" \
 	     "2:     movew " operands "        \n" \
@@ -188,14 +189,14 @@ static inline int mac_esp_wait_for_dreq(struct esp *esp)
 	     "14:    movew " operands "        \n" \
 	     "15:    movew " operands "        \n" \
 	     "16:    movew " operands "        \n" \
-	     "       subqw #1,%2               \n" \
+	     "       subqw #1,%1               \n" \
 	     "       jbne 1b                   \n" \
-	     "20:    tstw %3                   \n" \
+	     "20:    tstw %2                   \n" \
 	     "       jbeq 30f                  \n" \
 	     "21:    movew " operands "        \n" \
-	     "       subqw #1,%3               \n" \
+	     "       subqw #1,%2               \n" \
 	     "       jbne 21b                  \n" \
-	     "30:    tstw %4                   \n" \
+	     "30:    tstw %3                   \n" \
 	     "       jbeq 40f                  \n" \
 	     "31:    moveb " operands "        \n" \
 	     "32:    nop                       \n" \
@@ -223,8 +224,8 @@ static inline int mac_esp_wait_for_dreq(struct esp *esp)
 	     "       .long  31b,40b            \n" \
 	     "       .long  32b,40b            \n" \
 	     "       .previous                 \n" \
-	     : "+a" (addr) \
-	     : "a" (mep->pdma_io), "r" (count32), "r" (count2), "g" (esp_count))
+	     : "+a" (addr), "+r" (count32), "+r" (count2) \
+	     : "g" (count1), "a" (mep->pdma_io))
 
 static void mac_esp_send_pdma_cmd(struct esp *esp, u32 addr, u32 esp_count,
 				  u32 dma_count, int write, u8 cmd)
@@ -247,19 +248,20 @@ static void mac_esp_send_pdma_cmd(struct esp *esp, u32 addr, u32 esp_count,
 	do {
 		unsigned int count32 = esp_count >> 5;
 		unsigned int count2 = (esp_count & 0x1F) >> 1;
+		unsigned int count1 = esp_count & 1;
 		unsigned int start_addr = addr;
 
 		if (mac_esp_wait_for_dreq(esp))
 			break;
 
 		if (write) {
-			MAC_ESP_PDMA_LOOP("%1@,%0@+");
+			MAC_ESP_PDMA_LOOP("%4@,%0@+");
 
 			esp_count -= addr - start_addr;
 		} else {
 			unsigned int n;
 
-			MAC_ESP_PDMA_LOOP("%0@+,%1@");
+			MAC_ESP_PDMA_LOOP("%0@+,%4@");
 
 			if (mac_esp_wait_for_empty_fifo(esp))
 				break;
@@ -442,6 +444,32 @@ static u32 mac_esp_dma_length_limit(struct esp *esp, u32 dma_addr, u32 dma_len)
 	return dma_len > 0xFFFF ? 0xFFFF : dma_len;
 }
 
+static irqreturn_t mac_scsi_esp_intr(int irq, void *dev_id)
+{
+	int got_intr;
+
+	/*
+	 * This is an edge triggered IRQ, so we have to be careful to
+	 * avoid missing a transition when it is shared by two ESP devices.
+	 */
+
+	do {
+		got_intr = 0;
+		if (esp_chips[0] &&
+		    (mac_esp_read8(esp_chips[0], ESP_STATUS) & ESP_STAT_INTR)) {
+			(void)scsi_esp_intr(irq, esp_chips[0]);
+			got_intr = 1;
+		}
+		if (esp_chips[1] &&
+		    (mac_esp_read8(esp_chips[1], ESP_STATUS) & ESP_STAT_INTR)) {
+			(void)scsi_esp_intr(irq, esp_chips[1]);
+			got_intr = 1;
+		}
+	} while (got_intr);
+
+	return IRQ_HANDLED;
+}
+
 static struct esp_driver_ops mac_esp_ops = {
 	.esp_write8       = mac_esp_write8,
 	.esp_read8        = mac_esp_read8,
@@ -556,10 +584,16 @@ static int __devinit esp_mac_probe(struct platform_device *dev)
 	}
 
 	host->irq = IRQ_MAC_SCSI;
-	err = request_irq(host->irq, scsi_esp_intr, IRQF_SHARED, "Mac ESP",
-			  esp);
-	if (err < 0)
-		goto fail_free_priv;
+	esp_chips[dev->id] = esp;
+	mb();
+	if (esp_chips[!dev->id] == NULL) {
+		err = request_irq(host->irq, mac_scsi_esp_intr, 0,
+		                  "Mac ESP", NULL);
+		if (err < 0) {
+			esp_chips[dev->id] = NULL;
+			goto fail_free_priv;
+		}
+	}
 
 	err = scsi_esp_register(esp, &dev->dev);
 	if (err)
@@ -568,7 +602,8 @@ static int __devinit esp_mac_probe(struct platform_device *dev)
 	return 0;
 
 fail_free_irq:
-	free_irq(host->irq, esp);
+	if (esp_chips[!dev->id] == NULL)
+		free_irq(host->irq, esp);
 fail_free_priv:
 	kfree(mep);
 fail_free_command_block:
@@ -587,7 +622,9 @@ static int __devexit esp_mac_remove(struct platform_device *dev)
 
 	scsi_esp_unregister(esp);
 
-	free_irq(irq, esp);
+	esp_chips[dev->id] = NULL;
+	if (!(esp_chips[0] || esp_chips[1]))
+		free_irq(irq, NULL);
 
 	kfree(mep);
 
@@ -614,19 +651,18 @@ static int __init mac_esp_init(void)
 	if (err)
 		return err;
 
-	internal_esp = platform_device_alloc(DRV_MODULE_NAME, 0);
-	if (internal_esp && platform_device_add(internal_esp)) {
-		platform_device_put(internal_esp);
-		internal_esp = NULL;
+	internal_pdev = platform_device_alloc(DRV_MODULE_NAME, 0);
+	if (internal_pdev && platform_device_add(internal_pdev)) {
+		platform_device_put(internal_pdev);
+		internal_pdev = NULL;
 	}
-
-	external_esp = platform_device_alloc(DRV_MODULE_NAME, 1);
-	if (external_esp && platform_device_add(external_esp)) {
-		platform_device_put(external_esp);
-		external_esp = NULL;
+	external_pdev = platform_device_alloc(DRV_MODULE_NAME, 1);
+	if (external_pdev && platform_device_add(external_pdev)) {
+		platform_device_put(external_pdev);
+		external_pdev = NULL;
 	}
 
-	if (internal_esp || external_esp) {
+	if (internal_pdev || external_pdev) {
 		return 0;
 	} else {
 		platform_driver_unregister(&esp_mac_driver);
@@ -638,13 +674,13 @@ static void __exit mac_esp_exit(void)
 {
 	platform_driver_unregister(&esp_mac_driver);
 
-	if (internal_esp) {
-		platform_device_unregister(internal_esp);
-		internal_esp = NULL;
+	if (internal_pdev) {
+		platform_device_unregister(internal_pdev);
+		internal_pdev = NULL;
 	}
-	if (external_esp) {
-		platform_device_unregister(external_esp);
-		external_esp = NULL;
+	if (external_pdev) {
+		platform_device_unregister(external_pdev);
+		external_pdev = NULL;
 	}
 }
 
diff --git a/drivers/scsi/mac_scsi.c b/drivers/scsi/mac_scsi.c
index 0248919bc2df..bf2a1c516293 100644
--- a/drivers/scsi/mac_scsi.c
+++ b/drivers/scsi/mac_scsi.c
@@ -47,7 +47,6 @@
 
 #include <asm/macintosh.h>
 #include <asm/macints.h>
-#include <asm/machw.h>
 #include <asm/mac_via.h>
 
 #include "scsi.h"
diff --git a/drivers/scsi/raid_class.c b/drivers/scsi/raid_class.c
index 913a931176ef..8e5c169b03fb 100644
--- a/drivers/scsi/raid_class.c
+++ b/drivers/scsi/raid_class.c
@@ -237,8 +237,7 @@ int raid_component_add(struct raid_template *r,struct device *raid_dev,
 	rc->dev.parent = get_device(component_dev);
 	rc->num = rd->component_count++;
 
-	snprintf(rc->dev.bus_id, sizeof(rc->dev.bus_id),
-		 "component-%d", rc->num);
+	dev_set_name(&rc->dev, "component-%d", rc->num);
 	list_add_tail(&rc->node, &rd->component_list);
 	rc->dev.class = &raid_class.class;
 	err = device_add(&rc->dev);
diff --git a/drivers/scsi/scsi_debug.c b/drivers/scsi/scsi_debug.c
index 27c633f55794..6eebd0bbe8a8 100644
--- a/drivers/scsi/scsi_debug.c
+++ b/drivers/scsi/scsi_debug.c
@@ -2508,7 +2508,7 @@ static void pseudo_0_release(struct device *dev)
 }
 
 static struct device pseudo_primary = {
-	.bus_id		= "pseudo_0",
+	.init_name	= "pseudo_0",
 	.release	= pseudo_0_release,
 };
 
@@ -2680,7 +2680,7 @@ static int sdebug_add_adapter(void)
         sdbg_host->dev.bus = &pseudo_lld_bus;
         sdbg_host->dev.parent = &pseudo_primary;
         sdbg_host->dev.release = &sdebug_release_adapter;
-        sprintf(sdbg_host->dev.bus_id, "adapter%d", scsi_debug_add_host);
+        dev_set_name(&sdbg_host->dev, "adapter%d", scsi_debug_add_host);
 
         error = device_register(&sdbg_host->dev);
 
diff --git a/drivers/scsi/scsi_ioctl.c b/drivers/scsi/scsi_ioctl.c
index dc1cfb2fd76b..9ed8e2cbac30 100644
--- a/drivers/scsi/scsi_ioctl.c
+++ b/drivers/scsi/scsi_ioctl.c
@@ -170,7 +170,8 @@ static int scsi_ioctl_get_pci(struct scsi_device *sdev, void __user *arg)
 
         if (!dev)
 		return -ENXIO;
-        return copy_to_user(arg, dev->bus_id, sizeof(dev->bus_id))? -EFAULT: 0;
+        return copy_to_user(arg,
+			    dev_name(dev), strlen(dev_name(dev)))? -EFAULT: 0;
 }
 
 
diff --git a/drivers/scsi/scsi_scan.c b/drivers/scsi/scsi_scan.c
index b14dc02c3ded..61141fb189fc 100644
--- a/drivers/scsi/scsi_scan.c
+++ b/drivers/scsi/scsi_scan.c
@@ -411,8 +411,7 @@ static struct scsi_target *scsi_alloc_target(struct device *parent,
 	device_initialize(dev);
 	starget->reap_ref = 1;
 	dev->parent = get_device(parent);
-	sprintf(dev->bus_id, "target%d:%d:%d",
-		shost->host_no, channel, id);
+	dev_set_name(dev, "target%d:%d:%d", shost->host_no, channel, id);
 #ifndef CONFIG_SYSFS_DEPRECATED
 	dev->bus = &scsi_bus_type;
 #endif
@@ -1010,7 +1009,7 @@ static int scsi_probe_and_add_lun(struct scsi_target *starget,
 		if (rescan || !scsi_device_created(sdev)) {
 			SCSI_LOG_SCAN_BUS(3, printk(KERN_INFO
 				"scsi scan: device exists on %s\n",
-				sdev->sdev_gendev.bus_id));
+				dev_name(&sdev->sdev_gendev)));
 			if (sdevp)
 				*sdevp = sdev;
 			else
@@ -1149,7 +1148,7 @@ static void scsi_sequential_lun_scan(struct scsi_target *starget,
 	struct Scsi_Host *shost = dev_to_shost(starget->dev.parent);
 
 	SCSI_LOG_SCAN_BUS(3, printk(KERN_INFO "scsi scan: Sequential scan of"
-				    "%s\n", starget->dev.bus_id));
+				    "%s\n", dev_name(&starget->dev)));
 
 	max_dev_lun = min(max_scsi_luns, shost->max_lun);
 	/*
diff --git a/drivers/scsi/scsi_sysfs.c b/drivers/scsi/scsi_sysfs.c
index 93c28f30bbd7..da63802cbf9d 100644
--- a/drivers/scsi/scsi_sysfs.c
+++ b/drivers/scsi/scsi_sysfs.c
@@ -1079,16 +1079,14 @@ void scsi_sysfs_device_initialize(struct scsi_device *sdev)
 	device_initialize(&sdev->sdev_gendev);
 	sdev->sdev_gendev.bus = &scsi_bus_type;
 	sdev->sdev_gendev.type = &scsi_dev_type;
-	sprintf(sdev->sdev_gendev.bus_id,"%d:%d:%d:%d",
-		sdev->host->host_no, sdev->channel, sdev->id,
-		sdev->lun);
-	
+	dev_set_name(&sdev->sdev_gendev, "%d:%d:%d:%d",
+		     sdev->host->host_no, sdev->channel, sdev->id, sdev->lun);
+
 	device_initialize(&sdev->sdev_dev);
 	sdev->sdev_dev.parent = &sdev->sdev_gendev;
 	sdev->sdev_dev.class = &sdev_class;
-	snprintf(sdev->sdev_dev.bus_id, BUS_ID_SIZE,
-		 "%d:%d:%d:%d", sdev->host->host_no,
-		 sdev->channel, sdev->id, sdev->lun);
+	dev_set_name(&sdev->sdev_dev, "%d:%d:%d:%d",
+		     sdev->host->host_no, sdev->channel, sdev->id, sdev->lun);
 	sdev->scsi_level = starget->scsi_level;
 	transport_setup_device(&sdev->sdev_gendev);
 	spin_lock_irqsave(shost->host_lock, flags);
diff --git a/drivers/scsi/scsi_transport_fc.c b/drivers/scsi/scsi_transport_fc.c
index 1e71abf0607a..c845853600a2 100644
--- a/drivers/scsi/scsi_transport_fc.c
+++ b/drivers/scsi/scsi_transport_fc.c
@@ -2486,8 +2486,8 @@ fc_rport_create(struct Scsi_Host *shost, int channel,
 	device_initialize(dev);			/* takes self reference */
 	dev->parent = get_device(&shost->shost_gendev); /* parent reference */
 	dev->release = fc_rport_dev_release;
-	sprintf(dev->bus_id, "rport-%d:%d-%d",
-		shost->host_no, channel, rport->number);
+	dev_set_name(dev, "rport-%d:%d-%d",
+		     shost->host_no, channel, rport->number);
 	transport_setup_device(dev);
 
 	error = device_add(dev);
@@ -3157,8 +3157,8 @@ fc_vport_setup(struct Scsi_Host *shost, int channel, struct device *pdev,
 	device_initialize(dev);			/* takes self reference */
 	dev->parent = get_device(pdev);		/* takes parent reference */
 	dev->release = fc_vport_dev_release;
-	sprintf(dev->bus_id, "vport-%d:%d-%d",
-		shost->host_no, channel, vport->number);
+	dev_set_name(dev, "vport-%d:%d-%d",
+		     shost->host_no, channel, vport->number);
 	transport_setup_device(dev);
 
 	error = device_add(dev);
@@ -3181,19 +3181,19 @@ fc_vport_setup(struct Scsi_Host *shost, int channel, struct device *pdev,
 	 */
 	if (pdev != &shost->shost_gendev) {
 		error = sysfs_create_link(&shost->shost_gendev.kobj,
-				 &dev->kobj, dev->bus_id);
+				 &dev->kobj, dev_name(dev));
 		if (error)
 			printk(KERN_ERR
 				"%s: Cannot create vport symlinks for "
 				"%s, err=%d\n",
-				__func__, dev->bus_id, error);
+				__func__, dev_name(dev), error);
 	}
 	spin_lock_irqsave(shost->host_lock, flags);
 	vport->flags &= ~FC_VPORT_CREATING;
 	spin_unlock_irqrestore(shost->host_lock, flags);
 
 	dev_printk(KERN_NOTICE, pdev,
-			"%s created via shost%d channel %d\n", dev->bus_id,
+			"%s created via shost%d channel %d\n", dev_name(dev),
 			shost->host_no, channel);
 
 	*ret_vport = vport;
@@ -3290,7 +3290,7 @@ fc_vport_terminate(struct fc_vport *vport)
 		return stat;
 
 	if (dev->parent != &shost->shost_gendev)
-		sysfs_remove_link(&shost->shost_gendev.kobj, dev->bus_id);
+		sysfs_remove_link(&shost->shost_gendev.kobj, dev_name(dev));
 	transport_remove_device(dev);
 	device_del(dev);
 	transport_destroy_device(dev);
@@ -3322,7 +3322,7 @@ fc_vport_sched_delete(struct work_struct *work)
 		dev_printk(KERN_ERR, vport->dev.parent,
 			"%s: %s could not be deleted created via "
 			"shost%d channel %d - error %d\n", __func__,
-			vport->dev.bus_id, vport->shost->host_no,
+			dev_name(&vport->dev), vport->shost->host_no,
 			vport->channel, stat);
 }
 
diff --git a/drivers/scsi/scsi_transport_iscsi.c b/drivers/scsi/scsi_transport_iscsi.c
index 4a803ebaf508..75c9297694cb 100644
--- a/drivers/scsi/scsi_transport_iscsi.c
+++ b/drivers/scsi/scsi_transport_iscsi.c
@@ -187,8 +187,7 @@ iscsi_create_endpoint(int dd_size)
 
 	ep->id = id;
 	ep->dev.class = &iscsi_endpoint_class;
-	snprintf(ep->dev.bus_id, BUS_ID_SIZE, "ep-%llu",
-		 (unsigned long long) id);
+	dev_set_name(&ep->dev, "ep-%llu", (unsigned long long) id);
 	err = device_register(&ep->dev);
         if (err)
                 goto free_ep;
@@ -724,8 +723,7 @@ int iscsi_add_session(struct iscsi_cls_session *session, unsigned int target_id)
 	}
 	session->target_id = id;
 
-	snprintf(session->dev.bus_id, BUS_ID_SIZE, "session%u",
-		 session->sid);
+	dev_set_name(&session->dev, "session%u", session->sid);
 	err = device_add(&session->dev);
 	if (err) {
 		iscsi_cls_session_printk(KERN_ERR, session,
@@ -898,8 +896,7 @@ iscsi_create_conn(struct iscsi_cls_session *session, int dd_size, uint32_t cid)
 	if (!get_device(&session->dev))
 		goto free_conn;
 
-	snprintf(conn->dev.bus_id, BUS_ID_SIZE, "connection%d:%u",
-		 session->sid, cid);
+	dev_set_name(&conn->dev, "connection%d:%u", session->sid, cid);
 	conn->dev.parent = &session->dev;
 	conn->dev.release = iscsi_conn_release;
 	err = device_register(&conn->dev);
@@ -1816,7 +1813,7 @@ iscsi_register_transport(struct iscsi_transport *tt)
 		priv->t.create_work_queue = 1;
 
 	priv->dev.class = &iscsi_transport_class;
-	snprintf(priv->dev.bus_id, BUS_ID_SIZE, "%s", tt->name);
+	dev_set_name(&priv->dev, "%s", tt->name);
 	err = device_register(&priv->dev);
 	if (err)
 		goto free_priv;
diff --git a/drivers/scsi/scsi_transport_sas.c b/drivers/scsi/scsi_transport_sas.c
index 366609386be1..50988cbf7b2d 100644
--- a/drivers/scsi/scsi_transport_sas.c
+++ b/drivers/scsi/scsi_transport_sas.c
@@ -207,7 +207,7 @@ static int sas_bsg_initialize(struct Scsi_Host *shost, struct sas_rphy *rphy)
 	struct request_queue *q;
 	int error;
 	struct device *dev;
-	char namebuf[BUS_ID_SIZE];
+	char namebuf[20];
 	const char *name;
 	void (*release)(struct device *);
 
@@ -219,7 +219,7 @@ static int sas_bsg_initialize(struct Scsi_Host *shost, struct sas_rphy *rphy)
 	if (rphy) {
 		q = blk_init_queue(sas_non_host_smp_request, NULL);
 		dev = &rphy->dev;
-		name = dev->bus_id;
+		name = dev_name(dev);
 		release = NULL;
 	} else {
 		q = blk_init_queue(sas_host_smp_request, NULL);
@@ -629,10 +629,10 @@ struct sas_phy *sas_phy_alloc(struct device *parent, int number)
 	INIT_LIST_HEAD(&phy->port_siblings);
 	if (scsi_is_sas_expander_device(parent)) {
 		struct sas_rphy *rphy = dev_to_rphy(parent);
-		sprintf(phy->dev.bus_id, "phy-%d:%d:%d", shost->host_no,
+		dev_set_name(&phy->dev, "phy-%d:%d:%d", shost->host_no,
 			rphy->scsi_target_id, number);
 	} else
-		sprintf(phy->dev.bus_id, "phy-%d:%d", shost->host_no, number);
+		dev_set_name(&phy->dev, "phy-%d:%d", shost->host_no, number);
 
 	transport_setup_device(&phy->dev);
 
@@ -770,7 +770,7 @@ static void sas_port_create_link(struct sas_port *port,
 	int res;
 
 	res = sysfs_create_link(&port->dev.kobj, &phy->dev.kobj,
-				phy->dev.bus_id);
+				dev_name(&phy->dev));
 	if (res)
 		goto err;
 	res = sysfs_create_link(&phy->dev.kobj, &port->dev.kobj, "port");
@@ -785,7 +785,7 @@ err:
 static void sas_port_delete_link(struct sas_port *port,
 				 struct sas_phy *phy)
 {
-	sysfs_remove_link(&port->dev.kobj, phy->dev.bus_id);
+	sysfs_remove_link(&port->dev.kobj, dev_name(&phy->dev));
 	sysfs_remove_link(&phy->dev.kobj, "port");
 }
 
@@ -821,11 +821,11 @@ struct sas_port *sas_port_alloc(struct device *parent, int port_id)
 
 	if (scsi_is_sas_expander_device(parent)) {
 		struct sas_rphy *rphy = dev_to_rphy(parent);
-		sprintf(port->dev.bus_id, "port-%d:%d:%d", shost->host_no,
-			rphy->scsi_target_id, port->port_identifier);
+		dev_set_name(&port->dev, "port-%d:%d:%d", shost->host_no,
+			     rphy->scsi_target_id, port->port_identifier);
 	} else
-		sprintf(port->dev.bus_id, "port-%d:%d", shost->host_no,
-			port->port_identifier);
+		dev_set_name(&port->dev, "port-%d:%d", shost->host_no,
+			     port->port_identifier);
 
 	transport_setup_device(&port->dev);
 
@@ -935,7 +935,7 @@ void sas_port_delete(struct sas_port *port)
 	if (port->is_backlink) {
 		struct device *parent = port->dev.parent;
 
-		sysfs_remove_link(&port->dev.kobj, parent->bus_id);
+		sysfs_remove_link(&port->dev.kobj, dev_name(parent));
 		port->is_backlink = 0;
 	}
 
@@ -984,7 +984,8 @@ void sas_port_add_phy(struct sas_port *port, struct sas_phy *phy)
 		/* If this trips, you added a phy that was already
 		 * part of a different port */
 		if (unlikely(tmp != phy)) {
-			dev_printk(KERN_ERR, &port->dev, "trying to add phy %s fails: it's already part of another port\n", phy->dev.bus_id);
+			dev_printk(KERN_ERR, &port->dev, "trying to add phy %s fails: it's already part of another port\n",
+				   dev_name(&phy->dev));
 			BUG();
 		}
 	} else {
@@ -1023,7 +1024,7 @@ void sas_port_mark_backlink(struct sas_port *port)
 		return;
 	port->is_backlink = 1;
 	res = sysfs_create_link(&port->dev.kobj, &parent->kobj,
-				parent->bus_id);
+				dev_name(parent));
 	if (res)
 		goto err;
 	return;
@@ -1367,11 +1368,12 @@ struct sas_rphy *sas_end_device_alloc(struct sas_port *parent)
 	rdev->rphy.dev.release = sas_end_device_release;
 	if (scsi_is_sas_expander_device(parent->dev.parent)) {
 		struct sas_rphy *rphy = dev_to_rphy(parent->dev.parent);
-		sprintf(rdev->rphy.dev.bus_id, "end_device-%d:%d:%d",
-			shost->host_no, rphy->scsi_target_id, parent->port_identifier);
+		dev_set_name(&rdev->rphy.dev, "end_device-%d:%d:%d",
+			     shost->host_no, rphy->scsi_target_id,
+			     parent->port_identifier);
 	} else
-		sprintf(rdev->rphy.dev.bus_id, "end_device-%d:%d",
-			shost->host_no, parent->port_identifier);
+		dev_set_name(&rdev->rphy.dev, "end_device-%d:%d",
+			     shost->host_no, parent->port_identifier);
 	rdev->rphy.identify.device_type = SAS_END_DEVICE;
 	sas_rphy_initialize(&rdev->rphy);
 	transport_setup_device(&rdev->rphy.dev);
@@ -1411,8 +1413,8 @@ struct sas_rphy *sas_expander_alloc(struct sas_port *parent,
 	mutex_lock(&sas_host->lock);
 	rdev->rphy.scsi_target_id = sas_host->next_expander_id++;
 	mutex_unlock(&sas_host->lock);
-	sprintf(rdev->rphy.dev.bus_id, "expander-%d:%d",
-		shost->host_no, rdev->rphy.scsi_target_id);
+	dev_set_name(&rdev->rphy.dev, "expander-%d:%d",
+		     shost->host_no, rdev->rphy.scsi_target_id);
 	rdev->rphy.identify.device_type = type;
 	sas_rphy_initialize(&rdev->rphy);
 	transport_setup_device(&rdev->rphy.dev);
@@ -1445,7 +1447,7 @@ int sas_rphy_add(struct sas_rphy *rphy)
 	transport_add_device(&rphy->dev);
 	transport_configure_device(&rphy->dev);
 	if (sas_bsg_initialize(shost, rphy))
-		printk("fail to a bsg device %s\n", rphy->dev.bus_id);
+		printk("fail to a bsg device %s\n", dev_name(&rphy->dev));
 
 
 	mutex_lock(&sas_host->lock);
diff --git a/drivers/scsi/scsi_transport_srp.c b/drivers/scsi/scsi_transport_srp.c
index 8a7af951d98a..21a045e0559f 100644
--- a/drivers/scsi/scsi_transport_srp.c
+++ b/drivers/scsi/scsi_transport_srp.c
@@ -212,7 +212,7 @@ struct srp_rport *srp_rport_add(struct Scsi_Host *shost,
 	rport->roles = ids->roles;
 
 	id = atomic_inc_return(&to_srp_host_attrs(shost)->next_port_id);
-	sprintf(rport->dev.bus_id, "port-%d:%d", shost->host_no, id);
+	dev_set_name(&rport->dev, "port-%d:%d", shost->host_no, id);
 
 	transport_setup_device(&rport->dev);
 
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index c9e1242eaf25..4c8de2910999 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -757,7 +757,7 @@ static int sd_ioctl(struct block_device *bdev, fmode_t mode,
 	 * access to the device is prohibited.
 	 */
 	error = scsi_nonblockable_ioctl(sdp, cmd, p,
-					(mode & FMODE_NDELAY_NOW) != 0);
+					(mode & FMODE_NDELAY) != 0);
 	if (!scsi_block_when_processing_errors(sdp) || !error)
 		return error;
 
@@ -1875,7 +1875,7 @@ static int sd_probe(struct device *dev)
 	device_initialize(&sdkp->dev);
 	sdkp->dev.parent = &sdp->sdev_gendev;
 	sdkp->dev.class = &sd_disk_class;
-	strncpy(sdkp->dev.bus_id, sdp->sdev_gendev.bus_id, BUS_ID_SIZE);
+	dev_set_name(&sdkp->dev, dev_name(&sdp->sdev_gendev));
 
 	if (device_add(&sdkp->dev))
 		goto out_free_index;
diff --git a/drivers/scsi/ses.c b/drivers/scsi/ses.c
index 1bcf3c33d7ff..3b77b3b9c11e 100644
--- a/drivers/scsi/ses.c
+++ b/drivers/scsi/ses.c
@@ -525,7 +525,7 @@ static int ses_intf_add(struct device *cdev,
 	if (!scomp)
 		goto err_free;
 
-	edev = enclosure_register(cdev->parent, sdev->sdev_gendev.bus_id,
+	edev = enclosure_register(cdev->parent, dev_name(&sdev->sdev_gendev),
 				  components, &ses_enclosure_callbacks);
 	if (IS_ERR(edev)) {
 		err = PTR_ERR(edev);
diff --git a/drivers/scsi/sr.c b/drivers/scsi/sr.c
index 62b6633e3a97..45b66b98a516 100644
--- a/drivers/scsi/sr.c
+++ b/drivers/scsi/sr.c
@@ -521,7 +521,7 @@ static int sr_block_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd,
 	 * if it doesn't recognise the ioctl
 	 */
 	ret = scsi_nonblockable_ioctl(sdev, cmd, argp,
-					(mode & FMODE_NDELAY_NOW) != 0);
+					(mode & FMODE_NDELAY) != 0);
 	if (ret != -ENODEV)
 		return ret;
 	return scsi_ioctl(sdev, cmd, argp);
diff --git a/drivers/serial/amba-pl010.c b/drivers/serial/amba-pl010.c
index 71562689116f..e3a5ad5ef1d6 100644
--- a/drivers/serial/amba-pl010.c
+++ b/drivers/serial/amba-pl010.c
@@ -692,7 +692,7 @@ static int pl010_probe(struct amba_device *dev, void *id)
 		goto free;
 	}
 
-	uap->clk = clk_get(&dev->dev, "UARTCLK");
+	uap->clk = clk_get(&dev->dev, NULL);
 	if (IS_ERR(uap->clk)) {
 		ret = PTR_ERR(uap->clk);
 		goto unmap;
diff --git a/drivers/serial/amba-pl011.c b/drivers/serial/amba-pl011.c
index b7180046f8db..8b2b9700f3e4 100644
--- a/drivers/serial/amba-pl011.c
+++ b/drivers/serial/amba-pl011.c
@@ -756,7 +756,7 @@ static int pl011_probe(struct amba_device *dev, void *id)
 		goto free;
 	}
 
-	uap->clk = clk_get(&dev->dev, "UARTCLK");
+	uap->clk = clk_get(&dev->dev, NULL);
 	if (IS_ERR(uap->clk)) {
 		ret = PTR_ERR(uap->clk);
 		goto unmap;
diff --git a/drivers/serial/mpc52xx_uart.c b/drivers/serial/mpc52xx_uart.c
index 6117d3db0b66..28c00c3d58f5 100644
--- a/drivers/serial/mpc52xx_uart.c
+++ b/drivers/serial/mpc52xx_uart.c
@@ -591,8 +591,8 @@ mpc52xx_uart_set_termios(struct uart_port *port, struct ktermios *new,
 	/* Update the per-port timeout */
 	uart_update_timeout(port, new->c_cflag, baud);
 
-	/* Do our best to flush TX & RX, so we don't loose anything */
-	/* But we don't wait indefinitly ! */
+	/* Do our best to flush TX & RX, so we don't lose anything */
+	/* But we don't wait indefinitely ! */
 	j = 5000000;	/* Maximum wait */
 	/* FIXME Can't receive chars since set_termios might be called at early
 	 * boot for the console, all stuff is not yet ready to receive at that
diff --git a/drivers/serial/pmac_zilog.c b/drivers/serial/pmac_zilog.c
index 317b061f7641..ad3488504010 100644
--- a/drivers/serial/pmac_zilog.c
+++ b/drivers/serial/pmac_zilog.c
@@ -1383,6 +1383,29 @@ static int pmz_verify_port(struct uart_port *port, struct serial_struct *ser)
 	return -EINVAL;
 }
 
+#ifdef CONFIG_CONSOLE_POLL
+
+static int pmz_poll_get_char(struct uart_port *port)
+{
+	struct uart_pmac_port *uap = (struct uart_pmac_port *)port;
+
+	while ((read_zsreg(uap, R0) & Rx_CH_AV) == 0)
+		udelay(5);
+	return read_zsdata(uap);
+}
+
+static void pmz_poll_put_char(struct uart_port *port, unsigned char c)
+{
+	struct uart_pmac_port *uap = (struct uart_pmac_port *)port;
+
+	/* Wait for the transmit buffer to empty. */
+	while ((read_zsreg(uap, R0) & Tx_BUF_EMP) == 0)
+		udelay(5);
+	write_zsdata(uap, c);
+}
+
+#endif
+
 static struct uart_ops pmz_pops = {
 	.tx_empty	=	pmz_tx_empty,
 	.set_mctrl	=	pmz_set_mctrl,
@@ -1400,6 +1423,10 @@ static struct uart_ops pmz_pops = {
 	.request_port	=	pmz_request_port,
 	.config_port	=	pmz_config_port,
 	.verify_port	=	pmz_verify_port,
+#ifdef CONFIG_CONSOLE_POLL
+	.poll_get_char	=	pmz_poll_get_char,
+	.poll_put_char	=	pmz_poll_put_char,
+#endif
 };
 
 /*
diff --git a/drivers/serial/pxa.c b/drivers/serial/pxa.c
index abc00be55433..f6e3b86bb0be 100644
--- a/drivers/serial/pxa.c
+++ b/drivers/serial/pxa.c
@@ -48,6 +48,7 @@
 #include <mach/hardware.h>
 #include <asm/irq.h>
 #include <mach/pxa-regs.h>
+#include <mach/regs-uart.h>
 
 
 struct uart_pxa_port {
@@ -766,7 +767,7 @@ static int serial_pxa_probe(struct platform_device *dev)
 	if (!sport)
 		return -ENOMEM;
 
-	sport->clk = clk_get(&dev->dev, "UARTCLK");
+	sport->clk = clk_get(&dev->dev, NULL);
 	if (IS_ERR(sport->clk)) {
 		ret = PTR_ERR(sport->clk);
 		goto err_free;
diff --git a/drivers/serial/serial_core.c b/drivers/serial/serial_core.c
index 874786a11fe9..1b7a33b93f7d 100644
--- a/drivers/serial/serial_core.c
+++ b/drivers/serial/serial_core.c
@@ -2049,7 +2049,7 @@ int uart_suspend_port(struct uart_driver *drv, struct uart_port *port)
 		if (!tries)
 			printk(KERN_ERR "%s%s%s%d: Unable to drain "
 					"transmitter\n",
-			       port->dev ? port->dev->bus_id : "",
+			       port->dev ? dev_name(port->dev) : "",
 			       port->dev ? ": " : "",
 			       drv->dev_name,
 			       drv->tty_driver->name_base + port->line);
@@ -2175,7 +2175,7 @@ uart_report_port(struct uart_driver *drv, struct uart_port *port)
 	}
 
 	printk(KERN_INFO "%s%s%s%d at %s (irq = %d) is a %s\n",
-	       port->dev ? port->dev->bus_id : "",
+	       port->dev ? dev_name(port->dev) : "",
 	       port->dev ? ": " : "",
 	       drv->dev_name,
 	       drv->tty_driver->name_base + port->line,
diff --git a/drivers/serial/serial_lh7a40x.c b/drivers/serial/serial_lh7a40x.c
index 61dc8b3daa26..a7bf024a8286 100644
--- a/drivers/serial/serial_lh7a40x.c
+++ b/drivers/serial/serial_lh7a40x.c
@@ -41,9 +41,10 @@
 #include <linux/tty_flip.h>
 #include <linux/serial_core.h>
 #include <linux/serial.h>
+#include <linux/io.h>
 
-#include <asm/io.h>
 #include <asm/irq.h>
+#include <mach/hardware.h>
 
 #define DEV_MAJOR	204
 #define DEV_MINOR	16
diff --git a/drivers/serial/sh-sci.c b/drivers/serial/sh-sci.c
index 165fc010978c..31532e97fb96 100644
--- a/drivers/serial/sh-sci.c
+++ b/drivers/serial/sh-sci.c
@@ -101,6 +101,12 @@ static void sci_stop_tx(struct uart_port *port);
 static struct sci_port sci_ports[SCI_NPORTS];
 static struct uart_driver sci_uart_driver;
 
+static inline struct sci_port *
+to_sci_port(struct uart_port *uart)
+{
+	return container_of(uart, struct sci_port, port);
+}
+
 #if defined(CONFIG_SERIAL_SH_SCI_CONSOLE) && \
     defined(CONFIG_SH_STANDARD_BIOS) || defined(CONFIG_SH_KGDB)
 static inline void handle_error(struct uart_port *port)
@@ -124,7 +130,8 @@ static int get_char(struct uart_port *port)
 		}
 	} while (!(status & SCxSR_RDxF(port)));
 	c = sci_in(port, SCxRDR);
-	sci_in(port, SCxSR);            /* Dummy read */
+	/* Dummy read */
+	sci_in(port, SCxSR);
 	sci_out(port, SCxSR, SCxSR_RDxF_CLEAR(port));
 	spin_unlock_irqrestore(&port->lock, flags);
 
@@ -161,7 +168,7 @@ static void put_string(struct sci_port *sci_port, const char *buffer, int count)
 
 #if defined(CONFIG_SH_STANDARD_BIOS) || defined(CONFIG_SH_KGDB)
 	int checksum;
-	int usegdb=0;
+	int usegdb = 0;
 
 #ifdef CONFIG_SH_STANDARD_BIOS
 	/* This call only does a trap the first time it is
@@ -181,7 +188,8 @@ static void put_string(struct sci_port *sci_port, const char *buffer, int count)
 		put_char(port, 'O'); /* 'O'utput to console */
 		checksum = 'O';
 
-		for (i=0; i<count; i++) { /* Don't use run length encoding */
+		/* Don't use run length encoding */
+		for (i = 0; i < count; i++) {
 			int h, l;
 
 			c = *p++;
@@ -197,7 +205,7 @@ static void put_string(struct sci_port *sci_port, const char *buffer, int count)
 	    } while  (get_char(port) != '+');
 	} else
 #endif /* CONFIG_SH_STANDARD_BIOS || CONFIG_SH_KGDB */
-	for (i=0; i<count; i++) {
+	for (i = 0; i < count; i++) {
 		if (*p == 10)
 			put_char(port, '\r');
 		put_char(port, *p++);
@@ -208,35 +216,34 @@ static void put_string(struct sci_port *sci_port, const char *buffer, int count)
 #ifdef CONFIG_SH_KGDB
 static int kgdb_sci_getchar(void)
 {
-        int c;
+	int c;
 
-        /* Keep trying to read a character, this could be neater */
-        while ((c = get_char(&kgdb_sci_port->port)) < 0)
+	/* Keep trying to read a character, this could be neater */
+	while ((c = get_char(&kgdb_sci_port->port)) < 0)
 		cpu_relax();
 
-        return c;
+	return c;
 }
 
 static inline void kgdb_sci_putchar(int c)
 {
-        put_char(&kgdb_sci_port->port, c);
+	put_char(&kgdb_sci_port->port, c);
 }
 #endif /* CONFIG_SH_KGDB */
 
 #if defined(__H8300S__)
 enum { sci_disable, sci_enable };
 
-static void h8300_sci_config(struct uart_port* port, unsigned int ctrl)
+static void h8300_sci_config(struct uart_port *port, unsigned int ctrl)
 {
-	volatile unsigned char *mstpcrl=(volatile unsigned char *)MSTPCRL;
+	volatile unsigned char *mstpcrl = (volatile unsigned char *)MSTPCRL;
 	int ch = (port->mapbase  - SMR0) >> 3;
 	unsigned char mask = 1 << (ch+1);
 
-	if (ctrl == sci_disable) {
+	if (ctrl == sci_disable)
 		*mstpcrl |= mask;
-	} else {
+	else
 		*mstpcrl &= ~mask;
-	}
 }
 
 static inline void h8300_sci_enable(struct uart_port *port)
@@ -251,7 +258,7 @@ static inline void h8300_sci_disable(struct uart_port *port)
 #endif
 
 #if defined(__H8300H__) || defined(__H8300S__)
-static void sci_init_pins_sci(struct uart_port* port, unsigned int cflag)
+static void sci_init_pins_sci(struct uart_port *port, unsigned int cflag)
 {
 	int ch = (port->mapbase - SMR0) >> 3;
 
@@ -285,14 +292,13 @@ static void sci_init_pins_irda(struct uart_port *port, unsigned int cflag)
 #endif
 
 #if defined(CONFIG_CPU_SUBTYPE_SH7710) || defined(CONFIG_CPU_SUBTYPE_SH7712)
-static void sci_init_pins_scif(struct uart_port* port, unsigned int cflag)
+static void sci_init_pins_scif(struct uart_port *port, unsigned int cflag)
 {
 	unsigned int fcr_val = 0;
 
 	set_sh771x_scif_pfc(port);
-	if (cflag & CRTSCTS) {
+	if (cflag & CRTSCTS)
 		fcr_val |= SCFCR_MCE;
-	}
 	sci_out(port, SCFCR, fcr_val);
 }
 #elif defined(CONFIG_CPU_SUBTYPE_SH7720) || defined(CONFIG_CPU_SUBTYPE_SH7721)
@@ -419,18 +425,26 @@ static inline int scif_rxroom(struct uart_port *port)
 #elif defined(CONFIG_CPU_SUBTYPE_SH7763)
 static inline int scif_txroom(struct uart_port *port)
 {
-	if((port->mapbase == 0xffe00000) || (port->mapbase == 0xffe08000)) /* SCIF0/1*/
+	if ((port->mapbase == 0xffe00000) ||
+	    (port->mapbase == 0xffe08000)) {
+		/* SCIF0/1*/
 		return SCIF_TXROOM_MAX - (sci_in(port, SCTFDR) & 0xff);
-	else /* SCIF2 */
+	} else {
+		/* SCIF2 */
 		return SCIF2_TXROOM_MAX - (sci_in(port, SCFDR) >> 8);
+	}
 }
 
 static inline int scif_rxroom(struct uart_port *port)
 {
-	if((port->mapbase == 0xffe00000) || (port->mapbase == 0xffe08000)) /* SCIF0/1*/
+	if ((port->mapbase == 0xffe00000) ||
+	    (port->mapbase == 0xffe08000)) {
+		/* SCIF0/1*/
 		return sci_in(port, SCRFDR) & 0xff;
-	else /* SCIF2 */
+	} else {
+		/* SCIF2 */
 		return sci_in(port, SCFDR) & SCIF2_RFDC_MASK;
+	}
 }
 #else
 static inline int scif_txroom(struct uart_port *port)
@@ -446,12 +460,12 @@ static inline int scif_rxroom(struct uart_port *port)
 
 static inline int sci_txroom(struct uart_port *port)
 {
-	return ((sci_in(port, SCxSR) & SCI_TDRE) != 0);
+	return (sci_in(port, SCxSR) & SCI_TDRE) != 0;
 }
 
 static inline int sci_rxroom(struct uart_port *port)
 {
-	return ((sci_in(port, SCxSR) & SCxSR_RDxF(port)) != 0);
+	return (sci_in(port, SCxSR) & SCxSR_RDxF(port)) != 0;
 }
 
 /* ********************************************************************** *
@@ -469,11 +483,10 @@ static void sci_transmit_chars(struct uart_port *port)
 	status = sci_in(port, SCxSR);
 	if (!(status & SCxSR_TDxE(port))) {
 		ctrl = sci_in(port, SCSCR);
-		if (uart_circ_empty(xmit)) {
+		if (uart_circ_empty(xmit))
 			ctrl &= ~SCI_CTRL_FLAGS_TIE;
-		} else {
+		else
 			ctrl |= SCI_CTRL_FLAGS_TIE;
-		}
 		sci_out(port, SCSCR, ctrl);
 		return;
 	}
@@ -521,11 +534,11 @@ static void sci_transmit_chars(struct uart_port *port)
 }
 
 /* On SH3, SCIF may read end-of-break as a space->mark char */
-#define STEPFN(c)  ({int __c=(c); (((__c-1)|(__c)) == -1); })
+#define STEPFN(c)  ({int __c = (c); (((__c-1)|(__c)) == -1); })
 
 static inline void sci_receive_chars(struct uart_port *port)
 {
-	struct sci_port *sci_port = (struct sci_port *)port;
+	struct sci_port *sci_port = to_sci_port(port);
 	struct tty_struct *tty = port->info->port.tty;
 	int i, count, copied = 0;
 	unsigned short status;
@@ -550,13 +563,13 @@ static inline void sci_receive_chars(struct uart_port *port)
 
 		if (port->type == PORT_SCI) {
 			char c = sci_in(port, SCxRDR);
-			if (uart_handle_sysrq_char(port, c) || sci_port->break_flag)
+			if (uart_handle_sysrq_char(port, c) ||
+			    sci_port->break_flag)
 				count = 0;
-			else {
+			else
 				tty_insert_flip_char(tty, c, TTY_NORMAL);
-			}
 		} else {
-			for (i=0; i<count; i++) {
+			for (i = 0; i < count; i++) {
 				char c = sci_in(port, SCxRDR);
 				status = sci_in(port, SCxSR);
 #if defined(CONFIG_CPU_SH3)
@@ -657,7 +670,7 @@ static inline int sci_handle_errors(struct uart_port *port)
 	if (status & SCxSR_FER(port)) {
 		if (sci_rxd_in(port) == 0) {
 			/* Notify of BREAK */
-			struct sci_port *sci_port = (struct sci_port *)port;
+			struct sci_port *sci_port = to_sci_port(port);
 
 			if (!sci_port->break_flag) {
 				sci_port->break_flag = 1;
@@ -666,10 +679,11 @@ static inline int sci_handle_errors(struct uart_port *port)
 				/* Do sysrq handling. */
 				if (uart_handle_break(port))
 					return 0;
-			        pr_debug("sci: BREAK detected\n");
+				pr_debug("sci: BREAK detected\n");
 				if (tty_insert_flip_char(tty, 0, TTY_BREAK))
-				        copied++;
-                       }
+					copied++;
+			}
+
 		} else {
 			/* frame error */
 			if (tty_insert_flip_char(tty, 0, TTY_FRAME))
@@ -764,7 +778,7 @@ static irqreturn_t sci_er_interrupt(int irq, void *ptr)
 		}
 	} else {
 #if defined(SCIF_ORER)
-		if((sci_in(port, SCLSR) & SCIF_ORER) != 0) {
+		if ((sci_in(port, SCLSR) & SCIF_ORER) != 0) {
 			struct tty_struct *tty = port->info->port.tty;
 
 			sci_out(port, SCLSR, 0);
@@ -801,8 +815,8 @@ static irqreturn_t sci_mpxed_interrupt(int irq, void *ptr)
 	struct uart_port *port = ptr;
 	irqreturn_t ret = IRQ_NONE;
 
-        ssr_status = sci_in(port,SCxSR);
-        scr_status = sci_in(port,SCSCR);
+	ssr_status = sci_in(port, SCxSR);
+	scr_status = sci_in(port, SCSCR);
 
 	/* Tx Interrupt */
 	if ((ssr_status & 0x0020) && (scr_status & SCI_CTRL_FLAGS_TIE))
@@ -832,7 +846,7 @@ static int sci_notifier(struct notifier_block *self,
 	int i;
 
 	if ((phase == CPUFREQ_POSTCHANGE) ||
-	    (phase == CPUFREQ_RESUMECHANGE)){
+	    (phase == CPUFREQ_RESUMECHANGE)) {
 		for (i = 0; i < SCI_NPORTS; i++) {
 			struct uart_port *port = &sci_ports[i].port;
 			struct clk *clk;
@@ -904,12 +918,12 @@ static void sci_free_irq(struct sci_port *port)
 {
 	int i;
 
-        if (port->irqs[0] == port->irqs[1]) {
-                if (!port->irqs[0])
-                        printk("sci: sci_free_irq error\n");
+	if (port->irqs[0] == port->irqs[1]) {
+		if (!port->irqs[0])
+			printk(KERN_ERR "sci: sci_free_irq error\n");
 		else
-                        free_irq(port->irqs[0], port);
-        } else {
+			free_irq(port->irqs[0], port);
+	} else {
 		for (i = 0; i < ARRAY_SIZE(port->irqs); i++) {
 			if (!port->irqs[i])
 				continue;
@@ -1060,12 +1074,12 @@ static void sci_set_termios(struct uart_port *port, struct ktermios *termios,
 	sci_out(port, SCSMR, smr_val);
 
 	if (t > 0) {
-		if(t >= 256) {
+		if (t >= 256) {
 			sci_out(port, SCSMR, (sci_in(port, SCSMR) & ~3) | 1);
 			t >>= 2;
-		} else {
+		} else
 			sci_out(port, SCSMR, sci_in(port, SCSMR) & ~3);
-		}
+
 		sci_out(port, SCBRR, t);
 		udelay((1000000+(baud-1)) / baud); /* Wait one bit interval */
 	}
@@ -1076,16 +1090,20 @@ static void sci_set_termios(struct uart_port *port, struct ktermios *termios,
 	sci_out(port, SCSCR, SCSCR_INIT(port));
 
 	if ((termios->c_cflag & CREAD) != 0)
-              sci_start_rx(port,0);
+		sci_start_rx(port, 0);
 }
 
 static const char *sci_type(struct uart_port *port)
 {
 	switch (port->type) {
-		case PORT_SCI:	return "sci";
-		case PORT_SCIF:	return "scif";
-		case PORT_IRDA: return "irda";
-		case PORT_SCIFA:	return "scifa";
+	case PORT_IRDA:
+		return "irda";
+	case PORT_SCI:
+		return "sci";
+	case PORT_SCIF:
+		return "scif";
+	case PORT_SCIFA:
+		return "scifa";
 	}
 
 	return NULL;
@@ -1387,9 +1405,9 @@ console_initcall(kgdb_console_init);
 #endif /* CONFIG_SH_KGDB_CONSOLE */
 
 #if defined(CONFIG_SH_KGDB_CONSOLE)
-#define SCI_CONSOLE	&kgdb_console
+#define SCI_CONSOLE	(&kgdb_console)
 #elif defined(CONFIG_SERIAL_SH_SCI_CONSOLE)
-#define SCI_CONSOLE	&serial_console
+#define SCI_CONSOLE	(&serial_console)
 #else
 #define SCI_CONSOLE	0
 #endif
diff --git a/drivers/serial/sh-sci.h b/drivers/serial/sh-sci.h
index 9f33b064172e..6da755d63529 100644
--- a/drivers/serial/sh-sci.h
+++ b/drivers/serial/sh-sci.h
@@ -133,13 +133,20 @@
 # define SCSPTR5	0xffef0024	/* 16 bit SCIF */
 # define SCIF_OPER	0x0001		/* Overrun error bit */
 # define SCSCR_INIT(port)	0x3a	/* TIE=0,RIE=0,TE=1,RE=1,REIE=1 */
-#elif defined(CONFIG_CPU_SUBTYPE_SH7203) || \
+#elif defined(CONFIG_CPU_SUBTYPE_SH7201) || \
+      defined(CONFIG_CPU_SUBTYPE_SH7203) || \
       defined(CONFIG_CPU_SUBTYPE_SH7206) || \
       defined(CONFIG_CPU_SUBTYPE_SH7263)
 # define SCSPTR0 0xfffe8020 /* 16 bit SCIF */
 # define SCSPTR1 0xfffe8820 /* 16 bit SCIF */
 # define SCSPTR2 0xfffe9020 /* 16 bit SCIF */
 # define SCSPTR3 0xfffe9820 /* 16 bit SCIF */
+# if defined(CONFIG_CPU_SUBTYPE_SH7201)
+#  define SCSPTR4 0xfffeA020 /* 16 bit SCIF */
+#  define SCSPTR5 0xfffeA820 /* 16 bit SCIF */
+#  define SCSPTR6 0xfffeB020 /* 16 bit SCIF */
+#  define SCSPTR7 0xfffeB820 /* 16 bit SCIF */
+# endif
 # define SCSCR_INIT(port)	0x38 /* TIE=0,RIE=0,TE=1,RE=1,REIE=1 */
 #elif defined(CONFIG_CPU_SUBTYPE_SH7619)
 # define SCSPTR0 0xf8400020 /* 16 bit SCIF */
@@ -664,7 +671,8 @@ static inline int sci_rxd_in(struct uart_port *port)
 		return ctrl_inw(SCSPTR5) & 0x0001 ? 1 : 0; /* SCIF */
 	return 1;
 }
-#elif defined(CONFIG_CPU_SUBTYPE_SH7203) || \
+#elif defined(CONFIG_CPU_SUBTYPE_SH7201) || \
+      defined(CONFIG_CPU_SUBTYPE_SH7203) || \
       defined(CONFIG_CPU_SUBTYPE_SH7206) || \
       defined(CONFIG_CPU_SUBTYPE_SH7263)
 static inline int sci_rxd_in(struct uart_port *port)
@@ -677,6 +685,16 @@ static inline int sci_rxd_in(struct uart_port *port)
 		return ctrl_inw(SCSPTR2) & 0x0001 ? 1 : 0; /* SCIF */
 	if (port->mapbase == 0xfffe9800)
 		return ctrl_inw(SCSPTR3) & 0x0001 ? 1 : 0; /* SCIF */
+#if defined(CONFIG_CPU_SUBTYPE_SH7201)
+	if (port->mapbase == 0xfffeA000)
+		return ctrl_inw(SCSPTR0) & 0x0001 ? 1 : 0; /* SCIF */
+	if (port->mapbase == 0xfffeA800)
+		return ctrl_inw(SCSPTR1) & 0x0001 ? 1 : 0; /* SCIF */
+	if (port->mapbase == 0xfffeB000)
+		return ctrl_inw(SCSPTR2) & 0x0001 ? 1 : 0; /* SCIF */
+	if (port->mapbase == 0xfffeB800)
+		return ctrl_inw(SCSPTR3) & 0x0001 ? 1 : 0; /* SCIF */
+#endif
 	return 1;
 }
 #elif defined(CONFIG_CPU_SUBTYPE_SH7619)
diff --git a/drivers/spi/pxa2xx_spi.c b/drivers/spi/pxa2xx_spi.c
index cf12f2d84be2..6104f461a3cd 100644
--- a/drivers/spi/pxa2xx_spi.c
+++ b/drivers/spi/pxa2xx_spi.c
@@ -32,8 +32,8 @@
 #include <asm/io.h>
 #include <asm/irq.h>
 #include <asm/delay.h>
-#include <asm/dma.h>
 
+#include <mach/dma.h>
 #include <mach/hardware.h>
 #include <mach/pxa-regs.h>
 #include <mach/regs-ssp.h>
diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c
index 3734dc9708e1..643908b74bc0 100644
--- a/drivers/spi/spi.c
+++ b/drivers/spi/spi.c
@@ -47,7 +47,7 @@ modalias_show(struct device *dev, struct device_attribute *a, char *buf)
 {
 	const struct spi_device	*spi = to_spi_device(dev);
 
-	return snprintf(buf, BUS_ID_SIZE + 1, "%s\n", spi->modalias);
+	return sprintf(buf, "%s\n", spi->modalias);
 }
 
 static struct device_attribute spi_dev_attrs[] = {
@@ -63,7 +63,7 @@ static int spi_match_device(struct device *dev, struct device_driver *drv)
 {
 	const struct spi_device	*spi = to_spi_device(dev);
 
-	return strncmp(spi->modalias, drv->name, BUS_ID_SIZE) == 0;
+	return strcmp(spi->modalias, drv->name) == 0;
 }
 
 static int spi_uevent(struct device *dev, struct kobj_uevent_env *env)
@@ -243,8 +243,7 @@ int spi_add_device(struct spi_device *spi)
 	}
 
 	/* Set the bus ID string */
-	snprintf(spi->dev.bus_id, sizeof spi->dev.bus_id,
-			"%s.%u", spi->master->dev.bus_id,
+	dev_set_name(&spi->dev, "%s.%u", dev_name(&spi->master->dev),
 			spi->chip_select);
 
 
@@ -254,7 +253,7 @@ int spi_add_device(struct spi_device *spi)
 	 */
 	mutex_lock(&spi_add_lock);
 
-	if (bus_find_device_by_name(&spi_bus_type, NULL, spi->dev.bus_id)
+	if (bus_find_device_by_name(&spi_bus_type, NULL, dev_name(&spi->dev))
 			!= NULL) {
 		dev_err(dev, "chipselect %d already in use\n",
 				spi->chip_select);
@@ -269,7 +268,7 @@ int spi_add_device(struct spi_device *spi)
 	status = spi->master->setup(spi);
 	if (status < 0) {
 		dev_err(dev, "can't %s %s, status %d\n",
-				"setup", spi->dev.bus_id, status);
+				"setup", dev_name(&spi->dev), status);
 		goto done;
 	}
 
@@ -277,9 +276,9 @@ int spi_add_device(struct spi_device *spi)
 	status = device_add(&spi->dev);
 	if (status < 0)
 		dev_err(dev, "can't %s %s, status %d\n",
-				"add", spi->dev.bus_id, status);
+				"add", dev_name(&spi->dev), status);
 	else
-		dev_dbg(dev, "registered child %s\n", spi->dev.bus_id);
+		dev_dbg(dev, "registered child %s\n", dev_name(&spi->dev));
 
 done:
 	mutex_unlock(&spi_add_lock);
@@ -504,12 +503,11 @@ int spi_register_master(struct spi_master *master)
 	/* register the device, then userspace will see it.
 	 * registration fails if the bus ID is in use.
 	 */
-	snprintf(master->dev.bus_id, sizeof master->dev.bus_id,
-		"spi%u", master->bus_num);
+	dev_set_name(&master->dev, "spi%u", master->bus_num);
 	status = device_add(&master->dev);
 	if (status < 0)
 		goto done;
-	dev_dbg(dev, "registered master %s%s\n", master->dev.bus_id,
+	dev_dbg(dev, "registered master %s%s\n", dev_name(&master->dev),
 			dynamic ? " (dynamic)" : "");
 
 	/* populate children from any spi device tables */
diff --git a/drivers/spi/spi_bitbang.c b/drivers/spi/spi_bitbang.c
index 96cc39ecb6e2..85e61f451218 100644
--- a/drivers/spi/spi_bitbang.c
+++ b/drivers/spi/spi_bitbang.c
@@ -475,7 +475,7 @@ int spi_bitbang_start(struct spi_bitbang *bitbang)
 	/* this task is the only thing to touch the SPI bits */
 	bitbang->busy = 0;
 	bitbang->workqueue = create_singlethread_workqueue(
-			bitbang->master->dev.parent->bus_id);
+			dev_name(bitbang->master->dev.parent));
 	if (bitbang->workqueue == NULL) {
 		status = -EBUSY;
 		goto err1;
diff --git a/drivers/spi/spi_butterfly.c b/drivers/spi/spi_butterfly.c
index 0ee2b2090252..c2184866fa9c 100644
--- a/drivers/spi/spi_butterfly.c
+++ b/drivers/spi/spi_butterfly.c
@@ -287,7 +287,7 @@ static void butterfly_attach(struct parport *p)
 	pp->dataflash = spi_new_device(pp->bitbang.master, &pp->info[0]);
 	if (pp->dataflash)
 		pr_debug("%s: dataflash at %s\n", p->name,
-				pp->dataflash->dev.bus_id);
+				dev_name(&pp->dataflash->dev));
 
 	// dev_info(_what?_, ...)
 	pr_info("%s: AVR Butterfly\n", p->name);
diff --git a/drivers/spi/spi_lm70llp.c b/drivers/spi/spi_lm70llp.c
index 39d8d8ad65c0..568c781ad91c 100644
--- a/drivers/spi/spi_lm70llp.c
+++ b/drivers/spi/spi_lm70llp.c
@@ -1,5 +1,5 @@
 /*
- * spi_lm70llp.c - driver for lm70llp eval board for the LM70 sensor
+ * spi_lm70llp.c - driver for LM70EVAL-LLP board for the LM70 sensor
  *
  * Copyright (C) 2006 Kaiwan N Billimoria <kaiwan@designergraphix.com>
  *
@@ -40,8 +40,12 @@
  * master controller driver.  The hwmon/lm70 driver is a "SPI protocol
  * driver", layered on top of this one and usable without the lm70llp.
  *
+ * Datasheet and Schematic:
  * The LM70 is a temperature sensor chip from National Semiconductor; its
  * datasheet is available at http://www.national.com/pf/LM/LM70.html
+ * The schematic for this particular board (the LM70EVAL-LLP) is
+ * available (on page 4) here:
+ *  http://www.national.com/appinfo/tempsensors/files/LM70LLPEVALmanual.pdf
  *
  * Also see Documentation/spi/spi-lm70llp.  The SPI<->parport code here is
  * (heavily) based on spi-butterfly by David Brownell.
@@ -64,7 +68,7 @@
  *
  * Note that parport pin 13 actually gets inverted by the transistor
  * arrangement which lets either the parport or the LM70 drive the
- * SI/SO signal.
+ * SI/SO signal (see the schematic for details).
  */
 
 #define DRVNAME		"spi-lm70llp"
@@ -106,12 +110,16 @@ static inline struct spi_lm70llp *spidev_to_pp(struct spi_device *spi)
 static inline void deassertCS(struct spi_lm70llp *pp)
 {
 	u8 data = parport_read_data(pp->port);
+
+	data &= ~0x80;		/* pull D7/SI-out low while de-asserted */
 	parport_write_data(pp->port, data | nCS);
 }
 
 static inline void assertCS(struct spi_lm70llp *pp)
 {
 	u8 data = parport_read_data(pp->port);
+
+	data |= 0x80;		/* pull D7/SI-out high so lm70 drives SO-in */
 	parport_write_data(pp->port, data & ~nCS);
 }
 
@@ -184,22 +192,7 @@ static void lm70_chipselect(struct spi_device *spi, int value)
  */
 static u32 lm70_txrx(struct spi_device *spi, unsigned nsecs, u32 word, u8 bits)
 {
-	static u32 sio=0;
-	static int first_time=1;
-
-	/* First time: perform SPI bitbang and return the LSB of
-	 * the result of the SPI call.
-	 */
-	if (first_time) {
-		sio = bitbang_txrx_be_cpha0(spi, nsecs, 0, word, bits);
-		first_time=0;
-		return (sio & 0x00ff);
-	}
-	/* Return the MSB of the result of the SPI call */
-	else {
-		first_time=1;
-		return (sio >> 8);
-	}
+	return bitbang_txrx_be_cpha0(spi, nsecs, 0, word, bits);
 }
 
 static void spi_lm70llp_attach(struct parport *p)
@@ -287,16 +280,15 @@ static void spi_lm70llp_attach(struct parport *p)
 	pp->spidev_lm70 = spi_new_device(pp->bitbang.master, &pp->info);
 	if (pp->spidev_lm70)
 		dev_dbg(&pp->spidev_lm70->dev, "spidev_lm70 at %s\n",
-				pp->spidev_lm70->dev.bus_id);
+				dev_name(&pp->spidev_lm70->dev));
 	else {
 		printk(KERN_WARNING "%s: spi_new_device failed\n", DRVNAME);
 		status = -ENODEV;
 		goto out_bitbang_stop;
 	}
-	pp->spidev_lm70->bits_per_word = 16;
+	pp->spidev_lm70->bits_per_word = 8;
 
 	lm70llp = pp;
-
 	return;
 
 out_bitbang_stop:
@@ -326,7 +318,6 @@ static void spi_lm70llp_detach(struct parport *p)
 
 	/* power down */
 	parport_write_data(pp->port, 0);
-	msleep(10);
 
 	parport_release(pp->pd);
 	parport_unregister_device(pp->pd);
diff --git a/drivers/spi/spi_s3c24xx.c b/drivers/spi/spi_s3c24xx.c
index c252cbac00f1..256d18395a23 100644
--- a/drivers/spi/spi_s3c24xx.c
+++ b/drivers/spi/spi_s3c24xx.c
@@ -28,7 +28,7 @@
 #include <mach/hardware.h>
 
 #include <mach/regs-gpio.h>
-#include <asm/plat-s3c24xx/regs-spi.h>
+#include <plat/regs-spi.h>
 #include <mach/spi.h>
 
 struct s3c24xx_spi {
diff --git a/drivers/ssb/main.c b/drivers/ssb/main.c
index 0ffabf5c0b60..65a1ed951a1d 100644
--- a/drivers/ssb/main.c
+++ b/drivers/ssb/main.c
@@ -226,7 +226,7 @@ int ssb_devices_freeze(struct ssb_bus *bus)
 		err = drv->suspend(dev, state);
 		if (err) {
 			ssb_printk(KERN_ERR PFX "Failed to freeze device %s\n",
-				   dev->dev->bus_id);
+				   dev_name(dev->dev));
 			goto err_unwind;
 		}
 	}
@@ -269,7 +269,7 @@ int ssb_devices_thaw(struct ssb_bus *bus)
 		err = drv->resume(dev);
 		if (err) {
 			ssb_printk(KERN_ERR PFX "Failed to thaw device %s\n",
-				   dev->dev->bus_id);
+				   dev_name(dev->dev));
 		}
 	}
 
@@ -454,8 +454,7 @@ static int ssb_devices_register(struct ssb_bus *bus)
 
 		dev->release = ssb_release_dev;
 		dev->bus = &ssb_bustype;
-		snprintf(dev->bus_id, sizeof(dev->bus_id),
-			 "ssb%u:%d", bus->busnumber, dev_idx);
+		dev_set_name(dev, "ssb%u:%d", bus->busnumber, dev_idx);
 
 		switch (bus->bustype) {
 		case SSB_BUSTYPE_PCI:
@@ -480,7 +479,7 @@ static int ssb_devices_register(struct ssb_bus *bus)
 		if (err) {
 			ssb_printk(KERN_ERR PFX
 				   "Could not register %s\n",
-				   dev->bus_id);
+				   dev_name(dev));
 			/* Set dev to NULL to not unregister
 			 * dev on error unwinding. */
 			sdev->dev = NULL;
@@ -796,7 +795,7 @@ int ssb_bus_pcibus_register(struct ssb_bus *bus,
 	err = ssb_bus_register(bus, ssb_pci_get_invariants, 0);
 	if (!err) {
 		ssb_printk(KERN_INFO PFX "Sonics Silicon Backplane found on "
-			   "PCI device %s\n", host_pci->dev.bus_id);
+			   "PCI device %s\n", dev_name(&host_pci->dev));
 	}
 
 	return err;
diff --git a/drivers/ssb/pcihost_wrapper.c b/drivers/ssb/pcihost_wrapper.c
index e82db4aaa050..26737a010c6d 100644
--- a/drivers/ssb/pcihost_wrapper.c
+++ b/drivers/ssb/pcihost_wrapper.c
@@ -65,7 +65,7 @@ static int ssb_pcihost_probe(struct pci_dev *dev,
 	err = pci_enable_device(dev);
 	if (err)
 		goto err_kfree_ssb;
-	name = dev->dev.bus_id;
+	name = dev_name(&dev->dev);
 	if (dev->driver && dev->driver->name)
 		name = dev->driver->name;
 	err = pci_request_regions(dev, name);
diff --git a/drivers/thermal/thermal_sys.c b/drivers/thermal/thermal_sys.c
index fe07462d5947..8171ca17b936 100644
--- a/drivers/thermal/thermal_sys.c
+++ b/drivers/thermal/thermal_sys.c
@@ -579,7 +579,7 @@ static void thermal_release(struct device *dev)
 	struct thermal_zone_device *tz;
 	struct thermal_cooling_device *cdev;
 
-	if (!strncmp(dev->bus_id, "thermal_zone", sizeof "thermal_zone" - 1)) {
+	if (!strncmp(dev_name(dev), "thermal_zone", sizeof "thermal_zone" - 1)) {
 		tz = to_thermal_zone(dev);
 		kfree(tz);
 	} else {
@@ -630,7 +630,7 @@ struct thermal_cooling_device *thermal_cooling_device_register(char *type,
 	cdev->ops = ops;
 	cdev->device.class = &thermal_class;
 	cdev->devdata = devdata;
-	sprintf(cdev->device.bus_id, "cooling_device%d", cdev->id);
+	dev_set_name(&cdev->device, "cooling_device%d", cdev->id);
 	result = device_register(&cdev->device);
 	if (result) {
 		release_idr(&thermal_cdev_idr, &thermal_idr_lock, cdev->id);
@@ -769,7 +769,7 @@ struct thermal_zone_device *thermal_zone_device_register(char *type,
 	tz->device.class = &thermal_class;
 	tz->devdata = devdata;
 	tz->trips = trips;
-	sprintf(tz->device.bus_id, "thermal_zone%d", tz->id);
+	dev_set_name(&tz->device, "thermal_zone%d", tz->id);
 	result = device_register(&tz->device);
 	if (result) {
 		release_idr(&thermal_tz_idr, &thermal_idr_lock, tz->id);
diff --git a/drivers/uio/uio_cif.c b/drivers/uio/uio_cif.c
index 57376060b978..c60b8fcf0e3e 100644
--- a/drivers/uio/uio_cif.c
+++ b/drivers/uio/uio_cif.c
@@ -57,8 +57,7 @@ static int __devinit hilscher_pci_probe(struct pci_dev *dev,
 	info->mem[0].addr = pci_resource_start(dev, 0);
 	if (!info->mem[0].addr)
 		goto out_release;
-	info->mem[0].internal_addr = ioremap(pci_resource_start(dev, 0),
-					     pci_resource_len(dev, 0));
+	info->mem[0].internal_addr = pci_ioremap_bar(dev, 0);
 	if (!info->mem[0].internal_addr)
 		goto out_release;
 
diff --git a/drivers/uio/uio_pdrv_genirq.c b/drivers/uio/uio_pdrv_genirq.c
index 1f82c83a92ae..3f06818cf9fa 100644
--- a/drivers/uio/uio_pdrv_genirq.c
+++ b/drivers/uio/uio_pdrv_genirq.c
@@ -81,7 +81,8 @@ static int uio_pdrv_genirq_probe(struct platform_device *pdev)
 		goto bad0;
 	}
 
-	if (uioinfo->handler || uioinfo->irqcontrol || uioinfo->irq_flags) {
+	if (uioinfo->handler || uioinfo->irqcontrol ||
+	    uioinfo->irq_flags & IRQF_SHARED) {
 		dev_err(&pdev->dev, "interrupt configuration error\n");
 		goto bad0;
 	}
@@ -132,7 +133,7 @@ static int uio_pdrv_genirq_probe(struct platform_device *pdev)
 	 * Interrupt sharing is not supported.
 	 */
 
-	uioinfo->irq_flags = IRQF_DISABLED;
+	uioinfo->irq_flags |= IRQF_DISABLED;
 	uioinfo->handler = uio_pdrv_genirq_handler;
 	uioinfo->irqcontrol = uio_pdrv_genirq_irqcontrol;
 	uioinfo->priv = priv;
diff --git a/drivers/usb/Kconfig b/drivers/usb/Kconfig
index 289d81adfb9c..83babb0a1df7 100644
--- a/drivers/usb/Kconfig
+++ b/drivers/usb/Kconfig
@@ -150,4 +150,6 @@ source "drivers/usb/atm/Kconfig"
 
 source "drivers/usb/gadget/Kconfig"
 
+source "drivers/usb/otg/Kconfig"
+
 endif # USB_SUPPORT
diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c
index d50a99f70aee..00b47ea24f86 100644
--- a/drivers/usb/class/cdc-acm.c
+++ b/drivers/usb/class/cdc-acm.c
@@ -1275,7 +1275,7 @@ static int acm_suspend(struct usb_interface *intf, pm_message_t message)
 	struct acm *acm = usb_get_intfdata(intf);
 	int cnt;
 
-	if (acm->dev->auto_pm) {
+	if (message.event & PM_EVENT_AUTO) {
 		int b;
 
 		spin_lock_irq(&acm->read_lock);
diff --git a/drivers/usb/class/cdc-wdm.c b/drivers/usb/class/cdc-wdm.c
index 5a8ecc045e3f..3771d6e6d0cc 100644
--- a/drivers/usb/class/cdc-wdm.c
+++ b/drivers/usb/class/cdc-wdm.c
@@ -764,7 +764,8 @@ static int wdm_suspend(struct usb_interface *intf, pm_message_t message)
 
 	mutex_lock(&desc->plock);
 #ifdef CONFIG_PM
-	if (interface_to_usbdev(desc->intf)->auto_pm && test_bit(WDM_IN_USE, &desc->flags)) {
+	if ((message.event & PM_EVENT_AUTO) &&
+			test_bit(WDM_IN_USE, &desc->flags)) {
 		rv = -EBUSY;
 	} else {
 #endif
diff --git a/drivers/usb/class/usbtmc.c b/drivers/usb/class/usbtmc.c
index 8e74657f106c..0f5c05f6f9df 100644
--- a/drivers/usb/class/usbtmc.c
+++ b/drivers/usb/class/usbtmc.c
@@ -21,6 +21,7 @@
 
 #include <linux/init.h>
 #include <linux/module.h>
+#include <linux/kernel.h>
 #include <linux/fs.h>
 #include <linux/uaccess.h>
 #include <linux/kref.h>
@@ -51,6 +52,7 @@ static struct usb_device_id usbtmc_devices[] = {
 	{ USB_INTERFACE_INFO(USB_CLASS_APP_SPEC, 3, 0), },
 	{ 0, } /* terminating entry */
 };
+MODULE_DEVICE_TABLE(usb, usbtmc_devices);
 
 /*
  * This structure is the capabilities for the device
@@ -481,7 +483,6 @@ static ssize_t usbtmc_write(struct file *filp, const char __user *buf,
 	int retval;
 	int actual;
 	unsigned long int n_bytes;
-	int n;
 	int remaining;
 	int done;
 	int this_part;
@@ -525,11 +526,8 @@ static ssize_t usbtmc_write(struct file *filp, const char __user *buf,
 			goto exit;
 		}
 
-		n_bytes = 12 + this_part;
-		if (this_part % 4)
-			n_bytes += 4 - this_part % 4;
-			for (n = 12 + this_part; n < n_bytes; n++)
-				buffer[n] = 0;
+		n_bytes = roundup(12 + this_part, 4);
+		memset(buffer + 12 + this_part, 0, n_bytes - (12 + this_part));
 
 		retval = usb_bulk_msg(data->usb_dev,
 				      usb_sndbulkpipe(data->usb_dev,
diff --git a/drivers/usb/core/devio.c b/drivers/usb/core/devio.c
index 2bccefebff1b..9bf97fca2259 100644
--- a/drivers/usb/core/devio.c
+++ b/drivers/usb/core/devio.c
@@ -979,9 +979,6 @@ static int proc_do_submiturb(struct dev_state *ps, struct usbdevfs_urb *uurb,
 		return -EINVAL;
 	if (!uurb->buffer)
 		return -EINVAL;
-	if (uurb->signr != 0 && (uurb->signr < SIGRTMIN ||
-				 uurb->signr > SIGRTMAX))
-		return -EINVAL;
 	if (!(uurb->type == USBDEVFS_URB_TYPE_CONTROL &&
 	    (uurb->endpoint & ~USB_ENDPOINT_DIR_MASK) == 0)) {
 		ifnum = findintfep(ps->dev, uurb->endpoint);
@@ -1399,8 +1396,6 @@ static int proc_disconnectsignal(struct dev_state *ps, void __user *arg)
 
 	if (copy_from_user(&ds, arg, sizeof(ds)))
 		return -EFAULT;
-	if (ds.signr != 0 && (ds.signr < SIGRTMIN || ds.signr > SIGRTMAX))
-		return -EINVAL;
 	ps->discsignr = ds.signr;
 	ps->disccontext = ds.context;
 	return 0;
diff --git a/drivers/usb/core/driver.c b/drivers/usb/core/driver.c
index 3d7793d93031..3b28897ee147 100644
--- a/drivers/usb/core/driver.c
+++ b/drivers/usb/core/driver.c
@@ -184,6 +184,20 @@ static int usb_unbind_device(struct device *dev)
 	return 0;
 }
 
+/*
+ * Cancel any pending scheduled resets
+ *
+ * [see usb_queue_reset_device()]
+ *
+ * Called after unconfiguring / when releasing interfaces. See
+ * comments in __usb_queue_reset_device() regarding
+ * udev->reset_running.
+ */
+static void usb_cancel_queued_reset(struct usb_interface *iface)
+{
+	if (iface->reset_running == 0)
+		cancel_work_sync(&iface->reset_ws);
+}
 
 /* called from driver core with dev locked */
 static int usb_probe_interface(struct device *dev)
@@ -242,6 +256,7 @@ static int usb_probe_interface(struct device *dev)
 			mark_quiesced(intf);
 			intf->needs_remote_wakeup = 0;
 			intf->condition = USB_INTERFACE_UNBOUND;
+			usb_cancel_queued_reset(intf);
 		} else
 			intf->condition = USB_INTERFACE_BOUND;
 
@@ -272,6 +287,7 @@ static int usb_unbind_interface(struct device *dev)
 		usb_disable_interface(udev, intf);
 
 	driver->disconnect(intf);
+	usb_cancel_queued_reset(intf);
 
 	/* Reset other interface state.
 	 * We cannot do a Set-Interface if the device is suspended or
@@ -378,8 +394,10 @@ void usb_driver_release_interface(struct usb_driver *driver,
 	if (device_is_registered(dev)) {
 		iface->condition = USB_INTERFACE_UNBINDING;
 		device_release_driver(dev);
+	} else {
+		iface->condition = USB_INTERFACE_UNBOUND;
+		usb_cancel_queued_reset(iface);
 	}
-
 	dev->driver = NULL;
 	usb_set_intfdata(iface, NULL);
 
@@ -902,7 +920,7 @@ static int usb_suspend_device(struct usb_device *udev, pm_message_t msg)
 }
 
 /* Caller has locked udev's pm_mutex */
-static int usb_resume_device(struct usb_device *udev)
+static int usb_resume_device(struct usb_device *udev, pm_message_t msg)
 {
 	struct usb_device_driver	*udriver;
 	int				status = 0;
@@ -920,7 +938,7 @@ static int usb_resume_device(struct usb_device *udev)
 		udev->reset_resume = 1;
 
 	udriver = to_usb_device_driver(udev->dev.driver);
-	status = udriver->resume(udev);
+	status = udriver->resume(udev, msg);
 
  done:
 	dev_vdbg(&udev->dev, "%s: status %d\n", __func__, status);
@@ -940,7 +958,8 @@ static int usb_suspend_interface(struct usb_device *udev,
 	if (udev->state == USB_STATE_NOTATTACHED || !is_active(intf))
 		goto done;
 
-	if (intf->condition == USB_INTERFACE_UNBOUND)	/* This can't happen */
+	/* This can happen; see usb_driver_release_interface() */
+	if (intf->condition == USB_INTERFACE_UNBOUND)
 		goto done;
 	driver = to_usb_driver(intf->dev.driver);
 
@@ -948,7 +967,7 @@ static int usb_suspend_interface(struct usb_device *udev,
 		status = driver->suspend(intf, msg);
 		if (status == 0)
 			mark_quiesced(intf);
-		else if (!udev->auto_pm)
+		else if (!(msg.event & PM_EVENT_AUTO))
 			dev_err(&intf->dev, "%s error %d\n",
 					"suspend", status);
 	} else {
@@ -966,7 +985,7 @@ static int usb_suspend_interface(struct usb_device *udev,
 
 /* Caller has locked intf's usb_device's pm_mutex */
 static int usb_resume_interface(struct usb_device *udev,
-		struct usb_interface *intf, int reset_resume)
+		struct usb_interface *intf, pm_message_t msg, int reset_resume)
 {
 	struct usb_driver	*driver;
 	int			status = 0;
@@ -1090,7 +1109,7 @@ static int autosuspend_check(struct usb_device *udev, int reschedule)
 	if (reschedule) {
 		if (!timer_pending(&udev->autosuspend.timer)) {
 			queue_delayed_work(ksuspend_usb_wq, &udev->autosuspend,
-				round_jiffies_relative(suspend_time - j));
+				round_jiffies_up_relative(suspend_time - j));
 		}
 		return -EAGAIN;
 	}
@@ -1117,10 +1136,9 @@ static inline int autosuspend_check(struct usb_device *udev, int reschedule)
  * all the interfaces which were suspended are resumed so that they remain
  * in the same state as the device.
  *
- * If an autosuspend is in progress (@udev->auto_pm is set), the routine
- * checks first to make sure that neither the device itself or any of its
- * active interfaces is in use (pm_usage_cnt is greater than 0).  If they
- * are, the autosuspend fails.
+ * If an autosuspend is in progress the routine checks first to make sure
+ * that neither the device itself or any of its active interfaces is in use
+ * (pm_usage_cnt is greater than 0).  If they are, the autosuspend fails.
  *
  * If the suspend succeeds, the routine recursively queues an autosuspend
  * request for @udev's parent device, thereby propagating the change up
@@ -1155,7 +1173,7 @@ static int usb_suspend_both(struct usb_device *udev, pm_message_t msg)
 
 	udev->do_remote_wakeup = device_may_wakeup(&udev->dev);
 
-	if (udev->auto_pm) {
+	if (msg.event & PM_EVENT_AUTO) {
 		status = autosuspend_check(udev, 0);
 		if (status < 0)
 			goto done;
@@ -1175,13 +1193,16 @@ static int usb_suspend_both(struct usb_device *udev, pm_message_t msg)
 
 	/* If the suspend failed, resume interfaces that did get suspended */
 	if (status != 0) {
+		pm_message_t msg2;
+
+		msg2.event = msg.event ^ (PM_EVENT_SUSPEND | PM_EVENT_RESUME);
 		while (--i >= 0) {
 			intf = udev->actconfig->interface[i];
-			usb_resume_interface(udev, intf, 0);
+			usb_resume_interface(udev, intf, msg2, 0);
 		}
 
 		/* Try another autosuspend when the interfaces aren't busy */
-		if (udev->auto_pm)
+		if (msg.event & PM_EVENT_AUTO)
 			autosuspend_check(udev, status == -EBUSY);
 
 	/* If the suspend succeeded then prevent any more URB submissions,
@@ -1211,6 +1232,7 @@ static int usb_suspend_both(struct usb_device *udev, pm_message_t msg)
 /**
  * usb_resume_both - resume a USB device and its interfaces
  * @udev: the usb_device to resume
+ * @msg: Power Management message describing this state transition
  *
  * This is the central routine for resuming USB devices.  It calls the
  * the resume method for @udev and then calls the resume methods for all
@@ -1236,7 +1258,7 @@ static int usb_suspend_both(struct usb_device *udev, pm_message_t msg)
  *
  * This routine can run only in process context.
  */
-static int usb_resume_both(struct usb_device *udev)
+static int usb_resume_both(struct usb_device *udev, pm_message_t msg)
 {
 	int			status = 0;
 	int			i;
@@ -1252,14 +1274,15 @@ static int usb_resume_both(struct usb_device *udev)
 
 	/* Propagate the resume up the tree, if necessary */
 	if (udev->state == USB_STATE_SUSPENDED) {
-		if (udev->auto_pm && udev->autoresume_disabled) {
+		if ((msg.event & PM_EVENT_AUTO) &&
+				udev->autoresume_disabled) {
 			status = -EPERM;
 			goto done;
 		}
 		if (parent) {
 			status = usb_autoresume_device(parent);
 			if (status == 0) {
-				status = usb_resume_device(udev);
+				status = usb_resume_device(udev, msg);
 				if (status || udev->state ==
 						USB_STATE_NOTATTACHED) {
 					usb_autosuspend_device(parent);
@@ -1282,15 +1305,16 @@ static int usb_resume_both(struct usb_device *udev)
 			/* We can't progagate beyond the USB subsystem,
 			 * so if a root hub's controller is suspended
 			 * then we're stuck. */
-			status = usb_resume_device(udev);
+			status = usb_resume_device(udev, msg);
 		}
 	} else if (udev->reset_resume)
-		status = usb_resume_device(udev);
+		status = usb_resume_device(udev, msg);
 
 	if (status == 0 && udev->actconfig) {
 		for (i = 0; i < udev->actconfig->desc.bNumInterfaces; i++) {
 			intf = udev->actconfig->interface[i];
-			usb_resume_interface(udev, intf, udev->reset_resume);
+			usb_resume_interface(udev, intf, msg,
+					udev->reset_resume);
 		}
 	}
 
@@ -1318,13 +1342,13 @@ static int usb_autopm_do_device(struct usb_device *udev, int inc_usage_cnt)
 		udev->last_busy = jiffies;
 	if (inc_usage_cnt >= 0 && udev->pm_usage_cnt > 0) {
 		if (udev->state == USB_STATE_SUSPENDED)
-			status = usb_resume_both(udev);
+			status = usb_resume_both(udev, PMSG_AUTO_RESUME);
 		if (status != 0)
 			udev->pm_usage_cnt -= inc_usage_cnt;
 		else if (inc_usage_cnt)
 			udev->last_busy = jiffies;
 	} else if (inc_usage_cnt <= 0 && udev->pm_usage_cnt <= 0) {
-		status = usb_suspend_both(udev, PMSG_SUSPEND);
+		status = usb_suspend_both(udev, PMSG_AUTO_SUSPEND);
 	}
 	usb_pm_unlock(udev);
 	return status;
@@ -1339,6 +1363,19 @@ void usb_autosuspend_work(struct work_struct *work)
 	usb_autopm_do_device(udev, 0);
 }
 
+/* usb_autoresume_work - callback routine to autoresume a USB device */
+void usb_autoresume_work(struct work_struct *work)
+{
+	struct usb_device *udev =
+		container_of(work, struct usb_device, autoresume);
+
+	/* Wake it up, let the drivers do their thing, and then put it
+	 * back to sleep.
+	 */
+	if (usb_autopm_do_device(udev, 1) == 0)
+		usb_autopm_do_device(udev, -1);
+}
+
 /**
  * usb_autosuspend_device - delayed autosuspend of a USB device and its interfaces
  * @udev: the usb_device to autosuspend
@@ -1435,13 +1472,14 @@ static int usb_autopm_do_interface(struct usb_interface *intf,
 		udev->last_busy = jiffies;
 		if (inc_usage_cnt >= 0 && intf->pm_usage_cnt > 0) {
 			if (udev->state == USB_STATE_SUSPENDED)
-				status = usb_resume_both(udev);
+				status = usb_resume_both(udev,
+						PMSG_AUTO_RESUME);
 			if (status != 0)
 				intf->pm_usage_cnt -= inc_usage_cnt;
 			else
 				udev->last_busy = jiffies;
 		} else if (inc_usage_cnt <= 0 && intf->pm_usage_cnt <= 0) {
-			status = usb_suspend_both(udev, PMSG_SUSPEND);
+			status = usb_suspend_both(udev, PMSG_AUTO_SUSPEND);
 		}
 	}
 	usb_pm_unlock(udev);
@@ -1490,6 +1528,45 @@ void usb_autopm_put_interface(struct usb_interface *intf)
 EXPORT_SYMBOL_GPL(usb_autopm_put_interface);
 
 /**
+ * usb_autopm_put_interface_async - decrement a USB interface's PM-usage counter
+ * @intf: the usb_interface whose counter should be decremented
+ *
+ * This routine does essentially the same thing as
+ * usb_autopm_put_interface(): it decrements @intf's usage counter and
+ * queues a delayed autosuspend request if the counter is <= 0.  The
+ * difference is that it does not acquire the device's pm_mutex;
+ * callers must handle all synchronization issues themselves.
+ *
+ * Typically a driver would call this routine during an URB's completion
+ * handler, if no more URBs were pending.
+ *
+ * This routine can run in atomic context.
+ */
+void usb_autopm_put_interface_async(struct usb_interface *intf)
+{
+	struct usb_device	*udev = interface_to_usbdev(intf);
+	int			status = 0;
+
+	if (intf->condition == USB_INTERFACE_UNBOUND) {
+		status = -ENODEV;
+	} else {
+		udev->last_busy = jiffies;
+		--intf->pm_usage_cnt;
+		if (udev->autosuspend_disabled || udev->autosuspend_delay < 0)
+			status = -EPERM;
+		else if (intf->pm_usage_cnt <= 0 &&
+				!timer_pending(&udev->autosuspend.timer)) {
+			queue_delayed_work(ksuspend_usb_wq, &udev->autosuspend,
+					round_jiffies_up_relative(
+						udev->autosuspend_delay));
+		}
+	}
+	dev_vdbg(&intf->dev, "%s: status %d cnt %d\n",
+			__func__, status, intf->pm_usage_cnt);
+}
+EXPORT_SYMBOL_GPL(usb_autopm_put_interface_async);
+
+/**
  * usb_autopm_get_interface - increment a USB interface's PM-usage counter
  * @intf: the usb_interface whose counter should be incremented
  *
@@ -1535,6 +1612,37 @@ int usb_autopm_get_interface(struct usb_interface *intf)
 EXPORT_SYMBOL_GPL(usb_autopm_get_interface);
 
 /**
+ * usb_autopm_get_interface_async - increment a USB interface's PM-usage counter
+ * @intf: the usb_interface whose counter should be incremented
+ *
+ * This routine does much the same thing as
+ * usb_autopm_get_interface(): it increments @intf's usage counter and
+ * queues an autoresume request if the result is > 0.  The differences
+ * are that it does not acquire the device's pm_mutex (callers must
+ * handle all synchronization issues themselves), and it does not
+ * autoresume the device directly (it only queues a request).  After a
+ * successful call, the device will generally not yet be resumed.
+ *
+ * This routine can run in atomic context.
+ */
+int usb_autopm_get_interface_async(struct usb_interface *intf)
+{
+	struct usb_device	*udev = interface_to_usbdev(intf);
+	int			status = 0;
+
+	if (intf->condition == USB_INTERFACE_UNBOUND)
+		status = -ENODEV;
+	else if (udev->autoresume_disabled)
+		status = -EPERM;
+	else if (++intf->pm_usage_cnt > 0 && udev->state == USB_STATE_SUSPENDED)
+		queue_work(ksuspend_usb_wq, &udev->autoresume);
+	dev_vdbg(&intf->dev, "%s: status %d cnt %d\n",
+			__func__, status, intf->pm_usage_cnt);
+	return status;
+}
+EXPORT_SYMBOL_GPL(usb_autopm_get_interface_async);
+
+/**
  * usb_autopm_set_interface - set a USB interface's autosuspend state
  * @intf: the usb_interface whose state should be set
  *
@@ -1561,6 +1669,9 @@ EXPORT_SYMBOL_GPL(usb_autopm_set_interface);
 void usb_autosuspend_work(struct work_struct *work)
 {}
 
+void usb_autoresume_work(struct work_struct *work)
+{}
+
 #endif /* CONFIG_USB_SUSPEND */
 
 /**
@@ -1593,6 +1704,7 @@ int usb_external_suspend_device(struct usb_device *udev, pm_message_t msg)
 /**
  * usb_external_resume_device - external resume of a USB device and its interfaces
  * @udev: the usb_device to resume
+ * @msg: Power Management message describing this state transition
  *
  * This routine handles external resume requests: ones not generated
  * internally by a USB driver (autoresume) but rather coming from the user
@@ -1601,13 +1713,13 @@ int usb_external_suspend_device(struct usb_device *udev, pm_message_t msg)
  *
  * The caller must hold @udev's device lock.
  */
-int usb_external_resume_device(struct usb_device *udev)
+int usb_external_resume_device(struct usb_device *udev, pm_message_t msg)
 {
 	int	status;
 
 	usb_pm_lock(udev);
 	udev->auto_pm = 0;
-	status = usb_resume_both(udev);
+	status = usb_resume_both(udev, msg);
 	udev->last_busy = jiffies;
 	usb_pm_unlock(udev);
 	if (status == 0)
@@ -1620,7 +1732,7 @@ int usb_external_resume_device(struct usb_device *udev)
 	return status;
 }
 
-int usb_suspend(struct device *dev, pm_message_t message)
+int usb_suspend(struct device *dev, pm_message_t msg)
 {
 	struct usb_device	*udev;
 
@@ -1639,10 +1751,10 @@ int usb_suspend(struct device *dev, pm_message_t message)
 	}
 
 	udev->skip_sys_resume = 0;
-	return usb_external_suspend_device(udev, message);
+	return usb_external_suspend_device(udev, msg);
 }
 
-int usb_resume(struct device *dev)
+int usb_resume(struct device *dev, pm_message_t msg)
 {
 	struct usb_device	*udev;
 
@@ -1654,7 +1766,7 @@ int usb_resume(struct device *dev)
 	 */
 	if (udev->skip_sys_resume)
 		return 0;
-	return usb_external_resume_device(udev);
+	return usb_external_resume_device(udev, msg);
 }
 
 #endif /* CONFIG_PM */
diff --git a/drivers/usb/core/generic.c b/drivers/usb/core/generic.c
index 7e912f21fd36..30ecac3af15a 100644
--- a/drivers/usb/core/generic.c
+++ b/drivers/usb/core/generic.c
@@ -200,18 +200,18 @@ static int generic_suspend(struct usb_device *udev, pm_message_t msg)
 	 * interfaces manually by doing a bus (or "global") suspend.
 	 */
 	if (!udev->parent)
-		rc = hcd_bus_suspend(udev);
+		rc = hcd_bus_suspend(udev, msg);
 
 	/* Non-root devices don't need to do anything for FREEZE or PRETHAW */
 	else if (msg.event == PM_EVENT_FREEZE || msg.event == PM_EVENT_PRETHAW)
 		rc = 0;
 	else
-		rc = usb_port_suspend(udev);
+		rc = usb_port_suspend(udev, msg);
 
 	return rc;
 }
 
-static int generic_resume(struct usb_device *udev)
+static int generic_resume(struct usb_device *udev, pm_message_t msg)
 {
 	int rc;
 
@@ -221,9 +221,9 @@ static int generic_resume(struct usb_device *udev)
 	 * interfaces manually by doing a bus (or "global") resume.
 	 */
 	if (!udev->parent)
-		rc = hcd_bus_resume(udev);
+		rc = hcd_bus_resume(udev, msg);
 	else
-		rc = usb_port_resume(udev);
+		rc = usb_port_resume(udev, msg);
 	return rc;
 }
 
diff --git a/drivers/usb/core/hcd.c b/drivers/usb/core/hcd.c
index e1b42626d04d..a0079876d74e 100644
--- a/drivers/usb/core/hcd.c
+++ b/drivers/usb/core/hcd.c
@@ -1573,14 +1573,14 @@ int usb_hcd_get_frame_number (struct usb_device *udev)
 
 #ifdef	CONFIG_PM
 
-int hcd_bus_suspend(struct usb_device *rhdev)
+int hcd_bus_suspend(struct usb_device *rhdev, pm_message_t msg)
 {
 	struct usb_hcd	*hcd = container_of(rhdev->bus, struct usb_hcd, self);
 	int		status;
 	int		old_state = hcd->state;
 
 	dev_dbg(&rhdev->dev, "bus %s%s\n",
-			rhdev->auto_pm ? "auto-" : "", "suspend");
+			(msg.event & PM_EVENT_AUTO ? "auto-" : ""), "suspend");
 	if (!hcd->driver->bus_suspend) {
 		status = -ENOENT;
 	} else {
@@ -1598,14 +1598,14 @@ int hcd_bus_suspend(struct usb_device *rhdev)
 	return status;
 }
 
-int hcd_bus_resume(struct usb_device *rhdev)
+int hcd_bus_resume(struct usb_device *rhdev, pm_message_t msg)
 {
 	struct usb_hcd	*hcd = container_of(rhdev->bus, struct usb_hcd, self);
 	int		status;
 	int		old_state = hcd->state;
 
 	dev_dbg(&rhdev->dev, "usb %s%s\n",
-			rhdev->auto_pm ? "auto-" : "", "resume");
+			(msg.event & PM_EVENT_AUTO ? "auto-" : ""), "resume");
 	if (!hcd->driver->bus_resume)
 		return -ENOENT;
 	if (hcd->state == HC_STATE_RUNNING)
@@ -1638,7 +1638,7 @@ static void hcd_resume_work(struct work_struct *work)
 
 	usb_lock_device(udev);
 	usb_mark_last_busy(udev);
-	usb_external_resume_device(udev);
+	usb_external_resume_device(udev, PMSG_REMOTE_RESUME);
 	usb_unlock_device(udev);
 }
 
@@ -2028,7 +2028,7 @@ EXPORT_SYMBOL_GPL(usb_hcd_platform_shutdown);
 
 /*-------------------------------------------------------------------------*/
 
-#if defined(CONFIG_USB_MON)
+#if defined(CONFIG_USB_MON) || defined(CONFIG_USB_MON_MODULE)
 
 struct usb_mon_operations *mon_ops;
 
@@ -2064,4 +2064,4 @@ void usb_mon_deregister (void)
 }
 EXPORT_SYMBOL_GPL (usb_mon_deregister);
 
-#endif /* CONFIG_USB_MON */
+#endif /* CONFIG_USB_MON || CONFIG_USB_MON_MODULE */
diff --git a/drivers/usb/core/hcd.h b/drivers/usb/core/hcd.h
index 9465e70f4dd0..aa5da82d9071 100644
--- a/drivers/usb/core/hcd.h
+++ b/drivers/usb/core/hcd.h
@@ -16,6 +16,8 @@
  * Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
+#ifndef __USB_CORE_HCD_H
+#define __USB_CORE_HCD_H
 
 #ifdef __KERNEL__
 
@@ -386,8 +388,8 @@ extern int usb_find_interface_driver(struct usb_device *dev,
 #ifdef CONFIG_PM
 extern void usb_hcd_resume_root_hub(struct usb_hcd *hcd);
 extern void usb_root_hub_lost_power(struct usb_device *rhdev);
-extern int hcd_bus_suspend(struct usb_device *rhdev);
-extern int hcd_bus_resume(struct usb_device *rhdev);
+extern int hcd_bus_suspend(struct usb_device *rhdev, pm_message_t msg);
+extern int hcd_bus_resume(struct usb_device *rhdev, pm_message_t msg);
 #else
 static inline void usb_hcd_resume_root_hub(struct usb_hcd *hcd)
 {
@@ -419,7 +421,7 @@ static inline void usbfs_cleanup(void) { }
 
 /*-------------------------------------------------------------------------*/
 
-#if defined(CONFIG_USB_MON)
+#if defined(CONFIG_USB_MON) || defined(CONFIG_USB_MON_MODULE)
 
 struct usb_mon_operations {
 	void (*urb_submit)(struct usb_bus *bus, struct urb *urb);
@@ -461,7 +463,7 @@ static inline void usbmon_urb_submit_error(struct usb_bus *bus, struct urb *urb,
 static inline void usbmon_urb_complete(struct usb_bus *bus, struct urb *urb,
 		int status) {}
 
-#endif /* CONFIG_USB_MON */
+#endif /* CONFIG_USB_MON || CONFIG_USB_MON_MODULE */
 
 /*-------------------------------------------------------------------------*/
 
@@ -490,3 +492,5 @@ extern struct rw_semaphore ehci_cf_port_reset_rwsem;
 extern unsigned long usb_hcds_loaded;
 
 #endif /* __KERNEL__ */
+
+#endif /* __USB_CORE_HCD_H */
diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c
index b19cbfcd51da..fc99ef67761d 100644
--- a/drivers/usb/core/hub.c
+++ b/drivers/usb/core/hub.c
@@ -1374,8 +1374,9 @@ static void usb_stop_pm(struct usb_device *udev)
 		usb_autosuspend_device(udev->parent);
 	usb_pm_unlock(udev);
 
-	/* Stop any autosuspend requests already submitted */
-	cancel_rearming_delayed_work(&udev->autosuspend);
+	/* Stop any autosuspend or autoresume requests already submitted */
+	cancel_delayed_work_sync(&udev->autosuspend);
+	cancel_work_sync(&udev->autoresume);
 }
 
 #else
@@ -1635,6 +1636,10 @@ int usb_new_device(struct usb_device *udev)
 {
 	int err;
 
+	/* Increment the parent's count of unsuspended children */
+	if (udev->parent)
+		usb_autoresume_device(udev->parent);
+
 	usb_detect_quirks(udev);		/* Determine quirks */
 	err = usb_configure_device(udev);	/* detect & probe dev/intfs */
 	if (err < 0)
@@ -1643,9 +1648,8 @@ int usb_new_device(struct usb_device *udev)
 	udev->dev.devt = MKDEV(USB_DEVICE_MAJOR,
 			(((udev->bus->busnum-1) * 128) + (udev->devnum-1)));
 
-	/* Increment the parent's count of unsuspended children */
-	if (udev->parent)
-		usb_autoresume_device(udev->parent);
+	/* Tell the world! */
+	announce_device(udev);
 
 	/* Register the device.  The device driver is responsible
 	 * for adding the device files to sysfs and for configuring
@@ -1659,13 +1663,11 @@ int usb_new_device(struct usb_device *udev)
 
 	/* put device-specific files into sysfs */
 	usb_create_sysfs_dev_files(udev);
-
-	/* Tell the world! */
-	announce_device(udev);
 	return err;
 
 fail:
 	usb_set_device_state(udev, USB_STATE_NOTATTACHED);
+	usb_stop_pm(udev);
 	return err;
 }
 
@@ -1982,7 +1984,7 @@ static int check_port_resume_type(struct usb_device *udev,
  *
  * Returns 0 on success, else negative errno.
  */
-int usb_port_suspend(struct usb_device *udev)
+int usb_port_suspend(struct usb_device *udev, pm_message_t msg)
 {
 	struct usb_hub	*hub = hdev_to_hub(udev->parent);
 	int		port1 = udev->portnum;
@@ -2021,7 +2023,7 @@ int usb_port_suspend(struct usb_device *udev)
 	} else {
 		/* device has up to 10 msec to fully suspend */
 		dev_dbg(&udev->dev, "usb %ssuspend\n",
-				udev->auto_pm ? "auto-" : "");
+				(msg.event & PM_EVENT_AUTO ? "auto-" : ""));
 		usb_set_device_state(udev, USB_STATE_SUSPENDED);
 		msleep(10);
 	}
@@ -2140,7 +2142,7 @@ static int finish_port_resume(struct usb_device *udev)
  *
  * Returns 0 on success, else negative errno.
  */
-int usb_port_resume(struct usb_device *udev)
+int usb_port_resume(struct usb_device *udev, pm_message_t msg)
 {
 	struct usb_hub	*hub = hdev_to_hub(udev->parent);
 	int		port1 = udev->portnum;
@@ -2165,7 +2167,7 @@ int usb_port_resume(struct usb_device *udev)
 	} else {
 		/* drive resume for at least 20 msec */
 		dev_dbg(&udev->dev, "usb %sresume\n",
-				udev->auto_pm ? "auto-" : "");
+				(msg.event & PM_EVENT_AUTO ? "auto-" : ""));
 		msleep(25);
 
 		/* Virtual root hubs can trigger on GET_PORT_STATUS to
@@ -2206,7 +2208,7 @@ static int remote_wakeup(struct usb_device *udev)
 	if (udev->state == USB_STATE_SUSPENDED) {
 		dev_dbg(&udev->dev, "usb %sresume\n", "wakeup-");
 		usb_mark_last_busy(udev);
-		status = usb_external_resume_device(udev);
+		status = usb_external_resume_device(udev, PMSG_REMOTE_RESUME);
 	}
 	return status;
 }
@@ -2215,14 +2217,14 @@ static int remote_wakeup(struct usb_device *udev)
 
 /* When CONFIG_USB_SUSPEND isn't set, we never suspend or resume any ports. */
 
-int usb_port_suspend(struct usb_device *udev)
+int usb_port_suspend(struct usb_device *udev, pm_message_t msg)
 {
 	return 0;
 }
 
 /* However we may need to do a reset-resume */
 
-int usb_port_resume(struct usb_device *udev)
+int usb_port_resume(struct usb_device *udev, pm_message_t msg)
 {
 	struct usb_hub	*hub = hdev_to_hub(udev->parent);
 	int		port1 = udev->portnum;
@@ -2262,7 +2264,7 @@ static int hub_suspend(struct usb_interface *intf, pm_message_t msg)
 
 		udev = hdev->children [port1-1];
 		if (udev && udev->can_submit) {
-			if (!hdev->auto_pm)
+			if (!(msg.event & PM_EVENT_AUTO))
 				dev_dbg(&intf->dev, "port %d nyet suspended\n",
 						port1);
 			return -EBUSY;
@@ -3517,3 +3519,46 @@ int usb_reset_device(struct usb_device *udev)
 	return ret;
 }
 EXPORT_SYMBOL_GPL(usb_reset_device);
+
+
+/**
+ * usb_queue_reset_device - Reset a USB device from an atomic context
+ * @iface: USB interface belonging to the device to reset
+ *
+ * This function can be used to reset a USB device from an atomic
+ * context, where usb_reset_device() won't work (as it blocks).
+ *
+ * Doing a reset via this method is functionally equivalent to calling
+ * usb_reset_device(), except for the fact that it is delayed to a
+ * workqueue. This means that any drivers bound to other interfaces
+ * might be unbound, as well as users from usbfs in user space.
+ *
+ * Corner cases:
+ *
+ * - Scheduling two resets at the same time from two different drivers
+ *   attached to two different interfaces of the same device is
+ *   possible; depending on how the driver attached to each interface
+ *   handles ->pre_reset(), the second reset might happen or not.
+ *
+ * - If a driver is unbound and it had a pending reset, the reset will
+ *   be cancelled.
+ *
+ * - This function can be called during .probe() or .disconnect()
+ *   times. On return from .disconnect(), any pending resets will be
+ *   cancelled.
+ *
+ * There is no no need to lock/unlock the @reset_ws as schedule_work()
+ * does its own.
+ *
+ * NOTE: We don't do any reference count tracking because it is not
+ *     needed. The lifecycle of the work_struct is tied to the
+ *     usb_interface. Before destroying the interface we cancel the
+ *     work_struct, so the fact that work_struct is queued and or
+ *     running means the interface (and thus, the device) exist and
+ *     are referenced.
+ */
+void usb_queue_reset_device(struct usb_interface *iface)
+{
+	schedule_work(&iface->reset_ws);
+}
+EXPORT_SYMBOL_GPL(usb_queue_reset_device);
diff --git a/drivers/usb/core/message.c b/drivers/usb/core/message.c
index 6d1048faf08e..aadf29f09c45 100644
--- a/drivers/usb/core/message.c
+++ b/drivers/usb/core/message.c
@@ -139,9 +139,9 @@ int usb_control_msg(struct usb_device *dev, unsigned int pipe, __u8 request,
 
 	dr->bRequestType = requesttype;
 	dr->bRequest = request;
-	dr->wValue = cpu_to_le16p(&value);
-	dr->wIndex = cpu_to_le16p(&index);
-	dr->wLength = cpu_to_le16p(&size);
+	dr->wValue = cpu_to_le16(value);
+	dr->wIndex = cpu_to_le16(index);
+	dr->wLength = cpu_to_le16(size);
 
 	/* dbg("usb_control_msg"); */
 
@@ -1441,6 +1441,46 @@ static struct usb_interface_assoc_descriptor *find_iad(struct usb_device *dev,
 	return retval;
 }
 
+
+/*
+ * Internal function to queue a device reset
+ *
+ * This is initialized into the workstruct in 'struct
+ * usb_device->reset_ws' that is launched by
+ * message.c:usb_set_configuration() when initializing each 'struct
+ * usb_interface'.
+ *
+ * It is safe to get the USB device without reference counts because
+ * the life cycle of @iface is bound to the life cycle of @udev. Then,
+ * this function will be ran only if @iface is alive (and before
+ * freeing it any scheduled instances of it will have been cancelled).
+ *
+ * We need to set a flag (usb_dev->reset_running) because when we call
+ * the reset, the interfaces might be unbound. The current interface
+ * cannot try to remove the queued work as it would cause a deadlock
+ * (you cannot remove your work from within your executing
+ * workqueue). This flag lets it know, so that
+ * usb_cancel_queued_reset() doesn't try to do it.
+ *
+ * See usb_queue_reset_device() for more details
+ */
+void __usb_queue_reset_device(struct work_struct *ws)
+{
+	int rc;
+	struct usb_interface *iface =
+		container_of(ws, struct usb_interface, reset_ws);
+	struct usb_device *udev = interface_to_usbdev(iface);
+
+	rc = usb_lock_device_for_reset(udev, iface);
+	if (rc >= 0) {
+		iface->reset_running = 1;
+		usb_reset_device(udev);
+		iface->reset_running = 0;
+		usb_unlock_device(udev);
+	}
+}
+
+
 /*
  * usb_set_configuration - Makes a particular device setting be current
  * @dev: the device whose configuration is being updated
@@ -1611,6 +1651,7 @@ free_interfaces:
 		intf->dev.type = &usb_if_device_type;
 		intf->dev.groups = usb_interface_groups;
 		intf->dev.dma_mask = dev->dev.dma_mask;
+		INIT_WORK(&intf->reset_ws, __usb_queue_reset_device);
 		device_initialize(&intf->dev);
 		mark_quiesced(intf);
 		dev_set_name(&intf->dev, "%d-%s:%d.%d",
diff --git a/drivers/usb/core/sysfs.c b/drivers/usb/core/sysfs.c
index 4fb65fdc9dc3..0f0ccf640114 100644
--- a/drivers/usb/core/sysfs.c
+++ b/drivers/usb/core/sysfs.c
@@ -359,19 +359,19 @@ set_level(struct device *dev, struct device_attribute *attr,
 			strncmp(buf, on_string, len) == 0) {
 		udev->autosuspend_disabled = 1;
 		udev->autoresume_disabled = 0;
-		rc = usb_external_resume_device(udev);
+		rc = usb_external_resume_device(udev, PMSG_USER_RESUME);
 
 	} else if (len == sizeof auto_string - 1 &&
 			strncmp(buf, auto_string, len) == 0) {
 		udev->autosuspend_disabled = 0;
 		udev->autoresume_disabled = 0;
-		rc = usb_external_resume_device(udev);
+		rc = usb_external_resume_device(udev, PMSG_USER_RESUME);
 
 	} else if (len == sizeof suspend_string - 1 &&
 			strncmp(buf, suspend_string, len) == 0) {
 		udev->autosuspend_disabled = 0;
 		udev->autoresume_disabled = 1;
-		rc = usb_external_suspend_device(udev, PMSG_SUSPEND);
+		rc = usb_external_suspend_device(udev, PMSG_USER_SUSPEND);
 
 	} else
 		rc = -EINVAL;
@@ -812,32 +812,11 @@ struct attribute_group *usb_interface_groups[] = {
 	NULL
 };
 
-static inline void usb_create_intf_ep_files(struct usb_interface *intf,
-		struct usb_device *udev)
-{
-	struct usb_host_interface *iface_desc;
-	int i;
-
-	iface_desc = intf->cur_altsetting;
-	for (i = 0; i < iface_desc->desc.bNumEndpoints; ++i)
-		usb_create_ep_files(&intf->dev, &iface_desc->endpoint[i],
-				udev);
-}
-
-static inline void usb_remove_intf_ep_files(struct usb_interface *intf)
-{
-	struct usb_host_interface *iface_desc;
-	int i;
-
-	iface_desc = intf->cur_altsetting;
-	for (i = 0; i < iface_desc->desc.bNumEndpoints; ++i)
-		usb_remove_ep_files(&iface_desc->endpoint[i]);
-}
-
 int usb_create_sysfs_intf_files(struct usb_interface *intf)
 {
 	struct usb_device *udev = interface_to_usbdev(intf);
 	struct usb_host_interface *alt = intf->cur_altsetting;
+	int i;
 	int retval;
 
 	if (intf->sysfs_files_created || intf->unregistering)
@@ -851,18 +830,22 @@ int usb_create_sysfs_intf_files(struct usb_interface *intf)
 		alt->string = usb_cache_string(udev, alt->desc.iInterface);
 	if (alt->string)
 		retval = device_create_file(&intf->dev, &dev_attr_interface);
-	usb_create_intf_ep_files(intf, udev);
+	for (i = 0; i < alt->desc.bNumEndpoints; ++i)
+		usb_create_ep_files(&intf->dev, &alt->endpoint[i], udev);
 	intf->sysfs_files_created = 1;
 	return 0;
 }
 
 void usb_remove_sysfs_intf_files(struct usb_interface *intf)
 {
-	struct device *dev = &intf->dev;
+	struct usb_host_interface *alt = intf->cur_altsetting;
+	int i;
 
 	if (!intf->sysfs_files_created)
 		return;
-	usb_remove_intf_ep_files(intf);
-	device_remove_file(dev, &dev_attr_interface);
+
+	for (i = 0; i < alt->desc.bNumEndpoints; ++i)
+		usb_remove_ep_files(&alt->endpoint[i]);
+	device_remove_file(&intf->dev, &dev_attr_interface);
 	intf->sysfs_files_created = 0;
 }
diff --git a/drivers/usb/core/usb.c b/drivers/usb/core/usb.c
index be1fa0723f2c..18ffa17f4b32 100644
--- a/drivers/usb/core/usb.c
+++ b/drivers/usb/core/usb.c
@@ -253,7 +253,7 @@ static int usb_dev_prepare(struct device *dev)
 static void usb_dev_complete(struct device *dev)
 {
 	/* Currently used only for rebinding interfaces */
-	usb_resume(dev);	/* Implement eventually? */
+	usb_resume(dev, PMSG_RESUME);	/* Message event is meaningless */
 }
 
 static int usb_dev_suspend(struct device *dev)
@@ -263,7 +263,7 @@ static int usb_dev_suspend(struct device *dev)
 
 static int usb_dev_resume(struct device *dev)
 {
-	return usb_resume(dev);
+	return usb_resume(dev, PMSG_RESUME);
 }
 
 static int usb_dev_freeze(struct device *dev)
@@ -273,7 +273,7 @@ static int usb_dev_freeze(struct device *dev)
 
 static int usb_dev_thaw(struct device *dev)
 {
-	return usb_resume(dev);
+	return usb_resume(dev, PMSG_THAW);
 }
 
 static int usb_dev_poweroff(struct device *dev)
@@ -283,10 +283,10 @@ static int usb_dev_poweroff(struct device *dev)
 
 static int usb_dev_restore(struct device *dev)
 {
-	return usb_resume(dev);
+	return usb_resume(dev, PMSG_RESTORE);
 }
 
-static struct pm_ops usb_device_pm_ops = {
+static struct dev_pm_ops usb_device_pm_ops = {
 	.prepare =	usb_dev_prepare,
 	.complete =	usb_dev_complete,
 	.suspend =	usb_dev_suspend,
@@ -301,7 +301,7 @@ static struct pm_ops usb_device_pm_ops = {
 
 #define ksuspend_usb_init()	0
 #define ksuspend_usb_cleanup()	do {} while (0)
-#define usb_device_pm_ops	(*(struct pm_ops *)0)
+#define usb_device_pm_ops	(*(struct dev_pm_ops *)0)
 
 #endif	/* CONFIG_PM */
 
@@ -402,6 +402,7 @@ struct usb_device *usb_alloc_dev(struct usb_device *parent,
 #ifdef	CONFIG_PM
 	mutex_init(&dev->pm_mutex);
 	INIT_DELAYED_WORK(&dev->autosuspend, usb_autosuspend_work);
+	INIT_WORK(&dev->autoresume, usb_autoresume_work);
 	dev->autosuspend_delay = usb_autosuspend_delay * HZ;
 	dev->connect_time = jiffies;
 	dev->active_duration = -jiffies;
@@ -513,10 +514,7 @@ EXPORT_SYMBOL_GPL(usb_put_intf);
  * disconnect; in some drivers (such as usb-storage) the disconnect()
  * or suspend() method will block waiting for a device reset to complete.
  *
- * Returns a negative error code for failure, otherwise 1 or 0 to indicate
- * that the device will or will not have to be unlocked.  (0 can be
- * returned when an interface is given and is BINDING, because in that
- * case the driver already owns the device lock.)
+ * Returns a negative error code for failure, otherwise 0.
  */
 int usb_lock_device_for_reset(struct usb_device *udev,
 			      const struct usb_interface *iface)
@@ -527,16 +525,9 @@ int usb_lock_device_for_reset(struct usb_device *udev,
 		return -ENODEV;
 	if (udev->state == USB_STATE_SUSPENDED)
 		return -EHOSTUNREACH;
-	if (iface) {
-		switch (iface->condition) {
-		case USB_INTERFACE_BINDING:
-			return 0;
-		case USB_INTERFACE_BOUND:
-			break;
-		default:
-			return -EINTR;
-		}
-	}
+	if (iface && (iface->condition == USB_INTERFACE_UNBINDING ||
+			iface->condition == USB_INTERFACE_UNBOUND))
+		return -EINTR;
 
 	while (usb_trylock_device(udev) != 0) {
 
@@ -550,10 +541,11 @@ int usb_lock_device_for_reset(struct usb_device *udev,
 			return -ENODEV;
 		if (udev->state == USB_STATE_SUSPENDED)
 			return -EHOSTUNREACH;
-		if (iface && iface->condition != USB_INTERFACE_BOUND)
+		if (iface && (iface->condition == USB_INTERFACE_UNBINDING ||
+				iface->condition == USB_INTERFACE_UNBOUND))
 			return -EINTR;
 	}
-	return 1;
+	return 0;
 }
 EXPORT_SYMBOL_GPL(usb_lock_device_for_reset);
 
@@ -962,9 +954,6 @@ void usb_buffer_unmap_sg(const struct usb_device *dev, int is_in,
 }
 EXPORT_SYMBOL_GPL(usb_buffer_unmap_sg);
 
-/* format to disable USB on kernel command line is: nousb */
-__module_param_call("", nousb, param_set_bool, param_get_bool, &nousb, 0444);
-
 /*
  * for external read access to <nousb>
  */
@@ -1052,6 +1041,11 @@ static void __exit usb_exit(void)
 	ksuspend_usb_cleanup();
 }
 
+/* To disable USB, kernel command line is 'nousb' not 'usbcore.nousb' */
+#undef MODULE_PARAM_PREFIX
+#define MODULE_PARAM_PREFIX
+module_param(nousb, bool, 0444);
+
 subsys_initcall(usb_init);
 module_exit(usb_exit);
 MODULE_LICENSE("GPL");
diff --git a/drivers/usb/core/usb.h b/drivers/usb/core/usb.h
index 9a1a45ac3add..9fb195665fa8 100644
--- a/drivers/usb/core/usb.h
+++ b/drivers/usb/core/usb.h
@@ -1,3 +1,5 @@
+#include <linux/pm.h>
+
 /* Functions local to drivers/usb/core/ */
 
 extern int usb_create_sysfs_dev_files(struct usb_device *dev);
@@ -42,14 +44,16 @@ extern void usb_host_cleanup(void);
 #ifdef	CONFIG_PM
 
 extern int usb_suspend(struct device *dev, pm_message_t msg);
-extern int usb_resume(struct device *dev);
+extern int usb_resume(struct device *dev, pm_message_t msg);
 
 extern void usb_autosuspend_work(struct work_struct *work);
-extern int usb_port_suspend(struct usb_device *dev);
-extern int usb_port_resume(struct usb_device *dev);
+extern void usb_autoresume_work(struct work_struct *work);
+extern int usb_port_suspend(struct usb_device *dev, pm_message_t msg);
+extern int usb_port_resume(struct usb_device *dev, pm_message_t msg);
 extern int usb_external_suspend_device(struct usb_device *udev,
 		pm_message_t msg);
-extern int usb_external_resume_device(struct usb_device *udev);
+extern int usb_external_resume_device(struct usb_device *udev,
+		pm_message_t msg);
 
 static inline void usb_pm_lock(struct usb_device *udev)
 {
@@ -63,12 +67,12 @@ static inline void usb_pm_unlock(struct usb_device *udev)
 
 #else
 
-static inline int usb_port_suspend(struct usb_device *udev)
+static inline int usb_port_suspend(struct usb_device *udev, pm_message_t msg)
 {
 	return 0;
 }
 
-static inline int usb_port_resume(struct usb_device *udev)
+static inline int usb_port_resume(struct usb_device *udev, pm_message_t msg)
 {
 	return 0;
 }
diff --git a/drivers/usb/gadget/Kconfig b/drivers/usb/gadget/Kconfig
index dd4cd5a51370..b61d101184d5 100644
--- a/drivers/usb/gadget/Kconfig
+++ b/drivers/usb/gadget/Kconfig
@@ -305,6 +305,27 @@ config USB_GADGET_MUSB_HDRC
 	  This OTG-capable silicon IP is used in dual designs including
 	  the TI DaVinci, OMAP 243x, OMAP 343x, and TUSB 6010.
 
+config USB_GADGET_IMX
+	boolean "Freescale IMX USB Peripheral Controller"
+	depends on ARCH_MX1
+	help
+	   Freescale's IMX series include an integrated full speed
+	   USB 1.1 device controller.  The controller in the IMX series
+	   is register-compatible.
+
+	   It has Six fixed-function endpoints, as well as endpoint
+	   zero (for control transfers).
+
+	   Say "y" to link the driver statically, or "m" to build a
+	   dynamically linked module called "imx_udc" and force all
+	   gadget drivers to also be dynamically linked.
+
+config USB_IMX
+	tristate
+	depends on USB_GADGET_IMX
+	default USB_GADGET
+	select USB_GADGET_SELECTED
+
 config USB_GADGET_M66592
 	boolean "Renesas M66592 USB Peripheral Controller"
 	select USB_GADGET_DUALSPEED
@@ -377,6 +398,24 @@ config USB_FSL_QE
 	default USB_GADGET
 	select USB_GADGET_SELECTED
 
+config USB_GADGET_CI13XXX
+	boolean "MIPS USB CI13xxx"
+	depends on PCI
+	select USB_GADGET_DUALSPEED
+	help
+	  MIPS USB IP core family device controller
+	  Currently it only supports IP part number CI13412
+
+	  Say "y" to link the driver statically, or "m" to build a
+	  dynamically linked module called "ci13xxx_udc" and force all
+	  gadget drivers to also be dynamically linked.
+
+config USB_CI13XXX
+	tristate
+	depends on USB_GADGET_CI13XXX
+	default USB_GADGET
+	select USB_GADGET_SELECTED
+
 config USB_GADGET_NET2280
 	boolean "NetChip 228x"
 	depends on PCI
diff --git a/drivers/usb/gadget/Makefile b/drivers/usb/gadget/Makefile
index bd4041b47dce..39a51d746cb7 100644
--- a/drivers/usb/gadget/Makefile
+++ b/drivers/usb/gadget/Makefile
@@ -10,6 +10,7 @@ obj-$(CONFIG_USB_NET2280)	+= net2280.o
 obj-$(CONFIG_USB_AMD5536UDC)	+= amd5536udc.o
 obj-$(CONFIG_USB_PXA25X)	+= pxa25x_udc.o
 obj-$(CONFIG_USB_PXA27X)	+= pxa27x_udc.o
+obj-$(CONFIG_USB_IMX)		+= imx_udc.o
 obj-$(CONFIG_USB_GOKU)		+= goku_udc.o
 obj-$(CONFIG_USB_OMAP)		+= omap_udc.o
 obj-$(CONFIG_USB_LH7A40X)	+= lh7a40x_udc.o
@@ -19,6 +20,7 @@ obj-$(CONFIG_USB_ATMEL_USBA)	+= atmel_usba_udc.o
 obj-$(CONFIG_USB_FSL_USB2)	+= fsl_usb2_udc.o
 obj-$(CONFIG_USB_M66592)	+= m66592-udc.o
 obj-$(CONFIG_USB_FSL_QE)	+= fsl_qe_udc.o
+obj-$(CONFIG_USB_CI13XXX)	+= ci13xxx_udc.o
 
 #
 # USB gadget drivers
diff --git a/drivers/usb/gadget/at91_udc.c b/drivers/usb/gadget/at91_udc.c
index a8a1de413321..0b2bb8f0706d 100644
--- a/drivers/usb/gadget/at91_udc.c
+++ b/drivers/usb/gadget/at91_udc.c
@@ -1474,7 +1474,7 @@ static struct at91_udc controller = {
 		.ep0	= &controller.ep[0].ep,
 		.name	= driver_name,
 		.dev	= {
-			.bus_id = "gadget",
+			.init_name = "gadget",
 			.release = nop_release,
 		}
 	},
diff --git a/drivers/usb/gadget/atmel_usba_udc.c b/drivers/usb/gadget/atmel_usba_udc.c
index ae30ab1d264f..65b03e3445a1 100644
--- a/drivers/usb/gadget/atmel_usba_udc.c
+++ b/drivers/usb/gadget/atmel_usba_udc.c
@@ -1034,7 +1034,7 @@ static struct usba_udc the_udc = {
 		.is_dualspeed	= 1,
 		.name		= "atmel_usba_udc",
 		.dev	= {
-			.bus_id		= "gadget",
+			.init_name	= "gadget",
 			.release	= nop_release,
 		},
 	},
diff --git a/drivers/usb/gadget/ci13xxx_udc.c b/drivers/usb/gadget/ci13xxx_udc.c
new file mode 100644
index 000000000000..bebf911c7e5f
--- /dev/null
+++ b/drivers/usb/gadget/ci13xxx_udc.c
@@ -0,0 +1,2830 @@
+/*
+ * ci13xxx_udc.c - MIPS USB IP core family device controller
+ *
+ * Copyright (C) 2008 Chipidea - MIPS Technologies, Inc. All rights reserved.
+ *
+ * Author: David Lopo
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+/*
+ * Description: MIPS USB IP core family device controller
+ *              Currently it only supports IP part number CI13412
+ *
+ * This driver is composed of several blocks:
+ * - HW:     hardware interface
+ * - DBG:    debug facilities (optional)
+ * - UTIL:   utilities
+ * - ISR:    interrupts handling
+ * - ENDPT:  endpoint operations (Gadget API)
+ * - GADGET: gadget operations (Gadget API)
+ * - BUS:    bus glue code, bus abstraction layer
+ * - PCI:    PCI core interface and PCI resources (interrupts, memory...)
+ *
+ * Compile Options
+ * - CONFIG_USB_GADGET_DEBUG_FILES: enable debug facilities
+ * - STALL_IN:  non-empty bulk-in pipes cannot be halted
+ *              if defined mass storage compliance succeeds but with warnings
+ *              => case 4: Hi >  Dn
+ *              => case 5: Hi >  Di
+ *              => case 8: Hi <> Do
+ *              if undefined usbtest 13 fails
+ * - TRACE:     enable function tracing (depends on DEBUG)
+ *
+ * Main Features
+ * - Chapter 9 & Mass Storage Compliance with Gadget File Storage
+ * - Chapter 9 Compliance with Gadget Zero (STALL_IN undefined)
+ * - Normal & LPM support
+ *
+ * USBTEST Report
+ * - OK: 0-12, 13 (STALL_IN defined) & 14
+ * - Not Supported: 15 & 16 (ISO)
+ *
+ * TODO List
+ * - OTG
+ * - Isochronous & Interrupt Traffic
+ * - Handle requests which spawns into several TDs
+ * - GET_STATUS(device) - always reports 0
+ * - Gadget API (majority of optional features)
+ * - Suspend & Remote Wakeup
+ */
+#include <linux/device.h>
+#include <linux/dmapool.h>
+#include <linux/dma-mapping.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/irq.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/usb/ch9.h>
+#include <linux/usb/gadget.h>
+
+#include "ci13xxx_udc.h"
+
+
+/******************************************************************************
+ * DEFINE
+ *****************************************************************************/
+/* ctrl register bank access */
+static DEFINE_SPINLOCK(udc_lock);
+
+/* driver name */
+#define UDC_DRIVER_NAME   "ci13xxx_udc"
+
+/* control endpoint description */
+static const struct usb_endpoint_descriptor
+ctrl_endpt_desc = {
+	.bLength         = USB_DT_ENDPOINT_SIZE,
+	.bDescriptorType = USB_DT_ENDPOINT,
+
+	.bmAttributes    = USB_ENDPOINT_XFER_CONTROL,
+	.wMaxPacketSize  = cpu_to_le16(CTRL_PAYLOAD_MAX),
+};
+
+/* UDC descriptor */
+static struct ci13xxx *_udc;
+
+/* Interrupt statistics */
+#define ISR_MASK   0x1F
+static struct {
+	u32 test;
+	u32 ui;
+	u32 uei;
+	u32 pci;
+	u32 uri;
+	u32 sli;
+	u32 none;
+	struct {
+		u32 cnt;
+		u32 buf[ISR_MASK+1];
+		u32 idx;
+	} hndl;
+} isr_statistics;
+
+/**
+ * ffs_nr: find first (least significant) bit set
+ * @x: the word to search
+ *
+ * This function returns bit number (instead of position)
+ */
+static int ffs_nr(u32 x)
+{
+	int n = ffs(x);
+
+	return n ? n-1 : 32;
+}
+
+/******************************************************************************
+ * HW block
+ *****************************************************************************/
+/* register bank descriptor */
+static struct {
+	unsigned      lpm;    /* is LPM? */
+	void __iomem *abs;    /* bus map offset */
+	void __iomem *cap;    /* bus map offset + CAP offset + CAP data */
+	size_t        size;   /* bank size */
+} hw_bank;
+
+/* UDC register map */
+#define ABS_CAPLENGTH       (0x100UL)
+#define ABS_HCCPARAMS       (0x108UL)
+#define ABS_DCCPARAMS       (0x124UL)
+#define ABS_TESTMODE        (hw_bank.lpm ? 0x0FCUL : 0x138UL)
+/* offset to CAPLENTGH (addr + data) */
+#define CAP_USBCMD          (0x000UL)
+#define CAP_USBSTS          (0x004UL)
+#define CAP_USBINTR         (0x008UL)
+#define CAP_DEVICEADDR      (0x014UL)
+#define CAP_ENDPTLISTADDR   (0x018UL)
+#define CAP_PORTSC          (0x044UL)
+#define CAP_DEVLC           (0x0B4UL)
+#define CAP_USBMODE         (hw_bank.lpm ? 0x0C8UL : 0x068UL)
+#define CAP_ENDPTSETUPSTAT  (hw_bank.lpm ? 0x0D8UL : 0x06CUL)
+#define CAP_ENDPTPRIME      (hw_bank.lpm ? 0x0DCUL : 0x070UL)
+#define CAP_ENDPTFLUSH      (hw_bank.lpm ? 0x0E0UL : 0x074UL)
+#define CAP_ENDPTSTAT       (hw_bank.lpm ? 0x0E4UL : 0x078UL)
+#define CAP_ENDPTCOMPLETE   (hw_bank.lpm ? 0x0E8UL : 0x07CUL)
+#define CAP_ENDPTCTRL       (hw_bank.lpm ? 0x0ECUL : 0x080UL)
+#define CAP_LAST            (hw_bank.lpm ? 0x12CUL : 0x0C0UL)
+
+/* maximum number of enpoints: valid only after hw_device_reset() */
+static unsigned hw_ep_max;
+
+/**
+ * hw_ep_bit: calculates the bit number
+ * @num: endpoint number
+ * @dir: endpoint direction
+ *
+ * This function returns bit number
+ */
+static inline int hw_ep_bit(int num, int dir)
+{
+	return num + (dir ? 16 : 0);
+}
+
+/**
+ * hw_aread: reads from register bitfield
+ * @addr: address relative to bus map
+ * @mask: bitfield mask
+ *
+ * This function returns register bitfield data
+ */
+static u32 hw_aread(u32 addr, u32 mask)
+{
+	return ioread32(addr + hw_bank.abs) & mask;
+}
+
+/**
+ * hw_awrite: writes to register bitfield
+ * @addr: address relative to bus map
+ * @mask: bitfield mask
+ * @data: new data
+ */
+static void hw_awrite(u32 addr, u32 mask, u32 data)
+{
+	iowrite32(hw_aread(addr, ~mask) | (data & mask),
+		  addr + hw_bank.abs);
+}
+
+/**
+ * hw_cread: reads from register bitfield
+ * @addr: address relative to CAP offset plus content
+ * @mask: bitfield mask
+ *
+ * This function returns register bitfield data
+ */
+static u32 hw_cread(u32 addr, u32 mask)
+{
+	return ioread32(addr + hw_bank.cap) & mask;
+}
+
+/**
+ * hw_cwrite: writes to register bitfield
+ * @addr: address relative to CAP offset plus content
+ * @mask: bitfield mask
+ * @data: new data
+ */
+static void hw_cwrite(u32 addr, u32 mask, u32 data)
+{
+	iowrite32(hw_cread(addr, ~mask) | (data & mask),
+		  addr + hw_bank.cap);
+}
+
+/**
+ * hw_ctest_and_clear: tests & clears register bitfield
+ * @addr: address relative to CAP offset plus content
+ * @mask: bitfield mask
+ *
+ * This function returns register bitfield data
+ */
+static u32 hw_ctest_and_clear(u32 addr, u32 mask)
+{
+	u32 reg = hw_cread(addr, mask);
+
+	iowrite32(reg, addr + hw_bank.cap);
+	return reg;
+}
+
+/**
+ * hw_ctest_and_write: tests & writes register bitfield
+ * @addr: address relative to CAP offset plus content
+ * @mask: bitfield mask
+ * @data: new data
+ *
+ * This function returns register bitfield data
+ */
+static u32 hw_ctest_and_write(u32 addr, u32 mask, u32 data)
+{
+	u32 reg = hw_cread(addr, ~0);
+
+	iowrite32((reg & ~mask) | (data & mask), addr + hw_bank.cap);
+	return (reg & mask) >> ffs_nr(mask);
+}
+
+/**
+ * hw_device_reset: resets chip (execute without interruption)
+ * @base: register base address
+ *
+ * This function returns an error code
+ */
+static int hw_device_reset(void __iomem *base)
+{
+	u32 reg;
+
+	/* bank is a module variable */
+	hw_bank.abs = base;
+
+	hw_bank.cap = hw_bank.abs;
+	hw_bank.cap += ABS_CAPLENGTH;
+	hw_bank.cap += ioread8(hw_bank.cap);
+
+	reg = hw_aread(ABS_HCCPARAMS, HCCPARAMS_LEN) >> ffs_nr(HCCPARAMS_LEN);
+	hw_bank.lpm  = reg;
+	hw_bank.size = hw_bank.cap - hw_bank.abs;
+	hw_bank.size += CAP_LAST;
+	hw_bank.size /= sizeof(u32);
+
+	/* should flush & stop before reset */
+	hw_cwrite(CAP_ENDPTFLUSH, ~0, ~0);
+	hw_cwrite(CAP_USBCMD, USBCMD_RS, 0);
+
+	hw_cwrite(CAP_USBCMD, USBCMD_RST, USBCMD_RST);
+	while (hw_cread(CAP_USBCMD, USBCMD_RST))
+		udelay(10);             /* not RTOS friendly */
+
+	/* USBMODE should be configured step by step */
+	hw_cwrite(CAP_USBMODE, USBMODE_CM, USBMODE_CM_IDLE);
+	hw_cwrite(CAP_USBMODE, USBMODE_CM, USBMODE_CM_DEVICE);
+	hw_cwrite(CAP_USBMODE, USBMODE_SLOM, USBMODE_SLOM);  /* HW >= 2.3 */
+
+	if (hw_cread(CAP_USBMODE, USBMODE_CM) != USBMODE_CM_DEVICE) {
+		pr_err("cannot enter in device mode");
+		pr_err("lpm = %i", hw_bank.lpm);
+		return -ENODEV;
+	}
+
+	reg = hw_aread(ABS_DCCPARAMS, DCCPARAMS_DEN) >> ffs_nr(DCCPARAMS_DEN);
+	if (reg == 0 || reg > ENDPT_MAX)
+		return -ENODEV;
+
+	hw_ep_max = reg;   /* cache hw ENDPT_MAX */
+
+	/* setup lock mode ? */
+
+	/* ENDPTSETUPSTAT is '0' by default */
+
+	/* HCSPARAMS.bf.ppc SHOULD BE zero for device */
+
+	return 0;
+}
+
+/**
+ * hw_device_state: enables/disables interrupts & starts/stops device (execute
+ *                  without interruption)
+ * @dma: 0 => disable, !0 => enable and set dma engine
+ *
+ * This function returns an error code
+ */
+static int hw_device_state(u32 dma)
+{
+	if (dma) {
+		hw_cwrite(CAP_ENDPTLISTADDR, ~0, dma);
+		/* interrupt, error, port change, reset, sleep/suspend */
+		hw_cwrite(CAP_USBINTR, ~0,
+			     USBi_UI|USBi_UEI|USBi_PCI|USBi_URI|USBi_SLI);
+		hw_cwrite(CAP_USBCMD, USBCMD_RS, USBCMD_RS);
+	} else {
+		hw_cwrite(CAP_USBCMD, USBCMD_RS, 0);
+		hw_cwrite(CAP_USBINTR, ~0, 0);
+	}
+	return 0;
+}
+
+/**
+ * hw_ep_flush: flush endpoint fifo (execute without interruption)
+ * @num: endpoint number
+ * @dir: endpoint direction
+ *
+ * This function returns an error code
+ */
+static int hw_ep_flush(int num, int dir)
+{
+	int n = hw_ep_bit(num, dir);
+
+	do {
+		/* flush any pending transfer */
+		hw_cwrite(CAP_ENDPTFLUSH, BIT(n), BIT(n));
+		while (hw_cread(CAP_ENDPTFLUSH, BIT(n)))
+			cpu_relax();
+	} while (hw_cread(CAP_ENDPTSTAT, BIT(n)));
+
+	return 0;
+}
+
+/**
+ * hw_ep_disable: disables endpoint (execute without interruption)
+ * @num: endpoint number
+ * @dir: endpoint direction
+ *
+ * This function returns an error code
+ */
+static int hw_ep_disable(int num, int dir)
+{
+	hw_ep_flush(num, dir);
+	hw_cwrite(CAP_ENDPTCTRL + num * sizeof(u32),
+		  dir ? ENDPTCTRL_TXE : ENDPTCTRL_RXE, 0);
+	return 0;
+}
+
+/**
+ * hw_ep_enable: enables endpoint (execute without interruption)
+ * @num:  endpoint number
+ * @dir:  endpoint direction
+ * @type: endpoint type
+ *
+ * This function returns an error code
+ */
+static int hw_ep_enable(int num, int dir, int type)
+{
+	u32 mask, data;
+
+	if (dir) {
+		mask  = ENDPTCTRL_TXT;  /* type    */
+		data  = type << ffs_nr(mask);
+
+		mask |= ENDPTCTRL_TXS;  /* unstall */
+		mask |= ENDPTCTRL_TXR;  /* reset data toggle */
+		data |= ENDPTCTRL_TXR;
+		mask |= ENDPTCTRL_TXE;  /* enable  */
+		data |= ENDPTCTRL_TXE;
+	} else {
+		mask  = ENDPTCTRL_RXT;  /* type    */
+		data  = type << ffs_nr(mask);
+
+		mask |= ENDPTCTRL_RXS;  /* unstall */
+		mask |= ENDPTCTRL_RXR;  /* reset data toggle */
+		data |= ENDPTCTRL_RXR;
+		mask |= ENDPTCTRL_RXE;  /* enable  */
+		data |= ENDPTCTRL_RXE;
+	}
+	hw_cwrite(CAP_ENDPTCTRL + num * sizeof(u32), mask, data);
+	return 0;
+}
+
+/**
+ * hw_ep_get_halt: return endpoint halt status
+ * @num: endpoint number
+ * @dir: endpoint direction
+ *
+ * This function returns 1 if endpoint halted
+ */
+static int hw_ep_get_halt(int num, int dir)
+{
+	u32 mask = dir ? ENDPTCTRL_TXS : ENDPTCTRL_RXS;
+
+	return hw_cread(CAP_ENDPTCTRL + num * sizeof(u32), mask) ? 1 : 0;
+}
+
+/**
+ * hw_ep_is_primed: test if endpoint is primed (execute without interruption)
+ * @num:   endpoint number
+ * @dir:   endpoint direction
+ *
+ * This function returns true if endpoint primed
+ */
+static int hw_ep_is_primed(int num, int dir)
+{
+	u32 reg = hw_cread(CAP_ENDPTPRIME, ~0) | hw_cread(CAP_ENDPTSTAT, ~0);
+
+	return test_bit(hw_ep_bit(num, dir), (void *)&reg);
+}
+
+/**
+ * hw_test_and_clear_setup_status: test & clear setup status (execute without
+ *                                 interruption)
+ * @n: bit number (endpoint)
+ *
+ * This function returns setup status
+ */
+static int hw_test_and_clear_setup_status(int n)
+{
+	return hw_ctest_and_clear(CAP_ENDPTSETUPSTAT, BIT(n));
+}
+
+/**
+ * hw_ep_prime: primes endpoint (execute without interruption)
+ * @num:     endpoint number
+ * @dir:     endpoint direction
+ * @is_ctrl: true if control endpoint
+ *
+ * This function returns an error code
+ */
+static int hw_ep_prime(int num, int dir, int is_ctrl)
+{
+	int n = hw_ep_bit(num, dir);
+
+	/* the caller should flush first */
+	if (hw_ep_is_primed(num, dir))
+		return -EBUSY;
+
+	if (is_ctrl && dir == RX && hw_cread(CAP_ENDPTSETUPSTAT, BIT(num)))
+		return -EAGAIN;
+
+	hw_cwrite(CAP_ENDPTPRIME, BIT(n), BIT(n));
+
+	while (hw_cread(CAP_ENDPTPRIME, BIT(n)))
+		cpu_relax();
+	if (is_ctrl && dir == RX  && hw_cread(CAP_ENDPTSETUPSTAT, BIT(num)))
+		return -EAGAIN;
+
+	/* status shoult be tested according with manual but it doesn't work */
+	return 0;
+}
+
+/**
+ * hw_ep_set_halt: configures ep halt & resets data toggle after clear (execute
+ *                 without interruption)
+ * @num:   endpoint number
+ * @dir:   endpoint direction
+ * @value: true => stall, false => unstall
+ *
+ * This function returns an error code
+ */
+static int hw_ep_set_halt(int num, int dir, int value)
+{
+	if (value != 0 && value != 1)
+		return -EINVAL;
+
+	do {
+		u32 addr = CAP_ENDPTCTRL + num * sizeof(u32);
+		u32 mask_xs = dir ? ENDPTCTRL_TXS : ENDPTCTRL_RXS;
+		u32 mask_xr = dir ? ENDPTCTRL_TXR : ENDPTCTRL_RXR;
+
+		/* data toggle - reserved for EP0 but it's in ESS */
+		hw_cwrite(addr, mask_xs|mask_xr, value ? mask_xs : mask_xr);
+
+	} while (value != hw_ep_get_halt(num, dir));
+
+	return 0;
+}
+
+/**
+ * hw_intr_clear: disables interrupt & clears interrupt status (execute without
+ *                interruption)
+ * @n: interrupt bit
+ *
+ * This function returns an error code
+ */
+static int hw_intr_clear(int n)
+{
+	if (n >= REG_BITS)
+		return -EINVAL;
+
+	hw_cwrite(CAP_USBINTR, BIT(n), 0);
+	hw_cwrite(CAP_USBSTS,  BIT(n), BIT(n));
+	return 0;
+}
+
+/**
+ * hw_intr_force: enables interrupt & forces interrupt status (execute without
+ *                interruption)
+ * @n: interrupt bit
+ *
+ * This function returns an error code
+ */
+static int hw_intr_force(int n)
+{
+	if (n >= REG_BITS)
+		return -EINVAL;
+
+	hw_awrite(ABS_TESTMODE, TESTMODE_FORCE, TESTMODE_FORCE);
+	hw_cwrite(CAP_USBINTR,  BIT(n), BIT(n));
+	hw_cwrite(CAP_USBSTS,   BIT(n), BIT(n));
+	hw_awrite(ABS_TESTMODE, TESTMODE_FORCE, 0);
+	return 0;
+}
+
+/**
+ * hw_is_port_high_speed: test if port is high speed
+ *
+ * This function returns true if high speed port
+ */
+static int hw_port_is_high_speed(void)
+{
+	return hw_bank.lpm ? hw_cread(CAP_DEVLC, DEVLC_PSPD) :
+		hw_cread(CAP_PORTSC, PORTSC_HSP);
+}
+
+/**
+ * hw_port_test_get: reads port test mode value
+ *
+ * This function returns port test mode value
+ */
+static u8 hw_port_test_get(void)
+{
+	return hw_cread(CAP_PORTSC, PORTSC_PTC) >> ffs_nr(PORTSC_PTC);
+}
+
+/**
+ * hw_port_test_set: writes port test mode (execute without interruption)
+ * @mode: new value
+ *
+ * This function returns an error code
+ */
+static int hw_port_test_set(u8 mode)
+{
+	const u8 TEST_MODE_MAX = 7;
+
+	if (mode > TEST_MODE_MAX)
+		return -EINVAL;
+
+	hw_cwrite(CAP_PORTSC, PORTSC_PTC, mode << ffs_nr(PORTSC_PTC));
+	return 0;
+}
+
+/**
+ * hw_read_intr_enable: returns interrupt enable register
+ *
+ * This function returns register data
+ */
+static u32 hw_read_intr_enable(void)
+{
+	return hw_cread(CAP_USBINTR, ~0);
+}
+
+/**
+ * hw_read_intr_status: returns interrupt status register
+ *
+ * This function returns register data
+ */
+static u32 hw_read_intr_status(void)
+{
+	return hw_cread(CAP_USBSTS, ~0);
+}
+
+/**
+ * hw_register_read: reads all device registers (execute without interruption)
+ * @buf:  destination buffer
+ * @size: buffer size
+ *
+ * This function returns number of registers read
+ */
+static size_t hw_register_read(u32 *buf, size_t size)
+{
+	unsigned i;
+
+	if (size > hw_bank.size)
+		size = hw_bank.size;
+
+	for (i = 0; i < size; i++)
+		buf[i] = hw_aread(i * sizeof(u32), ~0);
+
+	return size;
+}
+
+/**
+ * hw_register_write: writes to register
+ * @addr: register address
+ * @data: register value
+ *
+ * This function returns an error code
+ */
+static int hw_register_write(u16 addr, u32 data)
+{
+	/* align */
+	addr /= sizeof(u32);
+
+	if (addr >= hw_bank.size)
+		return -EINVAL;
+
+	/* align */
+	addr *= sizeof(u32);
+
+	hw_awrite(addr, ~0, data);
+	return 0;
+}
+
+/**
+ * hw_test_and_clear_complete: test & clear complete status (execute without
+ *                             interruption)
+ * @n: bit number (endpoint)
+ *
+ * This function returns complete status
+ */
+static int hw_test_and_clear_complete(int n)
+{
+	return hw_ctest_and_clear(CAP_ENDPTCOMPLETE, BIT(n));
+}
+
+/**
+ * hw_test_and_clear_intr_active: test & clear active interrupts (execute
+ *                                without interruption)
+ *
+ * This function returns active interrutps
+ */
+static u32 hw_test_and_clear_intr_active(void)
+{
+	u32 reg = hw_read_intr_status() & hw_read_intr_enable();
+
+	hw_cwrite(CAP_USBSTS, ~0, reg);
+	return reg;
+}
+
+/**
+ * hw_test_and_clear_setup_guard: test & clear setup guard (execute without
+ *                                interruption)
+ *
+ * This function returns guard value
+ */
+static int hw_test_and_clear_setup_guard(void)
+{
+	return hw_ctest_and_write(CAP_USBCMD, USBCMD_SUTW, 0);
+}
+
+/**
+ * hw_test_and_set_setup_guard: test & set setup guard (execute without
+ *                              interruption)
+ *
+ * This function returns guard value
+ */
+static int hw_test_and_set_setup_guard(void)
+{
+	return hw_ctest_and_write(CAP_USBCMD, USBCMD_SUTW, USBCMD_SUTW);
+}
+
+/**
+ * hw_usb_set_address: configures USB address (execute without interruption)
+ * @value: new USB address
+ *
+ * This function returns an error code
+ */
+static int hw_usb_set_address(u8 value)
+{
+	/* advance */
+	hw_cwrite(CAP_DEVICEADDR, DEVICEADDR_USBADR | DEVICEADDR_USBADRA,
+		  value << ffs_nr(DEVICEADDR_USBADR) | DEVICEADDR_USBADRA);
+	return 0;
+}
+
+/**
+ * hw_usb_reset: restart device after a bus reset (execute without
+ *               interruption)
+ *
+ * This function returns an error code
+ */
+static int hw_usb_reset(void)
+{
+	hw_usb_set_address(0);
+
+	/* ESS flushes only at end?!? */
+	hw_cwrite(CAP_ENDPTFLUSH,    ~0, ~0);   /* flush all EPs */
+
+	/* clear setup token semaphores */
+	hw_cwrite(CAP_ENDPTSETUPSTAT, 0,  0);   /* writes its content */
+
+	/* clear complete status */
+	hw_cwrite(CAP_ENDPTCOMPLETE,  0,  0);   /* writes its content */
+
+	/* wait until all bits cleared */
+	while (hw_cread(CAP_ENDPTPRIME, ~0))
+		udelay(10);             /* not RTOS friendly */
+
+	/* reset all endpoints ? */
+
+	/* reset internal status and wait for further instructions
+	   no need to verify the port reset status (ESS does it) */
+
+	return 0;
+}
+
+/******************************************************************************
+ * DBG block
+ *****************************************************************************/
+/**
+ * show_device: prints information about device capabilities and status
+ *
+ * Check "device.h" for details
+ */
+static ssize_t show_device(struct device *dev, struct device_attribute *attr,
+			   char *buf)
+{
+	struct ci13xxx *udc = container_of(dev, struct ci13xxx, gadget.dev);
+	struct usb_gadget *gadget = &udc->gadget;
+	int n = 0;
+
+	dbg_trace("[%s] %p\n", __func__, buf);
+	if (attr == NULL || buf == NULL) {
+		dev_err(dev, "[%s] EINVAL\n", __func__);
+		return 0;
+	}
+
+	n += scnprintf(buf + n, PAGE_SIZE - n, "speed             = %d\n",
+		       gadget->speed);
+	n += scnprintf(buf + n, PAGE_SIZE - n, "is_dualspeed      = %d\n",
+		       gadget->is_dualspeed);
+	n += scnprintf(buf + n, PAGE_SIZE - n, "is_otg            = %d\n",
+		       gadget->is_otg);
+	n += scnprintf(buf + n, PAGE_SIZE - n, "is_a_peripheral   = %d\n",
+		       gadget->is_a_peripheral);
+	n += scnprintf(buf + n, PAGE_SIZE - n, "b_hnp_enable      = %d\n",
+		       gadget->b_hnp_enable);
+	n += scnprintf(buf + n, PAGE_SIZE - n, "a_hnp_support     = %d\n",
+		       gadget->a_hnp_support);
+	n += scnprintf(buf + n, PAGE_SIZE - n, "a_alt_hnp_support = %d\n",
+		       gadget->a_alt_hnp_support);
+	n += scnprintf(buf + n, PAGE_SIZE - n, "name              = %s\n",
+		       (gadget->name ? gadget->name : ""));
+
+	return n;
+}
+static DEVICE_ATTR(device, S_IRUSR, show_device, NULL);
+
+/**
+ * show_driver: prints information about attached gadget (if any)
+ *
+ * Check "device.h" for details
+ */
+static ssize_t show_driver(struct device *dev, struct device_attribute *attr,
+			   char *buf)
+{
+	struct ci13xxx *udc = container_of(dev, struct ci13xxx, gadget.dev);
+	struct usb_gadget_driver *driver = udc->driver;
+	int n = 0;
+
+	dbg_trace("[%s] %p\n", __func__, buf);
+	if (attr == NULL || buf == NULL) {
+		dev_err(dev, "[%s] EINVAL\n", __func__);
+		return 0;
+	}
+
+	if (driver == NULL)
+		return scnprintf(buf, PAGE_SIZE,
+				 "There is no gadget attached!\n");
+
+	n += scnprintf(buf + n, PAGE_SIZE - n, "function  = %s\n",
+		       (driver->function ? driver->function : ""));
+	n += scnprintf(buf + n, PAGE_SIZE - n, "max speed = %d\n",
+		       driver->speed);
+
+	return n;
+}
+static DEVICE_ATTR(driver, S_IRUSR, show_driver, NULL);
+
+/* Maximum event message length */
+#define DBG_DATA_MSG   64UL
+
+/* Maximum event messages */
+#define DBG_DATA_MAX   128UL
+
+/* Event buffer descriptor */
+static struct {
+	char     (buf[DBG_DATA_MAX])[DBG_DATA_MSG];   /* buffer */
+	unsigned idx;   /* index */
+	unsigned tty;   /* print to console? */
+	rwlock_t lck;   /* lock */
+} dbg_data = {
+	.idx = 0,
+	.tty = 0,
+	.lck = __RW_LOCK_UNLOCKED(lck)
+};
+
+/**
+ * dbg_dec: decrements debug event index
+ * @idx: buffer index
+ */
+static void dbg_dec(unsigned *idx)
+{
+	*idx = (*idx - 1) & (DBG_DATA_MAX-1);
+}
+
+/**
+ * dbg_inc: increments debug event index
+ * @idx: buffer index
+ */
+static void dbg_inc(unsigned *idx)
+{
+	*idx = (*idx + 1) & (DBG_DATA_MAX-1);
+}
+
+/**
+ * dbg_print:  prints the common part of the event
+ * @addr:   endpoint address
+ * @name:   event name
+ * @status: status
+ * @extra:  extra information
+ */
+static void dbg_print(u8 addr, const char *name, int status, const char *extra)
+{
+	struct timeval tval;
+	unsigned int stamp;
+	unsigned long flags;
+
+	write_lock_irqsave(&dbg_data.lck, flags);
+
+	do_gettimeofday(&tval);
+	stamp = tval.tv_sec & 0xFFFF;	/* 2^32 = 4294967296. Limit to 4096s */
+	stamp = stamp * 1000000 + tval.tv_usec;
+
+	scnprintf(dbg_data.buf[dbg_data.idx], DBG_DATA_MSG,
+		  "%04X\t» %02X %-7.7s %4i «\t%s\n",
+		  stamp, addr, name, status, extra);
+
+	dbg_inc(&dbg_data.idx);
+
+	write_unlock_irqrestore(&dbg_data.lck, flags);
+
+	if (dbg_data.tty != 0)
+		pr_notice("%04X\t» %02X %-7.7s %4i «\t%s\n",
+			  stamp, addr, name, status, extra);
+}
+
+/**
+ * dbg_done: prints a DONE event
+ * @addr:   endpoint address
+ * @td:     transfer descriptor
+ * @status: status
+ */
+static void dbg_done(u8 addr, const u32 token, int status)
+{
+	char msg[DBG_DATA_MSG];
+
+	scnprintf(msg, sizeof(msg), "%d %02X",
+		  (int)(token & TD_TOTAL_BYTES) >> ffs_nr(TD_TOTAL_BYTES),
+		  (int)(token & TD_STATUS)      >> ffs_nr(TD_STATUS));
+	dbg_print(addr, "DONE", status, msg);
+}
+
+/**
+ * dbg_event: prints a generic event
+ * @addr:   endpoint address
+ * @name:   event name
+ * @status: status
+ */
+static void dbg_event(u8 addr, const char *name, int status)
+{
+	if (name != NULL)
+		dbg_print(addr, name, status, "");
+}
+
+/*
+ * dbg_queue: prints a QUEUE event
+ * @addr:   endpoint address
+ * @req:    USB request
+ * @status: status
+ */
+static void dbg_queue(u8 addr, const struct usb_request *req, int status)
+{
+	char msg[DBG_DATA_MSG];
+
+	if (req != NULL) {
+		scnprintf(msg, sizeof(msg),
+			  "%d %d", !req->no_interrupt, req->length);
+		dbg_print(addr, "QUEUE", status, msg);
+	}
+}
+
+/**
+ * dbg_setup: prints a SETUP event
+ * @addr: endpoint address
+ * @req:  setup request
+ */
+static void dbg_setup(u8 addr, const struct usb_ctrlrequest *req)
+{
+	char msg[DBG_DATA_MSG];
+
+	if (req != NULL) {
+		scnprintf(msg, sizeof(msg),
+			  "%02X %02X %04X %04X %d", req->bRequestType,
+			  req->bRequest, le16_to_cpu(req->wValue),
+			  le16_to_cpu(req->wIndex), le16_to_cpu(req->wLength));
+		dbg_print(addr, "SETUP", 0, msg);
+	}
+}
+
+/**
+ * show_events: displays the event buffer
+ *
+ * Check "device.h" for details
+ */
+static ssize_t show_events(struct device *dev, struct device_attribute *attr,
+			   char *buf)
+{
+	unsigned long flags;
+	unsigned i, j, n = 0;
+
+	dbg_trace("[%s] %p\n", __func__, buf);
+	if (attr == NULL || buf == NULL) {
+		dev_err(dev, "[%s] EINVAL\n", __func__);
+		return 0;
+	}
+
+	read_lock_irqsave(&dbg_data.lck, flags);
+
+	i = dbg_data.idx;
+	for (dbg_dec(&i); i != dbg_data.idx; dbg_dec(&i)) {
+		n += strlen(dbg_data.buf[i]);
+		if (n >= PAGE_SIZE) {
+			n -= strlen(dbg_data.buf[i]);
+			break;
+		}
+	}
+	for (j = 0, dbg_inc(&i); j < n; dbg_inc(&i))
+		j += scnprintf(buf + j, PAGE_SIZE - j,
+			       "%s", dbg_data.buf[i]);
+
+	read_unlock_irqrestore(&dbg_data.lck, flags);
+
+	return n;
+}
+
+/**
+ * store_events: configure if events are going to be also printed to console
+ *
+ * Check "device.h" for details
+ */
+static ssize_t store_events(struct device *dev, struct device_attribute *attr,
+			    const char *buf, size_t count)
+{
+	unsigned tty;
+
+	dbg_trace("[%s] %p, %d\n", __func__, buf, count);
+	if (attr == NULL || buf == NULL) {
+		dev_err(dev, "[%s] EINVAL\n", __func__);
+		goto done;
+	}
+
+	if (sscanf(buf, "%u", &tty) != 1 || tty > 1) {
+		dev_err(dev, "<1|0>: enable|disable console log\n");
+		goto done;
+	}
+
+	dbg_data.tty = tty;
+	dev_info(dev, "tty = %u", dbg_data.tty);
+
+ done:
+	return count;
+}
+static DEVICE_ATTR(events, S_IRUSR | S_IWUSR, show_events, store_events);
+
+/**
+ * show_inters: interrupt status, enable status and historic
+ *
+ * Check "device.h" for details
+ */
+static ssize_t show_inters(struct device *dev, struct device_attribute *attr,
+			   char *buf)
+{
+	struct ci13xxx *udc = container_of(dev, struct ci13xxx, gadget.dev);
+	unsigned long flags;
+	u32 intr;
+	unsigned i, j, n = 0;
+
+	dbg_trace("[%s] %p\n", __func__, buf);
+	if (attr == NULL || buf == NULL) {
+		dev_err(dev, "[%s] EINVAL\n", __func__);
+		return 0;
+	}
+
+	spin_lock_irqsave(udc->lock, flags);
+
+	n += scnprintf(buf + n, PAGE_SIZE - n,
+		       "status = %08x\n", hw_read_intr_status());
+	n += scnprintf(buf + n, PAGE_SIZE - n,
+		       "enable = %08x\n", hw_read_intr_enable());
+
+	n += scnprintf(buf + n, PAGE_SIZE - n, "*test = %d\n",
+		       isr_statistics.test);
+	n += scnprintf(buf + n, PAGE_SIZE - n, "» ui  = %d\n",
+		       isr_statistics.ui);
+	n += scnprintf(buf + n, PAGE_SIZE - n, "» uei = %d\n",
+		       isr_statistics.uei);
+	n += scnprintf(buf + n, PAGE_SIZE - n, "» pci = %d\n",
+		       isr_statistics.pci);
+	n += scnprintf(buf + n, PAGE_SIZE - n, "» uri = %d\n",
+		       isr_statistics.uri);
+	n += scnprintf(buf + n, PAGE_SIZE - n, "» sli = %d\n",
+		       isr_statistics.sli);
+	n += scnprintf(buf + n, PAGE_SIZE - n, "*none = %d\n",
+		       isr_statistics.none);
+	n += scnprintf(buf + n, PAGE_SIZE - n, "*hndl = %d\n",
+		       isr_statistics.hndl.cnt);
+
+	for (i = isr_statistics.hndl.idx, j = 0; j <= ISR_MASK; j++, i++) {
+		i   &= ISR_MASK;
+		intr = isr_statistics.hndl.buf[i];
+
+		if (USBi_UI  & intr)
+			n += scnprintf(buf + n, PAGE_SIZE - n, "ui  ");
+		intr &= ~USBi_UI;
+		if (USBi_UEI & intr)
+			n += scnprintf(buf + n, PAGE_SIZE - n, "uei ");
+		intr &= ~USBi_UEI;
+		if (USBi_PCI & intr)
+			n += scnprintf(buf + n, PAGE_SIZE - n, "pci ");
+		intr &= ~USBi_PCI;
+		if (USBi_URI & intr)
+			n += scnprintf(buf + n, PAGE_SIZE - n, "uri ");
+		intr &= ~USBi_URI;
+		if (USBi_SLI & intr)
+			n += scnprintf(buf + n, PAGE_SIZE - n, "sli ");
+		intr &= ~USBi_SLI;
+		if (intr)
+			n += scnprintf(buf + n, PAGE_SIZE - n, "??? ");
+		if (isr_statistics.hndl.buf[i])
+			n += scnprintf(buf + n, PAGE_SIZE - n, "\n");
+	}
+
+	spin_unlock_irqrestore(udc->lock, flags);
+
+	return n;
+}
+
+/**
+ * store_inters: enable & force or disable an individual interrutps
+ *                   (to be used for test purposes only)
+ *
+ * Check "device.h" for details
+ */
+static ssize_t store_inters(struct device *dev, struct device_attribute *attr,
+			    const char *buf, size_t count)
+{
+	struct ci13xxx *udc = container_of(dev, struct ci13xxx, gadget.dev);
+	unsigned long flags;
+	unsigned en, bit;
+
+	dbg_trace("[%s] %p, %d\n", __func__, buf, count);
+	if (attr == NULL || buf == NULL) {
+		dev_err(dev, "[%s] EINVAL\n", __func__);
+		goto done;
+	}
+
+	if (sscanf(buf, "%u %u", &en, &bit) != 2 || en > 1) {
+		dev_err(dev, "<1|0> <bit>: enable|disable interrupt");
+		goto done;
+	}
+
+	spin_lock_irqsave(udc->lock, flags);
+	if (en) {
+		if (hw_intr_force(bit))
+			dev_err(dev, "invalid bit number\n");
+		else
+			isr_statistics.test++;
+	} else {
+		if (hw_intr_clear(bit))
+			dev_err(dev, "invalid bit number\n");
+	}
+	spin_unlock_irqrestore(udc->lock, flags);
+
+ done:
+	return count;
+}
+static DEVICE_ATTR(inters, S_IRUSR | S_IWUSR, show_inters, store_inters);
+
+/**
+ * show_port_test: reads port test mode
+ *
+ * Check "device.h" for details
+ */
+static ssize_t show_port_test(struct device *dev,
+			      struct device_attribute *attr, char *buf)
+{
+	struct ci13xxx *udc = container_of(dev, struct ci13xxx, gadget.dev);
+	unsigned long flags;
+	unsigned mode;
+
+	dbg_trace("[%s] %p\n", __func__, buf);
+	if (attr == NULL || buf == NULL) {
+		dev_err(dev, "[%s] EINVAL\n", __func__);
+		return 0;
+	}
+
+	spin_lock_irqsave(udc->lock, flags);
+	mode = hw_port_test_get();
+	spin_unlock_irqrestore(udc->lock, flags);
+
+	return scnprintf(buf, PAGE_SIZE, "mode = %u\n", mode);
+}
+
+/**
+ * store_port_test: writes port test mode
+ *
+ * Check "device.h" for details
+ */
+static ssize_t store_port_test(struct device *dev,
+			       struct device_attribute *attr,
+			       const char *buf, size_t count)
+{
+	struct ci13xxx *udc = container_of(dev, struct ci13xxx, gadget.dev);
+	unsigned long flags;
+	unsigned mode;
+
+	dbg_trace("[%s] %p, %d\n", __func__, buf, count);
+	if (attr == NULL || buf == NULL) {
+		dev_err(dev, "[%s] EINVAL\n", __func__);
+		goto done;
+	}
+
+	if (sscanf(buf, "%u", &mode) != 1) {
+		dev_err(dev, "<mode>: set port test mode");
+		goto done;
+	}
+
+	spin_lock_irqsave(udc->lock, flags);
+	if (hw_port_test_set(mode))
+		dev_err(dev, "invalid mode\n");
+	spin_unlock_irqrestore(udc->lock, flags);
+
+ done:
+	return count;
+}
+static DEVICE_ATTR(port_test, S_IRUSR | S_IWUSR,
+		   show_port_test, store_port_test);
+
+/**
+ * show_qheads: DMA contents of all queue heads
+ *
+ * Check "device.h" for details
+ */
+static ssize_t show_qheads(struct device *dev, struct device_attribute *attr,
+			   char *buf)
+{
+	struct ci13xxx *udc = container_of(dev, struct ci13xxx, gadget.dev);
+	unsigned long flags;
+	unsigned i, j, n = 0;
+
+	dbg_trace("[%s] %p\n", __func__, buf);
+	if (attr == NULL || buf == NULL) {
+		dev_err(dev, "[%s] EINVAL\n", __func__);
+		return 0;
+	}
+
+	spin_lock_irqsave(udc->lock, flags);
+	for (i = 0; i < hw_ep_max; i++) {
+		struct ci13xxx_ep *mEp = &udc->ci13xxx_ep[i];
+		n += scnprintf(buf + n, PAGE_SIZE - n,
+			       "EP=%02i: RX=%08X TX=%08X\n",
+			       i, (u32)mEp->qh[RX].dma, (u32)mEp->qh[TX].dma);
+		for (j = 0; j < (sizeof(struct ci13xxx_qh)/sizeof(u32)); j++) {
+			n += scnprintf(buf + n, PAGE_SIZE - n,
+				       " %04X:    %08X    %08X\n", j,
+				       *((u32 *)mEp->qh[RX].ptr + j),
+				       *((u32 *)mEp->qh[TX].ptr + j));
+		}
+	}
+	spin_unlock_irqrestore(udc->lock, flags);
+
+	return n;
+}
+static DEVICE_ATTR(qheads, S_IRUSR, show_qheads, NULL);
+
+/**
+ * show_registers: dumps all registers
+ *
+ * Check "device.h" for details
+ */
+static ssize_t show_registers(struct device *dev,
+			      struct device_attribute *attr, char *buf)
+{
+	struct ci13xxx *udc = container_of(dev, struct ci13xxx, gadget.dev);
+	unsigned long flags;
+	u32 dump[512];
+	unsigned i, k, n = 0;
+
+	dbg_trace("[%s] %p\n", __func__, buf);
+	if (attr == NULL || buf == NULL) {
+		dev_err(dev, "[%s] EINVAL\n", __func__);
+		return 0;
+	}
+
+	spin_lock_irqsave(udc->lock, flags);
+	k = hw_register_read(dump, sizeof(dump)/sizeof(u32));
+	spin_unlock_irqrestore(udc->lock, flags);
+
+	for (i = 0; i < k; i++) {
+		n += scnprintf(buf + n, PAGE_SIZE - n,
+			       "reg[0x%04X] = 0x%08X\n",
+			       i * (unsigned)sizeof(u32), dump[i]);
+	}
+
+	return n;
+}
+
+/**
+ * store_registers: writes value to register address
+ *
+ * Check "device.h" for details
+ */
+static ssize_t store_registers(struct device *dev,
+			       struct device_attribute *attr,
+			       const char *buf, size_t count)
+{
+	struct ci13xxx *udc = container_of(dev, struct ci13xxx, gadget.dev);
+	unsigned long addr, data, flags;
+
+	dbg_trace("[%s] %p, %d\n", __func__, buf, count);
+	if (attr == NULL || buf == NULL) {
+		dev_err(dev, "[%s] EINVAL\n", __func__);
+		goto done;
+	}
+
+	if (sscanf(buf, "%li %li", &addr, &data) != 2) {
+		dev_err(dev, "<addr> <data>: write data to register address");
+		goto done;
+	}
+
+	spin_lock_irqsave(udc->lock, flags);
+	if (hw_register_write(addr, data))
+		dev_err(dev, "invalid address range\n");
+	spin_unlock_irqrestore(udc->lock, flags);
+
+ done:
+	return count;
+}
+static DEVICE_ATTR(registers, S_IRUSR | S_IWUSR,
+		   show_registers, store_registers);
+
+/**
+ * show_requests: DMA contents of all requests currently queued (all endpts)
+ *
+ * Check "device.h" for details
+ */
+static ssize_t show_requests(struct device *dev, struct device_attribute *attr,
+			     char *buf)
+{
+	struct ci13xxx *udc = container_of(dev, struct ci13xxx, gadget.dev);
+	unsigned long flags;
+	struct list_head   *ptr = NULL;
+	struct ci13xxx_req *req = NULL;
+	unsigned i, j, k, n = 0, qSize = sizeof(struct ci13xxx_td)/sizeof(u32);
+
+	dbg_trace("[%s] %p\n", __func__, buf);
+	if (attr == NULL || buf == NULL) {
+		dev_err(dev, "[%s] EINVAL\n", __func__);
+		return 0;
+	}
+
+	spin_lock_irqsave(udc->lock, flags);
+	for (i = 0; i < hw_ep_max; i++)
+		for (k = RX; k <= TX; k++)
+			list_for_each(ptr, &udc->ci13xxx_ep[i].qh[k].queue)
+			{
+				req = list_entry(ptr,
+						 struct ci13xxx_req, queue);
+
+				n += scnprintf(buf + n, PAGE_SIZE - n,
+					       "EP=%02i: TD=%08X %s\n",
+					       i, (u32)req->dma,
+					       ((k == RX) ? "RX" : "TX"));
+
+				for (j = 0; j < qSize; j++)
+					n += scnprintf(buf + n, PAGE_SIZE - n,
+						       " %04X:    %08X\n", j,
+						       *((u32 *)req->ptr + j));
+			}
+	spin_unlock_irqrestore(udc->lock, flags);
+
+	return n;
+}
+static DEVICE_ATTR(requests, S_IRUSR, show_requests, NULL);
+
+/**
+ * dbg_create_files: initializes the attribute interface
+ * @dev: device
+ *
+ * This function returns an error code
+ */
+__maybe_unused static int dbg_create_files(struct device *dev)
+{
+	int retval = 0;
+
+	if (dev == NULL)
+		return -EINVAL;
+	retval = device_create_file(dev, &dev_attr_device);
+	if (retval)
+		goto done;
+	retval = device_create_file(dev, &dev_attr_driver);
+	if (retval)
+		goto rm_device;
+	retval = device_create_file(dev, &dev_attr_events);
+	if (retval)
+		goto rm_driver;
+	retval = device_create_file(dev, &dev_attr_inters);
+	if (retval)
+		goto rm_events;
+	retval = device_create_file(dev, &dev_attr_port_test);
+	if (retval)
+		goto rm_inters;
+	retval = device_create_file(dev, &dev_attr_qheads);
+	if (retval)
+		goto rm_port_test;
+	retval = device_create_file(dev, &dev_attr_registers);
+	if (retval)
+		goto rm_qheads;
+	retval = device_create_file(dev, &dev_attr_requests);
+	if (retval)
+		goto rm_registers;
+	return 0;
+
+ rm_registers:
+	device_remove_file(dev, &dev_attr_registers);
+ rm_qheads:
+	device_remove_file(dev, &dev_attr_qheads);
+ rm_port_test:
+	device_remove_file(dev, &dev_attr_port_test);
+ rm_inters:
+	device_remove_file(dev, &dev_attr_inters);
+ rm_events:
+	device_remove_file(dev, &dev_attr_events);
+ rm_driver:
+	device_remove_file(dev, &dev_attr_driver);
+ rm_device:
+	device_remove_file(dev, &dev_attr_device);
+ done:
+	return retval;
+}
+
+/**
+ * dbg_remove_files: destroys the attribute interface
+ * @dev: device
+ *
+ * This function returns an error code
+ */
+__maybe_unused static int dbg_remove_files(struct device *dev)
+{
+	if (dev == NULL)
+		return -EINVAL;
+	device_remove_file(dev, &dev_attr_requests);
+	device_remove_file(dev, &dev_attr_registers);
+	device_remove_file(dev, &dev_attr_qheads);
+	device_remove_file(dev, &dev_attr_port_test);
+	device_remove_file(dev, &dev_attr_inters);
+	device_remove_file(dev, &dev_attr_events);
+	device_remove_file(dev, &dev_attr_driver);
+	device_remove_file(dev, &dev_attr_device);
+	return 0;
+}
+
+/******************************************************************************
+ * UTIL block
+ *****************************************************************************/
+/**
+ * _usb_addr: calculates endpoint address from direction & number
+ * @ep:  endpoint
+ */
+static inline u8 _usb_addr(struct ci13xxx_ep *ep)
+{
+	return ((ep->dir == TX) ? USB_ENDPOINT_DIR_MASK : 0) | ep->num;
+}
+
+/**
+ * _hardware_queue: configures a request at hardware level
+ * @gadget: gadget
+ * @mEp:    endpoint
+ *
+ * This function returns an error code
+ */
+static int _hardware_enqueue(struct ci13xxx_ep *mEp, struct ci13xxx_req *mReq)
+{
+	unsigned i;
+
+	trace("%p, %p", mEp, mReq);
+
+	/* don't queue twice */
+	if (mReq->req.status == -EALREADY)
+		return -EALREADY;
+
+	if (hw_ep_is_primed(mEp->num, mEp->dir))
+		return -EBUSY;
+
+	mReq->req.status = -EALREADY;
+
+	if (mReq->req.length && !mReq->req.dma) {
+		mReq->req.dma = \
+			dma_map_single(mEp->device, mReq->req.buf,
+				       mReq->req.length, mEp->dir ?
+				       DMA_TO_DEVICE : DMA_FROM_DEVICE);
+		if (mReq->req.dma == 0)
+			return -ENOMEM;
+
+		mReq->map = 1;
+	}
+
+	/*
+	 * TD configuration
+	 * TODO - handle requests which spawns into several TDs
+	 */
+	memset(mReq->ptr, 0, sizeof(*mReq->ptr));
+	mReq->ptr->next    |= TD_TERMINATE;
+	mReq->ptr->token    = mReq->req.length << ffs_nr(TD_TOTAL_BYTES);
+	mReq->ptr->token   &= TD_TOTAL_BYTES;
+	mReq->ptr->token   |= TD_IOC;
+	mReq->ptr->token   |= TD_STATUS_ACTIVE;
+	mReq->ptr->page[0]  = mReq->req.dma;
+	for (i = 1; i < 5; i++)
+		mReq->ptr->page[i] =
+			(mReq->req.dma + i * PAGE_SIZE) & ~TD_RESERVED_MASK;
+
+	/*
+	 *  QH configuration
+	 *  At this point it's guaranteed exclusive access to qhead
+	 *  (endpt is not primed) so it's no need to use tripwire
+	 */
+	mEp->qh[mEp->dir].ptr->td.next   = mReq->dma;    /* TERMINATE = 0 */
+	mEp->qh[mEp->dir].ptr->td.token &= ~TD_STATUS;   /* clear status */
+	if (mReq->req.zero == 0)
+		mEp->qh[mEp->dir].ptr->cap |=  QH_ZLT;
+	else
+		mEp->qh[mEp->dir].ptr->cap &= ~QH_ZLT;
+
+	wmb();   /* synchronize before ep prime */
+
+	return hw_ep_prime(mEp->num, mEp->dir,
+			   mEp->type == USB_ENDPOINT_XFER_CONTROL);
+}
+
+/**
+ * _hardware_dequeue: handles a request at hardware level
+ * @gadget: gadget
+ * @mEp:    endpoint
+ *
+ * This function returns an error code
+ */
+static int _hardware_dequeue(struct ci13xxx_ep *mEp, struct ci13xxx_req *mReq)
+{
+	trace("%p, %p", mEp, mReq);
+
+	if (mReq->req.status != -EALREADY)
+		return -EINVAL;
+
+	if (hw_ep_is_primed(mEp->num, mEp->dir))
+		hw_ep_flush(mEp->num, mEp->dir);
+
+	mReq->req.status = 0;
+
+	if (mReq->map) {
+		dma_unmap_single(mEp->device, mReq->req.dma, mReq->req.length,
+				 mEp->dir ? DMA_TO_DEVICE : DMA_FROM_DEVICE);
+		mReq->req.dma = 0;
+		mReq->map     = 0;
+	}
+
+	mReq->req.status = mReq->ptr->token & TD_STATUS;
+	if      ((TD_STATUS_ACTIVE & mReq->req.status) != 0)
+		mReq->req.status = -ECONNRESET;
+	else if ((TD_STATUS_HALTED & mReq->req.status) != 0)
+		mReq->req.status = -1;
+	else if ((TD_STATUS_DT_ERR & mReq->req.status) != 0)
+		mReq->req.status = -1;
+	else if ((TD_STATUS_TR_ERR & mReq->req.status) != 0)
+		mReq->req.status = -1;
+
+	mReq->req.actual   = mReq->ptr->token & TD_TOTAL_BYTES;
+	mReq->req.actual >>= ffs_nr(TD_TOTAL_BYTES);
+	mReq->req.actual   = mReq->req.length - mReq->req.actual;
+	mReq->req.actual   = mReq->req.status ? 0 : mReq->req.actual;
+
+	return mReq->req.actual;
+}
+
+/**
+ * _ep_nuke: dequeues all endpoint requests
+ * @mEp: endpoint
+ *
+ * This function returns an error code
+ * Caller must hold lock
+ */
+static int _ep_nuke(struct ci13xxx_ep *mEp)
+__releases(mEp->lock)
+__acquires(mEp->lock)
+{
+	trace("%p", mEp);
+
+	if (mEp == NULL)
+		return -EINVAL;
+
+	hw_ep_flush(mEp->num, mEp->dir);
+
+	while (!list_empty(&mEp->qh[mEp->dir].queue)) {
+
+		/* pop oldest request */
+		struct ci13xxx_req *mReq = \
+			list_entry(mEp->qh[mEp->dir].queue.next,
+				   struct ci13xxx_req, queue);
+		list_del_init(&mReq->queue);
+		mReq->req.status = -ESHUTDOWN;
+
+		if (!mReq->req.no_interrupt && mReq->req.complete != NULL) {
+			spin_unlock(mEp->lock);
+			mReq->req.complete(&mEp->ep, &mReq->req);
+			spin_lock(mEp->lock);
+		}
+	}
+	return 0;
+}
+
+/**
+ * _gadget_stop_activity: stops all USB activity, flushes & disables all endpts
+ * @gadget: gadget
+ *
+ * This function returns an error code
+ * Caller must hold lock
+ */
+static int _gadget_stop_activity(struct usb_gadget *gadget)
+__releases(udc->lock)
+__acquires(udc->lock)
+{
+	struct usb_ep *ep;
+	struct ci13xxx    *udc = container_of(gadget, struct ci13xxx, gadget);
+	struct ci13xxx_ep *mEp = container_of(gadget->ep0,
+					      struct ci13xxx_ep, ep);
+
+	trace("%p", gadget);
+
+	if (gadget == NULL)
+		return -EINVAL;
+
+	spin_unlock(udc->lock);
+
+	/* flush all endpoints */
+	gadget_for_each_ep(ep, gadget) {
+		usb_ep_fifo_flush(ep);
+	}
+	usb_ep_fifo_flush(gadget->ep0);
+
+	udc->driver->disconnect(gadget);
+
+	/* make sure to disable all endpoints */
+	gadget_for_each_ep(ep, gadget) {
+		usb_ep_disable(ep);
+	}
+	usb_ep_disable(gadget->ep0);
+
+	if (mEp->status != NULL) {
+		usb_ep_free_request(gadget->ep0, mEp->status);
+		mEp->status = NULL;
+	}
+
+	spin_lock(udc->lock);
+
+	return 0;
+}
+
+/******************************************************************************
+ * ISR block
+ *****************************************************************************/
+/**
+ * isr_reset_handler: USB reset interrupt handler
+ * @udc: UDC device
+ *
+ * This function resets USB engine after a bus reset occurred
+ */
+static void isr_reset_handler(struct ci13xxx *udc)
+__releases(udc->lock)
+__acquires(udc->lock)
+{
+	struct ci13xxx_ep *mEp = &udc->ci13xxx_ep[0];
+	int retval;
+
+	trace("%p", udc);
+
+	if (udc == NULL) {
+		err("EINVAL");
+		return;
+	}
+
+	dbg_event(0xFF, "BUS RST", 0);
+
+	retval = _gadget_stop_activity(&udc->gadget);
+	if (retval)
+		goto done;
+
+	retval = hw_usb_reset();
+	if (retval)
+		goto done;
+
+	spin_unlock(udc->lock);
+	retval = usb_ep_enable(&mEp->ep, &ctrl_endpt_desc);
+	if (!retval) {
+		mEp->status = usb_ep_alloc_request(&mEp->ep, GFP_KERNEL);
+		if (mEp->status == NULL) {
+			usb_ep_disable(&mEp->ep);
+			retval = -ENOMEM;
+		}
+	}
+	spin_lock(udc->lock);
+
+ done:
+	if (retval)
+		err("error: %i", retval);
+}
+
+/**
+ * isr_get_status_complete: get_status request complete function
+ * @ep:  endpoint
+ * @req: request handled
+ *
+ * Caller must release lock
+ */
+static void isr_get_status_complete(struct usb_ep *ep, struct usb_request *req)
+{
+	trace("%p, %p", ep, req);
+
+	if (ep == NULL || req == NULL) {
+		err("EINVAL");
+		return;
+	}
+
+	kfree(req->buf);
+	usb_ep_free_request(ep, req);
+}
+
+/**
+ * isr_get_status_response: get_status request response
+ * @ep:    endpoint
+ * @setup: setup request packet
+ *
+ * This function returns an error code
+ */
+static int isr_get_status_response(struct ci13xxx_ep *mEp,
+				   struct usb_ctrlrequest *setup)
+__releases(mEp->lock)
+__acquires(mEp->lock)
+{
+	struct usb_request *req = NULL;
+	gfp_t gfp_flags = GFP_ATOMIC;
+	int dir, num, retval;
+
+	trace("%p, %p", mEp, setup);
+
+	if (mEp == NULL || setup == NULL)
+		return -EINVAL;
+
+	spin_unlock(mEp->lock);
+	req = usb_ep_alloc_request(&mEp->ep, gfp_flags);
+	spin_lock(mEp->lock);
+	if (req == NULL)
+		return -ENOMEM;
+
+	req->complete = isr_get_status_complete;
+	req->length   = 2;
+	req->buf      = kzalloc(req->length, gfp_flags);
+	if (req->buf == NULL) {
+		retval = -ENOMEM;
+		goto err_free_req;
+	}
+
+	if ((setup->bRequestType & USB_RECIP_MASK) == USB_RECIP_DEVICE) {
+		/* TODO: D1 - Remote Wakeup; D0 - Self Powered */
+		retval = 0;
+	} else if ((setup->bRequestType & USB_RECIP_MASK) \
+		   == USB_RECIP_ENDPOINT) {
+		dir = (le16_to_cpu(setup->wIndex) & USB_ENDPOINT_DIR_MASK) ?
+			TX : RX;
+		num =  le16_to_cpu(setup->wIndex) & USB_ENDPOINT_NUMBER_MASK;
+		*((u16 *)req->buf) = hw_ep_get_halt(num, dir);
+	}
+	/* else do nothing; reserved for future use */
+
+	spin_unlock(mEp->lock);
+	retval = usb_ep_queue(&mEp->ep, req, gfp_flags);
+	spin_lock(mEp->lock);
+	if (retval)
+		goto err_free_buf;
+
+	return 0;
+
+ err_free_buf:
+	kfree(req->buf);
+ err_free_req:
+	spin_unlock(mEp->lock);
+	usb_ep_free_request(&mEp->ep, req);
+	spin_lock(mEp->lock);
+	return retval;
+}
+
+/**
+ * isr_setup_status_phase: queues the status phase of a setup transation
+ * @mEp: endpoint
+ *
+ * This function returns an error code
+ */
+static int isr_setup_status_phase(struct ci13xxx_ep *mEp)
+__releases(mEp->lock)
+__acquires(mEp->lock)
+{
+	int retval;
+
+	trace("%p", mEp);
+
+	/* mEp is always valid & configured */
+
+	if (mEp->type == USB_ENDPOINT_XFER_CONTROL)
+		mEp->dir = (mEp->dir == TX) ? RX : TX;
+
+	mEp->status->no_interrupt = 1;
+
+	spin_unlock(mEp->lock);
+	retval = usb_ep_queue(&mEp->ep, mEp->status, GFP_ATOMIC);
+	spin_lock(mEp->lock);
+
+	return retval;
+}
+
+/**
+ * isr_tr_complete_low: transaction complete low level handler
+ * @mEp: endpoint
+ *
+ * This function returns an error code
+ * Caller must hold lock
+ */
+static int isr_tr_complete_low(struct ci13xxx_ep *mEp)
+__releases(mEp->lock)
+__acquires(mEp->lock)
+{
+	struct ci13xxx_req *mReq;
+	int retval;
+
+	trace("%p", mEp);
+
+	if (list_empty(&mEp->qh[mEp->dir].queue))
+		return -EINVAL;
+
+	/* pop oldest request */
+	mReq = list_entry(mEp->qh[mEp->dir].queue.next,
+			  struct ci13xxx_req, queue);
+	list_del_init(&mReq->queue);
+
+	retval = _hardware_dequeue(mEp, mReq);
+	if (retval < 0) {
+		dbg_event(_usb_addr(mEp), "DONE", retval);
+		goto done;
+	}
+
+	dbg_done(_usb_addr(mEp), mReq->ptr->token, retval);
+
+	if (!mReq->req.no_interrupt && mReq->req.complete != NULL) {
+		spin_unlock(mEp->lock);
+		mReq->req.complete(&mEp->ep, &mReq->req);
+		spin_lock(mEp->lock);
+	}
+
+	if (!list_empty(&mEp->qh[mEp->dir].queue)) {
+		mReq = list_entry(mEp->qh[mEp->dir].queue.next,
+				  struct ci13xxx_req, queue);
+		_hardware_enqueue(mEp, mReq);
+	}
+
+ done:
+	return retval;
+}
+
+/**
+ * isr_tr_complete_handler: transaction complete interrupt handler
+ * @udc: UDC descriptor
+ *
+ * This function handles traffic events
+ */
+static void isr_tr_complete_handler(struct ci13xxx *udc)
+__releases(udc->lock)
+__acquires(udc->lock)
+{
+	unsigned i;
+
+	trace("%p", udc);
+
+	if (udc == NULL) {
+		err("EINVAL");
+		return;
+	}
+
+	for (i = 0; i < hw_ep_max; i++) {
+		struct ci13xxx_ep *mEp  = &udc->ci13xxx_ep[i];
+		int type, num, err = -EINVAL;
+		struct usb_ctrlrequest req;
+
+
+		if (mEp->desc == NULL)
+			continue;   /* not configured */
+
+		if ((mEp->dir == RX && hw_test_and_clear_complete(i)) ||
+		    (mEp->dir == TX && hw_test_and_clear_complete(i + 16))) {
+			err = isr_tr_complete_low(mEp);
+			if (mEp->type == USB_ENDPOINT_XFER_CONTROL) {
+				if (err > 0)   /* needs status phase */
+					err = isr_setup_status_phase(mEp);
+				if (err < 0) {
+					dbg_event(_usb_addr(mEp),
+						  "ERROR", err);
+					spin_unlock(udc->lock);
+					if (usb_ep_set_halt(&mEp->ep))
+						err("error: ep_set_halt");
+					spin_lock(udc->lock);
+				}
+			}
+		}
+
+		if (mEp->type != USB_ENDPOINT_XFER_CONTROL ||
+		    !hw_test_and_clear_setup_status(i))
+			continue;
+
+		if (i != 0) {
+			warn("ctrl traffic received at endpoint");
+			continue;
+		}
+
+		/* read_setup_packet */
+		do {
+			hw_test_and_set_setup_guard();
+			memcpy(&req, &mEp->qh[RX].ptr->setup, sizeof(req));
+		} while (!hw_test_and_clear_setup_guard());
+
+		type = req.bRequestType;
+
+		mEp->dir = (type & USB_DIR_IN) ? TX : RX;
+
+		dbg_setup(_usb_addr(mEp), &req);
+
+		switch (req.bRequest) {
+		case USB_REQ_CLEAR_FEATURE:
+			if (type != (USB_DIR_OUT|USB_RECIP_ENDPOINT) &&
+			    le16_to_cpu(req.wValue) != USB_ENDPOINT_HALT)
+				goto delegate;
+			if (req.wLength != 0)
+				break;
+			num  = le16_to_cpu(req.wIndex);
+			num &= USB_ENDPOINT_NUMBER_MASK;
+			if (!udc->ci13xxx_ep[num].wedge) {
+				spin_unlock(udc->lock);
+				err = usb_ep_clear_halt(
+					&udc->ci13xxx_ep[num].ep);
+				spin_lock(udc->lock);
+				if (err)
+					break;
+			}
+			err = isr_setup_status_phase(mEp);
+			break;
+		case USB_REQ_GET_STATUS:
+			if (type != (USB_DIR_IN|USB_RECIP_DEVICE)   &&
+			    type != (USB_DIR_IN|USB_RECIP_ENDPOINT) &&
+			    type != (USB_DIR_IN|USB_RECIP_INTERFACE))
+				goto delegate;
+			if (le16_to_cpu(req.wLength) != 2 ||
+			    le16_to_cpu(req.wValue)  != 0)
+				break;
+			err = isr_get_status_response(mEp, &req);
+			break;
+		case USB_REQ_SET_ADDRESS:
+			if (type != (USB_DIR_OUT|USB_RECIP_DEVICE))
+				goto delegate;
+			if (le16_to_cpu(req.wLength) != 0 ||
+			    le16_to_cpu(req.wIndex)  != 0)
+				break;
+			err = hw_usb_set_address((u8)le16_to_cpu(req.wValue));
+			if (err)
+				break;
+			err = isr_setup_status_phase(mEp);
+			break;
+		case USB_REQ_SET_FEATURE:
+			if (type != (USB_DIR_OUT|USB_RECIP_ENDPOINT) &&
+			    le16_to_cpu(req.wValue) != USB_ENDPOINT_HALT)
+				goto delegate;
+			if (req.wLength != 0)
+				break;
+			num  = le16_to_cpu(req.wIndex);
+			num &= USB_ENDPOINT_NUMBER_MASK;
+
+			spin_unlock(udc->lock);
+			err = usb_ep_set_halt(&udc->ci13xxx_ep[num].ep);
+			spin_lock(udc->lock);
+			if (err)
+				break;
+			err = isr_setup_status_phase(mEp);
+			break;
+		default:
+delegate:
+			if (req.wLength == 0)   /* no data phase */
+				mEp->dir = TX;
+
+			spin_unlock(udc->lock);
+			err = udc->driver->setup(&udc->gadget, &req);
+			spin_lock(udc->lock);
+			break;
+		}
+
+		if (err < 0) {
+			dbg_event(_usb_addr(mEp), "ERROR", err);
+
+			spin_unlock(udc->lock);
+			if (usb_ep_set_halt(&mEp->ep))
+				err("error: ep_set_halt");
+			spin_lock(udc->lock);
+		}
+	}
+}
+
+/******************************************************************************
+ * ENDPT block
+ *****************************************************************************/
+/**
+ * ep_enable: configure endpoint, making it usable
+ *
+ * Check usb_ep_enable() at "usb_gadget.h" for details
+ */
+static int ep_enable(struct usb_ep *ep,
+		     const struct usb_endpoint_descriptor *desc)
+{
+	struct ci13xxx_ep *mEp = container_of(ep, struct ci13xxx_ep, ep);
+	int direction, retval = 0;
+	unsigned long flags;
+
+	trace("%p, %p", ep, desc);
+
+	if (ep == NULL || desc == NULL)
+		return -EINVAL;
+
+	spin_lock_irqsave(mEp->lock, flags);
+
+	/* only internal SW should enable ctrl endpts */
+
+	mEp->desc = desc;
+
+	if (!list_empty(&mEp->qh[mEp->dir].queue))
+		warn("enabling a non-empty endpoint!");
+
+	mEp->dir  = (desc->bEndpointAddress & USB_ENDPOINT_DIR_MASK) ? TX : RX;
+	mEp->num  =  desc->bEndpointAddress & USB_ENDPOINT_NUMBER_MASK;
+	mEp->type =  desc->bmAttributes & USB_ENDPOINT_XFERTYPE_MASK;
+
+	mEp->ep.maxpacket = __constant_le16_to_cpu(desc->wMaxPacketSize);
+
+	direction = mEp->dir;
+	do {
+		dbg_event(_usb_addr(mEp), "ENABLE", 0);
+
+		if (mEp->type == USB_ENDPOINT_XFER_CONTROL)
+			mEp->qh[mEp->dir].ptr->cap |=  QH_IOS;
+		else if (mEp->type == USB_ENDPOINT_XFER_ISOC)
+			mEp->qh[mEp->dir].ptr->cap &= ~QH_MULT;
+		else
+			mEp->qh[mEp->dir].ptr->cap &= ~QH_ZLT;
+
+		mEp->qh[mEp->dir].ptr->cap |=
+			(mEp->ep.maxpacket << ffs_nr(QH_MAX_PKT)) & QH_MAX_PKT;
+		mEp->qh[mEp->dir].ptr->td.next |= TD_TERMINATE;   /* needed? */
+
+		retval |= hw_ep_enable(mEp->num, mEp->dir, mEp->type);
+
+		if (mEp->type == USB_ENDPOINT_XFER_CONTROL)
+			mEp->dir = (mEp->dir == TX) ? RX : TX;
+
+	} while (mEp->dir != direction);
+
+	spin_unlock_irqrestore(mEp->lock, flags);
+	return retval;
+}
+
+/**
+ * ep_disable: endpoint is no longer usable
+ *
+ * Check usb_ep_disable() at "usb_gadget.h" for details
+ */
+static int ep_disable(struct usb_ep *ep)
+{
+	struct ci13xxx_ep *mEp = container_of(ep, struct ci13xxx_ep, ep);
+	int direction, retval = 0;
+	unsigned long flags;
+
+	trace("%p", ep);
+
+	if (ep == NULL)
+		return -EINVAL;
+	else if (mEp->desc == NULL)
+		return -EBUSY;
+
+	spin_lock_irqsave(mEp->lock, flags);
+
+	/* only internal SW should disable ctrl endpts */
+
+	direction = mEp->dir;
+	do {
+		dbg_event(_usb_addr(mEp), "DISABLE", 0);
+
+		retval |= _ep_nuke(mEp);
+		retval |= hw_ep_disable(mEp->num, mEp->dir);
+
+		if (mEp->type == USB_ENDPOINT_XFER_CONTROL)
+			mEp->dir = (mEp->dir == TX) ? RX : TX;
+
+	} while (mEp->dir != direction);
+
+	mEp->desc = NULL;
+
+	spin_unlock_irqrestore(mEp->lock, flags);
+	return retval;
+}
+
+/**
+ * ep_alloc_request: allocate a request object to use with this endpoint
+ *
+ * Check usb_ep_alloc_request() at "usb_gadget.h" for details
+ */
+static struct usb_request *ep_alloc_request(struct usb_ep *ep, gfp_t gfp_flags)
+{
+	struct ci13xxx_ep  *mEp  = container_of(ep, struct ci13xxx_ep, ep);
+	struct ci13xxx_req *mReq = NULL;
+	unsigned long flags;
+
+	trace("%p, %i", ep, gfp_flags);
+
+	if (ep == NULL) {
+		err("EINVAL");
+		return NULL;
+	}
+
+	spin_lock_irqsave(mEp->lock, flags);
+
+	mReq = kzalloc(sizeof(struct ci13xxx_req), gfp_flags);
+	if (mReq != NULL) {
+		INIT_LIST_HEAD(&mReq->queue);
+
+		mReq->ptr = dma_pool_alloc(mEp->td_pool, gfp_flags,
+					   &mReq->dma);
+		if (mReq->ptr == NULL) {
+			kfree(mReq);
+			mReq = NULL;
+		}
+	}
+
+	dbg_event(_usb_addr(mEp), "ALLOC", mReq == NULL);
+
+	spin_unlock_irqrestore(mEp->lock, flags);
+
+	return (mReq == NULL) ? NULL : &mReq->req;
+}
+
+/**
+ * ep_free_request: frees a request object
+ *
+ * Check usb_ep_free_request() at "usb_gadget.h" for details
+ */
+static void ep_free_request(struct usb_ep *ep, struct usb_request *req)
+{
+	struct ci13xxx_ep  *mEp  = container_of(ep,  struct ci13xxx_ep, ep);
+	struct ci13xxx_req *mReq = container_of(req, struct ci13xxx_req, req);
+	unsigned long flags;
+
+	trace("%p, %p", ep, req);
+
+	if (ep == NULL || req == NULL) {
+		err("EINVAL");
+		return;
+	} else if (!list_empty(&mReq->queue)) {
+		err("EBUSY");
+		return;
+	}
+
+	spin_lock_irqsave(mEp->lock, flags);
+
+	if (mReq->ptr)
+		dma_pool_free(mEp->td_pool, mReq->ptr, mReq->dma);
+	kfree(mReq);
+
+	dbg_event(_usb_addr(mEp), "FREE", 0);
+
+	spin_unlock_irqrestore(mEp->lock, flags);
+}
+
+/**
+ * ep_queue: queues (submits) an I/O request to an endpoint
+ *
+ * Check usb_ep_queue()* at usb_gadget.h" for details
+ */
+static int ep_queue(struct usb_ep *ep, struct usb_request *req,
+		    gfp_t __maybe_unused gfp_flags)
+{
+	struct ci13xxx_ep  *mEp  = container_of(ep,  struct ci13xxx_ep, ep);
+	struct ci13xxx_req *mReq = container_of(req, struct ci13xxx_req, req);
+	int retval = 0;
+	unsigned long flags;
+
+	trace("%p, %p, %X", ep, req, gfp_flags);
+
+	if (ep == NULL || req == NULL || mEp->desc == NULL)
+		return -EINVAL;
+
+	spin_lock_irqsave(mEp->lock, flags);
+
+	if (mEp->type == USB_ENDPOINT_XFER_CONTROL &&
+	    !list_empty(&mEp->qh[mEp->dir].queue)) {
+		_ep_nuke(mEp);
+		retval = -EOVERFLOW;
+		warn("endpoint ctrl %X nuked", _usb_addr(mEp));
+	}
+
+	/* first nuke then test link, e.g. previous status has not sent */
+	if (!list_empty(&mReq->queue)) {
+		retval = -EBUSY;
+		err("request already in queue");
+		goto done;
+	}
+
+	if (req->length > (4 * PAGE_SIZE)) {
+		req->length = (4 * PAGE_SIZE);
+		retval = -EMSGSIZE;
+		warn("request length truncated");
+	}
+
+	dbg_queue(_usb_addr(mEp), req, retval);
+
+	/* push request */
+	mReq->req.status = -EINPROGRESS;
+	mReq->req.actual = 0;
+	list_add_tail(&mReq->queue, &mEp->qh[mEp->dir].queue);
+
+	retval = _hardware_enqueue(mEp, mReq);
+	if (retval == -EALREADY || retval == -EBUSY) {
+		dbg_event(_usb_addr(mEp), "QUEUE", retval);
+		retval = 0;
+	}
+
+ done:
+	spin_unlock_irqrestore(mEp->lock, flags);
+	return retval;
+}
+
+/**
+ * ep_dequeue: dequeues (cancels, unlinks) an I/O request from an endpoint
+ *
+ * Check usb_ep_dequeue() at "usb_gadget.h" for details
+ */
+static int ep_dequeue(struct usb_ep *ep, struct usb_request *req)
+{
+	struct ci13xxx_ep  *mEp  = container_of(ep,  struct ci13xxx_ep, ep);
+	struct ci13xxx_req *mReq = container_of(req, struct ci13xxx_req, req);
+	unsigned long flags;
+
+	trace("%p, %p", ep, req);
+
+	if (ep == NULL || req == NULL || mEp->desc == NULL ||
+	    list_empty(&mReq->queue)  || list_empty(&mEp->qh[mEp->dir].queue))
+		return -EINVAL;
+
+	spin_lock_irqsave(mEp->lock, flags);
+
+	dbg_event(_usb_addr(mEp), "DEQUEUE", 0);
+
+	if (mReq->req.status == -EALREADY)
+		_hardware_dequeue(mEp, mReq);
+
+	/* pop request */
+	list_del_init(&mReq->queue);
+	req->status = -ECONNRESET;
+
+	if (!mReq->req.no_interrupt && mReq->req.complete != NULL) {
+		spin_unlock(mEp->lock);
+		mReq->req.complete(&mEp->ep, &mReq->req);
+		spin_lock(mEp->lock);
+	}
+
+	spin_unlock_irqrestore(mEp->lock, flags);
+	return 0;
+}
+
+/**
+ * ep_set_halt: sets the endpoint halt feature
+ *
+ * Check usb_ep_set_halt() at "usb_gadget.h" for details
+ */
+static int ep_set_halt(struct usb_ep *ep, int value)
+{
+	struct ci13xxx_ep *mEp = container_of(ep, struct ci13xxx_ep, ep);
+	int direction, retval = 0;
+	unsigned long flags;
+
+	trace("%p, %i", ep, value);
+
+	if (ep == NULL || mEp->desc == NULL)
+		return -EINVAL;
+
+	spin_lock_irqsave(mEp->lock, flags);
+
+#ifndef STALL_IN
+	/* g_file_storage MS compliant but g_zero fails chapter 9 compliance */
+	if (value && mEp->type == USB_ENDPOINT_XFER_BULK && mEp->dir == TX &&
+	    !list_empty(&mEp->qh[mEp->dir].queue)) {
+		spin_unlock_irqrestore(mEp->lock, flags);
+		return -EAGAIN;
+	}
+#endif
+
+	direction = mEp->dir;
+	do {
+		dbg_event(_usb_addr(mEp), "HALT", value);
+		retval |= hw_ep_set_halt(mEp->num, mEp->dir, value);
+
+		if (!value)
+			mEp->wedge = 0;
+
+		if (mEp->type == USB_ENDPOINT_XFER_CONTROL)
+			mEp->dir = (mEp->dir == TX) ? RX : TX;
+
+	} while (mEp->dir != direction);
+
+	spin_unlock_irqrestore(mEp->lock, flags);
+	return retval;
+}
+
+/**
+ * ep_set_wedge: sets the halt feature and ignores clear requests
+ *
+ * Check usb_ep_set_wedge() at "usb_gadget.h" for details
+ */
+static int ep_set_wedge(struct usb_ep *ep)
+{
+	struct ci13xxx_ep *mEp = container_of(ep, struct ci13xxx_ep, ep);
+	unsigned long flags;
+
+	trace("%p", ep);
+
+	if (ep == NULL || mEp->desc == NULL)
+		return -EINVAL;
+
+	spin_lock_irqsave(mEp->lock, flags);
+
+	dbg_event(_usb_addr(mEp), "WEDGE", 0);
+	mEp->wedge = 1;
+
+	spin_unlock_irqrestore(mEp->lock, flags);
+
+	return usb_ep_set_halt(ep);
+}
+
+/**
+ * ep_fifo_flush: flushes contents of a fifo
+ *
+ * Check usb_ep_fifo_flush() at "usb_gadget.h" for details
+ */
+static void ep_fifo_flush(struct usb_ep *ep)
+{
+	struct ci13xxx_ep *mEp = container_of(ep, struct ci13xxx_ep, ep);
+	unsigned long flags;
+
+	trace("%p", ep);
+
+	if (ep == NULL) {
+		err("%02X: -EINVAL", _usb_addr(mEp));
+		return;
+	}
+
+	spin_lock_irqsave(mEp->lock, flags);
+
+	dbg_event(_usb_addr(mEp), "FFLUSH", 0);
+	hw_ep_flush(mEp->num, mEp->dir);
+
+	spin_unlock_irqrestore(mEp->lock, flags);
+}
+
+/**
+ * Endpoint-specific part of the API to the USB controller hardware
+ * Check "usb_gadget.h" for details
+ */
+static const struct usb_ep_ops usb_ep_ops = {
+	.enable	       = ep_enable,
+	.disable       = ep_disable,
+	.alloc_request = ep_alloc_request,
+	.free_request  = ep_free_request,
+	.queue	       = ep_queue,
+	.dequeue       = ep_dequeue,
+	.set_halt      = ep_set_halt,
+	.set_wedge     = ep_set_wedge,
+	.fifo_flush    = ep_fifo_flush,
+};
+
+/******************************************************************************
+ * GADGET block
+ *****************************************************************************/
+/**
+ * Device operations part of the API to the USB controller hardware,
+ * which don't involve endpoints (or i/o)
+ * Check  "usb_gadget.h" for details
+ */
+static const struct usb_gadget_ops usb_gadget_ops;
+
+/**
+ * usb_gadget_register_driver: register a gadget driver
+ *
+ * Check usb_gadget_register_driver() at "usb_gadget.h" for details
+ * Interrupts are enabled here
+ */
+int usb_gadget_register_driver(struct usb_gadget_driver *driver)
+{
+	struct ci13xxx *udc = _udc;
+	unsigned long i, k, flags;
+	int retval = -ENOMEM;
+
+	trace("%p", driver);
+
+	if (driver             == NULL ||
+	    driver->bind       == NULL ||
+	    driver->unbind     == NULL ||
+	    driver->setup      == NULL ||
+	    driver->disconnect == NULL ||
+	    driver->suspend    == NULL ||
+	    driver->resume     == NULL)
+		return -EINVAL;
+	else if (udc         == NULL)
+		return -ENODEV;
+	else if (udc->driver != NULL)
+		return -EBUSY;
+
+	/* alloc resources */
+	udc->qh_pool = dma_pool_create("ci13xxx_qh", &udc->gadget.dev,
+				       sizeof(struct ci13xxx_qh),
+				       64, PAGE_SIZE);
+	if (udc->qh_pool == NULL)
+		return -ENOMEM;
+
+	udc->td_pool = dma_pool_create("ci13xxx_td", &udc->gadget.dev,
+				       sizeof(struct ci13xxx_td),
+				       64, PAGE_SIZE);
+	if (udc->td_pool == NULL) {
+		dma_pool_destroy(udc->qh_pool);
+		udc->qh_pool = NULL;
+		return -ENOMEM;
+	}
+
+	spin_lock_irqsave(udc->lock, flags);
+
+	info("hw_ep_max = %d", hw_ep_max);
+
+	udc->driver = driver;
+	udc->gadget.ops        = NULL;
+	udc->gadget.dev.driver = NULL;
+
+	retval = 0;
+	for (i = 0; i < hw_ep_max; i++) {
+		struct ci13xxx_ep *mEp = &udc->ci13xxx_ep[i];
+
+		scnprintf(mEp->name, sizeof(mEp->name), "ep%i", (int)i);
+
+		mEp->lock         = udc->lock;
+		mEp->device       = &udc->gadget.dev;
+		mEp->td_pool      = udc->td_pool;
+
+		mEp->ep.name      = mEp->name;
+		mEp->ep.ops       = &usb_ep_ops;
+		mEp->ep.maxpacket = CTRL_PAYLOAD_MAX;
+
+		/* this allocation cannot be random */
+		for (k = RX; k <= TX; k++) {
+			INIT_LIST_HEAD(&mEp->qh[k].queue);
+			mEp->qh[k].ptr = dma_pool_alloc(udc->qh_pool,
+							GFP_KERNEL,
+							&mEp->qh[k].dma);
+			if (mEp->qh[k].ptr == NULL)
+				retval = -ENOMEM;
+			else
+				memset(mEp->qh[k].ptr, 0,
+				       sizeof(*mEp->qh[k].ptr));
+		}
+		if (i == 0)
+			udc->gadget.ep0 = &mEp->ep;
+		else
+			list_add_tail(&mEp->ep.ep_list, &udc->gadget.ep_list);
+	}
+	if (retval)
+		goto done;
+
+	/* bind gadget */
+	driver->driver.bus     = NULL;
+	udc->gadget.ops        = &usb_gadget_ops;
+	udc->gadget.dev.driver = &driver->driver;
+
+	spin_unlock_irqrestore(udc->lock, flags);
+	retval = driver->bind(&udc->gadget);                /* MAY SLEEP */
+	spin_lock_irqsave(udc->lock, flags);
+
+	if (retval) {
+		udc->gadget.ops        = NULL;
+		udc->gadget.dev.driver = NULL;
+		goto done;
+	}
+
+	retval = hw_device_state(udc->ci13xxx_ep[0].qh[RX].dma);
+
+ done:
+	spin_unlock_irqrestore(udc->lock, flags);
+	if (retval)
+		usb_gadget_unregister_driver(driver);
+	return retval;
+}
+EXPORT_SYMBOL(usb_gadget_register_driver);
+
+/**
+ * usb_gadget_unregister_driver: unregister a gadget driver
+ *
+ * Check usb_gadget_unregister_driver() at "usb_gadget.h" for details
+ */
+int usb_gadget_unregister_driver(struct usb_gadget_driver *driver)
+{
+	struct ci13xxx *udc = _udc;
+	unsigned long i, k, flags;
+
+	trace("%p", driver);
+
+	if (driver             == NULL ||
+	    driver->bind       == NULL ||
+	    driver->unbind     == NULL ||
+	    driver->setup      == NULL ||
+	    driver->disconnect == NULL ||
+	    driver->suspend    == NULL ||
+	    driver->resume     == NULL ||
+	    driver             != udc->driver)
+		return -EINVAL;
+
+	spin_lock_irqsave(udc->lock, flags);
+
+	hw_device_state(0);
+
+	/* unbind gadget */
+	if (udc->gadget.ops != NULL) {
+		_gadget_stop_activity(&udc->gadget);
+
+		spin_unlock_irqrestore(udc->lock, flags);
+		driver->unbind(&udc->gadget);               /* MAY SLEEP */
+		spin_lock_irqsave(udc->lock, flags);
+
+		udc->gadget.ops        = NULL;
+		udc->gadget.dev.driver = NULL;
+	}
+
+	/* free resources */
+	for (i = 0; i < hw_ep_max; i++) {
+		struct ci13xxx_ep *mEp = &udc->ci13xxx_ep[i];
+
+		if (i == 0)
+			udc->gadget.ep0 = NULL;
+		else if (!list_empty(&mEp->ep.ep_list))
+			list_del_init(&mEp->ep.ep_list);
+
+		for (k = RX; k <= TX; k++)
+			if (mEp->qh[k].ptr != NULL)
+				dma_pool_free(udc->qh_pool,
+					      mEp->qh[k].ptr, mEp->qh[k].dma);
+	}
+
+	udc->driver = NULL;
+
+	spin_unlock_irqrestore(udc->lock, flags);
+
+	if (udc->td_pool != NULL) {
+		dma_pool_destroy(udc->td_pool);
+		udc->td_pool = NULL;
+	}
+	if (udc->qh_pool != NULL) {
+		dma_pool_destroy(udc->qh_pool);
+		udc->qh_pool = NULL;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(usb_gadget_unregister_driver);
+
+/******************************************************************************
+ * BUS block
+ *****************************************************************************/
+/**
+ * udc_irq: global interrupt handler
+ *
+ * This function returns IRQ_HANDLED if the IRQ has been handled
+ * It locks access to registers
+ */
+static irqreturn_t udc_irq(void)
+{
+	struct ci13xxx *udc = _udc;
+	irqreturn_t retval;
+	u32 intr;
+
+	trace();
+
+	if (udc == NULL) {
+		err("ENODEV");
+		return IRQ_HANDLED;
+	}
+
+	spin_lock(udc->lock);
+	intr = hw_test_and_clear_intr_active();
+	if (intr) {
+		isr_statistics.hndl.buf[isr_statistics.hndl.idx++] = intr;
+		isr_statistics.hndl.idx &= ISR_MASK;
+		isr_statistics.hndl.cnt++;
+
+		/* order defines priority - do NOT change it */
+		if (USBi_URI & intr) {
+			isr_statistics.uri++;
+			isr_reset_handler(udc);
+		}
+		if (USBi_PCI & intr) {
+			isr_statistics.pci++;
+			udc->gadget.speed = hw_port_is_high_speed() ?
+				USB_SPEED_HIGH : USB_SPEED_FULL;
+		}
+		if (USBi_UEI & intr)
+			isr_statistics.uei++;
+		if (USBi_UI  & intr) {
+			isr_statistics.ui++;
+			isr_tr_complete_handler(udc);
+		}
+		if (USBi_SLI & intr)
+			isr_statistics.sli++;
+		retval = IRQ_HANDLED;
+	} else {
+		isr_statistics.none++;
+		retval = IRQ_NONE;
+	}
+	spin_unlock(udc->lock);
+
+	return retval;
+}
+
+/**
+ * udc_release: driver release function
+ * @dev: device
+ *
+ * Currently does nothing
+ */
+static void udc_release(struct device *dev)
+{
+	trace("%p", dev);
+
+	if (dev == NULL)
+		err("EINVAL");
+}
+
+/**
+ * udc_probe: parent probe must call this to initialize UDC
+ * @dev:  parent device
+ * @regs: registers base address
+ * @name: driver name
+ *
+ * This function returns an error code
+ * No interrupts active, the IRQ has not been requested yet
+ * Kernel assumes 32-bit DMA operations by default, no need to dma_set_mask
+ */
+static int udc_probe(struct device *dev, void __iomem *regs, const char *name)
+{
+	struct ci13xxx *udc;
+	int retval = 0;
+
+	trace("%p, %p, %p", dev, regs, name);
+
+	if (dev == NULL || regs == NULL || name == NULL)
+		return -EINVAL;
+
+	udc = kzalloc(sizeof(struct ci13xxx), GFP_KERNEL);
+	if (udc == NULL)
+		return -ENOMEM;
+
+	udc->lock = &udc_lock;
+
+	retval = hw_device_reset(regs);
+	if (retval)
+		goto done;
+
+	udc->gadget.ops          = NULL;
+	udc->gadget.speed        = USB_SPEED_UNKNOWN;
+	udc->gadget.is_dualspeed = 1;
+	udc->gadget.is_otg       = 0;
+	udc->gadget.name         = name;
+
+	INIT_LIST_HEAD(&udc->gadget.ep_list);
+	udc->gadget.ep0 = NULL;
+
+	strcpy(udc->gadget.dev.bus_id, "gadget");
+	udc->gadget.dev.dma_mask = dev->dma_mask;
+	udc->gadget.dev.parent   = dev;
+	udc->gadget.dev.release  = udc_release;
+
+	retval = device_register(&udc->gadget.dev);
+	if (retval)
+		goto done;
+
+#ifdef CONFIG_USB_GADGET_DEBUG_FILES
+	retval = dbg_create_files(&udc->gadget.dev);
+#endif
+	if (retval) {
+		device_unregister(&udc->gadget.dev);
+		goto done;
+	}
+
+	_udc = udc;
+	return retval;
+
+ done:
+	err("error = %i", retval);
+	kfree(udc);
+	_udc = NULL;
+	return retval;
+}
+
+/**
+ * udc_remove: parent remove must call this to remove UDC
+ *
+ * No interrupts active, the IRQ has been released
+ */
+static void udc_remove(void)
+{
+	struct ci13xxx *udc = _udc;
+
+	if (udc == NULL) {
+		err("EINVAL");
+		return;
+	}
+
+#ifdef CONFIG_USB_GADGET_DEBUG_FILES
+	dbg_remove_files(&udc->gadget.dev);
+#endif
+	device_unregister(&udc->gadget.dev);
+
+	kfree(udc);
+	_udc = NULL;
+}
+
+/******************************************************************************
+ * PCI block
+ *****************************************************************************/
+/**
+ * ci13xxx_pci_irq: interrut handler
+ * @irq:  irq number
+ * @pdev: USB Device Controller interrupt source
+ *
+ * This function returns IRQ_HANDLED if the IRQ has been handled
+ * This is an ISR don't trace, use attribute interface instead
+ */
+static irqreturn_t ci13xxx_pci_irq(int irq, void *pdev)
+{
+	if (irq == 0) {
+		dev_err(&((struct pci_dev *)pdev)->dev, "Invalid IRQ0 usage!");
+		return IRQ_HANDLED;
+	}
+	return udc_irq();
+}
+
+/**
+ * ci13xxx_pci_probe: PCI probe
+ * @pdev: USB device controller being probed
+ * @id:   PCI hotplug ID connecting controller to UDC framework
+ *
+ * This function returns an error code
+ * Allocates basic PCI resources for this USB device controller, and then
+ * invokes the udc_probe() method to start the UDC associated with it
+ */
+static int __devinit ci13xxx_pci_probe(struct pci_dev *pdev,
+				       const struct pci_device_id *id)
+{
+	void __iomem *regs = NULL;
+	int retval = 0;
+
+	if (id == NULL)
+		return -EINVAL;
+
+	retval = pci_enable_device(pdev);
+	if (retval)
+		goto done;
+
+	if (!pdev->irq) {
+		dev_err(&pdev->dev, "No IRQ, check BIOS/PCI setup!");
+		retval = -ENODEV;
+		goto disable_device;
+	}
+
+	retval = pci_request_regions(pdev, UDC_DRIVER_NAME);
+	if (retval)
+		goto disable_device;
+
+	/* BAR 0 holds all the registers */
+	regs = pci_iomap(pdev, 0, 0);
+	if (!regs) {
+		dev_err(&pdev->dev, "Error mapping memory!");
+		retval = -EFAULT;
+		goto release_regions;
+	}
+	pci_set_drvdata(pdev, (__force void *)regs);
+
+	pci_set_master(pdev);
+	pci_try_set_mwi(pdev);
+
+	retval = udc_probe(&pdev->dev, regs, UDC_DRIVER_NAME);
+	if (retval)
+		goto iounmap;
+
+	/* our device does not have MSI capability */
+
+	retval = request_irq(pdev->irq, ci13xxx_pci_irq, IRQF_SHARED,
+			     UDC_DRIVER_NAME, pdev);
+	if (retval)
+		goto gadget_remove;
+
+	return 0;
+
+ gadget_remove:
+	udc_remove();
+ iounmap:
+	pci_iounmap(pdev, regs);
+ release_regions:
+	pci_release_regions(pdev);
+ disable_device:
+	pci_disable_device(pdev);
+ done:
+	return retval;
+}
+
+/**
+ * ci13xxx_pci_remove: PCI remove
+ * @pdev: USB Device Controller being removed
+ *
+ * Reverses the effect of ci13xxx_pci_probe(),
+ * first invoking the udc_remove() and then releases
+ * all PCI resources allocated for this USB device controller
+ */
+static void __devexit ci13xxx_pci_remove(struct pci_dev *pdev)
+{
+	free_irq(pdev->irq, pdev);
+	udc_remove();
+	pci_iounmap(pdev, (__force void __iomem *)pci_get_drvdata(pdev));
+	pci_release_regions(pdev);
+	pci_disable_device(pdev);
+}
+
+/**
+ * PCI device table
+ * PCI device structure
+ *
+ * Check "pci.h" for details
+ */
+static DEFINE_PCI_DEVICE_TABLE(ci13xxx_pci_id_table) = {
+	{ PCI_DEVICE(0x153F, 0x1004) },
+	{ PCI_DEVICE(0x153F, 0x1006) },
+	{ 0, 0, 0, 0, 0, 0, 0 /* end: all zeroes */ }
+};
+MODULE_DEVICE_TABLE(pci, ci13xxx_pci_id_table);
+
+static struct pci_driver ci13xxx_pci_driver = {
+	.name         =	UDC_DRIVER_NAME,
+	.id_table     =	ci13xxx_pci_id_table,
+	.probe        =	ci13xxx_pci_probe,
+	.remove       =	__devexit_p(ci13xxx_pci_remove),
+};
+
+/**
+ * ci13xxx_pci_init: module init
+ *
+ * Driver load
+ */
+static int __init ci13xxx_pci_init(void)
+{
+	return pci_register_driver(&ci13xxx_pci_driver);
+}
+module_init(ci13xxx_pci_init);
+
+/**
+ * ci13xxx_pci_exit: module exit
+ *
+ * Driver unload
+ */
+static void __exit ci13xxx_pci_exit(void)
+{
+	pci_unregister_driver(&ci13xxx_pci_driver);
+}
+module_exit(ci13xxx_pci_exit);
+
+MODULE_AUTHOR("MIPS - David Lopo <dlopo@chipidea.mips.com>");
+MODULE_DESCRIPTION("MIPS CI13XXX USB Peripheral Controller");
+MODULE_LICENSE("GPL");
+MODULE_VERSION("June 2008");
diff --git a/drivers/usb/gadget/ci13xxx_udc.h b/drivers/usb/gadget/ci13xxx_udc.h
new file mode 100644
index 000000000000..4026e9cede34
--- /dev/null
+++ b/drivers/usb/gadget/ci13xxx_udc.h
@@ -0,0 +1,195 @@
+/*
+ * ci13xxx_udc.h - structures, registers, and macros MIPS USB IP core
+ *
+ * Copyright (C) 2008 Chipidea - MIPS Technologies, Inc. All rights reserved.
+ *
+ * Author: David Lopo
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Description: MIPS USB IP core family device controller
+ *              Structures, registers and logging macros
+ */
+
+#ifndef _CI13XXX_h_
+#define _CI13XXX_h_
+
+/******************************************************************************
+ * DEFINE
+ *****************************************************************************/
+#define ENDPT_MAX          (16)
+#define CTRL_PAYLOAD_MAX   (64)
+#define RX        (0)  /* similar to USB_DIR_OUT but can be used as an index */
+#define TX        (1)  /* similar to USB_DIR_IN  but can be used as an index */
+
+/******************************************************************************
+ * STRUCTURES
+ *****************************************************************************/
+/* DMA layout of transfer descriptors */
+struct ci13xxx_td {
+	/* 0 */
+	u32 next;
+#define TD_TERMINATE          BIT(0)
+	/* 1 */
+	u32 token;
+#define TD_STATUS             (0x00FFUL <<  0)
+#define TD_STATUS_TR_ERR      BIT(3)
+#define TD_STATUS_DT_ERR      BIT(5)
+#define TD_STATUS_HALTED      BIT(6)
+#define TD_STATUS_ACTIVE      BIT(7)
+#define TD_MULTO              (0x0003UL << 10)
+#define TD_IOC                BIT(15)
+#define TD_TOTAL_BYTES        (0x7FFFUL << 16)
+	/* 2 */
+	u32 page[5];
+#define TD_CURR_OFFSET        (0x0FFFUL <<  0)
+#define TD_FRAME_NUM          (0x07FFUL <<  0)
+#define TD_RESERVED_MASK      (0x0FFFUL <<  0)
+} __attribute__ ((packed));
+
+/* DMA layout of queue heads */
+struct ci13xxx_qh {
+	/* 0 */
+	u32 cap;
+#define QH_IOS                BIT(15)
+#define QH_MAX_PKT            (0x07FFUL << 16)
+#define QH_ZLT                BIT(29)
+#define QH_MULT               (0x0003UL << 30)
+	/* 1 */
+	u32 curr;
+	/* 2 - 8 */
+	struct ci13xxx_td        td;
+	/* 9 */
+	u32 RESERVED;
+	struct usb_ctrlrequest   setup;
+} __attribute__ ((packed));
+
+/* Extension of usb_request */
+struct ci13xxx_req {
+	struct usb_request   req;
+	unsigned             map;
+	struct list_head     queue;
+	struct ci13xxx_td   *ptr;
+	dma_addr_t           dma;
+};
+
+/* Extension of usb_ep */
+struct ci13xxx_ep {
+	struct usb_ep                          ep;
+	const struct usb_endpoint_descriptor  *desc;
+	u8                                     dir;
+	u8                                     num;
+	u8                                     type;
+	char                                   name[16];
+	struct {
+		struct list_head   queue;
+		struct ci13xxx_qh *ptr;
+		dma_addr_t         dma;
+	}                                      qh[2];
+	struct usb_request                    *status;
+	int                                    wedge;
+
+	/* global resources */
+	spinlock_t                            *lock;
+	struct device                         *device;
+	struct dma_pool                       *td_pool;
+};
+
+/* CI13XXX UDC descriptor & global resources */
+struct ci13xxx {
+	spinlock_t		  *lock;      /* ctrl register bank access */
+
+	struct dma_pool           *qh_pool;   /* DMA pool for queue heads */
+	struct dma_pool           *td_pool;   /* DMA pool for transfer descs */
+
+	struct usb_gadget          gadget;     /* USB slave device */
+	struct ci13xxx_ep          ci13xxx_ep[ENDPT_MAX]; /* extended endpts */
+
+	struct usb_gadget_driver  *driver;     /* 3rd party gadget driver */
+};
+
+/******************************************************************************
+ * REGISTERS
+ *****************************************************************************/
+/* register size */
+#define REG_BITS   (32)
+
+/* HCCPARAMS */
+#define HCCPARAMS_LEN         BIT(17)
+
+/* DCCPARAMS */
+#define DCCPARAMS_DEN         (0x1F << 0)
+#define DCCPARAMS_DC          BIT(7)
+
+/* TESTMODE */
+#define TESTMODE_FORCE        BIT(0)
+
+/* USBCMD */
+#define USBCMD_RS             BIT(0)
+#define USBCMD_RST            BIT(1)
+#define USBCMD_SUTW           BIT(13)
+
+/* USBSTS & USBINTR */
+#define USBi_UI               BIT(0)
+#define USBi_UEI              BIT(1)
+#define USBi_PCI              BIT(2)
+#define USBi_URI              BIT(6)
+#define USBi_SLI              BIT(8)
+
+/* DEVICEADDR */
+#define DEVICEADDR_USBADRA    BIT(24)
+#define DEVICEADDR_USBADR     (0x7FUL << 25)
+
+/* PORTSC */
+#define PORTSC_SUSP           BIT(7)
+#define PORTSC_HSP            BIT(9)
+#define PORTSC_PTC            (0x0FUL << 16)
+
+/* DEVLC */
+#define DEVLC_PSPD            (0x03UL << 25)
+#define    DEVLC_PSPD_HS      (0x02UL << 25)
+
+/* USBMODE */
+#define USBMODE_CM            (0x03UL <<  0)
+#define    USBMODE_CM_IDLE    (0x00UL <<  0)
+#define    USBMODE_CM_DEVICE  (0x02UL <<  0)
+#define    USBMODE_CM_HOST    (0x03UL <<  0)
+#define USBMODE_SLOM          BIT(3)
+
+/* ENDPTCTRL */
+#define ENDPTCTRL_RXS         BIT(0)
+#define ENDPTCTRL_RXT         (0x03UL <<  2)
+#define ENDPTCTRL_RXR         BIT(6)         /* reserved for port 0 */
+#define ENDPTCTRL_RXE         BIT(7)
+#define ENDPTCTRL_TXS         BIT(16)
+#define ENDPTCTRL_TXT         (0x03UL << 18)
+#define ENDPTCTRL_TXR         BIT(22)        /* reserved for port 0 */
+#define ENDPTCTRL_TXE         BIT(23)
+
+/******************************************************************************
+ * LOGGING
+ *****************************************************************************/
+#define ci13xxx_printk(level, format, args...) \
+do { \
+	if (_udc == NULL) \
+		printk(level "[%s] " format "\n", __func__, ## args); \
+	else \
+		dev_printk(level, _udc->gadget.dev.parent, \
+			   "[%s] " format "\n", __func__, ## args); \
+} while (0)
+
+#define err(format, args...)    ci13xxx_printk(KERN_ERR, format, ## args)
+#define warn(format, args...)   ci13xxx_printk(KERN_WARNING, format, ## args)
+#define info(format, args...)   ci13xxx_printk(KERN_INFO, format, ## args)
+
+#ifdef TRACE
+#define trace(format, args...)      ci13xxx_printk(KERN_DEBUG, format, ## args)
+#define dbg_trace(format, args...)  dev_dbg(dev, format, ##args)
+#else
+#define trace(format, args...)      do {} while (0)
+#define dbg_trace(format, args...)  do {} while (0)
+#endif
+
+#endif	/* _CI13XXX_h_ */
diff --git a/drivers/usb/gadget/epautoconf.c b/drivers/usb/gadget/epautoconf.c
index 9462e30192d8..a36b1175b18d 100644
--- a/drivers/usb/gadget/epautoconf.c
+++ b/drivers/usb/gadget/epautoconf.c
@@ -161,7 +161,7 @@ ep_matches (
 	/* report address */
 	desc->bEndpointAddress &= USB_DIR_IN;
 	if (isdigit (ep->name [2])) {
-		u8	num = simple_strtol (&ep->name [2], NULL, 10);
+		u8	num = simple_strtoul (&ep->name [2], NULL, 10);
 		desc->bEndpointAddress |= num;
 #ifdef	MANY_ENDPOINTS
 	} else if (desc->bEndpointAddress & USB_DIR_IN) {
diff --git a/drivers/usb/gadget/file_storage.c b/drivers/usb/gadget/file_storage.c
index c4e62a6297d7..1aee5b063330 100644
--- a/drivers/usb/gadget/file_storage.c
+++ b/drivers/usb/gadget/file_storage.c
@@ -1,7 +1,7 @@
 /*
  * file_storage.c -- File-backed USB Storage Gadget, for USB development
  *
- * Copyright (C) 2003-2007 Alan Stern
+ * Copyright (C) 2003-2008 Alan Stern
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -38,16 +38,17 @@
 
 /*
  * The File-backed Storage Gadget acts as a USB Mass Storage device,
- * appearing to the host as a disk drive.  In addition to providing an
- * example of a genuinely useful gadget driver for a USB device, it also
- * illustrates a technique of double-buffering for increased throughput.
- * Last but not least, it gives an easy way to probe the behavior of the
- * Mass Storage drivers in a USB host.
+ * appearing to the host as a disk drive or as a CD-ROM drive.  In addition
+ * to providing an example of a genuinely useful gadget driver for a USB
+ * device, it also illustrates a technique of double-buffering for increased
+ * throughput.  Last but not least, it gives an easy way to probe the
+ * behavior of the Mass Storage drivers in a USB host.
  *
  * Backing storage is provided by a regular file or a block device, specified
  * by the "file" module parameter.  Access can be limited to read-only by
- * setting the optional "ro" module parameter.  The gadget will indicate that
- * it has removable media if the optional "removable" module parameter is set.
+ * setting the optional "ro" module parameter.  (For CD-ROM emulation,
+ * access is always read-only.)  The gadget will indicate that it has
+ * removable media if the optional "removable" module parameter is set.
  *
  * The gadget supports the Control-Bulk (CB), Control-Bulk-Interrupt (CBI),
  * and Bulk-Only (also known as Bulk-Bulk-Bulk or BBB) transports, selected
@@ -64,7 +65,12 @@
  * The default number of LUNs is taken from the number of "file" elements;
  * it is 1 if "file" is not given.  If "removable" is not set then a backing
  * file must be specified for each LUN.  If it is set, then an unspecified
- * or empty backing filename means the LUN's medium is not loaded.
+ * or empty backing filename means the LUN's medium is not loaded.  Ideally
+ * each LUN would be settable independently as a disk drive or a CD-ROM
+ * drive, but currently all LUNs have to be the same type.  The CD-ROM
+ * emulation includes a single data track and no audio tracks; hence there
+ * need be only one backing file per LUN.  Note also that the CD-ROM block
+ * length is set to 512 rather than the more common value 2048.
  *
  * Requirements are modest; only a bulk-in and a bulk-out endpoint are
  * needed (an interrupt-out endpoint is also needed for CBI).  The memory
@@ -91,6 +97,8 @@
  *					USB device controller (usually true),
  *					boolean to permit the driver to halt
  *					bulk endpoints
+ *	cdrom			Default false, boolean for whether to emulate
+ *					a CD-ROM drive
  *	transport=XXX		Default BBB, transport name (CB, CBI, or BBB)
  *	protocol=YYY		Default SCSI, protocol name (RBC, 8020 or
  *					ATAPI, QIC, UFI, 8070, or SCSI;
@@ -103,15 +111,16 @@
  *					PAGE_CACHE_SIZE)
  *
  * If CONFIG_USB_FILE_STORAGE_TEST is not set, only the "file", "ro",
- * "removable", "luns", and "stall" options are available; default values
- * are used for everything else.
+ * "removable", "luns", "stall", and "cdrom" options are available; default
+ * values are used for everything else.
  *
  * The pathnames of the backing files and the ro settings are available in
  * the attribute files "file" and "ro" in the lun<n> subdirectory of the
  * gadget's sysfs directory.  If the "removable" option is set, writing to
  * these files will simulate ejecting/loading the medium (writing an empty
  * line means eject) and adjusting a write-enable tab.  Changes to the ro
- * setting are not allowed when the medium is loaded.
+ * setting are not allowed when the medium is loaded or if CD-ROM emulation
+ * is being used.
  *
  * This gadget driver is heavily based on "Gadget Zero" by David Brownell.
  * The driver's SCSI command interface was based on the "Information
@@ -261,7 +270,7 @@
 
 #define DRIVER_DESC		"File-backed Storage Gadget"
 #define DRIVER_NAME		"g_file_storage"
-#define DRIVER_VERSION		"7 August 2007"
+#define DRIVER_VERSION		"20 November 2008"
 
 static const char longname[] = DRIVER_DESC;
 static const char shortname[] = DRIVER_NAME;
@@ -341,6 +350,7 @@ static struct {
 
 	int		removable;
 	int		can_stall;
+	int		cdrom;
 
 	char		*transport_parm;
 	char		*protocol_parm;
@@ -359,6 +369,7 @@ static struct {
 	.protocol_parm		= "SCSI",
 	.removable		= 0,
 	.can_stall		= 1,
+	.cdrom			= 0,
 	.vendor			= DRIVER_VENDOR_ID,
 	.product		= DRIVER_PRODUCT_ID,
 	.release		= 0xffff,	// Use controller chip type
@@ -382,6 +393,9 @@ MODULE_PARM_DESC(removable, "true to simulate removable media");
 module_param_named(stall, mod_data.can_stall, bool, S_IRUGO);
 MODULE_PARM_DESC(stall, "false to prevent bulk stalls");
 
+module_param_named(cdrom, mod_data.cdrom, bool, S_IRUGO);
+MODULE_PARM_DESC(cdrom, "true to emulate cdrom instead of disk");
+
 
 /* In the non-TEST version, only the module parameters listed above
  * are available. */
@@ -411,6 +425,10 @@ MODULE_PARM_DESC(buflen, "I/O buffer size");
 
 /*-------------------------------------------------------------------------*/
 
+/* SCSI device types */
+#define TYPE_DISK	0x00
+#define TYPE_CDROM	0x05
+
 /* USB protocol value = the transport method */
 #define USB_PR_CBI	0x00		// Control/Bulk/Interrupt
 #define USB_PR_CB	0x01		// Control/Bulk w/o interrupt
@@ -487,6 +505,8 @@ struct interrupt_data {
 #define SC_READ_12			0xa8
 #define SC_READ_CAPACITY		0x25
 #define SC_READ_FORMAT_CAPACITIES	0x23
+#define SC_READ_HEADER			0x44
+#define SC_READ_TOC			0x43
 #define SC_RELEASE			0x17
 #define SC_REQUEST_SENSE		0x03
 #define SC_RESERVE			0x16
@@ -2022,23 +2042,28 @@ static int do_inquiry(struct fsg_dev *fsg, struct fsg_buffhd *bh)
 	u8	*buf = (u8 *) bh->buf;
 
 	static char vendor_id[] = "Linux   ";
-	static char product_id[] = "File-Stor Gadget";
+	static char product_disk_id[] = "File-Stor Gadget";
+	static char product_cdrom_id[] = "File-CD Gadget  ";
 
 	if (!fsg->curlun) {		// Unsupported LUNs are okay
 		fsg->bad_lun_okay = 1;
 		memset(buf, 0, 36);
 		buf[0] = 0x7f;		// Unsupported, no device-type
+		buf[4] = 31;		// Additional length
 		return 36;
 	}
 
-	memset(buf, 0, 8);	// Non-removable, direct-access device
+	memset(buf, 0, 8);
+	buf[0] = (mod_data.cdrom ? TYPE_CDROM : TYPE_DISK);
 	if (mod_data.removable)
 		buf[1] = 0x80;
 	buf[2] = 2;		// ANSI SCSI level 2
 	buf[3] = 2;		// SCSI-2 INQUIRY data format
 	buf[4] = 31;		// Additional length
 				// No special options
-	sprintf(buf + 8, "%-8s%-16s%04x", vendor_id, product_id,
+	sprintf(buf + 8, "%-8s%-16s%04x", vendor_id,
+			(mod_data.cdrom ? product_cdrom_id :
+				product_disk_id),
 			mod_data.release);
 	return 36;
 }
@@ -2117,6 +2142,75 @@ static int do_read_capacity(struct fsg_dev *fsg, struct fsg_buffhd *bh)
 }
 
 
+static void store_cdrom_address(u8 *dest, int msf, u32 addr)
+{
+	if (msf) {
+		/* Convert to Minutes-Seconds-Frames */
+		addr >>= 2;		/* Convert to 2048-byte frames */
+		addr += 2*75;		/* Lead-in occupies 2 seconds */
+		dest[3] = addr % 75;	/* Frames */
+		addr /= 75;
+		dest[2] = addr % 60;	/* Seconds */
+		addr /= 60;
+		dest[1] = addr;		/* Minutes */
+		dest[0] = 0;		/* Reserved */
+	} else {
+		/* Absolute sector */
+		put_be32(dest, addr);
+	}
+}
+
+static int do_read_header(struct fsg_dev *fsg, struct fsg_buffhd *bh)
+{
+	struct lun	*curlun = fsg->curlun;
+	int		msf = fsg->cmnd[1] & 0x02;
+	u32		lba = get_be32(&fsg->cmnd[2]);
+	u8		*buf = (u8 *) bh->buf;
+
+	if ((fsg->cmnd[1] & ~0x02) != 0) {		/* Mask away MSF */
+		curlun->sense_data = SS_INVALID_FIELD_IN_CDB;
+		return -EINVAL;
+	}
+	if (lba >= curlun->num_sectors) {
+		curlun->sense_data = SS_LOGICAL_BLOCK_ADDRESS_OUT_OF_RANGE;
+		return -EINVAL;
+	}
+
+	memset(buf, 0, 8);
+	buf[0] = 0x01;		/* 2048 bytes of user data, rest is EC */
+	store_cdrom_address(&buf[4], msf, lba);
+	return 8;
+}
+
+
+static int do_read_toc(struct fsg_dev *fsg, struct fsg_buffhd *bh)
+{
+	struct lun	*curlun = fsg->curlun;
+	int		msf = fsg->cmnd[1] & 0x02;
+	int		start_track = fsg->cmnd[6];
+	u8		*buf = (u8 *) bh->buf;
+
+	if ((fsg->cmnd[1] & ~0x02) != 0 ||		/* Mask away MSF */
+			start_track > 1) {
+		curlun->sense_data = SS_INVALID_FIELD_IN_CDB;
+		return -EINVAL;
+	}
+
+	memset(buf, 0, 20);
+	buf[1] = (20-2);		/* TOC data length */
+	buf[2] = 1;			/* First track number */
+	buf[3] = 1;			/* Last track number */
+	buf[5] = 0x16;			/* Data track, copying allowed */
+	buf[6] = 0x01;			/* Only track is number 1 */
+	store_cdrom_address(&buf[8], msf, 0);
+
+	buf[13] = 0x16;			/* Lead-out track is data */
+	buf[14] = 0xAA;			/* Lead-out track number */
+	store_cdrom_address(&buf[16], msf, curlun->num_sectors);
+	return 20;
+}
+
+
 static int do_mode_sense(struct fsg_dev *fsg, struct fsg_buffhd *bh)
 {
 	struct lun	*curlun = fsg->curlun;
@@ -2864,6 +2958,26 @@ static int do_scsi_command(struct fsg_dev *fsg)
 			reply = do_read_capacity(fsg, bh);
 		break;
 
+	case SC_READ_HEADER:
+		if (!mod_data.cdrom)
+			goto unknown_cmnd;
+		fsg->data_size_from_cmnd = get_be16(&fsg->cmnd[7]);
+		if ((reply = check_command(fsg, 10, DATA_DIR_TO_HOST,
+				(3<<7) | (0x1f<<1), 1,
+				"READ HEADER")) == 0)
+			reply = do_read_header(fsg, bh);
+		break;
+
+	case SC_READ_TOC:
+		if (!mod_data.cdrom)
+			goto unknown_cmnd;
+		fsg->data_size_from_cmnd = get_be16(&fsg->cmnd[7]);
+		if ((reply = check_command(fsg, 10, DATA_DIR_TO_HOST,
+				(7<<6) | (1<<1), 1,
+				"READ TOC")) == 0)
+			reply = do_read_toc(fsg, bh);
+		break;
+
 	case SC_READ_FORMAT_CAPACITIES:
 		fsg->data_size_from_cmnd = get_be16(&fsg->cmnd[7]);
 		if ((reply = check_command(fsg, 10, DATA_DIR_TO_HOST,
@@ -2949,6 +3063,7 @@ static int do_scsi_command(struct fsg_dev *fsg)
 		// Fall through
 
 	default:
+ unknown_cmnd:
 		fsg->data_size_from_cmnd = 0;
 		sprintf(unknown, "Unknown x%02x", fsg->cmnd[0]);
 		if ((reply = check_command(fsg, fsg->cmnd_size,
@@ -3514,6 +3629,7 @@ static int open_backing_file(struct lun *curlun, const char *filename)
 	struct inode			*inode = NULL;
 	loff_t				size;
 	loff_t				num_sectors;
+	loff_t				min_sectors;
 
 	/* R/W if we can, R/O if we must */
 	ro = curlun->ro;
@@ -3557,8 +3673,19 @@ static int open_backing_file(struct lun *curlun, const char *filename)
 		rc = (int) size;
 		goto out;
 	}
-	num_sectors = size >> 9;	// File size in 512-byte sectors
-	if (num_sectors == 0) {
+	num_sectors = size >> 9;	// File size in 512-byte blocks
+	min_sectors = 1;
+	if (mod_data.cdrom) {
+		num_sectors &= ~3;	// Reduce to a multiple of 2048
+		min_sectors = 300*4;	// Smallest track is 300 frames
+		if (num_sectors >= 256*60*75*4) {
+			num_sectors = (256*60*75 - 1) * 4;
+			LINFO(curlun, "file too big: %s\n", filename);
+			LINFO(curlun, "using only first %d blocks\n",
+					(int) num_sectors);
+		}
+	}
+	if (num_sectors < min_sectors) {
 		LINFO(curlun, "file too small: %s\n", filename);
 		rc = -ETOOSMALL;
 		goto out;
@@ -3861,9 +3988,12 @@ static int __init fsg_bind(struct usb_gadget *gadget)
 		goto out;
 
 	if (mod_data.removable) {	// Enable the store_xxx attributes
-		dev_attr_ro.attr.mode = dev_attr_file.attr.mode = 0644;
-		dev_attr_ro.store = store_ro;
+		dev_attr_file.attr.mode = 0644;
 		dev_attr_file.store = store_file;
+		if (!mod_data.cdrom) {
+			dev_attr_ro.attr.mode = 0644;
+			dev_attr_ro.store = store_ro;
+		}
 	}
 
 	/* Find out how many LUNs there should be */
@@ -3888,6 +4018,8 @@ static int __init fsg_bind(struct usb_gadget *gadget)
 	for (i = 0; i < fsg->nluns; ++i) {
 		curlun = &fsg->luns[i];
 		curlun->ro = mod_data.ro[i];
+		if (mod_data.cdrom)
+			curlun->ro = 1;
 		curlun->dev.release = lun_release;
 		curlun->dev.parent = &gadget->dev;
 		curlun->dev.driver = &fsg_driver.driver;
@@ -4047,9 +4179,9 @@ static int __init fsg_bind(struct usb_gadget *gadget)
 			mod_data.protocol_name, mod_data.protocol_type);
 	DBG(fsg, "VendorID=x%04x, ProductID=x%04x, Release=x%04x\n",
 			mod_data.vendor, mod_data.product, mod_data.release);
-	DBG(fsg, "removable=%d, stall=%d, buflen=%u\n",
+	DBG(fsg, "removable=%d, stall=%d, cdrom=%d, buflen=%u\n",
 			mod_data.removable, mod_data.can_stall,
-			mod_data.buflen);
+			mod_data.cdrom, mod_data.buflen);
 	DBG(fsg, "I/O thread pid: %d\n", task_pid_nr(fsg->thread_task));
 
 	set_bit(REGISTERED, &fsg->atomic_bitflags);
diff --git a/drivers/usb/gadget/fsl_qe_udc.c b/drivers/usb/gadget/fsl_qe_udc.c
index b3408ff39fba..d6c5bcd40064 100644
--- a/drivers/usb/gadget/fsl_qe_udc.c
+++ b/drivers/usb/gadget/fsl_qe_udc.c
@@ -26,6 +26,7 @@
 #include <linux/ioport.h>
 #include <linux/types.h>
 #include <linux/errno.h>
+#include <linux/err.h>
 #include <linux/slab.h>
 #include <linux/list.h>
 #include <linux/interrupt.h>
@@ -370,6 +371,9 @@ static int qe_ep_bd_init(struct qe_udc *udc, unsigned char pipe_num)
 	/* alloc multi-ram for BD rings and set the ep parameters */
 	tmp_addr = cpm_muram_alloc(sizeof(struct qe_bd) * (bdring_len +
 				USB_BDRING_LEN_TX), QE_ALIGNMENT_OF_BD);
+	if (IS_ERR_VALUE(tmp_addr))
+		return -ENOMEM;
+
 	out_be16(&epparam->rbase, (u16)tmp_addr);
 	out_be16(&epparam->tbase, (u16)(tmp_addr +
 				(sizeof(struct qe_bd) * bdring_len)));
@@ -689,7 +693,7 @@ en_done2:
 en_done1:
 	spin_unlock_irqrestore(&udc->lock, flags);
 en_done:
-	dev_dbg(udc->dev, "failed to initialize %s\n", ep->ep.name);
+	dev_err(udc->dev, "failed to initialize %s\n", ep->ep.name);
 	return -ENODEV;
 }
 
@@ -2408,6 +2412,8 @@ static struct qe_udc __devinit *qe_udc_config(struct of_device *ofdev)
 	tmp_addr = cpm_muram_alloc((USB_MAX_ENDPOINTS *
 					sizeof(struct usb_ep_para)),
 					   USB_EP_PARA_ALIGNMENT);
+	if (IS_ERR_VALUE(tmp_addr))
+		goto cleanup;
 
 	for (i = 0; i < USB_MAX_ENDPOINTS; i++) {
 		out_be16(&usbpram->epptr[i], (u16)tmp_addr);
@@ -2513,7 +2519,7 @@ static int __devinit qe_udc_probe(struct of_device *ofdev,
 	/* Initialize the udc structure including QH member and other member */
 	udc_controller = qe_udc_config(ofdev);
 	if (!udc_controller) {
-		dev_dbg(&ofdev->dev, "udc_controll is NULL\n");
+		dev_err(&ofdev->dev, "failed to initialize\n");
 		return -ENOMEM;
 	}
 
@@ -2545,7 +2551,7 @@ static int __devinit qe_udc_probe(struct of_device *ofdev,
 
 	device_initialize(&udc_controller->gadget.dev);
 
-	strcpy(udc_controller->gadget.dev.bus_id, "gadget");
+	dev_set_name(&udc_controller->gadget.dev, "gadget");
 
 	udc_controller->gadget.dev.release = qe_udc_release;
 	udc_controller->gadget.dev.parent = &ofdev->dev;
@@ -2568,7 +2574,7 @@ static int __devinit qe_udc_probe(struct of_device *ofdev,
 	/* create a buf for ZLP send, need to remain zeroed */
 	udc_controller->nullbuf = kzalloc(256, GFP_KERNEL);
 	if (udc_controller->nullbuf == NULL) {
-		dev_dbg(udc_controller->dev, "cannot alloc nullbuf\n");
+		dev_err(udc_controller->dev, "cannot alloc nullbuf\n");
 		ret = -ENOMEM;
 		goto err3;
 	}
diff --git a/drivers/usb/gadget/gadget_chips.h b/drivers/usb/gadget/gadget_chips.h
index 4e3107dd2f34..ec6d439a2aa5 100644
--- a/drivers/usb/gadget/gadget_chips.h
+++ b/drivers/usb/gadget/gadget_chips.h
@@ -110,7 +110,6 @@
 #define gadget_is_at91(g)	0
 #endif
 
-/* status unclear */
 #ifdef CONFIG_USB_GADGET_IMX
 #define gadget_is_imx(g)	!strcmp("imx_udc", (g)->name)
 #else
@@ -158,6 +157,11 @@
 #define gadget_is_fsl_qe(g)	0
 #endif
 
+#ifdef CONFIG_USB_GADGET_CI13XXX
+#define gadget_is_ci13xxx(g)	(!strcmp("ci13xxx_udc", (g)->name))
+#else
+#define gadget_is_ci13xxx(g)	0
+#endif
 
 // CONFIG_USB_GADGET_SX2
 // CONFIG_USB_GADGET_AU1X00
@@ -225,6 +229,8 @@ static inline int usb_gadget_controller_number(struct usb_gadget *gadget)
 		return 0x21;
 	else if (gadget_is_fsl_qe(gadget))
 		return 0x22;
+	else if (gadget_is_ci13xxx(gadget))
+		return 0x23;
 	return -ENOENT;
 }
 
diff --git a/drivers/usb/gadget/imx_udc.c b/drivers/usb/gadget/imx_udc.c
new file mode 100644
index 000000000000..718cbe7bdf8f
--- /dev/null
+++ b/drivers/usb/gadget/imx_udc.c
@@ -0,0 +1,1494 @@
+/*
+ *	driver/usb/gadget/imx_udc.c
+ *
+ *	Copyright (C) 2005 Mike Lee(eemike@gmail.com)
+ *	Copyright (C) 2008 Darius Augulis <augulis.darius@gmail.com>
+ *
+ *	This program is free software; you can redistribute it and/or modify
+ *	it under the terms of the GNU General Public License as published by
+ *	the Free Software Foundation; either version 2 of the License, or
+ *	(at your option) any later version.
+ *
+ *	This program is distributed in the hope that it will be useful,
+ *	but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *	MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *	GNU General Public License for more details.
+ */
+
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/platform_device.h>
+#include <linux/module.h>
+#include <linux/errno.h>
+#include <linux/list.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/irq.h>
+#include <linux/device.h>
+#include <linux/dma-mapping.h>
+#include <linux/clk.h>
+#include <linux/delay.h>
+
+#include <linux/usb/ch9.h>
+#include <linux/usb/gadget.h>
+
+#include <mach/usb.h>
+#include <mach/hardware.h>
+
+#include "imx_udc.h"
+
+static const char driver_name[] = "imx_udc";
+static const char ep0name[] = "ep0";
+
+void ep0_chg_stat(const char *label, struct imx_udc_struct *imx_usb,
+							enum ep0_state stat);
+
+/*******************************************************************************
+ * IMX UDC hardware related functions
+ *******************************************************************************
+ */
+
+void imx_udc_enable(struct imx_udc_struct *imx_usb)
+{
+	int temp = __raw_readl(imx_usb->base + USB_CTRL);
+	__raw_writel(temp | CTRL_FE_ENA | CTRL_AFE_ENA, imx_usb->base + USB_CTRL);
+	imx_usb->gadget.speed = USB_SPEED_FULL;
+}
+
+void imx_udc_disable(struct imx_udc_struct *imx_usb)
+{
+	int temp = __raw_readl(imx_usb->base + USB_CTRL);
+
+	__raw_writel(temp & ~(CTRL_FE_ENA | CTRL_AFE_ENA),
+		 imx_usb->base + USB_CTRL);
+
+	ep0_chg_stat(__func__, imx_usb, EP0_IDLE);
+	imx_usb->gadget.speed = USB_SPEED_UNKNOWN;
+}
+
+void imx_udc_reset(struct imx_udc_struct *imx_usb)
+{
+	int temp = __raw_readl(imx_usb->base + USB_ENAB);
+
+	/* set RST bit */
+	__raw_writel(temp | ENAB_RST, imx_usb->base + USB_ENAB);
+
+	/* wait RST bit to clear */
+	do {} while (__raw_readl(imx_usb->base + USB_ENAB) & ENAB_RST);
+
+	/* wait CFG bit to assert */
+	do {} while (!(__raw_readl(imx_usb->base + USB_DADR) & DADR_CFG));
+
+	/* udc module is now ready */
+}
+
+void imx_udc_config(struct imx_udc_struct *imx_usb)
+{
+	u8 ep_conf[5];
+	u8 i, j, cfg;
+	struct imx_ep_struct *imx_ep;
+
+	/* wait CFG bit to assert */
+	do {} while (!(__raw_readl(imx_usb->base + USB_DADR) & DADR_CFG));
+
+	/* Download the endpoint buffer for endpoint 0. */
+	for (j = 0; j < 5; j++) {
+		i = (j == 2 ? imx_usb->imx_ep[0].fifosize : 0x00);
+		__raw_writeb(i, imx_usb->base + USB_DDAT);
+		do {} while (__raw_readl(imx_usb->base + USB_DADR) & DADR_BSY);
+	}
+
+	/* Download the endpoint buffers for endpoints 1-5.
+	 * We specify two configurations, one interface
+	 */
+	for (cfg = 1; cfg < 3; cfg++) {
+		for (i = 1; i < IMX_USB_NB_EP; i++) {
+			imx_ep = &imx_usb->imx_ep[i];
+			/* EP no | Config no */
+			ep_conf[0] = (i << 4) | (cfg << 2);
+			/* Type | Direction */
+			ep_conf[1] = (imx_ep->bmAttributes << 3) |
+					(EP_DIR(imx_ep) << 2);
+			/* Max packet size */
+			ep_conf[2] = imx_ep->fifosize;
+			/* TRXTYP */
+			ep_conf[3] = 0xC0;
+			/* FIFO no */
+			ep_conf[4] = i;
+
+			D_INI(imx_usb->dev,
+				"<%s> ep%d_conf[%d]:"
+				"[%02x-%02x-%02x-%02x-%02x]\n",
+				__func__, i, cfg,
+				ep_conf[0], ep_conf[1], ep_conf[2],
+				ep_conf[3], ep_conf[4]);
+
+			for (j = 0; j < 5; j++) {
+				__raw_writeb(ep_conf[j],
+					imx_usb->base + USB_DDAT);
+				do {} while (__raw_readl(imx_usb->base + USB_DADR)
+					& DADR_BSY);
+			}
+		}
+	}
+
+	/* wait CFG bit to clear */
+	do {} while (__raw_readl(imx_usb->base + USB_DADR) & DADR_CFG);
+}
+
+void imx_udc_init_irq(struct imx_udc_struct *imx_usb)
+{
+	int i;
+
+	/* Mask and clear all irqs */
+	__raw_writel(0xFFFFFFFF, imx_usb->base + USB_MASK);
+	__raw_writel(0xFFFFFFFF, imx_usb->base + USB_INTR);
+	for (i = 0; i < IMX_USB_NB_EP; i++) {
+		__raw_writel(0x1FF, imx_usb->base + USB_EP_MASK(i));
+		__raw_writel(0x1FF, imx_usb->base + USB_EP_INTR(i));
+	}
+
+	/* Enable USB irqs */
+	__raw_writel(INTR_MSOF | INTR_FRAME_MATCH, imx_usb->base + USB_MASK);
+
+	/* Enable EP0 irqs */
+	__raw_writel(0x1FF & ~(EPINTR_DEVREQ | EPINTR_EOT | EPINTR_EOF
+		| EPINTR_FIFO_EMPTY | EPINTR_FIFO_FULL),
+		imx_usb->base + USB_EP_MASK(0));
+}
+
+void imx_udc_init_ep(struct imx_udc_struct *imx_usb)
+{
+	int i, max, temp;
+	struct imx_ep_struct *imx_ep;
+	for (i = 0; i < IMX_USB_NB_EP; i++) {
+		imx_ep = &imx_usb->imx_ep[i];
+		switch (imx_ep->fifosize) {
+		case 8:
+			max = 0;
+			break;
+		case 16:
+			max = 1;
+			break;
+		case 32:
+			max = 2;
+			break;
+		case 64:
+			max = 3;
+			break;
+		default:
+			max = 1;
+			break;
+		}
+		temp = (EP_DIR(imx_ep) << 7) | (max << 5)
+			| (imx_ep->bmAttributes << 3);
+		__raw_writel(temp, imx_usb->base + USB_EP_STAT(i));
+		__raw_writel(temp | EPSTAT_FLUSH, imx_usb->base + USB_EP_STAT(i));
+		D_INI(imx_usb->dev, "<%s> ep%d_stat %08x\n", __func__, i,
+			__raw_readl(imx_usb->base + USB_EP_STAT(i)));
+	}
+}
+
+void imx_udc_init_fifo(struct imx_udc_struct *imx_usb)
+{
+	int i, temp;
+	struct imx_ep_struct *imx_ep;
+	for (i = 0; i < IMX_USB_NB_EP; i++) {
+		imx_ep = &imx_usb->imx_ep[i];
+
+		/* Fifo control */
+		temp = EP_DIR(imx_ep) ? 0x0B000000 : 0x0F000000;
+		__raw_writel(temp, imx_usb->base + USB_EP_FCTRL(i));
+		D_INI(imx_usb->dev, "<%s> ep%d_fctrl %08x\n", __func__, i,
+			__raw_readl(imx_usb->base + USB_EP_FCTRL(i)));
+
+		/* Fifo alarm */
+		temp = (i ? imx_ep->fifosize / 2 : 0);
+		__raw_writel(temp, imx_usb->base + USB_EP_FALRM(i));
+		D_INI(imx_usb->dev, "<%s> ep%d_falrm %08x\n", __func__, i,
+			__raw_readl(imx_usb->base + USB_EP_FALRM(i)));
+	}
+}
+
+static void imx_udc_init(struct imx_udc_struct *imx_usb)
+{
+	/* Reset UDC */
+	imx_udc_reset(imx_usb);
+
+	/* Download config to enpoint buffer */
+	imx_udc_config(imx_usb);
+
+	/* Setup interrups */
+	imx_udc_init_irq(imx_usb);
+
+	/* Setup endpoints */
+	imx_udc_init_ep(imx_usb);
+
+	/* Setup fifos */
+	imx_udc_init_fifo(imx_usb);
+}
+
+void imx_ep_irq_enable(struct imx_ep_struct *imx_ep)
+{
+
+	int i = EP_NO(imx_ep);
+
+	__raw_writel(0x1FF, imx_ep->imx_usb->base + USB_EP_MASK(i));
+	__raw_writel(0x1FF, imx_ep->imx_usb->base + USB_EP_INTR(i));
+	__raw_writel(0x1FF & ~(EPINTR_EOT | EPINTR_EOF | EPINTR_FIFO_EMPTY
+		| EPINTR_FIFO_FULL), imx_ep->imx_usb->base + USB_EP_MASK(i));
+}
+
+void imx_ep_irq_disable(struct imx_ep_struct *imx_ep)
+{
+
+	int i = EP_NO(imx_ep);
+
+	__raw_writel(0x1FF, imx_ep->imx_usb->base + USB_EP_MASK(i));
+	__raw_writel(0x1FF, imx_ep->imx_usb->base + USB_EP_INTR(i));
+}
+
+int imx_ep_empty(struct imx_ep_struct *imx_ep)
+{
+	struct imx_udc_struct *imx_usb = imx_ep->imx_usb;
+
+	return __raw_readl(imx_usb->base + USB_EP_FSTAT(EP_NO(imx_ep)))
+			& FSTAT_EMPTY;
+}
+
+unsigned imx_fifo_bcount(struct imx_ep_struct *imx_ep)
+{
+	struct imx_udc_struct *imx_usb = imx_ep->imx_usb;
+
+	return (__raw_readl(imx_usb->base + USB_EP_STAT(EP_NO(imx_ep)))
+			& EPSTAT_BCOUNT) >> 16;
+}
+
+void imx_flush(struct imx_ep_struct *imx_ep)
+{
+	struct imx_udc_struct *imx_usb = imx_ep->imx_usb;
+
+	int temp = __raw_readl(imx_usb->base + USB_EP_STAT(EP_NO(imx_ep)));
+	__raw_writel(temp | EPSTAT_FLUSH,
+		imx_usb->base + USB_EP_STAT(EP_NO(imx_ep)));
+}
+
+void imx_force_stall(struct imx_ep_struct *imx_ep)
+{
+	struct imx_udc_struct *imx_usb = imx_ep->imx_usb;
+	int temp;
+
+	imx_flush(imx_ep);
+	temp = __raw_readl(imx_usb->base + USB_EP_STAT(EP_NO(imx_ep)));
+	__raw_writel(temp | EPSTAT_STALL,
+		imx_usb->base + USB_EP_STAT(EP_NO(imx_ep)));
+}
+
+static int imx_udc_get_frame(struct usb_gadget *_gadget)
+{
+	struct imx_udc_struct *imx_usb = container_of(_gadget,
+			struct imx_udc_struct, gadget);
+
+	return __raw_readl(imx_usb->base + USB_FRAME) & 0x7FF;
+}
+
+static int imx_udc_wakeup(struct usb_gadget *_gadget)
+{
+	return 0;
+}
+
+/*******************************************************************************
+ * USB request control functions
+ *******************************************************************************
+ */
+
+static void ep_add_request(struct imx_ep_struct *imx_ep, struct imx_request *req)
+{
+	if (unlikely(!req))
+		return;
+
+	req->in_use = 1;
+	list_add_tail(&req->queue, &imx_ep->queue);
+}
+
+static void ep_del_request(struct imx_ep_struct *imx_ep, struct imx_request *req)
+{
+	if (unlikely(!req))
+		return;
+
+	list_del_init(&req->queue);
+	req->in_use = 0;
+}
+
+static void done(struct imx_ep_struct *imx_ep, struct imx_request *req, int status)
+{
+	ep_del_request(imx_ep, req);
+
+	if (likely(req->req.status == -EINPROGRESS))
+		req->req.status = status;
+	else
+		status = req->req.status;
+
+	if (status && status != -ESHUTDOWN)
+		D_REQ(imx_ep->imx_usb->dev,
+			"<%s> complete %s req %p stat %d len %u/%u\n", __func__,
+			imx_ep->ep.name, &req->req, status,
+			req->req.actual, req->req.length);
+
+	req->req.complete(&imx_ep->ep, &req->req);
+}
+
+static void nuke(struct imx_ep_struct *imx_ep, int status)
+{
+	struct imx_request *req;
+
+	while (!list_empty(&imx_ep->queue)) {
+		req = list_entry(imx_ep->queue.next, struct imx_request, queue);
+		done(imx_ep, req, status);
+	}
+}
+
+/*******************************************************************************
+ * Data tansfer over USB functions
+ *******************************************************************************
+ */
+static int read_packet(struct imx_ep_struct *imx_ep, struct imx_request *req)
+{
+	u8	*buf;
+	int	bytes_ep, bufferspace, count, i;
+
+	bytes_ep = imx_fifo_bcount(imx_ep);
+	bufferspace = req->req.length - req->req.actual;
+
+	buf = req->req.buf + req->req.actual;
+	prefetchw(buf);
+
+	if (unlikely(imx_ep_empty(imx_ep)))
+		count = 0;	/* zlp */
+	else
+		count = min(bytes_ep, bufferspace);
+
+	for (i = count; i > 0; i--)
+		*buf++ = __raw_readb(imx_ep->imx_usb->base
+						+ USB_EP_FDAT0(EP_NO(imx_ep)));
+	req->req.actual += count;
+
+	return count;
+}
+
+static int write_packet(struct imx_ep_struct *imx_ep, struct imx_request *req)
+{
+	u8	*buf;
+	int	length, count, temp;
+
+	buf = req->req.buf + req->req.actual;
+	prefetch(buf);
+
+	length = min(req->req.length - req->req.actual, (u32)imx_ep->fifosize);
+
+	if (imx_fifo_bcount(imx_ep) + length > imx_ep->fifosize) {
+		D_TRX(imx_ep->imx_usb->dev, "<%s> packet overfill %s fifo\n",
+			__func__, imx_ep->ep.name);
+		return -1;
+	}
+
+	req->req.actual += length;
+	count = length;
+
+	if (!count && req->req.zero) {	/* zlp */
+		temp = __raw_readl(imx_ep->imx_usb->base
+			+ USB_EP_STAT(EP_NO(imx_ep)));
+		__raw_writel(temp | EPSTAT_ZLPS, imx_ep->imx_usb->base
+			+ USB_EP_STAT(EP_NO(imx_ep)));
+		D_TRX(imx_ep->imx_usb->dev, "<%s> zero packet\n", __func__);
+		return 0;
+	}
+
+	while (count--) {
+		if (count == 0) {	/* last byte */
+			temp = __raw_readl(imx_ep->imx_usb->base
+				+ USB_EP_FCTRL(EP_NO(imx_ep)));
+			__raw_writel(temp | FCTRL_WFR, imx_ep->imx_usb->base
+				+ USB_EP_FCTRL(EP_NO(imx_ep)));
+		}
+		__raw_writeb(*buf++,
+			imx_ep->imx_usb->base + USB_EP_FDAT0(EP_NO(imx_ep)));
+	}
+
+	return length;
+}
+
+static int read_fifo(struct imx_ep_struct *imx_ep, struct imx_request *req)
+{
+	int 	bytes = 0,
+		count,
+		is_short,
+		completed = 0;
+
+	while (__raw_readl(imx_ep->imx_usb->base + USB_EP_FSTAT(EP_NO(imx_ep)))
+		& FSTAT_FR) {
+			count = read_packet(imx_ep, req);
+			bytes += count;
+
+			is_short = (count != imx_ep->fifosize);
+			if (is_short || req->req.actual == req->req.length) {
+				completed = 1;
+				break;
+			}
+	}
+
+	if (completed || !req->req.length) {
+		done(imx_ep, req, 0);
+		if (!EP_NO(imx_ep))
+			ep0_chg_stat(__func__, imx_ep->imx_usb, EP0_IDLE);
+	}
+
+	D_TRX(imx_ep->imx_usb->dev, "<%s> bytes read: %d\n", __func__, bytes);
+
+	return completed;
+}
+
+static int write_fifo(struct imx_ep_struct *imx_ep, struct imx_request *req)
+{
+	int	bytes = 0,
+		count,
+		is_short = 0;
+
+	while (!is_short) {
+		count = write_packet(imx_ep, req);
+		if (count < 0)
+			break; /* busy */
+		bytes += count;
+
+		/* last packet "must be" short (or a zlp) */
+		is_short = (count != imx_ep->fifosize);
+
+		if (unlikely(is_short)) {
+			done(imx_ep, req, 0);
+			if (!EP_NO(imx_ep))
+				ep0_chg_stat(__func__, imx_ep->imx_usb, EP0_IDLE);
+		}
+	}
+
+	D_TRX(imx_ep->imx_usb->dev, "<%s> bytes sent: %d\n", __func__, bytes);
+
+	return is_short;
+}
+
+/*******************************************************************************
+ * Endpoint handlers
+ *******************************************************************************
+ */
+static int handle_ep(struct imx_ep_struct *imx_ep)
+{
+	struct imx_request *req;
+	int completed = 0;
+
+	do {
+		if (!list_empty(&imx_ep->queue))
+			req = list_entry(imx_ep->queue.next,
+				struct imx_request, queue);
+		else {
+			D_REQ(imx_ep->imx_usb->dev, "<%s> no request on %s\n",
+				__func__, imx_ep->ep.name);
+			return 0;
+		}
+
+		if (EP_DIR(imx_ep))	/* to host */
+			completed = write_fifo(imx_ep, req);
+		else			/* to device */
+			completed = read_fifo(imx_ep, req);
+
+		D_REQ(imx_ep->imx_usb->dev, "<%s> %s req<%p> %s\n",
+			__func__, imx_ep->ep.name, req,
+			completed ? "completed" : "not completed");
+
+		dump_ep_stat(__func__, imx_ep);
+
+	} while (completed);
+
+	return 0;
+}
+
+static int handle_ep0(struct imx_ep_struct *imx_ep)
+{
+	struct imx_request *req = NULL;
+	int ret = 0;
+
+	if (!list_empty(&imx_ep->queue))
+		req = list_entry(imx_ep->queue.next, struct imx_request, queue);
+
+	if (req) {
+		switch (imx_ep->imx_usb->ep0state) {
+
+		case EP0_IN_DATA_PHASE:			/* GET_DESCRIPTOR */
+			write_fifo(imx_ep, req);
+			break;
+		case EP0_OUT_DATA_PHASE:		/* SET_DESCRIPTOR */
+			read_fifo(imx_ep, req);
+			break;
+		default:
+			D_EP0(imx_ep->imx_usb->dev,
+				"<%s> ep0 i/o, odd state %d\n",
+				__func__, imx_ep->imx_usb->ep0state);
+			ep_del_request(imx_ep, req);
+			ret = -EL2HLT;
+			break;
+		}
+	}
+
+	return ret;
+}
+
+static void handle_ep0_devreq(struct imx_udc_struct *imx_usb)
+{
+	struct imx_ep_struct *imx_ep = &imx_usb->imx_ep[0];
+	union {
+		struct usb_ctrlrequest	r;
+		u8			raw[8];
+		u32			word[2];
+	} u;
+	int temp, i;
+
+	nuke(imx_ep, -EPROTO);
+
+	/* read SETUP packet */
+	for (i = 0; i < 2; i++) {
+		if (imx_ep_empty(imx_ep)) {
+			D_EP0(imx_usb->dev,
+				"<%s> no setup packet received\n", __func__);
+			goto stall;
+		}
+		u.word[i] = __raw_readl(imx_usb->base +	USB_EP_FDAT(EP_NO(imx_ep)));
+	}
+
+	temp = imx_ep_empty(imx_ep);
+	while (!imx_ep_empty(imx_ep)) {
+		i = __raw_readl(imx_usb->base +	USB_EP_FDAT(EP_NO(imx_ep)));
+		D_EP0(imx_usb->dev,
+			"<%s> wrong to have extra bytes for setup : 0x%08x\n",
+			__func__, i);
+	}
+	if (!temp)
+		goto stall;
+
+	le16_to_cpus(&u.r.wValue);
+	le16_to_cpus(&u.r.wIndex);
+	le16_to_cpus(&u.r.wLength);
+
+	D_EP0(imx_usb->dev, "<%s> SETUP %02x.%02x v%04x i%04x l%04x\n",
+		__func__, u.r.bRequestType, u.r.bRequest,
+		u.r.wValue, u.r.wIndex, u.r.wLength);
+
+	if (imx_usb->set_config) {
+		/* NACK the host by using CMDOVER */
+		temp = __raw_readl(imx_usb->base + USB_CTRL);
+		__raw_writel(temp | CTRL_CMDOVER, imx_usb->base + USB_CTRL);
+
+		D_EP0(imx_usb->dev,
+			"<%s> set config req is pending, NACK the host\n",
+			__func__);
+		return;
+	}
+
+	if (u.r.bRequestType & USB_DIR_IN)
+		ep0_chg_stat(__func__, imx_usb, EP0_IN_DATA_PHASE);
+	else
+		ep0_chg_stat(__func__, imx_usb, EP0_OUT_DATA_PHASE);
+
+	i = imx_usb->driver->setup(&imx_usb->gadget, &u.r);
+	if (i < 0) {
+		D_EP0(imx_usb->dev, "<%s> protocol STALL, ep0 err %d\n",
+			__func__, i);
+		goto stall;
+	}
+
+	return;
+stall:
+	imx_force_stall(imx_ep);
+	ep0_chg_stat(__func__, imx_usb, EP0_STALL);
+	return;
+}
+
+/*******************************************************************************
+ * USB gadget callback functions
+ *******************************************************************************
+ */
+
+static int imx_ep_enable(struct usb_ep *usb_ep,
+				const struct usb_endpoint_descriptor *desc)
+{
+	struct imx_ep_struct *imx_ep = container_of(usb_ep,
+						struct imx_ep_struct, ep);
+	struct imx_udc_struct *imx_usb = imx_ep->imx_usb;
+	unsigned long flags;
+
+	if (!usb_ep
+		|| !desc
+		|| !EP_NO(imx_ep)
+		|| desc->bDescriptorType != USB_DT_ENDPOINT
+		|| imx_ep->bEndpointAddress != desc->bEndpointAddress) {
+			D_EPX(imx_usb->dev,
+				"<%s> bad ep or descriptor\n", __func__);
+			return -EINVAL;
+	}
+
+	if (imx_ep->bmAttributes != desc->bmAttributes) {
+		D_EPX(imx_usb->dev,
+			"<%s> %s type mismatch\n", __func__, usb_ep->name);
+		return -EINVAL;
+	}
+
+	if (imx_ep->fifosize < le16_to_cpu(desc->wMaxPacketSize)) {
+		D_EPX(imx_usb->dev,
+			"<%s> bad %s maxpacket\n", __func__, usb_ep->name);
+		return -ERANGE;
+	}
+
+	if (!imx_usb->driver || imx_usb->gadget.speed == USB_SPEED_UNKNOWN) {
+		D_EPX(imx_usb->dev, "<%s> bogus device state\n", __func__);
+		return -ESHUTDOWN;
+	}
+
+	spin_lock_irqsave(&imx_ep->lock, flags);
+
+	imx_ep->stopped = 0;
+	imx_flush(imx_ep);
+	imx_ep_irq_enable(imx_ep);
+
+	spin_unlock_irqrestore(&imx_ep->lock, flags);
+
+	D_EPX(imx_usb->dev, "<%s> ENABLED %s\n", __func__, usb_ep->name);
+	return 0;
+}
+
+static int imx_ep_disable(struct usb_ep *usb_ep)
+{
+	struct imx_ep_struct *imx_ep = container_of(usb_ep,
+						struct imx_ep_struct, ep);
+	unsigned long flags;
+
+	if (!usb_ep || !EP_NO(imx_ep) || !list_empty(&imx_ep->queue)) {
+		D_EPX(imx_ep->imx_usb->dev, "<%s> %s can not be disabled\n",
+			__func__, usb_ep ? imx_ep->ep.name : NULL);
+		return -EINVAL;
+	}
+
+	spin_lock_irqsave(&imx_ep->lock, flags);
+
+	imx_ep->stopped = 1;
+	nuke(imx_ep, -ESHUTDOWN);
+	imx_flush(imx_ep);
+	imx_ep_irq_disable(imx_ep);
+
+	spin_unlock_irqrestore(&imx_ep->lock, flags);
+
+	D_EPX(imx_ep->imx_usb->dev,
+		"<%s> DISABLED %s\n", __func__, usb_ep->name);
+	return 0;
+}
+
+static struct usb_request *imx_ep_alloc_request
+					(struct usb_ep *usb_ep, gfp_t gfp_flags)
+{
+	struct imx_request *req;
+
+	req = kzalloc(sizeof *req, gfp_flags);
+	if (!req || !usb_ep)
+		return 0;
+
+	INIT_LIST_HEAD(&req->queue);
+	req->in_use = 0;
+
+	return &req->req;
+}
+
+static void imx_ep_free_request
+			(struct usb_ep *usb_ep, struct usb_request *usb_req)
+{
+	struct imx_request *req;
+
+	req = container_of(usb_req, struct imx_request, req);
+	WARN_ON(!list_empty(&req->queue));
+	kfree(req);
+}
+
+static int imx_ep_queue
+	(struct usb_ep *usb_ep, struct usb_request *usb_req, gfp_t gfp_flags)
+{
+	struct imx_ep_struct	*imx_ep = container_of
+					(usb_ep, struct imx_ep_struct, ep);
+	struct imx_request	*req = container_of
+					(usb_req, struct imx_request, req);
+	struct imx_udc_struct	*imx_usb = imx_ep->imx_usb;
+	unsigned long		flags;
+	int			ret = 0;
+
+	if (imx_usb->set_config && !EP_NO(imx_ep)) {
+		/*
+		  Special care on IMX udc.
+		  Ignore enqueue when after set configuration from the
+		  host. This assume all gadget drivers reply set
+		  configuration with the next ep0 req enqueue.
+		*/
+		imx_usb->set_config = 0;
+		D_EPX(imx_usb->dev,
+			"<%s> gadget reply set config\n", __func__);
+		return 0;
+	}
+
+	if (unlikely(!usb_req || !req || !usb_req->complete || !usb_req->buf)) {
+		D_EPX(imx_usb->dev, "<%s> bad params\n", __func__);
+		return -EINVAL;
+	}
+
+	if (unlikely(!usb_ep || !imx_ep)) {
+		D_EPX(imx_usb->dev, "<%s> bad ep\n", __func__);
+		return -EINVAL;
+	}
+
+	if (!imx_usb->driver || imx_usb->gadget.speed == USB_SPEED_UNKNOWN) {
+		D_EPX(imx_usb->dev, "<%s> bogus device state\n", __func__);
+		return -ESHUTDOWN;
+	}
+
+	spin_lock_irqsave(&imx_ep->lock, flags);
+
+	/* Debug */
+	dump_usb_stat(__func__, imx_usb);
+	dump_req(__func__, imx_ep, usb_req);
+
+	if (imx_ep->stopped) {
+		usb_req->status = -ESHUTDOWN;
+		ret = -ESHUTDOWN;
+		goto out;
+	}
+
+	if (req->in_use) {
+		D_REQ(imx_usb->dev,
+			"<%s> refusing to queue req %p (already queued)\n",
+			__func__, req);
+		goto out;
+	}
+
+	usb_req->status = -EINPROGRESS;
+	usb_req->actual = 0;
+
+	ep_add_request(imx_ep, req);
+
+	if (!EP_NO(imx_ep))	/* ep0 */
+		ret = handle_ep0(imx_ep);
+	else
+		ret = handle_ep(imx_ep);
+out:
+	spin_unlock_irqrestore(&imx_ep->lock, flags);
+	return ret;
+}
+
+static int imx_ep_dequeue(struct usb_ep *usb_ep, struct usb_request *usb_req)
+{
+
+	struct imx_ep_struct *imx_ep = container_of
+					(usb_ep, struct imx_ep_struct, ep);
+	struct imx_request *req;
+	unsigned long flags;
+
+	if (unlikely(!usb_ep || !EP_NO(imx_ep))) {
+		D_EPX(imx_ep->imx_usb->dev, "<%s> bad ep\n", __func__);
+		return -EINVAL;
+	}
+
+	spin_lock_irqsave(&imx_ep->lock, flags);
+
+	/* make sure it's actually queued on this endpoint */
+	list_for_each_entry(req, &imx_ep->queue, queue) {
+		if (&req->req == usb_req)
+			break;
+	}
+	if (&req->req != usb_req) {
+		spin_unlock_irqrestore(&imx_ep->lock, flags);
+		return -EINVAL;
+	}
+
+	done(imx_ep, req, -ECONNRESET);
+
+	spin_unlock_irqrestore(&imx_ep->lock, flags);
+	return 0;
+}
+
+static int imx_ep_set_halt(struct usb_ep *usb_ep, int value)
+{
+	struct imx_ep_struct *imx_ep = container_of
+					(usb_ep, struct imx_ep_struct, ep);
+	unsigned long flags;
+
+	if (unlikely(!usb_ep || !EP_NO(imx_ep))) {
+		D_EPX(imx_ep->imx_usb->dev, "<%s> bad ep\n", __func__);
+		return -EINVAL;
+	}
+
+	spin_lock_irqsave(&imx_ep->lock, flags);
+
+	if ((imx_ep->bEndpointAddress & USB_DIR_IN)
+		&& !list_empty(&imx_ep->queue)) {
+			spin_unlock_irqrestore(&imx_ep->lock, flags);
+			return -EAGAIN;
+	}
+
+	imx_force_stall(imx_ep);
+
+	spin_unlock_irqrestore(&imx_ep->lock, flags);
+
+	D_EPX(imx_ep->imx_usb->dev, "<%s> %s halt\n", __func__, usb_ep->name);
+	return 0;
+}
+
+static int imx_ep_fifo_status(struct usb_ep *usb_ep)
+{
+	struct imx_ep_struct *imx_ep = container_of
+					(usb_ep, struct imx_ep_struct, ep);
+
+	if (!usb_ep) {
+		D_EPX(imx_ep->imx_usb->dev, "<%s> bad ep\n", __func__);
+		return -ENODEV;
+	}
+
+	if (imx_ep->imx_usb->gadget.speed == USB_SPEED_UNKNOWN)
+		return 0;
+	else
+		return imx_fifo_bcount(imx_ep);
+}
+
+static void imx_ep_fifo_flush(struct usb_ep *usb_ep)
+{
+	struct imx_ep_struct *imx_ep = container_of
+					(usb_ep, struct imx_ep_struct, ep);
+	unsigned long flags;
+
+	spin_lock_irqsave(&imx_ep->lock, flags);
+
+	if (!usb_ep || !EP_NO(imx_ep) || !list_empty(&imx_ep->queue)) {
+		D_EPX(imx_ep->imx_usb->dev, "<%s> bad ep\n", __func__);
+		spin_unlock_irqrestore(&imx_ep->lock, flags);
+		return;
+	}
+
+	/* toggle and halt bits stay unchanged */
+	imx_flush(imx_ep);
+
+	spin_unlock_irqrestore(&imx_ep->lock, flags);
+}
+
+static struct usb_ep_ops imx_ep_ops = {
+	.enable		= imx_ep_enable,
+	.disable	= imx_ep_disable,
+
+	.alloc_request	= imx_ep_alloc_request,
+	.free_request	= imx_ep_free_request,
+
+	.queue		= imx_ep_queue,
+	.dequeue	= imx_ep_dequeue,
+
+	.set_halt	= imx_ep_set_halt,
+	.fifo_status	= imx_ep_fifo_status,
+	.fifo_flush	= imx_ep_fifo_flush,
+};
+
+/*******************************************************************************
+ * USB endpoint control functions
+ *******************************************************************************
+ */
+
+void ep0_chg_stat(const char *label,
+			struct imx_udc_struct *imx_usb, enum ep0_state stat)
+{
+	D_STT(imx_usb->dev, "<%s> from %15s to %15s\n",
+		label, state_name[imx_usb->ep0state], state_name[stat]);
+
+	if (imx_usb->ep0state == stat)
+		return;
+
+	imx_usb->ep0state = stat;
+}
+
+static void usb_init_data(struct imx_udc_struct *imx_usb)
+{
+	struct imx_ep_struct *imx_ep;
+	u8 i;
+
+	/* device/ep0 records init */
+	INIT_LIST_HEAD(&imx_usb->gadget.ep_list);
+	INIT_LIST_HEAD(&imx_usb->gadget.ep0->ep_list);
+	ep0_chg_stat(__func__, imx_usb, EP0_IDLE);
+
+	/* basic endpoint records init */
+	for (i = 0; i < IMX_USB_NB_EP; i++) {
+		imx_ep = &imx_usb->imx_ep[i];
+
+		if (i) {
+			list_add_tail(&imx_ep->ep.ep_list,
+				&imx_usb->gadget.ep_list);
+			imx_ep->stopped = 1;
+		} else
+			imx_ep->stopped = 0;
+
+		INIT_LIST_HEAD(&imx_ep->queue);
+		spin_lock_init(&imx_ep->lock);
+	}
+}
+
+static void udc_stop_activity(struct imx_udc_struct *imx_usb,
+					struct usb_gadget_driver *driver)
+{
+	struct imx_ep_struct *imx_ep;
+	int i;
+
+
+	if (imx_usb->gadget.speed == USB_SPEED_UNKNOWN)
+		driver = 0;
+	/* prevent new request submissions, kill any outstanding requests  */
+	for (i = 1; i < IMX_USB_NB_EP; i++) {
+		imx_ep = &imx_usb->imx_ep[i];
+		imx_flush(imx_ep);
+		imx_ep->stopped = 1;
+		nuke(imx_ep, -ESHUTDOWN);
+	}
+	imx_usb->gadget.speed = USB_SPEED_UNKNOWN;
+	if (driver) {
+		imx_usb->cfg = 0;
+		imx_usb->intf = 0;
+		imx_usb->alt = 0;
+		driver->disconnect(&imx_usb->gadget);
+	}
+}
+
+/*******************************************************************************
+ * Interrupt handlers
+ *******************************************************************************
+ */
+
+static irqreturn_t imx_udc_irq(int irq, void *dev)
+{
+	struct imx_udc_struct *imx_usb = dev;
+	struct usb_ctrlrequest u;
+	int intr, temp, cfg, intf, alt;
+
+
+	intr = __raw_readl(imx_usb->base + USB_INTR);
+
+	if (intr & (INTR_WAKEUP | INTR_SUSPEND | INTR_RESUME | INTR_RESET_START
+			| INTR_RESET_STOP | INTR_CFG_CHG)) {
+				dump_intr(__func__, intr, imx_usb->dev);
+				dump_usb_stat(__func__, imx_usb);
+	}
+
+	if (!imx_usb->driver) {
+		/*imx_udc_disable(imx_usb);*/
+		goto end_irq;
+	}
+
+	if (intr & INTR_WAKEUP) {
+		if (imx_usb->gadget.speed == USB_SPEED_UNKNOWN
+			&& imx_usb->driver && imx_usb->driver->resume)
+				imx_usb->driver->resume(&imx_usb->gadget);
+		__raw_writel(intr, imx_usb->base + USB_INTR);
+		imx_usb->set_config = 0;
+		imx_usb->gadget.speed = USB_SPEED_FULL;
+	}
+
+	if (intr & INTR_SUSPEND) {
+		if (imx_usb->gadget.speed != USB_SPEED_UNKNOWN
+			&& imx_usb->driver && imx_usb->driver->suspend)
+				imx_usb->driver->suspend(&imx_usb->gadget);
+		imx_usb->gadget.speed = USB_SPEED_UNKNOWN;
+	}
+
+	if (intr & INTR_RESET_START) {
+		udc_stop_activity(imx_usb, imx_usb->driver);
+		__raw_writel(intr, imx_usb->base + USB_INTR);
+		imx_usb->set_config = 0;
+		imx_usb->gadget.speed = USB_SPEED_FULL;
+	}
+
+	if (intr & INTR_RESET_STOP)
+		imx_usb->gadget.speed = USB_SPEED_FULL;
+
+	if (intr & INTR_CFG_CHG) {
+		temp = __raw_readl(imx_usb->base + USB_STAT);
+		cfg  = (temp & STAT_CFG) >> 5;
+		intf = (temp & STAT_INTF) >> 3;
+		alt  =  temp & STAT_ALTSET;
+
+		D_IRQ(imx_usb->dev,
+			"<%s> orig config C=%d, I=%d, A=%d / "
+			"req config C=%d, I=%d, A=%d\n",
+			__func__, imx_usb->cfg, imx_usb->intf, imx_usb->alt,
+			cfg, intf, alt);
+
+		if (cfg != 1 && cfg != 2)
+			goto end_irq; /* can not happen */
+
+		imx_usb->set_config = 0;
+
+		/* Config setup */
+		if (imx_usb->cfg != cfg) {
+			u.bRequest = USB_REQ_SET_CONFIGURATION;
+			u.bRequestType = USB_DIR_OUT |
+					USB_TYPE_STANDARD |
+					USB_RECIP_DEVICE;
+			u.wValue = cfg;
+			u.wIndex = 0;
+			u.wLength = 0;
+			imx_usb->cfg = cfg;
+			imx_usb->set_config = 1;
+			imx_usb->driver->setup(&imx_usb->gadget, &u);
+		}
+
+		if (imx_usb->intf != intf || imx_usb->alt != alt) {
+
+			u.bRequest = USB_REQ_SET_INTERFACE;
+			u.bRequestType = USB_DIR_OUT |
+					  USB_TYPE_STANDARD |
+					  USB_RECIP_INTERFACE;
+			u.wValue = alt;
+			u.wIndex = intf;
+			u.wLength = 0;
+			imx_usb->intf = intf;
+			imx_usb->alt = alt;
+			imx_usb->set_config = 1;
+			imx_usb->driver->setup(&imx_usb->gadget, &u);
+		}
+	}
+
+	if (intr & INTR_SOF) {
+		/* copy from motorola bsp.
+		   We must enable SOF intr and signal CMDOVER.
+		   Datasheet don't specifiy this action, but it
+		   is done in motorola bsp, so just copy it
+		*/
+		if (imx_usb->ep0state == EP0_IDLE) {
+			temp = __raw_readl(imx_usb->base + USB_CTRL);
+			__raw_writel(temp | CTRL_CMDOVER, imx_usb->base + USB_CTRL);
+		}
+	}
+
+end_irq:
+	__raw_writel(intr, imx_usb->base + USB_INTR);
+	return IRQ_HANDLED;
+}
+
+static irqreturn_t imx_udc_ctrl_irq(int irq, void *dev)
+{
+	struct imx_udc_struct *imx_usb = dev;
+	int intr = __raw_readl(imx_usb->base + USB_EP_INTR(0));
+
+	dump_ep_intr(__func__, 0, intr, imx_usb->dev);
+
+	if (!imx_usb->driver) {
+		__raw_writel(intr, imx_usb->base + USB_EP_INTR(0));
+		return IRQ_HANDLED;
+	}
+
+	/* DEVREQ IRQ has highest priority */
+	if (intr & EPINTR_DEVREQ)
+		handle_ep0_devreq(imx_usb);
+	/* Seem i.MX is missing EOF interrupt sometimes.
+	 * Therefore we monitor both EOF and FIFO_EMPTY interrups
+	 * when transmiting, and both EOF and FIFO_FULL when
+	 * receiving data.
+	 */
+	else if (intr & (EPINTR_EOF | EPINTR_FIFO_EMPTY | EPINTR_FIFO_FULL))
+		handle_ep0(&imx_usb->imx_ep[0]);
+
+	__raw_writel(intr, imx_usb->base + USB_EP_INTR(0));
+
+	return IRQ_HANDLED;
+}
+
+static irqreturn_t imx_udc_bulk_irq(int irq, void *dev)
+{
+	struct imx_udc_struct *imx_usb = dev;
+	struct imx_ep_struct *imx_ep = &imx_usb->imx_ep[irq - USBD_INT0];
+	int intr = __raw_readl(imx_usb->base + USB_EP_INTR(EP_NO(imx_ep)));
+
+	dump_ep_intr(__func__, irq - USBD_INT0, intr, imx_usb->dev);
+
+	if (!imx_usb->driver) {
+		__raw_writel(intr, imx_usb->base + USB_EP_INTR(EP_NO(imx_ep)));
+		return IRQ_HANDLED;
+	}
+
+	handle_ep(imx_ep);
+
+	__raw_writel(intr, imx_usb->base + USB_EP_INTR(EP_NO(imx_ep)));
+
+	return IRQ_HANDLED;
+}
+
+irq_handler_t intr_handler(int i)
+{
+	switch (i) {
+	case 0:
+		return imx_udc_ctrl_irq;
+	case 1:
+	case 2:
+	case 3:
+	case 4:
+	case 5:
+		return imx_udc_bulk_irq;
+	default:
+		return imx_udc_irq;
+	}
+}
+
+/*******************************************************************************
+ * Static defined IMX UDC structure
+ *******************************************************************************
+ */
+
+static const struct usb_gadget_ops imx_udc_ops = {
+	.get_frame	 = imx_udc_get_frame,
+	.wakeup		 = imx_udc_wakeup,
+};
+
+static struct imx_udc_struct controller = {
+	.gadget = {
+		.ops		= &imx_udc_ops,
+		.ep0		= &controller.imx_ep[0].ep,
+		.name		= driver_name,
+		.dev = {
+			 .bus_id	= "gadget",
+		 },
+	},
+
+	.imx_ep[0] = {
+		.ep = {
+			.name		= ep0name,
+			.ops		= &imx_ep_ops,
+			.maxpacket	= 32,
+		},
+		.imx_usb		= &controller,
+		.fifosize		= 32,
+		.bEndpointAddress	= 0,
+		.bmAttributes		= USB_ENDPOINT_XFER_CONTROL,
+	 },
+
+	.imx_ep[1] = {
+		.ep = {
+			.name		= "ep1in-bulk",
+			.ops		= &imx_ep_ops,
+			.maxpacket	= 64,
+		},
+		.imx_usb		= &controller,
+		.fifosize		= 64,
+		.bEndpointAddress	= USB_DIR_IN | 1,
+		.bmAttributes		= USB_ENDPOINT_XFER_BULK,
+	 },
+	.imx_ep[2] = {
+		.ep = {
+			.name		= "ep2out-bulk",
+			.ops		= &imx_ep_ops,
+			.maxpacket	= 64,
+		},
+		.imx_usb		= &controller,
+		.fifosize		= 64,
+		.bEndpointAddress	= USB_DIR_OUT | 2,
+		.bmAttributes		= USB_ENDPOINT_XFER_BULK,
+	 },
+	.imx_ep[3] = {
+		.ep = {
+			.name		= "ep3out-bulk",
+			.ops		= &imx_ep_ops,
+			.maxpacket	= 32,
+		},
+		.imx_usb		= &controller,
+		.fifosize		= 32,
+		.bEndpointAddress 	= USB_DIR_OUT | 3,
+		.bmAttributes		= USB_ENDPOINT_XFER_BULK,
+	 },
+	.imx_ep[4] = {
+		.ep = {
+			.name		= "ep4in-int",
+			.ops		= &imx_ep_ops,
+			.maxpacket	= 16,
+		 },
+		.imx_usb		= &controller,
+		.fifosize		= 16,
+		.bEndpointAddress 	= USB_DIR_IN | 4,
+		.bmAttributes		= USB_ENDPOINT_XFER_INT,
+	 },
+	.imx_ep[5] = {
+		.ep = {
+			.name		= "ep5out-int",
+			.ops		= &imx_ep_ops,
+			.maxpacket	= 16,
+		},
+		.imx_usb		= &controller,
+		.fifosize		= 16,
+		.bEndpointAddress 	= USB_DIR_OUT | 5,
+		.bmAttributes		= USB_ENDPOINT_XFER_INT,
+	 },
+};
+
+/*******************************************************************************
+ * USB gadged driver functions
+ *******************************************************************************
+ */
+int usb_gadget_register_driver(struct usb_gadget_driver *driver)
+{
+	struct imx_udc_struct *imx_usb = &controller;
+	int retval;
+
+	if (!driver
+		|| driver->speed < USB_SPEED_FULL
+		|| !driver->bind
+		|| !driver->disconnect
+		|| !driver->setup)
+			return -EINVAL;
+	if (!imx_usb)
+		return -ENODEV;
+	if (imx_usb->driver)
+		return -EBUSY;
+
+	/* first hook up the driver ... */
+	imx_usb->driver = driver;
+	imx_usb->gadget.dev.driver = &driver->driver;
+
+	retval = device_add(&imx_usb->gadget.dev);
+	if (retval)
+		goto fail;
+	retval = driver->bind(&imx_usb->gadget);
+	if (retval) {
+		D_INI(imx_usb->dev, "<%s> bind to driver %s --> error %d\n",
+			__func__, driver->driver.name, retval);
+		device_del(&imx_usb->gadget.dev);
+
+		goto fail;
+	}
+
+	D_INI(imx_usb->dev, "<%s> registered gadget driver '%s'\n",
+		__func__, driver->driver.name);
+	imx_udc_enable(imx_usb);
+	imx_usb->cfg = 0;
+	imx_usb->intf = 0;
+	imx_usb->alt = 0;
+
+	return 0;
+fail:
+	imx_usb->driver = NULL;
+	imx_usb->gadget.dev.driver = NULL;
+	return retval;
+}
+EXPORT_SYMBOL(usb_gadget_register_driver);
+
+int usb_gadget_unregister_driver(struct usb_gadget_driver *driver)
+{
+	struct imx_udc_struct *imx_usb = &controller;
+
+	if (!imx_usb)
+		return -ENODEV;
+	if (!driver || driver != imx_usb->driver || !driver->unbind)
+		return -EINVAL;
+
+	udc_stop_activity(imx_usb, driver);
+	imx_udc_disable(imx_usb);
+
+	driver->unbind(&imx_usb->gadget);
+	imx_usb->gadget.dev.driver = NULL;
+	imx_usb->driver = NULL;
+
+	device_del(&imx_usb->gadget.dev);
+
+	D_INI(imx_usb->dev, "<%s> unregistered gadget driver '%s'\n",
+		__func__, driver->driver.name);
+
+	return 0;
+}
+EXPORT_SYMBOL(usb_gadget_unregister_driver);
+
+/*******************************************************************************
+ * Module functions
+ *******************************************************************************
+ */
+
+static int __init imx_udc_probe(struct platform_device *pdev)
+{
+	struct imx_udc_struct *imx_usb = &controller;
+	struct resource *res;
+	struct imxusb_platform_data *pdata;
+	struct clk *clk;
+	void __iomem *base;
+	int ret = 0;
+	int i, res_size;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!res) {
+		dev_err(&pdev->dev, "can't get device resources\n");
+		return -ENODEV;
+	}
+
+	pdata = pdev->dev.platform_data;
+	if (!pdata) {
+		dev_err(&pdev->dev, "driver needs platform data\n");
+		return -ENODEV;
+	}
+
+	res_size = res->end - res->start + 1;
+	if (!request_mem_region(res->start, res_size, res->name)) {
+		dev_err(&pdev->dev, "can't allocate %d bytes at %d address\n",
+			res_size, res->start);
+		return -ENOMEM;
+	}
+
+	if (pdata->init) {
+		ret = pdata->init(&pdev->dev);
+		if (ret)
+			goto fail0;
+	}
+
+	base = ioremap(res->start, res_size);
+	if (!base) {
+		dev_err(&pdev->dev, "ioremap failed\n");
+		ret = -EIO;
+		goto fail1;
+	}
+
+	clk = clk_get(NULL, "usbd_clk");
+	if (IS_ERR(clk)) {
+		ret = PTR_ERR(clk);
+		dev_err(&pdev->dev, "can't get USB clock\n");
+		goto fail2;
+	}
+	clk_enable(clk);
+
+	if (clk_get_rate(clk) != 48000000) {
+		D_INI(&pdev->dev,
+			"Bad USB clock (%d Hz), changing to 48000000 Hz\n",
+			(int)clk_get_rate(clk));
+		if (clk_set_rate(clk, 48000000)) {
+			dev_err(&pdev->dev,
+				"Unable to set correct USB clock (48MHz)\n");
+			ret = -EIO;
+			goto fail3;
+		}
+	}
+
+	for (i = 0; i < IMX_USB_NB_EP + 1; i++) {
+		imx_usb->usbd_int[i] = platform_get_irq(pdev, i);
+		if (imx_usb->usbd_int[i] < 0) {
+			dev_err(&pdev->dev, "can't get irq number\n");
+			ret = -ENODEV;
+			goto fail3;
+		}
+	}
+
+	for (i = 0; i < IMX_USB_NB_EP + 1; i++) {
+		ret = request_irq(imx_usb->usbd_int[i], intr_handler(i),
+				     IRQF_DISABLED, driver_name, imx_usb);
+		if (ret) {
+			dev_err(&pdev->dev, "can't get irq %i, err %d\n",
+				imx_usb->usbd_int[i], ret);
+			for (--i; i >= 0; i--)
+				free_irq(imx_usb->usbd_int[i], imx_usb);
+			goto fail3;
+		}
+	}
+
+	imx_usb->res = res;
+	imx_usb->base = base;
+	imx_usb->clk = clk;
+	imx_usb->dev = &pdev->dev;
+
+	device_initialize(&imx_usb->gadget.dev);
+
+	imx_usb->gadget.dev.parent = &pdev->dev;
+	imx_usb->gadget.dev.dma_mask = pdev->dev.dma_mask;
+
+	platform_set_drvdata(pdev, imx_usb);
+
+	dump_usb_stat(__func__, imx_usb);
+
+	usb_init_data(imx_usb);
+	imx_udc_init(imx_usb);
+
+	dump_usb_stat(__func__, imx_usb);
+
+	return 0;
+
+fail3:
+	clk_put(clk);
+	clk_disable(clk);
+fail2:
+	iounmap(base);
+fail1:
+	if (pdata->exit)
+		pdata->exit(&pdev->dev);
+fail0:
+	release_mem_region(res->start, res_size);
+	return ret;
+}
+
+static int __exit imx_udc_remove(struct platform_device *pdev)
+{
+	struct imx_udc_struct *imx_usb = platform_get_drvdata(pdev);
+	struct imxusb_platform_data *pdata = pdev->dev.platform_data;
+	int i;
+
+	imx_udc_disable(imx_usb);
+
+	for (i = 0; i < IMX_USB_NB_EP + 1; i++)
+		free_irq(imx_usb->usbd_int[i], imx_usb);
+
+	clk_put(imx_usb->clk);
+	clk_disable(imx_usb->clk);
+	iounmap(imx_usb->base);
+
+	release_mem_region(imx_usb->res->start,
+		imx_usb->res->end - imx_usb->res->start + 1);
+
+	if (pdata->exit)
+		pdata->exit(&pdev->dev);
+
+	platform_set_drvdata(pdev, NULL);
+
+	return 0;
+}
+
+/*----------------------------------------------------------------------------*/
+
+#ifdef	CONFIG_PM
+#define	imx_udc_suspend	NULL
+#define	imx_udc_resume	NULL
+#else
+#define	imx_udc_suspend	NULL
+#define	imx_udc_resume	NULL
+#endif
+
+/*----------------------------------------------------------------------------*/
+
+static struct platform_driver udc_driver = {
+	.driver		= {
+		.name	= driver_name,
+		.owner	= THIS_MODULE,
+	},
+	.remove		= __exit_p(imx_udc_remove),
+	.suspend	= imx_udc_suspend,
+	.resume		= imx_udc_resume,
+};
+
+static int __init udc_init(void)
+{
+	return platform_driver_probe(&udc_driver, imx_udc_probe);
+}
+module_init(udc_init);
+
+static void __exit udc_exit(void)
+{
+	platform_driver_unregister(&udc_driver);
+}
+module_exit(udc_exit);
+
+MODULE_DESCRIPTION("IMX USB Device Controller driver");
+MODULE_AUTHOR("Darius Augulis <augulis.darius@gmail.com>");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS("platform:imx_udc");
diff --git a/drivers/usb/gadget/imx_udc.h b/drivers/usb/gadget/imx_udc.h
new file mode 100644
index 000000000000..192161a756bd
--- /dev/null
+++ b/drivers/usb/gadget/imx_udc.h
@@ -0,0 +1,327 @@
+/*
+ *	Copyright (C) 2005 Mike Lee(eemike@gmail.com)
+ *
+ *	This udc driver is now under testing and code is based on pxa2xx_udc.h
+ *	Please use it with your own risk!
+ *
+ *	This program is free software; you can redistribute it and/or modify
+ *	it under the terms of the GNU General Public License as published by
+ *	the Free Software Foundation; either version 2 of the License, or
+ *	(at your option) any later version.
+ *
+ *	This program is distributed in the hope that it will be useful,
+ *	but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *	MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *	GNU General Public License for more details.
+ */
+
+#ifndef __LINUX_USB_GADGET_IMX_H
+#define __LINUX_USB_GADGET_IMX_H
+
+#include <linux/types.h>
+
+/* Helper macros */
+#define EP_NO(ep)	((ep->bEndpointAddress) & ~USB_DIR_IN) /* IN:1, OUT:0 */
+#define EP_DIR(ep)	((ep->bEndpointAddress) & USB_DIR_IN ? 1 : 0)
+#define irq_to_ep(irq)	(((irq) >= USBD_INT0) || ((irq) <= USBD_INT6) ? ((irq) - USBD_INT0) : (USBD_INT6)) /*should not happen*/
+#define ep_to_irq(ep)	(EP_NO((ep)) + USBD_INT0)
+#define IMX_USB_NB_EP	6
+
+/* Driver structures */
+struct imx_request {
+	struct usb_request			req;
+	struct list_head			queue;
+	unsigned int				in_use;
+};
+
+enum ep0_state {
+	EP0_IDLE,
+	EP0_IN_DATA_PHASE,
+	EP0_OUT_DATA_PHASE,
+	EP0_END_XFER,
+	EP0_STALL,
+};
+
+struct imx_ep_struct {
+	struct usb_ep				ep;
+	struct imx_udc_struct			*imx_usb;
+	struct list_head			queue;
+	spinlock_t				lock;
+	unsigned char				stopped;
+	unsigned char				fifosize;
+	unsigned char				bEndpointAddress;
+	unsigned char				bmAttributes;
+};
+
+struct imx_udc_struct {
+	struct usb_gadget			gadget;
+	struct usb_gadget_driver		*driver;
+	struct device				*dev;
+	struct imx_ep_struct			imx_ep[IMX_USB_NB_EP];
+	struct clk				*clk;
+	enum ep0_state				ep0state;
+	struct resource				*res;
+	void __iomem				*base;
+	spinlock_t				lock;
+	unsigned char				set_config;
+	int					cfg,
+						intf,
+						alt,
+						usbd_int[7];
+};
+
+/* USB registers */
+#define  USB_FRAME		(0x00)	/* USB frame */
+#define  USB_SPEC		(0x04)	/* USB Spec */
+#define  USB_STAT		(0x08)	/* USB Status */
+#define  USB_CTRL		(0x0C)	/* USB Control */
+#define  USB_DADR		(0x10)	/* USB Desc RAM addr */
+#define  USB_DDAT		(0x14)	/* USB Desc RAM/EP buffer data */
+#define  USB_INTR		(0x18)	/* USB interrupt */
+#define  USB_MASK		(0x1C)	/* USB Mask */
+#define  USB_ENAB		(0x24)	/* USB Enable */
+#define  USB_EP_STAT(x)		(0x30 + (x*0x30)) /* USB status/control */
+#define  USB_EP_INTR(x)		(0x34 + (x*0x30)) /* USB interrupt */
+#define  USB_EP_MASK(x)		(0x38 + (x*0x30)) /* USB mask */
+#define  USB_EP_FDAT(x)		(0x3C + (x*0x30)) /* USB FIFO data */
+#define  USB_EP_FDAT0(x)	(0x3C + (x*0x30)) /* USB FIFO data */
+#define  USB_EP_FDAT1(x)	(0x3D + (x*0x30)) /* USB FIFO data */
+#define  USB_EP_FDAT2(x)	(0x3E + (x*0x30)) /* USB FIFO data */
+#define  USB_EP_FDAT3(x)	(0x3F + (x*0x30)) /* USB FIFO data */
+#define  USB_EP_FSTAT(x)	(0x40 + (x*0x30)) /* USB FIFO status */
+#define  USB_EP_FCTRL(x)	(0x44 + (x*0x30)) /* USB FIFO control */
+#define  USB_EP_LRFP(x)		(0x48 + (x*0x30)) /* USB last read frame pointer */
+#define  USB_EP_LWFP(x)		(0x4C + (x*0x30)) /* USB last write frame pointer */
+#define  USB_EP_FALRM(x)	(0x50 + (x*0x30)) /* USB FIFO alarm */
+#define  USB_EP_FRDP(x)		(0x54 + (x*0x30)) /* USB FIFO read pointer */
+#define  USB_EP_FWRP(x)		(0x58 + (x*0x30)) /* USB FIFO write pointer */
+/* USB Control Register Bit Fields.*/
+#define CTRL_CMDOVER		(1<<6)	/* UDC status */
+#define CTRL_CMDERROR		(1<<5)	/* UDC status */
+#define CTRL_FE_ENA		(1<<3)	/* Enable Font End logic */
+#define CTRL_UDC_RST		(1<<2)	/* UDC reset */
+#define CTRL_AFE_ENA		(1<<1)	/* Analog Font end enable */
+#define CTRL_RESUME		(1<<0)	/* UDC resume */
+/* USB Status Register Bit Fields.*/
+#define STAT_RST		(1<<8)
+#define STAT_SUSP		(1<<7)
+#define STAT_CFG		(3<<5)
+#define STAT_INTF		(3<<3)
+#define STAT_ALTSET		(7<<0)
+/* USB Interrupt Status/Mask Registers Bit fields */
+#define INTR_WAKEUP		(1<<31)	/* Wake up Interrupt */
+#define INTR_MSOF		(1<<7)	/* Missed Start of Frame */
+#define INTR_SOF		(1<<6)	/* Start of Frame */
+#define INTR_RESET_STOP		(1<<5)	/* Reset Signaling stop */
+#define INTR_RESET_START	(1<<4)	/* Reset Signaling start */
+#define INTR_RESUME		(1<<3)	/* Suspend to resume */
+#define INTR_SUSPEND		(1<<2)	/* Active to suspend */
+#define INTR_FRAME_MATCH	(1<<1)	/* Frame matched */
+#define INTR_CFG_CHG		(1<<0)	/* Configuration change occurred */
+/* USB Enable Register Bit Fields.*/
+#define ENAB_RST		(1<<31)	/* Reset USB modules */
+#define ENAB_ENAB		(1<<30)	/* Enable USB modules*/
+#define ENAB_SUSPEND		(1<<29)	/* Suspend USB modules */
+#define ENAB_ENDIAN		(1<<28)	/* Endian of USB modules */
+#define ENAB_PWRMD		(1<<0)	/* Power mode of USB modules */
+/* USB Descriptor Ram Address Register bit fields */
+#define DADR_CFG		(1<<31)	/* Configuration */
+#define DADR_BSY		(1<<30)	/* Busy status */
+#define DADR_DADR		(0x1FF)	/* Descriptor Ram Address */
+/* USB Descriptor RAM/Endpoint Buffer Data Register bit fields */
+#define DDAT_DDAT		(0xFF)	/* Descriptor Endpoint Buffer */
+/* USB Endpoint Status Register bit fields */
+#define EPSTAT_BCOUNT		(0x7F<<16)	/* Endpoint FIFO byte count */
+#define EPSTAT_SIP		(1<<8)	/* Endpoint setup in progress */
+#define EPSTAT_DIR		(1<<7)	/* Endpoint transfer direction */
+#define EPSTAT_MAX		(3<<5)	/* Endpoint Max packet size */
+#define EPSTAT_TYP		(3<<3)	/* Endpoint type */
+#define EPSTAT_ZLPS		(1<<2)	/* Send zero length packet */
+#define EPSTAT_FLUSH		(1<<1)	/* Endpoint FIFO Flush */
+#define EPSTAT_STALL		(1<<0)	/* Force stall */
+/* USB Endpoint FIFO Status Register bit fields */
+#define FSTAT_FRAME_STAT	(0xF<<24)	/* Frame status bit [0-3] */
+#define FSTAT_ERR		(1<<22)	/* FIFO error */
+#define FSTAT_UF		(1<<21)	/* FIFO underflow */
+#define FSTAT_OF		(1<<20)	/* FIFO overflow */
+#define FSTAT_FR		(1<<19)	/* FIFO frame ready */
+#define FSTAT_FULL		(1<<18)	/* FIFO full */
+#define FSTAT_ALRM		(1<<17)	/* FIFO alarm */
+#define FSTAT_EMPTY		(1<<16)	/* FIFO empty */
+/* USB Endpoint FIFO Control Register bit fields */
+#define FCTRL_WFR		(1<<29)	/* Write frame end */
+/* USB Endpoint Interrupt Status Regsiter bit fields */
+#define EPINTR_FIFO_FULL	(1<<8)	/* fifo full */
+#define EPINTR_FIFO_EMPTY	(1<<7)	/* fifo empty */
+#define EPINTR_FIFO_ERROR	(1<<6)	/* fifo error */
+#define EPINTR_FIFO_HIGH	(1<<5)	/* fifo high */
+#define EPINTR_FIFO_LOW		(1<<4)	/* fifo low */
+#define EPINTR_MDEVREQ		(1<<3)	/* multi Device request */
+#define EPINTR_EOT		(1<<2)	/* fifo end of transfer */
+#define EPINTR_DEVREQ		(1<<1)	/* Device request */
+#define EPINTR_EOF		(1<<0)	/* fifo end of frame */
+
+/* Debug macros */
+#ifdef DEBUG
+
+//#define DEBUG_IRQ
+//#define DEBUG_REQ
+//#define DEBUG_STATES
+//#define DEBUG_TRX
+//#define DEBUG_INIT
+//#define DEBUG_EP0
+#define DEBUG_EPX
+
+#ifdef DEBUG_IRQ
+	static void dump_ep_intr(const char *label, int nr, int irqreg, struct device *dev)
+	{
+		dev_dbg(dev, "<%s> EP%d_INTR=[%s%s%s%s%s%s%s%s%s]\n", label, nr,
+			(irqreg & EPINTR_FIFO_FULL) ? " full" : "",
+			(irqreg & EPINTR_FIFO_EMPTY) ? " fempty" : "",
+			(irqreg & EPINTR_FIFO_ERROR) ? " ferr" : "",
+			(irqreg & EPINTR_FIFO_HIGH) ? " fhigh" : "",
+			(irqreg & EPINTR_FIFO_LOW) ? " flow" : "",
+			(irqreg & EPINTR_MDEVREQ) ? " mreq" : "",
+			(irqreg & EPINTR_EOF) ? " eof" : "",
+			(irqreg & EPINTR_DEVREQ) ? " devreq" : "",
+			(irqreg & EPINTR_EOT) ? " eot" : "");
+	}
+
+	static void dump_intr(const char *label, int irqreg, struct device *dev)
+	{
+		dev_dbg(dev, "<%s> USB_INTR=[%s%s%s%s%s%s%s%s%s]\n", label,
+			(irqreg & INTR_WAKEUP) ? " wake" : "",
+			(irqreg & INTR_MSOF) ? " msof" : "",
+			(irqreg & INTR_SOF) ? " sof" : "",
+			(irqreg & INTR_RESUME) ? " resume" : "",
+			(irqreg & INTR_SUSPEND) ? " suspend" : "",
+			(irqreg & INTR_RESET_STOP) ? " noreset" : "",
+			(irqreg & INTR_RESET_START) ? " reset" : "",
+			(irqreg & INTR_FRAME_MATCH) ? " fmatch" : "",
+			(irqreg & INTR_CFG_CHG) ? " config" : "");
+	}
+	#define D_IRQ(dev, args...)		dev_dbg(dev, ## args)
+#else
+	#define dump_ep_intr(x, y, z, i)	do {} while (0)
+	#define dump_intr(x, y, z)		do {} while (0)
+	#define D_IRQ(dev, args...)		do {} while (0)
+#endif /* DEBUG_IRQ */
+
+#ifdef DEBUG_REQ
+	static void dump_req(const char *label, struct imx_ep_struct *imx_ep, struct usb_request *req)
+	{
+		int i;
+
+		if (!req || !req->buf) {
+			dev_dbg(imx_ep->imx_usb->dev, "<%s> req or req buf is free\n", label);
+			return;
+		}
+
+		if ((!EP_NO(imx_ep) && imx_ep->imx_usb->ep0state == EP0_IN_DATA_PHASE)
+			|| (EP_NO(imx_ep) && EP_DIR(imx_ep))) {
+
+			dev_dbg(imx_ep->imx_usb->dev, "<%s> ep%d IN request for [%d] bytes; dump <", label, EP_NO(imx_ep), req->length);
+			for (i = 0; i < req->length; i++)
+				printk("%02x-", *((u8 *)req->buf + i));
+			printk(">\n");
+		} else
+			dev_dbg(imx_ep->imx_usb->dev, "<%s> ep%d OUT request for [%d] bytes\n", label, EP_NO(imx_ep), req->length);
+	}
+	#define D_REQ(dev, args...)	dev_dbg(dev, ## args)
+#else
+	#define dump_req(x, y, z)	do {} while (0)
+	#define D_REQ(dev, args...)	do {} while (0)
+#endif /* DEBUG_REQ */
+
+#ifdef DEBUG_STATES
+	static const char *state_name[] = {
+		"EP0_IDLE",
+		"EP0_IN_DATA_PHASE",
+		"EP0_OUT_DATA_PHASE",
+		"EP0_END_XFER",
+		"EP0_STALL"
+	};
+
+	static void dump_usb_stat(const char *label, struct imx_udc_struct *imx_usb)
+	{
+		int temp = __raw_readl(imx_usb->base + USB_STAT);
+
+		dev_dbg(imx_usb->dev,
+			"<%s> USB_STAT=[%s%s CFG=%d, INTF=%d, ALTR=%d]\n", label,
+			(temp & STAT_RST) ? " reset" : "",
+			(temp & STAT_SUSP) ? " suspend" : "",
+			(temp & STAT_CFG) >> 5,
+			(temp & STAT_INTF) >> 3,
+			(temp & STAT_ALTSET));
+	}
+
+	static void dump_ep_stat(const char *label, struct imx_ep_struct *imx_ep)
+	{
+		int temp = __raw_readl(imx_ep->imx_usb->base + USB_EP_INTR(EP_NO(imx_ep)));
+
+		dev_dbg(imx_ep->imx_usb->dev,
+			"<%s> EP%d_INTR=[%s%s%s%s%s%s%s%s%s]\n", label, EP_NO(imx_ep),
+			(temp & EPINTR_FIFO_FULL) ? " full" : "",
+			(temp & EPINTR_FIFO_EMPTY) ? " fempty" : "",
+			(temp & EPINTR_FIFO_ERROR) ? " ferr" : "",
+			(temp & EPINTR_FIFO_HIGH) ? " fhigh" : "",
+			(temp & EPINTR_FIFO_LOW) ? " flow" : "",
+			(temp & EPINTR_MDEVREQ) ? " mreq" : "",
+			(temp & EPINTR_EOF) ? " eof" : "",
+			(temp & EPINTR_DEVREQ) ? " devreq" : "",
+			(temp & EPINTR_EOT) ? " eot" : "");
+
+		temp = __raw_readl(imx_ep->imx_usb->base + USB_EP_STAT(EP_NO(imx_ep)));
+
+		dev_dbg(imx_ep->imx_usb->dev,
+			"<%s> EP%d_STAT=[%s%s bcount=%d]\n", label, EP_NO(imx_ep),
+			(temp & EPSTAT_SIP) ? " sip" : "",
+			(temp & EPSTAT_STALL) ? " stall" : "",
+			(temp & EPSTAT_BCOUNT) >> 16);
+
+		temp = __raw_readl(imx_ep->imx_usb->base + USB_EP_FSTAT(EP_NO(imx_ep)));
+
+		dev_dbg(imx_ep->imx_usb->dev,
+			"<%s> EP%d_FSTAT=[%s%s%s%s%s%s%s]\n", label, EP_NO(imx_ep),
+			(temp & FSTAT_ERR) ? " ferr" : "",
+			(temp & FSTAT_UF) ? " funder" : "",
+			(temp & FSTAT_OF) ? " fover" : "",
+			(temp & FSTAT_FR) ? " fready" : "",
+			(temp & FSTAT_FULL) ? " ffull" : "",
+			(temp & FSTAT_ALRM) ? " falarm" : "",
+			(temp & FSTAT_EMPTY) ? " fempty" : "");
+	}
+	#define D_STT(dev, args...)	dev_dbg(dev, ## args)
+#else
+	#define dump_ep_stat(x, y)	do {} while (0)
+	#define dump_usb_stat(x, y)	do {} while (0)
+	#define D_STT(dev, args...)	do {} while (0)
+#endif /* DEBUG_STATES */
+
+#ifdef DEBUG_TRX
+	#define D_TRX(dev, args...)	dev_dbg(dev, ## args)
+#else
+	#define D_TRX(dev, args...)	do {} while (0)
+#endif /* DEBUG_TRX */
+
+#ifdef DEBUG_INIT
+	#define D_INI(dev, args...)	dev_dbg(dev, ## args)
+#else
+	#define D_INI(dev, args...)	do {} while (0)
+#endif /* DEBUG_INIT */
+
+#ifdef DEBUG_EP0
+	#define D_EP0(dev, args...)	dev_dbg(dev, ## args)
+#else
+	#define D_EP0(dev, args...)	do {} while (0)
+#endif /* DEBUG_EP0 */
+
+#ifdef DEBUG_EPX
+	#define D_EPX(dev, args...)	dev_dbg(dev, ## args)
+#else
+	#define D_EPX(dev, args...)	do {} while (0)
+#endif /* DEBUG_EP0 */
+
+#endif /* DEBUG */
+
+#endif /* __LINUX_USB_GADGET_IMX_H */
diff --git a/drivers/usb/gadget/lh7a40x_udc.c b/drivers/usb/gadget/lh7a40x_udc.c
index c6e7df04c69a..d554b0895603 100644
--- a/drivers/usb/gadget/lh7a40x_udc.c
+++ b/drivers/usb/gadget/lh7a40x_udc.c
@@ -1981,7 +1981,7 @@ static struct lh7a40x_udc memory = {
 		   .ep0 = &memory.ep[0].ep,
 		   .name = driver_name,
 		   .dev = {
-			   .bus_id = "gadget",
+			   .init_name = "gadget",
 			   .release = nop_release,
 			   },
 		   },
diff --git a/drivers/usb/gadget/m66592-udc.c b/drivers/usb/gadget/m66592-udc.c
index 77b44fb48f0a..43dcf9e1af6b 100644
--- a/drivers/usb/gadget/m66592-udc.c
+++ b/drivers/usb/gadget/m66592-udc.c
@@ -623,7 +623,6 @@ static void start_ep0(struct m66592_ep *ep, struct m66592_request *req)
 #if defined(CONFIG_SUPERH_BUILT_IN_M66592)
 static void init_controller(struct m66592 *m66592)
 {
-	usbf_start_clock();
 	m66592_bset(m66592, M66592_HSE, M66592_SYSCFG);		/* High spd */
 	m66592_bclr(m66592, M66592_USBE, M66592_SYSCFG);
 	m66592_bclr(m66592, M66592_DPRPU, M66592_SYSCFG);
@@ -671,9 +670,7 @@ static void init_controller(struct m66592 *m66592)
 
 static void disable_controller(struct m66592 *m66592)
 {
-#if defined(CONFIG_SUPERH_BUILT_IN_M66592)
-	usbf_stop_clock();
-#else
+#if !defined(CONFIG_SUPERH_BUILT_IN_M66592)
 	m66592_bclr(m66592, M66592_SCKE, M66592_SYSCFG);
 	udelay(1);
 	m66592_bclr(m66592, M66592_PLLC, M66592_SYSCFG);
@@ -686,9 +683,7 @@ static void disable_controller(struct m66592 *m66592)
 
 static void m66592_start_xclock(struct m66592 *m66592)
 {
-#if defined(CONFIG_SUPERH_BUILT_IN_M66592)
-	usbf_start_clock();
-#else
+#if !defined(CONFIG_SUPERH_BUILT_IN_M66592)
 	u16 tmp;
 
 	tmp = m66592_read(m66592, M66592_SYSCFG);
@@ -1539,7 +1534,10 @@ static int __exit m66592_remove(struct platform_device *pdev)
 	iounmap(m66592->reg);
 	free_irq(platform_get_irq(pdev, 0), m66592);
 	m66592_free_request(&m66592->ep[0].ep, m66592->ep0_req);
-	usbf_stop_clock();
+#if defined(CONFIG_SUPERH_BUILT_IN_M66592) && defined(CONFIG_HAVE_CLK)
+	clk_disable(m66592->clk);
+	clk_put(m66592->clk);
+#endif
 	kfree(m66592);
 	return 0;
 }
@@ -1548,22 +1546,22 @@ static void nop_completion(struct usb_ep *ep, struct usb_request *r)
 {
 }
 
-#define resource_len(r) (((r)->end - (r)->start) + 1)
-
 static int __init m66592_probe(struct platform_device *pdev)
 {
 	struct resource *res;
 	int irq;
 	void __iomem *reg = NULL;
 	struct m66592 *m66592 = NULL;
+#if defined(CONFIG_SUPERH_BUILT_IN_M66592) && defined(CONFIG_HAVE_CLK)
+	char clk_name[8];
+#endif
 	int ret = 0;
 	int i;
 
-	res = platform_get_resource_byname(pdev, IORESOURCE_MEM,
-			(char *)udc_name);
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	if (!res) {
 		ret = -ENODEV;
-		pr_err("platform_get_resource_byname error.\n");
+		pr_err("platform_get_resource error.\n");
 		goto clean_up;
 	}
 
@@ -1574,7 +1572,7 @@ static int __init m66592_probe(struct platform_device *pdev)
 		goto clean_up;
 	}
 
-	reg = ioremap(res->start, resource_len(res));
+	reg = ioremap(res->start, resource_size(res));
 	if (reg == NULL) {
 		ret = -ENOMEM;
 		pr_err("ioremap error.\n");
@@ -1614,6 +1612,16 @@ static int __init m66592_probe(struct platform_device *pdev)
 		goto clean_up;
 	}
 
+#if defined(CONFIG_SUPERH_BUILT_IN_M66592) && defined(CONFIG_HAVE_CLK)
+	snprintf(clk_name, sizeof(clk_name), "usbf%d", pdev->id);
+	m66592->clk = clk_get(&pdev->dev, clk_name);
+	if (IS_ERR(m66592->clk)) {
+		dev_err(&pdev->dev, "cannot get clock \"%s\"\n", clk_name);
+		ret = PTR_ERR(m66592->clk);
+		goto clean_up2;
+	}
+	clk_enable(m66592->clk);
+#endif
 	INIT_LIST_HEAD(&m66592->gadget.ep_list);
 	m66592->gadget.ep0 = &m66592->ep[0].ep;
 	INIT_LIST_HEAD(&m66592->gadget.ep0->ep_list);
@@ -1645,7 +1653,7 @@ static int __init m66592_probe(struct platform_device *pdev)
 
 	m66592->ep0_req = m66592_alloc_request(&m66592->ep[0].ep, GFP_KERNEL);
 	if (m66592->ep0_req == NULL)
-		goto clean_up2;
+		goto clean_up3;
 	m66592->ep0_req->complete = nop_completion;
 
 	init_controller(m66592);
@@ -1653,7 +1661,12 @@ static int __init m66592_probe(struct platform_device *pdev)
 	dev_info(&pdev->dev, "version %s\n", DRIVER_VERSION);
 	return 0;
 
+clean_up3:
+#if defined(CONFIG_SUPERH_BUILT_IN_M66592) && defined(CONFIG_HAVE_CLK)
+	clk_disable(m66592->clk);
+	clk_put(m66592->clk);
 clean_up2:
+#endif
 	free_irq(irq, m66592);
 clean_up:
 	if (m66592) {
diff --git a/drivers/usb/gadget/m66592-udc.h b/drivers/usb/gadget/m66592-udc.h
index f118f00f1466..286ce07e7960 100644
--- a/drivers/usb/gadget/m66592-udc.h
+++ b/drivers/usb/gadget/m66592-udc.h
@@ -23,6 +23,10 @@
 #ifndef __M66592_UDC_H__
 #define __M66592_UDC_H__
 
+#if defined(CONFIG_SUPERH_BUILT_IN_M66592) && defined(CONFIG_HAVE_CLK)
+#include <linux/clk.h>
+#endif
+
 #define M66592_SYSCFG		0x00
 #define M66592_XTAL		0xC000	/* b15-14: Crystal selection */
 #define   M66592_XTAL48		 0x8000		/* 48MHz */
@@ -476,6 +480,9 @@ struct m66592_ep {
 struct m66592 {
 	spinlock_t		lock;
 	void __iomem		*reg;
+#if defined(CONFIG_SUPERH_BUILT_IN_M66592) && defined(CONFIG_HAVE_CLK)
+	struct clk *clk;
+#endif
 
 	struct usb_gadget		gadget;
 	struct usb_gadget_driver	*driver;
@@ -604,26 +611,6 @@ static inline void m66592_mdfy(struct m66592 *m66592, u16 val, u16 pat,
 #define m66592_bset(m66592, val, offset)	\
 			m66592_mdfy(m66592, val, 0, offset)
 
-#if defined(CONFIG_SUPERH_BUILT_IN_M66592)
-#include <asm/io.h>
-#define MSTPCR2		0xA4150038	/* for SH7722 */
-#define MSTPCR2_USB	0x00000800
-
-static inline void usbf_start_clock(void)
-{
-	ctrl_outl(ctrl_inl(MSTPCR2) & ~MSTPCR2_USB, MSTPCR2);
-}
-
-static inline void usbf_stop_clock(void)
-{
-	ctrl_outl(ctrl_inl(MSTPCR2) | MSTPCR2_USB, MSTPCR2);
-}
-
-#else
-#define usbf_start_clock(x)
-#define usbf_stop_clock(x)
-#endif	/* if defined(CONFIG_SUPERH_BUILT_IN_M66592) */
-
 #endif	/* ifndef __M66592_UDC_H__ */
 
 
diff --git a/drivers/usb/gadget/net2280.c b/drivers/usb/gadget/net2280.c
index 8ae70de2c37d..12c6d83b218c 100644
--- a/drivers/usb/gadget/net2280.c
+++ b/drivers/usb/gadget/net2280.c
@@ -669,7 +669,7 @@ fill_dma_desc (struct net2280_ep *ep, struct net2280_request *req, int valid)
 
 	/* 2280 may be polling VALID_BIT through ep->dma->dmadesc */
 	wmb ();
-	td->dmacount = cpu_to_le32p (&dmacount);
+	td->dmacount = cpu_to_le32(dmacount);
 }
 
 static const u32 dmactl_default =
diff --git a/drivers/usb/gadget/omap_udc.c b/drivers/usb/gadget/omap_udc.c
index 34e9e393f929..57d9641c6bf8 100644
--- a/drivers/usb/gadget/omap_udc.c
+++ b/drivers/usb/gadget/omap_udc.c
@@ -3006,7 +3006,7 @@ cleanup1:
 
 cleanup0:
 	if (xceiv)
-		put_device(xceiv->dev);
+		otg_put_transceiver(xceiv);
 
 	if (cpu_is_omap16xx() || cpu_is_omap24xx()) {
 		clk_disable(hhc_clk);
@@ -3034,7 +3034,7 @@ static int __exit omap_udc_remove(struct platform_device *pdev)
 
 	pullup_disable(udc);
 	if (udc->transceiver) {
-		put_device(udc->transceiver->dev);
+		otg_put_transceiver(udc->transceiver);
 		udc->transceiver = NULL;
 	}
 	omap_writew(0, UDC_SYSCON1);
diff --git a/drivers/usb/gadget/pxa25x_udc.c b/drivers/usb/gadget/pxa25x_udc.c
index 2dbc0db0b46c..9b36205c5759 100644
--- a/drivers/usb/gadget/pxa25x_udc.c
+++ b/drivers/usb/gadget/pxa25x_udc.c
@@ -1833,7 +1833,7 @@ static struct pxa25x_udc memory = {
 		.ep0		= &memory.ep[0].ep,
 		.name		= driver_name,
 		.dev = {
-			.bus_id		= "gadget",
+			.init_name	= "gadget",
 			.release	= nop_release,
 		},
 	},
@@ -2145,7 +2145,7 @@ static int __init pxa25x_udc_probe(struct platform_device *pdev)
 	if (irq < 0)
 		return -ENODEV;
 
-	dev->clk = clk_get(&pdev->dev, "UDCCLK");
+	dev->clk = clk_get(&pdev->dev, NULL);
 	if (IS_ERR(dev->clk)) {
 		retval = PTR_ERR(dev->clk);
 		goto err_clk;
@@ -2198,7 +2198,7 @@ static int __init pxa25x_udc_probe(struct platform_device *pdev)
 	udc_disable(dev);
 	udc_reinit(dev);
 
-	dev->vbus = is_vbus_present();
+	dev->vbus = !!is_vbus_present();
 
 	/* irq setup after old hardware state is cleaned up */
 	retval = request_irq(irq, pxa25x_udc_irq,
diff --git a/drivers/usb/gadget/pxa27x_udc.c b/drivers/usb/gadget/pxa27x_udc.c
index caa37c95802c..990f40f988d4 100644
--- a/drivers/usb/gadget/pxa27x_udc.c
+++ b/drivers/usb/gadget/pxa27x_udc.c
@@ -430,7 +430,6 @@ static void pio_irq_enable(struct pxa_ep *ep)
 /**
  * pio_irq_disable - Disables irq generation for one endpoint
  * @ep: udc endpoint
- * @index: endpoint number
  */
 static void pio_irq_disable(struct pxa_ep *ep)
 {
@@ -586,7 +585,6 @@ static void inc_ep_stats_reqs(struct pxa_ep *ep, int is_in)
  * inc_ep_stats_bytes - Update ep stats counts
  * @ep: physical endpoint
  * @count: bytes transfered on endpoint
- * @req: usb request
  * @is_in: ep direction (USB_DIR_IN or 0)
  */
 static void inc_ep_stats_bytes(struct pxa_ep *ep, int count, int is_in)
@@ -2162,7 +2160,7 @@ static struct pxa_udc memory = {
 		.ep0		= &memory.udc_usb_ep[0].usb_ep,
 		.name		= driver_name,
 		.dev = {
-			.bus_id		= "gadget",
+			.init_name	= "gadget",
 		},
 	},
 
@@ -2226,7 +2224,7 @@ static int __init pxa_udc_probe(struct platform_device *pdev)
 	udc->dev = &pdev->dev;
 	udc->mach = pdev->dev.platform_data;
 
-	udc->clk = clk_get(&pdev->dev, "UDCCLK");
+	udc->clk = clk_get(&pdev->dev, NULL);
 	if (IS_ERR(udc->clk)) {
 		retval = PTR_ERR(udc->clk);
 		goto err_clk;
diff --git a/drivers/usb/gadget/s3c2410_udc.c b/drivers/usb/gadget/s3c2410_udc.c
index 00ba06b44752..9a2b8920532d 100644
--- a/drivers/usb/gadget/s3c2410_udc.c
+++ b/drivers/usb/gadget/s3c2410_udc.c
@@ -36,6 +36,7 @@
 #include <linux/interrupt.h>
 #include <linux/platform_device.h>
 #include <linux/clk.h>
+#include <linux/gpio.h>
 
 #include <linux/debugfs.h>
 #include <linux/seq_file.h>
@@ -51,10 +52,9 @@
 #include <mach/irqs.h>
 
 #include <mach/hardware.h>
-#include <mach/regs-gpio.h>
 
-#include <asm/plat-s3c24xx/regs-udc.h>
-#include <asm/plat-s3c24xx/udc.h>
+#include <plat/regs-udc.h>
+#include <plat/udc.h>
 
 
 #include "s3c2410_udc.h"
@@ -1510,11 +1510,7 @@ static irqreturn_t s3c2410_udc_vbus_irq(int irq, void *_dev)
 
 	dprintk(DEBUG_NORMAL, "%s()\n", __func__);
 
-	/* some cpus cannot read from an line configured to IRQ! */
-	s3c2410_gpio_cfgpin(udc_info->vbus_pin, S3C2410_GPIO_INPUT);
-	value = s3c2410_gpio_getpin(udc_info->vbus_pin);
-	s3c2410_gpio_cfgpin(udc_info->vbus_pin, S3C2410_GPIO_SFN2);
-
+	value = gpio_get_value(udc_info->vbus_pin) ? 1 : 0;
 	if (udc_info->vbus_pin_inverted)
 		value = !value;
 
@@ -1727,7 +1723,7 @@ static struct s3c2410_udc memory = {
 		.ep0		= &memory.ep[0].ep,
 		.name		= gadget_name,
 		.dev = {
-			.bus_id		= "gadget",
+			.init_name	= "gadget",
 		},
 	},
 
@@ -1802,7 +1798,7 @@ static int s3c2410_udc_probe(struct platform_device *pdev)
 	struct s3c2410_udc *udc = &memory;
 	struct device *dev = &pdev->dev;
 	int retval;
-	unsigned int irq;
+	int irq;
 
 	dev_dbg(dev, "%s()\n", __func__);
 
@@ -1861,7 +1857,7 @@ static int s3c2410_udc_probe(struct platform_device *pdev)
 
 	/* irq setup after old hardware state is cleaned up */
 	retval = request_irq(IRQ_USBD, s3c2410_udc_irq,
-			IRQF_DISABLED, gadget_name, udc);
+			     IRQF_DISABLED, gadget_name, udc);
 
 	if (retval != 0) {
 		dev_err(dev, "cannot get irq %i, err %d\n", IRQ_USBD, retval);
@@ -1872,17 +1868,28 @@ static int s3c2410_udc_probe(struct platform_device *pdev)
 	dev_dbg(dev, "got irq %i\n", IRQ_USBD);
 
 	if (udc_info && udc_info->vbus_pin > 0) {
-		irq = s3c2410_gpio_getirq(udc_info->vbus_pin);
+		retval = gpio_request(udc_info->vbus_pin, "udc vbus");
+		if (retval < 0) {
+			dev_err(dev, "cannot claim vbus pin\n");
+			goto err_int;
+		}
+
+		irq = gpio_to_irq(udc_info->vbus_pin);
+		if (irq < 0) {
+			dev_err(dev, "no irq for gpio vbus pin\n");
+			goto err_gpio_claim;
+		}
+
 		retval = request_irq(irq, s3c2410_udc_vbus_irq,
 				     IRQF_DISABLED | IRQF_TRIGGER_RISING
 				     | IRQF_TRIGGER_FALLING | IRQF_SHARED,
 				     gadget_name, udc);
 
 		if (retval != 0) {
-			dev_err(dev, "can't get vbus irq %i, err %d\n",
+			dev_err(dev, "can't get vbus irq %d, err %d\n",
 				irq, retval);
 			retval = -EBUSY;
-			goto err_int;
+			goto err_gpio_claim;
 		}
 
 		dev_dbg(dev, "got irq %i\n", irq);
@@ -1902,6 +1909,9 @@ static int s3c2410_udc_probe(struct platform_device *pdev)
 
 	return 0;
 
+err_gpio_claim:
+	if (udc_info && udc_info->vbus_pin > 0)
+		gpio_free(udc_info->vbus_pin);
 err_int:
 	free_irq(IRQ_USBD, udc);
 err_map:
@@ -1927,7 +1937,7 @@ static int s3c2410_udc_remove(struct platform_device *pdev)
 	debugfs_remove(udc->regs_info);
 
 	if (udc_info && udc_info->vbus_pin > 0) {
-		irq = s3c2410_gpio_getirq(udc_info->vbus_pin);
+		irq = gpio_to_irq(udc_info->vbus_pin);
 		free_irq(irq, udc);
 	}
 
diff --git a/drivers/usb/host/Kconfig b/drivers/usb/host/Kconfig
index f3a75a929e0a..2b476b6b3d4d 100644
--- a/drivers/usb/host/Kconfig
+++ b/drivers/usb/host/Kconfig
@@ -96,6 +96,19 @@ config USB_EHCI_HCD_PPC_OF
 	  Enables support for the USB controller present on the PowerPC
 	  OpenFirmware platform bus.
 
+config USB_OXU210HP_HCD
+	tristate "OXU210HP HCD support"
+	depends on USB
+	---help---
+	  The OXU210HP is an USB host/OTG/device controller. Enable this
+	  option if your board has this chip. If unsure, say N.
+
+	  This driver does not support isochronous transfers and doesn't
+	  implement OTG nor USB device controllers.
+
+	  To compile this driver as a module, choose M here: the
+	  module will be called oxu210hp-hcd.
+
 config USB_ISP116X_HCD
 	tristate "ISP116X HCD support"
 	depends on USB
diff --git a/drivers/usb/host/Makefile b/drivers/usb/host/Makefile
index 23be22224044..e5f3f20787e4 100644
--- a/drivers/usb/host/Makefile
+++ b/drivers/usb/host/Makefile
@@ -13,6 +13,7 @@ obj-$(CONFIG_USB_WHCI_HCD)	+= whci/
 obj-$(CONFIG_PCI)		+= pci-quirks.o
 
 obj-$(CONFIG_USB_EHCI_HCD)	+= ehci-hcd.o
+obj-$(CONFIG_USB_OXU210HP_HCD)	+= oxu210hp-hcd.o
 obj-$(CONFIG_USB_ISP116X_HCD)	+= isp116x-hcd.o
 obj-$(CONFIG_USB_OHCI_HCD)	+= ohci-hcd.o
 obj-$(CONFIG_USB_UHCI_HCD)	+= uhci-hcd.o
diff --git a/drivers/usb/host/ehci-dbg.c b/drivers/usb/host/ehci-dbg.c
index 0cb53ca8d343..7f4ace73d44a 100644
--- a/drivers/usb/host/ehci-dbg.c
+++ b/drivers/usb/host/ehci-dbg.c
@@ -455,9 +455,7 @@ static void qh_lines (
 				(scratch >> 16) & 0x7fff,
 				scratch,
 				td->urb);
-		if (temp < 0)
-			temp = 0;
-		else if (size < temp)
+		if (size < temp)
 			temp = size;
 		size -= temp;
 		next += temp;
@@ -466,9 +464,7 @@ static void qh_lines (
 	}
 
 	temp = snprintf (next, size, "\n");
-	if (temp < 0)
-		temp = 0;
-	else if (size < temp)
+	if (size < temp)
 		temp = size;
 	size -= temp;
 	next += temp;
diff --git a/drivers/usb/host/ehci-hub.c b/drivers/usb/host/ehci-hub.c
index 218f9660d7ee..97a53a48a3d8 100644
--- a/drivers/usb/host/ehci-hub.c
+++ b/drivers/usb/host/ehci-hub.c
@@ -194,6 +194,7 @@ static int ehci_bus_resume (struct usb_hcd *hcd)
 	u32			temp;
 	u32			power_okay;
 	int			i;
+	u8			resume_needed = 0;
 
 	if (time_before (jiffies, ehci->next_statechange))
 		msleep(5);
@@ -228,7 +229,9 @@ static int ehci_bus_resume (struct usb_hcd *hcd)
 
 	/* Some controller/firmware combinations need a delay during which
 	 * they set up the port statuses.  See Bugzilla #8190. */
-	mdelay(8);
+	spin_unlock_irq(&ehci->lock);
+	msleep(8);
+	spin_lock_irq(&ehci->lock);
 
 	/* manually resume the ports we suspended during bus_suspend() */
 	i = HCS_N_PORTS (ehci->hcs_params);
@@ -236,12 +239,21 @@ static int ehci_bus_resume (struct usb_hcd *hcd)
 		temp = ehci_readl(ehci, &ehci->regs->port_status [i]);
 		temp &= ~(PORT_RWC_BITS | PORT_WAKE_BITS);
 		if (test_bit(i, &ehci->bus_suspended) &&
-				(temp & PORT_SUSPEND))
+				(temp & PORT_SUSPEND)) {
 			temp |= PORT_RESUME;
+			resume_needed = 1;
+		}
 		ehci_writel(ehci, temp, &ehci->regs->port_status [i]);
 	}
+
+	/* msleep for 20ms only if code is trying to resume port */
+	if (resume_needed) {
+		spin_unlock_irq(&ehci->lock);
+		msleep(20);
+		spin_lock_irq(&ehci->lock);
+	}
+
 	i = HCS_N_PORTS (ehci->hcs_params);
-	mdelay (20);
 	while (i--) {
 		temp = ehci_readl(ehci, &ehci->regs->port_status [i]);
 		if (test_bit(i, &ehci->bus_suspended) &&
@@ -422,8 +434,15 @@ static int check_reset_complete (
 		port_status &= ~PORT_RWC_BITS;
 		ehci_writel(ehci, port_status, status_reg);
 
-	} else
+		/* ensure 440EPX ohci controller state is operational */
+		if (ehci->has_amcc_usb23)
+			set_ohci_hcfs(ehci, 1);
+	} else {
 		ehci_dbg (ehci, "port %d high speed\n", index + 1);
+		/* ensure 440EPx ohci controller state is suspended */
+		if (ehci->has_amcc_usb23)
+			set_ohci_hcfs(ehci, 0);
+	}
 
 	return port_status;
 }
diff --git a/drivers/usb/host/ehci-ppc-of.c b/drivers/usb/host/ehci-ppc-of.c
index b018deed2e8f..ef732b704f53 100644
--- a/drivers/usb/host/ehci-ppc-of.c
+++ b/drivers/usb/host/ehci-ppc-of.c
@@ -107,11 +107,13 @@ ehci_hcd_ppc_of_probe(struct of_device *op, const struct of_device_id *match)
 {
 	struct device_node *dn = op->node;
 	struct usb_hcd *hcd;
-	struct ehci_hcd	*ehci;
+	struct ehci_hcd	*ehci = NULL;
 	struct resource res;
 	int irq;
 	int rv;
 
+	struct device_node *np;
+
 	if (usb_disabled())
 		return -ENODEV;
 
@@ -149,6 +151,20 @@ ehci_hcd_ppc_of_probe(struct of_device *op, const struct of_device_id *match)
 	}
 
 	ehci = hcd_to_ehci(hcd);
+	np = of_find_compatible_node(NULL, NULL, "ibm,usb-ohci-440epx");
+	if (np != NULL) {
+		/* claim we really affected by usb23 erratum */
+		if (!of_address_to_resource(np, 0, &res))
+			ehci->ohci_hcctrl_reg = ioremap(res.start +
+					OHCI_HCCTRL_OFFSET, OHCI_HCCTRL_LEN);
+		else
+			pr_debug(__FILE__ ": no ohci offset in fdt\n");
+		if (!ehci->ohci_hcctrl_reg) {
+			pr_debug(__FILE__ ": ioremap for ohci hcctrl failed\n");
+		} else {
+			ehci->has_amcc_usb23 = 1;
+		}
+	}
 
 	if (of_get_property(dn, "big-endian", NULL)) {
 		ehci->big_endian_mmio = 1;
@@ -181,6 +197,9 @@ err_ioremap:
 	irq_dispose_mapping(irq);
 err_irq:
 	release_mem_region(hcd->rsrc_start, hcd->rsrc_len);
+
+	if (ehci->has_amcc_usb23)
+		iounmap(ehci->ohci_hcctrl_reg);
 err_rmr:
 	usb_put_hcd(hcd);
 
@@ -191,6 +210,11 @@ err_rmr:
 static int ehci_hcd_ppc_of_remove(struct of_device *op)
 {
 	struct usb_hcd *hcd = dev_get_drvdata(&op->dev);
+	struct ehci_hcd *ehci = hcd_to_ehci(hcd);
+
+	struct device_node *np;
+	struct resource res;
+
 	dev_set_drvdata(&op->dev, NULL);
 
 	dev_dbg(&op->dev, "stopping PPC-OF USB Controller\n");
@@ -201,6 +225,25 @@ static int ehci_hcd_ppc_of_remove(struct of_device *op)
 	irq_dispose_mapping(hcd->irq);
 	release_mem_region(hcd->rsrc_start, hcd->rsrc_len);
 
+	/* use request_mem_region to test if the ohci driver is loaded.  if so
+	 * ensure the ohci core is operational.
+	 */
+	if (ehci->has_amcc_usb23) {
+		np = of_find_compatible_node(NULL, NULL, "ibm,usb-ohci-440epx");
+		if (np != NULL) {
+			if (!of_address_to_resource(np, 0, &res))
+				if (!request_mem_region(res.start,
+							    0x4, hcd_name))
+					set_ohci_hcfs(ehci, 1);
+				else
+					release_mem_region(res.start, 0x4);
+			else
+				pr_debug(__FILE__ ": no ohci offset in fdt\n");
+			of_node_put(np);
+		}
+
+		iounmap(ehci->ohci_hcctrl_reg);
+	}
 	usb_put_hcd(hcd);
 
 	return 0;
diff --git a/drivers/usb/host/ehci.h b/drivers/usb/host/ehci.h
index c7d4b5a06bdb..fb7054ccf4fc 100644
--- a/drivers/usb/host/ehci.h
+++ b/drivers/usb/host/ehci.h
@@ -120,6 +120,16 @@ struct ehci_hcd {			/* one per controller */
 	unsigned		has_fsl_port_bug:1; /* FreeScale */
 	unsigned		big_endian_mmio:1;
 	unsigned		big_endian_desc:1;
+	unsigned		has_amcc_usb23:1;
+
+	/* required for usb32 quirk */
+	#define OHCI_CTRL_HCFS          (3 << 6)
+	#define OHCI_USB_OPER           (2 << 6)
+	#define OHCI_USB_SUSPEND        (3 << 6)
+
+	#define OHCI_HCCTRL_OFFSET      0x4
+	#define OHCI_HCCTRL_LEN         0x4
+	__hc32			*ohci_hcctrl_reg;
 
 	u8			sbrn;		/* packed release number */
 
@@ -636,6 +646,30 @@ static inline void ehci_writel(const struct ehci_hcd *ehci,
 #endif
 }
 
+/*
+ * On certain ppc-44x SoC there is a HW issue, that could only worked around with
+ * explicit suspend/operate of OHCI. This function hereby makes sense only on that arch.
+ * Other common bits are dependant on has_amcc_usb23 quirk flag.
+ */
+#ifdef CONFIG_44x
+static inline void set_ohci_hcfs(struct ehci_hcd *ehci, int operational)
+{
+	u32 hc_control;
+
+	hc_control = (readl_be(ehci->ohci_hcctrl_reg) & ~OHCI_CTRL_HCFS);
+	if (operational)
+		hc_control |= OHCI_USB_OPER;
+	else
+		hc_control |= OHCI_USB_SUSPEND;
+
+	writel_be(hc_control, ehci->ohci_hcctrl_reg);
+	(void) readl_be(ehci->ohci_hcctrl_reg);
+}
+#else
+static inline void set_ohci_hcfs(struct ehci_hcd *ehci, int operational)
+{ }
+#endif
+
 /*-------------------------------------------------------------------------*/
 
 /*
diff --git a/drivers/usb/host/ohci-pnx4008.c b/drivers/usb/host/ohci-pnx4008.c
index e306ca6aef3d..100bf3d8437c 100644
--- a/drivers/usb/host/ohci-pnx4008.c
+++ b/drivers/usb/host/ohci-pnx4008.c
@@ -106,65 +106,34 @@ extern int ocpi_enable(void);
 
 static struct clk *usb_clk;
 
-static int isp1301_probe(struct i2c_adapter *adap);
-static int isp1301_detach(struct i2c_client *client);
-
 static const unsigned short normal_i2c[] =
     { ISP1301_I2C_ADDR, ISP1301_I2C_ADDR + 1, I2C_CLIENT_END };
-static const unsigned short dummy_i2c_addrlist[] = { I2C_CLIENT_END };
-
-static struct i2c_client_address_data addr_data = {
-	.normal_i2c = normal_i2c,
-	.probe = dummy_i2c_addrlist,
-	.ignore = dummy_i2c_addrlist,
-};
-
-struct i2c_driver isp1301_driver = {
-	.driver = {
-		.name = "isp1301_pnx",
-	},
-	.attach_adapter = isp1301_probe,
-	.detach_client = isp1301_detach,
-};
 
-static int isp1301_attach(struct i2c_adapter *adap, int addr, int kind)
+static int isp1301_probe(struct i2c_client *client,
+			 const struct i2c_device_id *id)
 {
-	struct i2c_client *c;
-	int err;
-
-	c = kzalloc(sizeof(*c), GFP_KERNEL);
-	if (!c)
-		return -ENOMEM;
-
-	strlcpy(c->name, "isp1301_pnx", I2C_NAME_SIZE);
-	c->flags = 0;
-	c->addr = addr;
-	c->adapter = adap;
-	c->driver = &isp1301_driver;
-
-	err = i2c_attach_client(c);
-	if (err) {
-		kfree(c);
-		return err;
-	}
-
-	isp1301_i2c_client = c;
-
 	return 0;
 }
 
-static int isp1301_probe(struct i2c_adapter *adap)
+static int isp1301_remove(struct i2c_client *client)
 {
-	return i2c_probe(adap, &addr_data, isp1301_attach);
-}
-
-static int isp1301_detach(struct i2c_client *client)
-{
-	i2c_detach_client(client);
-	kfree(isp1301_i2c_client);
 	return 0;
 }
 
+const struct i2c_device_id isp1301_id[] = {
+	{ "isp1301_pnx", 0 },
+	{ }
+};
+
+struct i2c_driver isp1301_driver = {
+	.driver = {
+		.name = "isp1301_pnx",
+	},
+	.probe = isp1301_probe,
+	.remove = isp1301_remove,
+	.id_table = isp1301_id,
+};
+
 static void i2c_write(u8 buf, u8 subaddr)
 {
 	char tmpbuf[2];
@@ -328,6 +297,8 @@ static int __devinit usb_hcd_pnx4008_probe(struct platform_device *pdev)
 	struct usb_hcd *hcd = 0;
 	struct ohci_hcd *ohci;
 	const struct hc_driver *driver = &ohci_pnx4008_hc_driver;
+	struct i2c_adapter *i2c_adap;
+	struct i2c_board_info i2c_info;
 
 	int ret = 0, irq;
 
@@ -351,9 +322,20 @@ static int __devinit usb_hcd_pnx4008_probe(struct platform_device *pdev)
 
 	ret = i2c_add_driver(&isp1301_driver);
 	if (ret < 0) {
-		err("failed to connect I2C to ISP1301 USB Transceiver");
+		err("failed to add ISP1301 driver");
 		goto out;
 	}
+	i2c_adap = i2c_get_adapter(2);
+	memset(&i2c_info, 0, sizeof(struct i2c_board_info));
+	strlcpy(i2c_info.name, "isp1301_pnx", I2C_NAME_SIZE);
+	isp1301_i2c_client = i2c_new_probed_device(i2c_adap, &i2c_info,
+						   normal_i2c);
+	i2c_put_adapter(i2c_adap);
+	if (!isp1301_i2c_client) {
+		err("failed to connect I2C to ISP1301 USB Transceiver");
+		ret = -ENODEV;
+		goto out_i2c_driver;
+	}
 
 	isp1301_configure();
 
@@ -429,6 +411,9 @@ out3:
 out2:
 	clk_put(usb_clk);
 out1:
+	i2c_unregister_client(isp1301_i2c_client);
+	isp1301_i2c_client = NULL;
+out_i2c_driver:
 	i2c_del_driver(&isp1301_driver);
 out:
 	return ret;
@@ -445,6 +430,8 @@ static int usb_hcd_pnx4008_remove(struct platform_device *pdev)
 	pnx4008_unset_usb_bits();
 	clk_disable(usb_clk);
 	clk_put(usb_clk);
+	i2c_unregister_client(isp1301_i2c_client);
+	isp1301_i2c_client = NULL;
 	i2c_del_driver(&isp1301_driver);
 
 	platform_set_drvdata(pdev, NULL);
diff --git a/drivers/usb/host/ohci-ppc-of.c b/drivers/usb/host/ohci-ppc-of.c
index 7ac53264ead3..68a301710297 100644
--- a/drivers/usb/host/ohci-ppc-of.c
+++ b/drivers/usb/host/ohci-ppc-of.c
@@ -91,6 +91,7 @@ ohci_hcd_ppc_of_probe(struct of_device *op, const struct of_device_id *match)
 
 	int rv;
 	int is_bigendian;
+	struct device_node *np;
 
 	if (usb_disabled())
 		return -ENODEV;
@@ -147,6 +148,30 @@ ohci_hcd_ppc_of_probe(struct of_device *op, const struct of_device_id *match)
 	if (rv == 0)
 		return 0;
 
+	/* by now, 440epx is known to show usb_23 erratum */
+	np = of_find_compatible_node(NULL, NULL, "ibm,usb-ehci-440epx");
+
+	/* Work around - At this point ohci_run has executed, the
+	* controller is running, everything, the root ports, etc., is
+	* set up.  If the ehci driver is loaded, put the ohci core in
+	* the suspended state.  The ehci driver will bring it out of
+	* suspended state when / if a non-high speed USB device is
+	* attached to the USB Host port.  If the ehci driver is not
+	* loaded, do nothing. request_mem_region is used to test if
+	* the ehci driver is loaded.
+	*/
+	if (np !=  NULL) {
+		if (!of_address_to_resource(np, 0, &res)) {
+			if (!request_mem_region(res.start, 0x4, hcd_name)) {
+				writel_be((readl_be(&ohci->regs->control) |
+					OHCI_USB_SUSPEND), &ohci->regs->control);
+					(void) readl_be(&ohci->regs->control);
+			} else
+				release_mem_region(res.start, 0x4);
+		} else
+		    pr_debug(__FILE__ ": cannot get ehci offset from fdt\n");
+	}
+
 	iounmap(hcd->regs);
 err_ioremap:
 	irq_dispose_mapping(irq);
diff --git a/drivers/usb/host/ohci-pxa27x.c b/drivers/usb/host/ohci-pxa27x.c
index e294d430733b..e44dc2cbca24 100644
--- a/drivers/usb/host/ohci-pxa27x.c
+++ b/drivers/usb/host/ohci-pxa27x.c
@@ -296,7 +296,7 @@ int usb_hcd_pxa27x_probe (const struct hc_driver *driver, struct platform_device
 		return -ENXIO;
 	}
 
-	usb_clk = clk_get(&pdev->dev, "USBCLK");
+	usb_clk = clk_get(&pdev->dev, NULL);
 	if (IS_ERR(usb_clk))
 		return PTR_ERR(usb_clk);
 
diff --git a/drivers/usb/host/ohci-tmio.c b/drivers/usb/host/ohci-tmio.c
index f9f134af0bd1..8dabe8e31d8c 100644
--- a/drivers/usb/host/ohci-tmio.c
+++ b/drivers/usb/host/ohci-tmio.c
@@ -201,7 +201,7 @@ static int __devinit ohci_hcd_tmio_drv_probe(struct platform_device *dev)
 	if (!cell)
 		return -EINVAL;
 
-	hcd = usb_create_hcd(&ohci_tmio_hc_driver, &dev->dev, dev->dev.bus_id);
+	hcd = usb_create_hcd(&ohci_tmio_hc_driver, &dev->dev, dev_name(&dev->dev));
 	if (!hcd) {
 		ret = -ENOMEM;
 		goto err_usb_create_hcd;
diff --git a/drivers/usb/host/oxu210hp-hcd.c b/drivers/usb/host/oxu210hp-hcd.c
new file mode 100644
index 000000000000..75548f7c716b
--- /dev/null
+++ b/drivers/usb/host/oxu210hp-hcd.c
@@ -0,0 +1,3985 @@
+/*
+ * Copyright (c) 2008 Rodolfo Giometti <giometti@linux.it>
+ * Copyright (c) 2008 Eurotech S.p.A. <info@eurtech.it>
+ *
+ * This code is *strongly* based on EHCI-HCD code by David Brownell since
+ * the chip is a quasi-EHCI compatible.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the
+ * Free Software Foundation; either version 2 of the License, or (at your
+ * option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY
+ * or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
+ * for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software Foundation,
+ * Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ */
+
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/dmapool.h>
+#include <linux/kernel.h>
+#include <linux/delay.h>
+#include <linux/ioport.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/errno.h>
+#include <linux/init.h>
+#include <linux/timer.h>
+#include <linux/list.h>
+#include <linux/interrupt.h>
+#include <linux/reboot.h>
+#include <linux/usb.h>
+#include <linux/moduleparam.h>
+#include <linux/dma-mapping.h>
+#include <linux/io.h>
+
+#include "../core/hcd.h"
+
+#include <asm/irq.h>
+#include <asm/system.h>
+#include <asm/unaligned.h>
+
+#include <linux/irq.h>
+#include <linux/platform_device.h>
+
+#include "oxu210hp.h"
+
+#define DRIVER_VERSION "0.0.50"
+
+/*
+ * Main defines
+ */
+
+#define oxu_dbg(oxu, fmt, args...) \
+		dev_dbg(oxu_to_hcd(oxu)->self.controller , fmt , ## args)
+#define oxu_err(oxu, fmt, args...) \
+		dev_err(oxu_to_hcd(oxu)->self.controller , fmt , ## args)
+#define oxu_info(oxu, fmt, args...) \
+		dev_info(oxu_to_hcd(oxu)->self.controller , fmt , ## args)
+
+static inline struct usb_hcd *oxu_to_hcd(struct oxu_hcd *oxu)
+{
+	return container_of((void *) oxu, struct usb_hcd, hcd_priv);
+}
+
+static inline struct oxu_hcd *hcd_to_oxu(struct usb_hcd *hcd)
+{
+	return (struct oxu_hcd *) (hcd->hcd_priv);
+}
+
+/*
+ * Debug stuff
+ */
+
+#undef OXU_URB_TRACE
+#undef OXU_VERBOSE_DEBUG
+
+#ifdef OXU_VERBOSE_DEBUG
+#define oxu_vdbg			oxu_dbg
+#else
+#define oxu_vdbg(oxu, fmt, args...)	/* Nop */
+#endif
+
+#ifdef DEBUG
+
+static int __attribute__((__unused__))
+dbg_status_buf(char *buf, unsigned len, const char *label, u32 status)
+{
+	return scnprintf(buf, len, "%s%sstatus %04x%s%s%s%s%s%s%s%s%s%s",
+		label, label[0] ? " " : "", status,
+		(status & STS_ASS) ? " Async" : "",
+		(status & STS_PSS) ? " Periodic" : "",
+		(status & STS_RECL) ? " Recl" : "",
+		(status & STS_HALT) ? " Halt" : "",
+		(status & STS_IAA) ? " IAA" : "",
+		(status & STS_FATAL) ? " FATAL" : "",
+		(status & STS_FLR) ? " FLR" : "",
+		(status & STS_PCD) ? " PCD" : "",
+		(status & STS_ERR) ? " ERR" : "",
+		(status & STS_INT) ? " INT" : ""
+		);
+}
+
+static int __attribute__((__unused__))
+dbg_intr_buf(char *buf, unsigned len, const char *label, u32 enable)
+{
+	return scnprintf(buf, len, "%s%sintrenable %02x%s%s%s%s%s%s",
+		label, label[0] ? " " : "", enable,
+		(enable & STS_IAA) ? " IAA" : "",
+		(enable & STS_FATAL) ? " FATAL" : "",
+		(enable & STS_FLR) ? " FLR" : "",
+		(enable & STS_PCD) ? " PCD" : "",
+		(enable & STS_ERR) ? " ERR" : "",
+		(enable & STS_INT) ? " INT" : ""
+		);
+}
+
+static const char *const fls_strings[] =
+    { "1024", "512", "256", "??" };
+
+static int dbg_command_buf(char *buf, unsigned len,
+				const char *label, u32 command)
+{
+	return scnprintf(buf, len,
+		"%s%scommand %06x %s=%d ithresh=%d%s%s%s%s period=%s%s %s",
+		label, label[0] ? " " : "", command,
+		(command & CMD_PARK) ? "park" : "(park)",
+		CMD_PARK_CNT(command),
+		(command >> 16) & 0x3f,
+		(command & CMD_LRESET) ? " LReset" : "",
+		(command & CMD_IAAD) ? " IAAD" : "",
+		(command & CMD_ASE) ? " Async" : "",
+		(command & CMD_PSE) ? " Periodic" : "",
+		fls_strings[(command >> 2) & 0x3],
+		(command & CMD_RESET) ? " Reset" : "",
+		(command & CMD_RUN) ? "RUN" : "HALT"
+		);
+}
+
+static int dbg_port_buf(char *buf, unsigned len, const char *label,
+				int port, u32 status)
+{
+	char	*sig;
+
+	/* signaling state */
+	switch (status & (3 << 10)) {
+	case 0 << 10:
+		sig = "se0";
+		break;
+	case 1 << 10:
+		sig = "k";	/* low speed */
+		break;
+	case 2 << 10:
+		sig = "j";
+		break;
+	default:
+		sig = "?";
+		break;
+	}
+
+	return scnprintf(buf, len,
+		"%s%sport %d status %06x%s%s sig=%s%s%s%s%s%s%s%s%s%s",
+		label, label[0] ? " " : "", port, status,
+		(status & PORT_POWER) ? " POWER" : "",
+		(status & PORT_OWNER) ? " OWNER" : "",
+		sig,
+		(status & PORT_RESET) ? " RESET" : "",
+		(status & PORT_SUSPEND) ? " SUSPEND" : "",
+		(status & PORT_RESUME) ? " RESUME" : "",
+		(status & PORT_OCC) ? " OCC" : "",
+		(status & PORT_OC) ? " OC" : "",
+		(status & PORT_PEC) ? " PEC" : "",
+		(status & PORT_PE) ? " PE" : "",
+		(status & PORT_CSC) ? " CSC" : "",
+		(status & PORT_CONNECT) ? " CONNECT" : ""
+	    );
+}
+
+#else
+
+static inline int __attribute__((__unused__))
+dbg_status_buf(char *buf, unsigned len, const char *label, u32 status)
+{ return 0; }
+
+static inline int __attribute__((__unused__))
+dbg_command_buf(char *buf, unsigned len, const char *label, u32 command)
+{ return 0; }
+
+static inline int __attribute__((__unused__))
+dbg_intr_buf(char *buf, unsigned len, const char *label, u32 enable)
+{ return 0; }
+
+static inline int __attribute__((__unused__))
+dbg_port_buf(char *buf, unsigned len, const char *label, int port, u32 status)
+{ return 0; }
+
+#endif /* DEBUG */
+
+/* functions have the "wrong" filename when they're output... */
+#define dbg_status(oxu, label, status) { \
+	char _buf[80]; \
+	dbg_status_buf(_buf, sizeof _buf, label, status); \
+	oxu_dbg(oxu, "%s\n", _buf); \
+}
+
+#define dbg_cmd(oxu, label, command) { \
+	char _buf[80]; \
+	dbg_command_buf(_buf, sizeof _buf, label, command); \
+	oxu_dbg(oxu, "%s\n", _buf); \
+}
+
+#define dbg_port(oxu, label, port, status) { \
+	char _buf[80]; \
+	dbg_port_buf(_buf, sizeof _buf, label, port, status); \
+	oxu_dbg(oxu, "%s\n", _buf); \
+}
+
+/*
+ * Module parameters
+ */
+
+/* Initial IRQ latency: faster than hw default */
+static int log2_irq_thresh;			/* 0 to 6 */
+module_param(log2_irq_thresh, int, S_IRUGO);
+MODULE_PARM_DESC(log2_irq_thresh, "log2 IRQ latency, 1-64 microframes");
+
+/* Initial park setting: slower than hw default */
+static unsigned park;
+module_param(park, uint, S_IRUGO);
+MODULE_PARM_DESC(park, "park setting; 1-3 back-to-back async packets");
+
+/* For flakey hardware, ignore overcurrent indicators */
+static int ignore_oc;
+module_param(ignore_oc, bool, S_IRUGO);
+MODULE_PARM_DESC(ignore_oc, "ignore bogus hardware overcurrent indications");
+
+
+static void ehci_work(struct oxu_hcd *oxu);
+static int oxu_hub_control(struct usb_hcd *hcd,
+				u16 typeReq, u16 wValue, u16 wIndex,
+				char *buf, u16 wLength);
+
+/*
+ * Local functions
+ */
+
+/* Low level read/write registers functions */
+static inline u32 oxu_readl(void *base, u32 reg)
+{
+	return readl(base + reg);
+}
+
+static inline void oxu_writel(void *base, u32 reg, u32 val)
+{
+	writel(val, base + reg);
+}
+
+static inline void timer_action_done(struct oxu_hcd *oxu,
+					enum ehci_timer_action action)
+{
+	clear_bit(action, &oxu->actions);
+}
+
+static inline void timer_action(struct oxu_hcd *oxu,
+					enum ehci_timer_action action)
+{
+	if (!test_and_set_bit(action, &oxu->actions)) {
+		unsigned long t;
+
+		switch (action) {
+		case TIMER_IAA_WATCHDOG:
+			t = EHCI_IAA_JIFFIES;
+			break;
+		case TIMER_IO_WATCHDOG:
+			t = EHCI_IO_JIFFIES;
+			break;
+		case TIMER_ASYNC_OFF:
+			t = EHCI_ASYNC_JIFFIES;
+			break;
+		case TIMER_ASYNC_SHRINK:
+		default:
+			t = EHCI_SHRINK_JIFFIES;
+			break;
+		}
+		t += jiffies;
+		/* all timings except IAA watchdog can be overridden.
+		 * async queue SHRINK often precedes IAA.  while it's ready
+		 * to go OFF neither can matter, and afterwards the IO
+		 * watchdog stops unless there's still periodic traffic.
+		 */
+		if (action != TIMER_IAA_WATCHDOG
+				&& t > oxu->watchdog.expires
+				&& timer_pending(&oxu->watchdog))
+			return;
+		mod_timer(&oxu->watchdog, t);
+	}
+}
+
+/*
+ * handshake - spin reading hc until handshake completes or fails
+ * @ptr: address of hc register to be read
+ * @mask: bits to look at in result of read
+ * @done: value of those bits when handshake succeeds
+ * @usec: timeout in microseconds
+ *
+ * Returns negative errno, or zero on success
+ *
+ * Success happens when the "mask" bits have the specified value (hardware
+ * handshake done).  There are two failure modes:  "usec" have passed (major
+ * hardware flakeout), or the register reads as all-ones (hardware removed).
+ *
+ * That last failure should_only happen in cases like physical cardbus eject
+ * before driver shutdown. But it also seems to be caused by bugs in cardbus
+ * bridge shutdown:  shutting down the bridge before the devices using it.
+ */
+static int handshake(struct oxu_hcd *oxu, void __iomem *ptr,
+					u32 mask, u32 done, int usec)
+{
+	u32 result;
+
+	do {
+		result = readl(ptr);
+		if (result == ~(u32)0)		/* card removed */
+			return -ENODEV;
+		result &= mask;
+		if (result == done)
+			return 0;
+		udelay(1);
+		usec--;
+	} while (usec > 0);
+	return -ETIMEDOUT;
+}
+
+/* Force HC to halt state from unknown (EHCI spec section 2.3) */
+static int ehci_halt(struct oxu_hcd *oxu)
+{
+	u32	temp = readl(&oxu->regs->status);
+
+	/* disable any irqs left enabled by previous code */
+	writel(0, &oxu->regs->intr_enable);
+
+	if ((temp & STS_HALT) != 0)
+		return 0;
+
+	temp = readl(&oxu->regs->command);
+	temp &= ~CMD_RUN;
+	writel(temp, &oxu->regs->command);
+	return handshake(oxu, &oxu->regs->status,
+			  STS_HALT, STS_HALT, 16 * 125);
+}
+
+/* Put TDI/ARC silicon into EHCI mode */
+static void tdi_reset(struct oxu_hcd *oxu)
+{
+	u32 __iomem *reg_ptr;
+	u32 tmp;
+
+	reg_ptr = (u32 __iomem *)(((u8 __iomem *)oxu->regs) + 0x68);
+	tmp = readl(reg_ptr);
+	tmp |= 0x3;
+	writel(tmp, reg_ptr);
+}
+
+/* Reset a non-running (STS_HALT == 1) controller */
+static int ehci_reset(struct oxu_hcd *oxu)
+{
+	int	retval;
+	u32	command = readl(&oxu->regs->command);
+
+	command |= CMD_RESET;
+	dbg_cmd(oxu, "reset", command);
+	writel(command, &oxu->regs->command);
+	oxu_to_hcd(oxu)->state = HC_STATE_HALT;
+	oxu->next_statechange = jiffies;
+	retval = handshake(oxu, &oxu->regs->command,
+			    CMD_RESET, 0, 250 * 1000);
+
+	if (retval)
+		return retval;
+
+	tdi_reset(oxu);
+
+	return retval;
+}
+
+/* Idle the controller (from running) */
+static void ehci_quiesce(struct oxu_hcd *oxu)
+{
+	u32	temp;
+
+#ifdef DEBUG
+	if (!HC_IS_RUNNING(oxu_to_hcd(oxu)->state))
+		BUG();
+#endif
+
+	/* wait for any schedule enables/disables to take effect */
+	temp = readl(&oxu->regs->command) << 10;
+	temp &= STS_ASS | STS_PSS;
+	if (handshake(oxu, &oxu->regs->status, STS_ASS | STS_PSS,
+				temp, 16 * 125) != 0) {
+		oxu_to_hcd(oxu)->state = HC_STATE_HALT;
+		return;
+	}
+
+	/* then disable anything that's still active */
+	temp = readl(&oxu->regs->command);
+	temp &= ~(CMD_ASE | CMD_IAAD | CMD_PSE);
+	writel(temp, &oxu->regs->command);
+
+	/* hardware can take 16 microframes to turn off ... */
+	if (handshake(oxu, &oxu->regs->status, STS_ASS | STS_PSS,
+				0, 16 * 125) != 0) {
+		oxu_to_hcd(oxu)->state = HC_STATE_HALT;
+		return;
+	}
+}
+
+static int check_reset_complete(struct oxu_hcd *oxu, int index,
+				u32 __iomem *status_reg, int port_status)
+{
+	if (!(port_status & PORT_CONNECT)) {
+		oxu->reset_done[index] = 0;
+		return port_status;
+	}
+
+	/* if reset finished and it's still not enabled -- handoff */
+	if (!(port_status & PORT_PE)) {
+		oxu_dbg(oxu, "Failed to enable port %d on root hub TT\n",
+				index+1);
+		return port_status;
+	} else
+		oxu_dbg(oxu, "port %d high speed\n", index + 1);
+
+	return port_status;
+}
+
+static void ehci_hub_descriptor(struct oxu_hcd *oxu,
+				struct usb_hub_descriptor *desc)
+{
+	int ports = HCS_N_PORTS(oxu->hcs_params);
+	u16 temp;
+
+	desc->bDescriptorType = 0x29;
+	desc->bPwrOn2PwrGood = 10;	/* oxu 1.0, 2.3.9 says 20ms max */
+	desc->bHubContrCurrent = 0;
+
+	desc->bNbrPorts = ports;
+	temp = 1 + (ports / 8);
+	desc->bDescLength = 7 + 2 * temp;
+
+	/* two bitmaps:  ports removable, and usb 1.0 legacy PortPwrCtrlMask */
+	memset(&desc->bitmap[0], 0, temp);
+	memset(&desc->bitmap[temp], 0xff, temp);
+
+	temp = 0x0008;			/* per-port overcurrent reporting */
+	if (HCS_PPC(oxu->hcs_params))
+		temp |= 0x0001;		/* per-port power control */
+	else
+		temp |= 0x0002;		/* no power switching */
+	desc->wHubCharacteristics = (__force __u16)cpu_to_le16(temp);
+}
+
+
+/* Allocate an OXU210HP on-chip memory data buffer
+ *
+ * An on-chip memory data buffer is required for each OXU210HP USB transfer.
+ * Each transfer descriptor has one or more on-chip memory data buffers.
+ *
+ * Data buffers are allocated from a fix sized pool of data blocks.
+ * To minimise fragmentation and give reasonable memory utlisation,
+ * data buffers are allocated with sizes the power of 2 multiples of
+ * the block size, starting on an address a multiple of the allocated size.
+ *
+ * FIXME: callers of this function require a buffer to be allocated for
+ * len=0. This is a waste of on-chip memory and should be fix. Then this
+ * function should be changed to not allocate a buffer for len=0.
+ */
+static int oxu_buf_alloc(struct oxu_hcd *oxu, struct ehci_qtd *qtd, int len)
+{
+	int n_blocks;	/* minium blocks needed to hold len */
+	int a_blocks;	/* blocks allocated */
+	int i, j;
+
+	/* Don't allocte bigger than supported */
+	if (len > BUFFER_SIZE * BUFFER_NUM) {
+		oxu_err(oxu, "buffer too big (%d)\n", len);
+		return -ENOMEM;
+	}
+
+	spin_lock(&oxu->mem_lock);
+
+	/* Number of blocks needed to hold len */
+	n_blocks = (len + BUFFER_SIZE - 1) / BUFFER_SIZE;
+
+	/* Round the number of blocks up to the power of 2 */
+	for (a_blocks = 1; a_blocks < n_blocks; a_blocks <<= 1)
+		;
+
+	/* Find a suitable available data buffer */
+	for (i = 0; i < BUFFER_NUM;
+			i += max(a_blocks, (int)oxu->db_used[i])) {
+
+		/* Check all the required blocks are available */
+		for (j = 0; j < a_blocks; j++)
+			if (oxu->db_used[i + j])
+				break;
+
+		if (j != a_blocks)
+			continue;
+
+		/* Allocate blocks found! */
+		qtd->buffer = (void *) &oxu->mem->db_pool[i];
+		qtd->buffer_dma = virt_to_phys(qtd->buffer);
+
+		qtd->qtd_buffer_len = BUFFER_SIZE * a_blocks;
+		oxu->db_used[i] = a_blocks;
+
+		spin_unlock(&oxu->mem_lock);
+
+		return 0;
+	}
+
+	/* Failed */
+
+	spin_unlock(&oxu->mem_lock);
+
+	return -ENOMEM;
+}
+
+static void oxu_buf_free(struct oxu_hcd *oxu, struct ehci_qtd *qtd)
+{
+	int index;
+
+	spin_lock(&oxu->mem_lock);
+
+	index = (qtd->buffer - (void *) &oxu->mem->db_pool[0])
+							 / BUFFER_SIZE;
+	oxu->db_used[index] = 0;
+	qtd->qtd_buffer_len = 0;
+	qtd->buffer_dma = 0;
+	qtd->buffer = NULL;
+
+	spin_unlock(&oxu->mem_lock);
+
+	return;
+}
+
+static inline void ehci_qtd_init(struct ehci_qtd *qtd, dma_addr_t dma)
+{
+	memset(qtd, 0, sizeof *qtd);
+	qtd->qtd_dma = dma;
+	qtd->hw_token = cpu_to_le32(QTD_STS_HALT);
+	qtd->hw_next = EHCI_LIST_END;
+	qtd->hw_alt_next = EHCI_LIST_END;
+	INIT_LIST_HEAD(&qtd->qtd_list);
+}
+
+static inline void oxu_qtd_free(struct oxu_hcd *oxu, struct ehci_qtd *qtd)
+{
+	int index;
+
+	if (qtd->buffer)
+		oxu_buf_free(oxu, qtd);
+
+	spin_lock(&oxu->mem_lock);
+
+	index = qtd - &oxu->mem->qtd_pool[0];
+	oxu->qtd_used[index] = 0;
+
+	spin_unlock(&oxu->mem_lock);
+
+	return;
+}
+
+static struct ehci_qtd *ehci_qtd_alloc(struct oxu_hcd *oxu)
+{
+	int i;
+	struct ehci_qtd *qtd = NULL;
+
+	spin_lock(&oxu->mem_lock);
+
+	for (i = 0; i < QTD_NUM; i++)
+		if (!oxu->qtd_used[i])
+			break;
+
+	if (i < QTD_NUM) {
+		qtd = (struct ehci_qtd *) &oxu->mem->qtd_pool[i];
+		memset(qtd, 0, sizeof *qtd);
+
+		qtd->hw_token = cpu_to_le32(QTD_STS_HALT);
+		qtd->hw_next = EHCI_LIST_END;
+		qtd->hw_alt_next = EHCI_LIST_END;
+		INIT_LIST_HEAD(&qtd->qtd_list);
+
+		qtd->qtd_dma = virt_to_phys(qtd);
+
+		oxu->qtd_used[i] = 1;
+	}
+
+	spin_unlock(&oxu->mem_lock);
+
+	return qtd;
+}
+
+static void oxu_qh_free(struct oxu_hcd *oxu, struct ehci_qh *qh)
+{
+	int index;
+
+	spin_lock(&oxu->mem_lock);
+
+	index = qh - &oxu->mem->qh_pool[0];
+	oxu->qh_used[index] = 0;
+
+	spin_unlock(&oxu->mem_lock);
+
+	return;
+}
+
+static void qh_destroy(struct kref *kref)
+{
+	struct ehci_qh *qh = container_of(kref, struct ehci_qh, kref);
+	struct oxu_hcd *oxu = qh->oxu;
+
+	/* clean qtds first, and know this is not linked */
+	if (!list_empty(&qh->qtd_list) || qh->qh_next.ptr) {
+		oxu_dbg(oxu, "unused qh not empty!\n");
+		BUG();
+	}
+	if (qh->dummy)
+		oxu_qtd_free(oxu, qh->dummy);
+	oxu_qh_free(oxu, qh);
+}
+
+static struct ehci_qh *oxu_qh_alloc(struct oxu_hcd *oxu)
+{
+	int i;
+	struct ehci_qh *qh = NULL;
+
+	spin_lock(&oxu->mem_lock);
+
+	for (i = 0; i < QHEAD_NUM; i++)
+		if (!oxu->qh_used[i])
+			break;
+
+	if (i < QHEAD_NUM) {
+		qh = (struct ehci_qh *) &oxu->mem->qh_pool[i];
+		memset(qh, 0, sizeof *qh);
+
+		kref_init(&qh->kref);
+		qh->oxu = oxu;
+		qh->qh_dma = virt_to_phys(qh);
+		INIT_LIST_HEAD(&qh->qtd_list);
+
+		/* dummy td enables safe urb queuing */
+		qh->dummy = ehci_qtd_alloc(oxu);
+		if (qh->dummy == NULL) {
+			oxu_dbg(oxu, "no dummy td\n");
+			oxu->qh_used[i] = 0;
+
+			return NULL;
+		}
+
+		oxu->qh_used[i] = 1;
+	}
+
+	spin_unlock(&oxu->mem_lock);
+
+	return qh;
+}
+
+/* to share a qh (cpu threads, or hc) */
+static inline struct ehci_qh *qh_get(struct ehci_qh *qh)
+{
+	kref_get(&qh->kref);
+	return qh;
+}
+
+static inline void qh_put(struct ehci_qh *qh)
+{
+	kref_put(&qh->kref, qh_destroy);
+}
+
+static void oxu_murb_free(struct oxu_hcd *oxu, struct oxu_murb *murb)
+{
+	int index;
+
+	spin_lock(&oxu->mem_lock);
+
+	index = murb - &oxu->murb_pool[0];
+	oxu->murb_used[index] = 0;
+
+	spin_unlock(&oxu->mem_lock);
+
+	return;
+}
+
+static struct oxu_murb *oxu_murb_alloc(struct oxu_hcd *oxu)
+
+{
+	int i;
+	struct oxu_murb *murb = NULL;
+
+	spin_lock(&oxu->mem_lock);
+
+	for (i = 0; i < MURB_NUM; i++)
+		if (!oxu->murb_used[i])
+			break;
+
+	if (i < MURB_NUM) {
+		murb = &(oxu->murb_pool)[i];
+
+		oxu->murb_used[i] = 1;
+	}
+
+	spin_unlock(&oxu->mem_lock);
+
+	return murb;
+}
+
+/* The queue heads and transfer descriptors are managed from pools tied
+ * to each of the "per device" structures.
+ * This is the initialisation and cleanup code.
+ */
+static void ehci_mem_cleanup(struct oxu_hcd *oxu)
+{
+	kfree(oxu->murb_pool);
+	oxu->murb_pool = NULL;
+
+	if (oxu->async)
+		qh_put(oxu->async);
+	oxu->async = NULL;
+
+	del_timer(&oxu->urb_timer);
+
+	oxu->periodic = NULL;
+
+	/* shadow periodic table */
+	kfree(oxu->pshadow);
+	oxu->pshadow = NULL;
+}
+
+/* Remember to add cleanup code (above) if you add anything here.
+ */
+static int ehci_mem_init(struct oxu_hcd *oxu, gfp_t flags)
+{
+	int i;
+
+	for (i = 0; i < oxu->periodic_size; i++)
+		oxu->mem->frame_list[i] = EHCI_LIST_END;
+	for (i = 0; i < QHEAD_NUM; i++)
+		oxu->qh_used[i] = 0;
+	for (i = 0; i < QTD_NUM; i++)
+		oxu->qtd_used[i] = 0;
+
+	oxu->murb_pool = kcalloc(MURB_NUM, sizeof(struct oxu_murb), flags);
+	if (!oxu->murb_pool)
+		goto fail;
+
+	for (i = 0; i < MURB_NUM; i++)
+		oxu->murb_used[i] = 0;
+
+	oxu->async = oxu_qh_alloc(oxu);
+	if (!oxu->async)
+		goto fail;
+
+	oxu->periodic = (__le32 *) &oxu->mem->frame_list;
+	oxu->periodic_dma = virt_to_phys(oxu->periodic);
+
+	for (i = 0; i < oxu->periodic_size; i++)
+		oxu->periodic[i] = EHCI_LIST_END;
+
+	/* software shadow of hardware table */
+	oxu->pshadow = kcalloc(oxu->periodic_size, sizeof(void *), flags);
+	if (oxu->pshadow != NULL)
+		return 0;
+
+fail:
+	oxu_dbg(oxu, "couldn't init memory\n");
+	ehci_mem_cleanup(oxu);
+	return -ENOMEM;
+}
+
+/* Fill a qtd, returning how much of the buffer we were able to queue up.
+ */
+static int qtd_fill(struct ehci_qtd *qtd, dma_addr_t buf, size_t len,
+				int token, int maxpacket)
+{
+	int i, count;
+	u64 addr = buf;
+
+	/* one buffer entry per 4K ... first might be short or unaligned */
+	qtd->hw_buf[0] = cpu_to_le32((u32)addr);
+	qtd->hw_buf_hi[0] = cpu_to_le32((u32)(addr >> 32));
+	count = 0x1000 - (buf & 0x0fff);	/* rest of that page */
+	if (likely(len < count))		/* ... iff needed */
+		count = len;
+	else {
+		buf +=  0x1000;
+		buf &= ~0x0fff;
+
+		/* per-qtd limit: from 16K to 20K (best alignment) */
+		for (i = 1; count < len && i < 5; i++) {
+			addr = buf;
+			qtd->hw_buf[i] = cpu_to_le32((u32)addr);
+			qtd->hw_buf_hi[i] = cpu_to_le32((u32)(addr >> 32));
+			buf += 0x1000;
+			if ((count + 0x1000) < len)
+				count += 0x1000;
+			else
+				count = len;
+		}
+
+		/* short packets may only terminate transfers */
+		if (count != len)
+			count -= (count % maxpacket);
+	}
+	qtd->hw_token = cpu_to_le32((count << 16) | token);
+	qtd->length = count;
+
+	return count;
+}
+
+static inline void qh_update(struct oxu_hcd *oxu,
+				struct ehci_qh *qh, struct ehci_qtd *qtd)
+{
+	/* writes to an active overlay are unsafe */
+	BUG_ON(qh->qh_state != QH_STATE_IDLE);
+
+	qh->hw_qtd_next = QTD_NEXT(qtd->qtd_dma);
+	qh->hw_alt_next = EHCI_LIST_END;
+
+	/* Except for control endpoints, we make hardware maintain data
+	 * toggle (like OHCI) ... here (re)initialize the toggle in the QH,
+	 * and set the pseudo-toggle in udev. Only usb_clear_halt() will
+	 * ever clear it.
+	 */
+	if (!(qh->hw_info1 & cpu_to_le32(1 << 14))) {
+		unsigned	is_out, epnum;
+
+		is_out = !(qtd->hw_token & cpu_to_le32(1 << 8));
+		epnum = (le32_to_cpup(&qh->hw_info1) >> 8) & 0x0f;
+		if (unlikely(!usb_gettoggle(qh->dev, epnum, is_out))) {
+			qh->hw_token &= ~__constant_cpu_to_le32(QTD_TOGGLE);
+			usb_settoggle(qh->dev, epnum, is_out, 1);
+		}
+	}
+
+	/* HC must see latest qtd and qh data before we clear ACTIVE+HALT */
+	wmb();
+	qh->hw_token &= __constant_cpu_to_le32(QTD_TOGGLE | QTD_STS_PING);
+}
+
+/* If it weren't for a common silicon quirk (writing the dummy into the qh
+ * overlay, so qh->hw_token wrongly becomes inactive/halted), only fault
+ * recovery (including urb dequeue) would need software changes to a QH...
+ */
+static void qh_refresh(struct oxu_hcd *oxu, struct ehci_qh *qh)
+{
+	struct ehci_qtd *qtd;
+
+	if (list_empty(&qh->qtd_list))
+		qtd = qh->dummy;
+	else {
+		qtd = list_entry(qh->qtd_list.next,
+				struct ehci_qtd, qtd_list);
+		/* first qtd may already be partially processed */
+		if (cpu_to_le32(qtd->qtd_dma) == qh->hw_current)
+			qtd = NULL;
+	}
+
+	if (qtd)
+		qh_update(oxu, qh, qtd);
+}
+
+static void qtd_copy_status(struct oxu_hcd *oxu, struct urb *urb,
+				size_t length, u32 token)
+{
+	/* count IN/OUT bytes, not SETUP (even short packets) */
+	if (likely(QTD_PID(token) != 2))
+		urb->actual_length += length - QTD_LENGTH(token);
+
+	/* don't modify error codes */
+	if (unlikely(urb->status != -EINPROGRESS))
+		return;
+
+	/* force cleanup after short read; not always an error */
+	if (unlikely(IS_SHORT_READ(token)))
+		urb->status = -EREMOTEIO;
+
+	/* serious "can't proceed" faults reported by the hardware */
+	if (token & QTD_STS_HALT) {
+		if (token & QTD_STS_BABBLE) {
+			/* FIXME "must" disable babbling device's port too */
+			urb->status = -EOVERFLOW;
+		} else if (token & QTD_STS_MMF) {
+			/* fs/ls interrupt xfer missed the complete-split */
+			urb->status = -EPROTO;
+		} else if (token & QTD_STS_DBE) {
+			urb->status = (QTD_PID(token) == 1) /* IN ? */
+				? -ENOSR  /* hc couldn't read data */
+				: -ECOMM; /* hc couldn't write data */
+		} else if (token & QTD_STS_XACT) {
+			/* timeout, bad crc, wrong PID, etc; retried */
+			if (QTD_CERR(token))
+				urb->status = -EPIPE;
+			else {
+				oxu_dbg(oxu, "devpath %s ep%d%s 3strikes\n",
+					urb->dev->devpath,
+					usb_pipeendpoint(urb->pipe),
+					usb_pipein(urb->pipe) ? "in" : "out");
+				urb->status = -EPROTO;
+			}
+		/* CERR nonzero + no errors + halt --> stall */
+		} else if (QTD_CERR(token))
+			urb->status = -EPIPE;
+		else	/* unknown */
+			urb->status = -EPROTO;
+
+		oxu_vdbg(oxu, "dev%d ep%d%s qtd token %08x --> status %d\n",
+			usb_pipedevice(urb->pipe),
+			usb_pipeendpoint(urb->pipe),
+			usb_pipein(urb->pipe) ? "in" : "out",
+			token, urb->status);
+	}
+}
+
+static void ehci_urb_done(struct oxu_hcd *oxu, struct urb *urb)
+__releases(oxu->lock)
+__acquires(oxu->lock)
+{
+	if (likely(urb->hcpriv != NULL)) {
+		struct ehci_qh	*qh = (struct ehci_qh *) urb->hcpriv;
+
+		/* S-mask in a QH means it's an interrupt urb */
+		if ((qh->hw_info2 & __constant_cpu_to_le32(QH_SMASK)) != 0) {
+
+			/* ... update hc-wide periodic stats (for usbfs) */
+			oxu_to_hcd(oxu)->self.bandwidth_int_reqs--;
+		}
+		qh_put(qh);
+	}
+
+	urb->hcpriv = NULL;
+	switch (urb->status) {
+	case -EINPROGRESS:		/* success */
+		urb->status = 0;
+	default:			/* fault */
+		break;
+	case -EREMOTEIO:		/* fault or normal */
+		if (!(urb->transfer_flags & URB_SHORT_NOT_OK))
+			urb->status = 0;
+		break;
+	case -ECONNRESET:		/* canceled */
+	case -ENOENT:
+		break;
+	}
+
+#ifdef OXU_URB_TRACE
+	oxu_dbg(oxu, "%s %s urb %p ep%d%s status %d len %d/%d\n",
+		__func__, urb->dev->devpath, urb,
+		usb_pipeendpoint(urb->pipe),
+		usb_pipein(urb->pipe) ? "in" : "out",
+		urb->status,
+		urb->actual_length, urb->transfer_buffer_length);
+#endif
+
+	/* complete() can reenter this HCD */
+	spin_unlock(&oxu->lock);
+	usb_hcd_giveback_urb(oxu_to_hcd(oxu), urb, urb->status);
+	spin_lock(&oxu->lock);
+}
+
+static void start_unlink_async(struct oxu_hcd *oxu, struct ehci_qh *qh);
+static void unlink_async(struct oxu_hcd *oxu, struct ehci_qh *qh);
+
+static void intr_deschedule(struct oxu_hcd *oxu, struct ehci_qh *qh);
+static int qh_schedule(struct oxu_hcd *oxu, struct ehci_qh *qh);
+
+#define HALT_BIT __constant_cpu_to_le32(QTD_STS_HALT)
+
+/* Process and free completed qtds for a qh, returning URBs to drivers.
+ * Chases up to qh->hw_current.  Returns number of completions called,
+ * indicating how much "real" work we did.
+ */
+static unsigned qh_completions(struct oxu_hcd *oxu, struct ehci_qh *qh)
+{
+	struct ehci_qtd *last = NULL, *end = qh->dummy;
+	struct list_head *entry, *tmp;
+	int stopped;
+	unsigned count = 0;
+	int do_status = 0;
+	u8 state;
+	struct oxu_murb *murb = NULL;
+
+	if (unlikely(list_empty(&qh->qtd_list)))
+		return count;
+
+	/* completions (or tasks on other cpus) must never clobber HALT
+	 * till we've gone through and cleaned everything up, even when
+	 * they add urbs to this qh's queue or mark them for unlinking.
+	 *
+	 * NOTE:  unlinking expects to be done in queue order.
+	 */
+	state = qh->qh_state;
+	qh->qh_state = QH_STATE_COMPLETING;
+	stopped = (state == QH_STATE_IDLE);
+
+	/* remove de-activated QTDs from front of queue.
+	 * after faults (including short reads), cleanup this urb
+	 * then let the queue advance.
+	 * if queue is stopped, handles unlinks.
+	 */
+	list_for_each_safe(entry, tmp, &qh->qtd_list) {
+		struct ehci_qtd	*qtd;
+		struct urb *urb;
+		u32 token = 0;
+
+		qtd = list_entry(entry, struct ehci_qtd, qtd_list);
+		urb = qtd->urb;
+
+		/* Clean up any state from previous QTD ...*/
+		if (last) {
+			if (likely(last->urb != urb)) {
+				if (last->urb->complete == NULL) {
+					murb = (struct oxu_murb *) last->urb;
+					last->urb = murb->main;
+					if (murb->last) {
+						ehci_urb_done(oxu, last->urb);
+						count++;
+					}
+					oxu_murb_free(oxu, murb);
+				} else {
+					ehci_urb_done(oxu, last->urb);
+					count++;
+				}
+			}
+			oxu_qtd_free(oxu, last);
+			last = NULL;
+		}
+
+		/* ignore urbs submitted during completions we reported */
+		if (qtd == end)
+			break;
+
+		/* hardware copies qtd out of qh overlay */
+		rmb();
+		token = le32_to_cpu(qtd->hw_token);
+
+		/* always clean up qtds the hc de-activated */
+		if ((token & QTD_STS_ACTIVE) == 0) {
+
+			if ((token & QTD_STS_HALT) != 0) {
+				stopped = 1;
+
+			/* magic dummy for some short reads; qh won't advance.
+			 * that silicon quirk can kick in with this dummy too.
+			 */
+			} else if (IS_SHORT_READ(token) &&
+					!(qtd->hw_alt_next & EHCI_LIST_END)) {
+				stopped = 1;
+				goto halt;
+			}
+
+		/* stop scanning when we reach qtds the hc is using */
+		} else if (likely(!stopped &&
+				HC_IS_RUNNING(oxu_to_hcd(oxu)->state))) {
+			break;
+
+		} else {
+			stopped = 1;
+
+			if (unlikely(!HC_IS_RUNNING(oxu_to_hcd(oxu)->state)))
+				urb->status = -ESHUTDOWN;
+
+			/* ignore active urbs unless some previous qtd
+			 * for the urb faulted (including short read) or
+			 * its urb was canceled.  we may patch qh or qtds.
+			 */
+			if (likely(urb->status == -EINPROGRESS))
+				continue;
+
+			/* issue status after short control reads */
+			if (unlikely(do_status != 0)
+					&& QTD_PID(token) == 0 /* OUT */) {
+				do_status = 0;
+				continue;
+			}
+
+			/* token in overlay may be most current */
+			if (state == QH_STATE_IDLE
+					&& cpu_to_le32(qtd->qtd_dma)
+						== qh->hw_current)
+				token = le32_to_cpu(qh->hw_token);
+
+			/* force halt for unlinked or blocked qh, so we'll
+			 * patch the qh later and so that completions can't
+			 * activate it while we "know" it's stopped.
+			 */
+			if ((HALT_BIT & qh->hw_token) == 0) {
+halt:
+				qh->hw_token |= HALT_BIT;
+				wmb();
+			}
+		}
+
+		/* Remove it from the queue */
+		qtd_copy_status(oxu, urb->complete ?
+					urb : ((struct oxu_murb *) urb)->main,
+				qtd->length, token);
+		if ((usb_pipein(qtd->urb->pipe)) &&
+				(NULL != qtd->transfer_buffer))
+			memcpy(qtd->transfer_buffer, qtd->buffer, qtd->length);
+		do_status = (urb->status == -EREMOTEIO)
+				&& usb_pipecontrol(urb->pipe);
+
+		if (stopped && qtd->qtd_list.prev != &qh->qtd_list) {
+			last = list_entry(qtd->qtd_list.prev,
+					struct ehci_qtd, qtd_list);
+			last->hw_next = qtd->hw_next;
+		}
+		list_del(&qtd->qtd_list);
+		last = qtd;
+	}
+
+	/* last urb's completion might still need calling */
+	if (likely(last != NULL)) {
+		if (last->urb->complete == NULL) {
+			murb = (struct oxu_murb *) last->urb;
+			last->urb = murb->main;
+			if (murb->last) {
+				ehci_urb_done(oxu, last->urb);
+				count++;
+			}
+			oxu_murb_free(oxu, murb);
+		} else {
+			ehci_urb_done(oxu, last->urb);
+			count++;
+		}
+		oxu_qtd_free(oxu, last);
+	}
+
+	/* restore original state; caller must unlink or relink */
+	qh->qh_state = state;
+
+	/* be sure the hardware's done with the qh before refreshing
+	 * it after fault cleanup, or recovering from silicon wrongly
+	 * overlaying the dummy qtd (which reduces DMA chatter).
+	 */
+	if (stopped != 0 || qh->hw_qtd_next == EHCI_LIST_END) {
+		switch (state) {
+		case QH_STATE_IDLE:
+			qh_refresh(oxu, qh);
+			break;
+		case QH_STATE_LINKED:
+			/* should be rare for periodic transfers,
+			 * except maybe high bandwidth ...
+			 */
+			if ((__constant_cpu_to_le32(QH_SMASK)
+					& qh->hw_info2) != 0) {
+				intr_deschedule(oxu, qh);
+				(void) qh_schedule(oxu, qh);
+			} else
+				unlink_async(oxu, qh);
+			break;
+		/* otherwise, unlink already started */
+		}
+	}
+
+	return count;
+}
+
+/* High bandwidth multiplier, as encoded in highspeed endpoint descriptors */
+#define hb_mult(wMaxPacketSize)		(1 + (((wMaxPacketSize) >> 11) & 0x03))
+/* ... and packet size, for any kind of endpoint descriptor */
+#define max_packet(wMaxPacketSize)	((wMaxPacketSize) & 0x07ff)
+
+/* Reverse of qh_urb_transaction: free a list of TDs.
+ * used for cleanup after errors, before HC sees an URB's TDs.
+ */
+static void qtd_list_free(struct oxu_hcd *oxu,
+				struct urb *urb, struct list_head *qtd_list)
+{
+	struct list_head *entry, *temp;
+
+	list_for_each_safe(entry, temp, qtd_list) {
+		struct ehci_qtd	*qtd;
+
+		qtd = list_entry(entry, struct ehci_qtd, qtd_list);
+		list_del(&qtd->qtd_list);
+		oxu_qtd_free(oxu, qtd);
+	}
+}
+
+/* Create a list of filled qtds for this URB; won't link into qh.
+ */
+static struct list_head *qh_urb_transaction(struct oxu_hcd *oxu,
+						struct urb *urb,
+						struct list_head *head,
+						gfp_t flags)
+{
+	struct ehci_qtd	*qtd, *qtd_prev;
+	dma_addr_t buf;
+	int len, maxpacket;
+	int is_input;
+	u32 token;
+	void *transfer_buf = NULL;
+	int ret;
+
+	/*
+	 * URBs map to sequences of QTDs: one logical transaction
+	 */
+	qtd = ehci_qtd_alloc(oxu);
+	if (unlikely(!qtd))
+		return NULL;
+	list_add_tail(&qtd->qtd_list, head);
+	qtd->urb = urb;
+
+	token = QTD_STS_ACTIVE;
+	token |= (EHCI_TUNE_CERR << 10);
+	/* for split transactions, SplitXState initialized to zero */
+
+	len = urb->transfer_buffer_length;
+	is_input = usb_pipein(urb->pipe);
+	if (!urb->transfer_buffer && urb->transfer_buffer_length && is_input)
+		urb->transfer_buffer = phys_to_virt(urb->transfer_dma);
+
+	if (usb_pipecontrol(urb->pipe)) {
+		/* SETUP pid */
+		ret = oxu_buf_alloc(oxu, qtd, sizeof(struct usb_ctrlrequest));
+		if (ret)
+			goto cleanup;
+
+		qtd_fill(qtd, qtd->buffer_dma, sizeof(struct usb_ctrlrequest),
+				token | (2 /* "setup" */ << 8), 8);
+		memcpy(qtd->buffer, qtd->urb->setup_packet,
+				sizeof(struct usb_ctrlrequest));
+
+		/* ... and always at least one more pid */
+		token ^= QTD_TOGGLE;
+		qtd_prev = qtd;
+		qtd = ehci_qtd_alloc(oxu);
+		if (unlikely(!qtd))
+			goto cleanup;
+		qtd->urb = urb;
+		qtd_prev->hw_next = QTD_NEXT(qtd->qtd_dma);
+		list_add_tail(&qtd->qtd_list, head);
+
+		/* for zero length DATA stages, STATUS is always IN */
+		if (len == 0)
+			token |= (1 /* "in" */ << 8);
+	}
+
+	/*
+	 * Data transfer stage: buffer setup
+	 */
+
+	ret = oxu_buf_alloc(oxu, qtd, len);
+	if (ret)
+		goto cleanup;
+
+	buf = qtd->buffer_dma;
+	transfer_buf = urb->transfer_buffer;
+
+	if (!is_input)
+		memcpy(qtd->buffer, qtd->urb->transfer_buffer, len);
+
+	if (is_input)
+		token |= (1 /* "in" */ << 8);
+	/* else it's already initted to "out" pid (0 << 8) */
+
+	maxpacket = max_packet(usb_maxpacket(urb->dev, urb->pipe, !is_input));
+
+	/*
+	 * buffer gets wrapped in one or more qtds;
+	 * last one may be "short" (including zero len)
+	 * and may serve as a control status ack
+	 */
+	for (;;) {
+		int this_qtd_len;
+
+		this_qtd_len = qtd_fill(qtd, buf, len, token, maxpacket);
+		qtd->transfer_buffer = transfer_buf;
+		len -= this_qtd_len;
+		buf += this_qtd_len;
+		transfer_buf += this_qtd_len;
+		if (is_input)
+			qtd->hw_alt_next = oxu->async->hw_alt_next;
+
+		/* qh makes control packets use qtd toggle; maybe switch it */
+		if ((maxpacket & (this_qtd_len + (maxpacket - 1))) == 0)
+			token ^= QTD_TOGGLE;
+
+		if (likely(len <= 0))
+			break;
+
+		qtd_prev = qtd;
+		qtd = ehci_qtd_alloc(oxu);
+		if (unlikely(!qtd))
+			goto cleanup;
+		if (likely(len > 0)) {
+			ret = oxu_buf_alloc(oxu, qtd, len);
+			if (ret)
+				goto cleanup;
+		}
+		qtd->urb = urb;
+		qtd_prev->hw_next = QTD_NEXT(qtd->qtd_dma);
+		list_add_tail(&qtd->qtd_list, head);
+	}
+
+	/* unless the bulk/interrupt caller wants a chance to clean
+	 * up after short reads, hc should advance qh past this urb
+	 */
+	if (likely((urb->transfer_flags & URB_SHORT_NOT_OK) == 0
+				|| usb_pipecontrol(urb->pipe)))
+		qtd->hw_alt_next = EHCI_LIST_END;
+
+	/*
+	 * control requests may need a terminating data "status" ack;
+	 * bulk ones may need a terminating short packet (zero length).
+	 */
+	if (likely(urb->transfer_buffer_length != 0)) {
+		int	one_more = 0;
+
+		if (usb_pipecontrol(urb->pipe)) {
+			one_more = 1;
+			token ^= 0x0100;	/* "in" <--> "out"  */
+			token |= QTD_TOGGLE;	/* force DATA1 */
+		} else if (usb_pipebulk(urb->pipe)
+				&& (urb->transfer_flags & URB_ZERO_PACKET)
+				&& !(urb->transfer_buffer_length % maxpacket)) {
+			one_more = 1;
+		}
+		if (one_more) {
+			qtd_prev = qtd;
+			qtd = ehci_qtd_alloc(oxu);
+			if (unlikely(!qtd))
+				goto cleanup;
+			qtd->urb = urb;
+			qtd_prev->hw_next = QTD_NEXT(qtd->qtd_dma);
+			list_add_tail(&qtd->qtd_list, head);
+
+			/* never any data in such packets */
+			qtd_fill(qtd, 0, 0, token, 0);
+		}
+	}
+
+	/* by default, enable interrupt on urb completion */
+		qtd->hw_token |= __constant_cpu_to_le32(QTD_IOC);
+	return head;
+
+cleanup:
+	qtd_list_free(oxu, urb, head);
+	return NULL;
+}
+
+/* Each QH holds a qtd list; a QH is used for everything except iso.
+ *
+ * For interrupt urbs, the scheduler must set the microframe scheduling
+ * mask(s) each time the QH gets scheduled.  For highspeed, that's
+ * just one microframe in the s-mask.  For split interrupt transactions
+ * there are additional complications: c-mask, maybe FSTNs.
+ */
+static struct ehci_qh *qh_make(struct oxu_hcd *oxu,
+				struct urb *urb, gfp_t flags)
+{
+	struct ehci_qh *qh = oxu_qh_alloc(oxu);
+	u32 info1 = 0, info2 = 0;
+	int is_input, type;
+	int maxp = 0;
+
+	if (!qh)
+		return qh;
+
+	/*
+	 * init endpoint/device data for this QH
+	 */
+	info1 |= usb_pipeendpoint(urb->pipe) << 8;
+	info1 |= usb_pipedevice(urb->pipe) << 0;
+
+	is_input = usb_pipein(urb->pipe);
+	type = usb_pipetype(urb->pipe);
+	maxp = usb_maxpacket(urb->dev, urb->pipe, !is_input);
+
+	/* Compute interrupt scheduling parameters just once, and save.
+	 * - allowing for high bandwidth, how many nsec/uframe are used?
+	 * - split transactions need a second CSPLIT uframe; same question
+	 * - splits also need a schedule gap (for full/low speed I/O)
+	 * - qh has a polling interval
+	 *
+	 * For control/bulk requests, the HC or TT handles these.
+	 */
+	if (type == PIPE_INTERRUPT) {
+		qh->usecs = NS_TO_US(usb_calc_bus_time(USB_SPEED_HIGH,
+								is_input, 0,
+				hb_mult(maxp) * max_packet(maxp)));
+		qh->start = NO_FRAME;
+
+		if (urb->dev->speed == USB_SPEED_HIGH) {
+			qh->c_usecs = 0;
+			qh->gap_uf = 0;
+
+			qh->period = urb->interval >> 3;
+			if (qh->period == 0 && urb->interval != 1) {
+				/* NOTE interval 2 or 4 uframes could work.
+				 * But interval 1 scheduling is simpler, and
+				 * includes high bandwidth.
+				 */
+				dbg("intr period %d uframes, NYET!",
+						urb->interval);
+				goto done;
+			}
+		} else {
+			struct usb_tt	*tt = urb->dev->tt;
+			int		think_time;
+
+			/* gap is f(FS/LS transfer times) */
+			qh->gap_uf = 1 + usb_calc_bus_time(urb->dev->speed,
+					is_input, 0, maxp) / (125 * 1000);
+
+			/* FIXME this just approximates SPLIT/CSPLIT times */
+			if (is_input) {		/* SPLIT, gap, CSPLIT+DATA */
+				qh->c_usecs = qh->usecs + HS_USECS(0);
+				qh->usecs = HS_USECS(1);
+			} else {		/* SPLIT+DATA, gap, CSPLIT */
+				qh->usecs += HS_USECS(1);
+				qh->c_usecs = HS_USECS(0);
+			}
+
+			think_time = tt ? tt->think_time : 0;
+			qh->tt_usecs = NS_TO_US(think_time +
+					usb_calc_bus_time(urb->dev->speed,
+					is_input, 0, max_packet(maxp)));
+			qh->period = urb->interval;
+		}
+	}
+
+	/* support for tt scheduling, and access to toggles */
+	qh->dev = urb->dev;
+
+	/* using TT? */
+	switch (urb->dev->speed) {
+	case USB_SPEED_LOW:
+		info1 |= (1 << 12);	/* EPS "low" */
+		/* FALL THROUGH */
+
+	case USB_SPEED_FULL:
+		/* EPS 0 means "full" */
+		if (type != PIPE_INTERRUPT)
+			info1 |= (EHCI_TUNE_RL_TT << 28);
+		if (type == PIPE_CONTROL) {
+			info1 |= (1 << 27);	/* for TT */
+			info1 |= 1 << 14;	/* toggle from qtd */
+		}
+		info1 |= maxp << 16;
+
+		info2 |= (EHCI_TUNE_MULT_TT << 30);
+		info2 |= urb->dev->ttport << 23;
+
+		/* NOTE:  if (PIPE_INTERRUPT) { scheduler sets c-mask } */
+
+		break;
+
+	case USB_SPEED_HIGH:		/* no TT involved */
+		info1 |= (2 << 12);	/* EPS "high" */
+		if (type == PIPE_CONTROL) {
+			info1 |= (EHCI_TUNE_RL_HS << 28);
+			info1 |= 64 << 16;	/* usb2 fixed maxpacket */
+			info1 |= 1 << 14;	/* toggle from qtd */
+			info2 |= (EHCI_TUNE_MULT_HS << 30);
+		} else if (type == PIPE_BULK) {
+			info1 |= (EHCI_TUNE_RL_HS << 28);
+			info1 |= 512 << 16;	/* usb2 fixed maxpacket */
+			info2 |= (EHCI_TUNE_MULT_HS << 30);
+		} else {		/* PIPE_INTERRUPT */
+			info1 |= max_packet(maxp) << 16;
+			info2 |= hb_mult(maxp) << 30;
+		}
+		break;
+	default:
+		dbg("bogus dev %p speed %d", urb->dev, urb->dev->speed);
+done:
+		qh_put(qh);
+		return NULL;
+	}
+
+	/* NOTE:  if (PIPE_INTERRUPT) { scheduler sets s-mask } */
+
+	/* init as live, toggle clear, advance to dummy */
+	qh->qh_state = QH_STATE_IDLE;
+	qh->hw_info1 = cpu_to_le32(info1);
+	qh->hw_info2 = cpu_to_le32(info2);
+	usb_settoggle(urb->dev, usb_pipeendpoint(urb->pipe), !is_input, 1);
+	qh_refresh(oxu, qh);
+	return qh;
+}
+
+/* Move qh (and its qtds) onto async queue; maybe enable queue.
+ */
+static void qh_link_async(struct oxu_hcd *oxu, struct ehci_qh *qh)
+{
+	__le32 dma = QH_NEXT(qh->qh_dma);
+	struct ehci_qh *head;
+
+	/* (re)start the async schedule? */
+	head = oxu->async;
+	timer_action_done(oxu, TIMER_ASYNC_OFF);
+	if (!head->qh_next.qh) {
+		u32	cmd = readl(&oxu->regs->command);
+
+		if (!(cmd & CMD_ASE)) {
+			/* in case a clear of CMD_ASE didn't take yet */
+			(void)handshake(oxu, &oxu->regs->status,
+					STS_ASS, 0, 150);
+			cmd |= CMD_ASE | CMD_RUN;
+			writel(cmd, &oxu->regs->command);
+			oxu_to_hcd(oxu)->state = HC_STATE_RUNNING;
+			/* posted write need not be known to HC yet ... */
+		}
+	}
+
+	/* clear halt and/or toggle; and maybe recover from silicon quirk */
+	if (qh->qh_state == QH_STATE_IDLE)
+		qh_refresh(oxu, qh);
+
+	/* splice right after start */
+	qh->qh_next = head->qh_next;
+	qh->hw_next = head->hw_next;
+	wmb();
+
+	head->qh_next.qh = qh;
+	head->hw_next = dma;
+
+	qh->qh_state = QH_STATE_LINKED;
+	/* qtd completions reported later by interrupt */
+}
+
+#define	QH_ADDR_MASK	__constant_cpu_to_le32(0x7f)
+
+/*
+ * For control/bulk/interrupt, return QH with these TDs appended.
+ * Allocates and initializes the QH if necessary.
+ * Returns null if it can't allocate a QH it needs to.
+ * If the QH has TDs (urbs) already, that's great.
+ */
+static struct ehci_qh *qh_append_tds(struct oxu_hcd *oxu,
+				struct urb *urb, struct list_head *qtd_list,
+				int epnum, void	**ptr)
+{
+	struct ehci_qh *qh = NULL;
+
+	qh = (struct ehci_qh *) *ptr;
+	if (unlikely(qh == NULL)) {
+		/* can't sleep here, we have oxu->lock... */
+		qh = qh_make(oxu, urb, GFP_ATOMIC);
+		*ptr = qh;
+	}
+	if (likely(qh != NULL)) {
+		struct ehci_qtd	*qtd;
+
+		if (unlikely(list_empty(qtd_list)))
+			qtd = NULL;
+		else
+			qtd = list_entry(qtd_list->next, struct ehci_qtd,
+					qtd_list);
+
+		/* control qh may need patching ... */
+		if (unlikely(epnum == 0)) {
+
+			/* usb_reset_device() briefly reverts to address 0 */
+			if (usb_pipedevice(urb->pipe) == 0)
+				qh->hw_info1 &= ~QH_ADDR_MASK;
+		}
+
+		/* just one way to queue requests: swap with the dummy qtd.
+		 * only hc or qh_refresh() ever modify the overlay.
+		 */
+		if (likely(qtd != NULL)) {
+			struct ehci_qtd	*dummy;
+			dma_addr_t dma;
+			__le32 token;
+
+			/* to avoid racing the HC, use the dummy td instead of
+			 * the first td of our list (becomes new dummy).  both
+			 * tds stay deactivated until we're done, when the
+			 * HC is allowed to fetch the old dummy (4.10.2).
+			 */
+			token = qtd->hw_token;
+			qtd->hw_token = HALT_BIT;
+			wmb();
+			dummy = qh->dummy;
+
+			dma = dummy->qtd_dma;
+			*dummy = *qtd;
+			dummy->qtd_dma = dma;
+
+			list_del(&qtd->qtd_list);
+			list_add(&dummy->qtd_list, qtd_list);
+			list_splice(qtd_list, qh->qtd_list.prev);
+
+			ehci_qtd_init(qtd, qtd->qtd_dma);
+			qh->dummy = qtd;
+
+			/* hc must see the new dummy at list end */
+			dma = qtd->qtd_dma;
+			qtd = list_entry(qh->qtd_list.prev,
+					struct ehci_qtd, qtd_list);
+			qtd->hw_next = QTD_NEXT(dma);
+
+			/* let the hc process these next qtds */
+			dummy->hw_token = (token & ~(0x80));
+			wmb();
+			dummy->hw_token = token;
+
+			urb->hcpriv = qh_get(qh);
+		}
+	}
+	return qh;
+}
+
+static int submit_async(struct oxu_hcd	*oxu, struct urb *urb,
+			struct list_head *qtd_list, gfp_t mem_flags)
+{
+	struct ehci_qtd	*qtd;
+	int epnum;
+	unsigned long flags;
+	struct ehci_qh *qh = NULL;
+	int rc = 0;
+
+	qtd = list_entry(qtd_list->next, struct ehci_qtd, qtd_list);
+	epnum = urb->ep->desc.bEndpointAddress;
+
+#ifdef OXU_URB_TRACE
+	oxu_dbg(oxu, "%s %s urb %p ep%d%s len %d, qtd %p [qh %p]\n",
+		__func__, urb->dev->devpath, urb,
+		epnum & 0x0f, (epnum & USB_DIR_IN) ? "in" : "out",
+		urb->transfer_buffer_length,
+		qtd, urb->ep->hcpriv);
+#endif
+
+	spin_lock_irqsave(&oxu->lock, flags);
+	if (unlikely(!test_bit(HCD_FLAG_HW_ACCESSIBLE,
+			       &oxu_to_hcd(oxu)->flags))) {
+		rc = -ESHUTDOWN;
+		goto done;
+	}
+
+	qh = qh_append_tds(oxu, urb, qtd_list, epnum, &urb->ep->hcpriv);
+	if (unlikely(qh == NULL)) {
+		rc = -ENOMEM;
+		goto done;
+	}
+
+	/* Control/bulk operations through TTs don't need scheduling,
+	 * the HC and TT handle it when the TT has a buffer ready.
+	 */
+	if (likely(qh->qh_state == QH_STATE_IDLE))
+		qh_link_async(oxu, qh_get(qh));
+done:
+	spin_unlock_irqrestore(&oxu->lock, flags);
+	if (unlikely(qh == NULL))
+		qtd_list_free(oxu, urb, qtd_list);
+	return rc;
+}
+
+/* The async qh for the qtds being reclaimed are now unlinked from the HC */
+
+static void end_unlink_async(struct oxu_hcd *oxu)
+{
+	struct ehci_qh *qh = oxu->reclaim;
+	struct ehci_qh *next;
+
+	timer_action_done(oxu, TIMER_IAA_WATCHDOG);
+
+	qh->qh_state = QH_STATE_IDLE;
+	qh->qh_next.qh = NULL;
+	qh_put(qh);			/* refcount from reclaim */
+
+	/* other unlink(s) may be pending (in QH_STATE_UNLINK_WAIT) */
+	next = qh->reclaim;
+	oxu->reclaim = next;
+	oxu->reclaim_ready = 0;
+	qh->reclaim = NULL;
+
+	qh_completions(oxu, qh);
+
+	if (!list_empty(&qh->qtd_list)
+			&& HC_IS_RUNNING(oxu_to_hcd(oxu)->state))
+		qh_link_async(oxu, qh);
+	else {
+		qh_put(qh);		/* refcount from async list */
+
+		/* it's not free to turn the async schedule on/off; leave it
+		 * active but idle for a while once it empties.
+		 */
+		if (HC_IS_RUNNING(oxu_to_hcd(oxu)->state)
+				&& oxu->async->qh_next.qh == NULL)
+			timer_action(oxu, TIMER_ASYNC_OFF);
+	}
+
+	if (next) {
+		oxu->reclaim = NULL;
+		start_unlink_async(oxu, next);
+	}
+}
+
+/* makes sure the async qh will become idle */
+/* caller must own oxu->lock */
+
+static void start_unlink_async(struct oxu_hcd *oxu, struct ehci_qh *qh)
+{
+	int cmd = readl(&oxu->regs->command);
+	struct ehci_qh *prev;
+
+#ifdef DEBUG
+	assert_spin_locked(&oxu->lock);
+	if (oxu->reclaim || (qh->qh_state != QH_STATE_LINKED
+				&& qh->qh_state != QH_STATE_UNLINK_WAIT))
+		BUG();
+#endif
+
+	/* stop async schedule right now? */
+	if (unlikely(qh == oxu->async)) {
+		/* can't get here without STS_ASS set */
+		if (oxu_to_hcd(oxu)->state != HC_STATE_HALT
+				&& !oxu->reclaim) {
+			/* ... and CMD_IAAD clear */
+			writel(cmd & ~CMD_ASE, &oxu->regs->command);
+			wmb();
+			/* handshake later, if we need to */
+			timer_action_done(oxu, TIMER_ASYNC_OFF);
+		}
+		return;
+	}
+
+	qh->qh_state = QH_STATE_UNLINK;
+	oxu->reclaim = qh = qh_get(qh);
+
+	prev = oxu->async;
+	while (prev->qh_next.qh != qh)
+		prev = prev->qh_next.qh;
+
+	prev->hw_next = qh->hw_next;
+	prev->qh_next = qh->qh_next;
+	wmb();
+
+	if (unlikely(oxu_to_hcd(oxu)->state == HC_STATE_HALT)) {
+		/* if (unlikely(qh->reclaim != 0))
+		 *	this will recurse, probably not much
+		 */
+		end_unlink_async(oxu);
+		return;
+	}
+
+	oxu->reclaim_ready = 0;
+	cmd |= CMD_IAAD;
+	writel(cmd, &oxu->regs->command);
+	(void) readl(&oxu->regs->command);
+	timer_action(oxu, TIMER_IAA_WATCHDOG);
+}
+
+static void scan_async(struct oxu_hcd *oxu)
+{
+	struct ehci_qh *qh;
+	enum ehci_timer_action action = TIMER_IO_WATCHDOG;
+
+	if (!++(oxu->stamp))
+		oxu->stamp++;
+	timer_action_done(oxu, TIMER_ASYNC_SHRINK);
+rescan:
+	qh = oxu->async->qh_next.qh;
+	if (likely(qh != NULL)) {
+		do {
+			/* clean any finished work for this qh */
+			if (!list_empty(&qh->qtd_list)
+					&& qh->stamp != oxu->stamp) {
+				int temp;
+
+				/* unlinks could happen here; completion
+				 * reporting drops the lock.  rescan using
+				 * the latest schedule, but don't rescan
+				 * qhs we already finished (no looping).
+				 */
+				qh = qh_get(qh);
+				qh->stamp = oxu->stamp;
+				temp = qh_completions(oxu, qh);
+				qh_put(qh);
+				if (temp != 0)
+					goto rescan;
+			}
+
+			/* unlink idle entries, reducing HC PCI usage as well
+			 * as HCD schedule-scanning costs.  delay for any qh
+			 * we just scanned, there's a not-unusual case that it
+			 * doesn't stay idle for long.
+			 * (plus, avoids some kind of re-activation race.)
+			 */
+			if (list_empty(&qh->qtd_list)) {
+				if (qh->stamp == oxu->stamp)
+					action = TIMER_ASYNC_SHRINK;
+				else if (!oxu->reclaim
+					    && qh->qh_state == QH_STATE_LINKED)
+					start_unlink_async(oxu, qh);
+			}
+
+			qh = qh->qh_next.qh;
+		} while (qh);
+	}
+	if (action == TIMER_ASYNC_SHRINK)
+		timer_action(oxu, TIMER_ASYNC_SHRINK);
+}
+
+/*
+ * periodic_next_shadow - return "next" pointer on shadow list
+ * @periodic: host pointer to qh/itd/sitd
+ * @tag: hardware tag for type of this record
+ */
+static union ehci_shadow *periodic_next_shadow(union ehci_shadow *periodic,
+						__le32 tag)
+{
+	switch (tag) {
+	default:
+	case Q_TYPE_QH:
+		return &periodic->qh->qh_next;
+	}
+}
+
+/* caller must hold oxu->lock */
+static void periodic_unlink(struct oxu_hcd *oxu, unsigned frame, void *ptr)
+{
+	union ehci_shadow *prev_p = &oxu->pshadow[frame];
+	__le32 *hw_p = &oxu->periodic[frame];
+	union ehci_shadow here = *prev_p;
+
+	/* find predecessor of "ptr"; hw and shadow lists are in sync */
+	while (here.ptr && here.ptr != ptr) {
+		prev_p = periodic_next_shadow(prev_p, Q_NEXT_TYPE(*hw_p));
+		hw_p = here.hw_next;
+		here = *prev_p;
+	}
+	/* an interrupt entry (at list end) could have been shared */
+	if (!here.ptr)
+		return;
+
+	/* update shadow and hardware lists ... the old "next" pointers
+	 * from ptr may still be in use, the caller updates them.
+	 */
+	*prev_p = *periodic_next_shadow(&here, Q_NEXT_TYPE(*hw_p));
+	*hw_p = *here.hw_next;
+}
+
+/* how many of the uframe's 125 usecs are allocated? */
+static unsigned short periodic_usecs(struct oxu_hcd *oxu,
+					unsigned frame, unsigned uframe)
+{
+	__le32 *hw_p = &oxu->periodic[frame];
+	union ehci_shadow *q = &oxu->pshadow[frame];
+	unsigned usecs = 0;
+
+	while (q->ptr) {
+		switch (Q_NEXT_TYPE(*hw_p)) {
+		case Q_TYPE_QH:
+		default:
+			/* is it in the S-mask? */
+			if (q->qh->hw_info2 & cpu_to_le32(1 << uframe))
+				usecs += q->qh->usecs;
+			/* ... or C-mask? */
+			if (q->qh->hw_info2 & cpu_to_le32(1 << (8 + uframe)))
+				usecs += q->qh->c_usecs;
+			hw_p = &q->qh->hw_next;
+			q = &q->qh->qh_next;
+			break;
+		}
+	}
+#ifdef DEBUG
+	if (usecs > 100)
+		oxu_err(oxu, "uframe %d sched overrun: %d usecs\n",
+						frame * 8 + uframe, usecs);
+#endif
+	return usecs;
+}
+
+static int enable_periodic(struct oxu_hcd *oxu)
+{
+	u32 cmd;
+	int status;
+
+	/* did clearing PSE did take effect yet?
+	 * takes effect only at frame boundaries...
+	 */
+	status = handshake(oxu, &oxu->regs->status, STS_PSS, 0, 9 * 125);
+	if (status != 0) {
+		oxu_to_hcd(oxu)->state = HC_STATE_HALT;
+		return status;
+	}
+
+	cmd = readl(&oxu->regs->command) | CMD_PSE;
+	writel(cmd, &oxu->regs->command);
+	/* posted write ... PSS happens later */
+	oxu_to_hcd(oxu)->state = HC_STATE_RUNNING;
+
+	/* make sure ehci_work scans these */
+	oxu->next_uframe = readl(&oxu->regs->frame_index)
+		% (oxu->periodic_size << 3);
+	return 0;
+}
+
+static int disable_periodic(struct oxu_hcd *oxu)
+{
+	u32 cmd;
+	int status;
+
+	/* did setting PSE not take effect yet?
+	 * takes effect only at frame boundaries...
+	 */
+	status = handshake(oxu, &oxu->regs->status, STS_PSS, STS_PSS, 9 * 125);
+	if (status != 0) {
+		oxu_to_hcd(oxu)->state = HC_STATE_HALT;
+		return status;
+	}
+
+	cmd = readl(&oxu->regs->command) & ~CMD_PSE;
+	writel(cmd, &oxu->regs->command);
+	/* posted write ... */
+
+	oxu->next_uframe = -1;
+	return 0;
+}
+
+/* periodic schedule slots have iso tds (normal or split) first, then a
+ * sparse tree for active interrupt transfers.
+ *
+ * this just links in a qh; caller guarantees uframe masks are set right.
+ * no FSTN support (yet; oxu 0.96+)
+ */
+static int qh_link_periodic(struct oxu_hcd *oxu, struct ehci_qh *qh)
+{
+	unsigned i;
+	unsigned period = qh->period;
+
+	dev_dbg(&qh->dev->dev,
+		"link qh%d-%04x/%p start %d [%d/%d us]\n",
+		period, le32_to_cpup(&qh->hw_info2) & (QH_CMASK | QH_SMASK),
+		qh, qh->start, qh->usecs, qh->c_usecs);
+
+	/* high bandwidth, or otherwise every microframe */
+	if (period == 0)
+		period = 1;
+
+	for (i = qh->start; i < oxu->periodic_size; i += period) {
+		union ehci_shadow	*prev = &oxu->pshadow[i];
+		__le32			*hw_p = &oxu->periodic[i];
+		union ehci_shadow	here = *prev;
+		__le32			type = 0;
+
+		/* skip the iso nodes at list head */
+		while (here.ptr) {
+			type = Q_NEXT_TYPE(*hw_p);
+			if (type == Q_TYPE_QH)
+				break;
+			prev = periodic_next_shadow(prev, type);
+			hw_p = &here.qh->hw_next;
+			here = *prev;
+		}
+
+		/* sorting each branch by period (slow-->fast)
+		 * enables sharing interior tree nodes
+		 */
+		while (here.ptr && qh != here.qh) {
+			if (qh->period > here.qh->period)
+				break;
+			prev = &here.qh->qh_next;
+			hw_p = &here.qh->hw_next;
+			here = *prev;
+		}
+		/* link in this qh, unless some earlier pass did that */
+		if (qh != here.qh) {
+			qh->qh_next = here;
+			if (here.qh)
+				qh->hw_next = *hw_p;
+			wmb();
+			prev->qh = qh;
+			*hw_p = QH_NEXT(qh->qh_dma);
+		}
+	}
+	qh->qh_state = QH_STATE_LINKED;
+	qh_get(qh);
+
+	/* update per-qh bandwidth for usbfs */
+	oxu_to_hcd(oxu)->self.bandwidth_allocated += qh->period
+		? ((qh->usecs + qh->c_usecs) / qh->period)
+		: (qh->usecs * 8);
+
+	/* maybe enable periodic schedule processing */
+	if (!oxu->periodic_sched++)
+		return enable_periodic(oxu);
+
+	return 0;
+}
+
+static void qh_unlink_periodic(struct oxu_hcd *oxu, struct ehci_qh *qh)
+{
+	unsigned i;
+	unsigned period;
+
+	/* FIXME:
+	 *   IF this isn't high speed
+	 *   and this qh is active in the current uframe
+	 *   (and overlay token SplitXstate is false?)
+	 * THEN
+	 *   qh->hw_info1 |= __constant_cpu_to_le32(1 << 7 "ignore");
+	 */
+
+	/* high bandwidth, or otherwise part of every microframe */
+	period = qh->period;
+	if (period == 0)
+		period = 1;
+
+	for (i = qh->start; i < oxu->periodic_size; i += period)
+		periodic_unlink(oxu, i, qh);
+
+	/* update per-qh bandwidth for usbfs */
+	oxu_to_hcd(oxu)->self.bandwidth_allocated -= qh->period
+		? ((qh->usecs + qh->c_usecs) / qh->period)
+		: (qh->usecs * 8);
+
+	dev_dbg(&qh->dev->dev,
+		"unlink qh%d-%04x/%p start %d [%d/%d us]\n",
+		qh->period,
+		le32_to_cpup(&qh->hw_info2) & (QH_CMASK | QH_SMASK),
+		qh, qh->start, qh->usecs, qh->c_usecs);
+
+	/* qh->qh_next still "live" to HC */
+	qh->qh_state = QH_STATE_UNLINK;
+	qh->qh_next.ptr = NULL;
+	qh_put(qh);
+
+	/* maybe turn off periodic schedule */
+	oxu->periodic_sched--;
+	if (!oxu->periodic_sched)
+		(void) disable_periodic(oxu);
+}
+
+static void intr_deschedule(struct oxu_hcd *oxu, struct ehci_qh *qh)
+{
+	unsigned wait;
+
+	qh_unlink_periodic(oxu, qh);
+
+	/* simple/paranoid:  always delay, expecting the HC needs to read
+	 * qh->hw_next or finish a writeback after SPLIT/CSPLIT ... and
+	 * expect khubd to clean up after any CSPLITs we won't issue.
+	 * active high speed queues may need bigger delays...
+	 */
+	if (list_empty(&qh->qtd_list)
+		|| (__constant_cpu_to_le32(QH_CMASK) & qh->hw_info2) != 0)
+		wait = 2;
+	else
+		wait = 55;	/* worst case: 3 * 1024 */
+
+	udelay(wait);
+	qh->qh_state = QH_STATE_IDLE;
+	qh->hw_next = EHCI_LIST_END;
+	wmb();
+}
+
+static int check_period(struct oxu_hcd *oxu,
+			unsigned frame, unsigned uframe,
+			unsigned period, unsigned usecs)
+{
+	int claimed;
+
+	/* complete split running into next frame?
+	 * given FSTN support, we could sometimes check...
+	 */
+	if (uframe >= 8)
+		return 0;
+
+	/*
+	 * 80% periodic == 100 usec/uframe available
+	 * convert "usecs we need" to "max already claimed"
+	 */
+	usecs = 100 - usecs;
+
+	/* we "know" 2 and 4 uframe intervals were rejected; so
+	 * for period 0, check _every_ microframe in the schedule.
+	 */
+	if (unlikely(period == 0)) {
+		do {
+			for (uframe = 0; uframe < 7; uframe++) {
+				claimed = periodic_usecs(oxu, frame, uframe);
+				if (claimed > usecs)
+					return 0;
+			}
+		} while ((frame += 1) < oxu->periodic_size);
+
+	/* just check the specified uframe, at that period */
+	} else {
+		do {
+			claimed = periodic_usecs(oxu, frame, uframe);
+			if (claimed > usecs)
+				return 0;
+		} while ((frame += period) < oxu->periodic_size);
+	}
+
+	return 1;
+}
+
+static int check_intr_schedule(struct oxu_hcd	*oxu,
+				unsigned frame, unsigned uframe,
+				const struct ehci_qh *qh, __le32 *c_maskp)
+{
+	int retval = -ENOSPC;
+
+	if (qh->c_usecs && uframe >= 6)		/* FSTN territory? */
+		goto done;
+
+	if (!check_period(oxu, frame, uframe, qh->period, qh->usecs))
+		goto done;
+	if (!qh->c_usecs) {
+		retval = 0;
+		*c_maskp = 0;
+		goto done;
+	}
+
+done:
+	return retval;
+}
+
+/* "first fit" scheduling policy used the first time through,
+ * or when the previous schedule slot can't be re-used.
+ */
+static int qh_schedule(struct oxu_hcd *oxu, struct ehci_qh *qh)
+{
+	int		status;
+	unsigned	uframe;
+	__le32		c_mask;
+	unsigned	frame;		/* 0..(qh->period - 1), or NO_FRAME */
+
+	qh_refresh(oxu, qh);
+	qh->hw_next = EHCI_LIST_END;
+	frame = qh->start;
+
+	/* reuse the previous schedule slots, if we can */
+	if (frame < qh->period) {
+		uframe = ffs(le32_to_cpup(&qh->hw_info2) & QH_SMASK);
+		status = check_intr_schedule(oxu, frame, --uframe,
+				qh, &c_mask);
+	} else {
+		uframe = 0;
+		c_mask = 0;
+		status = -ENOSPC;
+	}
+
+	/* else scan the schedule to find a group of slots such that all
+	 * uframes have enough periodic bandwidth available.
+	 */
+	if (status) {
+		/* "normal" case, uframing flexible except with splits */
+		if (qh->period) {
+			frame = qh->period - 1;
+			do {
+				for (uframe = 0; uframe < 8; uframe++) {
+					status = check_intr_schedule(oxu,
+							frame, uframe, qh,
+							&c_mask);
+					if (status == 0)
+						break;
+				}
+			} while (status && frame--);
+
+		/* qh->period == 0 means every uframe */
+		} else {
+			frame = 0;
+			status = check_intr_schedule(oxu, 0, 0, qh, &c_mask);
+		}
+		if (status)
+			goto done;
+		qh->start = frame;
+
+		/* reset S-frame and (maybe) C-frame masks */
+		qh->hw_info2 &= __constant_cpu_to_le32(~(QH_CMASK | QH_SMASK));
+		qh->hw_info2 |= qh->period
+			? cpu_to_le32(1 << uframe)
+			: __constant_cpu_to_le32(QH_SMASK);
+		qh->hw_info2 |= c_mask;
+	} else
+		oxu_dbg(oxu, "reused qh %p schedule\n", qh);
+
+	/* stuff into the periodic schedule */
+	status = qh_link_periodic(oxu, qh);
+done:
+	return status;
+}
+
+static int intr_submit(struct oxu_hcd *oxu, struct urb *urb,
+			struct list_head *qtd_list, gfp_t mem_flags)
+{
+	unsigned epnum;
+	unsigned long flags;
+	struct ehci_qh *qh;
+	int status = 0;
+	struct list_head	empty;
+
+	/* get endpoint and transfer/schedule data */
+	epnum = urb->ep->desc.bEndpointAddress;
+
+	spin_lock_irqsave(&oxu->lock, flags);
+
+	if (unlikely(!test_bit(HCD_FLAG_HW_ACCESSIBLE,
+			       &oxu_to_hcd(oxu)->flags))) {
+		status = -ESHUTDOWN;
+		goto done;
+	}
+
+	/* get qh and force any scheduling errors */
+	INIT_LIST_HEAD(&empty);
+	qh = qh_append_tds(oxu, urb, &empty, epnum, &urb->ep->hcpriv);
+	if (qh == NULL) {
+		status = -ENOMEM;
+		goto done;
+	}
+	if (qh->qh_state == QH_STATE_IDLE) {
+		status = qh_schedule(oxu, qh);
+		if (status != 0)
+			goto done;
+	}
+
+	/* then queue the urb's tds to the qh */
+	qh = qh_append_tds(oxu, urb, qtd_list, epnum, &urb->ep->hcpriv);
+	BUG_ON(qh == NULL);
+
+	/* ... update usbfs periodic stats */
+	oxu_to_hcd(oxu)->self.bandwidth_int_reqs++;
+
+done:
+	spin_unlock_irqrestore(&oxu->lock, flags);
+	if (status)
+		qtd_list_free(oxu, urb, qtd_list);
+
+	return status;
+}
+
+static inline int itd_submit(struct oxu_hcd *oxu, struct urb *urb,
+						gfp_t mem_flags)
+{
+	oxu_dbg(oxu, "iso support is missing!\n");
+	return -ENOSYS;
+}
+
+static inline int sitd_submit(struct oxu_hcd *oxu, struct urb *urb,
+						gfp_t mem_flags)
+{
+	oxu_dbg(oxu, "split iso support is missing!\n");
+	return -ENOSYS;
+}
+
+static void scan_periodic(struct oxu_hcd *oxu)
+{
+	unsigned frame, clock, now_uframe, mod;
+	unsigned modified;
+
+	mod = oxu->periodic_size << 3;
+
+	/*
+	 * When running, scan from last scan point up to "now"
+	 * else clean up by scanning everything that's left.
+	 * Touches as few pages as possible:  cache-friendly.
+	 */
+	now_uframe = oxu->next_uframe;
+	if (HC_IS_RUNNING(oxu_to_hcd(oxu)->state))
+		clock = readl(&oxu->regs->frame_index);
+	else
+		clock = now_uframe + mod - 1;
+	clock %= mod;
+
+	for (;;) {
+		union ehci_shadow	q, *q_p;
+		__le32			type, *hw_p;
+		unsigned		uframes;
+
+		/* don't scan past the live uframe */
+		frame = now_uframe >> 3;
+		if (frame == (clock >> 3))
+			uframes = now_uframe & 0x07;
+		else {
+			/* safe to scan the whole frame at once */
+			now_uframe |= 0x07;
+			uframes = 8;
+		}
+
+restart:
+		/* scan each element in frame's queue for completions */
+		q_p = &oxu->pshadow[frame];
+		hw_p = &oxu->periodic[frame];
+		q.ptr = q_p->ptr;
+		type = Q_NEXT_TYPE(*hw_p);
+		modified = 0;
+
+		while (q.ptr != NULL) {
+			union ehci_shadow temp;
+			int live;
+
+			live = HC_IS_RUNNING(oxu_to_hcd(oxu)->state);
+			switch (type) {
+			case Q_TYPE_QH:
+				/* handle any completions */
+				temp.qh = qh_get(q.qh);
+				type = Q_NEXT_TYPE(q.qh->hw_next);
+				q = q.qh->qh_next;
+				modified = qh_completions(oxu, temp.qh);
+				if (unlikely(list_empty(&temp.qh->qtd_list)))
+					intr_deschedule(oxu, temp.qh);
+				qh_put(temp.qh);
+				break;
+			default:
+				dbg("corrupt type %d frame %d shadow %p",
+					type, frame, q.ptr);
+				q.ptr = NULL;
+			}
+
+			/* assume completion callbacks modify the queue */
+			if (unlikely(modified))
+				goto restart;
+		}
+
+		/* Stop when we catch up to the HC */
+
+		/* FIXME:  this assumes we won't get lapped when
+		 * latencies climb; that should be rare, but...
+		 * detect it, and just go all the way around.
+		 * FLR might help detect this case, so long as latencies
+		 * don't exceed periodic_size msec (default 1.024 sec).
+		 */
+
+		/* FIXME: likewise assumes HC doesn't halt mid-scan */
+
+		if (now_uframe == clock) {
+			unsigned	now;
+
+			if (!HC_IS_RUNNING(oxu_to_hcd(oxu)->state))
+				break;
+			oxu->next_uframe = now_uframe;
+			now = readl(&oxu->regs->frame_index) % mod;
+			if (now_uframe == now)
+				break;
+
+			/* rescan the rest of this frame, then ... */
+			clock = now;
+		} else {
+			now_uframe++;
+			now_uframe %= mod;
+		}
+	}
+}
+
+/* On some systems, leaving remote wakeup enabled prevents system shutdown.
+ * The firmware seems to think that powering off is a wakeup event!
+ * This routine turns off remote wakeup and everything else, on all ports.
+ */
+static void ehci_turn_off_all_ports(struct oxu_hcd *oxu)
+{
+	int port = HCS_N_PORTS(oxu->hcs_params);
+
+	while (port--)
+		writel(PORT_RWC_BITS, &oxu->regs->port_status[port]);
+}
+
+static void ehci_port_power(struct oxu_hcd *oxu, int is_on)
+{
+	unsigned port;
+
+	if (!HCS_PPC(oxu->hcs_params))
+		return;
+
+	oxu_dbg(oxu, "...power%s ports...\n", is_on ? "up" : "down");
+	for (port = HCS_N_PORTS(oxu->hcs_params); port > 0; )
+		(void) oxu_hub_control(oxu_to_hcd(oxu),
+				is_on ? SetPortFeature : ClearPortFeature,
+				USB_PORT_FEAT_POWER,
+				port--, NULL, 0);
+	msleep(20);
+}
+
+/* Called from some interrupts, timers, and so on.
+ * It calls driver completion functions, after dropping oxu->lock.
+ */
+static void ehci_work(struct oxu_hcd *oxu)
+{
+	timer_action_done(oxu, TIMER_IO_WATCHDOG);
+	if (oxu->reclaim_ready)
+		end_unlink_async(oxu);
+
+	/* another CPU may drop oxu->lock during a schedule scan while
+	 * it reports urb completions.  this flag guards against bogus
+	 * attempts at re-entrant schedule scanning.
+	 */
+	if (oxu->scanning)
+		return;
+	oxu->scanning = 1;
+	scan_async(oxu);
+	if (oxu->next_uframe != -1)
+		scan_periodic(oxu);
+	oxu->scanning = 0;
+
+	/* the IO watchdog guards against hardware or driver bugs that
+	 * misplace IRQs, and should let us run completely without IRQs.
+	 * such lossage has been observed on both VT6202 and VT8235.
+	 */
+	if (HC_IS_RUNNING(oxu_to_hcd(oxu)->state) &&
+			(oxu->async->qh_next.ptr != NULL ||
+			 oxu->periodic_sched != 0))
+		timer_action(oxu, TIMER_IO_WATCHDOG);
+}
+
+static void unlink_async(struct oxu_hcd *oxu, struct ehci_qh *qh)
+{
+	/* if we need to use IAA and it's busy, defer */
+	if (qh->qh_state == QH_STATE_LINKED
+			&& oxu->reclaim
+			&& HC_IS_RUNNING(oxu_to_hcd(oxu)->state)) {
+		struct ehci_qh		*last;
+
+		for (last = oxu->reclaim;
+				last->reclaim;
+				last = last->reclaim)
+			continue;
+		qh->qh_state = QH_STATE_UNLINK_WAIT;
+		last->reclaim = qh;
+
+	/* bypass IAA if the hc can't care */
+	} else if (!HC_IS_RUNNING(oxu_to_hcd(oxu)->state) && oxu->reclaim)
+		end_unlink_async(oxu);
+
+	/* something else might have unlinked the qh by now */
+	if (qh->qh_state == QH_STATE_LINKED)
+		start_unlink_async(oxu, qh);
+}
+
+/*
+ * USB host controller methods
+ */
+
+static irqreturn_t oxu210_hcd_irq(struct usb_hcd *hcd)
+{
+	struct oxu_hcd *oxu = hcd_to_oxu(hcd);
+	u32 status, pcd_status = 0;
+	int bh;
+
+	spin_lock(&oxu->lock);
+
+	status = readl(&oxu->regs->status);
+
+	/* e.g. cardbus physical eject */
+	if (status == ~(u32) 0) {
+		oxu_dbg(oxu, "device removed\n");
+		goto dead;
+	}
+
+	status &= INTR_MASK;
+	if (!status) {			/* irq sharing? */
+		spin_unlock(&oxu->lock);
+		return IRQ_NONE;
+	}
+
+	/* clear (just) interrupts */
+	writel(status, &oxu->regs->status);
+	readl(&oxu->regs->command);	/* unblock posted write */
+	bh = 0;
+
+#ifdef OXU_VERBOSE_DEBUG
+	/* unrequested/ignored: Frame List Rollover */
+	dbg_status(oxu, "irq", status);
+#endif
+
+	/* INT, ERR, and IAA interrupt rates can be throttled */
+
+	/* normal [4.15.1.2] or error [4.15.1.1] completion */
+	if (likely((status & (STS_INT|STS_ERR)) != 0))
+		bh = 1;
+
+	/* complete the unlinking of some qh [4.15.2.3] */
+	if (status & STS_IAA) {
+		oxu->reclaim_ready = 1;
+		bh = 1;
+	}
+
+	/* remote wakeup [4.3.1] */
+	if (status & STS_PCD) {
+		unsigned i = HCS_N_PORTS(oxu->hcs_params);
+		pcd_status = status;
+
+		/* resume root hub? */
+		if (!(readl(&oxu->regs->command) & CMD_RUN))
+			usb_hcd_resume_root_hub(hcd);
+
+		while (i--) {
+			int pstatus = readl(&oxu->regs->port_status[i]);
+
+			if (pstatus & PORT_OWNER)
+				continue;
+			if (!(pstatus & PORT_RESUME)
+					|| oxu->reset_done[i] != 0)
+				continue;
+
+			/* start 20 msec resume signaling from this port,
+			 * and make khubd collect PORT_STAT_C_SUSPEND to
+			 * stop that signaling.
+			 */
+			oxu->reset_done[i] = jiffies + msecs_to_jiffies(20);
+			oxu_dbg(oxu, "port %d remote wakeup\n", i + 1);
+			mod_timer(&hcd->rh_timer, oxu->reset_done[i]);
+		}
+	}
+
+	/* PCI errors [4.15.2.4] */
+	if (unlikely((status & STS_FATAL) != 0)) {
+		/* bogus "fatal" IRQs appear on some chips... why?  */
+		status = readl(&oxu->regs->status);
+		dbg_cmd(oxu, "fatal", readl(&oxu->regs->command));
+		dbg_status(oxu, "fatal", status);
+		if (status & STS_HALT) {
+			oxu_err(oxu, "fatal error\n");
+dead:
+			ehci_reset(oxu);
+			writel(0, &oxu->regs->configured_flag);
+			/* generic layer kills/unlinks all urbs, then
+			 * uses oxu_stop to clean up the rest
+			 */
+			bh = 1;
+		}
+	}
+
+	if (bh)
+		ehci_work(oxu);
+	spin_unlock(&oxu->lock);
+	if (pcd_status & STS_PCD)
+		usb_hcd_poll_rh_status(hcd);
+	return IRQ_HANDLED;
+}
+
+static irqreturn_t oxu_irq(struct usb_hcd *hcd)
+{
+	struct oxu_hcd *oxu = hcd_to_oxu(hcd);
+	int ret = IRQ_HANDLED;
+
+	u32 status = oxu_readl(hcd->regs, OXU_CHIPIRQSTATUS);
+	u32 enable = oxu_readl(hcd->regs, OXU_CHIPIRQEN_SET);
+
+	/* Disable all interrupt */
+	oxu_writel(hcd->regs, OXU_CHIPIRQEN_CLR, enable);
+
+	if ((oxu->is_otg && (status & OXU_USBOTGI)) ||
+		(!oxu->is_otg && (status & OXU_USBSPHI)))
+		oxu210_hcd_irq(hcd);
+	else
+		ret = IRQ_NONE;
+
+	/* Enable all interrupt back */
+	oxu_writel(hcd->regs, OXU_CHIPIRQEN_SET, enable);
+
+	return ret;
+}
+
+static void oxu_watchdog(unsigned long param)
+{
+	struct oxu_hcd	*oxu = (struct oxu_hcd *) param;
+	unsigned long flags;
+
+	spin_lock_irqsave(&oxu->lock, flags);
+
+	/* lost IAA irqs wedge things badly; seen with a vt8235 */
+	if (oxu->reclaim) {
+		u32 status = readl(&oxu->regs->status);
+		if (status & STS_IAA) {
+			oxu_vdbg(oxu, "lost IAA\n");
+			writel(STS_IAA, &oxu->regs->status);
+			oxu->reclaim_ready = 1;
+		}
+	}
+
+	/* stop async processing after it's idled a bit */
+	if (test_bit(TIMER_ASYNC_OFF, &oxu->actions))
+		start_unlink_async(oxu, oxu->async);
+
+	/* oxu could run by timer, without IRQs ... */
+	ehci_work(oxu);
+
+	spin_unlock_irqrestore(&oxu->lock, flags);
+}
+
+/* One-time init, only for memory state.
+ */
+static int oxu_hcd_init(struct usb_hcd *hcd)
+{
+	struct oxu_hcd *oxu = hcd_to_oxu(hcd);
+	u32 temp;
+	int retval;
+	u32 hcc_params;
+
+	spin_lock_init(&oxu->lock);
+
+	init_timer(&oxu->watchdog);
+	oxu->watchdog.function = oxu_watchdog;
+	oxu->watchdog.data = (unsigned long) oxu;
+
+	/*
+	 * hw default: 1K periodic list heads, one per frame.
+	 * periodic_size can shrink by USBCMD update if hcc_params allows.
+	 */
+	oxu->periodic_size = DEFAULT_I_TDPS;
+	retval = ehci_mem_init(oxu, GFP_KERNEL);
+	if (retval < 0)
+		return retval;
+
+	/* controllers may cache some of the periodic schedule ... */
+	hcc_params = readl(&oxu->caps->hcc_params);
+	if (HCC_ISOC_CACHE(hcc_params))		/* full frame cache */
+		oxu->i_thresh = 8;
+	else					/* N microframes cached */
+		oxu->i_thresh = 2 + HCC_ISOC_THRES(hcc_params);
+
+	oxu->reclaim = NULL;
+	oxu->reclaim_ready = 0;
+	oxu->next_uframe = -1;
+
+	/*
+	 * dedicate a qh for the async ring head, since we couldn't unlink
+	 * a 'real' qh without stopping the async schedule [4.8].  use it
+	 * as the 'reclamation list head' too.
+	 * its dummy is used in hw_alt_next of many tds, to prevent the qh
+	 * from automatically advancing to the next td after short reads.
+	 */
+	oxu->async->qh_next.qh = NULL;
+	oxu->async->hw_next = QH_NEXT(oxu->async->qh_dma);
+	oxu->async->hw_info1 = cpu_to_le32(QH_HEAD);
+	oxu->async->hw_token = cpu_to_le32(QTD_STS_HALT);
+	oxu->async->hw_qtd_next = EHCI_LIST_END;
+	oxu->async->qh_state = QH_STATE_LINKED;
+	oxu->async->hw_alt_next = QTD_NEXT(oxu->async->dummy->qtd_dma);
+
+	/* clear interrupt enables, set irq latency */
+	if (log2_irq_thresh < 0 || log2_irq_thresh > 6)
+		log2_irq_thresh = 0;
+	temp = 1 << (16 + log2_irq_thresh);
+	if (HCC_CANPARK(hcc_params)) {
+		/* HW default park == 3, on hardware that supports it (like
+		 * NVidia and ALI silicon), maximizes throughput on the async
+		 * schedule by avoiding QH fetches between transfers.
+		 *
+		 * With fast usb storage devices and NForce2, "park" seems to
+		 * make problems:  throughput reduction (!), data errors...
+		 */
+		if (park) {
+			park = min(park, (unsigned) 3);
+			temp |= CMD_PARK;
+			temp |= park << 8;
+		}
+		oxu_dbg(oxu, "park %d\n", park);
+	}
+	if (HCC_PGM_FRAMELISTLEN(hcc_params)) {
+		/* periodic schedule size can be smaller than default */
+		temp &= ~(3 << 2);
+		temp |= (EHCI_TUNE_FLS << 2);
+	}
+	oxu->command = temp;
+
+	return 0;
+}
+
+/* Called during probe() after chip reset completes.
+ */
+static int oxu_reset(struct usb_hcd *hcd)
+{
+	struct oxu_hcd *oxu = hcd_to_oxu(hcd);
+	int ret;
+
+	spin_lock_init(&oxu->mem_lock);
+	INIT_LIST_HEAD(&oxu->urb_list);
+	oxu->urb_len = 0;
+
+	/* FIMXE */
+	hcd->self.controller->dma_mask = 0UL;
+
+	if (oxu->is_otg) {
+		oxu->caps = hcd->regs + OXU_OTG_CAP_OFFSET;
+		oxu->regs = hcd->regs + OXU_OTG_CAP_OFFSET + \
+			HC_LENGTH(readl(&oxu->caps->hc_capbase));
+
+		oxu->mem = hcd->regs + OXU_SPH_MEM;
+	} else {
+		oxu->caps = hcd->regs + OXU_SPH_CAP_OFFSET;
+		oxu->regs = hcd->regs + OXU_SPH_CAP_OFFSET + \
+			HC_LENGTH(readl(&oxu->caps->hc_capbase));
+
+		oxu->mem = hcd->regs + OXU_OTG_MEM;
+	}
+
+	oxu->hcs_params = readl(&oxu->caps->hcs_params);
+	oxu->sbrn = 0x20;
+
+	ret = oxu_hcd_init(hcd);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+static int oxu_run(struct usb_hcd *hcd)
+{
+	struct oxu_hcd *oxu = hcd_to_oxu(hcd);
+	int retval;
+	u32 temp, hcc_params;
+
+	hcd->uses_new_polling = 1;
+	hcd->poll_rh = 0;
+
+	/* EHCI spec section 4.1 */
+	retval = ehci_reset(oxu);
+	if (retval != 0) {
+		ehci_mem_cleanup(oxu);
+		return retval;
+	}
+	writel(oxu->periodic_dma, &oxu->regs->frame_list);
+	writel((u32) oxu->async->qh_dma, &oxu->regs->async_next);
+
+	/* hcc_params controls whether oxu->regs->segment must (!!!)
+	 * be used; it constrains QH/ITD/SITD and QTD locations.
+	 * pci_pool consistent memory always uses segment zero.
+	 * streaming mappings for I/O buffers, like pci_map_single(),
+	 * can return segments above 4GB, if the device allows.
+	 *
+	 * NOTE:  the dma mask is visible through dma_supported(), so
+	 * drivers can pass this info along ... like NETIF_F_HIGHDMA,
+	 * Scsi_Host.highmem_io, and so forth.  It's readonly to all
+	 * host side drivers though.
+	 */
+	hcc_params = readl(&oxu->caps->hcc_params);
+	if (HCC_64BIT_ADDR(hcc_params))
+		writel(0, &oxu->regs->segment);
+
+	oxu->command &= ~(CMD_LRESET | CMD_IAAD | CMD_PSE |
+				CMD_ASE | CMD_RESET);
+	oxu->command |= CMD_RUN;
+	writel(oxu->command, &oxu->regs->command);
+	dbg_cmd(oxu, "init", oxu->command);
+
+	/*
+	 * Start, enabling full USB 2.0 functionality ... usb 1.1 devices
+	 * are explicitly handed to companion controller(s), so no TT is
+	 * involved with the root hub.  (Except where one is integrated,
+	 * and there's no companion controller unless maybe for USB OTG.)
+	 */
+	hcd->state = HC_STATE_RUNNING;
+	writel(FLAG_CF, &oxu->regs->configured_flag);
+	readl(&oxu->regs->command);	/* unblock posted writes */
+
+	temp = HC_VERSION(readl(&oxu->caps->hc_capbase));
+	oxu_info(oxu, "USB %x.%x started, quasi-EHCI %x.%02x, driver %s%s\n",
+		((oxu->sbrn & 0xf0)>>4), (oxu->sbrn & 0x0f),
+		temp >> 8, temp & 0xff, DRIVER_VERSION,
+		ignore_oc ? ", overcurrent ignored" : "");
+
+	writel(INTR_MASK, &oxu->regs->intr_enable); /* Turn On Interrupts */
+
+	return 0;
+}
+
+static void oxu_stop(struct usb_hcd *hcd)
+{
+	struct oxu_hcd *oxu = hcd_to_oxu(hcd);
+
+	/* Turn off port power on all root hub ports. */
+	ehci_port_power(oxu, 0);
+
+	/* no more interrupts ... */
+	del_timer_sync(&oxu->watchdog);
+
+	spin_lock_irq(&oxu->lock);
+	if (HC_IS_RUNNING(hcd->state))
+		ehci_quiesce(oxu);
+
+	ehci_reset(oxu);
+	writel(0, &oxu->regs->intr_enable);
+	spin_unlock_irq(&oxu->lock);
+
+	/* let companion controllers work when we aren't */
+	writel(0, &oxu->regs->configured_flag);
+
+	/* root hub is shut down separately (first, when possible) */
+	spin_lock_irq(&oxu->lock);
+	if (oxu->async)
+		ehci_work(oxu);
+	spin_unlock_irq(&oxu->lock);
+	ehci_mem_cleanup(oxu);
+
+	dbg_status(oxu, "oxu_stop completed", readl(&oxu->regs->status));
+}
+
+/* Kick in for silicon on any bus (not just pci, etc).
+ * This forcibly disables dma and IRQs, helping kexec and other cases
+ * where the next system software may expect clean state.
+ */
+static void oxu_shutdown(struct usb_hcd *hcd)
+{
+	struct oxu_hcd *oxu = hcd_to_oxu(hcd);
+
+	(void) ehci_halt(oxu);
+	ehci_turn_off_all_ports(oxu);
+
+	/* make BIOS/etc use companion controller during reboot */
+	writel(0, &oxu->regs->configured_flag);
+
+	/* unblock posted writes */
+	readl(&oxu->regs->configured_flag);
+}
+
+/* Non-error returns are a promise to giveback() the urb later
+ * we drop ownership so next owner (or urb unlink) can get it
+ *
+ * urb + dev is in hcd.self.controller.urb_list
+ * we're queueing TDs onto software and hardware lists
+ *
+ * hcd-specific init for hcpriv hasn't been done yet
+ *
+ * NOTE:  control, bulk, and interrupt share the same code to append TDs
+ * to a (possibly active) QH, and the same QH scanning code.
+ */
+static int __oxu_urb_enqueue(struct usb_hcd *hcd, struct urb *urb,
+				gfp_t mem_flags)
+{
+	struct oxu_hcd *oxu = hcd_to_oxu(hcd);
+	struct list_head qtd_list;
+
+	INIT_LIST_HEAD(&qtd_list);
+
+	switch (usb_pipetype(urb->pipe)) {
+	case PIPE_CONTROL:
+	case PIPE_BULK:
+	default:
+		if (!qh_urb_transaction(oxu, urb, &qtd_list, mem_flags))
+			return -ENOMEM;
+		return submit_async(oxu, urb, &qtd_list, mem_flags);
+
+	case PIPE_INTERRUPT:
+		if (!qh_urb_transaction(oxu, urb, &qtd_list, mem_flags))
+			return -ENOMEM;
+		return intr_submit(oxu, urb, &qtd_list, mem_flags);
+
+	case PIPE_ISOCHRONOUS:
+		if (urb->dev->speed == USB_SPEED_HIGH)
+			return itd_submit(oxu, urb, mem_flags);
+		else
+			return sitd_submit(oxu, urb, mem_flags);
+	}
+}
+
+/* This function is responsible for breaking URBs with big data size
+ * into smaller size and processing small urbs in sequence.
+ */
+static int oxu_urb_enqueue(struct usb_hcd *hcd, struct urb *urb,
+				gfp_t mem_flags)
+{
+	struct oxu_hcd *oxu = hcd_to_oxu(hcd);
+	int num, rem;
+	int transfer_buffer_length;
+	void *transfer_buffer;
+	struct urb *murb;
+	int i, ret;
+
+	/* If not bulk pipe just enqueue the URB */
+	if (!usb_pipebulk(urb->pipe))
+		return __oxu_urb_enqueue(hcd, urb, mem_flags);
+
+	/* Otherwise we should verify the USB transfer buffer size! */
+	transfer_buffer = urb->transfer_buffer;
+	transfer_buffer_length = urb->transfer_buffer_length;
+
+	num = urb->transfer_buffer_length / 4096;
+	rem = urb->transfer_buffer_length % 4096;
+	if (rem != 0)
+		num++;
+
+	/* If URB is smaller than 4096 bytes just enqueue it! */
+	if (num == 1)
+		return __oxu_urb_enqueue(hcd, urb, mem_flags);
+
+	/* Ok, we have more job to do! :) */
+
+	for (i = 0; i < num - 1; i++) {
+		/* Get free micro URB poll till a free urb is recieved */
+
+		do {
+			murb = (struct urb *) oxu_murb_alloc(oxu);
+			if (!murb)
+				schedule();
+		} while (!murb);
+
+		/* Coping the urb */
+		memcpy(murb, urb, sizeof(struct urb));
+
+		murb->transfer_buffer_length = 4096;
+		murb->transfer_buffer = transfer_buffer + i * 4096;
+
+		/* Null pointer for the encodes that this is a micro urb */
+		murb->complete = NULL;
+
+		((struct oxu_murb *) murb)->main = urb;
+		((struct oxu_murb *) murb)->last = 0;
+
+		/* This loop is to guarantee urb to be processed when there's
+		 * not enough resources at a particular time by retrying.
+		 */
+		do {
+			ret  = __oxu_urb_enqueue(hcd, murb, mem_flags);
+			if (ret)
+				schedule();
+		} while (ret);
+	}
+
+	/* Last urb requires special handling  */
+
+	/* Get free micro URB poll till a free urb is recieved */
+	do {
+		murb = (struct urb *) oxu_murb_alloc(oxu);
+		if (!murb)
+			schedule();
+	} while (!murb);
+
+	/* Coping the urb */
+	memcpy(murb, urb, sizeof(struct urb));
+
+	murb->transfer_buffer_length = rem > 0 ? rem : 4096;
+	murb->transfer_buffer = transfer_buffer + (num - 1) * 4096;
+
+	/* Null pointer for the encodes that this is a micro urb */
+	murb->complete = NULL;
+
+	((struct oxu_murb *) murb)->main = urb;
+	((struct oxu_murb *) murb)->last = 1;
+
+	do {
+		ret = __oxu_urb_enqueue(hcd, murb, mem_flags);
+		if (ret)
+			schedule();
+	} while (ret);
+
+	return ret;
+}
+
+/* Remove from hardware lists.
+ * Completions normally happen asynchronously
+ */
+static int oxu_urb_dequeue(struct usb_hcd *hcd, struct urb *urb, int status)
+{
+	struct oxu_hcd *oxu = hcd_to_oxu(hcd);
+	struct ehci_qh *qh;
+	unsigned long flags;
+
+	spin_lock_irqsave(&oxu->lock, flags);
+	switch (usb_pipetype(urb->pipe)) {
+	case PIPE_CONTROL:
+	case PIPE_BULK:
+	default:
+		qh = (struct ehci_qh *) urb->hcpriv;
+		if (!qh)
+			break;
+		unlink_async(oxu, qh);
+		break;
+
+	case PIPE_INTERRUPT:
+		qh = (struct ehci_qh *) urb->hcpriv;
+		if (!qh)
+			break;
+		switch (qh->qh_state) {
+		case QH_STATE_LINKED:
+			intr_deschedule(oxu, qh);
+			/* FALL THROUGH */
+		case QH_STATE_IDLE:
+			qh_completions(oxu, qh);
+			break;
+		default:
+			oxu_dbg(oxu, "bogus qh %p state %d\n",
+					qh, qh->qh_state);
+			goto done;
+		}
+
+		/* reschedule QH iff another request is queued */
+		if (!list_empty(&qh->qtd_list)
+				&& HC_IS_RUNNING(hcd->state)) {
+			int status;
+
+			status = qh_schedule(oxu, qh);
+			spin_unlock_irqrestore(&oxu->lock, flags);
+
+			if (status != 0) {
+				/* shouldn't happen often, but ...
+				 * FIXME kill those tds' urbs
+				 */
+				err("can't reschedule qh %p, err %d",
+					qh, status);
+			}
+			return status;
+		}
+		break;
+	}
+done:
+	spin_unlock_irqrestore(&oxu->lock, flags);
+	return 0;
+}
+
+/* Bulk qh holds the data toggle */
+static void oxu_endpoint_disable(struct usb_hcd *hcd,
+					struct usb_host_endpoint *ep)
+{
+	struct oxu_hcd *oxu = hcd_to_oxu(hcd);
+	unsigned long		flags;
+	struct ehci_qh		*qh, *tmp;
+
+	/* ASSERT:  any requests/urbs are being unlinked */
+	/* ASSERT:  nobody can be submitting urbs for this any more */
+
+rescan:
+	spin_lock_irqsave(&oxu->lock, flags);
+	qh = ep->hcpriv;
+	if (!qh)
+		goto done;
+
+	/* endpoints can be iso streams.  for now, we don't
+	 * accelerate iso completions ... so spin a while.
+	 */
+	if (qh->hw_info1 == 0) {
+		oxu_vdbg(oxu, "iso delay\n");
+		goto idle_timeout;
+	}
+
+	if (!HC_IS_RUNNING(hcd->state))
+		qh->qh_state = QH_STATE_IDLE;
+	switch (qh->qh_state) {
+	case QH_STATE_LINKED:
+		for (tmp = oxu->async->qh_next.qh;
+				tmp && tmp != qh;
+				tmp = tmp->qh_next.qh)
+			continue;
+		/* periodic qh self-unlinks on empty */
+		if (!tmp)
+			goto nogood;
+		unlink_async(oxu, qh);
+		/* FALL THROUGH */
+	case QH_STATE_UNLINK:		/* wait for hw to finish? */
+idle_timeout:
+		spin_unlock_irqrestore(&oxu->lock, flags);
+		schedule_timeout_uninterruptible(1);
+		goto rescan;
+	case QH_STATE_IDLE:		/* fully unlinked */
+		if (list_empty(&qh->qtd_list)) {
+			qh_put(qh);
+			break;
+		}
+		/* else FALL THROUGH */
+	default:
+nogood:
+		/* caller was supposed to have unlinked any requests;
+		 * that's not our job.  just leak this memory.
+		 */
+		oxu_err(oxu, "qh %p (#%02x) state %d%s\n",
+			qh, ep->desc.bEndpointAddress, qh->qh_state,
+			list_empty(&qh->qtd_list) ? "" : "(has tds)");
+		break;
+	}
+	ep->hcpriv = NULL;
+done:
+	spin_unlock_irqrestore(&oxu->lock, flags);
+	return;
+}
+
+static int oxu_get_frame(struct usb_hcd *hcd)
+{
+	struct oxu_hcd *oxu = hcd_to_oxu(hcd);
+
+	return (readl(&oxu->regs->frame_index) >> 3) %
+		oxu->periodic_size;
+}
+
+/* Build "status change" packet (one or two bytes) from HC registers */
+static int oxu_hub_status_data(struct usb_hcd *hcd, char *buf)
+{
+	struct oxu_hcd *oxu = hcd_to_oxu(hcd);
+	u32 temp, mask, status = 0;
+	int ports, i, retval = 1;
+	unsigned long flags;
+
+	/* if !USB_SUSPEND, root hub timers won't get shut down ... */
+	if (!HC_IS_RUNNING(hcd->state))
+		return 0;
+
+	/* init status to no-changes */
+	buf[0] = 0;
+	ports = HCS_N_PORTS(oxu->hcs_params);
+	if (ports > 7) {
+		buf[1] = 0;
+		retval++;
+	}
+
+	/* Some boards (mostly VIA?) report bogus overcurrent indications,
+	 * causing massive log spam unless we completely ignore them.  It
+	 * may be relevant that VIA VT8235 controlers, where PORT_POWER is
+	 * always set, seem to clear PORT_OCC and PORT_CSC when writing to
+	 * PORT_POWER; that's surprising, but maybe within-spec.
+	 */
+	if (!ignore_oc)
+		mask = PORT_CSC | PORT_PEC | PORT_OCC;
+	else
+		mask = PORT_CSC | PORT_PEC;
+
+	/* no hub change reports (bit 0) for now (power, ...) */
+
+	/* port N changes (bit N)? */
+	spin_lock_irqsave(&oxu->lock, flags);
+	for (i = 0; i < ports; i++) {
+		temp = readl(&oxu->regs->port_status[i]);
+
+		/*
+		 * Return status information even for ports with OWNER set.
+		 * Otherwise khubd wouldn't see the disconnect event when a
+		 * high-speed device is switched over to the companion
+		 * controller by the user.
+		 */
+
+		if (!(temp & PORT_CONNECT))
+			oxu->reset_done[i] = 0;
+		if ((temp & mask) != 0 || ((temp & PORT_RESUME) != 0 &&
+				time_after_eq(jiffies, oxu->reset_done[i]))) {
+			if (i < 7)
+				buf[0] |= 1 << (i + 1);
+			else
+				buf[1] |= 1 << (i - 7);
+			status = STS_PCD;
+		}
+	}
+	/* FIXME autosuspend idle root hubs */
+	spin_unlock_irqrestore(&oxu->lock, flags);
+	return status ? retval : 0;
+}
+
+/* Returns the speed of a device attached to a port on the root hub. */
+static inline unsigned int oxu_port_speed(struct oxu_hcd *oxu,
+						unsigned int portsc)
+{
+	switch ((portsc >> 26) & 3) {
+	case 0:
+		return 0;
+	case 1:
+		return 1 << USB_PORT_FEAT_LOWSPEED;
+	case 2:
+	default:
+		return 1 << USB_PORT_FEAT_HIGHSPEED;
+	}
+}
+
+#define	PORT_WAKE_BITS	(PORT_WKOC_E|PORT_WKDISC_E|PORT_WKCONN_E)
+static int oxu_hub_control(struct usb_hcd *hcd, u16 typeReq,
+				u16 wValue, u16 wIndex, char *buf, u16 wLength)
+{
+	struct oxu_hcd *oxu = hcd_to_oxu(hcd);
+	int ports = HCS_N_PORTS(oxu->hcs_params);
+	u32 __iomem *status_reg = &oxu->regs->port_status[wIndex - 1];
+	u32 temp, status;
+	unsigned long	flags;
+	int retval = 0;
+	unsigned selector;
+
+	/*
+	 * FIXME:  support SetPortFeatures USB_PORT_FEAT_INDICATOR.
+	 * HCS_INDICATOR may say we can change LEDs to off/amber/green.
+	 * (track current state ourselves) ... blink for diagnostics,
+	 * power, "this is the one", etc.  EHCI spec supports this.
+	 */
+
+	spin_lock_irqsave(&oxu->lock, flags);
+	switch (typeReq) {
+	case ClearHubFeature:
+		switch (wValue) {
+		case C_HUB_LOCAL_POWER:
+		case C_HUB_OVER_CURRENT:
+			/* no hub-wide feature/status flags */
+			break;
+		default:
+			goto error;
+		}
+		break;
+	case ClearPortFeature:
+		if (!wIndex || wIndex > ports)
+			goto error;
+		wIndex--;
+		temp = readl(status_reg);
+
+		/*
+		 * Even if OWNER is set, so the port is owned by the
+		 * companion controller, khubd needs to be able to clear
+		 * the port-change status bits (especially
+		 * USB_PORT_FEAT_C_CONNECTION).
+		 */
+
+		switch (wValue) {
+		case USB_PORT_FEAT_ENABLE:
+			writel(temp & ~PORT_PE, status_reg);
+			break;
+		case USB_PORT_FEAT_C_ENABLE:
+			writel((temp & ~PORT_RWC_BITS) | PORT_PEC, status_reg);
+			break;
+		case USB_PORT_FEAT_SUSPEND:
+			if (temp & PORT_RESET)
+				goto error;
+			if (temp & PORT_SUSPEND) {
+				if ((temp & PORT_PE) == 0)
+					goto error;
+				/* resume signaling for 20 msec */
+				temp &= ~(PORT_RWC_BITS | PORT_WAKE_BITS);
+				writel(temp | PORT_RESUME, status_reg);
+				oxu->reset_done[wIndex] = jiffies
+						+ msecs_to_jiffies(20);
+			}
+			break;
+		case USB_PORT_FEAT_C_SUSPEND:
+			/* we auto-clear this feature */
+			break;
+		case USB_PORT_FEAT_POWER:
+			if (HCS_PPC(oxu->hcs_params))
+				writel(temp & ~(PORT_RWC_BITS | PORT_POWER),
+					  status_reg);
+			break;
+		case USB_PORT_FEAT_C_CONNECTION:
+			writel((temp & ~PORT_RWC_BITS) | PORT_CSC, status_reg);
+			break;
+		case USB_PORT_FEAT_C_OVER_CURRENT:
+			writel((temp & ~PORT_RWC_BITS) | PORT_OCC, status_reg);
+			break;
+		case USB_PORT_FEAT_C_RESET:
+			/* GetPortStatus clears reset */
+			break;
+		default:
+			goto error;
+		}
+		readl(&oxu->regs->command);	/* unblock posted write */
+		break;
+	case GetHubDescriptor:
+		ehci_hub_descriptor(oxu, (struct usb_hub_descriptor *)
+			buf);
+		break;
+	case GetHubStatus:
+		/* no hub-wide feature/status flags */
+		memset(buf, 0, 4);
+		break;
+	case GetPortStatus:
+		if (!wIndex || wIndex > ports)
+			goto error;
+		wIndex--;
+		status = 0;
+		temp = readl(status_reg);
+
+		/* wPortChange bits */
+		if (temp & PORT_CSC)
+			status |= 1 << USB_PORT_FEAT_C_CONNECTION;
+		if (temp & PORT_PEC)
+			status |= 1 << USB_PORT_FEAT_C_ENABLE;
+		if ((temp & PORT_OCC) && !ignore_oc)
+			status |= 1 << USB_PORT_FEAT_C_OVER_CURRENT;
+
+		/* whoever resumes must GetPortStatus to complete it!! */
+		if (temp & PORT_RESUME) {
+
+			/* Remote Wakeup received? */
+			if (!oxu->reset_done[wIndex]) {
+				/* resume signaling for 20 msec */
+				oxu->reset_done[wIndex] = jiffies
+						+ msecs_to_jiffies(20);
+				/* check the port again */
+				mod_timer(&oxu_to_hcd(oxu)->rh_timer,
+						oxu->reset_done[wIndex]);
+			}
+
+			/* resume completed? */
+			else if (time_after_eq(jiffies,
+					oxu->reset_done[wIndex])) {
+				status |= 1 << USB_PORT_FEAT_C_SUSPEND;
+				oxu->reset_done[wIndex] = 0;
+
+				/* stop resume signaling */
+				temp = readl(status_reg);
+				writel(temp & ~(PORT_RWC_BITS | PORT_RESUME),
+					status_reg);
+				retval = handshake(oxu, status_reg,
+					   PORT_RESUME, 0, 2000 /* 2msec */);
+				if (retval != 0) {
+					oxu_err(oxu,
+						"port %d resume error %d\n",
+						wIndex + 1, retval);
+					goto error;
+				}
+				temp &= ~(PORT_SUSPEND|PORT_RESUME|(3<<10));
+			}
+		}
+
+		/* whoever resets must GetPortStatus to complete it!! */
+		if ((temp & PORT_RESET)
+				&& time_after_eq(jiffies,
+					oxu->reset_done[wIndex])) {
+			status |= 1 << USB_PORT_FEAT_C_RESET;
+			oxu->reset_done[wIndex] = 0;
+
+			/* force reset to complete */
+			writel(temp & ~(PORT_RWC_BITS | PORT_RESET),
+					status_reg);
+			/* REVISIT:  some hardware needs 550+ usec to clear
+			 * this bit; seems too long to spin routinely...
+			 */
+			retval = handshake(oxu, status_reg,
+					PORT_RESET, 0, 750);
+			if (retval != 0) {
+				oxu_err(oxu, "port %d reset error %d\n",
+					wIndex + 1, retval);
+				goto error;
+			}
+
+			/* see what we found out */
+			temp = check_reset_complete(oxu, wIndex, status_reg,
+					readl(status_reg));
+		}
+
+		/* transfer dedicated ports to the companion hc */
+		if ((temp & PORT_CONNECT) &&
+				test_bit(wIndex, &oxu->companion_ports)) {
+			temp &= ~PORT_RWC_BITS;
+			temp |= PORT_OWNER;
+			writel(temp, status_reg);
+			oxu_dbg(oxu, "port %d --> companion\n", wIndex + 1);
+			temp = readl(status_reg);
+		}
+
+		/*
+		 * Even if OWNER is set, there's no harm letting khubd
+		 * see the wPortStatus values (they should all be 0 except
+		 * for PORT_POWER anyway).
+		 */
+
+		if (temp & PORT_CONNECT) {
+			status |= 1 << USB_PORT_FEAT_CONNECTION;
+			/* status may be from integrated TT */
+			status |= oxu_port_speed(oxu, temp);
+		}
+		if (temp & PORT_PE)
+			status |= 1 << USB_PORT_FEAT_ENABLE;
+		if (temp & (PORT_SUSPEND|PORT_RESUME))
+			status |= 1 << USB_PORT_FEAT_SUSPEND;
+		if (temp & PORT_OC)
+			status |= 1 << USB_PORT_FEAT_OVER_CURRENT;
+		if (temp & PORT_RESET)
+			status |= 1 << USB_PORT_FEAT_RESET;
+		if (temp & PORT_POWER)
+			status |= 1 << USB_PORT_FEAT_POWER;
+
+#ifndef	OXU_VERBOSE_DEBUG
+	if (status & ~0xffff)	/* only if wPortChange is interesting */
+#endif
+		dbg_port(oxu, "GetStatus", wIndex + 1, temp);
+		put_unaligned(cpu_to_le32(status), (__le32 *) buf);
+		break;
+	case SetHubFeature:
+		switch (wValue) {
+		case C_HUB_LOCAL_POWER:
+		case C_HUB_OVER_CURRENT:
+			/* no hub-wide feature/status flags */
+			break;
+		default:
+			goto error;
+		}
+		break;
+	case SetPortFeature:
+		selector = wIndex >> 8;
+		wIndex &= 0xff;
+		if (!wIndex || wIndex > ports)
+			goto error;
+		wIndex--;
+		temp = readl(status_reg);
+		if (temp & PORT_OWNER)
+			break;
+
+		temp &= ~PORT_RWC_BITS;
+		switch (wValue) {
+		case USB_PORT_FEAT_SUSPEND:
+			if ((temp & PORT_PE) == 0
+					|| (temp & PORT_RESET) != 0)
+				goto error;
+			if (device_may_wakeup(&hcd->self.root_hub->dev))
+				temp |= PORT_WAKE_BITS;
+			writel(temp | PORT_SUSPEND, status_reg);
+			break;
+		case USB_PORT_FEAT_POWER:
+			if (HCS_PPC(oxu->hcs_params))
+				writel(temp | PORT_POWER, status_reg);
+			break;
+		case USB_PORT_FEAT_RESET:
+			if (temp & PORT_RESUME)
+				goto error;
+			/* line status bits may report this as low speed,
+			 * which can be fine if this root hub has a
+			 * transaction translator built in.
+			 */
+			oxu_vdbg(oxu, "port %d reset\n", wIndex + 1);
+			temp |= PORT_RESET;
+			temp &= ~PORT_PE;
+
+			/*
+			 * caller must wait, then call GetPortStatus
+			 * usb 2.0 spec says 50 ms resets on root
+			 */
+			oxu->reset_done[wIndex] = jiffies
+					+ msecs_to_jiffies(50);
+			writel(temp, status_reg);
+			break;
+
+		/* For downstream facing ports (these):  one hub port is put
+		 * into test mode according to USB2 11.24.2.13, then the hub
+		 * must be reset (which for root hub now means rmmod+modprobe,
+		 * or else system reboot).  See EHCI 2.3.9 and 4.14 for info
+		 * about the EHCI-specific stuff.
+		 */
+		case USB_PORT_FEAT_TEST:
+			if (!selector || selector > 5)
+				goto error;
+			ehci_quiesce(oxu);
+			ehci_halt(oxu);
+			temp |= selector << 16;
+			writel(temp, status_reg);
+			break;
+
+		default:
+			goto error;
+		}
+		readl(&oxu->regs->command);	/* unblock posted writes */
+		break;
+
+	default:
+error:
+		/* "stall" on error */
+		retval = -EPIPE;
+	}
+	spin_unlock_irqrestore(&oxu->lock, flags);
+	return retval;
+}
+
+#ifdef CONFIG_PM
+
+static int oxu_bus_suspend(struct usb_hcd *hcd)
+{
+	struct oxu_hcd *oxu = hcd_to_oxu(hcd);
+	int port;
+	int mask;
+
+	oxu_dbg(oxu, "suspend root hub\n");
+
+	if (time_before(jiffies, oxu->next_statechange))
+		msleep(5);
+
+	port = HCS_N_PORTS(oxu->hcs_params);
+	spin_lock_irq(&oxu->lock);
+
+	/* stop schedules, clean any completed work */
+	if (HC_IS_RUNNING(hcd->state)) {
+		ehci_quiesce(oxu);
+		hcd->state = HC_STATE_QUIESCING;
+	}
+	oxu->command = readl(&oxu->regs->command);
+	if (oxu->reclaim)
+		oxu->reclaim_ready = 1;
+	ehci_work(oxu);
+
+	/* Unlike other USB host controller types, EHCI doesn't have
+	 * any notion of "global" or bus-wide suspend.  The driver has
+	 * to manually suspend all the active unsuspended ports, and
+	 * then manually resume them in the bus_resume() routine.
+	 */
+	oxu->bus_suspended = 0;
+	while (port--) {
+		u32 __iomem *reg = &oxu->regs->port_status[port];
+		u32 t1 = readl(reg) & ~PORT_RWC_BITS;
+		u32 t2 = t1;
+
+		/* keep track of which ports we suspend */
+		if ((t1 & PORT_PE) && !(t1 & PORT_OWNER) &&
+				!(t1 & PORT_SUSPEND)) {
+			t2 |= PORT_SUSPEND;
+			set_bit(port, &oxu->bus_suspended);
+		}
+
+		/* enable remote wakeup on all ports */
+		if (device_may_wakeup(&hcd->self.root_hub->dev))
+			t2 |= PORT_WKOC_E|PORT_WKDISC_E|PORT_WKCONN_E;
+		else
+			t2 &= ~(PORT_WKOC_E|PORT_WKDISC_E|PORT_WKCONN_E);
+
+		if (t1 != t2) {
+			oxu_vdbg(oxu, "port %d, %08x -> %08x\n",
+				port + 1, t1, t2);
+			writel(t2, reg);
+		}
+	}
+
+	/* turn off now-idle HC */
+	del_timer_sync(&oxu->watchdog);
+	ehci_halt(oxu);
+	hcd->state = HC_STATE_SUSPENDED;
+
+	/* allow remote wakeup */
+	mask = INTR_MASK;
+	if (!device_may_wakeup(&hcd->self.root_hub->dev))
+		mask &= ~STS_PCD;
+	writel(mask, &oxu->regs->intr_enable);
+	readl(&oxu->regs->intr_enable);
+
+	oxu->next_statechange = jiffies + msecs_to_jiffies(10);
+	spin_unlock_irq(&oxu->lock);
+	return 0;
+}
+
+/* Caller has locked the root hub, and should reset/reinit on error */
+static int oxu_bus_resume(struct usb_hcd *hcd)
+{
+	struct oxu_hcd *oxu = hcd_to_oxu(hcd);
+	u32 temp;
+	int i;
+
+	if (time_before(jiffies, oxu->next_statechange))
+		msleep(5);
+	spin_lock_irq(&oxu->lock);
+
+	/* Ideally and we've got a real resume here, and no port's power
+	 * was lost.  (For PCI, that means Vaux was maintained.)  But we
+	 * could instead be restoring a swsusp snapshot -- so that BIOS was
+	 * the last user of the controller, not reset/pm hardware keeping
+	 * state we gave to it.
+	 */
+	temp = readl(&oxu->regs->intr_enable);
+	oxu_dbg(oxu, "resume root hub%s\n", temp ? "" : " after power loss");
+
+	/* at least some APM implementations will try to deliver
+	 * IRQs right away, so delay them until we're ready.
+	 */
+	writel(0, &oxu->regs->intr_enable);
+
+	/* re-init operational registers */
+	writel(0, &oxu->regs->segment);
+	writel(oxu->periodic_dma, &oxu->regs->frame_list);
+	writel((u32) oxu->async->qh_dma, &oxu->regs->async_next);
+
+	/* restore CMD_RUN, framelist size, and irq threshold */
+	writel(oxu->command, &oxu->regs->command);
+
+	/* Some controller/firmware combinations need a delay during which
+	 * they set up the port statuses.  See Bugzilla #8190. */
+	mdelay(8);
+
+	/* manually resume the ports we suspended during bus_suspend() */
+	i = HCS_N_PORTS(oxu->hcs_params);
+	while (i--) {
+		temp = readl(&oxu->regs->port_status[i]);
+		temp &= ~(PORT_RWC_BITS
+			| PORT_WKOC_E | PORT_WKDISC_E | PORT_WKCONN_E);
+		if (test_bit(i, &oxu->bus_suspended) && (temp & PORT_SUSPEND)) {
+			oxu->reset_done[i] = jiffies + msecs_to_jiffies(20);
+			temp |= PORT_RESUME;
+		}
+		writel(temp, &oxu->regs->port_status[i]);
+	}
+	i = HCS_N_PORTS(oxu->hcs_params);
+	mdelay(20);
+	while (i--) {
+		temp = readl(&oxu->regs->port_status[i]);
+		if (test_bit(i, &oxu->bus_suspended) && (temp & PORT_SUSPEND)) {
+			temp &= ~(PORT_RWC_BITS | PORT_RESUME);
+			writel(temp, &oxu->regs->port_status[i]);
+			oxu_vdbg(oxu, "resumed port %d\n", i + 1);
+		}
+	}
+	(void) readl(&oxu->regs->command);
+
+	/* maybe re-activate the schedule(s) */
+	temp = 0;
+	if (oxu->async->qh_next.qh)
+		temp |= CMD_ASE;
+	if (oxu->periodic_sched)
+		temp |= CMD_PSE;
+	if (temp) {
+		oxu->command |= temp;
+		writel(oxu->command, &oxu->regs->command);
+	}
+
+	oxu->next_statechange = jiffies + msecs_to_jiffies(5);
+	hcd->state = HC_STATE_RUNNING;
+
+	/* Now we can safely re-enable irqs */
+	writel(INTR_MASK, &oxu->regs->intr_enable);
+
+	spin_unlock_irq(&oxu->lock);
+	return 0;
+}
+
+#else
+
+static int oxu_bus_suspend(struct usb_hcd *hcd)
+{
+	return 0;
+}
+
+static int oxu_bus_resume(struct usb_hcd *hcd)
+{
+	return 0;
+}
+
+#endif	/* CONFIG_PM */
+
+static const struct hc_driver oxu_hc_driver = {
+	.description =		"oxu210hp_hcd",
+	.product_desc =		"oxu210hp HCD",
+	.hcd_priv_size =	sizeof(struct oxu_hcd),
+
+	/*
+	 * Generic hardware linkage
+	 */
+	.irq =			oxu_irq,
+	.flags =		HCD_MEMORY | HCD_USB2,
+
+	/*
+	 * Basic lifecycle operations
+	 */
+	.reset =		oxu_reset,
+	.start =		oxu_run,
+	.stop =			oxu_stop,
+	.shutdown =		oxu_shutdown,
+
+	/*
+	 * Managing i/o requests and associated device resources
+	 */
+	.urb_enqueue =		oxu_urb_enqueue,
+	.urb_dequeue =		oxu_urb_dequeue,
+	.endpoint_disable =	oxu_endpoint_disable,
+
+	/*
+	 * Scheduling support
+	 */
+	.get_frame_number =	oxu_get_frame,
+
+	/*
+	 * Root hub support
+	 */
+	.hub_status_data =	oxu_hub_status_data,
+	.hub_control =		oxu_hub_control,
+	.bus_suspend =		oxu_bus_suspend,
+	.bus_resume =		oxu_bus_resume,
+};
+
+/*
+ * Module stuff
+ */
+
+static void oxu_configuration(struct platform_device *pdev, void *base)
+{
+	u32 tmp;
+
+	/* Initialize top level registers.
+	 * First write ever
+	 */
+	oxu_writel(base, OXU_HOSTIFCONFIG, 0x0000037D);
+	oxu_writel(base, OXU_SOFTRESET, OXU_SRESET);
+	oxu_writel(base, OXU_HOSTIFCONFIG, 0x0000037D);
+
+	tmp = oxu_readl(base, OXU_PIOBURSTREADCTRL);
+	oxu_writel(base, OXU_PIOBURSTREADCTRL, tmp | 0x0040);
+
+	oxu_writel(base, OXU_ASO, OXU_SPHPOEN | OXU_OVRCCURPUPDEN |
+					OXU_COMPARATOR | OXU_ASO_OP);
+
+	tmp = oxu_readl(base, OXU_CLKCTRL_SET);
+	oxu_writel(base, OXU_CLKCTRL_SET, tmp | OXU_SYSCLKEN | OXU_USBOTGCLKEN);
+
+	/* Clear all top interrupt enable */
+	oxu_writel(base, OXU_CHIPIRQEN_CLR, 0xff);
+
+	/* Clear all top interrupt status */
+	oxu_writel(base, OXU_CHIPIRQSTATUS, 0xff);
+
+	/* Enable all needed top interrupt except OTG SPH core */
+	oxu_writel(base, OXU_CHIPIRQEN_SET, OXU_USBSPHLPWUI | OXU_USBOTGLPWUI);
+}
+
+static int oxu_verify_id(struct platform_device *pdev, void *base)
+{
+	u32 id;
+	char *bo[] = {
+		"reserved",
+		"128-pin LQFP",
+		"84-pin TFBGA",
+		"reserved",
+	};
+
+	/* Read controller signature register to find a match */
+	id = oxu_readl(base, OXU_DEVICEID);
+	dev_info(&pdev->dev, "device ID %x\n", id);
+	if ((id & OXU_REV_MASK) != (OXU_REV_2100 << OXU_REV_SHIFT))
+		return -1;
+
+	dev_info(&pdev->dev, "found device %x %s (%04x:%04x)\n",
+		id >> OXU_REV_SHIFT,
+		bo[(id & OXU_BO_MASK) >> OXU_BO_SHIFT],
+		(id & OXU_MAJ_REV_MASK) >> OXU_MAJ_REV_SHIFT,
+		(id & OXU_MIN_REV_MASK) >> OXU_MIN_REV_SHIFT);
+
+	return 0;
+}
+
+static const struct hc_driver oxu_hc_driver;
+static struct usb_hcd *oxu_create(struct platform_device *pdev,
+				unsigned long memstart, unsigned long memlen,
+				void *base, int irq, int otg)
+{
+	struct device *dev = &pdev->dev;
+
+	struct usb_hcd *hcd;
+	struct oxu_hcd *oxu;
+	int ret;
+
+	/* Set endian mode and host mode */
+	oxu_writel(base + (otg ? OXU_OTG_CORE_OFFSET : OXU_SPH_CORE_OFFSET),
+				OXU_USBMODE,
+				OXU_CM_HOST_ONLY | OXU_ES_LITTLE | OXU_VBPS);
+
+	hcd = usb_create_hcd(&oxu_hc_driver, dev,
+				otg ? "oxu210hp_otg" : "oxu210hp_sph");
+	if (!hcd)
+		return ERR_PTR(-ENOMEM);
+
+	hcd->rsrc_start = memstart;
+	hcd->rsrc_len = memlen;
+	hcd->regs = base;
+	hcd->irq = irq;
+	hcd->state = HC_STATE_HALT;
+
+	oxu = hcd_to_oxu(hcd);
+	oxu->is_otg = otg;
+
+	ret = usb_add_hcd(hcd, irq, IRQF_SHARED);
+	if (ret < 0)
+		return ERR_PTR(ret);
+
+	return hcd;
+}
+
+static int oxu_init(struct platform_device *pdev,
+				unsigned long memstart, unsigned long memlen,
+				void *base, int irq)
+{
+	struct oxu_info *info = platform_get_drvdata(pdev);
+	struct usb_hcd *hcd;
+	int ret;
+
+	/* First time configuration at start up */
+	oxu_configuration(pdev, base);
+
+	ret = oxu_verify_id(pdev, base);
+	if (ret) {
+		dev_err(&pdev->dev, "no devices found!\n");
+		return -ENODEV;
+	}
+
+	/* Create the OTG controller */
+	hcd = oxu_create(pdev, memstart, memlen, base, irq, 1);
+	if (IS_ERR(hcd)) {
+		dev_err(&pdev->dev, "cannot create OTG controller!\n");
+		ret = PTR_ERR(hcd);
+		goto error_create_otg;
+	}
+	info->hcd[0] = hcd;
+
+	/* Create the SPH host controller */
+	hcd = oxu_create(pdev, memstart, memlen, base, irq, 0);
+	if (IS_ERR(hcd)) {
+		dev_err(&pdev->dev, "cannot create SPH controller!\n");
+		ret = PTR_ERR(hcd);
+		goto error_create_sph;
+	}
+	info->hcd[1] = hcd;
+
+	oxu_writel(base, OXU_CHIPIRQEN_SET,
+		oxu_readl(base, OXU_CHIPIRQEN_SET) | 3);
+
+	return 0;
+
+error_create_sph:
+	usb_remove_hcd(info->hcd[0]);
+	usb_put_hcd(info->hcd[0]);
+
+error_create_otg:
+	return ret;
+}
+
+static int oxu_drv_probe(struct platform_device *pdev)
+{
+	struct resource *res;
+	void *base;
+	unsigned long memstart, memlen;
+	int irq, ret;
+	struct oxu_info *info;
+
+	if (usb_disabled())
+		return -ENODEV;
+
+	/*
+	 * Get the platform resources
+	 */
+	res = platform_get_resource(pdev, IORESOURCE_IRQ, 0);
+	if (!res) {
+		dev_err(&pdev->dev,
+			"no IRQ! Check %s setup!\n", dev_name(&pdev->dev));
+		return -ENODEV;
+	}
+	irq = res->start;
+	dev_dbg(&pdev->dev, "IRQ resource %d\n", irq);
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!res) {
+		dev_err(&pdev->dev, "no registers address! Check %s setup!\n",
+			dev_name(&pdev->dev));
+		return -ENODEV;
+	}
+	memstart = res->start;
+	memlen = res->end - res->start + 1;
+	dev_dbg(&pdev->dev, "MEM resource %lx-%lx\n", memstart, memlen);
+	if (!request_mem_region(memstart, memlen,
+				oxu_hc_driver.description)) {
+		dev_dbg(&pdev->dev, "memory area already in use\n");
+		return -EBUSY;
+	}
+
+	ret = set_irq_type(irq, IRQF_TRIGGER_FALLING);
+	if (ret) {
+		dev_err(&pdev->dev, "error setting irq type\n");
+		ret = -EFAULT;
+		goto error_set_irq_type;
+	}
+
+	base = ioremap(memstart, memlen);
+	if (!base) {
+		dev_dbg(&pdev->dev, "error mapping memory\n");
+		ret = -EFAULT;
+		goto error_ioremap;
+	}
+
+	/* Allocate a driver data struct to hold useful info for both
+	 * SPH & OTG devices
+	 */
+	info = kzalloc(sizeof(struct oxu_info), GFP_KERNEL);
+	if (!info) {
+		dev_dbg(&pdev->dev, "error allocating memory\n");
+		ret = -EFAULT;
+		goto error_alloc;
+	}
+	platform_set_drvdata(pdev, info);
+
+	ret = oxu_init(pdev, memstart, memlen, base, irq);
+	if (ret < 0) {
+		dev_dbg(&pdev->dev, "cannot init USB devices\n");
+		goto error_init;
+	}
+
+	dev_info(&pdev->dev, "devices enabled and running\n");
+	platform_set_drvdata(pdev, info);
+
+	return 0;
+
+error_init:
+	kfree(info);
+	platform_set_drvdata(pdev, NULL);
+
+error_alloc:
+	iounmap(base);
+
+error_set_irq_type:
+error_ioremap:
+	release_mem_region(memstart, memlen);
+
+	dev_err(&pdev->dev, "init %s fail, %d\n", dev_name(&pdev->dev), ret);
+	return ret;
+}
+
+static void oxu_remove(struct platform_device *pdev, struct usb_hcd *hcd)
+{
+	usb_remove_hcd(hcd);
+	usb_put_hcd(hcd);
+}
+
+static int oxu_drv_remove(struct platform_device *pdev)
+{
+	struct oxu_info *info = platform_get_drvdata(pdev);
+	unsigned long memstart = info->hcd[0]->rsrc_start,
+			memlen = info->hcd[0]->rsrc_len;
+	void *base = info->hcd[0]->regs;
+
+	oxu_remove(pdev, info->hcd[0]);
+	oxu_remove(pdev, info->hcd[1]);
+
+	iounmap(base);
+	release_mem_region(memstart, memlen);
+
+	kfree(info);
+	platform_set_drvdata(pdev, NULL);
+
+	return 0;
+}
+
+static void oxu_drv_shutdown(struct platform_device *pdev)
+{
+	oxu_drv_remove(pdev);
+}
+
+#if 0
+/* FIXME: TODO */
+static int oxu_drv_suspend(struct device *dev)
+{
+	struct platform_device *pdev = to_platform_device(dev);
+	struct usb_hcd *hcd = dev_get_drvdata(dev);
+
+	return 0;
+}
+
+static int oxu_drv_resume(struct device *dev)
+{
+	struct platform_device *pdev = to_platform_device(dev);
+	struct usb_hcd *hcd = dev_get_drvdata(dev);
+
+	return 0;
+}
+#else
+#define oxu_drv_suspend	NULL
+#define oxu_drv_resume	NULL
+#endif
+
+static struct platform_driver oxu_driver = {
+	.probe		= oxu_drv_probe,
+	.remove		= oxu_drv_remove,
+	.shutdown	= oxu_drv_shutdown,
+	.suspend	= oxu_drv_suspend,
+	.resume		= oxu_drv_resume,
+	.driver = {
+		.name = "oxu210hp-hcd",
+		.bus = &platform_bus_type
+	}
+};
+
+static int __init oxu_module_init(void)
+{
+	int retval = 0;
+
+	retval = platform_driver_register(&oxu_driver);
+	if (retval < 0)
+		return retval;
+
+	return retval;
+}
+
+static void __exit oxu_module_cleanup(void)
+{
+	platform_driver_unregister(&oxu_driver);
+}
+
+module_init(oxu_module_init);
+module_exit(oxu_module_cleanup);
+
+MODULE_DESCRIPTION("Oxford OXU210HP HCD driver - ver. " DRIVER_VERSION);
+MODULE_AUTHOR("Rodolfo Giometti <giometti@linux.it>");
+MODULE_LICENSE("GPL");
diff --git a/drivers/usb/host/oxu210hp.h b/drivers/usb/host/oxu210hp.h
new file mode 100644
index 000000000000..8910e271cc7d
--- /dev/null
+++ b/drivers/usb/host/oxu210hp.h
@@ -0,0 +1,447 @@
+/*
+ * Host interface registers
+ */
+
+#define OXU_DEVICEID			0x00
+	#define OXU_REV_MASK		0xffff0000
+	#define OXU_REV_SHIFT		16
+	#define OXU_REV_2100		0x2100
+	#define OXU_BO_SHIFT		8
+	#define OXU_BO_MASK		(0x3 << OXU_BO_SHIFT)
+	#define OXU_MAJ_REV_SHIFT	4
+	#define OXU_MAJ_REV_MASK	(0xf << OXU_MAJ_REV_SHIFT)
+	#define OXU_MIN_REV_SHIFT	0
+	#define OXU_MIN_REV_MASK	(0xf << OXU_MIN_REV_SHIFT)
+#define OXU_HOSTIFCONFIG		0x04
+#define OXU_SOFTRESET			0x08
+	#define OXU_SRESET		(1 << 0)
+
+#define OXU_PIOBURSTREADCTRL		0x0C
+
+#define OXU_CHIPIRQSTATUS		0x10
+#define OXU_CHIPIRQEN_SET		0x14
+#define OXU_CHIPIRQEN_CLR		0x18
+	#define OXU_USBSPHLPWUI		0x00000080
+	#define OXU_USBOTGLPWUI		0x00000040
+	#define OXU_USBSPHI		0x00000002
+	#define OXU_USBOTGI		0x00000001
+
+#define OXU_CLKCTRL_SET			0x1C
+	#define OXU_SYSCLKEN		0x00000008
+	#define OXU_USBSPHCLKEN		0x00000002
+	#define OXU_USBOTGCLKEN		0x00000001
+
+#define OXU_ASO				0x68
+	#define OXU_SPHPOEN		0x00000100
+	#define OXU_OVRCCURPUPDEN	0x00000800
+	#define OXU_ASO_OP		(1 << 10)
+	#define OXU_COMPARATOR		0x000004000
+
+#define OXU_USBMODE			0x1A8
+	#define OXU_VBPS		0x00000020
+	#define OXU_ES_LITTLE		0x00000000
+	#define OXU_CM_HOST_ONLY	0x00000003
+
+/*
+ * Proper EHCI structs & defines
+ */
+
+/* Magic numbers that can affect system performance */
+#define EHCI_TUNE_CERR		3	/* 0-3 qtd retries; 0 == don't stop */
+#define EHCI_TUNE_RL_HS		4	/* nak throttle; see 4.9 */
+#define EHCI_TUNE_RL_TT		0
+#define EHCI_TUNE_MULT_HS	1	/* 1-3 transactions/uframe; 4.10.3 */
+#define EHCI_TUNE_MULT_TT	1
+#define EHCI_TUNE_FLS		2	/* (small) 256 frame schedule */
+
+struct oxu_hcd;
+
+/* EHCI register interface, corresponds to EHCI Revision 0.95 specification */
+
+/* Section 2.2 Host Controller Capability Registers */
+struct ehci_caps {
+	/* these fields are specified as 8 and 16 bit registers,
+	 * but some hosts can't perform 8 or 16 bit PCI accesses.
+	 */
+	u32		hc_capbase;
+#define HC_LENGTH(p)		(((p)>>00)&0x00ff)	/* bits 7:0 */
+#define HC_VERSION(p)		(((p)>>16)&0xffff)	/* bits 31:16 */
+	u32		hcs_params;     /* HCSPARAMS - offset 0x4 */
+#define HCS_DEBUG_PORT(p)	(((p)>>20)&0xf)	/* bits 23:20, debug port? */
+#define HCS_INDICATOR(p)	((p)&(1 << 16))	/* true: has port indicators */
+#define HCS_N_CC(p)		(((p)>>12)&0xf)	/* bits 15:12, #companion HCs */
+#define HCS_N_PCC(p)		(((p)>>8)&0xf)	/* bits 11:8, ports per CC */
+#define HCS_PORTROUTED(p)	((p)&(1 << 7))	/* true: port routing */
+#define HCS_PPC(p)		((p)&(1 << 4))	/* true: port power control */
+#define HCS_N_PORTS(p)		(((p)>>0)&0xf)	/* bits 3:0, ports on HC */
+
+	u32		hcc_params;      /* HCCPARAMS - offset 0x8 */
+#define HCC_EXT_CAPS(p)		(((p)>>8)&0xff)	/* for pci extended caps */
+#define HCC_ISOC_CACHE(p)       ((p)&(1 << 7))  /* true: can cache isoc frame */
+#define HCC_ISOC_THRES(p)       (((p)>>4)&0x7)  /* bits 6:4, uframes cached */
+#define HCC_CANPARK(p)		((p)&(1 << 2))  /* true: can park on async qh */
+#define HCC_PGM_FRAMELISTLEN(p) ((p)&(1 << 1))  /* true: periodic_size changes*/
+#define HCC_64BIT_ADDR(p)       ((p)&(1))       /* true: can use 64-bit addr */
+	u8		portroute[8];	 /* nibbles for routing - offset 0xC */
+} __attribute__ ((packed));
+
+
+/* Section 2.3 Host Controller Operational Registers */
+struct ehci_regs {
+	/* USBCMD: offset 0x00 */
+	u32		command;
+/* 23:16 is r/w intr rate, in microframes; default "8" == 1/msec */
+#define CMD_PARK	(1<<11)		/* enable "park" on async qh */
+#define CMD_PARK_CNT(c)	(((c)>>8)&3)	/* how many transfers to park for */
+#define CMD_LRESET	(1<<7)		/* partial reset (no ports, etc) */
+#define CMD_IAAD	(1<<6)		/* "doorbell" interrupt async advance */
+#define CMD_ASE		(1<<5)		/* async schedule enable */
+#define CMD_PSE		(1<<4)		/* periodic schedule enable */
+/* 3:2 is periodic frame list size */
+#define CMD_RESET	(1<<1)		/* reset HC not bus */
+#define CMD_RUN		(1<<0)		/* start/stop HC */
+
+	/* USBSTS: offset 0x04 */
+	u32		status;
+#define STS_ASS		(1<<15)		/* Async Schedule Status */
+#define STS_PSS		(1<<14)		/* Periodic Schedule Status */
+#define STS_RECL	(1<<13)		/* Reclamation */
+#define STS_HALT	(1<<12)		/* Not running (any reason) */
+/* some bits reserved */
+	/* these STS_* flags are also intr_enable bits (USBINTR) */
+#define STS_IAA		(1<<5)		/* Interrupted on async advance */
+#define STS_FATAL	(1<<4)		/* such as some PCI access errors */
+#define STS_FLR		(1<<3)		/* frame list rolled over */
+#define STS_PCD		(1<<2)		/* port change detect */
+#define STS_ERR		(1<<1)		/* "error" completion (overflow, ...) */
+#define STS_INT		(1<<0)		/* "normal" completion (short, ...) */
+
+#define INTR_MASK (STS_IAA | STS_FATAL | STS_PCD | STS_ERR | STS_INT)
+
+	/* USBINTR: offset 0x08 */
+	u32		intr_enable;
+
+	/* FRINDEX: offset 0x0C */
+	u32		frame_index;	/* current microframe number */
+	/* CTRLDSSEGMENT: offset 0x10 */
+	u32		segment;	/* address bits 63:32 if needed */
+	/* PERIODICLISTBASE: offset 0x14 */
+	u32		frame_list;	/* points to periodic list */
+	/* ASYNCLISTADDR: offset 0x18 */
+	u32		async_next;	/* address of next async queue head */
+
+	u32		reserved[9];
+
+	/* CONFIGFLAG: offset 0x40 */
+	u32		configured_flag;
+#define FLAG_CF		(1<<0)		/* true: we'll support "high speed" */
+
+	/* PORTSC: offset 0x44 */
+	u32		port_status[0];	/* up to N_PORTS */
+/* 31:23 reserved */
+#define PORT_WKOC_E	(1<<22)		/* wake on overcurrent (enable) */
+#define PORT_WKDISC_E	(1<<21)		/* wake on disconnect (enable) */
+#define PORT_WKCONN_E	(1<<20)		/* wake on connect (enable) */
+/* 19:16 for port testing */
+#define PORT_LED_OFF	(0<<14)
+#define PORT_LED_AMBER	(1<<14)
+#define PORT_LED_GREEN	(2<<14)
+#define PORT_LED_MASK	(3<<14)
+#define PORT_OWNER	(1<<13)		/* true: companion hc owns this port */
+#define PORT_POWER	(1<<12)		/* true: has power (see PPC) */
+#define PORT_USB11(x) (((x)&(3<<10)) == (1<<10))	/* USB 1.1 device */
+/* 11:10 for detecting lowspeed devices (reset vs release ownership) */
+/* 9 reserved */
+#define PORT_RESET	(1<<8)		/* reset port */
+#define PORT_SUSPEND	(1<<7)		/* suspend port */
+#define PORT_RESUME	(1<<6)		/* resume it */
+#define PORT_OCC	(1<<5)		/* over current change */
+#define PORT_OC		(1<<4)		/* over current active */
+#define PORT_PEC	(1<<3)		/* port enable change */
+#define PORT_PE		(1<<2)		/* port enable */
+#define PORT_CSC	(1<<1)		/* connect status change */
+#define PORT_CONNECT	(1<<0)		/* device connected */
+#define PORT_RWC_BITS   (PORT_CSC | PORT_PEC | PORT_OCC)
+} __attribute__ ((packed));
+
+/* Appendix C, Debug port ... intended for use with special "debug devices"
+ * that can help if there's no serial console.  (nonstandard enumeration.)
+ */
+struct ehci_dbg_port {
+	u32	control;
+#define DBGP_OWNER	(1<<30)
+#define DBGP_ENABLED	(1<<28)
+#define DBGP_DONE	(1<<16)
+#define DBGP_INUSE	(1<<10)
+#define DBGP_ERRCODE(x)	(((x)>>7)&0x07)
+#	define DBGP_ERR_BAD	1
+#	define DBGP_ERR_SIGNAL	2
+#define DBGP_ERROR	(1<<6)
+#define DBGP_GO		(1<<5)
+#define DBGP_OUT	(1<<4)
+#define DBGP_LEN(x)	(((x)>>0)&0x0f)
+	u32	pids;
+#define DBGP_PID_GET(x)		(((x)>>16)&0xff)
+#define DBGP_PID_SET(data, tok)	(((data)<<8)|(tok))
+	u32	data03;
+	u32	data47;
+	u32	address;
+#define DBGP_EPADDR(dev, ep)	(((dev)<<8)|(ep))
+} __attribute__ ((packed));
+
+
+#define	QTD_NEXT(dma)	cpu_to_le32((u32)dma)
+
+/*
+ * EHCI Specification 0.95 Section 3.5
+ * QTD: describe data transfer components (buffer, direction, ...)
+ * See Fig 3-6 "Queue Element Transfer Descriptor Block Diagram".
+ *
+ * These are associated only with "QH" (Queue Head) structures,
+ * used with control, bulk, and interrupt transfers.
+ */
+struct ehci_qtd {
+	/* first part defined by EHCI spec */
+	__le32			hw_next;		/* see EHCI 3.5.1 */
+	__le32			hw_alt_next;		/* see EHCI 3.5.2 */
+	__le32			hw_token;		/* see EHCI 3.5.3 */
+#define	QTD_TOGGLE	(1 << 31)	/* data toggle */
+#define	QTD_LENGTH(tok)	(((tok)>>16) & 0x7fff)
+#define	QTD_IOC		(1 << 15)	/* interrupt on complete */
+#define	QTD_CERR(tok)	(((tok)>>10) & 0x3)
+#define	QTD_PID(tok)	(((tok)>>8) & 0x3)
+#define	QTD_STS_ACTIVE	(1 << 7)	/* HC may execute this */
+#define	QTD_STS_HALT	(1 << 6)	/* halted on error */
+#define	QTD_STS_DBE	(1 << 5)	/* data buffer error (in HC) */
+#define	QTD_STS_BABBLE	(1 << 4)	/* device was babbling (qtd halted) */
+#define	QTD_STS_XACT	(1 << 3)	/* device gave illegal response */
+#define	QTD_STS_MMF	(1 << 2)	/* incomplete split transaction */
+#define	QTD_STS_STS	(1 << 1)	/* split transaction state */
+#define	QTD_STS_PING	(1 << 0)	/* issue PING? */
+	__le32			hw_buf[5];		/* see EHCI 3.5.4 */
+	__le32			hw_buf_hi[5];		/* Appendix B */
+
+	/* the rest is HCD-private */
+	dma_addr_t		qtd_dma;		/* qtd address */
+	struct list_head	qtd_list;		/* sw qtd list */
+	struct urb		*urb;			/* qtd's urb */
+	size_t			length;			/* length of buffer */
+
+	u32			qtd_buffer_len;
+	void			*buffer;
+	dma_addr_t		buffer_dma;
+	void			*transfer_buffer;
+	void			*transfer_dma;
+} __attribute__ ((aligned(32)));
+
+/* mask NakCnt+T in qh->hw_alt_next */
+#define QTD_MASK __constant_cpu_to_le32 (~0x1f)
+
+#define IS_SHORT_READ(token) (QTD_LENGTH(token) != 0 && QTD_PID(token) == 1)
+
+/* Type tag from {qh, itd, sitd, fstn}->hw_next */
+#define Q_NEXT_TYPE(dma) ((dma) & __constant_cpu_to_le32 (3 << 1))
+
+/* values for that type tag */
+#define Q_TYPE_QH	__constant_cpu_to_le32 (1 << 1)
+
+/* next async queue entry, or pointer to interrupt/periodic QH */
+#define	QH_NEXT(dma)	(cpu_to_le32(((u32)dma)&~0x01f)|Q_TYPE_QH)
+
+/* for periodic/async schedules and qtd lists, mark end of list */
+#define	EHCI_LIST_END	__constant_cpu_to_le32(1) /* "null pointer" to hw */
+
+/*
+ * Entries in periodic shadow table are pointers to one of four kinds
+ * of data structure.  That's dictated by the hardware; a type tag is
+ * encoded in the low bits of the hardware's periodic schedule.  Use
+ * Q_NEXT_TYPE to get the tag.
+ *
+ * For entries in the async schedule, the type tag always says "qh".
+ */
+union ehci_shadow {
+	struct ehci_qh		*qh;		/* Q_TYPE_QH */
+	__le32			*hw_next;	/* (all types) */
+	void			*ptr;
+};
+
+/*
+ * EHCI Specification 0.95 Section 3.6
+ * QH: describes control/bulk/interrupt endpoints
+ * See Fig 3-7 "Queue Head Structure Layout".
+ *
+ * These appear in both the async and (for interrupt) periodic schedules.
+ */
+
+struct ehci_qh {
+	/* first part defined by EHCI spec */
+	__le32			hw_next;	 /* see EHCI 3.6.1 */
+	__le32			hw_info1;	/* see EHCI 3.6.2 */
+#define	QH_HEAD		0x00008000
+	__le32			hw_info2;	/* see EHCI 3.6.2 */
+#define	QH_SMASK	0x000000ff
+#define	QH_CMASK	0x0000ff00
+#define	QH_HUBADDR	0x007f0000
+#define	QH_HUBPORT	0x3f800000
+#define	QH_MULT		0xc0000000
+	__le32			hw_current;	 /* qtd list - see EHCI 3.6.4 */
+
+	/* qtd overlay (hardware parts of a struct ehci_qtd) */
+	__le32			hw_qtd_next;
+	__le32			hw_alt_next;
+	__le32			hw_token;
+	__le32			hw_buf[5];
+	__le32			hw_buf_hi[5];
+
+	/* the rest is HCD-private */
+	dma_addr_t		qh_dma;		/* address of qh */
+	union ehci_shadow	qh_next;	/* ptr to qh; or periodic */
+	struct list_head	qtd_list;	/* sw qtd list */
+	struct ehci_qtd		*dummy;
+	struct ehci_qh		*reclaim;	/* next to reclaim */
+
+	struct oxu_hcd		*oxu;
+	struct kref		kref;
+	unsigned		stamp;
+
+	u8			qh_state;
+#define	QH_STATE_LINKED		1		/* HC sees this */
+#define	QH_STATE_UNLINK		2		/* HC may still see this */
+#define	QH_STATE_IDLE		3		/* HC doesn't see this */
+#define	QH_STATE_UNLINK_WAIT	4		/* LINKED and on reclaim q */
+#define	QH_STATE_COMPLETING	5		/* don't touch token.HALT */
+
+	/* periodic schedule info */
+	u8			usecs;		/* intr bandwidth */
+	u8			gap_uf;		/* uframes split/csplit gap */
+	u8			c_usecs;	/* ... split completion bw */
+	u16			tt_usecs;	/* tt downstream bandwidth */
+	unsigned short		period;		/* polling interval */
+	unsigned short		start;		/* where polling starts */
+#define NO_FRAME ((unsigned short)~0)			/* pick new start */
+	struct usb_device	*dev;		/* access to TT */
+} __attribute__ ((aligned(32)));
+
+/*
+ * Proper OXU210HP structs
+ */
+
+#define OXU_OTG_CORE_OFFSET	0x00400
+#define OXU_OTG_CAP_OFFSET	(OXU_OTG_CORE_OFFSET + 0x100)
+#define OXU_SPH_CORE_OFFSET	0x00800
+#define OXU_SPH_CAP_OFFSET	(OXU_SPH_CORE_OFFSET + 0x100)
+
+#define OXU_OTG_MEM		0xE000
+#define OXU_SPH_MEM		0x16000
+
+/* Only how many elements & element structure are specifies here. */
+/* 2 host controllers are enabled - total size <= 28 kbytes */
+#define	DEFAULT_I_TDPS		1024
+#define QHEAD_NUM		16
+#define QTD_NUM			32
+#define SITD_NUM		8
+#define MURB_NUM		8
+
+#define BUFFER_NUM		8
+#define BUFFER_SIZE		512
+
+struct oxu_info {
+	struct usb_hcd *hcd[2];
+};
+
+struct oxu_buf {
+	u8			buffer[BUFFER_SIZE];
+} __attribute__ ((aligned(BUFFER_SIZE)));
+
+struct oxu_onchip_mem {
+	struct oxu_buf		db_pool[BUFFER_NUM];
+
+	u32			frame_list[DEFAULT_I_TDPS];
+	struct ehci_qh		qh_pool[QHEAD_NUM];
+	struct ehci_qtd		qtd_pool[QTD_NUM];
+} __attribute__ ((aligned(4 << 10)));
+
+#define	EHCI_MAX_ROOT_PORTS	15		/* see HCS_N_PORTS */
+
+struct oxu_murb {
+	struct urb		urb;
+	struct urb		*main;
+	u8			last;
+};
+
+struct oxu_hcd {				/* one per controller */
+	unsigned int		is_otg:1;
+
+	u8			qh_used[QHEAD_NUM];
+	u8			qtd_used[QTD_NUM];
+	u8			db_used[BUFFER_NUM];
+	u8			murb_used[MURB_NUM];
+
+	struct oxu_onchip_mem	__iomem *mem;
+	spinlock_t		mem_lock;
+
+	struct timer_list	urb_timer;
+
+	struct ehci_caps __iomem *caps;
+	struct ehci_regs __iomem *regs;
+
+	__u32			hcs_params;	/* cached register copy */
+	spinlock_t		lock;
+
+	/* async schedule support */
+	struct ehci_qh		*async;
+	struct ehci_qh		*reclaim;
+	unsigned		reclaim_ready:1;
+	unsigned		scanning:1;
+
+	/* periodic schedule support */
+	unsigned		periodic_size;
+	__le32			*periodic;	/* hw periodic table */
+	dma_addr_t		periodic_dma;
+	unsigned		i_thresh;	/* uframes HC might cache */
+
+	union ehci_shadow	*pshadow;	/* mirror hw periodic table */
+	int			next_uframe;	/* scan periodic, start here */
+	unsigned		periodic_sched;	/* periodic activity count */
+
+	/* per root hub port */
+	unsigned long		reset_done[EHCI_MAX_ROOT_PORTS];
+	/* bit vectors (one bit per port) */
+	unsigned long		bus_suspended;	/* which ports were
+						 * already suspended at the
+						 * start of a bus suspend
+						 */
+	unsigned long		companion_ports;/* which ports are dedicated
+						 * to the companion controller
+						 */
+
+	struct timer_list	watchdog;
+	unsigned long		actions;
+	unsigned		stamp;
+	unsigned long		next_statechange;
+	u32			command;
+
+	/* SILICON QUIRKS */
+	struct list_head	urb_list;	/* this is the head to urb
+						 * queue that didn't get enough
+						 * resources
+						 */
+	struct oxu_murb		*murb_pool;	/* murb per split big urb */
+	unsigned urb_len;
+
+	u8			sbrn;		/* packed release number */
+};
+
+#define EHCI_IAA_JIFFIES	(HZ/100)	/* arbitrary; ~10 msec */
+#define EHCI_IO_JIFFIES	 	(HZ/10)		/* io watchdog > irq_thresh */
+#define EHCI_ASYNC_JIFFIES      (HZ/20)		/* async idle timeout */
+#define EHCI_SHRINK_JIFFIES     (HZ/200)	/* async qh unlink delay */
+
+enum ehci_timer_action {
+	TIMER_IO_WATCHDOG,
+	TIMER_IAA_WATCHDOG,
+	TIMER_ASYNC_SHRINK,
+	TIMER_ASYNC_OFF,
+};
+
+#include <linux/oxu210hp.h>
diff --git a/drivers/usb/host/pci-quirks.c b/drivers/usb/host/pci-quirks.c
index ae6e70edd745..75b69847918e 100644
--- a/drivers/usb/host/pci-quirks.c
+++ b/drivers/usb/host/pci-quirks.c
@@ -172,9 +172,9 @@ static void __devinit quirk_usb_handoff_ohci(struct pci_dev *pdev)
 	if (!mmio_resource_enabled(pdev, 0))
 		return;
 
-	base = ioremap_nocache(pci_resource_start(pdev, 0),
-				     pci_resource_len(pdev, 0));
-	if (base == NULL) return;
+	base = pci_ioremap_bar(pdev, 0);
+	if (base == NULL)
+		return;
 
 /* On PA-RISC, PDC can leave IR set incorrectly; ignore it there. */
 #ifndef __hppa__
@@ -221,9 +221,9 @@ static void __devinit quirk_usb_disable_ehci(struct pci_dev *pdev)
 	if (!mmio_resource_enabled(pdev, 0))
 		return;
 
-	base = ioremap_nocache(pci_resource_start(pdev, 0),
-				pci_resource_len(pdev, 0));
-	if (base == NULL) return;
+	base = pci_ioremap_bar(pdev, 0);
+	if (base == NULL)
+		return;
 
 	cap_length = readb(base);
 	op_reg_base = base + cap_length;
@@ -271,7 +271,7 @@ static void __devinit quirk_usb_disable_ehci(struct pci_dev *pdev)
 			/* if boot firmware now owns EHCI, spin till
 			 * it hands it over.
 			 */
-			msec = 5000;
+			msec = 1000;
 			while ((cap & EHCI_USBLEGSUP_BIOS) && (msec > 0)) {
 				tried_handoff = 1;
 				msleep(10);
diff --git a/drivers/usb/host/r8a66597-hcd.c b/drivers/usb/host/r8a66597-hcd.c
index 2376f24f3c83..319041205b57 100644
--- a/drivers/usb/host/r8a66597-hcd.c
+++ b/drivers/usb/host/r8a66597-hcd.c
@@ -114,6 +114,9 @@ static int r8a66597_clock_enable(struct r8a66597 *r8a66597)
 	int i = 0;
 
 #if defined(CONFIG_SUPERH_ON_CHIP_R8A66597)
+#if defined(CONFIG_HAVE_CLK)
+	clk_enable(r8a66597->clk);
+#endif
 	do {
 		r8a66597_write(r8a66597, SCKE, SYSCFG0);
 		tmp = r8a66597_read(r8a66597, SYSCFG0);
@@ -154,7 +157,11 @@ static void r8a66597_clock_disable(struct r8a66597 *r8a66597)
 {
 	r8a66597_bclr(r8a66597, SCKE, SYSCFG0);
 	udelay(1);
-#if !defined(CONFIG_SUPERH_ON_CHIP_R8A66597)
+#if defined(CONFIG_SUPERH_ON_CHIP_R8A66597)
+#if defined(CONFIG_HAVE_CLK)
+	clk_disable(r8a66597->clk);
+#endif
+#else
 	r8a66597_bclr(r8a66597, PLLC, SYSCFG0);
 	r8a66597_bclr(r8a66597, XCKE, SYSCFG0);
 	r8a66597_bclr(r8a66597, USBE, SYSCFG0);
@@ -2261,13 +2268,18 @@ static int __init_or_module r8a66597_remove(struct platform_device *pdev)
 	del_timer_sync(&r8a66597->rh_timer);
 	usb_remove_hcd(hcd);
 	iounmap((void *)r8a66597->reg);
+#if defined(CONFIG_SUPERH_ON_CHIP_R8A66597) && defined(CONFIG_HAVE_CLK)
+	clk_put(r8a66597->clk);
+#endif
 	usb_put_hcd(hcd);
 	return 0;
 }
 
-#define resource_len(r) (((r)->end - (r)->start) + 1)
 static int __init r8a66597_probe(struct platform_device *pdev)
 {
+#if defined(CONFIG_SUPERH_ON_CHIP_R8A66597) && defined(CONFIG_HAVE_CLK)
+	char clk_name[8];
+#endif
 	struct resource *res = NULL, *ires;
 	int irq = -1;
 	void __iomem *reg = NULL;
@@ -2283,11 +2295,10 @@ static int __init r8a66597_probe(struct platform_device *pdev)
 		goto clean_up;
 	}
 
-	res = platform_get_resource_byname(pdev, IORESOURCE_MEM,
-					   (char *)hcd_name);
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	if (!res) {
 		ret = -ENODEV;
-		dev_err(&pdev->dev, "platform_get_resource_byname error.\n");
+		dev_err(&pdev->dev, "platform_get_resource error.\n");
 		goto clean_up;
 	}
 
@@ -2302,7 +2313,7 @@ static int __init r8a66597_probe(struct platform_device *pdev)
 	irq = ires->start;
 	irq_trigger = ires->flags & IRQF_TRIGGER_MASK;
 
-	reg = ioremap(res->start, resource_len(res));
+	reg = ioremap(res->start, resource_size(res));
 	if (reg == NULL) {
 		ret = -ENOMEM;
 		dev_err(&pdev->dev, "ioremap error.\n");
@@ -2320,6 +2331,16 @@ static int __init r8a66597_probe(struct platform_device *pdev)
 	memset(r8a66597, 0, sizeof(struct r8a66597));
 	dev_set_drvdata(&pdev->dev, r8a66597);
 
+#if defined(CONFIG_SUPERH_ON_CHIP_R8A66597) && defined(CONFIG_HAVE_CLK)
+	snprintf(clk_name, sizeof(clk_name), "usb%d", pdev->id);
+	r8a66597->clk = clk_get(&pdev->dev, clk_name);
+	if (IS_ERR(r8a66597->clk)) {
+		dev_err(&pdev->dev, "cannot get clock \"%s\"\n", clk_name);
+		ret = PTR_ERR(r8a66597->clk);
+		goto clean_up2;
+	}
+#endif
+
 	spin_lock_init(&r8a66597->lock);
 	init_timer(&r8a66597->rh_timer);
 	r8a66597->rh_timer.function = r8a66597_timer;
@@ -2365,11 +2386,18 @@ static int __init r8a66597_probe(struct platform_device *pdev)
 	ret = usb_add_hcd(hcd, irq, IRQF_DISABLED | irq_trigger);
 	if (ret != 0) {
 		dev_err(&pdev->dev, "Failed to add hcd\n");
-		goto clean_up;
+		goto clean_up3;
 	}
 
 	return 0;
 
+clean_up3:
+#if defined(CONFIG_SUPERH_ON_CHIP_R8A66597) && defined(CONFIG_HAVE_CLK)
+	clk_put(r8a66597->clk);
+clean_up2:
+#endif
+	usb_put_hcd(hcd);
+
 clean_up:
 	if (reg)
 		iounmap(reg);
diff --git a/drivers/usb/host/r8a66597.h b/drivers/usb/host/r8a66597.h
index 84ee01417315..ecacde4d69b0 100644
--- a/drivers/usb/host/r8a66597.h
+++ b/drivers/usb/host/r8a66597.h
@@ -26,6 +26,10 @@
 #ifndef __R8A66597_H__
 #define __R8A66597_H__
 
+#if defined(CONFIG_SUPERH_ON_CHIP_R8A66597) && defined(CONFIG_HAVE_CLK)
+#include <linux/clk.h>
+#endif
+
 #define SYSCFG0		0x00
 #define SYSCFG1		0x02
 #define SYSSTS0		0x04
@@ -481,7 +485,9 @@ struct r8a66597_root_hub {
 struct r8a66597 {
 	spinlock_t lock;
 	unsigned long reg;
-
+#if defined(CONFIG_SUPERH_ON_CHIP_R8A66597) && defined(CONFIG_HAVE_CLK)
+	struct clk *clk;
+#endif
 	struct r8a66597_device		device0;
 	struct r8a66597_root_hub	root_hub[R8A66597_MAX_ROOT_HUB];
 	struct list_head		pipe_queue[R8A66597_MAX_NUM_PIPE];
diff --git a/drivers/usb/image/microtek.c b/drivers/usb/image/microtek.c
index 885867a86de8..4541dfcea88f 100644
--- a/drivers/usb/image/microtek.c
+++ b/drivers/usb/image/microtek.c
@@ -350,17 +350,16 @@ static int mts_scsi_abort(struct scsi_cmnd *srb)
 static int mts_scsi_host_reset(struct scsi_cmnd *srb)
 {
 	struct mts_desc* desc = (struct mts_desc*)(srb->device->host->hostdata[0]);
-	int result, rc;
+	int result;
 
 	MTS_DEBUG_GOT_HERE();
 	mts_debug_dump(desc);
 
-	rc = usb_lock_device_for_reset(desc->usb_dev, desc->usb_intf);
-	if (rc < 0)
-		return FAILED;
-	result = usb_reset_device(desc->usb_dev);
-	if (rc)
+	result = usb_lock_device_for_reset(desc->usb_dev, desc->usb_intf);
+	if (result == 0) {
+		result = usb_reset_device(desc->usb_dev);
 		usb_unlock_device(desc->usb_dev);
+	}
 	return result ? FAILED : SUCCESS;
 }
 
diff --git a/drivers/usb/misc/berry_charge.c b/drivers/usb/misc/berry_charge.c
index 24e2dc3148a4..c05a85bc5925 100644
--- a/drivers/usb/misc/berry_charge.c
+++ b/drivers/usb/misc/berry_charge.c
@@ -123,6 +123,11 @@ static int berry_probe(struct usb_interface *intf,
 {
 	struct usb_device *udev = interface_to_usbdev(intf);
 
+	if (udev->bus_mA < 500) {
+		dbg(&udev->dev, "Not enough power to charge available\n");
+		return -ENODEV;
+	}
+
 	dbg(&udev->dev, "Power is set to %dmA\n",
 	    udev->actconfig->desc.bMaxPower * 2);
 
diff --git a/drivers/usb/misc/usbtest.c b/drivers/usb/misc/usbtest.c
index 444c69c447be..5f1a19d1497d 100644
--- a/drivers/usb/misc/usbtest.c
+++ b/drivers/usb/misc/usbtest.c
@@ -192,8 +192,6 @@ static struct urb *simple_alloc_urb (
 {
 	struct urb		*urb;
 
-	if (bytes < 0)
-		return NULL;
 	urb = usb_alloc_urb (0, GFP_KERNEL);
 	if (!urb)
 		return urb;
diff --git a/drivers/usb/mon/Kconfig b/drivers/usb/mon/Kconfig
index deb9ddffa402..f28f350cd96a 100644
--- a/drivers/usb/mon/Kconfig
+++ b/drivers/usb/mon/Kconfig
@@ -3,14 +3,13 @@
 #
 
 config USB_MON
-	bool "USB Monitor"
-	depends on USB!=n
-	default y
+	tristate "USB Monitor"
+	depends on USB
+	default y if USB=y
+	default m if USB=m
 	help
-	  If you say Y here, a component which captures the USB traffic
+	  If you select this option, a component which captures the USB traffic
 	  between peripheral-specific drivers and HC drivers will be built.
 	  For more information, see <file:Documentation/usb/usbmon.txt>.
 
-	  This is somewhat experimental at this time, but it should be safe.
-
-	  If unsure, say Y.
+	  If unsure, say Y (if allowed), otherwise M.
diff --git a/drivers/usb/mon/Makefile b/drivers/usb/mon/Makefile
index 0f76ed5e1617..c6516b566731 100644
--- a/drivers/usb/mon/Makefile
+++ b/drivers/usb/mon/Makefile
@@ -4,5 +4,4 @@
 
 usbmon-objs	:= mon_main.o mon_stat.o mon_text.o mon_bin.o mon_dma.o
 
-# This does not use CONFIG_USB_MON because we want this to use a tristate.
-obj-$(CONFIG_USB)	+= usbmon.o
+obj-$(CONFIG_USB_MON)	+= usbmon.o
diff --git a/drivers/usb/musb/davinci.c b/drivers/usb/musb/davinci.c
index dfb3bcbe00fc..0d566dc5ce06 100644
--- a/drivers/usb/musb/davinci.c
+++ b/drivers/usb/musb/davinci.c
@@ -32,9 +32,9 @@
 #include <linux/io.h>
 #include <linux/gpio.h>
 
-#include <asm/arch/hardware.h>
-#include <asm/arch/memory.h>
-#include <asm/arch/gpio.h>
+#include <mach/arch/hardware.h>
+#include <mach/arch/memory.h>
+#include <mach/arch/gpio.h>
 #include <asm/mach-types.h>
 
 #include "musb_core.h"
@@ -364,6 +364,18 @@ static irqreturn_t davinci_interrupt(int irq, void *__hci)
 	return IRQ_HANDLED;
 }
 
+int musb_platform_set_mode(struct musb *musb, u8 mode)
+{
+	/* EVM can't do this (right?) */
+	return -EIO;
+}
+
+int musb_platform_set_mode(struct musb *musb, u8 mode)
+{
+       /* EVM can't do this (right?) */
+       return -EIO;
+}
+
 int __init musb_platform_init(struct musb *musb)
 {
 	void __iomem	*tibase = musb->ctrl_base;
diff --git a/drivers/usb/musb/musb_core.c b/drivers/usb/musb/musb_core.c
index 5280dba9b1fb..83720f61fdba 100644
--- a/drivers/usb/musb/musb_core.c
+++ b/drivers/usb/musb/musb_core.c
@@ -1212,7 +1212,7 @@ static int __init ep_config_from_table(struct musb *musb)
 		if (epn >= musb->config->num_eps) {
 			pr_debug("%s: invalid ep %d\n",
 					musb_driver_name, epn);
-			continue;
+			return -EINVAL;
 		}
 		offset = fifo_setup(musb, hw_ep + epn, cfg++, offset);
 		if (offset < 0) {
@@ -1671,17 +1671,20 @@ musb_mode_store(struct device *dev, struct device_attribute *attr,
 {
 	struct musb	*musb = dev_to_musb(dev);
 	unsigned long	flags;
+	int		status;
 
 	spin_lock_irqsave(&musb->lock, flags);
-	if (!strncmp(buf, "host", 4))
-		musb_platform_set_mode(musb, MUSB_HOST);
-	if (!strncmp(buf, "peripheral", 10))
-		musb_platform_set_mode(musb, MUSB_PERIPHERAL);
-	if (!strncmp(buf, "otg", 3))
-		musb_platform_set_mode(musb, MUSB_OTG);
+	if (sysfs_streq(buf, "host"))
+		status = musb_platform_set_mode(musb, MUSB_HOST);
+	else if (sysfs_streq(buf, "peripheral"))
+		status = musb_platform_set_mode(musb, MUSB_PERIPHERAL);
+	else if (sysfs_streq(buf, "otg"))
+		status = musb_platform_set_mode(musb, MUSB_OTG);
+	else
+		status = -EINVAL;
 	spin_unlock_irqrestore(&musb->lock, flags);
 
-	return n;
+	return (status == 0) ? n : status;
 }
 static DEVICE_ATTR(mode, 0644, musb_mode_show, musb_mode_store);
 
@@ -1781,7 +1784,7 @@ allocate_instance(struct device *dev,
 #ifdef CONFIG_USB_MUSB_HDRC_HCD
 	struct usb_hcd	*hcd;
 
-	hcd = usb_create_hcd(&musb_hc_driver, dev, dev->bus_id);
+	hcd = usb_create_hcd(&musb_hc_driver, dev, dev_name(dev));
 	if (!hcd)
 		return NULL;
 	/* usbcore sets dev->driver_data to hcd, and sometimes uses that... */
@@ -1810,7 +1813,6 @@ allocate_instance(struct device *dev,
 	for (epnum = 0, ep = musb->endpoints;
 			epnum < musb->config->num_eps;
 			epnum++, ep++) {
-
 		ep->musb = musb;
 		ep->epnum = epnum;
 	}
@@ -1838,7 +1840,7 @@ static void musb_free(struct musb *musb)
 	musb_gadget_cleanup(musb);
 #endif
 
-	if (musb->nIrq >= 0) {
+	if (musb->nIrq >= 0 && musb->irq_wake) {
 		disable_irq_wake(musb->nIrq);
 		free_irq(musb->nIrq, musb);
 	}
@@ -1984,15 +1986,19 @@ bad_config:
 	INIT_WORK(&musb->irq_work, musb_irq_work);
 
 	/* attach to the IRQ */
-	if (request_irq(nIrq, musb->isr, 0, dev->bus_id, musb)) {
+	if (request_irq(nIrq, musb->isr, 0, dev_name(dev), musb)) {
 		dev_err(dev, "request_irq %d failed!\n", nIrq);
 		status = -ENODEV;
 		goto fail2;
 	}
 	musb->nIrq = nIrq;
 /* FIXME this handles wakeup irqs wrong */
-	if (enable_irq_wake(nIrq) == 0)
+	if (enable_irq_wake(nIrq) == 0) {
+		musb->irq_wake = 1;
 		device_init_wakeup(dev, 1);
+	} else {
+		musb->irq_wake = 0;
+	}
 
 	pr_info("%s: USB %s mode controller at %p using %s, IRQ %d\n",
 			musb_driver_name,
diff --git a/drivers/usb/musb/musb_core.h b/drivers/usb/musb/musb_core.h
index 82227251931b..d45d258e63f0 100644
--- a/drivers/usb/musb/musb_core.h
+++ b/drivers/usb/musb/musb_core.h
@@ -359,6 +359,7 @@ struct musb {
 	struct otg_transceiver	xceiv;
 
 	int nIrq;
+	unsigned		irq_wake:1;
 
 	struct musb_hw_ep	 endpoints[MUSB_C_NUM_EPS];
 #define control_ep		endpoints
@@ -467,7 +468,7 @@ extern void musb_platform_disable(struct musb *musb);
 
 extern void musb_hnp_stop(struct musb *musb);
 
-extern void musb_platform_set_mode(struct musb *musb, u8 musb_mode);
+extern int musb_platform_set_mode(struct musb *musb, u8 musb_mode);
 
 #if defined(CONFIG_USB_TUSB6010) || \
 	defined(CONFIG_ARCH_OMAP2430) || defined(CONFIG_ARCH_OMAP34XX)
diff --git a/drivers/usb/musb/musb_gadget.c b/drivers/usb/musb/musb_gadget.c
index d6a802c224fa..6197daeab8f9 100644
--- a/drivers/usb/musb/musb_gadget.c
+++ b/drivers/usb/musb/musb_gadget.c
@@ -1633,7 +1633,7 @@ int __init musb_gadget_setup(struct musb *musb)
 	musb->g.speed = USB_SPEED_UNKNOWN;
 
 	/* this "gadget" abstracts/virtualizes the controller */
-	strcpy(musb->g.dev.bus_id, "gadget");
+	dev_set_name(&musb->g.dev, "gadget");
 	musb->g.dev.parent = musb->controller;
 	musb->g.dev.dma_mask = musb->controller->dma_mask;
 	musb->g.dev.release = musb_gadget_release;
diff --git a/drivers/usb/musb/musb_host.c b/drivers/usb/musb/musb_host.c
index cc64462d4c4e..bf25ef4cc151 100644
--- a/drivers/usb/musb/musb_host.c
+++ b/drivers/usb/musb/musb_host.c
@@ -112,18 +112,21 @@ static void musb_h_tx_flush_fifo(struct musb_hw_ep *ep)
 {
 	void __iomem	*epio = ep->regs;
 	u16		csr;
+	u16		lastcsr = 0;
 	int		retries = 1000;
 
 	csr = musb_readw(epio, MUSB_TXCSR);
 	while (csr & MUSB_TXCSR_FIFONOTEMPTY) {
-		DBG(5, "Host TX FIFONOTEMPTY csr: %02x\n", csr);
+		if (csr != lastcsr)
+			DBG(3, "Host TX FIFONOTEMPTY csr: %02x\n", csr);
+		lastcsr = csr;
 		csr |= MUSB_TXCSR_FLUSHFIFO;
 		musb_writew(epio, MUSB_TXCSR, csr);
 		csr = musb_readw(epio, MUSB_TXCSR);
-		if (retries-- < 1) {
-			ERR("Could not flush host TX fifo: csr: %04x\n", csr);
+		if (WARN(retries-- < 1,
+				"Could not flush host TX%d fifo: csr: %04x\n",
+				ep->epnum, csr))
 			return;
-		}
 		mdelay(1);
 	}
 }
@@ -268,7 +271,7 @@ __musb_giveback(struct musb *musb, struct urb *urb, int status)
 __releases(musb->lock)
 __acquires(musb->lock)
 {
-	DBG(({ int level; switch (urb->status) {
+	DBG(({ int level; switch (status) {
 				case 0:
 					level = 4;
 					break;
@@ -283,8 +286,8 @@ __acquires(musb->lock)
 					level = 2;
 					break;
 				}; level; }),
-			"complete %p (%d), dev%d ep%d%s, %d/%d\n",
-			urb, urb->status,
+			"complete %p %pF (%d), dev%d ep%d%s, %d/%d\n",
+			urb, urb->complete, status,
 			usb_pipedevice(urb->pipe),
 			usb_pipeendpoint(urb->pipe),
 			usb_pipein(urb->pipe) ? "in" : "out",
@@ -988,8 +991,10 @@ static bool musb_h_ep0_continue(struct musb *musb, u16 len, struct urb *urb)
 		if (fifo_count) {
 			fifo_dest = (u8 *) (urb->transfer_buffer
 					+ urb->actual_length);
-			DBG(3, "Sending %d bytes to %p\n",
-					fifo_count, fifo_dest);
+			DBG(3, "Sending %d byte%s to ep0 fifo %p\n",
+					fifo_count,
+					(fifo_count == 1) ? "" : "s",
+					fifo_dest);
 			musb_write_fifo(hw_ep, fifo_count, fifo_dest);
 
 			urb->actual_length += fifo_count;
diff --git a/drivers/usb/musb/musbhsdma.c b/drivers/usb/musb/musbhsdma.c
index 8c734ef2c1ed..d193b7849087 100644
--- a/drivers/usb/musb/musbhsdma.c
+++ b/drivers/usb/musb/musbhsdma.c
@@ -424,7 +424,7 @@ dma_controller_create(struct musb *musb, void __iomem *base)
 	controller->controller.channel_abort = dma_channel_abort;
 
 	if (request_irq(irq, dma_controller_irq, IRQF_DISABLED,
-			musb->controller->bus_id, &controller->controller)) {
+			dev_name(musb->controller), &controller->controller)) {
 		dev_err(dev, "request_irq %d failed!\n", irq);
 		dma_controller_destroy(&controller->controller);
 
diff --git a/drivers/usb/musb/omap2430.c b/drivers/usb/musb/omap2430.c
index ce6c162920f7..901dffdf23b1 100644
--- a/drivers/usb/musb/omap2430.c
+++ b/drivers/usb/musb/omap2430.c
@@ -58,10 +58,10 @@ static void musb_do_idle(unsigned long _musb)
 #endif
 	u8	devctl;
 
-	devctl = musb_readb(musb->mregs, MUSB_DEVCTL);
-
 	spin_lock_irqsave(&musb->lock, flags);
 
+	devctl = musb_readb(musb->mregs, MUSB_DEVCTL);
+
 	switch (musb->xceiv.state) {
 	case OTG_STATE_A_WAIT_BCON:
 		devctl &= ~MUSB_DEVCTL_SESSION;
@@ -196,7 +196,7 @@ static int omap_set_power(struct otg_transceiver *x, unsigned mA)
 
 static int musb_platform_resume(struct musb *musb);
 
-void musb_platform_set_mode(struct musb *musb, u8 musb_mode)
+int musb_platform_set_mode(struct musb *musb, u8 musb_mode)
 {
 	u8	devctl = musb_readb(musb->mregs, MUSB_DEVCTL);
 
@@ -204,15 +204,24 @@ void musb_platform_set_mode(struct musb *musb, u8 musb_mode)
 	musb_writeb(musb->mregs, MUSB_DEVCTL, devctl);
 
 	switch (musb_mode) {
+#ifdef CONFIG_USB_MUSB_HDRC_HCD
 	case MUSB_HOST:
 		otg_set_host(&musb->xceiv, musb->xceiv.host);
 		break;
+#endif
+#ifdef CONFIG_USB_GADGET_MUSB_HDRC
 	case MUSB_PERIPHERAL:
 		otg_set_peripheral(&musb->xceiv, musb->xceiv.gadget);
 		break;
+#endif
+#ifdef CONFIG_USB_MUSB_OTG
 	case MUSB_OTG:
 		break;
+#endif
+	default:
+		return -EINVAL;
 	}
+	return 0;
 }
 
 int __init musb_platform_init(struct musb *musb)
diff --git a/drivers/usb/musb/tusb6010.c b/drivers/usb/musb/tusb6010.c
index ee8fca92a4ac..9e20fd070d71 100644
--- a/drivers/usb/musb/tusb6010.c
+++ b/drivers/usb/musb/tusb6010.c
@@ -598,7 +598,7 @@ static void tusb_source_power(struct musb *musb, int is_on)
  * and peripheral modes in non-OTG configurations by reconfiguring hardware
  * and then setting musb->board_mode. For now, only support OTG mode.
  */
-void musb_platform_set_mode(struct musb *musb, u8 musb_mode)
+int musb_platform_set_mode(struct musb *musb, u8 musb_mode)
 {
 	void __iomem	*tbase = musb->ctrl_base;
 	u32		otg_stat, phy_otg_ctrl, phy_otg_ena, dev_conf;
@@ -641,7 +641,8 @@ void musb_platform_set_mode(struct musb *musb, u8 musb_mode)
 #endif
 
 	default:
-		DBG(2, "Trying to set unknown mode %i\n", musb_mode);
+		DBG(2, "Trying to set mode %i\n", musb_mode);
+		return -EINVAL;
 	}
 
 	musb_writel(tbase, TUSB_PHY_OTG_CTRL,
@@ -655,6 +656,8 @@ void musb_platform_set_mode(struct musb *musb, u8 musb_mode)
 		!(otg_stat & TUSB_DEV_OTG_STAT_ID_STATUS))
 			INFO("Cannot be peripheral with mini-A cable "
 			"otg_stat: %08x\n", otg_stat);
+
+	return 0;
 }
 
 static inline unsigned long
diff --git a/drivers/usb/otg/Kconfig b/drivers/usb/otg/Kconfig
new file mode 100644
index 000000000000..afe91bfea7f2
--- /dev/null
+++ b/drivers/usb/otg/Kconfig
@@ -0,0 +1,44 @@
+#
+# USB OTG infrastructure may be needed for peripheral-only, host-only,
+# or OTG-capable configurations when OTG transceivers or controllers
+# are used.
+#
+
+comment "OTG and related infrastructure"
+
+if USB || USB_GADGET
+
+config USB_OTG_UTILS
+	bool
+	help
+	  Select this to make sure the build includes objects from
+	  the OTG infrastructure directory.
+
+#
+# USB Transceiver Drivers
+#
+config USB_GPIO_VBUS
+	tristate "GPIO based peripheral-only VBUS sensing 'transceiver'"
+	depends on GENERIC_GPIO
+	select USB_OTG_UTILS
+	help
+	  Provides simple GPIO VBUS sensing for controllers with an
+	  internal transceiver via the otg_transceiver interface, and
+	  optionally control of a D+ pullup GPIO as well as a VBUS
+	  current limit regulator.
+
+config ISP1301_OMAP
+	tristate "Philips ISP1301 with OMAP OTG"
+	depends on I2C && ARCH_OMAP_OTG
+	select USB_OTG_UTILS
+	help
+	  If you say yes here you get support for the Philips ISP1301
+	  USB-On-The-Go transceiver working with the OMAP OTG controller.
+	  The ISP1301 is a full speed USB  transceiver which is used in
+	  products including H2, H3, and H4 development boards for Texas
+	  Instruments OMAP processors.
+
+	  This driver can also be built as a module.  If so, the module
+	  will be called isp1301_omap.
+
+endif # USB || OTG
diff --git a/drivers/usb/otg/Makefile b/drivers/usb/otg/Makefile
new file mode 100644
index 000000000000..7ceefc676fcb
--- /dev/null
+++ b/drivers/usb/otg/Makefile
@@ -0,0 +1,17 @@
+#
+# OTG infrastructure and transceiver drivers
+#
+
+# infrastructure
+obj-$(CONFIG_USB_OTG_UTILS)	+= otg.o
+
+# transceiver drivers
+obj-$(CONFIG_USB_GPIO_VBUS)	+= gpio_vbus.o
+obj-$(CONFIG_ISP1301_OMAP)	+= isp1301_omap.o
+
+ifeq ($(CONFIG_USB_DEBUG),y)
+EXTRA_CFLAGS += -DDEBUG
+else ifeq ($(CONFIG_USB_GADGET_DEBUG),y)
+EXTRA_CFLAGS += -DDEBUG
+endif
+
diff --git a/drivers/usb/otg/gpio_vbus.c b/drivers/usb/otg/gpio_vbus.c
new file mode 100644
index 000000000000..63a6036f04be
--- /dev/null
+++ b/drivers/usb/otg/gpio_vbus.c
@@ -0,0 +1,335 @@
+/*
+ * gpio-vbus.c - simple GPIO VBUS sensing driver for B peripheral devices
+ *
+ * Copyright (c) 2008 Philipp Zabel <philipp.zabel@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/kernel.h>
+#include <linux/platform_device.h>
+#include <linux/gpio.h>
+#include <linux/interrupt.h>
+#include <linux/usb.h>
+
+#include <linux/regulator/consumer.h>
+
+#include <linux/usb/gadget.h>
+#include <linux/usb/gpio_vbus.h>
+#include <linux/usb/otg.h>
+
+
+/*
+ * A simple GPIO VBUS sensing driver for B peripheral only devices
+ * with internal transceivers. It can control a D+ pullup GPIO and
+ * a regulator to limit the current drawn from VBUS.
+ *
+ * Needs to be loaded before the UDC driver that will use it.
+ */
+struct gpio_vbus_data {
+	struct otg_transceiver otg;
+	struct device          *dev;
+	struct regulator       *vbus_draw;
+	int			vbus_draw_enabled;
+	unsigned		mA;
+};
+
+
+/*
+ * This driver relies on "both edges" triggering.  VBUS has 100 msec to
+ * stabilize, so the peripheral controller driver may need to cope with
+ * some bouncing due to current surges (e.g. charging local capacitance)
+ * and contact chatter.
+ *
+ * REVISIT in desperate straits, toggling between rising and falling
+ * edges might be workable.
+ */
+#define VBUS_IRQ_FLAGS \
+	( IRQF_SAMPLE_RANDOM | IRQF_SHARED \
+	| IRQF_TRIGGER_RISING | IRQF_TRIGGER_FALLING )
+
+
+/* interface to regulator framework */
+static void set_vbus_draw(struct gpio_vbus_data *gpio_vbus, unsigned mA)
+{
+	struct regulator *vbus_draw = gpio_vbus->vbus_draw;
+	int enabled;
+
+	if (!vbus_draw)
+		return;
+
+	enabled = gpio_vbus->vbus_draw_enabled;
+	if (mA) {
+		regulator_set_current_limit(vbus_draw, 0, 1000 * mA);
+		if (!enabled) {
+			regulator_enable(vbus_draw);
+			gpio_vbus->vbus_draw_enabled = 1;
+		}
+	} else {
+		if (enabled) {
+			regulator_disable(vbus_draw);
+			gpio_vbus->vbus_draw_enabled = 0;
+		}
+	}
+	gpio_vbus->mA = mA;
+}
+
+/* VBUS change IRQ handler */
+static irqreturn_t gpio_vbus_irq(int irq, void *data)
+{
+	struct platform_device *pdev = data;
+	struct gpio_vbus_mach_info *pdata = pdev->dev.platform_data;
+	struct gpio_vbus_data *gpio_vbus = platform_get_drvdata(pdev);
+	int gpio, vbus;
+
+	vbus = gpio_get_value(pdata->gpio_vbus);
+	if (pdata->gpio_vbus_inverted)
+		vbus = !vbus;
+
+	dev_dbg(&pdev->dev, "VBUS %s (gadget: %s)\n",
+		vbus ? "supplied" : "inactive",
+		gpio_vbus->otg.gadget ? gpio_vbus->otg.gadget->name : "none");
+
+	if (!gpio_vbus->otg.gadget)
+		return IRQ_HANDLED;
+
+	/* Peripheral controllers which manage the pullup themselves won't have
+	 * gpio_pullup configured here.  If it's configured here, we'll do what
+	 * isp1301_omap::b_peripheral() does and enable the pullup here... although
+	 * that may complicate usb_gadget_{,dis}connect() support.
+	 */
+	gpio = pdata->gpio_pullup;
+	if (vbus) {
+		gpio_vbus->otg.state = OTG_STATE_B_PERIPHERAL;
+		usb_gadget_vbus_connect(gpio_vbus->otg.gadget);
+
+		/* drawing a "unit load" is *always* OK, except for OTG */
+		set_vbus_draw(gpio_vbus, 100);
+
+		/* optionally enable D+ pullup */
+		if (gpio_is_valid(gpio))
+			gpio_set_value(gpio, !pdata->gpio_pullup_inverted);
+	} else {
+		/* optionally disable D+ pullup */
+		if (gpio_is_valid(gpio))
+			gpio_set_value(gpio, pdata->gpio_pullup_inverted);
+
+		set_vbus_draw(gpio_vbus, 0);
+
+		usb_gadget_vbus_disconnect(gpio_vbus->otg.gadget);
+		gpio_vbus->otg.state = OTG_STATE_B_IDLE;
+	}
+
+	return IRQ_HANDLED;
+}
+
+/* OTG transceiver interface */
+
+/* bind/unbind the peripheral controller */
+static int gpio_vbus_set_peripheral(struct otg_transceiver *otg,
+				struct usb_gadget *gadget)
+{
+	struct gpio_vbus_data *gpio_vbus;
+	struct gpio_vbus_mach_info *pdata;
+	struct platform_device *pdev;
+	int gpio, irq;
+
+	gpio_vbus = container_of(otg, struct gpio_vbus_data, otg);
+	pdev = to_platform_device(gpio_vbus->dev);
+	pdata = gpio_vbus->dev->platform_data;
+	irq = gpio_to_irq(pdata->gpio_vbus);
+	gpio = pdata->gpio_pullup;
+
+	if (!gadget) {
+		dev_dbg(&pdev->dev, "unregistering gadget '%s'\n",
+			otg->gadget->name);
+
+		/* optionally disable D+ pullup */
+		if (gpio_is_valid(gpio))
+			gpio_set_value(gpio, pdata->gpio_pullup_inverted);
+
+		set_vbus_draw(gpio_vbus, 0);
+
+		usb_gadget_vbus_disconnect(otg->gadget);
+		otg->state = OTG_STATE_UNDEFINED;
+
+		otg->gadget = NULL;
+		return 0;
+	}
+
+	otg->gadget = gadget;
+	dev_dbg(&pdev->dev, "registered gadget '%s'\n", gadget->name);
+
+	/* initialize connection state */
+	gpio_vbus_irq(irq, pdev);
+	return 0;
+}
+
+/* effective for B devices, ignored for A-peripheral */
+static int gpio_vbus_set_power(struct otg_transceiver *otg, unsigned mA)
+{
+	struct gpio_vbus_data *gpio_vbus;
+
+	gpio_vbus = container_of(otg, struct gpio_vbus_data, otg);
+
+	if (otg->state == OTG_STATE_B_PERIPHERAL)
+		set_vbus_draw(gpio_vbus, mA);
+	return 0;
+}
+
+/* for non-OTG B devices: set/clear transceiver suspend mode */
+static int gpio_vbus_set_suspend(struct otg_transceiver *otg, int suspend)
+{
+	struct gpio_vbus_data *gpio_vbus;
+
+	gpio_vbus = container_of(otg, struct gpio_vbus_data, otg);
+
+	/* draw max 0 mA from vbus in suspend mode; or the previously
+	 * recorded amount of current if not suspended
+	 *
+	 * NOTE: high powered configs (mA > 100) may draw up to 2.5 mA
+	 * if they're wake-enabled ... we don't handle that yet.
+	 */
+	return gpio_vbus_set_power(otg, suspend ? 0 : gpio_vbus->mA);
+}
+
+/* platform driver interface */
+
+static int __init gpio_vbus_probe(struct platform_device *pdev)
+{
+	struct gpio_vbus_mach_info *pdata = pdev->dev.platform_data;
+	struct gpio_vbus_data *gpio_vbus;
+	struct resource *res;
+	int err, gpio, irq;
+
+	if (!pdata || !gpio_is_valid(pdata->gpio_vbus))
+		return -EINVAL;
+	gpio = pdata->gpio_vbus;
+
+	gpio_vbus = kzalloc(sizeof(struct gpio_vbus_data), GFP_KERNEL);
+	if (!gpio_vbus)
+		return -ENOMEM;
+
+	platform_set_drvdata(pdev, gpio_vbus);
+	gpio_vbus->dev = &pdev->dev;
+	gpio_vbus->otg.label = "gpio-vbus";
+	gpio_vbus->otg.state = OTG_STATE_UNDEFINED;
+	gpio_vbus->otg.set_peripheral = gpio_vbus_set_peripheral;
+	gpio_vbus->otg.set_power = gpio_vbus_set_power;
+	gpio_vbus->otg.set_suspend = gpio_vbus_set_suspend;
+
+	err = gpio_request(gpio, "vbus_detect");
+	if (err) {
+		dev_err(&pdev->dev, "can't request vbus gpio %d, err: %d\n",
+			gpio, err);
+		goto err_gpio;
+	}
+	gpio_direction_input(gpio);
+
+	res = platform_get_resource(pdev, IORESOURCE_IRQ, 0);
+	if (res) {
+		irq = res->start;
+		res->flags &= IRQF_TRIGGER_MASK;
+		res->flags |= IRQF_SAMPLE_RANDOM | IRQF_SHARED;
+	} else
+		irq = gpio_to_irq(gpio);
+
+	/* if data line pullup is in use, initialize it to "not pulling up" */
+	gpio = pdata->gpio_pullup;
+	if (gpio_is_valid(gpio)) {
+		err = gpio_request(gpio, "udc_pullup");
+		if (err) {
+			dev_err(&pdev->dev,
+				"can't request pullup gpio %d, err: %d\n",
+				gpio, err);
+			gpio_free(pdata->gpio_vbus);
+			goto err_gpio;
+		}
+		gpio_direction_output(gpio, pdata->gpio_pullup_inverted);
+	}
+
+	err = request_irq(irq, gpio_vbus_irq, VBUS_IRQ_FLAGS,
+		"vbus_detect", pdev);
+	if (err) {
+		dev_err(&pdev->dev, "can't request irq %i, err: %d\n",
+			irq, err);
+		goto err_irq;
+	}
+
+	/* only active when a gadget is registered */
+	err = otg_set_transceiver(&gpio_vbus->otg);
+	if (err) {
+		dev_err(&pdev->dev, "can't register transceiver, err: %d\n",
+			err);
+		goto err_otg;
+	}
+
+	gpio_vbus->vbus_draw = regulator_get(&pdev->dev, "vbus_draw");
+	if (IS_ERR(gpio_vbus->vbus_draw)) {
+		dev_dbg(&pdev->dev, "can't get vbus_draw regulator, err: %ld\n",
+			PTR_ERR(gpio_vbus->vbus_draw));
+		gpio_vbus->vbus_draw = NULL;
+	}
+
+	return 0;
+err_otg:
+	free_irq(irq, &pdev->dev);
+err_irq:
+	if (gpio_is_valid(pdata->gpio_pullup))
+		gpio_free(pdata->gpio_pullup);
+	gpio_free(pdata->gpio_vbus);
+err_gpio:
+	platform_set_drvdata(pdev, NULL);
+	kfree(gpio_vbus);
+	return err;
+}
+
+static int __exit gpio_vbus_remove(struct platform_device *pdev)
+{
+	struct gpio_vbus_data *gpio_vbus = platform_get_drvdata(pdev);
+	struct gpio_vbus_mach_info *pdata = pdev->dev.platform_data;
+	int gpio = pdata->gpio_vbus;
+
+	regulator_put(gpio_vbus->vbus_draw);
+
+	otg_set_transceiver(NULL);
+
+	free_irq(gpio_to_irq(gpio), &pdev->dev);
+	if (gpio_is_valid(pdata->gpio_pullup))
+		gpio_free(pdata->gpio_pullup);
+	gpio_free(gpio);
+	platform_set_drvdata(pdev, NULL);
+	kfree(gpio_vbus);
+
+	return 0;
+}
+
+/* NOTE:  the gpio-vbus device may *NOT* be hotplugged */
+
+MODULE_ALIAS("platform:gpio-vbus");
+
+static struct platform_driver gpio_vbus_driver = {
+	.driver = {
+		.name  = "gpio-vbus",
+		.owner = THIS_MODULE,
+	},
+	.remove  = __exit_p(gpio_vbus_remove),
+};
+
+static int __init gpio_vbus_init(void)
+{
+	return platform_driver_probe(&gpio_vbus_driver, gpio_vbus_probe);
+}
+module_init(gpio_vbus_init);
+
+static void __exit gpio_vbus_exit(void)
+{
+	platform_driver_unregister(&gpio_vbus_driver);
+}
+module_exit(gpio_vbus_exit);
+
+MODULE_DESCRIPTION("simple GPIO controlled OTG transceiver driver");
+MODULE_AUTHOR("Philipp Zabel");
+MODULE_LICENSE("GPL");
diff --git a/drivers/i2c/chips/isp1301_omap.c b/drivers/usb/otg/isp1301_omap.c
index e0d56ef2bcb0..e0d56ef2bcb0 100644
--- a/drivers/i2c/chips/isp1301_omap.c
+++ b/drivers/usb/otg/isp1301_omap.c
diff --git a/drivers/usb/otg/otg.c b/drivers/usb/otg/otg.c
new file mode 100644
index 000000000000..019d775291d1
--- /dev/null
+++ b/drivers/usb/otg/otg.c
@@ -0,0 +1,59 @@
+/*
+ * otg.c -- USB OTG utility code
+ *
+ * Copyright (C) 2004 Texas Instruments
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <linux/kernel.h>
+#include <linux/device.h>
+
+#include <linux/usb/otg.h>
+
+static struct otg_transceiver *xceiv;
+
+/**
+ * otg_get_transceiver - find the (single) OTG transceiver driver
+ *
+ * Returns the transceiver driver, after getting a refcount to it; or
+ * null if there is no such transceiver.  The caller is responsible for
+ * calling otg_put_transceiver() to release that count.
+ */
+struct otg_transceiver *otg_get_transceiver(void)
+{
+	if (xceiv)
+		get_device(xceiv->dev);
+	return xceiv;
+}
+EXPORT_SYMBOL(otg_get_transceiver);
+
+/**
+ * otg_put_transceiver - release the (single) OTG transceiver driver
+ * @x: the transceiver returned by otg_get_transceiver()
+ *
+ * Releases a refcount the caller received from otg_get_transceiver().
+ */
+void otg_put_transceiver(struct otg_transceiver *x)
+{
+	put_device(x->dev);
+}
+EXPORT_SYMBOL(otg_put_transceiver);
+
+/**
+ * otg_set_transceiver - release the (single) OTG transceiver driver
+ * @x: the USB OTG transceiver to be used; or NULL
+ *
+ * This call is exclusively for use by transceiver drivers.
+ */
+int otg_set_transceiver(struct otg_transceiver *x)
+{
+	if (xceiv && x)
+		return -EBUSY;
+	xceiv = x;
+	return 0;
+}
+EXPORT_SYMBOL(otg_set_transceiver);
diff --git a/drivers/usb/serial/Kconfig b/drivers/usb/serial/Kconfig
index 70338f4ec918..b361f05cafac 100644
--- a/drivers/usb/serial/Kconfig
+++ b/drivers/usb/serial/Kconfig
@@ -496,6 +496,14 @@ config USB_SERIAL_SAFE_PADDED
 	bool "USB Secure Encapsulated Driver - Padded"
 	depends on USB_SERIAL_SAFE
 
+config USB_SERIAL_SIEMENS_MPI
+	tristate "USB Siemens MPI driver"
+	help
+	  Say M here if you want to use a Siemens USB/MPI adapter.
+
+	  To compile this driver as a module, choose M here: the
+	  module will be called siemens_mpi.
+
 config USB_SERIAL_SIERRAWIRELESS
 	tristate "USB Sierra Wireless Driver"
 	help
@@ -565,6 +573,15 @@ config USB_SERIAL_OMNINET
 	  To compile this driver as a module, choose M here: the
 	  module will be called omninet.
 
+config USB_SERIAL_OPTICON
+	tristate "USB Opticon Barcode driver (serial mode)"
+	help
+	  Say Y here if you want to use a Opticon USB Barcode device
+	  in serial emulation mode.
+
+	  To compile this driver as a module, choose M here: the
+	  module will be called opticon.
+
 config USB_SERIAL_DEBUG
 	tristate "USB Debugging Device"
 	help
diff --git a/drivers/usb/serial/Makefile b/drivers/usb/serial/Makefile
index 6047f818adfe..b75be91eb8f1 100644
--- a/drivers/usb/serial/Makefile
+++ b/drivers/usb/serial/Makefile
@@ -41,10 +41,12 @@ obj-$(CONFIG_USB_SERIAL_MOS7840)		+= mos7840.o
 obj-$(CONFIG_USB_SERIAL_MOTOROLA)		+= moto_modem.o
 obj-$(CONFIG_USB_SERIAL_NAVMAN)			+= navman.o
 obj-$(CONFIG_USB_SERIAL_OMNINET)		+= omninet.o
+obj-$(CONFIG_USB_SERIAL_OPTICON)		+= opticon.o
 obj-$(CONFIG_USB_SERIAL_OPTION)			+= option.o
 obj-$(CONFIG_USB_SERIAL_OTI6858)		+= oti6858.o
 obj-$(CONFIG_USB_SERIAL_PL2303)			+= pl2303.o
 obj-$(CONFIG_USB_SERIAL_SAFE)			+= safe_serial.o
+obj-$(CONFIG_USB_SERIAL_SIEMENS_MPI)		+= siemens_mpi.o
 obj-$(CONFIG_USB_SERIAL_SIERRAWIRELESS)		+= sierra.o
 obj-$(CONFIG_USB_SERIAL_SPCP8X5)		+= spcp8x5.o
 obj-$(CONFIG_USB_SERIAL_TI)			+= ti_usb_3410_5052.o
diff --git a/drivers/usb/serial/ftdi_sio.c b/drivers/usb/serial/ftdi_sio.c
index 51d7bdea2869..aad1359a3eb1 100644
--- a/drivers/usb/serial/ftdi_sio.c
+++ b/drivers/usb/serial/ftdi_sio.c
@@ -1498,7 +1498,7 @@ static int ftdi_open(struct tty_struct *tty,
 			priv->interface, buf, 0, WDR_TIMEOUT);
 
 	/* Termios defaults are set by usb_serial_init. We don't change
-	   port->tty->termios - this would loose speed settings, etc.
+	   port->tty->termios - this would lose speed settings, etc.
 	   This is same behaviour as serial.c/rs_open() - Kuba */
 
 	/* ftdi_set_termios  will send usb control messages */
diff --git a/drivers/usb/serial/ipw.c b/drivers/usb/serial/ipw.c
index 3ac59a8a980f..f530032ed93d 100644
--- a/drivers/usb/serial/ipw.c
+++ b/drivers/usb/serial/ipw.c
@@ -473,7 +473,7 @@ static struct usb_serial_driver ipw_device = {
 
 
 
-static int usb_ipw_init(void)
+static int __init usb_ipw_init(void)
 {
 	int retval;
 
@@ -490,7 +490,7 @@ static int usb_ipw_init(void)
 	return 0;
 }
 
-static void usb_ipw_exit(void)
+static void __exit usb_ipw_exit(void)
 {
 	usb_deregister(&usb_ipw_driver);
 	usb_serial_deregister(&ipw_device);
diff --git a/drivers/usb/serial/opticon.c b/drivers/usb/serial/opticon.c
new file mode 100644
index 000000000000..cea326f1f105
--- /dev/null
+++ b/drivers/usb/serial/opticon.c
@@ -0,0 +1,358 @@
+/*
+ * Opticon USB barcode to serial driver
+ *
+ * Copyright (C) 2008 Greg Kroah-Hartman <gregkh@suse.de>
+ * Copyright (C) 2008 Novell Inc.
+ *
+ *	This program is free software; you can redistribute it and/or
+ *	modify it under the terms of the GNU General Public License version
+ *	2 as published by the Free Software Foundation.
+ */
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/tty.h>
+#include <linux/tty_driver.h>
+#include <linux/tty_flip.h>
+#include <linux/module.h>
+#include <linux/usb.h>
+#include <linux/usb/serial.h>
+#include <linux/uaccess.h>
+
+static int debug;
+
+static struct usb_device_id id_table[] = {
+	{ USB_DEVICE(0x065a, 0x0009) },
+	{ },
+};
+MODULE_DEVICE_TABLE(usb, id_table);
+
+/* This structure holds all of the individual device information */
+struct opticon_private {
+	struct usb_device *udev;
+	struct usb_serial *serial;
+	struct usb_serial_port *port;
+	unsigned char *bulk_in_buffer;
+	struct urb *bulk_read_urb;
+	int buffer_size;
+	u8 bulk_address;
+	spinlock_t lock;	/* protects the following flags */
+	bool throttled;
+	bool actually_throttled;
+	bool rts;
+};
+
+static void opticon_bulk_callback(struct urb *urb)
+{
+	struct opticon_private *priv = urb->context;
+	unsigned char *data = urb->transfer_buffer;
+	struct usb_serial_port *port = priv->port;
+	int status = urb->status;
+	struct tty_struct *tty;
+	int result;
+	int available_room = 0;
+	int data_length;
+
+	dbg("%s - port %d", __func__, port->number);
+
+	switch (status) {
+	case 0:
+		/* success */
+		break;
+	case -ECONNRESET:
+	case -ENOENT:
+	case -ESHUTDOWN:
+		/* this urb is terminated, clean up */
+		dbg("%s - urb shutting down with status: %d",
+		    __func__, status);
+		return;
+	default:
+		dbg("%s - nonzero urb status received: %d",
+		    __func__, status);
+		goto exit;
+	}
+
+	usb_serial_debug_data(debug, &port->dev, __func__, urb->actual_length,
+			      data);
+
+	if (urb->actual_length > 2) {
+		data_length = urb->actual_length - 2;
+
+		/*
+		 * Data from the device comes with a 2 byte header:
+		 *
+		 * <0x00><0x00>data...
+		 * 	This is real data to be sent to the tty layer
+		 * <0x00><0x01)level
+		 * 	This is a RTS level change, the third byte is the RTS
+		 * 	value (0 for low, 1 for high).
+		 */
+		if ((data[0] == 0x00) && (data[1] == 0x00)) {
+			/* real data, send it to the tty layer */
+			tty = tty_port_tty_get(&port->port);
+			if (tty) {
+				available_room = tty_buffer_request_room(tty,
+								data_length);
+				if (available_room) {
+					tty_insert_flip_string(tty, data,
+							       available_room);
+					tty_flip_buffer_push(tty);
+				}
+				tty_kref_put(tty);
+			}
+		} else {
+			if ((data[0] == 0x00) && (data[1] == 0x01)) {
+				if (data[2] == 0x00)
+					priv->rts = false;
+				else
+					priv->rts = true;
+				/* FIXME change the RTS level */
+			} else {
+			dev_dbg(&priv->udev->dev,
+				"Unknown data packet received from the device:"
+				" %2x %2x\n",
+				data[0], data[1]);
+			}
+		}
+	} else {
+		dev_dbg(&priv->udev->dev,
+			"Improper ammount of data received from the device, "
+			"%d bytes", urb->actual_length);
+	}
+
+exit:
+	spin_lock(&priv->lock);
+
+	/* Continue trying to always read if we should */
+	if (!priv->throttled) {
+		usb_fill_bulk_urb(priv->bulk_read_urb, priv->udev,
+				  usb_rcvbulkpipe(priv->udev,
+						  priv->bulk_address),
+				  priv->bulk_in_buffer, priv->buffer_size,
+				  opticon_bulk_callback, priv);
+		result = usb_submit_urb(port->read_urb, GFP_ATOMIC);
+		if (result)
+			dev_err(&port->dev,
+			    "%s - failed resubmitting read urb, error %d\n",
+							__func__, result);
+	} else
+		priv->actually_throttled = true;
+	spin_unlock(&priv->lock);
+}
+
+static int opticon_open(struct tty_struct *tty, struct usb_serial_port *port,
+			struct file *filp)
+{
+	struct opticon_private *priv = usb_get_serial_data(port->serial);
+	unsigned long flags;
+	int result = 0;
+
+	dbg("%s - port %d", __func__, port->number);
+
+	spin_lock_irqsave(&priv->lock, flags);
+	priv->throttled = false;
+	priv->actually_throttled = false;
+	priv->port = port;
+	spin_unlock_irqrestore(&priv->lock, flags);
+
+	/*
+	 * Force low_latency on so that our tty_push actually forces the data
+	 * through, otherwise it is scheduled, and with high data rates (like
+	 * with OHCI) data can get lost.
+	 */
+	if (tty)
+		tty->low_latency = 1;
+
+	/* Start reading from the device */
+	usb_fill_bulk_urb(priv->bulk_read_urb, priv->udev,
+			  usb_rcvbulkpipe(priv->udev,
+					  priv->bulk_address),
+			  priv->bulk_in_buffer, priv->buffer_size,
+			  opticon_bulk_callback, priv);
+	result = usb_submit_urb(priv->bulk_read_urb, GFP_KERNEL);
+	if (result)
+		dev_err(&port->dev,
+			"%s - failed resubmitting read urb, error %d\n",
+			__func__, result);
+	return result;
+}
+
+static void opticon_close(struct tty_struct *tty, struct usb_serial_port *port,
+			  struct file *filp)
+{
+	struct opticon_private *priv = usb_get_serial_data(port->serial);
+
+	dbg("%s - port %d", __func__, port->number);
+
+	/* shutdown our urbs */
+	usb_kill_urb(priv->bulk_read_urb);
+}
+
+static void opticon_throttle(struct tty_struct *tty)
+{
+	struct usb_serial_port *port = tty->driver_data;
+	struct opticon_private *priv = usb_get_serial_data(port->serial);
+	unsigned long flags;
+
+	dbg("%s - port %d", __func__, port->number);
+	spin_lock_irqsave(&priv->lock, flags);
+	priv->throttled = true;
+	spin_unlock_irqrestore(&priv->lock, flags);
+}
+
+
+static void opticon_unthrottle(struct tty_struct *tty)
+{
+	struct usb_serial_port *port = tty->driver_data;
+	struct opticon_private *priv = usb_get_serial_data(port->serial);
+	unsigned long flags;
+	int result;
+
+	dbg("%s - port %d", __func__, port->number);
+
+	spin_lock_irqsave(&priv->lock, flags);
+	priv->throttled = false;
+	priv->actually_throttled = false;
+	spin_unlock_irqrestore(&priv->lock, flags);
+
+	priv->bulk_read_urb->dev = port->serial->dev;
+	result = usb_submit_urb(priv->bulk_read_urb, GFP_ATOMIC);
+	if (result)
+		dev_err(&port->dev,
+			"%s - failed submitting read urb, error %d\n",
+							__func__, result);
+}
+
+static int opticon_startup(struct usb_serial *serial)
+{
+	struct opticon_private *priv;
+	struct usb_host_interface *intf;
+	int i;
+	int retval = -ENOMEM;
+	bool bulk_in_found = false;
+
+	/* create our private serial structure */
+	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
+	if (priv == NULL) {
+		dev_err(&serial->dev->dev, "%s - Out of memory\n", __func__);
+		return -ENOMEM;
+	}
+	spin_lock_init(&priv->lock);
+	priv->serial = serial;
+	priv->port = serial->port[0];
+	priv->udev = serial->dev;
+
+	/* find our bulk endpoint */
+	intf = serial->interface->altsetting;
+	for (i = 0; i < intf->desc.bNumEndpoints; ++i) {
+		struct usb_endpoint_descriptor *endpoint;
+
+		endpoint = &intf->endpoint[i].desc;
+		if (!usb_endpoint_is_bulk_in(endpoint))
+			continue;
+
+		priv->bulk_read_urb = usb_alloc_urb(0, GFP_KERNEL);
+		if (!priv->bulk_read_urb) {
+			dev_err(&priv->udev->dev, "out of memory\n");
+			goto error;
+		}
+
+		priv->buffer_size = le16_to_cpu(endpoint->wMaxPacketSize) * 2;
+		priv->bulk_in_buffer = kmalloc(priv->buffer_size, GFP_KERNEL);
+		if (!priv->bulk_in_buffer) {
+			dev_err(&priv->udev->dev, "out of memory\n");
+			goto error;
+		}
+
+		priv->bulk_address = endpoint->bEndpointAddress;
+
+		/* set up our bulk urb */
+		usb_fill_bulk_urb(priv->bulk_read_urb, priv->udev,
+				  usb_rcvbulkpipe(priv->udev,
+						  endpoint->bEndpointAddress),
+				  priv->bulk_in_buffer, priv->buffer_size,
+				  opticon_bulk_callback, priv);
+
+		bulk_in_found = true;
+		break;
+		}
+
+	if (!bulk_in_found) {
+		dev_err(&priv->udev->dev,
+			"Error - the proper endpoints were not found!\n");
+		goto error;
+	}
+
+	usb_set_serial_data(serial, priv);
+	return 0;
+
+error:
+	usb_free_urb(priv->bulk_read_urb);
+	kfree(priv->bulk_in_buffer);
+	kfree(priv);
+	return retval;
+}
+
+static void opticon_shutdown(struct usb_serial *serial)
+{
+	struct opticon_private *priv = usb_get_serial_data(serial);
+
+	dbg("%s", __func__);
+
+	usb_kill_urb(priv->bulk_read_urb);
+	usb_free_urb(priv->bulk_read_urb);
+	kfree(priv->bulk_in_buffer);
+	kfree(priv);
+	usb_set_serial_data(serial, NULL);
+}
+
+
+static struct usb_driver opticon_driver = {
+	.name =		"opticon",
+	.probe =	usb_serial_probe,
+	.disconnect =	usb_serial_disconnect,
+	.id_table =	id_table,
+	.no_dynamic_id = 	1,
+};
+
+static struct usb_serial_driver opticon_device = {
+	.driver = {
+		.owner =	THIS_MODULE,
+		.name =		"opticon",
+	},
+	.id_table =		id_table,
+	.usb_driver = 		&opticon_driver,
+	.num_ports =		1,
+	.attach =		opticon_startup,
+	.open =			opticon_open,
+	.close =		opticon_close,
+	.shutdown =		opticon_shutdown,
+	.throttle = 		opticon_throttle,
+	.unthrottle =		opticon_unthrottle,
+};
+
+static int __init opticon_init(void)
+{
+	int retval;
+
+	retval = usb_serial_register(&opticon_device);
+	if (retval)
+		return retval;
+	retval = usb_register(&opticon_driver);
+	if (retval)
+		usb_serial_deregister(&opticon_device);
+	return retval;
+}
+
+static void __exit opticon_exit(void)
+{
+	usb_deregister(&opticon_driver);
+	usb_serial_deregister(&opticon_device);
+}
+
+module_init(opticon_init);
+module_exit(opticon_exit);
+MODULE_LICENSE("GPL");
+
+module_param(debug, bool, S_IRUGO | S_IWUSR);
+MODULE_PARM_DESC(debug, "Debug enabled or not");
diff --git a/drivers/usb/serial/siemens_mpi.c b/drivers/usb/serial/siemens_mpi.c
new file mode 100644
index 000000000000..951ea0c6ba77
--- /dev/null
+++ b/drivers/usb/serial/siemens_mpi.c
@@ -0,0 +1,77 @@
+/*
+ * Siemens USB-MPI Serial USB driver
+ *
+ * Copyright (C) 2005 Thomas Hergenhahn <thomas.hergenhahn@suse.de>
+ * Copyright (C) 2005,2008 Greg Kroah-Hartman <gregkh@suse.de>
+ *
+ *	This program is free software; you can redistribute it and/or
+ *	modify it under the terms of the GNU General Public License version
+ *	2 as published by the Free Software Foundation.
+ */
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/tty.h>
+#include <linux/module.h>
+#include <linux/usb.h>
+#include <linux/usb/serial.h>
+
+/* Version Information */
+#define DRIVER_VERSION "Version 0.1 09/26/2005"
+#define DRIVER_AUTHOR "Thomas Hergenhahn@web.de http://libnodave.sf.net"
+#define DRIVER_DESC "Driver for Siemens USB/MPI adapter"
+
+
+static struct usb_device_id id_table[] = {
+	/* Vendor and product id for 6ES7-972-0CB20-0XA0 */
+	{ USB_DEVICE(0x908, 0x0004) },
+	{ },
+};
+MODULE_DEVICE_TABLE(usb, id_table);
+
+static struct usb_driver siemens_usb_mpi_driver = {
+	.name =		"siemens_mpi",
+	.probe =	usb_serial_probe,
+	.disconnect =	usb_serial_disconnect,
+	.id_table =	id_table,
+};
+
+static struct usb_serial_driver siemens_usb_mpi_device = {
+	.driver = {
+		.owner =	THIS_MODULE,
+		.name =		"siemens_mpi",
+	},
+	.id_table =		id_table,
+	.num_ports =		1,
+};
+
+static int __init siemens_usb_mpi_init(void)
+{
+	int retval;
+
+	retval = usb_serial_register(&siemens_usb_mpi_device);
+	if (retval)
+		goto failed_usb_serial_register;
+	retval = usb_register(&siemens_usb_mpi_driver);
+	if (retval)
+		goto failed_usb_register;
+	printk(KERN_INFO DRIVER_DESC "\n");
+	printk(KERN_INFO DRIVER_VERSION " " DRIVER_AUTHOR "\n");
+	return retval;
+failed_usb_register:
+	usb_serial_deregister(&siemens_usb_mpi_device);
+failed_usb_serial_register:
+	return retval;
+}
+
+static void __exit siemens_usb_mpi_exit(void)
+{
+	usb_deregister(&siemens_usb_mpi_driver);
+	usb_serial_deregister(&siemens_usb_mpi_device);
+}
+
+module_init(siemens_usb_mpi_init);
+module_exit(siemens_usb_mpi_exit);
+MODULE_AUTHOR(DRIVER_AUTHOR);
+MODULE_DESCRIPTION(DRIVER_DESC);
+MODULE_LICENSE("GPL");
diff --git a/drivers/usb/storage/protocol.c b/drivers/usb/storage/protocol.c
index 3b3357e20ea7..be441d84bc64 100644
--- a/drivers/usb/storage/protocol.c
+++ b/drivers/usb/storage/protocol.c
@@ -56,9 +56,9 @@
  * Protocol routines
  ***********************************************************************/
 
-void usb_stor_qic157_command(struct scsi_cmnd *srb, struct us_data *us)
+void usb_stor_pad12_command(struct scsi_cmnd *srb, struct us_data *us)
 {
-	/* Pad the ATAPI command with zeros 
+	/* Pad the SCSI command with zeros out to 12 bytes
 	 *
 	 * NOTE: This only works because a scsi_cmnd struct field contains
 	 * a unsigned char cmnd[16], so we know we have storage available
@@ -73,26 +73,6 @@ void usb_stor_qic157_command(struct scsi_cmnd *srb, struct us_data *us)
 	usb_stor_invoke_transport(srb, us);
 }
 
-void usb_stor_ATAPI_command(struct scsi_cmnd *srb, struct us_data *us)
-{
-	/* Pad the ATAPI command with zeros 
-	 *
-	 * NOTE: This only works because a scsi_cmnd struct field contains
-	 * a unsigned char cmnd[16], so we know we have storage available
-	 */
-
-	/* Pad the ATAPI command with zeros */
-	for (; srb->cmd_len<12; srb->cmd_len++)
-		srb->cmnd[srb->cmd_len] = 0;
-
-	/* set command length to 12 bytes */
-	srb->cmd_len = 12;
-
-	/* send the command to the transport layer */
-	usb_stor_invoke_transport(srb, us);
-}
-
-
 void usb_stor_ufi_command(struct scsi_cmnd *srb, struct us_data *us)
 {
 	/* fix some commands -- this is a form of mode translation
diff --git a/drivers/usb/storage/protocol.h b/drivers/usb/storage/protocol.h
index 487056ffb516..ffc3e2af0156 100644
--- a/drivers/usb/storage/protocol.h
+++ b/drivers/usb/storage/protocol.h
@@ -40,8 +40,7 @@
 #define _PROTOCOL_H_
 
 /* Protocol handling routines */
-extern void usb_stor_ATAPI_command(struct scsi_cmnd*, struct us_data*);
-extern void usb_stor_qic157_command(struct scsi_cmnd*, struct us_data*);
+extern void usb_stor_pad12_command(struct scsi_cmnd*, struct us_data*);
 extern void usb_stor_ufi_command(struct scsi_cmnd*, struct us_data*);
 extern void usb_stor_transparent_scsi_command(struct scsi_cmnd*,
 		struct us_data*);
diff --git a/drivers/usb/storage/scsiglue.c b/drivers/usb/storage/scsiglue.c
index 09779f6a8179..e9d6c196a7ab 100644
--- a/drivers/usb/storage/scsiglue.c
+++ b/drivers/usb/storage/scsiglue.c
@@ -129,6 +129,14 @@ static int slave_configure(struct scsi_device *sdev)
 					      max_sectors);
 	}
 
+	/* Some USB host controllers can't do DMA; they have to use PIO.
+	 * They indicate this by setting their dma_mask to NULL.  For
+	 * such controllers we need to make sure the block layer sets
+	 * up bounce buffers in addressable memory.
+	 */
+	if (!us->pusb_dev->bus->controller->dma_mask)
+		blk_queue_bounce_limit(sdev->request_queue, BLK_BOUNCE_HIGH);
+
 	/* We can't put these settings in slave_alloc() because that gets
 	 * called before the device type is known.  Consequently these
 	 * settings can't be overridden via the scsi devinfo mechanism. */
@@ -170,6 +178,10 @@ static int slave_configure(struct scsi_device *sdev)
 		if (us->fflags & US_FL_CAPACITY_HEURISTICS)
 			sdev->guess_capacity = 1;
 
+		/* assume SPC3 or latter devices support sense size > 18 */
+		if (sdev->scsi_level > SCSI_SPC_2)
+			us->fflags |= US_FL_SANE_SENSE;
+
 		/* Some devices report a SCSI revision level above 2 but are
 		 * unable to handle the REPORT LUNS command (for which
 		 * support is mandatory at level 3).  Since we already have
diff --git a/drivers/usb/storage/transport.c b/drivers/usb/storage/transport.c
index 79108d5d3171..9cc30afd6d31 100644
--- a/drivers/usb/storage/transport.c
+++ b/drivers/usb/storage/transport.c
@@ -579,6 +579,20 @@ void usb_stor_invoke_transport(struct scsi_cmnd *srb, struct us_data *us)
 	}
 
 	/*
+	 * Determine if this device is SAT by seeing if the
+	 * command executed successfully.  Otherwise we'll have
+	 * to wait for at least one CHECK_CONDITION to determine
+	 * SANE_SENSE support
+	 */
+	if ((srb->cmnd[0] == ATA_16 || srb->cmnd[0] == ATA_12) &&
+	    result == USB_STOR_TRANSPORT_GOOD &&
+	    !(us->fflags & US_FL_SANE_SENSE) &&
+	    !(srb->cmnd[2] & 0x20)) {
+		US_DEBUGP("-- SAT supported, increasing auto-sense\n");
+		us->fflags |= US_FL_SANE_SENSE;
+	}
+
+	/*
 	 * A short transfer on a command where we don't expect it
 	 * is unusual, but it doesn't mean we need to auto-sense.
 	 */
@@ -595,10 +609,15 @@ void usb_stor_invoke_transport(struct scsi_cmnd *srb, struct us_data *us)
 	if (need_auto_sense) {
 		int temp_result;
 		struct scsi_eh_save ses;
+		int sense_size = US_SENSE_SIZE;
+
+		/* device supports and needs bigger sense buffer */
+		if (us->fflags & US_FL_SANE_SENSE)
+			sense_size = ~0;
 
 		US_DEBUGP("Issuing auto-REQUEST_SENSE\n");
 
-		scsi_eh_prep_cmnd(srb, &ses, NULL, 0, US_SENSE_SIZE);
+		scsi_eh_prep_cmnd(srb, &ses, NULL, 0, sense_size);
 
 		/* FIXME: we must do the protocol translation here */
 		if (us->subclass == US_SC_RBC || us->subclass == US_SC_SCSI ||
@@ -632,6 +651,25 @@ void usb_stor_invoke_transport(struct scsi_cmnd *srb, struct us_data *us)
 			return;
 		}
 
+		/* If the sense data returned is larger than 18-bytes then we
+		 * assume this device supports requesting more in the future.
+		 * The response code must be 70h through 73h inclusive.
+		 */
+		if (srb->sense_buffer[7] > (US_SENSE_SIZE - 8) &&
+		    !(us->fflags & US_FL_SANE_SENSE) &&
+		    (srb->sense_buffer[0] & 0x7C) == 0x70) {
+			US_DEBUGP("-- SANE_SENSE support enabled\n");
+			us->fflags |= US_FL_SANE_SENSE;
+
+			/* Indicate to the user that we truncated their sense
+			 * because we didn't know it supported larger sense.
+			 */
+			US_DEBUGP("-- Sense data truncated to %i from %i\n",
+			          US_SENSE_SIZE,
+			          srb->sense_buffer[7] + 8);
+			srb->sense_buffer[7] = (US_SENSE_SIZE - 8);
+		}
+
 		US_DEBUGP("-- Result from auto-sense is %d\n", temp_result);
 		US_DEBUGP("-- code: 0x%x, key: 0x%x, ASC: 0x%x, ASCQ: 0x%x\n",
 			  srb->sense_buffer[0],
@@ -718,10 +756,10 @@ void usb_stor_stop_transport(struct us_data *us)
 }
 
 /*
- * Control/Bulk/Interrupt transport
+ * Control/Bulk and Control/Bulk/Interrupt transport
  */
 
-int usb_stor_CBI_transport(struct scsi_cmnd *srb, struct us_data *us)
+int usb_stor_CB_transport(struct scsi_cmnd *srb, struct us_data *us)
 {
 	unsigned int transfer_length = scsi_bufflen(srb);
 	unsigned int pipe = 0;
@@ -763,6 +801,13 @@ int usb_stor_CBI_transport(struct scsi_cmnd *srb, struct us_data *us)
 	}
 
 	/* STATUS STAGE */
+
+	/* NOTE: CB does not have a status stage.  Silly, I know.  So
+	 * we have to catch this at a higher level.
+	 */
+	if (us->protocol != US_PR_CBI)
+		return USB_STOR_TRANSPORT_GOOD;
+
 	result = usb_stor_intr_transfer(us, us->iobuf, 2);
 	US_DEBUGP("Got interrupt data (0x%x, 0x%x)\n", 
 			us->iobuf[0], us->iobuf[1]);
@@ -817,56 +862,6 @@ int usb_stor_CBI_transport(struct scsi_cmnd *srb, struct us_data *us)
 }
 
 /*
- * Control/Bulk transport
- */
-int usb_stor_CB_transport(struct scsi_cmnd *srb, struct us_data *us)
-{
-	unsigned int transfer_length = scsi_bufflen(srb);
-	int result;
-
-	/* COMMAND STAGE */
-	/* let's send the command via the control pipe */
-	result = usb_stor_ctrl_transfer(us, us->send_ctrl_pipe,
-				      US_CBI_ADSC, 
-				      USB_TYPE_CLASS | USB_RECIP_INTERFACE, 0, 
-				      us->ifnum, srb->cmnd, srb->cmd_len);
-
-	/* check the return code for the command */
-	US_DEBUGP("Call to usb_stor_ctrl_transfer() returned %d\n", result);
-
-	/* if we stalled the command, it means command failed */
-	if (result == USB_STOR_XFER_STALLED) {
-		return USB_STOR_TRANSPORT_FAILED;
-	}
-
-	/* Uh oh... serious problem here */
-	if (result != USB_STOR_XFER_GOOD) {
-		return USB_STOR_TRANSPORT_ERROR;
-	}
-
-	/* DATA STAGE */
-	/* transfer the data payload for this command, if one exists*/
-	if (transfer_length) {
-		unsigned int pipe = srb->sc_data_direction == DMA_FROM_DEVICE ? 
-				us->recv_bulk_pipe : us->send_bulk_pipe;
-		result = usb_stor_bulk_srb(us, pipe, srb);
-		US_DEBUGP("CB data stage result is 0x%x\n", result);
-
-		/* if we stalled the data transfer it means command failed */
-		if (result == USB_STOR_XFER_STALLED)
-			return USB_STOR_TRANSPORT_FAILED;
-		if (result > USB_STOR_XFER_STALLED)
-			return USB_STOR_TRANSPORT_ERROR;
-	}
-
-	/* STATUS STAGE */
-	/* NOTE: CB does not have a status stage.  Silly, I know.  So
-	 * we have to catch this at a higher level.
-	 */
-	return USB_STOR_TRANSPORT_GOOD;
-}
-
-/*
  * Bulk only transport
  */
 
@@ -1173,10 +1168,9 @@ int usb_stor_Bulk_reset(struct us_data *us)
  */
 int usb_stor_port_reset(struct us_data *us)
 {
-	int result, rc_lock;
+	int result;
 
-	result = rc_lock =
-		usb_lock_device_for_reset(us->pusb_dev, us->pusb_intf);
+	result = usb_lock_device_for_reset(us->pusb_dev, us->pusb_intf);
 	if (result < 0)
 		US_DEBUGP("unable to lock device for reset: %d\n", result);
 	else {
@@ -1189,8 +1183,7 @@ int usb_stor_port_reset(struct us_data *us)
 			US_DEBUGP("usb_reset_device returns %d\n",
 					result);
 		}
-		if (rc_lock)
-			usb_unlock_device(us->pusb_dev);
+		usb_unlock_device(us->pusb_dev);
 	}
 	return result;
 }
diff --git a/drivers/usb/storage/transport.h b/drivers/usb/storage/transport.h
index e70b88182f0e..242ff5e791a5 100644
--- a/drivers/usb/storage/transport.h
+++ b/drivers/usb/storage/transport.h
@@ -113,8 +113,6 @@ struct bulk_cs_wrap {
 
 #define US_CBI_ADSC		0
 
-extern int usb_stor_CBI_transport(struct scsi_cmnd *, struct us_data*);
-
 extern int usb_stor_CB_transport(struct scsi_cmnd *, struct us_data*);
 extern int usb_stor_CB_reset(struct us_data*);
 
diff --git a/drivers/usb/storage/unusual_devs.h b/drivers/usb/storage/unusual_devs.h
index e61f2bfc64ad..b964ed590212 100644
--- a/drivers/usb/storage/unusual_devs.h
+++ b/drivers/usb/storage/unusual_devs.h
@@ -85,6 +85,13 @@ UNUSUAL_DEV(  0x03f0, 0x0307, 0x0001, 0x0001,
 		US_SC_8070, US_PR_USBAT, init_usbat_cd, 0),
 #endif
 
+/* Reported by Ben Efros <ben@pc-doctor.com> */
+UNUSUAL_DEV(  0x03f0, 0x070c, 0x0000, 0x0000,
+		"HP",
+		"Personal Media Drive",
+		US_SC_DEVICE, US_PR_DEVICE, NULL,
+		US_FL_SANE_SENSE ),
+
 /* Reported by Grant Grundler <grundler@parisc-linux.org>
  * HP r707 camera in "Disk" mode with 2.00.23 or 2.00.24 firmware.
  */
@@ -174,6 +181,14 @@ UNUSUAL_DEV(  0x0421, 0x006a, 0x0000, 0x0591,
 		US_SC_DEVICE, US_PR_DEVICE, NULL,
 		US_FL_FIX_CAPACITY ),
 
+/* Submitted by Ricky Wong Yung Fei <evilbladewarrior@gmail.com> */
+/* Nokia 7610 Supernova - Too many sectors reported in usb storage mode */
+UNUSUAL_DEV(  0x0421, 0x00f5, 0x0000, 0x0470,
+		"Nokia",
+		"7610 Supernova",
+		US_SC_DEVICE, US_PR_DEVICE, NULL,
+		US_FL_FIX_CAPACITY ),
+
 /* Reported by Mario Rettig <mariorettig@web.de> */
 UNUSUAL_DEV(  0x0421, 0x042e, 0x0100, 0x0100,
 		"Nokia",
@@ -253,21 +268,6 @@ UNUSUAL_DEV(  0x0421, 0x04fa, 0x0550, 0x0660,
 		US_SC_DEVICE, US_PR_DEVICE, NULL,
 		US_FL_FIX_CAPACITY ),
 
-/* Patch for Nokia 5310 capacity */
-UNUSUAL_DEV(  0x0421, 0x006a, 0x0000, 0x0591,
-	"Nokia",
-	"5310",
-	US_SC_DEVICE, US_PR_DEVICE, NULL,
-	US_FL_FIX_CAPACITY ),
-
-/* Submitted by Ricky Wong Yung Fei <evilbladewarrior@gmail.com> */
-/* Nokia 7610 Supernova - Too many sectors reported in usb storage mode */
-UNUSUAL_DEV(  0x0421, 0x00f5, 0x0000, 0x0470,
-	"Nokia",
-	"7610 Supernova",
-	US_SC_DEVICE, US_PR_DEVICE, NULL,
-	US_FL_FIX_CAPACITY ),
-
 /* Reported by Olaf Hering <olh@suse.de> from novell bug #105878 */
 UNUSUAL_DEV(  0x0424, 0x0fdc, 0x0210, 0x0210,
 		"SMSC",
@@ -374,6 +374,15 @@ UNUSUAL_DEV(  0x04a4, 0x0004, 0x0001, 0x0001,
 		"DVD-CAM DZ-MV100A Camcorder",
 		US_SC_SCSI, US_PR_CB, NULL, US_FL_SINGLE_LUN),
 
+/* BENQ DC5330
+ * Reported by Manuel Fombuena <mfombuena@ya.com> and
+ * Frank Copeland <fjc@thingy.apana.org.au> */
+UNUSUAL_DEV(  0x04a5, 0x3010, 0x0100, 0x0100,
+		"Tekom Technologies, Inc",
+		"300_CAMERA",
+		US_SC_DEVICE, US_PR_DEVICE, NULL,
+		US_FL_IGNORE_RESIDUE ),
+
 /* Patch for Nikon coolpix 2000
  * Submitted by Fabien Cosse <fabien.cosse@wanadoo.fr>*/
 UNUSUAL_DEV(  0x04b0, 0x0301, 0x0010, 0x0010,
@@ -466,15 +475,6 @@ UNUSUAL_DEV(  0x04b3, 0x4001, 0x0110, 0x0110,
 		US_SC_DEVICE, US_PR_CB, NULL,
 		US_FL_MAX_SECTORS_MIN),
 
-/* BENQ DC5330
- * Reported by Manuel Fombuena <mfombuena@ya.com> and
- * Frank Copeland <fjc@thingy.apana.org.au> */
-UNUSUAL_DEV(  0x04a5, 0x3010, 0x0100, 0x0100,
-		"Tekom Technologies, Inc",
-		"300_CAMERA",
-		US_SC_DEVICE, US_PR_DEVICE, NULL,
-		US_FL_IGNORE_RESIDUE ),
-
 #ifdef CONFIG_USB_STORAGE_CYPRESS_ATACB
 /* CY7C68300 : support atacb */
 UNUSUAL_DEV(  0x04b4, 0x6830, 0x0000, 0x9999,
@@ -793,15 +793,15 @@ UNUSUAL_DEV(  0x054c, 0x006d, 0x0000, 0x9999,
 		US_SC_DEVICE, US_PR_DEVICE, NULL,
 		US_FL_FIX_INQUIRY ),
 
-/* Submitted by Mike Alborn <malborn@deandra.homeip.net> */
-UNUSUAL_DEV(  0x054c, 0x016a, 0x0000, 0x9999,
+/* Submitted by Frank Engel <frankie@cse.unsw.edu.au> */
+UNUSUAL_DEV(  0x054c, 0x0099, 0x0000, 0x9999,
 		"Sony",
 		"PEG Mass Storage",
 		US_SC_DEVICE, US_PR_DEVICE, NULL,
 		US_FL_FIX_INQUIRY ),
-		
-/* Submitted by Frank Engel <frankie@cse.unsw.edu.au> */
-UNUSUAL_DEV(  0x054c, 0x0099, 0x0000, 0x9999,
+
+/* Submitted by Mike Alborn <malborn@deandra.homeip.net> */
+UNUSUAL_DEV(  0x054c, 0x016a, 0x0000, 0x9999,
 		"Sony",
 		"PEG Mass Storage",
 		US_SC_DEVICE, US_PR_DEVICE, NULL,
@@ -990,6 +990,13 @@ UNUSUAL_DEV(  0x05e3, 0x0702, 0x0000, 0xffff,
 		US_SC_DEVICE, US_PR_DEVICE, NULL,
 		US_FL_GO_SLOW | US_FL_MAX_SECTORS_64 ),
 
+/* Reported by Ben Efros <ben@pc-doctor.com> */
+UNUSUAL_DEV(  0x05e3, 0x0723, 0x9451, 0x9451,
+		"Genesys Logic",
+		"USB to SATA",
+		US_SC_DEVICE, US_PR_DEVICE, NULL,
+		US_FL_SANE_SENSE ),
+
 /* Reported by Hanno Boeck <hanno@gmx.de>
  * Taken from the Lycoris Kernel */
 UNUSUAL_DEV(  0x0636, 0x0003, 0x0000, 0x9999,
@@ -1329,17 +1336,6 @@ UNUSUAL_DEV(  0x0851, 0x1543, 0x0200, 0x0200,
 		US_SC_DEVICE, US_PR_DEVICE, NULL,
 		US_FL_NOT_LOCKABLE),
 
-/* Andrew Lunn <andrew@lunn.ch>
- * PanDigital Digital Picture Frame. Does not like ALLOW_MEDIUM_REMOVAL
- * on LUN 4.
- * Note: Vend:Prod clash with "Ltd Maxell WS30 Slim Digital Camera"
-*/
-UNUSUAL_DEV(  0x0851, 0x1543, 0x0200, 0x0200,
-		"PanDigital",
-		"Photo Frame",
-		US_SC_DEVICE, US_PR_DEVICE, NULL,
-		US_FL_NOT_LOCKABLE),
-
 /* Submitted by Jan De Luyck <lkml@kcore.org> */
 UNUSUAL_DEV(  0x08bd, 0x1100, 0x0000, 0x0000,
 		"CITIZEN",
@@ -1435,6 +1431,13 @@ UNUSUAL_DEV( 0x0af0, 0x7401, 0x0000, 0x0000,
 		US_SC_DEVICE, US_PR_DEVICE, NULL,
 		0 ),
 
+/* Reported by Ben Efros <ben@pc-doctor.com> */
+UNUSUAL_DEV( 0x0bc2, 0x3010, 0x0000, 0x0000,
+		"Seagate",
+		"FreeAgent Pro",
+		US_SC_DEVICE, US_PR_DEVICE, NULL,
+		US_FL_SANE_SENSE ),
+
 #ifdef CONFIG_USB_STORAGE_ISD200
 UNUSUAL_DEV(  0x0bf6, 0xa001, 0x0100, 0x0110,
 		"ATI",
@@ -1458,6 +1461,22 @@ UNUSUAL_DEV( 0x0c0b, 0xa109, 0x0000, 0xffff,
 		US_FL_SINGLE_LUN ),
 #endif
 
+UNUSUAL_DEV(  0x0d49, 0x7310, 0x0000, 0x9999,
+		"Maxtor",
+		"USB to SATA",
+		US_SC_DEVICE, US_PR_DEVICE, NULL,
+		US_FL_SANE_SENSE),
+
+/*
+ * Pete Zaitcev <zaitcev@yahoo.com>, bz#164688.
+ * The device blatantly ignores LUN and returns 1 in GetMaxLUN.
+ */
+UNUSUAL_DEV( 0x0c45, 0x1060, 0x0100, 0x0100,
+		"Unknown",
+		"Unknown",
+		US_SC_DEVICE, US_PR_DEVICE, NULL,
+		US_FL_SINGLE_LUN ),
+
 /* Submitted by: Nick Sillik <n.sillik@temple.edu>
  * Needed for OneTouch extension to usb-storage
  *
@@ -1475,16 +1494,6 @@ UNUSUAL_DEV( 0x0c0b, 0xa109, 0x0000, 0xffff,
 			0),
 #endif
 
-/*
- * Pete Zaitcev <zaitcev@yahoo.com>, bz#164688.
- * The device blatantly ignores LUN and returns 1 in GetMaxLUN.
- */
-UNUSUAL_DEV( 0x0c45, 0x1060, 0x0100, 0x0100,
-		"Unknown",
-		"Unknown",
-		US_SC_DEVICE, US_PR_DEVICE, NULL,
-		US_FL_SINGLE_LUN ),
-
 /* Submitted by Joris Struyve <joris@struyve.be> */
 UNUSUAL_DEV( 0x0d96, 0x410a, 0x0001, 0xffff,
 		"Medion",
@@ -1624,13 +1633,6 @@ UNUSUAL_DEV(  0x0fce, 0xe030, 0x0000, 0x0000,
 		US_SC_DEVICE, US_PR_DEVICE, NULL,
 		US_FL_FIX_CAPACITY | US_FL_IGNORE_RESIDUE ),
 
-/* Reported by Ricardo Barberis <ricardo@dattatec.com> */
-UNUSUAL_DEV(  0x0fce, 0xe092, 0x0000, 0x0000,
-		"Sony Ericsson",
-		"P1i",
-		US_SC_DEVICE, US_PR_DEVICE, NULL,
-		US_FL_IGNORE_RESIDUE ),
-
 /* Reported by Emmanuel Vasilakis <evas@forthnet.gr> */
 UNUSUAL_DEV(  0x0fce, 0xe031, 0x0000, 0x0000,
 		"Sony Ericsson",
@@ -1638,6 +1640,13 @@ UNUSUAL_DEV(  0x0fce, 0xe031, 0x0000, 0x0000,
 		US_SC_DEVICE, US_PR_DEVICE, NULL,
 		US_FL_IGNORE_RESIDUE | US_FL_FIX_CAPACITY ),
 
+/* Reported by Ricardo Barberis <ricardo@dattatec.com> */
+UNUSUAL_DEV(  0x0fce, 0xe092, 0x0000, 0x0000,
+		"Sony Ericsson",
+		"P1i",
+		US_SC_DEVICE, US_PR_DEVICE, NULL,
+		US_FL_IGNORE_RESIDUE ),
+
 /* Reported by Kevin Cernekee <kpc-usbdev@gelato.uiuc.edu>
  * Tested on hardware version 1.10.
  * Entry is needed only for the initializer function override.
@@ -1650,6 +1659,12 @@ UNUSUAL_DEV(  0x1019, 0x0c55, 0x0000, 0x0110,
 		US_SC_DEVICE, US_PR_DEVICE, usb_stor_ucr61s2b_init,
 		0 ),
 
+UNUSUAL_DEV(  0x1058, 0x0704, 0x0000, 0x9999,
+		"Western Digital",
+		"External HDD",
+		US_SC_DEVICE, US_PR_DEVICE, NULL,
+		US_FL_SANE_SENSE),
+
 /* Reported by Fabio Venturi <f.venturi@tdnet.it>
  * The device reports a vendor-specific bDeviceClass.
  */
@@ -2039,10 +2054,10 @@ UNUSUAL_DEV(  0x14cd, 0x6600, 0x0201, 0x0201,
  * JMicron responds to USN and several other SCSI ioctls with a
  * residue that causes subsequent I/O requests to fail.  */
 UNUSUAL_DEV(  0x152d, 0x2329, 0x0100, 0x0100,
-	        "JMicron",
-	        "USB to ATA/ATAPI Bridge",
-	        US_SC_DEVICE, US_PR_DEVICE, NULL,
-	        US_FL_IGNORE_RESIDUE ),
+		"JMicron",
+		"USB to ATA/ATAPI Bridge",
+		US_SC_DEVICE, US_PR_DEVICE, NULL,
+		US_FL_IGNORE_RESIDUE | US_FL_SANE_SENSE ),
 
 /* Reported by Robert Schedel <r.schedel@yahoo.de>
  * Note: this is a 'super top' device like the above 14cd/6600 device */
diff --git a/drivers/usb/storage/usb.c b/drivers/usb/storage/usb.c
index 27016fd2cad1..06c735703f4a 100644
--- a/drivers/usb/storage/usb.c
+++ b/drivers/usb/storage/usb.c
@@ -113,6 +113,16 @@ static unsigned int delay_use = 5;
 module_param(delay_use, uint, S_IRUGO | S_IWUSR);
 MODULE_PARM_DESC(delay_use, "seconds to delay before using a new device");
 
+static char *quirks;
+module_param(quirks, charp, S_IRUGO);
+MODULE_PARM_DESC(quirks, "supplemental list of device IDs and their quirks");
+
+struct quirks_entry {
+	u16	vid, pid;
+	u32	fflags;
+};
+static struct quirks_entry *quirks_list, *quirks_end;
+
 
 /*
  * The entries in this table correspond, line for line,
@@ -464,13 +474,31 @@ static int associate_dev(struct us_data *us, struct usb_interface *intf)
 		US_DEBUGP("I/O buffer allocation failed\n");
 		return -ENOMEM;
 	}
+	return 0;
+}
 
-	us->sensebuf = kmalloc(US_SENSE_SIZE, GFP_KERNEL);
-	if (!us->sensebuf) {
-		US_DEBUGP("Sense buffer allocation failed\n");
-		return -ENOMEM;
+/* Adjust device flags based on the "quirks=" module parameter */
+static void adjust_quirks(struct us_data *us)
+{
+	u16 vid, pid;
+	struct quirks_entry *q;
+	unsigned int mask = (US_FL_FIX_CAPACITY | US_FL_IGNORE_DEVICE |
+			US_FL_NOT_LOCKABLE | US_FL_MAX_SECTORS_64 |
+			US_FL_IGNORE_RESIDUE | US_FL_SINGLE_LUN |
+			US_FL_NO_WP_DETECT);
+
+	vid = le16_to_cpu(us->pusb_dev->descriptor.idVendor);
+	pid = le16_to_cpu(us->pusb_dev->descriptor.idProduct);
+
+	for (q = quirks_list; q != quirks_end; ++q) {
+		if (q->vid == vid && q->pid == pid) {
+			us->fflags = (us->fflags & ~mask) | q->fflags;
+			dev_info(&us->pusb_intf->dev, "Quirks match for "
+					"vid %04x pid %04x: %x\n",
+					vid, pid, q->fflags);
+			break;
+		}
 	}
-	return 0;
 }
 
 /* Find an unusual_dev descriptor (always succeeds in the current code) */
@@ -497,6 +525,7 @@ static int get_device_info(struct us_data *us, const struct usb_device_id *id)
 			idesc->bInterfaceProtocol :
 			unusual_dev->useTransport;
 	us->fflags = USB_US_ORIG_FLAGS(id->driver_info);
+	adjust_quirks(us);
 
 	if (us->fflags & US_FL_IGNORE_DEVICE) {
 		printk(KERN_INFO USB_STORAGE "device ignored\n");
@@ -562,7 +591,7 @@ static int get_transport(struct us_data *us)
 
 	case US_PR_CBI:
 		us->transport_name = "Control/Bulk/Interrupt";
-		us->transport = usb_stor_CBI_transport;
+		us->transport = usb_stor_CB_transport;
 		us->transport_reset = usb_stor_CB_reset;
 		us->max_lun = 7;
 		break;
@@ -675,19 +704,19 @@ static int get_protocol(struct us_data *us)
 
 	case US_SC_8020:
 		us->protocol_name = "8020i";
-		us->proto_handler = usb_stor_ATAPI_command;
+		us->proto_handler = usb_stor_pad12_command;
 		us->max_lun = 0;
 		break;
 
 	case US_SC_QIC:
 		us->protocol_name = "QIC-157";
-		us->proto_handler = usb_stor_qic157_command;
+		us->proto_handler = usb_stor_pad12_command;
 		us->max_lun = 0;
 		break;
 
 	case US_SC_8070:
 		us->protocol_name = "8070i";
-		us->proto_handler = usb_stor_ATAPI_command;
+		us->proto_handler = usb_stor_pad12_command;
 		us->max_lun = 0;
 		break;
 
@@ -840,8 +869,6 @@ static void dissociate_dev(struct us_data *us)
 {
 	US_DEBUGP("-- %s\n", __func__);
 
-	kfree(us->sensebuf);
-
 	/* Free the device-related DMA-mapped buffers */
 	if (us->cr)
 		usb_buffer_free(us->pusb_dev, sizeof(*us->cr), us->cr,
@@ -1061,10 +1088,88 @@ static struct usb_driver usb_storage_driver = {
 	.soft_unbind =	1,
 };
 
+/* Works only for digits and letters, but small and fast */
+#define TOLOWER(x) ((x) | 0x20)
+
+static void __init parse_quirks(void)
+{
+	int n, i;
+	char *p;
+
+	if (!quirks)
+		return;
+
+	/* Count the ':' characters to get 2 * the number of entries */
+	n = 0;
+	for (p = quirks; *p; ++p) {
+		if (*p == ':')
+			++n;
+	}
+	n /= 2;
+	if (n == 0)
+		return;		/* Don't allocate 0 bytes */
+
+	quirks_list = kmalloc(n * sizeof(*quirks_list), GFP_KERNEL);
+	if (!quirks_list)
+		return;
+
+	p = quirks;
+	quirks_end = quirks_list;
+	for (i = 0; i < n && *p; ++i) {
+		unsigned f = 0;
+
+		/* Each entry consists of VID:PID:flags */
+		quirks_end->vid = simple_strtoul(p, &p, 16);
+		if (*p != ':')
+			goto skip_to_next;
+		quirks_end->pid = simple_strtoul(p+1, &p, 16);
+		if (*p != ':')
+			goto skip_to_next;
+
+		while (*++p && *p != ',') {
+			switch (TOLOWER(*p)) {
+			case 'c':
+				f |= US_FL_FIX_CAPACITY;
+				break;
+			case 'i':
+				f |= US_FL_IGNORE_DEVICE;
+				break;
+			case 'l':
+				f |= US_FL_NOT_LOCKABLE;
+				break;
+			case 'm':
+				f |= US_FL_MAX_SECTORS_64;
+				break;
+			case 'r':
+				f |= US_FL_IGNORE_RESIDUE;
+				break;
+			case 's':
+				f |= US_FL_SINGLE_LUN;
+				break;
+			case 'w':
+				f |= US_FL_NO_WP_DETECT;
+				break;
+			/* Ignore unrecognized flag characters */
+			}
+		}
+		quirks_end->fflags = f;
+		++quirks_end;
+
+ skip_to_next:
+		/* Entries are separated by commas */
+		while (*p) {
+			if (*p++ == ',')
+				break;
+		}
+	} /* for (i = 0; ...) */
+}
+
 static int __init usb_stor_init(void)
 {
 	int retval;
+
 	printk(KERN_INFO "Initializing USB Mass Storage driver...\n");
+	parse_quirks();
 
 	/* register the driver, return usb_register return code if error */
 	retval = usb_register(&usb_storage_driver);
diff --git a/drivers/usb/storage/usb.h b/drivers/usb/storage/usb.h
index a4ad73bd832d..e4674fc715e6 100644
--- a/drivers/usb/storage/usb.h
+++ b/drivers/usb/storage/usb.h
@@ -138,7 +138,6 @@ struct us_data {
 	struct usb_ctrlrequest	*cr;		 /* control requests	 */
 	struct usb_sg_request	current_sg;	 /* scatter-gather req.  */
 	unsigned char		*iobuf;		 /* I/O buffer		 */
-	unsigned char		*sensebuf;	 /* sense data buffer	 */
 	dma_addr_t		cr_dma;		 /* buffer DMA addresses */
 	dma_addr_t		iobuf_dma;
 	struct task_struct	*ctl_thread;	 /* the control thread   */
diff --git a/drivers/usb/wusbcore/rh.c b/drivers/usb/wusbcore/rh.c
index 267a64325106..b1bb82db4abc 100644
--- a/drivers/usb/wusbcore/rh.c
+++ b/drivers/usb/wusbcore/rh.c
@@ -352,7 +352,7 @@ static int wusbhc_rh_get_port_status(struct wusbhc *wusbhc, u16 port_idx,
 				     u32 *_buf, u16 wLength)
 {
 	int result = -EINVAL;
-	u16 *buf = (u16 *) _buf;
+	__le16 *buf = (__le16 *)_buf;
 
 	d_fnstart(1, wusbhc->dev, "(wusbhc %p port_idx %u wLength %u)\n",
 		  wusbhc, port_idx, wLength);
diff --git a/drivers/video/Kconfig b/drivers/video/Kconfig
index 3f3ce13fef43..5611a4f1559b 100644
--- a/drivers/video/Kconfig
+++ b/drivers/video/Kconfig
@@ -362,7 +362,7 @@ endchoice
 
 config FB_ACORN
 	bool "Acorn VIDC support"
-	depends on (FB = y) && ARM && (ARCH_ACORN || ARCH_CLPS7500)
+	depends on (FB = y) && ARM && ARCH_ACORN
 	select FB_CFB_FILLRECT
 	select FB_CFB_COPYAREA
 	select FB_CFB_IMAGEBLIT
@@ -2021,17 +2021,19 @@ config FB_COBALT
 	depends on FB && MIPS_COBALT
 
 config FB_SH7760
-       bool "SH7760/SH7763 LCDC support"
-       depends on FB && (CPU_SUBTYPE_SH7760 || CPU_SUBTYPE_SH7763)
-       select FB_CFB_FILLRECT
-       select FB_CFB_COPYAREA
-       select FB_CFB_IMAGEBLIT
-       help
-         Support for the SH7760/SH7763 integrated (D)STN/TFT LCD Controller.
-         Supports display resolutions up to 1024x1024 pixel, grayscale and
-         color operation, with depths ranging from 1 bpp to 8 bpp monochrome
-         and 8, 15 or 16 bpp color; 90 degrees clockwise display rotation for
-         panels <= 320 pixel horizontal resolution.
+	bool "SH7760/SH7763/SH7720/SH7721 LCDC support"
+	depends on FB && (CPU_SUBTYPE_SH7760 || CPU_SUBTYPE_SH7763 \
+		|| CPU_SUBTYPE_SH7720 || CPU_SUBTYPE_SH7721)
+	select FB_CFB_FILLRECT
+	select FB_CFB_COPYAREA
+	select FB_CFB_IMAGEBLIT
+	---help---
+	  Support for the SH7760/SH7763/SH7720/SH7721 integrated
+	  (D)STN/TFT LCD Controller.
+	  Supports display resolutions up to 1024x1024 pixel, grayscale and
+	  color operation, with depths ranging from 1 bpp to 8 bpp monochrome
+	  and 8, 15 or 16 bpp color; 90 degrees clockwise display rotation for
+	  panels <= 320 pixel horizontal resolution.
 
 config FB_VIRTUAL
 	tristate "Virtual Frame Buffer support (ONLY FOR TESTING!)"
diff --git a/drivers/video/amba-clcd.c b/drivers/video/amba-clcd.c
index a7a1c891bfa2..2ac52fd8cc11 100644
--- a/drivers/video/amba-clcd.c
+++ b/drivers/video/amba-clcd.c
@@ -343,14 +343,14 @@ static int clcdfb_register(struct clcd_fb *fb)
 {
 	int ret;
 
-	fb->clk = clk_get(&fb->dev->dev, "CLCDCLK");
+	fb->clk = clk_get(&fb->dev->dev, NULL);
 	if (IS_ERR(fb->clk)) {
 		ret = PTR_ERR(fb->clk);
 		goto out;
 	}
 
 	fb->fb.fix.mmio_start	= fb->dev->res.start;
-	fb->fb.fix.mmio_len	= SZ_4K;
+	fb->fb.fix.mmio_len	= 4096;
 
 	fb->regs = ioremap(fb->fb.fix.mmio_start, fb->fb.fix.mmio_len);
 	if (!fb->regs) {
diff --git a/drivers/video/backlight/backlight.c b/drivers/video/backlight/backlight.c
index fab0bc874b58..0664fc032235 100644
--- a/drivers/video/backlight/backlight.c
+++ b/drivers/video/backlight/backlight.c
@@ -217,7 +217,7 @@ struct backlight_device *backlight_device_register(const char *name,
 	new_bd->dev.class = backlight_class;
 	new_bd->dev.parent = parent;
 	new_bd->dev.release = bl_device_release;
-	strlcpy(new_bd->dev.bus_id, name, BUS_ID_SIZE);
+	dev_set_name(&new_bd->dev, name);
 	dev_set_drvdata(&new_bd->dev, devdata);
 
 	rc = device_register(&new_bd->dev);
diff --git a/drivers/video/backlight/lcd.c b/drivers/video/backlight/lcd.c
index 680e57b616cd..b6449470106c 100644
--- a/drivers/video/backlight/lcd.c
+++ b/drivers/video/backlight/lcd.c
@@ -208,7 +208,7 @@ struct lcd_device *lcd_device_register(const char *name, struct device *parent,
 	new_ld->dev.class = lcd_class;
 	new_ld->dev.parent = parent;
 	new_ld->dev.release = lcd_device_release;
-	strlcpy(new_ld->dev.bus_id, name, BUS_ID_SIZE);
+	dev_set_name(&new_ld->dev, name);
 	dev_set_drvdata(&new_ld->dev, devdata);
 
 	rc = device_register(&new_ld->dev);
diff --git a/drivers/video/console/fbcon.c b/drivers/video/console/fbcon.c
index 67ff370d80af..2fde28d9430c 100644
--- a/drivers/video/console/fbcon.c
+++ b/drivers/video/console/fbcon.c
@@ -81,9 +81,6 @@
 #ifdef CONFIG_ATARI
 #include <asm/atariints.h>
 #endif
-#ifdef CONFIG_MAC
-#include <asm/macints.h>
-#endif
 #if defined(__mc68000__)
 #include <asm/machdep.h>
 #include <asm/setup.h>
@@ -160,8 +157,6 @@ static int fbcon_set_origin(struct vc_data *);
 
 /* # VBL ints between cursor state changes */
 #define ATARI_CURSOR_BLINK_RATE		(42)
-#define MAC_CURSOR_BLINK_RATE		(32)
-#define DEFAULT_CURSOR_BLINK_RATE	(20)
 
 static int vbl_cursor_cnt;
 static int fbcon_cursor_noblink;
@@ -210,19 +205,6 @@ static void fbcon_start(void);
 static void fbcon_exit(void);
 static struct device *fbcon_device;
 
-#ifdef CONFIG_MAC
-/*
- * On the Macintoy, there may or may not be a working VBL int. We need to probe
- */
-static int vbl_detected;
-
-static irqreturn_t fb_vbl_detect(int irq, void *dummy)
-{
-	vbl_detected++;
-	return IRQ_HANDLED;
-}
-#endif
-
 #ifdef CONFIG_FRAMEBUFFER_CONSOLE_ROTATION
 static inline void fbcon_set_rotation(struct fb_info *info)
 {
@@ -421,7 +403,7 @@ static void fb_flashcursor(struct work_struct *work)
 	release_console_sem();
 }
 
-#if defined(CONFIG_ATARI) || defined(CONFIG_MAC)
+#ifdef CONFIG_ATARI
 static int cursor_blink_rate;
 static irqreturn_t fb_vbl_handler(int irq, void *dev_id)
 {
@@ -949,9 +931,7 @@ static const char *fbcon_startup(void)
 	struct fb_info *info = NULL;
 	struct fbcon_ops *ops;
 	int rows, cols;
-	int irqres;
 
-	irqres = 1;
 	/*
 	 *  If num_registered_fb is zero, this is a call for the dummy part.
 	 *  The frame buffer devices weren't initialized yet.
@@ -1040,56 +1020,11 @@ static const char *fbcon_startup(void)
 #ifdef CONFIG_ATARI
 	if (MACH_IS_ATARI) {
 		cursor_blink_rate = ATARI_CURSOR_BLINK_RATE;
-		irqres =
-		    request_irq(IRQ_AUTO_4, fb_vbl_handler,
+		(void)request_irq(IRQ_AUTO_4, fb_vbl_handler,
 				IRQ_TYPE_PRIO, "framebuffer vbl",
 				info);
 	}
-#endif				/* CONFIG_ATARI */
-
-#ifdef CONFIG_MAC
-	/*
-	 * On a Macintoy, the VBL interrupt may or may not be active. 
-	 * As interrupt based cursor is more reliable and race free, we 
-	 * probe for VBL interrupts.
-	 */
-	if (MACH_IS_MAC) {
-		int ct = 0;
-		/*
-		 * Probe for VBL: set temp. handler ...
-		 */
-		irqres = request_irq(IRQ_MAC_VBL, fb_vbl_detect, 0,
-				     "framebuffer vbl", info);
-		vbl_detected = 0;
-
-		/*
-		 * ... and spin for 20 ms ...
-		 */
-		while (!vbl_detected && ++ct < 1000)
-			udelay(20);
-
-		if (ct == 1000)
-			printk
-			    ("fbcon_startup: No VBL detected, using timer based cursor.\n");
-
-		free_irq(IRQ_MAC_VBL, fb_vbl_detect);
-
-		if (vbl_detected) {
-			/*
-			 * interrupt based cursor ok
-			 */
-			cursor_blink_rate = MAC_CURSOR_BLINK_RATE;
-			irqres =
-			    request_irq(IRQ_MAC_VBL, fb_vbl_handler, 0,
-					"framebuffer vbl", info);
-		} else {
-			/*
-			 * VBL not detected: fall through, use timer based cursor
-			 */
-			irqres = 1;
-		}
-	}
-#endif				/* CONFIG_MAC */
+#endif /* CONFIG_ATARI */
 
 	fbcon_add_cursor_timer(info);
 	fbcon_has_exited = 0;
@@ -3520,11 +3455,8 @@ static void fbcon_exit(void)
 		return;
 
 #ifdef CONFIG_ATARI
-	free_irq(IRQ_AUTO_4, fb_vbl_handler);
-#endif
-#ifdef CONFIG_MAC
-	if (MACH_IS_MAC && vbl_detected)
-		free_irq(IRQ_MAC_VBL, fb_vbl_handler);
+	if (MACH_IS_ATARI)
+		free_irq(IRQ_AUTO_4, fb_vbl_handler);
 #endif
 
 	kfree((void *)softback_buf);
diff --git a/drivers/video/macfb.c b/drivers/video/macfb.c
index ee380d5f3410..d66887e8cbb1 100644
--- a/drivers/video/macfb.c
+++ b/drivers/video/macfb.c
@@ -36,7 +36,6 @@
 #include <asm/irq.h>
 #include <asm/macintosh.h>
 #include <asm/io.h>
-#include <asm/machw.h>
 
 /* Common DAC base address for the LC, RBV, Valkyrie, and IIvx */
 #define DAC_BASE 0x50f24000
@@ -78,34 +77,34 @@ static int csc_setpalette (unsigned int regno, unsigned int red,
 			   unsigned int green, unsigned int blue,
 			   struct fb_info *fb_info);
 
-static volatile struct {
+static struct {
 	unsigned char addr;
 	/* Note: word-aligned */
 	char pad[3];
 	unsigned char lut;
-} *valkyrie_cmap_regs;
+} __iomem *valkyrie_cmap_regs;
 
-static volatile struct {
+static struct {
 	unsigned char addr;
 	unsigned char lut;
-} *v8_brazil_cmap_regs;
+} __iomem *v8_brazil_cmap_regs;
 
-static volatile struct {
+static struct {
 	unsigned char addr;
 	char pad1[3]; /* word aligned */
 	unsigned char lut;
 	char pad2[3]; /* word aligned */
 	unsigned char cntl; /* a guess as to purpose */
-} *rbv_cmap_regs;
+} __iomem *rbv_cmap_regs;
 
-static volatile struct {
+static struct {
 	unsigned long reset;
 	unsigned long pad1[3];
 	unsigned char pad2[3];
 	unsigned char lut;
-} *dafb_cmap_regs;
+} __iomem *dafb_cmap_regs;
 
-static volatile struct {
+static struct {
 	unsigned char addr;	/* OFFSET: 0x00 */
 	unsigned char pad1[15];
 	unsigned char lut;	/* OFFSET: 0x10 */
@@ -114,16 +113,16 @@ static volatile struct {
 	unsigned char pad3[7];
 	unsigned long vbl_addr;	/* OFFSET: 0x28 */
 	unsigned int  status2;	/* OFFSET: 0x2C */
-} *civic_cmap_regs;
+} __iomem *civic_cmap_regs;
 
-static volatile struct {
+static struct {
 	char    pad1[0x40];
         unsigned char	clut_waddr;	/* 0x40 */
         char    pad2;
         unsigned char	clut_data;	/* 0x42 */
         char	pad3[0x3];
         unsigned char	clut_raddr;	/* 0x46 */
-} *csc_cmap_regs;
+} __iomem *csc_cmap_regs;
 
 /* We will leave these the way they are for the time being */
 struct mdc_cmap_regs {
@@ -507,10 +506,10 @@ static int csc_setpalette (unsigned int regno, unsigned int red,
 			   struct fb_info *info)
 {
 	mdelay(1);
-	csc_cmap_regs->clut_waddr = regno;
-	csc_cmap_regs->clut_data = red;
-	csc_cmap_regs->clut_data = green;
-	csc_cmap_regs->clut_data = blue;
+	nubus_writeb(regno, &csc_cmap_regs->clut_waddr);
+	nubus_writeb(red,   &csc_cmap_regs->clut_data);
+	nubus_writeb(green, &csc_cmap_regs->clut_data);
+	nubus_writeb(blue,  &csc_cmap_regs->clut_data);
 	return 0;
 }
 
diff --git a/drivers/video/omap/omapfb_main.c b/drivers/video/omap/omapfb_main.c
index 5a5e407dc45f..1a49519dafa4 100644
--- a/drivers/video/omap/omapfb_main.c
+++ b/drivers/video/omap/omapfb_main.c
@@ -392,7 +392,7 @@ static void set_fb_fix(struct fb_info *fbi)
 	int bpp;
 
 	rg = &plane->fbdev->mem_desc.region[plane->idx];
-	fbi->screen_base	= (char __iomem *)rg->vaddr;
+	fbi->screen_base	= rg->vaddr;
 	fix->smem_start		= rg->paddr;
 	fix->smem_len		= rg->size;
 
diff --git a/drivers/video/output.c b/drivers/video/output.c
index f2df5519c9c4..5e6439ae7394 100644
--- a/drivers/video/output.c
+++ b/drivers/video/output.c
@@ -96,7 +96,7 @@ struct output_device *video_output_register(const char *name,
 	new_dev->props = op;
 	new_dev->dev.class = &video_output_class;
 	new_dev->dev.parent = dev;
-	strlcpy(new_dev->dev.bus_id,name, BUS_ID_SIZE);
+	dev_set_name(&new_dev->dev, name);
 	dev_set_drvdata(&new_dev->dev, devdata);
 	ret_code = device_register(&new_dev->dev);
 	if (ret_code) {
diff --git a/drivers/video/ps3fb.c b/drivers/video/ps3fb.c
index 4b5d80771904..bd3e39baf7d2 100644
--- a/drivers/video/ps3fb.c
+++ b/drivers/video/ps3fb.c
@@ -460,12 +460,16 @@ static void ps3fb_sync_image(struct device *dev, u64 frame_offset,
 		line_length |= (u64)src_line_length << 32;
 
 	src_offset += GPU_FB_START;
+
+	mutex_lock(&ps3_gpu_mutex);
 	status = lv1_gpu_context_attribute(ps3fb.context_handle,
 					   L1GPU_CONTEXT_ATTRIBUTE_FB_BLIT,
 					   dst_offset, GPU_IOIF + src_offset,
 					   L1GPU_FB_BLIT_WAIT_FOR_COMPLETION |
 					   (width << 16) | height,
 					   line_length);
+	mutex_unlock(&ps3_gpu_mutex);
+
 	if (status)
 		dev_err(dev,
 			"%s: lv1_gpu_context_attribute FB_BLIT failed: %d\n",
@@ -784,15 +788,6 @@ static int ps3fb_wait_for_vsync(u32 crtc)
 	return 0;
 }
 
-static void ps3fb_flip_ctl(int on, void *data)
-{
-	struct ps3fb_priv *priv = data;
-	if (on)
-		atomic_dec_if_positive(&priv->ext_flip);
-	else
-		atomic_inc(&priv->ext_flip);
-}
-
 
     /*
      * ioctl
@@ -1228,7 +1223,6 @@ static int __devinit ps3fb_probe(struct ps3_system_bus_device *dev)
 	}
 
 	ps3fb.task = task;
-	ps3av_register_flip_ctl(ps3fb_flip_ctl, &ps3fb);
 
 	return 0;
 
@@ -1258,10 +1252,9 @@ static int ps3fb_shutdown(struct ps3_system_bus_device *dev)
 
 	dev_dbg(&dev->core, " -> %s:%d\n", __func__, __LINE__);
 
-	ps3fb_flip_ctl(0, &ps3fb);	/* flip off */
+	atomic_inc(&ps3fb.ext_flip);	/* flip off */
 	ps3fb.dinfo->irq.mask = 0;
 
-	ps3av_register_flip_ctl(NULL, NULL);
 	if (ps3fb.task) {
 		struct task_struct *task = ps3fb.task;
 		ps3fb.task = NULL;
diff --git a/drivers/video/pxafb.c b/drivers/video/pxafb.c
index cc59c52e1103..afe7a65c5603 100644
--- a/drivers/video/pxafb.c
+++ b/drivers/video/pxafb.c
@@ -69,9 +69,6 @@
 #define LCCR3_INVALID_CONFIG_MASK	(LCCR3_HSP | LCCR3_VSP |\
 					 LCCR3_PCD | LCCR3_BPP)
 
-static void (*pxafb_backlight_power)(int);
-static void (*pxafb_lcd_power)(int, struct fb_var_screeninfo *);
-
 static int pxafb_activate_var(struct fb_var_screeninfo *var,
 				struct pxafb_info *);
 static void set_ctrlr_state(struct pxafb_info *fbi, u_int state);
@@ -814,6 +811,7 @@ static int pxafb_smart_init(struct pxafb_info *fbi)
 				__func__);
 		return PTR_ERR(fbi->smart_thread);
 	}
+
 	return 0;
 }
 #else
@@ -976,16 +974,16 @@ static inline void __pxafb_backlight_power(struct pxafb_info *fbi, int on)
 {
 	pr_debug("pxafb: backlight o%s\n", on ? "n" : "ff");
 
-	if (pxafb_backlight_power)
-		pxafb_backlight_power(on);
+	if (fbi->backlight_power)
+		fbi->backlight_power(on);
 }
 
 static inline void __pxafb_lcd_power(struct pxafb_info *fbi, int on)
 {
 	pr_debug("pxafb: LCD power o%s\n", on ? "n" : "ff");
 
-	if (pxafb_lcd_power)
-		pxafb_lcd_power(on, &fbi->fb.var);
+	if (fbi->lcd_power)
+		fbi->lcd_power(on, &fbi->fb.var);
 }
 
 static void pxafb_setup_gpio(struct pxafb_info *fbi)
@@ -1429,7 +1427,7 @@ static struct pxafb_info * __devinit pxafb_init_fbinfo(struct device *dev)
 	memset(fbi, 0, sizeof(struct pxafb_info));
 	fbi->dev = dev;
 
-	fbi->clk = clk_get(dev, "LCDCLK");
+	fbi->clk = clk_get(dev, NULL);
 	if (IS_ERR(fbi->clk)) {
 		kfree(fbi);
 		return NULL;
@@ -1748,8 +1746,7 @@ static int __devinit pxafb_probe(struct platform_device *dev)
 		ret = -EINVAL;
 		goto failed;
 	}
-	pxafb_backlight_power = inf->pxafb_backlight_power;
-	pxafb_lcd_power = inf->pxafb_lcd_power;
+
 	fbi = pxafb_init_fbinfo(&dev->dev);
 	if (!fbi) {
 		/* only reason for pxafb_init_fbinfo to fail is kmalloc */
@@ -1758,6 +1755,9 @@ static int __devinit pxafb_probe(struct platform_device *dev)
 		goto failed;
 	}
 
+	fbi->backlight_power = inf->pxafb_backlight_power;
+	fbi->lcd_power = inf->pxafb_lcd_power;
+
 	r = platform_get_resource(dev, IORESOURCE_MEM, 0);
 	if (r == NULL) {
 		dev_err(&dev->dev, "no I/O memory resource defined\n");
diff --git a/drivers/video/pxafb.h b/drivers/video/pxafb.h
index 31541b86f13d..d8eb93fa03a3 100644
--- a/drivers/video/pxafb.h
+++ b/drivers/video/pxafb.h
@@ -124,6 +124,9 @@ struct pxafb_info {
 	struct notifier_block	freq_transition;
 	struct notifier_block	freq_policy;
 #endif
+
+	void (*lcd_power)(int, struct fb_var_screeninfo *);
+	void (*backlight_power)(int);
 };
 
 #define TO_INF(ptr,member) container_of(ptr,struct pxafb_info,member)
diff --git a/drivers/video/sa1100fb.c b/drivers/video/sa1100fb.c
index c052bd4c0b06..076f946fa0f5 100644
--- a/drivers/video/sa1100fb.c
+++ b/drivers/video/sa1100fb.c
@@ -114,7 +114,7 @@
  *	- convert dma address types to dma_addr_t
  *	- remove unused 'montype' stuff
  *	- remove redundant zero inits of init_var after the initial
- *	  memzero.
+ *	  memset.
  *	- remove allow_modeset (acornfb idea does not belong here)
  *
  * 2001/05/28: <rmk@arm.linux.org.uk>
diff --git a/drivers/video/sh7760fb.c b/drivers/video/sh7760fb.c
index 8d0212da4514..653bdfee3057 100644
--- a/drivers/video/sh7760fb.c
+++ b/drivers/video/sh7760fb.c
@@ -13,6 +13,8 @@
  *
  * Thanks to Siegfried Schaefer <s.schaefer at schaefer-edv.de>
  *     for his original source and testing!
+ *
+ * sh7760_setcolreg get from drivers/video/sh_mobile_lcdcfb.c
  */
 
 #include <linux/completion.h>
@@ -53,29 +55,6 @@ static irqreturn_t sh7760fb_irq(int irq, void *data)
 	return IRQ_HANDLED;
 }
 
-static void sh7760fb_wait_vsync(struct fb_info *info)
-{
-	struct sh7760fb_par *par = info->par;
-
-	if (par->pd->novsync)
-		return;
-
-	iowrite16(ioread16(par->base + LDINTR) & ~VINT_CHECK,
-		  par->base + LDINTR);
-
-	if (par->irq < 0) {
-		/* poll for vert. retrace: status bit is sticky */
-		while (!(ioread16(par->base + LDINTR) & VINT_CHECK))
-			cpu_relax();
-	} else {
-		/* a "wait_for_irq_event(par->irq)" would be extremely nice */
-		init_completion(&par->vsync);
-		enable_irq(par->irq);
-		wait_for_completion(&par->vsync);
-		disable_irq_nosync(par->irq);
-	}
-}
-
 /* wait_for_lps - wait until power supply has reached a certain state. */
 static int wait_for_lps(struct sh7760fb_par *par, int val)
 {
@@ -117,55 +96,28 @@ static int sh7760fb_blank(int blank, struct fb_info *info)
 	return wait_for_lps(par, lps);
 }
 
-/* set color registers */
-static int sh7760fb_setcmap(struct fb_cmap *cmap, struct fb_info *info)
+static int sh7760_setcolreg (u_int regno,
+	u_int red, u_int green, u_int blue,
+	u_int transp, struct fb_info *info)
 {
-	struct sh7760fb_par *par = info->par;
-	u32 s = cmap->start;
-	u32 l = cmap->len;
-	u16 *r = cmap->red;
-	u16 *g = cmap->green;
-	u16 *b = cmap->blue;
-	u32 col, tmo;
-	int ret;
+	u32 *palette = info->pseudo_palette;
 
-	ret = 0;
+	if (regno >= 16)
+		return -EINVAL;
 
-	sh7760fb_wait_vsync(info);
+	/* only FB_VISUAL_TRUECOLOR supported */
 
-	/* request palette access */
-	iowrite16(LDPALCR_PALEN, par->base + LDPALCR);
+	red >>= 16 - info->var.red.length;
+	green >>= 16 - info->var.green.length;
+	blue >>= 16 - info->var.blue.length;
+	transp >>= 16 - info->var.transp.length;
 
-	/* poll for access grant */
-	tmo = 100;
-	while (!(ioread16(par->base + LDPALCR) & LDPALCR_PALS) && (--tmo))
-		cpu_relax();
+	palette[regno] = (red << info->var.red.offset) |
+		(green << info->var.green.offset) |
+		(blue << info->var.blue.offset) |
+		(transp << info->var.transp.offset);
 
-	if (!tmo) {
-		ret = 1;
-		dev_dbg(info->dev, "no palette access!\n");
-		goto out;
-	}
-
-	while (l && (s < 256)) {
-		col = ((*r) & 0xff) << 16;
-		col |= ((*g) & 0xff) << 8;
-		col |= ((*b) & 0xff);
-		col &= SH7760FB_PALETTE_MASK;
-		iowrite32(col, par->base + LDPR(s));
-
-		if (s < 16)
-			((u32 *) (info->pseudo_palette))[s] = s;
-
-		s++;
-		l--;
-		r++;
-		g++;
-		b++;
-	}
-out:
-	iowrite16(0, par->base + LDPALCR);
-	return ret;
+	return 0;
 }
 
 static void encode_fix(struct fb_fix_screeninfo *fix, struct fb_info *info,
@@ -406,7 +358,7 @@ static struct fb_ops sh7760fb_ops = {
 	.owner = THIS_MODULE,
 	.fb_blank = sh7760fb_blank,
 	.fb_check_var = sh7760fb_check_var,
-	.fb_setcmap = sh7760fb_setcmap,
+	.fb_setcolreg = sh7760_setcolreg,
 	.fb_set_par = sh7760fb_set_par,
 	.fb_fillrect = cfb_fillrect,
 	.fb_copyarea = cfb_copyarea,
diff --git a/drivers/video/sh_mobile_lcdcfb.c b/drivers/video/sh_mobile_lcdcfb.c
index efff672fd7b8..c81ee00c54d7 100644
--- a/drivers/video/sh_mobile_lcdcfb.c
+++ b/drivers/video/sh_mobile_lcdcfb.c
@@ -35,6 +35,7 @@ struct sh_mobile_lcdc_chan {
 struct sh_mobile_lcdc_priv {
 	void __iomem *base;
 #ifdef CONFIG_HAVE_CLK
+	struct clk *dot_clk;
 	struct clk *clk;
 #endif
 	unsigned long lddckr;
@@ -207,6 +208,11 @@ static int sh_mobile_lcdc_start(struct sh_mobile_lcdc_priv *priv)
 	int k, m;
 	int ret = 0;
 
+#ifdef CONFIG_HAVE_CLK
+	clk_enable(priv->clk);
+	if (priv->dot_clk)
+		clk_enable(priv->dot_clk);
+#endif
 	/* reset */
 	lcdc_write(priv, _LDCNT2R, lcdc_read(priv, _LDCNT2R) | LCDC_RESET);
 	lcdc_wait_bit(priv, _LDCNT2R, LCDC_RESET, 0);
@@ -371,6 +377,12 @@ static void sh_mobile_lcdc_stop(struct sh_mobile_lcdc_priv *priv)
 
 	/* stop the lcdc */
 	sh_mobile_lcdc_start_stop(priv, 0);
+
+#ifdef CONFIG_HAVE_CLK
+	if (priv->dot_clk)
+		clk_disable(priv->dot_clk);
+	clk_disable(priv->clk);
+#endif
 }
 
 static int sh_mobile_lcdc_check_interface(struct sh_mobile_lcdc_chan *ch)
@@ -413,9 +425,13 @@ static int sh_mobile_lcdc_check_interface(struct sh_mobile_lcdc_chan *ch)
 	return -EINVAL;
 }
 
-static int sh_mobile_lcdc_setup_clocks(struct device *dev, int clock_source,
+static int sh_mobile_lcdc_setup_clocks(struct platform_device *pdev,
+				       int clock_source,
 				       struct sh_mobile_lcdc_priv *priv)
 {
+#ifdef CONFIG_HAVE_CLK
+	char clk_name[8];
+#endif
 	char *str;
 	int icksel;
 
@@ -430,14 +446,20 @@ static int sh_mobile_lcdc_setup_clocks(struct device *dev, int clock_source,
 	priv->lddckr = icksel << 16;
 
 #ifdef CONFIG_HAVE_CLK
+	snprintf(clk_name, sizeof(clk_name), "lcdc%d", pdev->id);
+	priv->clk = clk_get(&pdev->dev, clk_name);
+	if (IS_ERR(priv->clk)) {
+		dev_err(&pdev->dev, "cannot get clock \"%s\"\n", clk_name);
+		return PTR_ERR(priv->clk);
+	}
+	
 	if (str) {
-		priv->clk = clk_get(dev, str);
-		if (IS_ERR(priv->clk)) {
-			dev_err(dev, "cannot get clock %s\n", str);
-			return PTR_ERR(priv->clk);
+		priv->dot_clk = clk_get(&pdev->dev, str);
+		if (IS_ERR(priv->dot_clk)) {
+			dev_err(&pdev->dev, "cannot get dot clock %s\n", str);
+			clk_put(priv->clk);
+			return PTR_ERR(priv->dot_clk);
 		}
-
-		clk_enable(priv->clk);
 	}
 #endif
 
@@ -587,8 +609,7 @@ static int __init sh_mobile_lcdc_probe(struct platform_device *pdev)
 		goto err1;
 	}
 
-	error = sh_mobile_lcdc_setup_clocks(&pdev->dev,
-					    pdata->clock_source, priv);
+	error = sh_mobile_lcdc_setup_clocks(pdev, pdata->clock_source, priv);
 	if (error) {
 		dev_err(&pdev->dev, "unable to setup clocks\n");
 		goto err1;
@@ -697,10 +718,9 @@ static int sh_mobile_lcdc_remove(struct platform_device *pdev)
 	}
 
 #ifdef CONFIG_HAVE_CLK
-	if (priv->clk) {
-		clk_disable(priv->clk);
-		clk_put(priv->clk);
-	}
+	if (priv->dot_clk)
+		clk_put(priv->dot_clk);
+	clk_put(priv->clk);
 #endif
 
 	if (priv->base)
diff --git a/drivers/w1/w1.c b/drivers/w1/w1.c
index 3b615d4022ee..acc7e3b7fe17 100644
--- a/drivers/w1/w1.c
+++ b/drivers/w1/w1.c
@@ -197,7 +197,7 @@ struct device_driver w1_master_driver = {
 struct device w1_master_device = {
 	.parent = NULL,
 	.bus = &w1_bus_type,
-	.bus_id = "w1 bus master",
+	.init_name = "w1 bus master",
 	.driver = &w1_master_driver,
 	.release = &w1_master_release
 };
@@ -211,7 +211,7 @@ static struct device_driver w1_slave_driver = {
 struct device w1_slave_device = {
 	.parent = NULL,
 	.bus = &w1_bus_type,
-	.bus_id = "w1 bus slave",
+	.init_name = "w1 bus slave",
 	.driver = &w1_slave_driver,
 	.release = &w1_slave_release
 };
@@ -573,7 +573,7 @@ static int w1_uevent(struct device *dev, struct kobj_uevent_env *env)
 	}
 
 	dev_dbg(dev, "Hotplug event for %s %s, bus_id=%s.\n",
-			event_owner, name, dev->bus_id);
+			event_owner, name, dev_name(dev));
 
 	if (dev->driver != &w1_slave_driver || !sl)
 		return 0;
@@ -605,8 +605,7 @@ static int __w1_attach_slave_device(struct w1_slave *sl)
 	sl->dev.bus = &w1_bus_type;
 	sl->dev.release = &w1_slave_release;
 
-	snprintf(&sl->dev.bus_id[0], sizeof(sl->dev.bus_id),
-		 "%02x-%012llx",
+	dev_set_name(&sl->dev, "%02x-%012llx",
 		 (unsigned int) sl->reg_num.family,
 		 (unsigned long long) sl->reg_num.id);
 	snprintf(&sl->name[0], sizeof(sl->name),
@@ -615,13 +614,13 @@ static int __w1_attach_slave_device(struct w1_slave *sl)
 		 (unsigned long long) sl->reg_num.id);
 
 	dev_dbg(&sl->dev, "%s: registering %s as %p.\n", __func__,
-		&sl->dev.bus_id[0], sl);
+		dev_name(&sl->dev), sl);
 
 	err = device_register(&sl->dev);
 	if (err < 0) {
 		dev_err(&sl->dev,
 			"Device registration [%s] failed. err=%d\n",
-			sl->dev.bus_id, err);
+			dev_name(&sl->dev), err);
 		return err;
 	}
 
@@ -630,7 +629,7 @@ static int __w1_attach_slave_device(struct w1_slave *sl)
 	if (err < 0) {
 		dev_err(&sl->dev,
 			"sysfs file creation for [%s] failed. err=%d\n",
-			sl->dev.bus_id, err);
+			dev_name(&sl->dev), err);
 		goto out_unreg;
 	}
 
@@ -639,7 +638,7 @@ static int __w1_attach_slave_device(struct w1_slave *sl)
 	if (err < 0) {
 		dev_err(&sl->dev,
 			"sysfs file creation for [%s] failed. err=%d\n",
-			sl->dev.bus_id, err);
+			dev_name(&sl->dev), err);
 		goto out_rem1;
 	}
 
@@ -648,7 +647,7 @@ static int __w1_attach_slave_device(struct w1_slave *sl)
 	    ((err = sl->family->fops->add_slave(sl)) < 0)) {
 		dev_err(&sl->dev,
 			"sysfs file creation for [%s] failed. err=%d\n",
-			sl->dev.bus_id, err);
+			dev_name(&sl->dev), err);
 		goto out_rem2;
 	}
 
diff --git a/drivers/w1/w1_int.c b/drivers/w1/w1_int.c
index a3a54567bfba..4a46ed58ece9 100644
--- a/drivers/w1/w1_int.c
+++ b/drivers/w1/w1_int.c
@@ -75,8 +75,7 @@ static struct w1_master * w1_alloc_dev(u32 id, int slave_count, int slave_ttl,
 	mutex_init(&dev->mutex);
 
 	memcpy(&dev->dev, device, sizeof(struct device));
-	snprintf(dev->dev.bus_id, sizeof(dev->dev.bus_id),
-		  "w1_bus_master%u", dev->id);
+	dev_set_name(&dev->dev, "w1_bus_master%u", dev->id);
 	snprintf(dev->name, sizeof(dev->name), "w1_bus_master%u", dev->id);
 
 	dev->driver = driver;
diff --git a/drivers/watchdog/iTCO_wdt.c b/drivers/watchdog/iTCO_wdt.c
index 26173a270e94..5b395a4ddfdf 100644
--- a/drivers/watchdog/iTCO_wdt.c
+++ b/drivers/watchdog/iTCO_wdt.c
@@ -392,7 +392,7 @@ static int iTCO_wdt_stop(void)
 
 	/* Bit 13: TCO_EN -> 1 = Enables the TCO logic to generate SMI# */
 	val32 = inl(SMI_EN);
-	val32 &= 0x00002000;
+	val32 |= 0x00002000;
 	outl(val32, SMI_EN);
 
 	/* Set the NO_REBOOT bit to prevent later reboots, just for sure */
diff --git a/drivers/watchdog/s3c2410_wdt.c b/drivers/watchdog/s3c2410_wdt.c
index f7f6ce82a5e2..e31925ee8346 100644
--- a/drivers/watchdog/s3c2410_wdt.c
+++ b/drivers/watchdog/s3c2410_wdt.c
@@ -42,7 +42,7 @@
 #undef S3C_VA_WATCHDOG
 #define S3C_VA_WATCHDOG (0)
 
-#include <asm/plat-s3c/regs-watchdog.h>
+#include <plat/regs-watchdog.h>
 
 #define PFX "s3c2410-wdt: "
 
diff --git a/drivers/watchdog/sa1100_wdt.c b/drivers/watchdog/sa1100_wdt.c
index ed01e4c2beff..d6fbb4657210 100644
--- a/drivers/watchdog/sa1100_wdt.c
+++ b/drivers/watchdog/sa1100_wdt.c
@@ -27,6 +27,7 @@
 #include <linux/init.h>
 #include <linux/bitops.h>
 #include <linux/uaccess.h>
+#include <linux/timex.h>
 
 #ifdef CONFIG_ARCH_PXA
 #include <mach/pxa-regs.h>
diff --git a/drivers/xen/xenbus/xenbus_probe.c b/drivers/xen/xenbus/xenbus_probe.c
index 7f24a98a446f..b2a03184a246 100644
--- a/drivers/xen/xenbus/xenbus_probe.c
+++ b/drivers/xen/xenbus/xenbus_probe.c
@@ -99,15 +99,15 @@ static int xenbus_uevent(struct device *_dev, struct kobj_uevent_env *env)
 }
 
 /* device/<type>/<id> => <type>-<id> */
-static int frontend_bus_id(char bus_id[BUS_ID_SIZE], const char *nodename)
+static int frontend_bus_id(char bus_id[XEN_BUS_ID_SIZE], const char *nodename)
 {
 	nodename = strchr(nodename, '/');
-	if (!nodename || strlen(nodename + 1) >= BUS_ID_SIZE) {
+	if (!nodename || strlen(nodename + 1) >= XEN_BUS_ID_SIZE) {
 		printk(KERN_WARNING "XENBUS: bad frontend %s\n", nodename);
 		return -EINVAL;
 	}
 
-	strlcpy(bus_id, nodename + 1, BUS_ID_SIZE);
+	strlcpy(bus_id, nodename + 1, XEN_BUS_ID_SIZE);
 	if (!strchr(bus_id, '/')) {
 		printk(KERN_WARNING "XENBUS: bus_id %s no slash\n", bus_id);
 		return -EINVAL;
@@ -460,6 +460,7 @@ int xenbus_probe_node(struct xen_bus_type *bus,
 		      const char *type,
 		      const char *nodename)
 {
+	char devname[XEN_BUS_ID_SIZE];
 	int err;
 	struct xenbus_device *xendev;
 	size_t stringlen;
@@ -494,10 +495,12 @@ int xenbus_probe_node(struct xen_bus_type *bus,
 	xendev->dev.bus = &bus->bus;
 	xendev->dev.release = xenbus_dev_release;
 
-	err = bus->get_bus_id(xendev->dev.bus_id, xendev->nodename);
+	err = bus->get_bus_id(devname, xendev->nodename);
 	if (err)
 		goto fail;
 
+	dev_set_name(&xendev->dev, devname);
+
 	/* Register with generic device framework. */
 	err = device_register(&xendev->dev);
 	if (err)
@@ -611,7 +614,7 @@ void xenbus_dev_changed(const char *node, struct xen_bus_type *bus)
 {
 	int exists, rootlen;
 	struct xenbus_device *dev;
-	char type[BUS_ID_SIZE];
+	char type[XEN_BUS_ID_SIZE];
 	const char *p, *root;
 
 	if (char_count(node, '/') < 2)
@@ -625,8 +628,8 @@ void xenbus_dev_changed(const char *node, struct xen_bus_type *bus)
 
 	/* backend/<type>/... or device/<type>/... */
 	p = strchr(node, '/') + 1;
-	snprintf(type, BUS_ID_SIZE, "%.*s", (int)strcspn(p, "/"), p);
-	type[BUS_ID_SIZE-1] = '\0';
+	snprintf(type, XEN_BUS_ID_SIZE, "%.*s", (int)strcspn(p, "/"), p);
+	type[XEN_BUS_ID_SIZE-1] = '\0';
 
 	rootlen = strsep_len(node, '/', bus->levels);
 	if (rootlen < 0)
@@ -674,7 +677,7 @@ static int suspend_dev(struct device *dev, void *data)
 		err = drv->suspend(xdev);
 	if (err)
 		printk(KERN_WARNING
-		       "xenbus: suspend %s failed: %i\n", dev->bus_id, err);
+		       "xenbus: suspend %s failed: %i\n", dev_name(dev), err);
 	return 0;
 }
 
@@ -695,7 +698,7 @@ static int suspend_cancel_dev(struct device *dev, void *data)
 	if (err)
 		printk(KERN_WARNING
 		       "xenbus: suspend_cancel %s failed: %i\n",
-		       dev->bus_id, err);
+		       dev_name(dev), err);
 	return 0;
 }
 
@@ -717,7 +720,7 @@ static int resume_dev(struct device *dev, void *data)
 	if (err) {
 		printk(KERN_WARNING
 		       "xenbus: resume (talk_to_otherend) %s failed: %i\n",
-		       dev->bus_id, err);
+		       dev_name(dev), err);
 		return err;
 	}
 
@@ -728,7 +731,7 @@ static int resume_dev(struct device *dev, void *data)
 		if (err) {
 			printk(KERN_WARNING
 			       "xenbus: resume %s failed: %i\n",
-			       dev->bus_id, err);
+			       dev_name(dev), err);
 			return err;
 		}
 	}
@@ -737,7 +740,7 @@ static int resume_dev(struct device *dev, void *data)
 	if (err) {
 		printk(KERN_WARNING
 		       "xenbus_probe: resume (watch_otherend) %s failed: "
-		       "%d.\n", dev->bus_id, err);
+		       "%d.\n", dev_name(dev), err);
 		return err;
 	}
 
diff --git a/drivers/xen/xenbus/xenbus_probe.h b/drivers/xen/xenbus/xenbus_probe.h
index e09b19415a40..6c5e3185a6a2 100644
--- a/drivers/xen/xenbus/xenbus_probe.h
+++ b/drivers/xen/xenbus/xenbus_probe.h
@@ -34,6 +34,8 @@
 #ifndef _XENBUS_PROBE_H
 #define _XENBUS_PROBE_H
 
+#define XEN_BUS_ID_SIZE			20
+
 #ifdef CONFIG_XEN_BACKEND
 extern void xenbus_backend_suspend(int (*fn)(struct device *, void *));
 extern void xenbus_backend_resume(int (*fn)(struct device *, void *));
@@ -52,7 +54,7 @@ struct xen_bus_type
 {
 	char *root;
 	unsigned int levels;
-	int (*get_bus_id)(char bus_id[BUS_ID_SIZE], const char *nodename);
+	int (*get_bus_id)(char bus_id[XEN_BUS_ID_SIZE], const char *nodename);
 	int (*probe)(const char *type, const char *dir);
 	struct bus_type bus;
 };
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index 8fcfa398d350..95a76ff9e01b 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -949,7 +949,7 @@ static int load_elf_binary(struct linux_binprm *bprm, struct pt_regs *regs)
 	set_binfmt(&elf_format);
 
 #ifdef ARCH_HAS_SETUP_ADDITIONAL_PAGES
-	retval = arch_setup_additional_pages(bprm, executable_stack);
+	retval = arch_setup_additional_pages(bprm, !!elf_interpreter);
 	if (retval < 0) {
 		send_sig(SIGKILL, current, 0);
 		goto out;
diff --git a/fs/block_dev.c b/fs/block_dev.c
index db831efbdbbd..99e0ae1a4c78 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -1135,12 +1135,15 @@ static int blkdev_open(struct inode * inode, struct file * filp)
 	if (res)
 		return res;
 
-	if (!(filp->f_mode & FMODE_EXCL))
-		return 0;
+	if (filp->f_mode & FMODE_EXCL) {
+		res = bd_claim(bdev, filp);
+		if (res)
+			goto out_blkdev_put;
+	}
 
-	if (!(res = bd_claim(bdev, filp)))
-		return 0;
+	return 0;
 
+ out_blkdev_put:
 	blkdev_put(bdev, filp->f_mode);
 	return res;
 }
@@ -1203,8 +1206,16 @@ static long block_ioctl(struct file *file, unsigned cmd, unsigned long arg)
 {
 	struct block_device *bdev = I_BDEV(file->f_mapping->host);
 	fmode_t mode = file->f_mode;
+
+	/*
+	 * O_NDELAY can be altered using fcntl(.., F_SETFL, ..), so we have
+	 * to updated it before every ioctl.
+	 */
 	if (file->f_flags & O_NDELAY)
-		mode |= FMODE_NDELAY_NOW;
+		mode |= FMODE_NDELAY;
+	else
+		mode &= ~FMODE_NDELAY;
+
 	return blkdev_ioctl(bdev, mode, cmd, arg);
 }
 
diff --git a/fs/char_dev.c b/fs/char_dev.c
index 700697a72618..5ce907c4364f 100644
--- a/fs/char_dev.c
+++ b/fs/char_dev.c
@@ -482,26 +482,22 @@ void cdev_del(struct cdev *p)
 }
 
 
-static void cdev_default_release(struct kobject *kobj)
+static void cdev_release(struct kobject *kobj)
 {
 	struct cdev *p = container_of(kobj, struct cdev, kobj);
 	cdev_purge(p);
+	if (p->release)
+		p->release(p);
 }
 
-static void cdev_dynamic_release(struct kobject *kobj)
-{
-	struct cdev *p = container_of(kobj, struct cdev, kobj);
-	cdev_purge(p);
-	kfree(p);
-}
-
-static struct kobj_type ktype_cdev_default = {
-	.release	= cdev_default_release,
+static struct kobj_type cdev_ktype = {
+	.release	= cdev_release,
 };
 
-static struct kobj_type ktype_cdev_dynamic = {
-	.release	= cdev_dynamic_release,
-};
+static void cdev_alloc_release(struct cdev *cdev)
+{
+	kfree(cdev);
+}
 
 /**
  * cdev_alloc() - allocate a cdev structure
@@ -510,10 +506,10 @@ static struct kobj_type ktype_cdev_dynamic = {
  */
 struct cdev *cdev_alloc(void)
 {
-	struct cdev *p = kzalloc(sizeof(struct cdev), GFP_KERNEL);
+	struct cdev *p = kmalloc(sizeof(struct cdev), GFP_KERNEL);
 	if (p) {
-		INIT_LIST_HEAD(&p->list);
-		kobject_init(&p->kobj, &ktype_cdev_dynamic);
+		cdev_init(p, NULL);
+		p->release = cdev_alloc_release;
 	}
 	return p;
 }
@@ -530,7 +526,7 @@ void cdev_init(struct cdev *cdev, const struct file_operations *fops)
 {
 	memset(cdev, 0, sizeof *cdev);
 	INIT_LIST_HEAD(&cdev->list);
-	kobject_init(&cdev->kobj, &ktype_cdev_default);
+	kobject_init(&cdev->kobj, &cdev_ktype);
 	cdev->ops = fops;
 }
 
diff --git a/fs/fcntl.c b/fs/fcntl.c
index ac4f7db9f134..549daf8005fb 100644
--- a/fs/fcntl.c
+++ b/fs/fcntl.c
@@ -19,6 +19,7 @@
 #include <linux/signal.h>
 #include <linux/rcupdate.h>
 #include <linux/pid_namespace.h>
+#include <linux/smp_lock.h>
 
 #include <asm/poll.h>
 #include <asm/siginfo.h>
@@ -175,6 +176,11 @@ static int setfl(int fd, struct file * filp, unsigned long arg)
 	if (error)
 		return error;
 
+	/*
+	 * We still need a lock here for now to keep multiple FASYNC calls
+	 * from racing with each other.
+	 */
+	lock_kernel();
 	if ((arg ^ filp->f_flags) & FASYNC) {
 		if (filp->f_op && filp->f_op->fasync) {
 			error = filp->f_op->fasync(fd, filp, (arg & FASYNC) != 0);
@@ -185,6 +191,7 @@ static int setfl(int fd, struct file * filp, unsigned long arg)
 
 	filp->f_flags = (arg & SETFL_MASK) | (filp->f_flags & ~SETFL_MASK);
  out:
+	unlock_kernel();
 	return error;
 }
 
diff --git a/fs/inode.c b/fs/inode.c
index 0487ddba1397..098a2443196f 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -108,84 +108,100 @@ static void wake_up_inode(struct inode *inode)
 	wake_up_bit(&inode->i_state, __I_LOCK);
 }
 
-static struct inode *alloc_inode(struct super_block *sb)
+/**
+ * inode_init_always - perform inode structure intialisation
+ * @sb		- superblock inode belongs to.
+ * @inode	- inode to initialise
+ *
+ * These are initializations that need to be done on every inode
+ * allocation as the fields are not initialised by slab allocation.
+ */
+struct inode *inode_init_always(struct super_block *sb, struct inode *inode)
 {
 	static const struct address_space_operations empty_aops;
 	static struct inode_operations empty_iops;
 	static const struct file_operations empty_fops;
-	struct inode *inode;
-
-	if (sb->s_op->alloc_inode)
-		inode = sb->s_op->alloc_inode(sb);
-	else
-		inode = (struct inode *) kmem_cache_alloc(inode_cachep, GFP_KERNEL);
 
-	if (inode) {
-		struct address_space * const mapping = &inode->i_data;
-
-		inode->i_sb = sb;
-		inode->i_blkbits = sb->s_blocksize_bits;
-		inode->i_flags = 0;
-		atomic_set(&inode->i_count, 1);
-		inode->i_op = &empty_iops;
-		inode->i_fop = &empty_fops;
-		inode->i_nlink = 1;
-		atomic_set(&inode->i_writecount, 0);
-		inode->i_size = 0;
-		inode->i_blocks = 0;
-		inode->i_bytes = 0;
-		inode->i_generation = 0;
+	struct address_space * const mapping = &inode->i_data;
+
+	inode->i_sb = sb;
+	inode->i_blkbits = sb->s_blocksize_bits;
+	inode->i_flags = 0;
+	atomic_set(&inode->i_count, 1);
+	inode->i_op = &empty_iops;
+	inode->i_fop = &empty_fops;
+	inode->i_nlink = 1;
+	atomic_set(&inode->i_writecount, 0);
+	inode->i_size = 0;
+	inode->i_blocks = 0;
+	inode->i_bytes = 0;
+	inode->i_generation = 0;
 #ifdef CONFIG_QUOTA
-		memset(&inode->i_dquot, 0, sizeof(inode->i_dquot));
+	memset(&inode->i_dquot, 0, sizeof(inode->i_dquot));
 #endif
-		inode->i_pipe = NULL;
-		inode->i_bdev = NULL;
-		inode->i_cdev = NULL;
-		inode->i_rdev = 0;
-		inode->dirtied_when = 0;
-		if (security_inode_alloc(inode)) {
-			if (inode->i_sb->s_op->destroy_inode)
-				inode->i_sb->s_op->destroy_inode(inode);
-			else
-				kmem_cache_free(inode_cachep, (inode));
-			return NULL;
-		}
+	inode->i_pipe = NULL;
+	inode->i_bdev = NULL;
+	inode->i_cdev = NULL;
+	inode->i_rdev = 0;
+	inode->dirtied_when = 0;
+	if (security_inode_alloc(inode)) {
+		if (inode->i_sb->s_op->destroy_inode)
+			inode->i_sb->s_op->destroy_inode(inode);
+		else
+			kmem_cache_free(inode_cachep, (inode));
+		return NULL;
+	}
 
-		spin_lock_init(&inode->i_lock);
-		lockdep_set_class(&inode->i_lock, &sb->s_type->i_lock_key);
+	spin_lock_init(&inode->i_lock);
+	lockdep_set_class(&inode->i_lock, &sb->s_type->i_lock_key);
 
-		mutex_init(&inode->i_mutex);
-		lockdep_set_class(&inode->i_mutex, &sb->s_type->i_mutex_key);
+	mutex_init(&inode->i_mutex);
+	lockdep_set_class(&inode->i_mutex, &sb->s_type->i_mutex_key);
 
-		init_rwsem(&inode->i_alloc_sem);
-		lockdep_set_class(&inode->i_alloc_sem, &sb->s_type->i_alloc_sem_key);
+	init_rwsem(&inode->i_alloc_sem);
+	lockdep_set_class(&inode->i_alloc_sem, &sb->s_type->i_alloc_sem_key);
 
-		mapping->a_ops = &empty_aops;
- 		mapping->host = inode;
-		mapping->flags = 0;
-		mapping_set_gfp_mask(mapping, GFP_HIGHUSER_PAGECACHE);
-		mapping->assoc_mapping = NULL;
-		mapping->backing_dev_info = &default_backing_dev_info;
-		mapping->writeback_index = 0;
+	mapping->a_ops = &empty_aops;
+	mapping->host = inode;
+	mapping->flags = 0;
+	mapping_set_gfp_mask(mapping, GFP_HIGHUSER_PAGECACHE);
+	mapping->assoc_mapping = NULL;
+	mapping->backing_dev_info = &default_backing_dev_info;
+	mapping->writeback_index = 0;
 
-		/*
-		 * If the block_device provides a backing_dev_info for client
-		 * inodes then use that.  Otherwise the inode share the bdev's
-		 * backing_dev_info.
-		 */
-		if (sb->s_bdev) {
-			struct backing_dev_info *bdi;
+	/*
+	 * If the block_device provides a backing_dev_info for client
+	 * inodes then use that.  Otherwise the inode share the bdev's
+	 * backing_dev_info.
+	 */
+	if (sb->s_bdev) {
+		struct backing_dev_info *bdi;
 
-			bdi = sb->s_bdev->bd_inode_backing_dev_info;
-			if (!bdi)
-				bdi = sb->s_bdev->bd_inode->i_mapping->backing_dev_info;
-			mapping->backing_dev_info = bdi;
-		}
-		inode->i_private = NULL;
-		inode->i_mapping = mapping;
+		bdi = sb->s_bdev->bd_inode_backing_dev_info;
+		if (!bdi)
+			bdi = sb->s_bdev->bd_inode->i_mapping->backing_dev_info;
+		mapping->backing_dev_info = bdi;
 	}
+	inode->i_private = NULL;
+	inode->i_mapping = mapping;
+
 	return inode;
 }
+EXPORT_SYMBOL(inode_init_always);
+
+static struct inode *alloc_inode(struct super_block *sb)
+{
+	struct inode *inode;
+
+	if (sb->s_op->alloc_inode)
+		inode = sb->s_op->alloc_inode(sb);
+	else
+		inode = kmem_cache_alloc(inode_cachep, GFP_KERNEL);
+
+	if (inode)
+		return inode_init_always(sb, inode);
+	return NULL;
+}
 
 void destroy_inode(struct inode *inode) 
 {
@@ -196,6 +212,7 @@ void destroy_inode(struct inode *inode)
 	else
 		kmem_cache_free(inode_cachep, (inode));
 }
+EXPORT_SYMBOL(destroy_inode);
 
 
 /*
@@ -534,6 +551,49 @@ repeat:
 	return node ? inode : NULL;
 }
 
+static unsigned long hash(struct super_block *sb, unsigned long hashval)
+{
+	unsigned long tmp;
+
+	tmp = (hashval * (unsigned long)sb) ^ (GOLDEN_RATIO_PRIME + hashval) /
+			L1_CACHE_BYTES;
+	tmp = tmp ^ ((tmp ^ GOLDEN_RATIO_PRIME) >> I_HASHBITS);
+	return tmp & I_HASHMASK;
+}
+
+static inline void
+__inode_add_to_lists(struct super_block *sb, struct hlist_head *head,
+			struct inode *inode)
+{
+	inodes_stat.nr_inodes++;
+	list_add(&inode->i_list, &inode_in_use);
+	list_add(&inode->i_sb_list, &sb->s_inodes);
+	if (head)
+		hlist_add_head(&inode->i_hash, head);
+}
+
+/**
+ * inode_add_to_lists - add a new inode to relevant lists
+ * @sb		- superblock inode belongs to.
+ * @inode	- inode to mark in use
+ *
+ * When an inode is allocated it needs to be accounted for, added to the in use
+ * list, the owning superblock and the inode hash. This needs to be done under
+ * the inode_lock, so export a function to do this rather than the inode lock
+ * itself. We calculate the hash list to add to here so it is all internal
+ * which requires the caller to have already set up the inode number in the
+ * inode to add.
+ */
+void inode_add_to_lists(struct super_block *sb, struct inode *inode)
+{
+	struct hlist_head *head = inode_hashtable + hash(sb, inode->i_ino);
+
+	spin_lock(&inode_lock);
+	__inode_add_to_lists(sb, head, inode);
+	spin_unlock(&inode_lock);
+}
+EXPORT_SYMBOL_GPL(inode_add_to_lists);
+
 /**
  *	new_inode 	- obtain an inode
  *	@sb: superblock
@@ -561,9 +621,7 @@ struct inode *new_inode(struct super_block *sb)
 	inode = alloc_inode(sb);
 	if (inode) {
 		spin_lock(&inode_lock);
-		inodes_stat.nr_inodes++;
-		list_add(&inode->i_list, &inode_in_use);
-		list_add(&inode->i_sb_list, &sb->s_inodes);
+		__inode_add_to_lists(sb, NULL, inode);
 		inode->i_ino = ++last_ino;
 		inode->i_state = 0;
 		spin_unlock(&inode_lock);
@@ -622,10 +680,7 @@ static struct inode * get_new_inode(struct super_block *sb, struct hlist_head *h
 			if (set(inode, data))
 				goto set_failed;
 
-			inodes_stat.nr_inodes++;
-			list_add(&inode->i_list, &inode_in_use);
-			list_add(&inode->i_sb_list, &sb->s_inodes);
-			hlist_add_head(&inode->i_hash, head);
+			__inode_add_to_lists(sb, head, inode);
 			inode->i_state = I_LOCK|I_NEW;
 			spin_unlock(&inode_lock);
 
@@ -671,10 +726,7 @@ static struct inode * get_new_inode_fast(struct super_block *sb, struct hlist_he
 		old = find_inode_fast(sb, head, ino);
 		if (!old) {
 			inode->i_ino = ino;
-			inodes_stat.nr_inodes++;
-			list_add(&inode->i_list, &inode_in_use);
-			list_add(&inode->i_sb_list, &sb->s_inodes);
-			hlist_add_head(&inode->i_hash, head);
+			__inode_add_to_lists(sb, head, inode);
 			inode->i_state = I_LOCK|I_NEW;
 			spin_unlock(&inode_lock);
 
@@ -698,16 +750,6 @@ static struct inode * get_new_inode_fast(struct super_block *sb, struct hlist_he
 	return inode;
 }
 
-static unsigned long hash(struct super_block *sb, unsigned long hashval)
-{
-	unsigned long tmp;
-
-	tmp = (hashval * (unsigned long)sb) ^ (GOLDEN_RATIO_PRIME + hashval) /
-			L1_CACHE_BYTES;
-	tmp = tmp ^ ((tmp ^ GOLDEN_RATIO_PRIME) >> I_HASHBITS);
-	return tmp & I_HASHMASK;
-}
-
 /**
  *	iunique - get a unique inode number
  *	@sb: superblock
@@ -1292,6 +1334,7 @@ int inode_wait(void *word)
 	schedule();
 	return 0;
 }
+EXPORT_SYMBOL(inode_wait);
 
 /*
  * If we try to find an inode in the inode hash while it is being
diff --git a/fs/ioctl.c b/fs/ioctl.c
index d152856c371b..43e8b2c0664b 100644
--- a/fs/ioctl.c
+++ b/fs/ioctl.c
@@ -400,11 +400,9 @@ static int ioctl_fioasync(unsigned int fd, struct file *filp,
 
 	/* Did FASYNC state change ? */
 	if ((flag ^ filp->f_flags) & FASYNC) {
-		if (filp->f_op && filp->f_op->fasync) {
-			lock_kernel();
+		if (filp->f_op && filp->f_op->fasync)
 			error = filp->f_op->fasync(fd, filp, on);
-			unlock_kernel();
-		} else
+		else
 			error = -ENOTTY;
 	}
 	if (error)
@@ -440,11 +438,17 @@ int do_vfs_ioctl(struct file *filp, unsigned int fd, unsigned int cmd,
 		break;
 
 	case FIONBIO:
+		/* BKL needed to avoid races tweaking f_flags */
+		lock_kernel();
 		error = ioctl_fionbio(filp, argp);
+		unlock_kernel();
 		break;
 
 	case FIOASYNC:
+		/* BKL needed to avoid races tweaking f_flags */
+		lock_kernel();
 		error = ioctl_fioasync(fd, filp, argp);
+		unlock_kernel();
 		break;
 
 	case FIOQSIZE:
diff --git a/fs/lockd/host.c b/fs/lockd/host.c
index 9fd8889097b7..ec733ea7d5f6 100644
--- a/fs/lockd/host.c
+++ b/fs/lockd/host.c
@@ -111,9 +111,6 @@ static void nlm_display_address(const struct sockaddr *sap,
 	const struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)sap;
 
 	switch (sap->sa_family) {
-	case AF_UNSPEC:
-		snprintf(buf, len, "unspecified");
-		break;
 	case AF_INET:
 		snprintf(buf, len, NIPQUAD_FMT, NIPQUAD(sin->sin_addr.s_addr));
 		break;
@@ -167,7 +164,8 @@ static struct nlm_host *nlm_lookup_host(struct nlm_lookup_host_info *ni)
 			continue;
 		if (host->h_server != ni->server)
 			continue;
-		if (!nlm_cmp_addr(nlm_srcaddr(host), ni->src_sap))
+		if (ni->server &&
+		    !nlm_cmp_addr(nlm_srcaddr(host), ni->src_sap))
 			continue;
 
 		/* Move to head of hash chain. */
@@ -176,7 +174,7 @@ static struct nlm_host *nlm_lookup_host(struct nlm_lookup_host_info *ni)
 
 		nlm_get_host(host);
 		dprintk("lockd: nlm_lookup_host found host %s (%s)\n",
-				host->h_name, host->h_addrbuf);
+				host->h_name, nsm->sm_addrbuf);
 		goto out;
 	}
 
@@ -229,11 +227,6 @@ static struct nlm_host *nlm_lookup_host(struct nlm_lookup_host_info *ni)
 
 	nrhosts++;
 
-	nlm_display_address((struct sockaddr *)&host->h_addr,
-				host->h_addrbuf, sizeof(host->h_addrbuf));
-	nlm_display_address((struct sockaddr *)&host->h_srcaddr,
-				host->h_srcaddrbuf, sizeof(host->h_srcaddrbuf));
-
 	dprintk("lockd: nlm_lookup_host created host %s\n",
 			host->h_name);
 
@@ -371,8 +364,8 @@ nlm_bind_host(struct nlm_host *host)
 {
 	struct rpc_clnt	*clnt;
 
-	dprintk("lockd: nlm_bind_host %s (%s), my addr=%s\n",
-			host->h_name, host->h_addrbuf, host->h_srcaddrbuf);
+	dprintk("lockd: nlm_bind_host %s (%s)\n",
+			host->h_name, host->h_nsmhandle->sm_addrbuf);
 
 	/* Lock host handle */
 	mutex_lock(&host->h_mutex);
diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c
index c631a83931ce..c312df718911 100644
--- a/fs/lockd/svc.c
+++ b/fs/lockd/svc.c
@@ -62,6 +62,9 @@ static unsigned long		nlm_timeout = LOCKD_DFLT_TIMEO;
 static int			nlm_udpport, nlm_tcpport;
 int				nsm_use_hostnames = 0;
 
+/* RLIM_NOFILE defaults to 1024. That seems like a reasonable default here. */
+static unsigned int		nlm_max_connections = 1024;
+
 /*
  * Constants needed for the sysctl interface.
  */
@@ -143,6 +146,9 @@ lockd(void *vrqstp)
 		long timeout = MAX_SCHEDULE_TIMEOUT;
 		RPC_IFDEBUG(char buf[RPC_MAX_ADDRBUFLEN]);
 
+		/* update sv_maxconn if it has changed */
+		rqstp->rq_server->sv_maxconn = nlm_max_connections;
+
 		if (signalled()) {
 			flush_signals(current);
 			if (nlmsvc_ops) {
@@ -181,6 +187,7 @@ lockd(void *vrqstp)
 	}
 	flush_signals(current);
 	cancel_delayed_work_sync(&grace_period_end);
+	locks_end_grace(&lockd_manager);
 	if (nlmsvc_ops)
 		nlmsvc_invalidate_all();
 	nlm_shutdown_hosts();
@@ -275,6 +282,7 @@ int lockd_up(void)
 	}
 
 	svc_sock_update_bufs(serv);
+	serv->sv_maxconn = nlm_max_connections;
 
 	nlmsvc_task = kthread_run(lockd, nlmsvc_rqst, serv->sv_name);
 	if (IS_ERR(nlmsvc_task)) {
@@ -484,6 +492,7 @@ module_param_call(nlm_udpport, param_set_port, param_get_int,
 module_param_call(nlm_tcpport, param_set_port, param_get_int,
 		  &nlm_tcpport, 0644);
 module_param(nsm_use_hostnames, bool, 0644);
+module_param(nlm_max_connections, uint, 0644);
 
 /*
  * Initialising and terminating the module.
diff --git a/fs/nfsd/nfs4recover.c b/fs/nfsd/nfs4recover.c
index bb93946ace22..cf94563f5fd5 100644
--- a/fs/nfsd/nfs4recover.c
+++ b/fs/nfsd/nfs4recover.c
@@ -110,9 +110,9 @@ nfs4_make_rec_clidname(char *dname, struct xdr_netobj *clname)
 
 	md5_to_hex(dname, cksum.data);
 
-	kfree(cksum.data);
 	status = nfs_ok;
 out:
+	kfree(cksum.data);
 	crypto_free_hash(desc.tfm);
 out_no_tfm:
 	return status;
@@ -225,12 +225,12 @@ nfsd4_list_rec_dir(struct dentry *dir, recdir_func *f)
 		return 0;
 
 	nfs4_save_user(&uid, &gid);
+	INIT_LIST_HEAD(dentries);
 
 	filp = dentry_open(dget(dir), mntget(rec_dir.mnt), O_RDONLY);
 	status = PTR_ERR(filp);
 	if (IS_ERR(filp))
 		goto out;
-	INIT_LIST_HEAD(dentries);
 	status = vfs_readdir(filp, nfsd4_build_dentrylist, &dla);
 	fput(filp);
 	while (!list_empty(dentries)) {
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index b0bebc552a11..0e2720d12864 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -2423,13 +2423,13 @@ static struct list_head lockstateid_hashtbl[STATEID_HASH_SIZE];
 static struct nfs4_stateid *
 find_stateid(stateid_t *stid, int flags)
 {
-	struct nfs4_stateid *local = NULL;
+	struct nfs4_stateid *local;
 	u32 st_id = stid->si_stateownerid;
 	u32 f_id = stid->si_fileid;
 	unsigned int hashval;
 
 	dprintk("NFSD: find_stateid flags 0x%x\n",flags);
-	if ((flags & LOCK_STATE) || (flags & RD_STATE) || (flags & WR_STATE)) {
+	if (flags & (LOCK_STATE | RD_STATE | WR_STATE)) {
 		hashval = stateid_hashval(st_id, f_id);
 		list_for_each_entry(local, &lockstateid_hashtbl[hashval], st_hash) {
 			if ((local->st_stateid.si_stateownerid == st_id) &&
@@ -2437,7 +2437,8 @@ find_stateid(stateid_t *stid, int flags)
 				return local;
 		}
 	} 
-	if ((flags & OPEN_STATE) || (flags & RD_STATE) || (flags & WR_STATE)) {
+
+	if (flags & (OPEN_STATE | RD_STATE | WR_STATE)) {
 		hashval = stateid_hashval(st_id, f_id);
 		list_for_each_entry(local, &stateid_hashtbl[hashval], st_hash) {
 			if ((local->st_stateid.si_stateownerid == st_id) &&
@@ -3261,6 +3262,7 @@ nfs4_state_shutdown(void)
 {
 	cancel_rearming_delayed_workqueue(laundry_wq, &laundromat_work);
 	destroy_workqueue(laundry_wq);
+	locks_end_grace(&nfsd4_manager);
 	nfs4_lock_state();
 	nfs4_release_reclaim();
 	__nfs4_state_shutdown();
diff --git a/fs/nfsd/nfsfh.c b/fs/nfsd/nfsfh.c
index cd25d91895a1..8cabcfae1e62 100644
--- a/fs/nfsd/nfsfh.c
+++ b/fs/nfsd/nfsfh.c
@@ -253,14 +253,32 @@ out:
 	return error;
 }
 
-/*
- * Perform sanity checks on the dentry in a client's file handle.
+/**
+ * fh_verify - filehandle lookup and access checking
+ * @rqstp: pointer to current rpc request
+ * @fhp: filehandle to be verified
+ * @type: expected type of object pointed to by filehandle
+ * @access: type of access needed to object
+ *
+ * Look up a dentry from the on-the-wire filehandle, check the client's
+ * access to the export, and set the current task's credentials.
+ *
+ * Regardless of success or failure of fh_verify(), fh_put() should be
+ * called on @fhp when the caller is finished with the filehandle.
+ *
+ * fh_verify() may be called multiple times on a given filehandle, for
+ * example, when processing an NFSv4 compound.  The first call will look
+ * up a dentry using the on-the-wire filehandle.  Subsequent calls will
+ * skip the lookup and just perform the other checks and possibly change
+ * the current task's credentials.
  *
- * Note that the file handle dentry may need to be freed even after
- * an error return.
+ * @type specifies the type of object expected using one of the S_IF*
+ * constants defined in include/linux/stat.h.  The caller may use zero
+ * to indicate that it doesn't care, or a negative integer to indicate
+ * that it expects something not of the given type.
  *
- * This is only called at the start of an nfsproc call, so fhp points to
- * a svc_fh which is all 0 except for the over-the-wire file handle.
+ * @access is formed from the NFSD_MAY_* constants defined in
+ * include/linux/nfsd/nfsd.h.
  */
 __be32
 fh_verify(struct svc_rqst *rqstp, struct svc_fh *fhp, int type, int access)
diff --git a/fs/partitions/check.c b/fs/partitions/check.c
index 6d5b213b8a9b..5198ada67398 100644
--- a/fs/partitions/check.c
+++ b/fs/partitions/check.c
@@ -384,9 +384,9 @@ struct hd_struct *add_partition(struct gendisk *disk, int partno,
 
 	dname = dev_name(ddev);
 	if (isdigit(dname[strlen(dname) - 1]))
-		snprintf(pdev->bus_id, BUS_ID_SIZE, "%sp%d", dname, partno);
+		dev_set_name(pdev, "%sp%d", dname, partno);
 	else
-		snprintf(pdev->bus_id, BUS_ID_SIZE, "%s%d", dname, partno);
+		dev_set_name(pdev, "%s%d", dname, partno);
 
 	device_initialize(pdev);
 	pdev->class = &block_class;
@@ -447,16 +447,11 @@ void register_disk(struct gendisk *disk)
 	struct block_device *bdev;
 	struct disk_part_iter piter;
 	struct hd_struct *part;
-	char *s;
 	int err;
 
 	ddev->parent = disk->driverfs_dev;
 
-	strlcpy(ddev->bus_id, disk->disk_name, BUS_ID_SIZE);
-	/* ewww... some of these buggers have / in the name... */
-	s = strchr(ddev->bus_id, '/');
-	if (s)
-		*s = '!';
+	dev_set_name(ddev, disk->disk_name);
 
 	/* delay uevents, until we scanned partition table */
 	ddev->uevent_suppress = 1;
diff --git a/fs/seq_file.c b/fs/seq_file.c
index eba2eabcd2b8..f03220d7891b 100644
--- a/fs/seq_file.c
+++ b/fs/seq_file.c
@@ -357,7 +357,18 @@ int seq_printf(struct seq_file *m, const char *f, ...)
 }
 EXPORT_SYMBOL(seq_printf);
 
-static char *mangle_path(char *s, char *p, char *esc)
+/**
+ *	mangle_path -	mangle and copy path to buffer beginning
+ *	@s: buffer start
+ *	@p: beginning of path in above buffer
+ *	@esc: set of characters that need escaping
+ *
+ *      Copy the path from @p to @s, replacing each occurrence of character from
+ *      @esc with usual octal escape.
+ *      Returns pointer past last written character in @s, or NULL in case of
+ *      failure.
+ */
+char *mangle_path(char *s, char *p, char *esc)
 {
 	while (s <= p) {
 		char c = *p++;
@@ -376,6 +387,7 @@ static char *mangle_path(char *s, char *p, char *esc)
 	}
 	return NULL;
 }
+EXPORT_SYMBOL_GPL(mangle_path);
 
 /*
  * return the absolute path of 'dentry' residing in mount 'mnt'.
diff --git a/fs/xfs/Makefile b/fs/xfs/Makefile
index 737c9a425361..c3dc491fff89 100644
--- a/fs/xfs/Makefile
+++ b/fs/xfs/Makefile
@@ -85,13 +85,13 @@ xfs-y				+= xfs_alloc.o \
 				   xfs_trans_inode.o \
 				   xfs_trans_item.o \
 				   xfs_utils.o \
-				   xfs_vfsops.o \
 				   xfs_vnodeops.o \
 				   xfs_rw.o \
 				   xfs_dmops.o \
 				   xfs_qmops.o
 
-xfs-$(CONFIG_XFS_TRACE)		+= xfs_dir2_trace.o
+xfs-$(CONFIG_XFS_TRACE)		+= xfs_btree_trace.o \
+				   xfs_dir2_trace.o
 
 # Objects in linux/
 xfs-y				+= $(addprefix $(XFS_LINUX)/, \
@@ -106,7 +106,7 @@ xfs-y				+= $(addprefix $(XFS_LINUX)/, \
 				   xfs_iops.o \
 				   xfs_lrw.o \
 				   xfs_super.o \
-				   xfs_vnode.o \
+				   xfs_sync.o \
 				   xfs_xattr.o)
 
 # Objects in support/
diff --git a/fs/xfs/linux-2.6/sv.h b/fs/xfs/linux-2.6/sv.h
index 351a8f454bd1..4dfc7c370819 100644
--- a/fs/xfs/linux-2.6/sv.h
+++ b/fs/xfs/linux-2.6/sv.h
@@ -32,23 +32,15 @@ typedef struct sv_s {
 	wait_queue_head_t waiters;
 } sv_t;
 
-#define SV_FIFO		0x0		/* sv_t is FIFO type */
-#define SV_LIFO		0x2		/* sv_t is LIFO type */
-#define SV_PRIO		0x4		/* sv_t is PRIO type */
-#define SV_KEYED	0x6		/* sv_t is KEYED type */
-#define SV_DEFAULT      SV_FIFO
-
-
-static inline void _sv_wait(sv_t *sv, spinlock_t *lock, int state,
-			     unsigned long timeout)
+static inline void _sv_wait(sv_t *sv, spinlock_t *lock)
 {
 	DECLARE_WAITQUEUE(wait, current);
 
 	add_wait_queue_exclusive(&sv->waiters, &wait);
-	__set_current_state(state);
+	__set_current_state(TASK_UNINTERRUPTIBLE);
 	spin_unlock(lock);
 
-	schedule_timeout(timeout);
+	schedule();
 
 	remove_wait_queue(&sv->waiters, &wait);
 }
@@ -58,13 +50,7 @@ static inline void _sv_wait(sv_t *sv, spinlock_t *lock, int state,
 #define sv_destroy(sv) \
 	/*NOTHING*/
 #define sv_wait(sv, pri, lock, s) \
-	_sv_wait(sv, lock, TASK_UNINTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT)
-#define sv_wait_sig(sv, pri, lock, s)   \
-	_sv_wait(sv, lock, TASK_INTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT)
-#define sv_timedwait(sv, pri, lock, s, svf, ts, rts) \
-	_sv_wait(sv, lock, TASK_UNINTERRUPTIBLE, timespec_to_jiffies(ts))
-#define sv_timedwait_sig(sv, pri, lock, s, svf, ts, rts) \
-	_sv_wait(sv, lock, TASK_INTERRUPTIBLE, timespec_to_jiffies(ts))
+	_sv_wait(sv, lock)
 #define sv_signal(sv) \
 	wake_up(&(sv)->waiters)
 #define sv_broadcast(sv) \
diff --git a/fs/xfs/linux-2.6/xfs_aops.c b/fs/xfs/linux-2.6/xfs_aops.c
index a44d68eb50b5..de3a198f771e 100644
--- a/fs/xfs/linux-2.6/xfs_aops.c
+++ b/fs/xfs/linux-2.6/xfs_aops.c
@@ -42,6 +42,40 @@
 #include <linux/pagevec.h>
 #include <linux/writeback.h>
 
+
+/*
+ * Prime number of hash buckets since address is used as the key.
+ */
+#define NVSYNC		37
+#define to_ioend_wq(v)	(&xfs_ioend_wq[((unsigned long)v) % NVSYNC])
+static wait_queue_head_t xfs_ioend_wq[NVSYNC];
+
+void __init
+xfs_ioend_init(void)
+{
+	int i;
+
+	for (i = 0; i < NVSYNC; i++)
+		init_waitqueue_head(&xfs_ioend_wq[i]);
+}
+
+void
+xfs_ioend_wait(
+	xfs_inode_t	*ip)
+{
+	wait_queue_head_t *wq = to_ioend_wq(ip);
+
+	wait_event(*wq, (atomic_read(&ip->i_iocount) == 0));
+}
+
+STATIC void
+xfs_ioend_wake(
+	xfs_inode_t	*ip)
+{
+	if (atomic_dec_and_test(&ip->i_iocount))
+		wake_up(to_ioend_wq(ip));
+}
+
 STATIC void
 xfs_count_page_state(
 	struct page		*page,
@@ -146,16 +180,25 @@ xfs_destroy_ioend(
 	xfs_ioend_t		*ioend)
 {
 	struct buffer_head	*bh, *next;
+	struct xfs_inode	*ip = XFS_I(ioend->io_inode);
 
 	for (bh = ioend->io_buffer_head; bh; bh = next) {
 		next = bh->b_private;
 		bh->b_end_io(bh, !ioend->io_error);
 	}
-	if (unlikely(ioend->io_error)) {
-		vn_ioerror(XFS_I(ioend->io_inode), ioend->io_error,
-				__FILE__,__LINE__);
+
+	/*
+	 * Volume managers supporting multiple paths can send back ENODEV
+	 * when the final path disappears.  In this case continuing to fill
+	 * the page cache with dirty data which cannot be written out is
+	 * evil, so prevent that.
+	 */
+	if (unlikely(ioend->io_error == -ENODEV)) {
+		xfs_do_force_shutdown(ip->i_mount, SHUTDOWN_DEVICE_REQ,
+				      __FILE__, __LINE__);
 	}
-	vn_iowake(XFS_I(ioend->io_inode));
+
+	xfs_ioend_wake(ip);
 	mempool_free(ioend, xfs_ioend_pool);
 }
 
@@ -191,7 +234,7 @@ xfs_setfilesize(
 		ip->i_d.di_size = isize;
 		ip->i_update_core = 1;
 		ip->i_update_size = 1;
-		mark_inode_dirty_sync(ioend->io_inode);
+		xfs_mark_inode_dirty_sync(ip);
 	}
 
 	xfs_iunlock(ip, XFS_ILOCK_EXCL);
@@ -317,14 +360,9 @@ xfs_map_blocks(
 	xfs_iomap_t		*mapp,
 	int			flags)
 {
-	xfs_inode_t		*ip = XFS_I(inode);
-	int			error, nmaps = 1;
-
-	error = xfs_iomap(ip, offset, count,
-				flags, mapp, &nmaps);
-	if (!error && (flags & (BMAPI_WRITE|BMAPI_ALLOCATE)))
-		xfs_iflags_set(ip, XFS_IMODIFIED);
-	return -error;
+	int			nmaps = 1;
+
+	return -xfs_iomap(XFS_I(inode), offset, count, flags, mapp, &nmaps);
 }
 
 STATIC_INLINE int
@@ -512,7 +550,7 @@ xfs_cancel_ioend(
 			unlock_buffer(bh);
 		} while ((bh = next_bh) != NULL);
 
-		vn_iowake(XFS_I(ioend->io_inode));
+		xfs_ioend_wake(XFS_I(ioend->io_inode));
 		mempool_free(ioend, xfs_ioend_pool);
 	} while ((ioend = next) != NULL);
 }
diff --git a/fs/xfs/linux-2.6/xfs_aops.h b/fs/xfs/linux-2.6/xfs_aops.h
index 3ba0631a3818..7b26f5ff9692 100644
--- a/fs/xfs/linux-2.6/xfs_aops.h
+++ b/fs/xfs/linux-2.6/xfs_aops.h
@@ -43,4 +43,7 @@ typedef struct xfs_ioend {
 extern const struct address_space_operations xfs_address_space_operations;
 extern int xfs_get_blocks(struct inode *, sector_t, struct buffer_head *, int);
 
+extern void xfs_ioend_init(void);
+extern void xfs_ioend_wait(struct xfs_inode *);
+
 #endif /* __XFS_AOPS_H__ */
diff --git a/fs/xfs/linux-2.6/xfs_buf.c b/fs/xfs/linux-2.6/xfs_buf.c
index 36d5fcd3f593..cd89c56715a5 100644
--- a/fs/xfs/linux-2.6/xfs_buf.c
+++ b/fs/xfs/linux-2.6/xfs_buf.c
@@ -630,6 +630,29 @@ xfs_buf_get_flags(
 	return NULL;
 }
 
+STATIC int
+_xfs_buf_read(
+	xfs_buf_t		*bp,
+	xfs_buf_flags_t		flags)
+{
+	int			status;
+
+	XB_TRACE(bp, "_xfs_buf_read", (unsigned long)flags);
+
+	ASSERT(!(flags & (XBF_DELWRI|XBF_WRITE)));
+	ASSERT(bp->b_bn != XFS_BUF_DADDR_NULL);
+
+	bp->b_flags &= ~(XBF_WRITE | XBF_ASYNC | XBF_DELWRI | \
+			XBF_READ_AHEAD | _XBF_RUN_QUEUES);
+	bp->b_flags |= flags & (XBF_READ | XBF_ASYNC | \
+			XBF_READ_AHEAD | _XBF_RUN_QUEUES);
+
+	status = xfs_buf_iorequest(bp);
+	if (!status && !(flags & XBF_ASYNC))
+		status = xfs_buf_iowait(bp);
+	return status;
+}
+
 xfs_buf_t *
 xfs_buf_read_flags(
 	xfs_buftarg_t		*target,
@@ -646,7 +669,7 @@ xfs_buf_read_flags(
 		if (!XFS_BUF_ISDONE(bp)) {
 			XB_TRACE(bp, "read", (unsigned long)flags);
 			XFS_STATS_INC(xb_get_read);
-			xfs_buf_iostart(bp, flags);
+			_xfs_buf_read(bp, flags);
 		} else if (flags & XBF_ASYNC) {
 			XB_TRACE(bp, "read_async", (unsigned long)flags);
 			/*
@@ -1048,50 +1071,39 @@ xfs_buf_ioerror(
 	XB_TRACE(bp, "ioerror", (unsigned long)error);
 }
 
-/*
- *	Initiate I/O on a buffer, based on the flags supplied.
- *	The b_iodone routine in the buffer supplied will only be called
- *	when all of the subsidiary I/O requests, if any, have been completed.
- */
 int
-xfs_buf_iostart(
-	xfs_buf_t		*bp,
-	xfs_buf_flags_t		flags)
+xfs_bawrite(
+	void			*mp,
+	struct xfs_buf		*bp)
 {
-	int			status = 0;
+	XB_TRACE(bp, "bawrite", 0);
 
-	XB_TRACE(bp, "iostart", (unsigned long)flags);
+	ASSERT(bp->b_bn != XFS_BUF_DADDR_NULL);
 
-	if (flags & XBF_DELWRI) {
-		bp->b_flags &= ~(XBF_READ | XBF_WRITE | XBF_ASYNC);
-		bp->b_flags |= flags & (XBF_DELWRI | XBF_ASYNC);
-		xfs_buf_delwri_queue(bp, 1);
-		return 0;
-	}
+	xfs_buf_delwri_dequeue(bp);
 
-	bp->b_flags &= ~(XBF_READ | XBF_WRITE | XBF_ASYNC | XBF_DELWRI | \
-			XBF_READ_AHEAD | _XBF_RUN_QUEUES);
-	bp->b_flags |= flags & (XBF_READ | XBF_WRITE | XBF_ASYNC | \
-			XBF_READ_AHEAD | _XBF_RUN_QUEUES);
+	bp->b_flags &= ~(XBF_READ | XBF_DELWRI | XBF_READ_AHEAD);
+	bp->b_flags |= (XBF_WRITE | XBF_ASYNC | _XBF_RUN_QUEUES);
+
+	bp->b_fspriv3 = mp;
+	bp->b_strat = xfs_bdstrat_cb;
+	return xfs_bdstrat_cb(bp);
+}
 
-	BUG_ON(bp->b_bn == XFS_BUF_DADDR_NULL);
+void
+xfs_bdwrite(
+	void			*mp,
+	struct xfs_buf		*bp)
+{
+	XB_TRACE(bp, "bdwrite", 0);
 
-	/* For writes allow an alternate strategy routine to precede
-	 * the actual I/O request (which may not be issued at all in
-	 * a shutdown situation, for example).
-	 */
-	status = (flags & XBF_WRITE) ?
-		xfs_buf_iostrategy(bp) : xfs_buf_iorequest(bp);
+	bp->b_strat = xfs_bdstrat_cb;
+	bp->b_fspriv3 = mp;
 
-	/* Wait for I/O if we are not an async request.
-	 * Note: async I/O request completion will release the buffer,
-	 * and that can already be done by this point.  So using the
-	 * buffer pointer from here on, after async I/O, is invalid.
-	 */
-	if (!status && !(flags & XBF_ASYNC))
-		status = xfs_buf_iowait(bp);
+	bp->b_flags &= ~XBF_READ;
+	bp->b_flags |= (XBF_DELWRI | XBF_ASYNC);
 
-	return status;
+	xfs_buf_delwri_queue(bp, 1);
 }
 
 STATIC_INLINE void
diff --git a/fs/xfs/linux-2.6/xfs_buf.h b/fs/xfs/linux-2.6/xfs_buf.h
index 456519a088c7..0e2aa16f5e41 100644
--- a/fs/xfs/linux-2.6/xfs_buf.h
+++ b/fs/xfs/linux-2.6/xfs_buf.h
@@ -214,9 +214,10 @@ extern void xfs_buf_lock(xfs_buf_t *);
 extern void xfs_buf_unlock(xfs_buf_t *);
 
 /* Buffer Read and Write Routines */
+extern int xfs_bawrite(void *mp, xfs_buf_t *bp);
+extern void xfs_bdwrite(void *mp, xfs_buf_t *bp);
 extern void xfs_buf_ioend(xfs_buf_t *,	int);
 extern void xfs_buf_ioerror(xfs_buf_t *, int);
-extern int xfs_buf_iostart(xfs_buf_t *, xfs_buf_flags_t);
 extern int xfs_buf_iorequest(xfs_buf_t *);
 extern int xfs_buf_iowait(xfs_buf_t *);
 extern void xfs_buf_iomove(xfs_buf_t *, size_t, size_t, xfs_caddr_t,
@@ -366,14 +367,6 @@ extern void xfs_buf_trace(xfs_buf_t *, char *, void *, void *);
 #define XFS_BUF_TARGET(bp)		((bp)->b_target)
 #define XFS_BUFTARG_NAME(target)	xfs_buf_target_name(target)
 
-static inline int xfs_bawrite(void *mp, xfs_buf_t *bp)
-{
-	bp->b_fspriv3 = mp;
-	bp->b_strat = xfs_bdstrat_cb;
-	xfs_buf_delwri_dequeue(bp);
-	return xfs_buf_iostart(bp, XBF_WRITE | XBF_ASYNC | _XBF_RUN_QUEUES);
-}
-
 static inline void xfs_buf_relse(xfs_buf_t *bp)
 {
 	if (!bp->b_relse)
@@ -414,17 +407,6 @@ static inline int XFS_bwrite(xfs_buf_t *bp)
 	return error;
 }
 
-/*
- * No error can be returned from xfs_buf_iostart for delwri
- * buffers as they are queued and no I/O is issued.
- */
-static inline void xfs_bdwrite(void *mp, xfs_buf_t *bp)
-{
-	bp->b_strat = xfs_bdstrat_cb;
-	bp->b_fspriv3 = mp;
-	(void)xfs_buf_iostart(bp, XBF_DELWRI | XBF_ASYNC);
-}
-
 #define XFS_bdstrat(bp) xfs_buf_iorequest(bp)
 
 #define xfs_iowait(bp)	xfs_buf_iowait(bp)
diff --git a/fs/xfs/linux-2.6/xfs_cred.h b/fs/xfs/linux-2.6/xfs_cred.h
index 652721ce0ea5..e279d00779f4 100644
--- a/fs/xfs/linux-2.6/xfs_cred.h
+++ b/fs/xfs/linux-2.6/xfs_cred.h
@@ -24,15 +24,7 @@
  * Credentials
  */
 typedef struct cred {
-	/* EMPTY */
+       /* EMPTY */
 } cred_t;
 
-extern struct cred *sys_cred;
-
-/* this is a hack.. (assumes sys_cred is the only cred_t in the system) */
-static inline int capable_cred(cred_t *cr, int cid)
-{
-	return (cr == sys_cred) ? 1 : capable(cid);
-}
-
 #endif  /* __XFS_CRED_H__ */
diff --git a/fs/xfs/linux-2.6/xfs_export.c b/fs/xfs/linux-2.6/xfs_export.c
index 7f7abec25e14..595751f78350 100644
--- a/fs/xfs/linux-2.6/xfs_export.c
+++ b/fs/xfs/linux-2.6/xfs_export.c
@@ -29,7 +29,6 @@
 #include "xfs_vnodeops.h"
 #include "xfs_bmap_btree.h"
 #include "xfs_inode.h"
-#include "xfs_vfsops.h"
 
 /*
  * Note that we only accept fileids which are long enough rather than allow
diff --git a/fs/xfs/linux-2.6/xfs_file.c b/fs/xfs/linux-2.6/xfs_file.c
index 3fee790f138b..f999d20a429c 100644
--- a/fs/xfs/linux-2.6/xfs_file.c
+++ b/fs/xfs/linux-2.6/xfs_file.c
@@ -36,8 +36,9 @@
 #include "xfs_inode.h"
 #include "xfs_error.h"
 #include "xfs_rw.h"
-#include "xfs_ioctl32.h"
 #include "xfs_vnodeops.h"
+#include "xfs_da_btree.h"
+#include "xfs_ioctl.h"
 
 #include <linux/dcache.h>
 #include <linux/smp_lock.h>
@@ -169,11 +170,37 @@ xfs_file_splice_write_invis(
 STATIC int
 xfs_file_open(
 	struct inode	*inode,
-	struct file	*filp)
+	struct file	*file)
 {
-	if (!(filp->f_flags & O_LARGEFILE) && i_size_read(inode) > MAX_NON_LFS)
+	if (!(file->f_flags & O_LARGEFILE) && i_size_read(inode) > MAX_NON_LFS)
 		return -EFBIG;
-	return -xfs_open(XFS_I(inode));
+	if (XFS_FORCED_SHUTDOWN(XFS_M(inode->i_sb)))
+		return -EIO;
+	return 0;
+}
+
+STATIC int
+xfs_dir_open(
+	struct inode	*inode,
+	struct file	*file)
+{
+	struct xfs_inode *ip = XFS_I(inode);
+	int		mode;
+	int		error;
+
+	error = xfs_file_open(inode, file);
+	if (error)
+		return error;
+
+	/*
+	 * If there are any blocks, read-ahead block 0 as we're almost
+	 * certain to have the next operation be a read there.
+	 */
+	mode = xfs_ilock_map_shared(ip);
+	if (ip->i_d.di_nextents > 0)
+		xfs_da_reada_buf(NULL, ip, 0, XFS_DATA_FORK);
+	xfs_iunlock(ip, mode);
+	return 0;
 }
 
 STATIC int
@@ -254,11 +281,8 @@ xfs_file_ioctl(
 	unsigned int	cmd,
 	unsigned long	p)
 {
-	int		error;
 	struct inode	*inode = filp->f_path.dentry->d_inode;
 
-	error = xfs_ioctl(XFS_I(inode), filp, 0, cmd, (void __user *)p);
-	xfs_iflags_set(XFS_I(inode), XFS_IMODIFIED);
 
 	/* NOTE:  some of the ioctl's return positive #'s as a
 	 *	  byte count indicating success, such as
@@ -266,7 +290,7 @@ xfs_file_ioctl(
 	 *	  like most other routines.  This means true
 	 *	  errors need to be returned as a negative value.
 	 */
-	return error;
+	return xfs_ioctl(XFS_I(inode), filp, 0, cmd, (void __user *)p);
 }
 
 STATIC long
@@ -275,11 +299,8 @@ xfs_file_ioctl_invis(
 	unsigned int	cmd,
 	unsigned long	p)
 {
-	int		error;
 	struct inode	*inode = filp->f_path.dentry->d_inode;
 
-	error = xfs_ioctl(XFS_I(inode), filp, IO_INVIS, cmd, (void __user *)p);
-	xfs_iflags_set(XFS_I(inode), XFS_IMODIFIED);
 
 	/* NOTE:  some of the ioctl's return positive #'s as a
 	 *	  byte count indicating success, such as
@@ -287,7 +308,7 @@ xfs_file_ioctl_invis(
 	 *	  like most other routines.  This means true
 	 *	  errors need to be returned as a negative value.
 	 */
-	return error;
+	return xfs_ioctl(XFS_I(inode), filp, IO_INVIS, cmd, (void __user *)p);
 }
 
 /*
@@ -345,6 +366,7 @@ const struct file_operations xfs_invis_file_operations = {
 
 
 const struct file_operations xfs_dir_file_operations = {
+	.open		= xfs_dir_open,
 	.read		= generic_read_dir,
 	.readdir	= xfs_file_readdir,
 	.llseek		= generic_file_llseek,
diff --git a/fs/xfs/linux-2.6/xfs_fs_subr.c b/fs/xfs/linux-2.6/xfs_fs_subr.c
index 36caa6d957df..5aeb77776961 100644
--- a/fs/xfs/linux-2.6/xfs_fs_subr.c
+++ b/fs/xfs/linux-2.6/xfs_fs_subr.c
@@ -24,6 +24,10 @@ int  fs_noerr(void) { return 0; }
 int  fs_nosys(void) { return ENOSYS; }
 void fs_noval(void) { return; }
 
+/*
+ * note: all filemap functions return negative error codes. These
+ * need to be inverted before returning to the xfs core functions.
+ */
 void
 xfs_tosspages(
 	xfs_inode_t	*ip,
@@ -53,7 +57,7 @@ xfs_flushinval_pages(
 		if (!ret)
 			truncate_inode_pages(mapping, first);
 	}
-	return ret;
+	return -ret;
 }
 
 int
@@ -72,10 +76,23 @@ xfs_flush_pages(
 		xfs_iflags_clear(ip, XFS_ITRUNCATED);
 		ret = filemap_fdatawrite(mapping);
 		if (flags & XFS_B_ASYNC)
-			return ret;
+			return -ret;
 		ret2 = filemap_fdatawait(mapping);
 		if (!ret)
 			ret = ret2;
 	}
-	return ret;
+	return -ret;
+}
+
+int
+xfs_wait_on_pages(
+	xfs_inode_t	*ip,
+	xfs_off_t	first,
+	xfs_off_t	last)
+{
+	struct address_space *mapping = VFS_I(ip)->i_mapping;
+
+	if (mapping_tagged(mapping, PAGECACHE_TAG_WRITEBACK))
+		return -filemap_fdatawait(mapping);
+	return 0;
 }
diff --git a/fs/xfs/linux-2.6/xfs_globals.c b/fs/xfs/linux-2.6/xfs_globals.c
index ef90e64641e6..2ae8b1ccb02e 100644
--- a/fs/xfs/linux-2.6/xfs_globals.c
+++ b/fs/xfs/linux-2.6/xfs_globals.c
@@ -26,7 +26,6 @@
  */
 xfs_param_t xfs_params = {
 			  /*	MIN		DFLT		MAX	*/
-	.restrict_chown	= {	0,		1,		1	},
 	.sgid_inherit	= {	0,		0,		1	},
 	.symlink_mode	= {	0,		0,		1	},
 	.panic_mask	= {	0,		0,		255	},
@@ -43,10 +42,3 @@ xfs_param_t xfs_params = {
 	.inherit_nodfrg	= {	0,		1,		1	},
 	.fstrm_timer	= {	1,		30*100,		3600*100},
 };
-
-/*
- * Global system credential structure.
- */
-static cred_t sys_cred_val;
-cred_t *sys_cred = &sys_cred_val;
-
diff --git a/fs/xfs/linux-2.6/xfs_globals.h b/fs/xfs/linux-2.6/xfs_globals.h
index 2770b0085ee8..69f71caf061c 100644
--- a/fs/xfs/linux-2.6/xfs_globals.h
+++ b/fs/xfs/linux-2.6/xfs_globals.h
@@ -19,6 +19,5 @@
 #define __XFS_GLOBALS_H__
 
 extern uint64_t	xfs_panic_mask;		/* set to cause more panics */
-extern struct cred *sys_cred;
 
 #endif	/* __XFS_GLOBALS_H__ */
diff --git a/fs/xfs/linux-2.6/xfs_ioctl.c b/fs/xfs/linux-2.6/xfs_ioctl.c
index d3438c72dcaf..c8f1e632ba94 100644
--- a/fs/xfs/linux-2.6/xfs_ioctl.c
+++ b/fs/xfs/linux-2.6/xfs_ioctl.c
@@ -68,26 +68,22 @@
  * XFS_IOC_PATH_TO_HANDLE
  *    returns full handle for a path
  */
-STATIC int
+int
 xfs_find_handle(
 	unsigned int		cmd,
-	void			__user *arg)
+	xfs_fsop_handlereq_t	*hreq)
 {
 	int			hsize;
 	xfs_handle_t		handle;
-	xfs_fsop_handlereq_t	hreq;
 	struct inode		*inode;
 
-	if (copy_from_user(&hreq, arg, sizeof(hreq)))
-		return -XFS_ERROR(EFAULT);
-
 	memset((char *)&handle, 0, sizeof(handle));
 
 	switch (cmd) {
 	case XFS_IOC_PATH_TO_FSHANDLE:
 	case XFS_IOC_PATH_TO_HANDLE: {
 		struct path path;
-		int error = user_lpath((const char __user *)hreq.path, &path);
+		int error = user_lpath((const char __user *)hreq->path, &path);
 		if (error)
 			return error;
 
@@ -101,7 +97,7 @@ xfs_find_handle(
 	case XFS_IOC_FD_TO_HANDLE: {
 		struct file	*file;
 
-		file = fget(hreq.fd);
+		file = fget(hreq->fd);
 		if (!file)
 		    return -EBADF;
 
@@ -158,8 +154,8 @@ xfs_find_handle(
 	}
 
 	/* now copy our handle into the user buffer & write out the size */
-	if (copy_to_user(hreq.ohandle, &handle, hsize) ||
-	    copy_to_user(hreq.ohandlen, &hsize, sizeof(__s32))) {
+	if (copy_to_user(hreq->ohandle, &handle, hsize) ||
+	    copy_to_user(hreq->ohandlen, &hsize, sizeof(__s32))) {
 		iput(inode);
 		return -XFS_ERROR(EFAULT);
 	}
@@ -249,10 +245,10 @@ xfs_vget_fsop_handlereq(
 	return 0;
 }
 
-STATIC int
+int
 xfs_open_by_handle(
 	xfs_mount_t		*mp,
-	void			__user *arg,
+	xfs_fsop_handlereq_t	*hreq,
 	struct file		*parfilp,
 	struct inode		*parinode)
 {
@@ -262,14 +258,11 @@ xfs_open_by_handle(
 	struct file		*filp;
 	struct inode		*inode;
 	struct dentry		*dentry;
-	xfs_fsop_handlereq_t	hreq;
 
 	if (!capable(CAP_SYS_ADMIN))
 		return -XFS_ERROR(EPERM);
-	if (copy_from_user(&hreq, arg, sizeof(xfs_fsop_handlereq_t)))
-		return -XFS_ERROR(EFAULT);
 
-	error = xfs_vget_fsop_handlereq(mp, parinode, &hreq, &inode);
+	error = xfs_vget_fsop_handlereq(mp, parinode, hreq, &inode);
 	if (error)
 		return -error;
 
@@ -280,10 +273,10 @@ xfs_open_by_handle(
 	}
 
 #if BITS_PER_LONG != 32
-	hreq.oflags |= O_LARGEFILE;
+	hreq->oflags |= O_LARGEFILE;
 #endif
 	/* Put open permission in namei format. */
-	permflag = hreq.oflags;
+	permflag = hreq->oflags;
 	if ((permflag+1) & O_ACCMODE)
 		permflag++;
 	if (permflag & O_TRUNC)
@@ -321,7 +314,7 @@ xfs_open_by_handle(
 	mntget(parfilp->f_path.mnt);
 
 	/* Create file pointer. */
-	filp = dentry_open(dentry, parfilp->f_path.mnt, hreq.oflags);
+	filp = dentry_open(dentry, parfilp->f_path.mnt, hreq->oflags);
 	if (IS_ERR(filp)) {
 		put_unused_fd(new_fd);
 		return -XFS_ERROR(-PTR_ERR(filp));
@@ -362,24 +355,21 @@ do_readlink(
 }
 
 
-STATIC int
+int
 xfs_readlink_by_handle(
 	xfs_mount_t		*mp,
-	void			__user *arg,
+	xfs_fsop_handlereq_t	*hreq,
 	struct inode		*parinode)
 {
 	struct inode		*inode;
-	xfs_fsop_handlereq_t	hreq;
 	__u32			olen;
 	void			*link;
 	int			error;
 
 	if (!capable(CAP_SYS_ADMIN))
 		return -XFS_ERROR(EPERM);
-	if (copy_from_user(&hreq, arg, sizeof(xfs_fsop_handlereq_t)))
-		return -XFS_ERROR(EFAULT);
 
-	error = xfs_vget_fsop_handlereq(mp, parinode, &hreq, &inode);
+	error = xfs_vget_fsop_handlereq(mp, parinode, hreq, &inode);
 	if (error)
 		return -error;
 
@@ -389,7 +379,7 @@ xfs_readlink_by_handle(
 		goto out_iput;
 	}
 
-	if (copy_from_user(&olen, hreq.ohandlen, sizeof(__u32))) {
+	if (copy_from_user(&olen, hreq->ohandlen, sizeof(__u32))) {
 		error = -XFS_ERROR(EFAULT);
 		goto out_iput;
 	}
@@ -401,7 +391,7 @@ xfs_readlink_by_handle(
 	error = -xfs_readlink(XFS_I(inode), link);
 	if (error)
 		goto out_kfree;
-	error = do_readlink(hreq.ohandle, olen, link);
+	error = do_readlink(hreq->ohandle, olen, link);
 	if (error)
 		goto out_kfree;
 
@@ -500,7 +490,7 @@ xfs_attrlist_by_handle(
 	return -error;
 }
 
-STATIC int
+int
 xfs_attrmulti_attr_get(
 	struct inode		*inode,
 	char			*name,
@@ -529,7 +519,7 @@ xfs_attrmulti_attr_get(
 	return error;
 }
 
-STATIC int
+int
 xfs_attrmulti_attr_set(
 	struct inode		*inode,
 	char			*name,
@@ -559,7 +549,7 @@ xfs_attrmulti_attr_set(
 	return error;
 }
 
-STATIC int
+int
 xfs_attrmulti_attr_remove(
 	struct inode		*inode,
 	char			*name,
@@ -661,19 +651,26 @@ xfs_attrmulti_by_handle(
 	return -error;
 }
 
-STATIC int
+int
 xfs_ioc_space(
 	struct xfs_inode	*ip,
 	struct inode		*inode,
 	struct file		*filp,
 	int			ioflags,
 	unsigned int		cmd,
-	void			__user *arg)
+	xfs_flock64_t		*bf)
 {
-	xfs_flock64_t		bf;
 	int			attr_flags = 0;
 	int			error;
 
+	/*
+	 * Only allow the sys admin to reserve space unless
+	 * unwritten extents are enabled.
+	 */
+	if (!xfs_sb_version_hasextflgbit(&ip->i_mount->m_sb) &&
+	    !capable(CAP_SYS_ADMIN))
+		return -XFS_ERROR(EPERM);
+
 	if (inode->i_flags & (S_IMMUTABLE|S_APPEND))
 		return -XFS_ERROR(EPERM);
 
@@ -683,16 +680,12 @@ xfs_ioc_space(
 	if (!S_ISREG(inode->i_mode))
 		return -XFS_ERROR(EINVAL);
 
-	if (copy_from_user(&bf, arg, sizeof(bf)))
-		return -XFS_ERROR(EFAULT);
-
 	if (filp->f_flags & (O_NDELAY|O_NONBLOCK))
 		attr_flags |= XFS_ATTR_NONBLOCK;
 	if (ioflags & IO_INVIS)
 		attr_flags |= XFS_ATTR_DMI;
 
-	error = xfs_change_file_space(ip, cmd, &bf, filp->f_pos,
-					      NULL, attr_flags);
+	error = xfs_change_file_space(ip, cmd, bf, filp->f_pos, attr_flags);
 	return -error;
 }
 
@@ -1007,7 +1000,7 @@ xfs_ioctl_setattr(
 	 * to the file owner ID, except in cases where the
 	 * CAP_FSETID capability is applicable.
 	 */
-	if (current->fsuid != ip->i_d.di_uid && !capable(CAP_FOWNER)) {
+	if (current_fsuid() != ip->i_d.di_uid && !capable(CAP_FOWNER)) {
 		code = XFS_ERROR(EPERM);
 		goto error_return;
 	}
@@ -1104,10 +1097,6 @@ xfs_ioctl_setattr(
 
 	/*
 	 * Change file ownership.  Must be the owner or privileged.
-	 * If the system was configured with the "restricted_chown"
-	 * option, the owner is not permitted to give away the file,
-	 * and can change the group id only to a group of which he
-	 * or she is a member.
 	 */
 	if (mask & FSX_PROJID) {
 		/*
@@ -1136,7 +1125,7 @@ xfs_ioctl_setattr(
 			 * the superblock version number since projids didn't
 			 * exist before DINODE_VERSION_2 and SB_VERSION_NLINK.
 			 */
-			if (ip->i_d.di_version == XFS_DINODE_VERSION_1)
+			if (ip->i_d.di_version == 1)
 				xfs_bump_ino_vers2(tp, ip);
 		}
 
@@ -1255,43 +1244,67 @@ xfs_ioc_setxflags(
 }
 
 STATIC int
+xfs_getbmap_format(void **ap, struct getbmapx *bmv, int *full)
+{
+	struct getbmap __user	*base = *ap;
+
+	/* copy only getbmap portion (not getbmapx) */
+	if (copy_to_user(base, bmv, sizeof(struct getbmap)))
+		return XFS_ERROR(EFAULT);
+
+	*ap += sizeof(struct getbmap);
+	return 0;
+}
+
+STATIC int
 xfs_ioc_getbmap(
 	struct xfs_inode	*ip,
 	int			ioflags,
 	unsigned int		cmd,
 	void			__user *arg)
 {
-	struct getbmap		bm;
-	int			iflags;
+	struct getbmapx		bmx;
 	int			error;
 
-	if (copy_from_user(&bm, arg, sizeof(bm)))
+	if (copy_from_user(&bmx, arg, sizeof(struct getbmapx)))
 		return -XFS_ERROR(EFAULT);
 
-	if (bm.bmv_count < 2)
+	if (bmx.bmv_count < 2)
 		return -XFS_ERROR(EINVAL);
 
-	iflags = (cmd == XFS_IOC_GETBMAPA ? BMV_IF_ATTRFORK : 0);
+	bmx.bmv_iflags = (cmd == XFS_IOC_GETBMAPA ? BMV_IF_ATTRFORK : 0);
 	if (ioflags & IO_INVIS)
-		iflags |= BMV_IF_NO_DMAPI_READ;
+		bmx.bmv_iflags |= BMV_IF_NO_DMAPI_READ;
 
-	error = xfs_getbmap(ip, &bm, (struct getbmap __user *)arg+1, iflags);
+	error = xfs_getbmap(ip, &bmx, xfs_getbmap_format,
+			    (struct getbmap *)arg+1);
 	if (error)
 		return -error;
 
-	if (copy_to_user(arg, &bm, sizeof(bm)))
+	/* copy back header - only size of getbmap */
+	if (copy_to_user(arg, &bmx, sizeof(struct getbmap)))
 		return -XFS_ERROR(EFAULT);
 	return 0;
 }
 
 STATIC int
+xfs_getbmapx_format(void **ap, struct getbmapx *bmv, int *full)
+{
+	struct getbmapx __user	*base = *ap;
+
+	if (copy_to_user(base, bmv, sizeof(struct getbmapx)))
+		return XFS_ERROR(EFAULT);
+
+	*ap += sizeof(struct getbmapx);
+	return 0;
+}
+
+STATIC int
 xfs_ioc_getbmapx(
 	struct xfs_inode	*ip,
 	void			__user *arg)
 {
 	struct getbmapx		bmx;
-	struct getbmap		bm;
-	int			iflags;
 	int			error;
 
 	if (copy_from_user(&bmx, arg, sizeof(bmx)))
@@ -1300,26 +1313,16 @@ xfs_ioc_getbmapx(
 	if (bmx.bmv_count < 2)
 		return -XFS_ERROR(EINVAL);
 
-	/*
-	 * Map input getbmapx structure to a getbmap
-	 * structure for xfs_getbmap.
-	 */
-	GETBMAP_CONVERT(bmx, bm);
-
-	iflags = bmx.bmv_iflags;
-
-	if (iflags & (~BMV_IF_VALID))
+	if (bmx.bmv_iflags & (~BMV_IF_VALID))
 		return -XFS_ERROR(EINVAL);
 
-	iflags |= BMV_IF_EXTENDED;
-
-	error = xfs_getbmap(ip, &bm, (struct getbmapx __user *)arg+1, iflags);
+	error = xfs_getbmap(ip, &bmx, xfs_getbmapx_format,
+			    (struct getbmapx *)arg+1);
 	if (error)
 		return -error;
 
-	GETBMAP_CONVERT(bm, bmx);
-
-	if (copy_to_user(arg, &bmx, sizeof(bmx)))
+	/* copy back header */
+	if (copy_to_user(arg, &bmx, sizeof(struct getbmapx)))
 		return -XFS_ERROR(EFAULT);
 
 	return 0;
@@ -1347,17 +1350,13 @@ xfs_ioctl(
 	case XFS_IOC_ALLOCSP64:
 	case XFS_IOC_FREESP64:
 	case XFS_IOC_RESVSP64:
-	case XFS_IOC_UNRESVSP64:
-		/*
-		 * Only allow the sys admin to reserve space unless
-		 * unwritten extents are enabled.
-		 */
-		if (!xfs_sb_version_hasextflgbit(&mp->m_sb) &&
-		    !capable(CAP_SYS_ADMIN))
-			return -EPERM;
-
-		return xfs_ioc_space(ip, inode, filp, ioflags, cmd, arg);
+	case XFS_IOC_UNRESVSP64: {
+		xfs_flock64_t		bf;
 
+		if (copy_from_user(&bf, arg, sizeof(bf)))
+			return -XFS_ERROR(EFAULT);
+		return xfs_ioc_space(ip, inode, filp, ioflags, cmd, &bf);
+	}
 	case XFS_IOC_DIOINFO: {
 		struct dioattr	da;
 		xfs_buftarg_t	*target =
@@ -1417,18 +1416,30 @@ xfs_ioctl(
 
 	case XFS_IOC_FD_TO_HANDLE:
 	case XFS_IOC_PATH_TO_HANDLE:
-	case XFS_IOC_PATH_TO_FSHANDLE:
-		return xfs_find_handle(cmd, arg);
+	case XFS_IOC_PATH_TO_FSHANDLE: {
+		xfs_fsop_handlereq_t	hreq;
 
-	case XFS_IOC_OPEN_BY_HANDLE:
-		return xfs_open_by_handle(mp, arg, filp, inode);
+		if (copy_from_user(&hreq, arg, sizeof(hreq)))
+			return -XFS_ERROR(EFAULT);
+		return xfs_find_handle(cmd, &hreq);
+	}
+	case XFS_IOC_OPEN_BY_HANDLE: {
+		xfs_fsop_handlereq_t	hreq;
 
+		if (copy_from_user(&hreq, arg, sizeof(xfs_fsop_handlereq_t)))
+			return -XFS_ERROR(EFAULT);
+		return xfs_open_by_handle(mp, &hreq, filp, inode);
+	}
 	case XFS_IOC_FSSETDM_BY_HANDLE:
 		return xfs_fssetdm_by_handle(mp, arg, inode);
 
-	case XFS_IOC_READLINK_BY_HANDLE:
-		return xfs_readlink_by_handle(mp, arg, inode);
+	case XFS_IOC_READLINK_BY_HANDLE: {
+		xfs_fsop_handlereq_t	hreq;
 
+		if (copy_from_user(&hreq, arg, sizeof(xfs_fsop_handlereq_t)))
+			return -XFS_ERROR(EFAULT);
+		return xfs_readlink_by_handle(mp, &hreq, inode);
+	}
 	case XFS_IOC_ATTRLIST_BY_HANDLE:
 		return xfs_attrlist_by_handle(mp, arg, inode);
 
@@ -1436,7 +1447,11 @@ xfs_ioctl(
 		return xfs_attrmulti_by_handle(mp, arg, filp, inode);
 
 	case XFS_IOC_SWAPEXT: {
-		error = xfs_swapext((struct xfs_swapext __user *)arg);
+		struct xfs_swapext	sxp;
+
+		if (copy_from_user(&sxp, arg, sizeof(xfs_swapext_t)))
+			return -XFS_ERROR(EFAULT);
+		error = xfs_swapext(&sxp);
 		return -error;
 	}
 
@@ -1492,9 +1507,6 @@ xfs_ioctl(
 	case XFS_IOC_FSGROWFSDATA: {
 		xfs_growfs_data_t in;
 
-		if (!capable(CAP_SYS_ADMIN))
-			return -EPERM;
-
 		if (copy_from_user(&in, arg, sizeof(in)))
 			return -XFS_ERROR(EFAULT);
 
@@ -1505,9 +1517,6 @@ xfs_ioctl(
 	case XFS_IOC_FSGROWFSLOG: {
 		xfs_growfs_log_t in;
 
-		if (!capable(CAP_SYS_ADMIN))
-			return -EPERM;
-
 		if (copy_from_user(&in, arg, sizeof(in)))
 			return -XFS_ERROR(EFAULT);
 
@@ -1518,9 +1527,6 @@ xfs_ioctl(
 	case XFS_IOC_FSGROWFSRT: {
 		xfs_growfs_rt_t in;
 
-		if (!capable(CAP_SYS_ADMIN))
-			return -EPERM;
-
 		if (copy_from_user(&in, arg, sizeof(in)))
 			return -XFS_ERROR(EFAULT);
 
diff --git a/fs/xfs/linux-2.6/xfs_ioctl.h b/fs/xfs/linux-2.6/xfs_ioctl.h
new file mode 100644
index 000000000000..d92131c827bc
--- /dev/null
+++ b/fs/xfs/linux-2.6/xfs_ioctl.h
@@ -0,0 +1,82 @@
+/*
+ * Copyright (c) 2008 Silicon Graphics, Inc.
+ * All Rights Reserved.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it would be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write the Free Software Foundation,
+ * Inc.,  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
+ */
+#ifndef __XFS_IOCTL_H__
+#define __XFS_IOCTL_H__
+
+extern int
+xfs_ioc_space(
+	struct xfs_inode	*ip,
+	struct inode		*inode,
+	struct file		*filp,
+	int			ioflags,
+	unsigned int		cmd,
+	xfs_flock64_t		*bf);
+
+extern int
+xfs_find_handle(
+	unsigned int		cmd,
+	xfs_fsop_handlereq_t	*hreq);
+
+extern int
+xfs_open_by_handle(
+	xfs_mount_t		*mp,
+	xfs_fsop_handlereq_t	*hreq,
+	struct file		*parfilp,
+	struct inode		*parinode);
+
+extern int
+xfs_readlink_by_handle(
+	xfs_mount_t		*mp,
+	xfs_fsop_handlereq_t	*hreq,
+	struct inode		*parinode);
+
+extern int
+xfs_attrmulti_attr_get(
+	struct inode		*inode,
+	char			*name,
+	char			__user *ubuf,
+	__uint32_t		*len,
+	__uint32_t		flags);
+
+extern int
+	xfs_attrmulti_attr_set(
+	struct inode		*inode,
+	char			*name,
+	const char		__user *ubuf,
+	__uint32_t		len,
+	__uint32_t		flags);
+
+extern int
+xfs_attrmulti_attr_remove(
+	struct inode		*inode,
+	char			*name,
+	__uint32_t		flags);
+
+extern long
+xfs_file_compat_ioctl(
+	struct file		*file,
+	unsigned int		cmd,
+	unsigned long		arg);
+
+extern long
+xfs_file_compat_invis_ioctl(
+	struct file		*file,
+	unsigned int		cmd,
+	unsigned long		arg);
+
+#endif
diff --git a/fs/xfs/linux-2.6/xfs_ioctl32.c b/fs/xfs/linux-2.6/xfs_ioctl32.c
index a4b254eb43b2..b34b3d8892a2 100644
--- a/fs/xfs/linux-2.6/xfs_ioctl32.c
+++ b/fs/xfs/linux-2.6/xfs_ioctl32.c
@@ -16,11 +16,7 @@
  * Inc.,  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
  */
 #include <linux/compat.h>
-#include <linux/init.h>
 #include <linux/ioctl.h>
-#include <linux/syscalls.h>
-#include <linux/types.h>
-#include <linux/fs.h>
 #include <asm/uaccess.h>
 #include "xfs.h"
 #include "xfs_fs.h"
@@ -36,7 +32,6 @@
 #include "xfs_bmap_btree.h"
 #include "xfs_attr_sf.h"
 #include "xfs_dir2_sf.h"
-#include "xfs_vfs.h"
 #include "xfs_vnode.h"
 #include "xfs_dinode.h"
 #include "xfs_inode.h"
@@ -44,221 +39,219 @@
 #include "xfs_error.h"
 #include "xfs_dfrag.h"
 #include "xfs_vnodeops.h"
+#include "xfs_fsops.h"
+#include "xfs_alloc.h"
+#include "xfs_rtalloc.h"
+#include "xfs_attr.h"
+#include "xfs_ioctl.h"
 #include "xfs_ioctl32.h"
 
 #define  _NATIVE_IOC(cmd, type) \
 	  _IOC(_IOC_DIR(cmd), _IOC_TYPE(cmd), _IOC_NR(cmd), sizeof(type))
 
-#if defined(CONFIG_IA64) || defined(CONFIG_X86_64)
-#define BROKEN_X86_ALIGNMENT
-#define _PACKED __attribute__((packed))
-/* on ia32 l_start is on a 32-bit boundary */
-typedef struct xfs_flock64_32 {
-	__s16		l_type;
-	__s16		l_whence;
-	__s64		l_start	__attribute__((packed));
-			/* len == 0 means until end of file */
-	__s64		l_len __attribute__((packed));
-	__s32		l_sysid;
-	__u32		l_pid;
-	__s32		l_pad[4];	/* reserve area */
-} xfs_flock64_32_t;
-
-#define XFS_IOC_ALLOCSP_32	_IOW ('X', 10, struct xfs_flock64_32)
-#define XFS_IOC_FREESP_32	_IOW ('X', 11, struct xfs_flock64_32)
-#define XFS_IOC_ALLOCSP64_32	_IOW ('X', 36, struct xfs_flock64_32)
-#define XFS_IOC_FREESP64_32	_IOW ('X', 37, struct xfs_flock64_32)
-#define XFS_IOC_RESVSP_32	_IOW ('X', 40, struct xfs_flock64_32)
-#define XFS_IOC_UNRESVSP_32	_IOW ('X', 41, struct xfs_flock64_32)
-#define XFS_IOC_RESVSP64_32	_IOW ('X', 42, struct xfs_flock64_32)
-#define XFS_IOC_UNRESVSP64_32	_IOW ('X', 43, struct xfs_flock64_32)
-
-/* just account for different alignment */
-STATIC unsigned long
-xfs_ioctl32_flock(
-	unsigned long		arg)
+#ifdef BROKEN_X86_ALIGNMENT
+STATIC int
+xfs_compat_flock64_copyin(
+	xfs_flock64_t		*bf,
+	compat_xfs_flock64_t	__user *arg32)
 {
-	xfs_flock64_32_t	__user *p32 = (void __user *)arg;
-	xfs_flock64_t		__user *p = compat_alloc_user_space(sizeof(*p));
-
-	if (copy_in_user(&p->l_type,	&p32->l_type,	sizeof(s16)) ||
-	    copy_in_user(&p->l_whence,	&p32->l_whence, sizeof(s16)) ||
-	    copy_in_user(&p->l_start,	&p32->l_start,	sizeof(s64)) ||
-	    copy_in_user(&p->l_len,	&p32->l_len,	sizeof(s64)) ||
-	    copy_in_user(&p->l_sysid,	&p32->l_sysid,	sizeof(s32)) ||
-	    copy_in_user(&p->l_pid,	&p32->l_pid,	sizeof(u32)) ||
-	    copy_in_user(&p->l_pad,	&p32->l_pad,	4*sizeof(u32)))
-		return -EFAULT;
-
-	return (unsigned long)p;
+	if (get_user(bf->l_type,	&arg32->l_type) ||
+	    get_user(bf->l_whence,	&arg32->l_whence) ||
+	    get_user(bf->l_start,	&arg32->l_start) ||
+	    get_user(bf->l_len,		&arg32->l_len) ||
+	    get_user(bf->l_sysid,	&arg32->l_sysid) ||
+	    get_user(bf->l_pid,		&arg32->l_pid) ||
+	    copy_from_user(bf->l_pad,	&arg32->l_pad,	4*sizeof(u32)))
+		return -XFS_ERROR(EFAULT);
+	return 0;
 }
 
-typedef struct compat_xfs_fsop_geom_v1 {
-	__u32		blocksize;	/* filesystem (data) block size */
-	__u32		rtextsize;	/* realtime extent size		*/
-	__u32		agblocks;	/* fsblocks in an AG		*/
-	__u32		agcount;	/* number of allocation groups	*/
-	__u32		logblocks;	/* fsblocks in the log		*/
-	__u32		sectsize;	/* (data) sector size, bytes	*/
-	__u32		inodesize;	/* inode size in bytes		*/
-	__u32		imaxpct;	/* max allowed inode space(%)	*/
-	__u64		datablocks;	/* fsblocks in data subvolume	*/
-	__u64		rtblocks;	/* fsblocks in realtime subvol	*/
-	__u64		rtextents;	/* rt extents in realtime subvol*/
-	__u64		logstart;	/* starting fsblock of the log	*/
-	unsigned char	uuid[16];	/* unique id of the filesystem	*/
-	__u32		sunit;		/* stripe unit, fsblocks	*/
-	__u32		swidth;		/* stripe width, fsblocks	*/
-	__s32		version;	/* structure version		*/
-	__u32		flags;		/* superblock version flags	*/
-	__u32		logsectsize;	/* log sector size, bytes	*/
-	__u32		rtsectsize;	/* realtime sector size, bytes	*/
-	__u32		dirblocksize;	/* directory block size, bytes	*/
-} __attribute__((packed)) compat_xfs_fsop_geom_v1_t;
-
-#define XFS_IOC_FSGEOMETRY_V1_32  \
-	_IOR ('X', 100, struct compat_xfs_fsop_geom_v1)
-
-STATIC unsigned long xfs_ioctl32_geom_v1(unsigned long arg)
+STATIC int
+xfs_compat_ioc_fsgeometry_v1(
+	struct xfs_mount	  *mp,
+	compat_xfs_fsop_geom_v1_t __user *arg32)
 {
-	compat_xfs_fsop_geom_v1_t __user *p32 = (void __user *)arg;
-	xfs_fsop_geom_v1_t __user *p = compat_alloc_user_space(sizeof(*p));
+	xfs_fsop_geom_t		  fsgeo;
+	int			  error;
 
-	if (copy_in_user(p, p32, sizeof(*p32)))
-		return -EFAULT;
-	return (unsigned long)p;
+	error = xfs_fs_geometry(mp, &fsgeo, 3);
+	if (error)
+		return -error;
+	/* The 32-bit variant simply has some padding at the end */
+	if (copy_to_user(arg32, &fsgeo, sizeof(struct compat_xfs_fsop_geom_v1)))
+		return -XFS_ERROR(EFAULT);
+	return 0;
 }
 
-typedef struct compat_xfs_inogrp {
-	__u64		xi_startino;	/* starting inode number	*/
-	__s32		xi_alloccount;	/* # bits set in allocmask	*/
-	__u64		xi_allocmask;	/* mask of allocated inodes	*/
-} __attribute__((packed)) compat_xfs_inogrp_t;
-
-STATIC int xfs_inumbers_fmt_compat(
-	void __user *ubuffer,
-	const xfs_inogrp_t *buffer,
-	long count,
-	long *written)
+STATIC int
+xfs_compat_growfs_data_copyin(
+	struct xfs_growfs_data	 *in,
+	compat_xfs_growfs_data_t __user *arg32)
+{
+	if (get_user(in->newblocks, &arg32->newblocks) ||
+	    get_user(in->imaxpct,   &arg32->imaxpct))
+		return -XFS_ERROR(EFAULT);
+	return 0;
+}
+
+STATIC int
+xfs_compat_growfs_rt_copyin(
+	struct xfs_growfs_rt	 *in,
+	compat_xfs_growfs_rt_t	__user *arg32)
+{
+	if (get_user(in->newblocks, &arg32->newblocks) ||
+	    get_user(in->extsize,   &arg32->extsize))
+		return -XFS_ERROR(EFAULT);
+	return 0;
+}
+
+STATIC int
+xfs_inumbers_fmt_compat(
+	void			__user *ubuffer,
+	const xfs_inogrp_t	*buffer,
+	long			count,
+	long			*written)
 {
-	compat_xfs_inogrp_t __user *p32 = ubuffer;
-	long i;
+	compat_xfs_inogrp_t	__user *p32 = ubuffer;
+	long			i;
 
 	for (i = 0; i < count; i++) {
 		if (put_user(buffer[i].xi_startino,   &p32[i].xi_startino) ||
 		    put_user(buffer[i].xi_alloccount, &p32[i].xi_alloccount) ||
 		    put_user(buffer[i].xi_allocmask,  &p32[i].xi_allocmask))
-			return -EFAULT;
+			return -XFS_ERROR(EFAULT);
 	}
 	*written = count * sizeof(*p32);
 	return 0;
 }
 
 #else
-
 #define xfs_inumbers_fmt_compat xfs_inumbers_fmt
-#define _PACKED
+#endif	/* BROKEN_X86_ALIGNMENT */
 
-#endif
+STATIC int
+xfs_ioctl32_bstime_copyin(
+	xfs_bstime_t		*bstime,
+	compat_xfs_bstime_t	__user *bstime32)
+{
+	compat_time_t		sec32;	/* tv_sec differs on 64 vs. 32 */
 
-/* XFS_IOC_FSBULKSTAT and friends */
+	if (get_user(sec32,		&bstime32->tv_sec)	||
+	    get_user(bstime->tv_nsec,	&bstime32->tv_nsec))
+		return -XFS_ERROR(EFAULT);
+	bstime->tv_sec = sec32;
+	return 0;
+}
 
-typedef struct compat_xfs_bstime {
-	__s32		tv_sec;		/* seconds		*/
-	__s32		tv_nsec;	/* and nanoseconds	*/
-} compat_xfs_bstime_t;
+/* xfs_bstat_t has differing alignment on intel, & bstime_t sizes everywhere */
+STATIC int
+xfs_ioctl32_bstat_copyin(
+	xfs_bstat_t		*bstat,
+	compat_xfs_bstat_t	__user *bstat32)
+{
+	if (get_user(bstat->bs_ino,	&bstat32->bs_ino)	||
+	    get_user(bstat->bs_mode,	&bstat32->bs_mode)	||
+	    get_user(bstat->bs_nlink,	&bstat32->bs_nlink)	||
+	    get_user(bstat->bs_uid,	&bstat32->bs_uid)	||
+	    get_user(bstat->bs_gid,	&bstat32->bs_gid)	||
+	    get_user(bstat->bs_rdev,	&bstat32->bs_rdev)	||
+	    get_user(bstat->bs_blksize,	&bstat32->bs_blksize)	||
+	    get_user(bstat->bs_size,	&bstat32->bs_size)	||
+	    xfs_ioctl32_bstime_copyin(&bstat->bs_atime, &bstat32->bs_atime) ||
+	    xfs_ioctl32_bstime_copyin(&bstat->bs_mtime, &bstat32->bs_mtime) ||
+	    xfs_ioctl32_bstime_copyin(&bstat->bs_ctime, &bstat32->bs_ctime) ||
+	    get_user(bstat->bs_blocks,	&bstat32->bs_size)	||
+	    get_user(bstat->bs_xflags,	&bstat32->bs_size)	||
+	    get_user(bstat->bs_extsize,	&bstat32->bs_extsize)	||
+	    get_user(bstat->bs_extents,	&bstat32->bs_extents)	||
+	    get_user(bstat->bs_gen,	&bstat32->bs_gen)	||
+	    get_user(bstat->bs_projid,	&bstat32->bs_projid)	||
+	    get_user(bstat->bs_dmevmask, &bstat32->bs_dmevmask)	||
+	    get_user(bstat->bs_dmstate,	&bstat32->bs_dmstate)	||
+	    get_user(bstat->bs_aextents, &bstat32->bs_aextents))
+		return -XFS_ERROR(EFAULT);
+	return 0;
+}
+
+/* XFS_IOC_FSBULKSTAT and friends */
 
-STATIC int xfs_bstime_store_compat(
-	compat_xfs_bstime_t __user *p32,
-	const xfs_bstime_t *p)
+STATIC int
+xfs_bstime_store_compat(
+	compat_xfs_bstime_t	__user *p32,
+	const xfs_bstime_t	*p)
 {
-	__s32 sec32;
+	__s32			sec32;
 
 	sec32 = p->tv_sec;
 	if (put_user(sec32, &p32->tv_sec) ||
 	    put_user(p->tv_nsec, &p32->tv_nsec))
-		return -EFAULT;
+		return -XFS_ERROR(EFAULT);
 	return 0;
 }
 
-typedef struct compat_xfs_bstat {
-	__u64		bs_ino;		/* inode number			*/
-	__u16		bs_mode;	/* type and mode		*/
-	__u16		bs_nlink;	/* number of links		*/
-	__u32		bs_uid;		/* user id			*/
-	__u32		bs_gid;		/* group id			*/
-	__u32		bs_rdev;	/* device value			*/
-	__s32		bs_blksize;	/* block size			*/
-	__s64		bs_size;	/* file size			*/
-	compat_xfs_bstime_t bs_atime;	/* access time			*/
-	compat_xfs_bstime_t bs_mtime;	/* modify time			*/
-	compat_xfs_bstime_t bs_ctime;	/* inode change time		*/
-	int64_t		bs_blocks;	/* number of blocks		*/
-	__u32		bs_xflags;	/* extended flags		*/
-	__s32		bs_extsize;	/* extent size			*/
-	__s32		bs_extents;	/* number of extents		*/
-	__u32		bs_gen;		/* generation count		*/
-	__u16		bs_projid;	/* project id			*/
-	unsigned char	bs_pad[14];	/* pad space, unused		*/
-	__u32		bs_dmevmask;	/* DMIG event mask		*/
-	__u16		bs_dmstate;	/* DMIG state info		*/
-	__u16		bs_aextents;	/* attribute number of extents	*/
-} _PACKED compat_xfs_bstat_t;
-
-STATIC int xfs_bulkstat_one_fmt_compat(
+/* Return 0 on success or positive error (to xfs_bulkstat()) */
+STATIC int
+xfs_bulkstat_one_fmt_compat(
 	void			__user *ubuffer,
+	int			ubsize,
+	int			*ubused,
 	const xfs_bstat_t	*buffer)
 {
-	compat_xfs_bstat_t __user *p32 = ubuffer;
-
-	if (put_user(buffer->bs_ino, &p32->bs_ino) ||
-	    put_user(buffer->bs_mode, &p32->bs_mode) ||
-	    put_user(buffer->bs_nlink, &p32->bs_nlink) ||
-	    put_user(buffer->bs_uid, &p32->bs_uid) ||
-	    put_user(buffer->bs_gid, &p32->bs_gid) ||
-	    put_user(buffer->bs_rdev, &p32->bs_rdev) ||
-	    put_user(buffer->bs_blksize, &p32->bs_blksize) ||
-	    put_user(buffer->bs_size, &p32->bs_size) ||
+	compat_xfs_bstat_t	__user *p32 = ubuffer;
+
+	if (ubsize < sizeof(*p32))
+		return XFS_ERROR(ENOMEM);
+
+	if (put_user(buffer->bs_ino,	  &p32->bs_ino)		||
+	    put_user(buffer->bs_mode,	  &p32->bs_mode)	||
+	    put_user(buffer->bs_nlink,	  &p32->bs_nlink)	||
+	    put_user(buffer->bs_uid,	  &p32->bs_uid)		||
+	    put_user(buffer->bs_gid,	  &p32->bs_gid)		||
+	    put_user(buffer->bs_rdev,	  &p32->bs_rdev)	||
+	    put_user(buffer->bs_blksize,  &p32->bs_blksize)	||
+	    put_user(buffer->bs_size,	  &p32->bs_size)	||
 	    xfs_bstime_store_compat(&p32->bs_atime, &buffer->bs_atime) ||
 	    xfs_bstime_store_compat(&p32->bs_mtime, &buffer->bs_mtime) ||
 	    xfs_bstime_store_compat(&p32->bs_ctime, &buffer->bs_ctime) ||
-	    put_user(buffer->bs_blocks, &p32->bs_blocks) ||
-	    put_user(buffer->bs_xflags, &p32->bs_xflags) ||
-	    put_user(buffer->bs_extsize, &p32->bs_extsize) ||
-	    put_user(buffer->bs_extents, &p32->bs_extents) ||
-	    put_user(buffer->bs_gen, &p32->bs_gen) ||
-	    put_user(buffer->bs_projid, &p32->bs_projid) ||
-	    put_user(buffer->bs_dmevmask, &p32->bs_dmevmask) ||
-	    put_user(buffer->bs_dmstate, &p32->bs_dmstate) ||
+	    put_user(buffer->bs_blocks,	  &p32->bs_blocks)	||
+	    put_user(buffer->bs_xflags,	  &p32->bs_xflags)	||
+	    put_user(buffer->bs_extsize,  &p32->bs_extsize)	||
+	    put_user(buffer->bs_extents,  &p32->bs_extents)	||
+	    put_user(buffer->bs_gen,	  &p32->bs_gen)		||
+	    put_user(buffer->bs_projid,	  &p32->bs_projid)	||
+	    put_user(buffer->bs_dmevmask, &p32->bs_dmevmask)	||
+	    put_user(buffer->bs_dmstate,  &p32->bs_dmstate)	||
 	    put_user(buffer->bs_aextents, &p32->bs_aextents))
-		return -EFAULT;
-	return sizeof(*p32);
+		return XFS_ERROR(EFAULT);
+	if (ubused)
+		*ubused = sizeof(*p32);
+	return 0;
 }
 
-
-
-typedef struct compat_xfs_fsop_bulkreq {
-	compat_uptr_t	lastip;		/* last inode # pointer		*/
-	__s32		icount;		/* count of entries in buffer	*/
-	compat_uptr_t	ubuffer;	/* user buffer for inode desc.	*/
-	compat_uptr_t	ocount;		/* output count pointer		*/
-} compat_xfs_fsop_bulkreq_t;
-
-#define XFS_IOC_FSBULKSTAT_32 \
-	_IOWR('X', 101, struct compat_xfs_fsop_bulkreq)
-#define XFS_IOC_FSBULKSTAT_SINGLE_32 \
-	_IOWR('X', 102, struct compat_xfs_fsop_bulkreq)
-#define XFS_IOC_FSINUMBERS_32 \
-	_IOWR('X', 103, struct compat_xfs_fsop_bulkreq)
+STATIC int
+xfs_bulkstat_one_compat(
+	xfs_mount_t	*mp,		/* mount point for filesystem */
+	xfs_ino_t	ino,		/* inode number to get data for */
+	void		__user *buffer,	/* buffer to place output in */
+	int		ubsize,		/* size of buffer */
+	void		*private_data,	/* my private data */
+	xfs_daddr_t	bno,		/* starting bno of inode cluster */
+	int		*ubused,	/* bytes used by me */
+	void		*dibuff,	/* on-disk inode buffer */
+	int		*stat)		/* BULKSTAT_RV_... */
+{
+	return xfs_bulkstat_one_int(mp, ino, buffer, ubsize,
+				    xfs_bulkstat_one_fmt_compat, bno,
+				    ubused, dibuff, stat);
+}
 
 /* copied from xfs_ioctl.c */
 STATIC int
-xfs_ioc_bulkstat_compat(
-	xfs_mount_t		*mp,
-	unsigned int		cmd,
-	void			__user *arg)
+xfs_compat_ioc_bulkstat(
+	xfs_mount_t		  *mp,
+	unsigned int		  cmd,
+	compat_xfs_fsop_bulkreq_t __user *p32)
 {
-	compat_xfs_fsop_bulkreq_t __user *p32 = (void __user *)arg;
 	u32			addr;
 	xfs_fsop_bulkreq_t	bulkreq;
 	int			count;	/* # of records returned */
@@ -270,20 +263,20 @@ xfs_ioc_bulkstat_compat(
 	/* should be called again (unused here, but used in dmapi) */
 
 	if (!capable(CAP_SYS_ADMIN))
-		return -EPERM;
+		return -XFS_ERROR(EPERM);
 
 	if (XFS_FORCED_SHUTDOWN(mp))
 		return -XFS_ERROR(EIO);
 
 	if (get_user(addr, &p32->lastip))
-		return -EFAULT;
+		return -XFS_ERROR(EFAULT);
 	bulkreq.lastip = compat_ptr(addr);
 	if (get_user(bulkreq.icount, &p32->icount) ||
 	    get_user(addr, &p32->ubuffer))
-		return -EFAULT;
+		return -XFS_ERROR(EFAULT);
 	bulkreq.ubuffer = compat_ptr(addr);
 	if (get_user(addr, &p32->ocount))
-		return -EFAULT;
+		return -XFS_ERROR(EFAULT);
 	bulkreq.ocount = compat_ptr(addr);
 
 	if (copy_from_user(&inlast, bulkreq.lastip, sizeof(__s64)))
@@ -295,17 +288,22 @@ xfs_ioc_bulkstat_compat(
 	if (bulkreq.ubuffer == NULL)
 		return -XFS_ERROR(EINVAL);
 
-	if (cmd == XFS_IOC_FSINUMBERS)
+	if (cmd == XFS_IOC_FSINUMBERS_32) {
 		error = xfs_inumbers(mp, &inlast, &count,
 				bulkreq.ubuffer, xfs_inumbers_fmt_compat);
-	else {
-		/* declare a var to get a warning in case the type changes */
-		bulkstat_one_fmt_pf formatter = xfs_bulkstat_one_fmt_compat;
+	} else if (cmd == XFS_IOC_FSBULKSTAT_SINGLE_32) {
+		int res;
+
+		error = xfs_bulkstat_one_compat(mp, inlast, bulkreq.ubuffer,
+				sizeof(compat_xfs_bstat_t),
+				NULL, 0, NULL, NULL, &res);
+	} else if (cmd == XFS_IOC_FSBULKSTAT_32) {
 		error = xfs_bulkstat(mp, &inlast, &count,
-			xfs_bulkstat_one, formatter,
+			xfs_bulkstat_one_compat, NULL,
 			sizeof(compat_xfs_bstat_t), bulkreq.ubuffer,
 			BULKSTAT_FG_QUICK, &done);
-	}
+	} else
+		error = XFS_ERROR(EINVAL);
 	if (error)
 		return -error;
 
@@ -321,63 +319,301 @@ xfs_ioc_bulkstat_compat(
 	return 0;
 }
 
+STATIC int
+xfs_compat_handlereq_copyin(
+	xfs_fsop_handlereq_t		*hreq,
+	compat_xfs_fsop_handlereq_t	__user *arg32)
+{
+	compat_xfs_fsop_handlereq_t	hreq32;
 
+	if (copy_from_user(&hreq32, arg32, sizeof(compat_xfs_fsop_handlereq_t)))
+		return -XFS_ERROR(EFAULT);
+
+	hreq->fd = hreq32.fd;
+	hreq->path = compat_ptr(hreq32.path);
+	hreq->oflags = hreq32.oflags;
+	hreq->ihandle = compat_ptr(hreq32.ihandle);
+	hreq->ihandlen = hreq32.ihandlen;
+	hreq->ohandle = compat_ptr(hreq32.ohandle);
+	hreq->ohandlen = compat_ptr(hreq32.ohandlen);
+
+	return 0;
+}
 
-typedef struct compat_xfs_fsop_handlereq {
-	__u32		fd;		/* fd for FD_TO_HANDLE		*/
-	compat_uptr_t	path;		/* user pathname		*/
-	__u32		oflags;		/* open flags			*/
-	compat_uptr_t	ihandle;	/* user supplied handle		*/
-	__u32		ihandlen;	/* user supplied length		*/
-	compat_uptr_t	ohandle;	/* user buffer for handle	*/
-	compat_uptr_t	ohandlen;	/* user buffer length		*/
-} compat_xfs_fsop_handlereq_t;
-
-#define XFS_IOC_PATH_TO_FSHANDLE_32 \
-	_IOWR('X', 104, struct compat_xfs_fsop_handlereq)
-#define XFS_IOC_PATH_TO_HANDLE_32 \
-	_IOWR('X', 105, struct compat_xfs_fsop_handlereq)
-#define XFS_IOC_FD_TO_HANDLE_32 \
-	_IOWR('X', 106, struct compat_xfs_fsop_handlereq)
-#define XFS_IOC_OPEN_BY_HANDLE_32 \
-	_IOWR('X', 107, struct compat_xfs_fsop_handlereq)
-#define XFS_IOC_READLINK_BY_HANDLE_32 \
-	_IOWR('X', 108, struct compat_xfs_fsop_handlereq)
-
-STATIC unsigned long xfs_ioctl32_fshandle(unsigned long arg)
+/*
+ * Convert userspace handle data into inode.
+ *
+ * We use the fact that all the fsop_handlereq ioctl calls have a data
+ * structure argument whose first component is always a xfs_fsop_handlereq_t,
+ * so we can pass that sub structure into this handy, shared routine.
+ *
+ * If no error, caller must always iput the returned inode.
+ */
+STATIC int
+xfs_vget_fsop_handlereq_compat(
+	xfs_mount_t		*mp,
+	struct inode		*parinode,	/* parent inode pointer    */
+	compat_xfs_fsop_handlereq_t	*hreq,
+	struct inode		**inode)
 {
-	compat_xfs_fsop_handlereq_t __user *p32 = (void __user *)arg;
-	xfs_fsop_handlereq_t __user *p = compat_alloc_user_space(sizeof(*p));
-	u32 addr;
-
-	if (copy_in_user(&p->fd, &p32->fd, sizeof(__u32)) ||
-	    get_user(addr, &p32->path) ||
-	    put_user(compat_ptr(addr), &p->path) ||
-	    copy_in_user(&p->oflags, &p32->oflags, sizeof(__u32)) ||
-	    get_user(addr, &p32->ihandle) ||
-	    put_user(compat_ptr(addr), &p->ihandle) ||
-	    copy_in_user(&p->ihandlen, &p32->ihandlen, sizeof(__u32)) ||
-	    get_user(addr, &p32->ohandle) ||
-	    put_user(compat_ptr(addr), &p->ohandle) ||
-	    get_user(addr, &p32->ohandlen) ||
-	    put_user(compat_ptr(addr), &p->ohandlen))
-		return -EFAULT;
-
-	return (unsigned long)p;
+	void			__user *hanp;
+	size_t			hlen;
+	xfs_fid_t		*xfid;
+	xfs_handle_t		*handlep;
+	xfs_handle_t		handle;
+	xfs_inode_t		*ip;
+	xfs_ino_t		ino;
+	__u32			igen;
+	int			error;
+
+	/*
+	 * Only allow handle opens under a directory.
+	 */
+	if (!S_ISDIR(parinode->i_mode))
+		return XFS_ERROR(ENOTDIR);
+
+	hanp = compat_ptr(hreq->ihandle);
+	hlen = hreq->ihandlen;
+	handlep = &handle;
+
+	if (hlen < sizeof(handlep->ha_fsid) || hlen > sizeof(*handlep))
+		return XFS_ERROR(EINVAL);
+	if (copy_from_user(handlep, hanp, hlen))
+		return XFS_ERROR(EFAULT);
+	if (hlen < sizeof(*handlep))
+		memset(((char *)handlep) + hlen, 0, sizeof(*handlep) - hlen);
+	if (hlen > sizeof(handlep->ha_fsid)) {
+		if (handlep->ha_fid.fid_len !=
+		    (hlen - sizeof(handlep->ha_fsid) -
+			    sizeof(handlep->ha_fid.fid_len)) ||
+		    handlep->ha_fid.fid_pad)
+			return XFS_ERROR(EINVAL);
+	}
+
+	/*
+	 * Crack the handle, obtain the inode # & generation #
+	 */
+	xfid = (struct xfs_fid *)&handlep->ha_fid;
+	if (xfid->fid_len == sizeof(*xfid) - sizeof(xfid->fid_len)) {
+		ino  = xfid->fid_ino;
+		igen = xfid->fid_gen;
+	} else {
+		return XFS_ERROR(EINVAL);
+	}
+
+	/*
+	 * Get the XFS inode, building a Linux inode to go with it.
+	 */
+	error = xfs_iget(mp, NULL, ino, 0, XFS_ILOCK_SHARED, &ip, 0);
+	if (error)
+		return error;
+	if (ip == NULL)
+		return XFS_ERROR(EIO);
+	if (ip->i_d.di_gen != igen) {
+		xfs_iput_new(ip, XFS_ILOCK_SHARED);
+		return XFS_ERROR(ENOENT);
+	}
+
+	xfs_iunlock(ip, XFS_ILOCK_SHARED);
+
+	*inode = VFS_I(ip);
+	return 0;
 }
 
+STATIC int
+xfs_compat_attrlist_by_handle(
+	xfs_mount_t		*mp,
+	void			__user *arg,
+	struct inode		*parinode)
+{
+	int			error;
+	attrlist_cursor_kern_t	*cursor;
+	compat_xfs_fsop_attrlist_handlereq_t al_hreq;
+	struct inode		*inode;
+	char			*kbuf;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -XFS_ERROR(EPERM);
+	if (copy_from_user(&al_hreq, arg,
+			   sizeof(compat_xfs_fsop_attrlist_handlereq_t)))
+		return -XFS_ERROR(EFAULT);
+	if (al_hreq.buflen > XATTR_LIST_MAX)
+		return -XFS_ERROR(EINVAL);
+
+	/*
+	 * Reject flags, only allow namespaces.
+	 */
+	if (al_hreq.flags & ~(ATTR_ROOT | ATTR_SECURE))
+		return -XFS_ERROR(EINVAL);
+
+	error = xfs_vget_fsop_handlereq_compat(mp, parinode, &al_hreq.hreq,
+					       &inode);
+	if (error)
+		goto out;
+
+	kbuf = kmalloc(al_hreq.buflen, GFP_KERNEL);
+	if (!kbuf)
+		goto out_vn_rele;
+
+	cursor = (attrlist_cursor_kern_t *)&al_hreq.pos;
+	error = xfs_attr_list(XFS_I(inode), kbuf, al_hreq.buflen,
+					al_hreq.flags, cursor);
+	if (error)
+		goto out_kfree;
+
+	if (copy_to_user(compat_ptr(al_hreq.buffer), kbuf, al_hreq.buflen))
+		error = -EFAULT;
+
+ out_kfree:
+	kfree(kbuf);
+ out_vn_rele:
+	iput(inode);
+ out:
+	return -error;
+}
+
+STATIC int
+xfs_compat_attrmulti_by_handle(
+	xfs_mount_t				*mp,
+	void					__user *arg,
+	struct inode				*parinode)
+{
+	int					error;
+	compat_xfs_attr_multiop_t		*ops;
+	compat_xfs_fsop_attrmulti_handlereq_t	am_hreq;
+	struct inode				*inode;
+	unsigned int				i, size;
+	char					*attr_name;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -XFS_ERROR(EPERM);
+	if (copy_from_user(&am_hreq, arg,
+			   sizeof(compat_xfs_fsop_attrmulti_handlereq_t)))
+		return -XFS_ERROR(EFAULT);
+
+	error = xfs_vget_fsop_handlereq_compat(mp, parinode, &am_hreq.hreq,
+					       &inode);
+	if (error)
+		goto out;
+
+	error = E2BIG;
+	size = am_hreq.opcount * sizeof(compat_xfs_attr_multiop_t);
+	if (!size || size > 16 * PAGE_SIZE)
+		goto out_vn_rele;
+
+	error = ENOMEM;
+	ops = kmalloc(size, GFP_KERNEL);
+	if (!ops)
+		goto out_vn_rele;
+
+	error = EFAULT;
+	if (copy_from_user(ops, compat_ptr(am_hreq.ops), size))
+		goto out_kfree_ops;
+
+	attr_name = kmalloc(MAXNAMELEN, GFP_KERNEL);
+	if (!attr_name)
+		goto out_kfree_ops;
+
+
+	error = 0;
+	for (i = 0; i < am_hreq.opcount; i++) {
+		ops[i].am_error = strncpy_from_user(attr_name,
+				compat_ptr(ops[i].am_attrname),
+				MAXNAMELEN);
+		if (ops[i].am_error == 0 || ops[i].am_error == MAXNAMELEN)
+			error = -ERANGE;
+		if (ops[i].am_error < 0)
+			break;
+
+		switch (ops[i].am_opcode) {
+		case ATTR_OP_GET:
+			ops[i].am_error = xfs_attrmulti_attr_get(inode,
+					attr_name,
+					compat_ptr(ops[i].am_attrvalue),
+					&ops[i].am_length, ops[i].am_flags);
+			break;
+		case ATTR_OP_SET:
+			ops[i].am_error = xfs_attrmulti_attr_set(inode,
+					attr_name,
+					compat_ptr(ops[i].am_attrvalue),
+					ops[i].am_length, ops[i].am_flags);
+			break;
+		case ATTR_OP_REMOVE:
+			ops[i].am_error = xfs_attrmulti_attr_remove(inode,
+					attr_name, ops[i].am_flags);
+			break;
+		default:
+			ops[i].am_error = EINVAL;
+		}
+	}
+
+	if (copy_to_user(compat_ptr(am_hreq.ops), ops, size))
+		error = XFS_ERROR(EFAULT);
+
+	kfree(attr_name);
+ out_kfree_ops:
+	kfree(ops);
+ out_vn_rele:
+	iput(inode);
+ out:
+	return -error;
+}
+
+STATIC int
+xfs_compat_fssetdm_by_handle(
+	xfs_mount_t		*mp,
+	void			__user *arg,
+	struct inode		*parinode)
+{
+	int			error;
+	struct fsdmidata	fsd;
+	compat_xfs_fsop_setdm_handlereq_t dmhreq;
+	struct inode		*inode;
+
+	if (!capable(CAP_MKNOD))
+		return -XFS_ERROR(EPERM);
+	if (copy_from_user(&dmhreq, arg,
+			   sizeof(compat_xfs_fsop_setdm_handlereq_t)))
+		return -XFS_ERROR(EFAULT);
+
+	error = xfs_vget_fsop_handlereq_compat(mp, parinode, &dmhreq.hreq,
+					       &inode);
+	if (error)
+		return -error;
+
+	if (IS_IMMUTABLE(inode) || IS_APPEND(inode)) {
+		error = -XFS_ERROR(EPERM);
+		goto out;
+	}
+
+	if (copy_from_user(&fsd, compat_ptr(dmhreq.data), sizeof(fsd))) {
+		error = -XFS_ERROR(EFAULT);
+		goto out;
+	}
+
+	error = -xfs_set_dmattrs(XFS_I(inode), fsd.fsd_dmevmask,
+				 fsd.fsd_dmstate);
+
+out:
+	iput(inode);
+	return error;
+}
 
 STATIC long
 xfs_compat_ioctl(
-	int		mode,
-	struct file	*file,
+	xfs_inode_t	*ip,
+	struct file	*filp,
+	int		ioflags,
 	unsigned	cmd,
-	unsigned long	arg)
+	void		__user *arg)
 {
-	struct inode	*inode = file->f_path.dentry->d_inode;
+	struct inode	*inode = filp->f_path.dentry->d_inode;
+	xfs_mount_t	*mp = ip->i_mount;
 	int		error;
 
+	xfs_itrace_entry(XFS_I(inode));
 	switch (cmd) {
+	/* No size or alignment issues on any arch */
 	case XFS_IOC_DIOINFO:
 	case XFS_IOC_FSGEOMETRY:
 	case XFS_IOC_FSGETXATTR:
@@ -387,48 +623,18 @@ xfs_compat_ioctl(
 	case XFS_IOC_GETBMAP:
 	case XFS_IOC_GETBMAPA:
 	case XFS_IOC_GETBMAPX:
-/* not handled
-	case XFS_IOC_FSSETDM_BY_HANDLE:
-	case XFS_IOC_ATTRLIST_BY_HANDLE:
-	case XFS_IOC_ATTRMULTI_BY_HANDLE:
-*/
 	case XFS_IOC_FSCOUNTS:
 	case XFS_IOC_SET_RESBLKS:
 	case XFS_IOC_GET_RESBLKS:
-	case XFS_IOC_FSGROWFSDATA:
 	case XFS_IOC_FSGROWFSLOG:
-	case XFS_IOC_FSGROWFSRT:
 	case XFS_IOC_FREEZE:
 	case XFS_IOC_THAW:
 	case XFS_IOC_GOINGDOWN:
 	case XFS_IOC_ERROR_INJECTION:
 	case XFS_IOC_ERROR_CLEARALL:
-		break;
-
-	case XFS_IOC32_GETXFLAGS:
-	case XFS_IOC32_SETXFLAGS:
-	case XFS_IOC32_GETVERSION:
-		cmd = _NATIVE_IOC(cmd, long);
-		break;
-#ifdef BROKEN_X86_ALIGNMENT
-	/* xfs_flock_t has wrong u32 vs u64 alignment */
-	case XFS_IOC_ALLOCSP_32:
-	case XFS_IOC_FREESP_32:
-	case XFS_IOC_ALLOCSP64_32:
-	case XFS_IOC_FREESP64_32:
-	case XFS_IOC_RESVSP_32:
-	case XFS_IOC_UNRESVSP_32:
-	case XFS_IOC_RESVSP64_32:
-	case XFS_IOC_UNRESVSP64_32:
-		arg = xfs_ioctl32_flock(arg);
-		cmd = _NATIVE_IOC(cmd, struct xfs_flock64);
-		break;
-	case XFS_IOC_FSGEOMETRY_V1_32:
-		arg = xfs_ioctl32_geom_v1(arg);
-		cmd = _NATIVE_IOC(cmd, struct xfs_fsop_geom_v1);
-		break;
-
-#else /* These are handled fine if no alignment issues */
+		return xfs_ioctl(ip, filp, ioflags, cmd, arg);
+#ifndef BROKEN_X86_ALIGNMENT
+	/* These are handled fine if no alignment issues */
 	case XFS_IOC_ALLOCSP:
 	case XFS_IOC_FREESP:
 	case XFS_IOC_RESVSP:
@@ -438,51 +644,120 @@ xfs_compat_ioctl(
 	case XFS_IOC_RESVSP64:
 	case XFS_IOC_UNRESVSP64:
 	case XFS_IOC_FSGEOMETRY_V1:
-		break;
+	case XFS_IOC_FSGROWFSDATA:
+	case XFS_IOC_FSGROWFSRT:
+		return xfs_ioctl(ip, filp, ioflags, cmd, arg);
+#else
+	case XFS_IOC_ALLOCSP_32:
+	case XFS_IOC_FREESP_32:
+	case XFS_IOC_ALLOCSP64_32:
+	case XFS_IOC_FREESP64_32:
+	case XFS_IOC_RESVSP_32:
+	case XFS_IOC_UNRESVSP_32:
+	case XFS_IOC_RESVSP64_32:
+	case XFS_IOC_UNRESVSP64_32: {
+		struct xfs_flock64	bf;
 
-	/* xfs_bstat_t still has wrong u32 vs u64 alignment */
-	case XFS_IOC_SWAPEXT:
-		break;
+		if (xfs_compat_flock64_copyin(&bf, arg))
+			return -XFS_ERROR(EFAULT);
+		cmd = _NATIVE_IOC(cmd, struct xfs_flock64);
+		return xfs_ioc_space(ip, inode, filp, ioflags, cmd, &bf);
+	}
+	case XFS_IOC_FSGEOMETRY_V1_32:
+		return xfs_compat_ioc_fsgeometry_v1(mp, arg);
+	case XFS_IOC_FSGROWFSDATA_32: {
+		struct xfs_growfs_data	in;
 
+		if (xfs_compat_growfs_data_copyin(&in, arg))
+			return -XFS_ERROR(EFAULT);
+		error = xfs_growfs_data(mp, &in);
+		return -error;
+	}
+	case XFS_IOC_FSGROWFSRT_32: {
+		struct xfs_growfs_rt	in;
+
+		if (xfs_compat_growfs_rt_copyin(&in, arg))
+			return -XFS_ERROR(EFAULT);
+		error = xfs_growfs_rt(mp, &in);
+		return -error;
+	}
 #endif
+	/* long changes size, but xfs only copiese out 32 bits */
+	case XFS_IOC_GETXFLAGS_32:
+	case XFS_IOC_SETXFLAGS_32:
+	case XFS_IOC_GETVERSION_32:
+		cmd = _NATIVE_IOC(cmd, long);
+		return xfs_ioctl(ip, filp, ioflags, cmd, arg);
+	case XFS_IOC_SWAPEXT: {
+		struct xfs_swapext	  sxp;
+		struct compat_xfs_swapext __user *sxu = arg;
+
+		/* Bulk copy in up to the sx_stat field, then copy bstat */
+		if (copy_from_user(&sxp, sxu,
+				   offsetof(struct xfs_swapext, sx_stat)) ||
+		    xfs_ioctl32_bstat_copyin(&sxp.sx_stat, &sxu->sx_stat))
+			return -XFS_ERROR(EFAULT);
+		error = xfs_swapext(&sxp);
+		return -error;
+	}
 	case XFS_IOC_FSBULKSTAT_32:
 	case XFS_IOC_FSBULKSTAT_SINGLE_32:
 	case XFS_IOC_FSINUMBERS_32:
-		cmd = _NATIVE_IOC(cmd, struct xfs_fsop_bulkreq);
-		return xfs_ioc_bulkstat_compat(XFS_I(inode)->i_mount,
-				cmd, (void __user*)arg);
+		return xfs_compat_ioc_bulkstat(mp, cmd, arg);
 	case XFS_IOC_FD_TO_HANDLE_32:
 	case XFS_IOC_PATH_TO_HANDLE_32:
-	case XFS_IOC_PATH_TO_FSHANDLE_32:
-	case XFS_IOC_OPEN_BY_HANDLE_32:
-	case XFS_IOC_READLINK_BY_HANDLE_32:
-		arg = xfs_ioctl32_fshandle(arg);
+	case XFS_IOC_PATH_TO_FSHANDLE_32: {
+		struct xfs_fsop_handlereq	hreq;
+
+		if (xfs_compat_handlereq_copyin(&hreq, arg))
+			return -XFS_ERROR(EFAULT);
 		cmd = _NATIVE_IOC(cmd, struct xfs_fsop_handlereq);
-		break;
-	default:
-		return -ENOIOCTLCMD;
+		return xfs_find_handle(cmd, &hreq);
 	}
+	case XFS_IOC_OPEN_BY_HANDLE_32: {
+		struct xfs_fsop_handlereq	hreq;
 
-	error = xfs_ioctl(XFS_I(inode), file, mode, cmd, (void __user *)arg);
-	xfs_iflags_set(XFS_I(inode), XFS_IMODIFIED);
+		if (xfs_compat_handlereq_copyin(&hreq, arg))
+			return -XFS_ERROR(EFAULT);
+		return xfs_open_by_handle(mp, &hreq, filp, inode);
+	}
+	case XFS_IOC_READLINK_BY_HANDLE_32: {
+		struct xfs_fsop_handlereq	hreq;
 
-	return error;
+		if (xfs_compat_handlereq_copyin(&hreq, arg))
+			return -XFS_ERROR(EFAULT);
+		return xfs_readlink_by_handle(mp, &hreq, inode);
+	}
+	case XFS_IOC_ATTRLIST_BY_HANDLE_32:
+		return xfs_compat_attrlist_by_handle(mp, arg, inode);
+	case XFS_IOC_ATTRMULTI_BY_HANDLE_32:
+		return xfs_compat_attrmulti_by_handle(mp, arg, inode);
+	case XFS_IOC_FSSETDM_BY_HANDLE_32:
+		return xfs_compat_fssetdm_by_handle(mp, arg, inode);
+	default:
+		return -XFS_ERROR(ENOIOCTLCMD);
+	}
 }
 
 long
 xfs_file_compat_ioctl(
-	struct file		*file,
-	unsigned		cmd,
-	unsigned long		arg)
+	struct file		*filp,
+	unsigned int		cmd,
+	unsigned long		p)
 {
-	return xfs_compat_ioctl(0, file, cmd, arg);
+	struct inode	*inode = filp->f_path.dentry->d_inode;
+
+	return xfs_compat_ioctl(XFS_I(inode), filp, 0, cmd, (void __user *)p);
 }
 
 long
 xfs_file_compat_invis_ioctl(
-	struct file		*file,
-	unsigned		cmd,
-	unsigned long		arg)
+	struct file		*filp,
+	unsigned int		cmd,
+	unsigned long		p)
 {
-	return xfs_compat_ioctl(IO_INVIS, file, cmd, arg);
+	struct inode	*inode = filp->f_path.dentry->d_inode;
+
+	return xfs_compat_ioctl(XFS_I(inode), filp, IO_INVIS, cmd,
+				(void __user *)p);
 }
diff --git a/fs/xfs/linux-2.6/xfs_ioctl32.h b/fs/xfs/linux-2.6/xfs_ioctl32.h
index 02de6e62ee37..1024c4f8ba0d 100644
--- a/fs/xfs/linux-2.6/xfs_ioctl32.h
+++ b/fs/xfs/linux-2.6/xfs_ioctl32.h
@@ -18,7 +18,217 @@
 #ifndef __XFS_IOCTL32_H__
 #define __XFS_IOCTL32_H__
 
-extern long xfs_file_compat_ioctl(struct file *, unsigned, unsigned long);
-extern long xfs_file_compat_invis_ioctl(struct file *, unsigned, unsigned long);
+#include <linux/compat.h>
+
+/*
+ * on 32-bit arches, ioctl argument structures may have different sizes
+ * and/or alignment.  We define compat structures which match the
+ * 32-bit sizes/alignments here, and their associated ioctl numbers.
+ *
+ * xfs_ioctl32.c contains routines to copy these structures in and out.
+ */
+
+/* stock kernel-level ioctls we support */
+#define XFS_IOC_GETXFLAGS_32	FS_IOC32_GETFLAGS
+#define XFS_IOC_SETXFLAGS_32	FS_IOC32_SETFLAGS
+#define XFS_IOC_GETVERSION_32	FS_IOC32_GETVERSION
+
+/*
+ * On intel, even if sizes match, alignment and/or padding may differ.
+ */
+#if defined(CONFIG_IA64) || defined(CONFIG_X86_64)
+#define BROKEN_X86_ALIGNMENT
+#define __compat_packed __attribute__((packed))
+#else
+#define __compat_packed
+#endif
+
+typedef struct compat_xfs_bstime {
+	compat_time_t	tv_sec;		/* seconds		*/
+	__s32		tv_nsec;	/* and nanoseconds	*/
+} compat_xfs_bstime_t;
+
+typedef struct compat_xfs_bstat {
+	__u64		bs_ino;		/* inode number			*/
+	__u16		bs_mode;	/* type and mode		*/
+	__u16		bs_nlink;	/* number of links		*/
+	__u32		bs_uid;		/* user id			*/
+	__u32		bs_gid;		/* group id			*/
+	__u32		bs_rdev;	/* device value			*/
+	__s32		bs_blksize;	/* block size			*/
+	__s64		bs_size;	/* file size			*/
+	compat_xfs_bstime_t bs_atime;	/* access time			*/
+	compat_xfs_bstime_t bs_mtime;	/* modify time			*/
+	compat_xfs_bstime_t bs_ctime;	/* inode change time		*/
+	int64_t		bs_blocks;	/* number of blocks		*/
+	__u32		bs_xflags;	/* extended flags		*/
+	__s32		bs_extsize;	/* extent size			*/
+	__s32		bs_extents;	/* number of extents		*/
+	__u32		bs_gen;		/* generation count		*/
+	__u16		bs_projid;	/* project id			*/
+	unsigned char	bs_pad[14];	/* pad space, unused		*/
+	__u32		bs_dmevmask;	/* DMIG event mask		*/
+	__u16		bs_dmstate;	/* DMIG state info		*/
+	__u16		bs_aextents;	/* attribute number of extents	*/
+} __compat_packed compat_xfs_bstat_t;
+
+typedef struct compat_xfs_fsop_bulkreq {
+	compat_uptr_t	lastip;		/* last inode # pointer		*/
+	__s32		icount;		/* count of entries in buffer	*/
+	compat_uptr_t	ubuffer;	/* user buffer for inode desc.	*/
+	compat_uptr_t	ocount;		/* output count pointer		*/
+} compat_xfs_fsop_bulkreq_t;
+
+#define XFS_IOC_FSBULKSTAT_32 \
+	_IOWR('X', 101, struct compat_xfs_fsop_bulkreq)
+#define XFS_IOC_FSBULKSTAT_SINGLE_32 \
+	_IOWR('X', 102, struct compat_xfs_fsop_bulkreq)
+#define XFS_IOC_FSINUMBERS_32 \
+	_IOWR('X', 103, struct compat_xfs_fsop_bulkreq)
+
+typedef struct compat_xfs_fsop_handlereq {
+	__u32		fd;		/* fd for FD_TO_HANDLE		*/
+	compat_uptr_t	path;		/* user pathname		*/
+	__u32		oflags;		/* open flags			*/
+	compat_uptr_t	ihandle;	/* user supplied handle		*/
+	__u32		ihandlen;	/* user supplied length		*/
+	compat_uptr_t	ohandle;	/* user buffer for handle	*/
+	compat_uptr_t	ohandlen;	/* user buffer length		*/
+} compat_xfs_fsop_handlereq_t;
+
+#define XFS_IOC_PATH_TO_FSHANDLE_32 \
+	_IOWR('X', 104, struct compat_xfs_fsop_handlereq)
+#define XFS_IOC_PATH_TO_HANDLE_32 \
+	_IOWR('X', 105, struct compat_xfs_fsop_handlereq)
+#define XFS_IOC_FD_TO_HANDLE_32 \
+	_IOWR('X', 106, struct compat_xfs_fsop_handlereq)
+#define XFS_IOC_OPEN_BY_HANDLE_32 \
+	_IOWR('X', 107, struct compat_xfs_fsop_handlereq)
+#define XFS_IOC_READLINK_BY_HANDLE_32 \
+	_IOWR('X', 108, struct compat_xfs_fsop_handlereq)
+
+/* The bstat field in the swapext struct needs translation */
+typedef struct compat_xfs_swapext {
+	__int64_t		sx_version;	/* version */
+	__int64_t		sx_fdtarget;	/* fd of target file */
+	__int64_t		sx_fdtmp;	/* fd of tmp file */
+	xfs_off_t		sx_offset;	/* offset into file */
+	xfs_off_t		sx_length;	/* leng from offset */
+	char			sx_pad[16];	/* pad space, unused */
+	compat_xfs_bstat_t	sx_stat;	/* stat of target b4 copy */
+} __compat_packed compat_xfs_swapext_t;
+
+#define XFS_IOC_SWAPEXT_32	_IOWR('X', 109, struct compat_xfs_swapext)
+
+typedef struct compat_xfs_fsop_attrlist_handlereq {
+	struct compat_xfs_fsop_handlereq hreq; /* handle interface structure */
+	struct xfs_attrlist_cursor	pos; /* opaque cookie, list offset */
+	__u32				flags;	/* which namespace to use */
+	__u32				buflen;	/* length of buffer supplied */
+	compat_uptr_t			buffer;	/* returned names */
+} __compat_packed compat_xfs_fsop_attrlist_handlereq_t;
+
+/* Note: actually this is read/write */
+#define XFS_IOC_ATTRLIST_BY_HANDLE_32 \
+	_IOW('X', 122, struct compat_xfs_fsop_attrlist_handlereq)
+
+/* am_opcodes defined in xfs_fs.h */
+typedef struct compat_xfs_attr_multiop {
+	__u32		am_opcode;
+	__s32		am_error;
+	compat_uptr_t	am_attrname;
+	compat_uptr_t	am_attrvalue;
+	__u32		am_length;
+	__u32		am_flags;
+} compat_xfs_attr_multiop_t;
+
+typedef struct compat_xfs_fsop_attrmulti_handlereq {
+	struct compat_xfs_fsop_handlereq hreq; /* handle interface structure */
+	__u32				opcount;/* count of following multiop */
+	/* ptr to compat_xfs_attr_multiop */
+	compat_uptr_t			ops; /* attr_multi data */
+} compat_xfs_fsop_attrmulti_handlereq_t;
+
+#define XFS_IOC_ATTRMULTI_BY_HANDLE_32 \
+	_IOW('X', 123, struct compat_xfs_fsop_attrmulti_handlereq)
+
+typedef struct compat_xfs_fsop_setdm_handlereq {
+	struct compat_xfs_fsop_handlereq hreq;	/* handle information   */
+	/* ptr to struct fsdmidata */
+	compat_uptr_t			data;	/* DMAPI data   */
+} compat_xfs_fsop_setdm_handlereq_t;
+
+#define XFS_IOC_FSSETDM_BY_HANDLE_32 \
+	_IOW('X', 121, struct compat_xfs_fsop_setdm_handlereq)
+
+#ifdef BROKEN_X86_ALIGNMENT
+/* on ia32 l_start is on a 32-bit boundary */
+typedef struct compat_xfs_flock64 {
+	__s16		l_type;
+	__s16		l_whence;
+	__s64		l_start	__attribute__((packed));
+			/* len == 0 means until end of file */
+	__s64		l_len __attribute__((packed));
+	__s32		l_sysid;
+	__u32		l_pid;
+	__s32		l_pad[4];	/* reserve area */
+} compat_xfs_flock64_t;
+
+#define XFS_IOC_ALLOCSP_32	_IOW('X', 10, struct compat_xfs_flock64)
+#define XFS_IOC_FREESP_32	_IOW('X', 11, struct compat_xfs_flock64)
+#define XFS_IOC_ALLOCSP64_32	_IOW('X', 36, struct compat_xfs_flock64)
+#define XFS_IOC_FREESP64_32	_IOW('X', 37, struct compat_xfs_flock64)
+#define XFS_IOC_RESVSP_32	_IOW('X', 40, struct compat_xfs_flock64)
+#define XFS_IOC_UNRESVSP_32	_IOW('X', 41, struct compat_xfs_flock64)
+#define XFS_IOC_RESVSP64_32	_IOW('X', 42, struct compat_xfs_flock64)
+#define XFS_IOC_UNRESVSP64_32	_IOW('X', 43, struct compat_xfs_flock64)
+
+typedef struct compat_xfs_fsop_geom_v1 {
+	__u32		blocksize;	/* filesystem (data) block size */
+	__u32		rtextsize;	/* realtime extent size		*/
+	__u32		agblocks;	/* fsblocks in an AG		*/
+	__u32		agcount;	/* number of allocation groups	*/
+	__u32		logblocks;	/* fsblocks in the log		*/
+	__u32		sectsize;	/* (data) sector size, bytes	*/
+	__u32		inodesize;	/* inode size in bytes		*/
+	__u32		imaxpct;	/* max allowed inode space(%)	*/
+	__u64		datablocks;	/* fsblocks in data subvolume	*/
+	__u64		rtblocks;	/* fsblocks in realtime subvol	*/
+	__u64		rtextents;	/* rt extents in realtime subvol*/
+	__u64		logstart;	/* starting fsblock of the log	*/
+	unsigned char	uuid[16];	/* unique id of the filesystem	*/
+	__u32		sunit;		/* stripe unit, fsblocks	*/
+	__u32		swidth;		/* stripe width, fsblocks	*/
+	__s32		version;	/* structure version		*/
+	__u32		flags;		/* superblock version flags	*/
+	__u32		logsectsize;	/* log sector size, bytes	*/
+	__u32		rtsectsize;	/* realtime sector size, bytes	*/
+	__u32		dirblocksize;	/* directory block size, bytes	*/
+} __attribute__((packed)) compat_xfs_fsop_geom_v1_t;
+
+#define XFS_IOC_FSGEOMETRY_V1_32  \
+	_IOR('X', 100, struct compat_xfs_fsop_geom_v1)
+
+typedef struct compat_xfs_inogrp {
+	__u64		xi_startino;	/* starting inode number	*/
+	__s32		xi_alloccount;	/* # bits set in allocmask	*/
+	__u64		xi_allocmask;	/* mask of allocated inodes	*/
+} __attribute__((packed)) compat_xfs_inogrp_t;
+
+/* These growfs input structures have padding on the end, so must translate */
+typedef struct compat_xfs_growfs_data {
+	__u64		newblocks;	/* new data subvol size, fsblocks */
+	__u32		imaxpct;	/* new inode space percentage limit */
+} __attribute__((packed)) compat_xfs_growfs_data_t;
+
+typedef struct compat_xfs_growfs_rt {
+	__u64		newblocks;	/* new realtime size, fsblocks */
+	__u32		extsize;	/* new realtime extent size, fsblocks */
+} __attribute__((packed)) compat_xfs_growfs_rt_t;
+
+#define XFS_IOC_FSGROWFSDATA_32 _IOW('X', 110, struct compat_xfs_growfs_data)
+#define XFS_IOC_FSGROWFSRT_32   _IOW('X', 112, struct compat_xfs_growfs_rt)
+
+#endif /* BROKEN_X86_ALIGNMENT */
 
 #endif /* __XFS_IOCTL32_H__ */
diff --git a/fs/xfs/linux-2.6/xfs_iops.c b/fs/xfs/linux-2.6/xfs_iops.c
index 095d271f3434..7aa53fefc67f 100644
--- a/fs/xfs/linux-2.6/xfs_iops.c
+++ b/fs/xfs/linux-2.6/xfs_iops.c
@@ -53,6 +53,7 @@
 #include <linux/namei.h>
 #include <linux/security.h>
 #include <linux/falloc.h>
+#include <linux/fiemap.h>
 
 /*
  * Bring the atime in the XFS inode uptodate.
@@ -64,14 +65,14 @@ xfs_synchronize_atime(
 {
 	struct inode	*inode = VFS_I(ip);
 
-	if (inode) {
+	if (!(inode->i_state & I_CLEAR)) {
 		ip->i_d.di_atime.t_sec = (__int32_t)inode->i_atime.tv_sec;
 		ip->i_d.di_atime.t_nsec = (__int32_t)inode->i_atime.tv_nsec;
 	}
 }
 
 /*
- * If the linux inode exists, mark it dirty.
+ * If the linux inode is valid, mark it dirty.
  * Used when commiting a dirty inode into a transaction so that
  * the inode will get written back by the linux code
  */
@@ -81,7 +82,7 @@ xfs_mark_inode_dirty_sync(
 {
 	struct inode	*inode = VFS_I(ip);
 
-	if (inode)
+	if (!(inode->i_state & (I_WILL_FREE|I_FREEING|I_CLEAR)))
 		mark_inode_dirty_sync(inode);
 }
 
@@ -128,7 +129,7 @@ xfs_ichgtime(
 	if (sync_it) {
 		SYNCHRONIZE();
 		ip->i_update_core = 1;
-		mark_inode_dirty_sync(inode);
+		xfs_mark_inode_dirty_sync(ip);
 	}
 }
 
@@ -158,8 +159,6 @@ xfs_init_security(
 	}
 
 	error = xfs_attr_set(ip, name, value, length, ATTR_SECURE);
-	if (!error)
-		xfs_iflags_set(ip, XFS_IMODIFIED);
 
 	kfree(name);
 	kfree(value);
@@ -260,7 +259,6 @@ xfs_vn_mknod(
 		error = _ACL_INHERIT(inode, mode, default_acl);
 		if (unlikely(error))
 			goto out_cleanup_inode;
-		xfs_iflags_set(ip, XFS_IMODIFIED);
 		_ACL_FREE(default_acl);
 	}
 
@@ -366,21 +364,17 @@ xfs_vn_link(
 	struct inode	*dir,
 	struct dentry	*dentry)
 {
-	struct inode	*inode;	/* inode of guy being linked to */
+	struct inode	*inode = old_dentry->d_inode;
 	struct xfs_name	name;
 	int		error;
 
-	inode = old_dentry->d_inode;
 	xfs_dentry_to_name(&name, dentry);
 
-	igrab(inode);
 	error = xfs_link(XFS_I(dir), XFS_I(inode), &name);
-	if (unlikely(error)) {
-		iput(inode);
+	if (unlikely(error))
 		return -error;
-	}
 
-	xfs_iflags_set(XFS_I(dir), XFS_IMODIFIED);
+	atomic_inc(&inode->i_count);
 	d_instantiate(dentry, inode);
 	return 0;
 }
@@ -601,7 +595,7 @@ xfs_vn_setattr(
 	struct dentry	*dentry,
 	struct iattr	*iattr)
 {
-	return -xfs_setattr(XFS_I(dentry->d_inode), iattr, 0, NULL);
+	return -xfs_setattr(XFS_I(dentry->d_inode), iattr, 0);
 }
 
 /*
@@ -642,7 +636,7 @@ xfs_vn_fallocate(
 
 	xfs_ilock(ip, XFS_IOLOCK_EXCL);
 	error = xfs_change_file_space(ip, XFS_IOC_RESVSP, &bf,
-				      0, NULL, XFS_ATTR_NOLOCK);
+				      0, XFS_ATTR_NOLOCK);
 	if (!error && !(mode & FALLOC_FL_KEEP_SIZE) &&
 	    offset + len > i_size_read(inode))
 		new_size = offset + len;
@@ -653,7 +647,7 @@ xfs_vn_fallocate(
 
 		iattr.ia_valid = ATTR_SIZE;
 		iattr.ia_size = new_size;
-		error = xfs_setattr(ip, &iattr, XFS_ATTR_NOLOCK, NULL);
+		error = xfs_setattr(ip, &iattr, XFS_ATTR_NOLOCK);
 	}
 
 	xfs_iunlock(ip, XFS_IOLOCK_EXCL);
@@ -661,6 +655,88 @@ out_error:
 	return error;
 }
 
+#define XFS_FIEMAP_FLAGS	(FIEMAP_FLAG_SYNC|FIEMAP_FLAG_XATTR)
+
+/*
+ * Call fiemap helper to fill in user data.
+ * Returns positive errors to xfs_getbmap.
+ */
+STATIC int
+xfs_fiemap_format(
+	void			**arg,
+	struct getbmapx		*bmv,
+	int			*full)
+{
+	int			error;
+	struct fiemap_extent_info *fieinfo = *arg;
+	u32			fiemap_flags = 0;
+	u64			logical, physical, length;
+
+	/* Do nothing for a hole */
+	if (bmv->bmv_block == -1LL)
+		return 0;
+
+	logical = BBTOB(bmv->bmv_offset);
+	physical = BBTOB(bmv->bmv_block);
+	length = BBTOB(bmv->bmv_length);
+
+	if (bmv->bmv_oflags & BMV_OF_PREALLOC)
+		fiemap_flags |= FIEMAP_EXTENT_UNWRITTEN;
+	else if (bmv->bmv_oflags & BMV_OF_DELALLOC) {
+		fiemap_flags |= FIEMAP_EXTENT_DELALLOC;
+		physical = 0;   /* no block yet */
+	}
+	if (bmv->bmv_oflags & BMV_OF_LAST)
+		fiemap_flags |= FIEMAP_EXTENT_LAST;
+
+	error = fiemap_fill_next_extent(fieinfo, logical, physical,
+					length, fiemap_flags);
+	if (error > 0) {
+		error = 0;
+		*full = 1;	/* user array now full */
+	}
+
+	return -error;
+}
+
+STATIC int
+xfs_vn_fiemap(
+	struct inode		*inode,
+	struct fiemap_extent_info *fieinfo,
+	u64			start,
+	u64			length)
+{
+	xfs_inode_t		*ip = XFS_I(inode);
+	struct getbmapx		bm;
+	int			error;
+
+	error = fiemap_check_flags(fieinfo, XFS_FIEMAP_FLAGS);
+	if (error)
+		return error;
+
+	/* Set up bmap header for xfs internal routine */
+	bm.bmv_offset = BTOBB(start);
+	/* Special case for whole file */
+	if (length == FIEMAP_MAX_OFFSET)
+		bm.bmv_length = -1LL;
+	else
+		bm.bmv_length = BTOBB(length);
+
+	/* our formatter will tell xfs_getbmap when to stop. */
+	bm.bmv_count = MAXEXTNUM;
+	bm.bmv_iflags = BMV_IF_PREALLOC;
+	if (fieinfo->fi_flags & FIEMAP_FLAG_XATTR)
+		bm.bmv_iflags |= BMV_IF_ATTRFORK;
+	if (!(fieinfo->fi_flags & FIEMAP_FLAG_SYNC))
+		bm.bmv_iflags |= BMV_IF_DELALLOC;
+
+	error = xfs_getbmap(ip, &bm, xfs_fiemap_format, fieinfo);
+	if (error)
+		return -error;
+
+	return 0;
+}
+
 static const struct inode_operations xfs_inode_operations = {
 	.permission		= xfs_vn_permission,
 	.truncate		= xfs_vn_truncate,
@@ -671,6 +747,7 @@ static const struct inode_operations xfs_inode_operations = {
 	.removexattr		= generic_removexattr,
 	.listxattr		= xfs_vn_listxattr,
 	.fallocate		= xfs_vn_fallocate,
+	.fiemap			= xfs_vn_fiemap,
 };
 
 static const struct inode_operations xfs_dir_inode_operations = {
@@ -766,12 +843,20 @@ xfs_diflags_to_iflags(
  * When reading existing inodes from disk this is called directly
  * from xfs_iget, when creating a new inode it is called from
  * xfs_ialloc after setting up the inode.
+ *
+ * We are always called with an uninitialised linux inode here.
+ * We need to initialise the necessary fields and take a reference
+ * on it.
  */
 void
 xfs_setup_inode(
 	struct xfs_inode	*ip)
 {
-	struct inode		*inode = ip->i_vnode;
+	struct inode		*inode = &ip->i_vnode;
+
+	inode->i_ino = ip->i_ino;
+	inode->i_state = I_NEW|I_LOCK;
+	inode_add_to_lists(ip->i_mount->m_super, inode);
 
 	inode->i_mode	= ip->i_d.di_mode;
 	inode->i_nlink	= ip->i_d.di_nlink;
@@ -799,7 +884,6 @@ xfs_setup_inode(
 	inode->i_ctime.tv_sec	= ip->i_d.di_ctime.t_sec;
 	inode->i_ctime.tv_nsec	= ip->i_d.di_ctime.t_nsec;
 	xfs_diflags_to_iflags(inode, ip);
-	xfs_iflags_clear(ip, XFS_IMODIFIED);
 
 	switch (inode->i_mode & S_IFMT) {
 	case S_IFREG:
diff --git a/fs/xfs/linux-2.6/xfs_linux.h b/fs/xfs/linux-2.6/xfs_linux.h
index cc0f7b3a9795..507492d6dccd 100644
--- a/fs/xfs/linux-2.6/xfs_linux.h
+++ b/fs/xfs/linux-2.6/xfs_linux.h
@@ -21,18 +21,12 @@
 #include <linux/types.h>
 
 /*
- * Some types are conditional depending on the target system.
  * XFS_BIG_BLKNOS needs block layer disk addresses to be 64 bits.
- * XFS_BIG_INUMS needs the VFS inode number to be 64 bits, as well
- * as requiring XFS_BIG_BLKNOS to be set.
+ * XFS_BIG_INUMS requires XFS_BIG_BLKNOS to be set.
  */
 #if defined(CONFIG_LBD) || (BITS_PER_LONG == 64)
 # define XFS_BIG_BLKNOS	1
-# if BITS_PER_LONG == 64
-#  define XFS_BIG_INUMS	1
-# else
-#  define XFS_BIG_INUMS	0
-# endif
+# define XFS_BIG_INUMS	1
 #else
 # define XFS_BIG_BLKNOS	0
 # define XFS_BIG_INUMS	0
@@ -77,6 +71,7 @@
 #include <linux/spinlock.h>
 #include <linux/random.h>
 #include <linux/ctype.h>
+#include <linux/writeback.h>
 
 #include <asm/page.h>
 #include <asm/div64.h>
@@ -85,7 +80,6 @@
 #include <asm/byteorder.h>
 #include <asm/unaligned.h>
 
-#include <xfs_vfs.h>
 #include <xfs_cred.h>
 #include <xfs_vnode.h>
 #include <xfs_stats.h>
@@ -107,7 +101,6 @@
 #undef  HAVE_PERCPU_SB	/* per cpu superblock counters are a 2.6 feature */
 #endif
 
-#define restricted_chown	xfs_params.restrict_chown.val
 #define irix_sgid_inherit	xfs_params.sgid_inherit.val
 #define irix_symlink_mode	xfs_params.symlink_mode.val
 #define xfs_panic_mask		xfs_params.panic_mask.val
diff --git a/fs/xfs/linux-2.6/xfs_lrw.c b/fs/xfs/linux-2.6/xfs_lrw.c
index 1957e5357d04..59b7d5f9e64a 100644
--- a/fs/xfs/linux-2.6/xfs_lrw.c
+++ b/fs/xfs/linux-2.6/xfs_lrw.c
@@ -51,7 +51,6 @@
 #include "xfs_vnodeops.h"
 
 #include <linux/capability.h>
-#include <linux/mount.h>
 #include <linux/writeback.h>
 
 
@@ -243,7 +242,7 @@ xfs_read(
 
 	if (unlikely(ioflags & IO_ISDIRECT)) {
 		if (inode->i_mapping->nrpages)
-			ret = xfs_flushinval_pages(ip, (*offset & PAGE_CACHE_MASK),
+			ret = -xfs_flushinval_pages(ip, (*offset & PAGE_CACHE_MASK),
 						    -1, FI_REMAPF_LOCKED);
 		mutex_unlock(&inode->i_mutex);
 		if (ret) {
@@ -668,15 +667,8 @@ start:
 	if (new_size > xip->i_size)
 		xip->i_new_size = new_size;
 
-	/*
-	 * We're not supposed to change timestamps in readonly-mounted
-	 * filesystems.  Throw it away if anyone asks us.
-	 */
-	if (likely(!(ioflags & IO_INVIS) &&
-		   !mnt_want_write(file->f_path.mnt))) {
+	if (likely(!(ioflags & IO_INVIS)))
 		xfs_ichgtime(xip, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
-		mnt_drop_write(file->f_path.mnt);
-	}
 
 	/*
 	 * If the offset is beyond the size of the file, we have a couple
diff --git a/fs/xfs/linux-2.6/xfs_stats.c b/fs/xfs/linux-2.6/xfs_stats.c
index 3d5b67c075c7..c3526d445f6a 100644
--- a/fs/xfs/linux-2.6/xfs_stats.c
+++ b/fs/xfs/linux-2.6/xfs_stats.c
@@ -53,11 +53,15 @@ xfs_read_xfsstats(
 		{ "icluster",		XFSSTAT_END_INODE_CLUSTER	},
 		{ "vnodes",		XFSSTAT_END_VNODE_OPS		},
 		{ "buf",		XFSSTAT_END_BUF			},
+		{ "abtb2",		XFSSTAT_END_ABTB_V2		},
+		{ "abtc2",		XFSSTAT_END_ABTC_V2		},
+		{ "bmbt2",		XFSSTAT_END_BMBT_V2		},
+		{ "ibt2",		XFSSTAT_END_IBT_V2		},
 	};
 
 	/* Loop over all stats groups */
 	for (i=j=len = 0; i < ARRAY_SIZE(xstats); i++) {
-		len += sprintf(buffer + len, xstats[i].desc);
+		len += sprintf(buffer + len, "%s", xstats[i].desc);
 		/* inner loop does each group */
 		while (j < xstats[i].endpoint) {
 			val = 0;
diff --git a/fs/xfs/linux-2.6/xfs_stats.h b/fs/xfs/linux-2.6/xfs_stats.h
index e83820febc9f..736854b1ca1a 100644
--- a/fs/xfs/linux-2.6/xfs_stats.h
+++ b/fs/xfs/linux-2.6/xfs_stats.h
@@ -118,6 +118,71 @@ struct xfsstats {
 	__uint32_t		xb_page_retries;
 	__uint32_t		xb_page_found;
 	__uint32_t		xb_get_read;
+/* Version 2 btree counters */
+#define XFSSTAT_END_ABTB_V2		(XFSSTAT_END_BUF+15)
+	__uint32_t		xs_abtb_2_lookup;
+	__uint32_t		xs_abtb_2_compare;
+	__uint32_t		xs_abtb_2_insrec;
+	__uint32_t		xs_abtb_2_delrec;
+	__uint32_t		xs_abtb_2_newroot;
+	__uint32_t		xs_abtb_2_killroot;
+	__uint32_t		xs_abtb_2_increment;
+	__uint32_t		xs_abtb_2_decrement;
+	__uint32_t		xs_abtb_2_lshift;
+	__uint32_t		xs_abtb_2_rshift;
+	__uint32_t		xs_abtb_2_split;
+	__uint32_t		xs_abtb_2_join;
+	__uint32_t		xs_abtb_2_alloc;
+	__uint32_t		xs_abtb_2_free;
+	__uint32_t		xs_abtb_2_moves;
+#define XFSSTAT_END_ABTC_V2		(XFSSTAT_END_ABTB_V2+15)
+	__uint32_t		xs_abtc_2_lookup;
+	__uint32_t		xs_abtc_2_compare;
+	__uint32_t		xs_abtc_2_insrec;
+	__uint32_t		xs_abtc_2_delrec;
+	__uint32_t		xs_abtc_2_newroot;
+	__uint32_t		xs_abtc_2_killroot;
+	__uint32_t		xs_abtc_2_increment;
+	__uint32_t		xs_abtc_2_decrement;
+	__uint32_t		xs_abtc_2_lshift;
+	__uint32_t		xs_abtc_2_rshift;
+	__uint32_t		xs_abtc_2_split;
+	__uint32_t		xs_abtc_2_join;
+	__uint32_t		xs_abtc_2_alloc;
+	__uint32_t		xs_abtc_2_free;
+	__uint32_t		xs_abtc_2_moves;
+#define XFSSTAT_END_BMBT_V2		(XFSSTAT_END_ABTC_V2+15)
+	__uint32_t		xs_bmbt_2_lookup;
+	__uint32_t		xs_bmbt_2_compare;
+	__uint32_t		xs_bmbt_2_insrec;
+	__uint32_t		xs_bmbt_2_delrec;
+	__uint32_t		xs_bmbt_2_newroot;
+	__uint32_t		xs_bmbt_2_killroot;
+	__uint32_t		xs_bmbt_2_increment;
+	__uint32_t		xs_bmbt_2_decrement;
+	__uint32_t		xs_bmbt_2_lshift;
+	__uint32_t		xs_bmbt_2_rshift;
+	__uint32_t		xs_bmbt_2_split;
+	__uint32_t		xs_bmbt_2_join;
+	__uint32_t		xs_bmbt_2_alloc;
+	__uint32_t		xs_bmbt_2_free;
+	__uint32_t		xs_bmbt_2_moves;
+#define XFSSTAT_END_IBT_V2		(XFSSTAT_END_BMBT_V2+15)
+	__uint32_t		xs_ibt_2_lookup;
+	__uint32_t		xs_ibt_2_compare;
+	__uint32_t		xs_ibt_2_insrec;
+	__uint32_t		xs_ibt_2_delrec;
+	__uint32_t		xs_ibt_2_newroot;
+	__uint32_t		xs_ibt_2_killroot;
+	__uint32_t		xs_ibt_2_increment;
+	__uint32_t		xs_ibt_2_decrement;
+	__uint32_t		xs_ibt_2_lshift;
+	__uint32_t		xs_ibt_2_rshift;
+	__uint32_t		xs_ibt_2_split;
+	__uint32_t		xs_ibt_2_join;
+	__uint32_t		xs_ibt_2_alloc;
+	__uint32_t		xs_ibt_2_free;
+	__uint32_t		xs_ibt_2_moves;
 /* Extra precision counters */
 	__uint64_t		xs_xstrat_bytes;
 	__uint64_t		xs_write_bytes;
diff --git a/fs/xfs/linux-2.6/xfs_super.c b/fs/xfs/linux-2.6/xfs_super.c
index 37ebe36056eb..36f6cc703ef2 100644
--- a/fs/xfs/linux-2.6/xfs_super.c
+++ b/fs/xfs/linux-2.6/xfs_super.c
@@ -18,7 +18,6 @@
 #include "xfs.h"
 #include "xfs_bit.h"
 #include "xfs_log.h"
-#include "xfs_clnt.h"
 #include "xfs_inum.h"
 #include "xfs_trans.h"
 #include "xfs_sb.h"
@@ -36,6 +35,7 @@
 #include "xfs_dinode.h"
 #include "xfs_inode.h"
 #include "xfs_btree.h"
+#include "xfs_btree_trace.h"
 #include "xfs_ialloc.h"
 #include "xfs_bmap.h"
 #include "xfs_rtalloc.h"
@@ -48,7 +48,6 @@
 #include "xfs_buf_item.h"
 #include "xfs_utils.h"
 #include "xfs_vnodeops.h"
-#include "xfs_vfsops.h"
 #include "xfs_version.h"
 #include "xfs_log_priv.h"
 #include "xfs_trans_priv.h"
@@ -58,6 +57,7 @@
 #include "xfs_extfree_item.h"
 #include "xfs_mru_cache.h"
 #include "xfs_inode_item.h"
+#include "xfs_sync.h"
 
 #include <linux/namei.h>
 #include <linux/init.h>
@@ -70,36 +70,9 @@
 
 static struct quotactl_ops xfs_quotactl_operations;
 static struct super_operations xfs_super_operations;
-static kmem_zone_t *xfs_vnode_zone;
 static kmem_zone_t *xfs_ioend_zone;
 mempool_t *xfs_ioend_pool;
 
-STATIC struct xfs_mount_args *
-xfs_args_allocate(
-	struct super_block	*sb,
-	int			silent)
-{
-	struct xfs_mount_args	*args;
-
-	args = kzalloc(sizeof(struct xfs_mount_args), GFP_KERNEL);
-	if (!args)
-		return NULL;
-
-	args->logbufs = args->logbufsize = -1;
-	strncpy(args->fsname, sb->s_id, MAXNAMELEN);
-
-	/* Copy the already-parsed mount(2) flags we're interested in */
-	if (sb->s_flags & MS_DIRSYNC)
-		args->flags |= XFSMNT_DIRSYNC;
-	if (sb->s_flags & MS_SYNCHRONOUS)
-		args->flags |= XFSMNT_WSYNC;
-	if (silent)
-		args->flags |= XFSMNT_QUIET;
-	args->flags |= XFSMNT_32BITINODES;
-
-	return args;
-}
-
 #define MNTOPT_LOGBUFS	"logbufs"	/* number of XFS log buffers */
 #define MNTOPT_LOGBSIZE	"logbsize"	/* size of XFS log buffers */
 #define MNTOPT_LOGDEV	"logdev"	/* log device */
@@ -188,26 +161,54 @@ suffix_strtoul(char *s, char **endp, unsigned int base)
 	return simple_strtoul((const char *)s, endp, base) << shift_left_factor;
 }
 
+/*
+ * This function fills in xfs_mount_t fields based on mount args.
+ * Note: the superblock has _not_ yet been read in.
+ *
+ * Note that this function leaks the various device name allocations on
+ * failure.  The caller takes care of them.
+ */
 STATIC int
 xfs_parseargs(
 	struct xfs_mount	*mp,
 	char			*options,
-	struct xfs_mount_args	*args,
-	int			update)
+	char			**mtpt)
 {
+	struct super_block	*sb = mp->m_super;
 	char			*this_char, *value, *eov;
-	int			dsunit, dswidth, vol_dsunit, vol_dswidth;
-	int			iosize;
+	int			dsunit = 0;
+	int			dswidth = 0;
+	int			iosize = 0;
 	int			dmapi_implies_ikeep = 1;
+	uchar_t			iosizelog = 0;
+
+	/*
+	 * Copy binary VFS mount flags we are interested in.
+	 */
+	if (sb->s_flags & MS_RDONLY)
+		mp->m_flags |= XFS_MOUNT_RDONLY;
+	if (sb->s_flags & MS_DIRSYNC)
+		mp->m_flags |= XFS_MOUNT_DIRSYNC;
+	if (sb->s_flags & MS_SYNCHRONOUS)
+		mp->m_flags |= XFS_MOUNT_WSYNC;
+
+	/*
+	 * Set some default flags that could be cleared by the mount option
+	 * parsing.
+	 */
+	mp->m_flags |= XFS_MOUNT_BARRIER;
+	mp->m_flags |= XFS_MOUNT_COMPAT_IOSIZE;
+	mp->m_flags |= XFS_MOUNT_SMALL_INUMS;
 
-	args->flags |= XFSMNT_BARRIER;
-	args->flags2 |= XFSMNT2_COMPAT_IOSIZE;
+	/*
+	 * These can be overridden by the mount option parsing.
+	 */
+	mp->m_logbufs = -1;
+	mp->m_logbsize = -1;
 
 	if (!options)
 		goto done;
 
-	iosize = dsunit = dswidth = vol_dsunit = vol_dswidth = 0;
-
 	while ((this_char = strsep(&options, ",")) != NULL) {
 		if (!*this_char)
 			continue;
@@ -221,7 +222,7 @@ xfs_parseargs(
 					this_char);
 				return EINVAL;
 			}
-			args->logbufs = simple_strtoul(value, &eov, 10);
+			mp->m_logbufs = simple_strtoul(value, &eov, 10);
 		} else if (!strcmp(this_char, MNTOPT_LOGBSIZE)) {
 			if (!value || !*value) {
 				cmn_err(CE_WARN,
@@ -229,7 +230,7 @@ xfs_parseargs(
 					this_char);
 				return EINVAL;
 			}
-			args->logbufsize = suffix_strtoul(value, &eov, 10);
+			mp->m_logbsize = suffix_strtoul(value, &eov, 10);
 		} else if (!strcmp(this_char, MNTOPT_LOGDEV)) {
 			if (!value || !*value) {
 				cmn_err(CE_WARN,
@@ -237,7 +238,9 @@ xfs_parseargs(
 					this_char);
 				return EINVAL;
 			}
-			strncpy(args->logname, value, MAXNAMELEN);
+			mp->m_logname = kstrndup(value, MAXNAMELEN, GFP_KERNEL);
+			if (!mp->m_logname)
+				return ENOMEM;
 		} else if (!strcmp(this_char, MNTOPT_MTPT)) {
 			if (!value || !*value) {
 				cmn_err(CE_WARN,
@@ -245,7 +248,9 @@ xfs_parseargs(
 					this_char);
 				return EINVAL;
 			}
-			strncpy(args->mtpt, value, MAXNAMELEN);
+			*mtpt = kstrndup(value, MAXNAMELEN, GFP_KERNEL);
+			if (!*mtpt)
+				return ENOMEM;
 		} else if (!strcmp(this_char, MNTOPT_RTDEV)) {
 			if (!value || !*value) {
 				cmn_err(CE_WARN,
@@ -253,7 +258,9 @@ xfs_parseargs(
 					this_char);
 				return EINVAL;
 			}
-			strncpy(args->rtname, value, MAXNAMELEN);
+			mp->m_rtname = kstrndup(value, MAXNAMELEN, GFP_KERNEL);
+			if (!mp->m_rtname)
+				return ENOMEM;
 		} else if (!strcmp(this_char, MNTOPT_BIOSIZE)) {
 			if (!value || !*value) {
 				cmn_err(CE_WARN,
@@ -262,8 +269,7 @@ xfs_parseargs(
 				return EINVAL;
 			}
 			iosize = simple_strtoul(value, &eov, 10);
-			args->flags |= XFSMNT_IOSIZE;
-			args->iosizelog = (uint8_t) iosize;
+			iosizelog = ffs(iosize) - 1;
 		} else if (!strcmp(this_char, MNTOPT_ALLOCSIZE)) {
 			if (!value || !*value) {
 				cmn_err(CE_WARN,
@@ -272,8 +278,7 @@ xfs_parseargs(
 				return EINVAL;
 			}
 			iosize = suffix_strtoul(value, &eov, 10);
-			args->flags |= XFSMNT_IOSIZE;
-			args->iosizelog = ffs(iosize) - 1;
+			iosizelog = ffs(iosize) - 1;
 		} else if (!strcmp(this_char, MNTOPT_GRPID) ||
 			   !strcmp(this_char, MNTOPT_BSDGROUPS)) {
 			mp->m_flags |= XFS_MOUNT_GRPID;
@@ -281,23 +286,25 @@ xfs_parseargs(
 			   !strcmp(this_char, MNTOPT_SYSVGROUPS)) {
 			mp->m_flags &= ~XFS_MOUNT_GRPID;
 		} else if (!strcmp(this_char, MNTOPT_WSYNC)) {
-			args->flags |= XFSMNT_WSYNC;
+			mp->m_flags |= XFS_MOUNT_WSYNC;
 		} else if (!strcmp(this_char, MNTOPT_OSYNCISOSYNC)) {
-			args->flags |= XFSMNT_OSYNCISOSYNC;
+			mp->m_flags |= XFS_MOUNT_OSYNCISOSYNC;
 		} else if (!strcmp(this_char, MNTOPT_NORECOVERY)) {
-			args->flags |= XFSMNT_NORECOVERY;
+			mp->m_flags |= XFS_MOUNT_NORECOVERY;
 		} else if (!strcmp(this_char, MNTOPT_INO64)) {
-			args->flags |= XFSMNT_INO64;
-#if !XFS_BIG_INUMS
+#if XFS_BIG_INUMS
+			mp->m_flags |= XFS_MOUNT_INO64;
+			mp->m_inoadd = XFS_INO64_OFFSET;
+#else
 			cmn_err(CE_WARN,
 				"XFS: %s option not allowed on this system",
 				this_char);
 			return EINVAL;
 #endif
 		} else if (!strcmp(this_char, MNTOPT_NOALIGN)) {
-			args->flags |= XFSMNT_NOALIGN;
+			mp->m_flags |= XFS_MOUNT_NOALIGN;
 		} else if (!strcmp(this_char, MNTOPT_SWALLOC)) {
-			args->flags |= XFSMNT_SWALLOC;
+			mp->m_flags |= XFS_MOUNT_SWALLOC;
 		} else if (!strcmp(this_char, MNTOPT_SUNIT)) {
 			if (!value || !*value) {
 				cmn_err(CE_WARN,
@@ -315,7 +322,7 @@ xfs_parseargs(
 			}
 			dswidth = simple_strtoul(value, &eov, 10);
 		} else if (!strcmp(this_char, MNTOPT_64BITINODE)) {
-			args->flags &= ~XFSMNT_32BITINODES;
+			mp->m_flags &= ~XFS_MOUNT_SMALL_INUMS;
 #if !XFS_BIG_INUMS
 			cmn_err(CE_WARN,
 				"XFS: %s option not allowed on this system",
@@ -323,56 +330,61 @@ xfs_parseargs(
 			return EINVAL;
 #endif
 		} else if (!strcmp(this_char, MNTOPT_NOUUID)) {
-			args->flags |= XFSMNT_NOUUID;
+			mp->m_flags |= XFS_MOUNT_NOUUID;
 		} else if (!strcmp(this_char, MNTOPT_BARRIER)) {
-			args->flags |= XFSMNT_BARRIER;
+			mp->m_flags |= XFS_MOUNT_BARRIER;
 		} else if (!strcmp(this_char, MNTOPT_NOBARRIER)) {
-			args->flags &= ~XFSMNT_BARRIER;
+			mp->m_flags &= ~XFS_MOUNT_BARRIER;
 		} else if (!strcmp(this_char, MNTOPT_IKEEP)) {
-			args->flags |= XFSMNT_IKEEP;
+			mp->m_flags |= XFS_MOUNT_IKEEP;
 		} else if (!strcmp(this_char, MNTOPT_NOIKEEP)) {
 			dmapi_implies_ikeep = 0;
-			args->flags &= ~XFSMNT_IKEEP;
+			mp->m_flags &= ~XFS_MOUNT_IKEEP;
 		} else if (!strcmp(this_char, MNTOPT_LARGEIO)) {
-			args->flags2 &= ~XFSMNT2_COMPAT_IOSIZE;
+			mp->m_flags &= ~XFS_MOUNT_COMPAT_IOSIZE;
 		} else if (!strcmp(this_char, MNTOPT_NOLARGEIO)) {
-			args->flags2 |= XFSMNT2_COMPAT_IOSIZE;
+			mp->m_flags |= XFS_MOUNT_COMPAT_IOSIZE;
 		} else if (!strcmp(this_char, MNTOPT_ATTR2)) {
-			args->flags |= XFSMNT_ATTR2;
+			mp->m_flags |= XFS_MOUNT_ATTR2;
 		} else if (!strcmp(this_char, MNTOPT_NOATTR2)) {
-			args->flags &= ~XFSMNT_ATTR2;
-			args->flags |= XFSMNT_NOATTR2;
+			mp->m_flags &= ~XFS_MOUNT_ATTR2;
+			mp->m_flags |= XFS_MOUNT_NOATTR2;
 		} else if (!strcmp(this_char, MNTOPT_FILESTREAM)) {
-			args->flags2 |= XFSMNT2_FILESTREAMS;
+			mp->m_flags |= XFS_MOUNT_FILESTREAMS;
 		} else if (!strcmp(this_char, MNTOPT_NOQUOTA)) {
-			args->flags &= ~(XFSMNT_UQUOTAENF|XFSMNT_UQUOTA);
-			args->flags &= ~(XFSMNT_GQUOTAENF|XFSMNT_GQUOTA);
+			mp->m_qflags &= ~(XFS_UQUOTA_ACCT | XFS_UQUOTA_ACTIVE |
+					  XFS_GQUOTA_ACCT | XFS_GQUOTA_ACTIVE |
+					  XFS_PQUOTA_ACCT | XFS_PQUOTA_ACTIVE |
+					  XFS_UQUOTA_ENFD | XFS_OQUOTA_ENFD);
 		} else if (!strcmp(this_char, MNTOPT_QUOTA) ||
 			   !strcmp(this_char, MNTOPT_UQUOTA) ||
 			   !strcmp(this_char, MNTOPT_USRQUOTA)) {
-			args->flags |= XFSMNT_UQUOTA | XFSMNT_UQUOTAENF;
+			mp->m_qflags |= (XFS_UQUOTA_ACCT | XFS_UQUOTA_ACTIVE |
+					 XFS_UQUOTA_ENFD);
 		} else if (!strcmp(this_char, MNTOPT_QUOTANOENF) ||
 			   !strcmp(this_char, MNTOPT_UQUOTANOENF)) {
-			args->flags |= XFSMNT_UQUOTA;
-			args->flags &= ~XFSMNT_UQUOTAENF;
+			mp->m_qflags |= (XFS_UQUOTA_ACCT | XFS_UQUOTA_ACTIVE);
+			mp->m_qflags &= ~XFS_UQUOTA_ENFD;
 		} else if (!strcmp(this_char, MNTOPT_PQUOTA) ||
 			   !strcmp(this_char, MNTOPT_PRJQUOTA)) {
-			args->flags |= XFSMNT_PQUOTA | XFSMNT_PQUOTAENF;
+			mp->m_qflags |= (XFS_PQUOTA_ACCT | XFS_PQUOTA_ACTIVE |
+					 XFS_OQUOTA_ENFD);
 		} else if (!strcmp(this_char, MNTOPT_PQUOTANOENF)) {
-			args->flags |= XFSMNT_PQUOTA;
-			args->flags &= ~XFSMNT_PQUOTAENF;
+			mp->m_qflags |= (XFS_PQUOTA_ACCT | XFS_PQUOTA_ACTIVE);
+			mp->m_qflags &= ~XFS_OQUOTA_ENFD;
 		} else if (!strcmp(this_char, MNTOPT_GQUOTA) ||
 			   !strcmp(this_char, MNTOPT_GRPQUOTA)) {
-			args->flags |= XFSMNT_GQUOTA | XFSMNT_GQUOTAENF;
+			mp->m_qflags |= (XFS_GQUOTA_ACCT | XFS_GQUOTA_ACTIVE |
+					 XFS_OQUOTA_ENFD);
 		} else if (!strcmp(this_char, MNTOPT_GQUOTANOENF)) {
-			args->flags |= XFSMNT_GQUOTA;
-			args->flags &= ~XFSMNT_GQUOTAENF;
+			mp->m_qflags |= (XFS_GQUOTA_ACCT | XFS_GQUOTA_ACTIVE);
+			mp->m_qflags &= ~XFS_OQUOTA_ENFD;
 		} else if (!strcmp(this_char, MNTOPT_DMAPI)) {
-			args->flags |= XFSMNT_DMAPI;
+			mp->m_flags |= XFS_MOUNT_DMAPI;
 		} else if (!strcmp(this_char, MNTOPT_XDSM)) {
-			args->flags |= XFSMNT_DMAPI;
+			mp->m_flags |= XFS_MOUNT_DMAPI;
 		} else if (!strcmp(this_char, MNTOPT_DMI)) {
-			args->flags |= XFSMNT_DMAPI;
+			mp->m_flags |= XFS_MOUNT_DMAPI;
 		} else if (!strcmp(this_char, "ihashsize")) {
 			cmn_err(CE_WARN,
 	"XFS: ihashsize no longer used, option is deprecated.");
@@ -390,27 +402,29 @@ xfs_parseargs(
 		}
 	}
 
-	if (args->flags & XFSMNT_NORECOVERY) {
-		if ((mp->m_flags & XFS_MOUNT_RDONLY) == 0) {
-			cmn_err(CE_WARN,
-				"XFS: no-recovery mounts must be read-only.");
-			return EINVAL;
-		}
+	/*
+	 * no recovery flag requires a read-only mount
+	 */
+	if ((mp->m_flags & XFS_MOUNT_NORECOVERY) &&
+	    !(mp->m_flags & XFS_MOUNT_RDONLY)) {
+		cmn_err(CE_WARN, "XFS: no-recovery mounts must be read-only.");
+		return EINVAL;
 	}
 
-	if ((args->flags & XFSMNT_NOALIGN) && (dsunit || dswidth)) {
+	if ((mp->m_flags & XFS_MOUNT_NOALIGN) && (dsunit || dswidth)) {
 		cmn_err(CE_WARN,
 	"XFS: sunit and swidth options incompatible with the noalign option");
 		return EINVAL;
 	}
 
-	if ((args->flags & XFSMNT_GQUOTA) && (args->flags & XFSMNT_PQUOTA)) {
+	if ((mp->m_qflags & (XFS_GQUOTA_ACCT | XFS_GQUOTA_ACTIVE)) &&
+	    (mp->m_qflags & (XFS_PQUOTA_ACCT | XFS_PQUOTA_ACTIVE))) {
 		cmn_err(CE_WARN,
 			"XFS: cannot mount with both project and group quota");
 		return EINVAL;
 	}
 
-	if ((args->flags & XFSMNT_DMAPI) && *args->mtpt == '\0') {
+	if ((mp->m_flags & XFS_MOUNT_DMAPI) && (!*mtpt || *mtpt[0] == '\0')) {
 		printk("XFS: %s option needs the mount point option as well\n",
 			MNTOPT_DMAPI);
 		return EINVAL;
@@ -438,27 +452,66 @@ xfs_parseargs(
 	 * Note that if "ikeep" or "noikeep" mount options are
 	 * supplied, then they are honored.
 	 */
-	if ((args->flags & XFSMNT_DMAPI) && dmapi_implies_ikeep)
-		args->flags |= XFSMNT_IKEEP;
+	if ((mp->m_flags & XFS_MOUNT_DMAPI) && dmapi_implies_ikeep)
+		mp->m_flags |= XFS_MOUNT_IKEEP;
 
-	if ((args->flags & XFSMNT_NOALIGN) != XFSMNT_NOALIGN) {
+done:
+	if (!(mp->m_flags & XFS_MOUNT_NOALIGN)) {
+		/*
+		 * At this point the superblock has not been read
+		 * in, therefore we do not know the block size.
+		 * Before the mount call ends we will convert
+		 * these to FSBs.
+		 */
 		if (dsunit) {
-			args->sunit = dsunit;
-			args->flags |= XFSMNT_RETERR;
-		} else {
-			args->sunit = vol_dsunit;
+			mp->m_dalign = dsunit;
+			mp->m_flags |= XFS_MOUNT_RETERR;
 		}
-		dswidth ? (args->swidth = dswidth) :
-			  (args->swidth = vol_dswidth);
-	} else {
-		args->sunit = args->swidth = 0;
+
+		if (dswidth)
+			mp->m_swidth = dswidth;
+	}
+
+	if (mp->m_logbufs != -1 &&
+	    mp->m_logbufs != 0 &&
+	    (mp->m_logbufs < XLOG_MIN_ICLOGS ||
+	     mp->m_logbufs > XLOG_MAX_ICLOGS)) {
+		cmn_err(CE_WARN,
+			"XFS: invalid logbufs value: %d [not %d-%d]",
+			mp->m_logbufs, XLOG_MIN_ICLOGS, XLOG_MAX_ICLOGS);
+		return XFS_ERROR(EINVAL);
+	}
+	if (mp->m_logbsize != -1 &&
+	    mp->m_logbsize !=  0 &&
+	    (mp->m_logbsize < XLOG_MIN_RECORD_BSIZE ||
+	     mp->m_logbsize > XLOG_MAX_RECORD_BSIZE ||
+	     !is_power_of_2(mp->m_logbsize))) {
+		cmn_err(CE_WARN,
+	"XFS: invalid logbufsize: %d [not 16k,32k,64k,128k or 256k]",
+			mp->m_logbsize);
+		return XFS_ERROR(EINVAL);
+	}
+
+	mp->m_fsname = kstrndup(sb->s_id, MAXNAMELEN, GFP_KERNEL);
+	if (!mp->m_fsname)
+		return ENOMEM;
+	mp->m_fsname_len = strlen(mp->m_fsname) + 1;
+
+	if (iosizelog) {
+		if (iosizelog > XFS_MAX_IO_LOG ||
+		    iosizelog < XFS_MIN_IO_LOG) {
+			cmn_err(CE_WARN,
+		"XFS: invalid log iosize: %d [not %d-%d]",
+				iosizelog, XFS_MIN_IO_LOG,
+				XFS_MAX_IO_LOG);
+			return XFS_ERROR(EINVAL);
+		}
+
+		mp->m_flags |= XFS_MOUNT_DFLT_IOSIZE;
+		mp->m_readio_log = iosizelog;
+		mp->m_writeio_log = iosizelog;
 	}
 
-done:
-	if (args->flags & XFSMNT_32BITINODES)
-		mp->m_flags |= XFS_MOUNT_SMALL_INUMS;
-	if (args->flags2)
-		args->flags |= XFSMNT_FLAGS2;
 	return 0;
 }
 
@@ -704,8 +757,7 @@ xfs_close_devices(
  */
 STATIC int
 xfs_open_devices(
-	struct xfs_mount	*mp,
-	struct xfs_mount_args	*args)
+	struct xfs_mount	*mp)
 {
 	struct block_device	*ddev = mp->m_super->s_bdev;
 	struct block_device	*logdev = NULL, *rtdev = NULL;
@@ -714,14 +766,14 @@ xfs_open_devices(
 	/*
 	 * Open real time and log devices - order is important.
 	 */
-	if (args->logname[0]) {
-		error = xfs_blkdev_get(mp, args->logname, &logdev);
+	if (mp->m_logname) {
+		error = xfs_blkdev_get(mp, mp->m_logname, &logdev);
 		if (error)
 			goto out;
 	}
 
-	if (args->rtname[0]) {
-		error = xfs_blkdev_get(mp, args->rtname, &rtdev);
+	if (mp->m_rtname) {
+		error = xfs_blkdev_get(mp, mp->m_rtname, &rtdev);
 		if (error)
 			goto out_close_logdev;
 
@@ -813,18 +865,18 @@ xfs_setup_devices(
  */
 void
 xfsaild_wakeup(
-	xfs_mount_t		*mp,
+	struct xfs_ail		*ailp,
 	xfs_lsn_t		threshold_lsn)
 {
-	mp->m_ail.xa_target = threshold_lsn;
-	wake_up_process(mp->m_ail.xa_task);
+	ailp->xa_target = threshold_lsn;
+	wake_up_process(ailp->xa_task);
 }
 
 int
 xfsaild(
 	void	*data)
 {
-	xfs_mount_t	*mp = (xfs_mount_t *)data;
+	struct xfs_ail	*ailp = data;
 	xfs_lsn_t	last_pushed_lsn = 0;
 	long		tout = 0;
 
@@ -836,11 +888,11 @@ xfsaild(
 		/* swsusp */
 		try_to_freeze();
 
-		ASSERT(mp->m_log);
-		if (XFS_FORCED_SHUTDOWN(mp))
+		ASSERT(ailp->xa_mount->m_log);
+		if (XFS_FORCED_SHUTDOWN(ailp->xa_mount))
 			continue;
 
-		tout = xfsaild_push(mp, &last_pushed_lsn);
+		tout = xfsaild_push(ailp, &last_pushed_lsn);
 	}
 
 	return 0;
@@ -848,43 +900,82 @@ xfsaild(
 
 int
 xfsaild_start(
-	xfs_mount_t	*mp)
+	struct xfs_ail	*ailp)
 {
-	mp->m_ail.xa_target = 0;
-	mp->m_ail.xa_task = kthread_run(xfsaild, mp, "xfsaild");
-	if (IS_ERR(mp->m_ail.xa_task))
-		return -PTR_ERR(mp->m_ail.xa_task);
+	ailp->xa_target = 0;
+	ailp->xa_task = kthread_run(xfsaild, ailp, "xfsaild");
+	if (IS_ERR(ailp->xa_task))
+		return -PTR_ERR(ailp->xa_task);
 	return 0;
 }
 
 void
 xfsaild_stop(
-	xfs_mount_t	*mp)
+	struct xfs_ail	*ailp)
 {
-	kthread_stop(mp->m_ail.xa_task);
+	kthread_stop(ailp->xa_task);
 }
 
 
-
+/* Catch misguided souls that try to use this interface on XFS */
 STATIC struct inode *
 xfs_fs_alloc_inode(
 	struct super_block	*sb)
 {
-	return kmem_zone_alloc(xfs_vnode_zone, KM_SLEEP);
+	BUG();
+	return NULL;
 }
 
+/*
+ * Now that the generic code is guaranteed not to be accessing
+ * the linux inode, we can reclaim the inode.
+ */
 STATIC void
 xfs_fs_destroy_inode(
-	struct inode		*inode)
+	struct inode	*inode)
 {
-	kmem_zone_free(xfs_vnode_zone, inode);
+	xfs_inode_t		*ip = XFS_I(inode);
+
+	XFS_STATS_INC(vn_reclaim);
+	if (xfs_reclaim(ip))
+		panic("%s: cannot reclaim 0x%p\n", __func__, inode);
 }
 
+/*
+ * Slab object creation initialisation for the XFS inode.
+ * This covers only the idempotent fields in the XFS inode;
+ * all other fields need to be initialised on allocation
+ * from the slab. This avoids the need to repeatedly intialise
+ * fields in the xfs inode that left in the initialise state
+ * when freeing the inode.
+ */
 STATIC void
 xfs_fs_inode_init_once(
-	void			*vnode)
+	void			*inode)
 {
-	inode_init_once((struct inode *)vnode);
+	struct xfs_inode	*ip = inode;
+
+	memset(ip, 0, sizeof(struct xfs_inode));
+
+	/* vfs inode */
+	inode_init_once(VFS_I(ip));
+
+	/* xfs inode */
+	atomic_set(&ip->i_iocount, 0);
+	atomic_set(&ip->i_pincount, 0);
+	spin_lock_init(&ip->i_flags_lock);
+	init_waitqueue_head(&ip->i_ipin_wait);
+	/*
+	 * Because we want to use a counting completion, complete
+	 * the flush completion once to allow a single access to
+	 * the flush completion without blocking.
+	 */
+	init_completion(&ip->i_flush);
+	complete(&ip->i_flush);
+
+	mrlock_init(&ip->i_lock, MRLOCK_ALLOW_EQUAL_PRI|MRLOCK_BARRIER,
+		     "xfsino", ip->i_ino);
+	mrlock_init(&ip->i_iolock, MRLOCK_BARRIER, "xfsio", ip->i_ino);
 }
 
 /*
@@ -898,21 +989,26 @@ xfs_fs_write_inode(
 	struct inode		*inode,
 	int			sync)
 {
+	struct xfs_inode	*ip = XFS_I(inode);
 	int			error = 0;
 	int			flags = 0;
 
-	xfs_itrace_entry(XFS_I(inode));
+	xfs_itrace_entry(ip);
 	if (sync) {
-		filemap_fdatawait(inode->i_mapping);
+		error = xfs_wait_on_pages(ip, 0, -1);
+		if (error)
+			goto out_error;
 		flags |= FLUSH_SYNC;
 	}
-	error = xfs_inode_flush(XFS_I(inode), flags);
+	error = xfs_inode_flush(ip, flags);
+
+out_error:
 	/*
 	 * if we failed to write out the inode then mark
 	 * it dirty again so we'll try again later.
 	 */
 	if (error)
-		mark_inode_dirty_sync(inode);
+		xfs_mark_inode_dirty_sync(ip);
 
 	return -error;
 }
@@ -923,164 +1019,12 @@ xfs_fs_clear_inode(
 {
 	xfs_inode_t		*ip = XFS_I(inode);
 
-	/*
-	 * ip can be null when xfs_iget_core calls xfs_idestroy if we
-	 * find an inode with di_mode == 0 but without IGET_CREATE set.
-	 */
-	if (ip) {
-		xfs_itrace_entry(ip);
-		XFS_STATS_INC(vn_rele);
-		XFS_STATS_INC(vn_remove);
-		XFS_STATS_INC(vn_reclaim);
-		XFS_STATS_DEC(vn_active);
-
-		xfs_inactive(ip);
-		xfs_iflags_clear(ip, XFS_IMODIFIED);
-		if (xfs_reclaim(ip))
-			panic("%s: cannot reclaim 0x%p\n", __func__, inode);
-	}
-
-	ASSERT(XFS_I(inode) == NULL);
-}
+	xfs_itrace_entry(ip);
+	XFS_STATS_INC(vn_rele);
+	XFS_STATS_INC(vn_remove);
+	XFS_STATS_DEC(vn_active);
 
-/*
- * Enqueue a work item to be picked up by the vfs xfssyncd thread.
- * Doing this has two advantages:
- * - It saves on stack space, which is tight in certain situations
- * - It can be used (with care) as a mechanism to avoid deadlocks.
- * Flushing while allocating in a full filesystem requires both.
- */
-STATIC void
-xfs_syncd_queue_work(
-	struct xfs_mount *mp,
-	void		*data,
-	void		(*syncer)(struct xfs_mount *, void *))
-{
-	struct bhv_vfs_sync_work *work;
-
-	work = kmem_alloc(sizeof(struct bhv_vfs_sync_work), KM_SLEEP);
-	INIT_LIST_HEAD(&work->w_list);
-	work->w_syncer = syncer;
-	work->w_data = data;
-	work->w_mount = mp;
-	spin_lock(&mp->m_sync_lock);
-	list_add_tail(&work->w_list, &mp->m_sync_list);
-	spin_unlock(&mp->m_sync_lock);
-	wake_up_process(mp->m_sync_task);
-}
-
-/*
- * Flush delayed allocate data, attempting to free up reserved space
- * from existing allocations.  At this point a new allocation attempt
- * has failed with ENOSPC and we are in the process of scratching our
- * heads, looking about for more room...
- */
-STATIC void
-xfs_flush_inode_work(
-	struct xfs_mount *mp,
-	void		*arg)
-{
-	struct inode	*inode = arg;
-	filemap_flush(inode->i_mapping);
-	iput(inode);
-}
-
-void
-xfs_flush_inode(
-	xfs_inode_t	*ip)
-{
-	struct inode	*inode = VFS_I(ip);
-
-	igrab(inode);
-	xfs_syncd_queue_work(ip->i_mount, inode, xfs_flush_inode_work);
-	delay(msecs_to_jiffies(500));
-}
-
-/*
- * This is the "bigger hammer" version of xfs_flush_inode_work...
- * (IOW, "If at first you don't succeed, use a Bigger Hammer").
- */
-STATIC void
-xfs_flush_device_work(
-	struct xfs_mount *mp,
-	void		*arg)
-{
-	struct inode	*inode = arg;
-	sync_blockdev(mp->m_super->s_bdev);
-	iput(inode);
-}
-
-void
-xfs_flush_device(
-	xfs_inode_t	*ip)
-{
-	struct inode	*inode = VFS_I(ip);
-
-	igrab(inode);
-	xfs_syncd_queue_work(ip->i_mount, inode, xfs_flush_device_work);
-	delay(msecs_to_jiffies(500));
-	xfs_log_force(ip->i_mount, (xfs_lsn_t)0, XFS_LOG_FORCE|XFS_LOG_SYNC);
-}
-
-STATIC void
-xfs_sync_worker(
-	struct xfs_mount *mp,
-	void		*unused)
-{
-	int		error;
-
-	if (!(mp->m_flags & XFS_MOUNT_RDONLY))
-		error = xfs_sync(mp, SYNC_FSDATA | SYNC_BDFLUSH | SYNC_ATTR);
-	mp->m_sync_seq++;
-	wake_up(&mp->m_wait_single_sync_task);
-}
-
-STATIC int
-xfssyncd(
-	void			*arg)
-{
-	struct xfs_mount	*mp = arg;
-	long			timeleft;
-	bhv_vfs_sync_work_t	*work, *n;
-	LIST_HEAD		(tmp);
-
-	set_freezable();
-	timeleft = xfs_syncd_centisecs * msecs_to_jiffies(10);
-	for (;;) {
-		timeleft = schedule_timeout_interruptible(timeleft);
-		/* swsusp */
-		try_to_freeze();
-		if (kthread_should_stop() && list_empty(&mp->m_sync_list))
-			break;
-
-		spin_lock(&mp->m_sync_lock);
-		/*
-		 * We can get woken by laptop mode, to do a sync -
-		 * that's the (only!) case where the list would be
-		 * empty with time remaining.
-		 */
-		if (!timeleft || list_empty(&mp->m_sync_list)) {
-			if (!timeleft)
-				timeleft = xfs_syncd_centisecs *
-							msecs_to_jiffies(10);
-			INIT_LIST_HEAD(&mp->m_sync_work.w_list);
-			list_add_tail(&mp->m_sync_work.w_list,
-					&mp->m_sync_list);
-		}
-		list_for_each_entry_safe(work, n, &mp->m_sync_list, w_list)
-			list_move(&work->w_list, &tmp);
-		spin_unlock(&mp->m_sync_lock);
-
-		list_for_each_entry_safe(work, n, &tmp, w_list) {
-			(*work->w_syncer)(mp, work->w_data);
-			list_del(&work->w_list);
-			if (work == &mp->m_sync_work)
-				continue;
-			kmem_free(work);
-		}
-	}
-
-	return 0;
+	xfs_inactive(ip);
 }
 
 STATIC void
@@ -1099,11 +1043,9 @@ xfs_fs_put_super(
 	struct xfs_mount	*mp = XFS_M(sb);
 	struct xfs_inode	*rip = mp->m_rootip;
 	int			unmount_event_flags = 0;
-	int			error;
 
-	kthread_stop(mp->m_sync_task);
-
-	xfs_sync(mp, SYNC_ATTR | SYNC_DELWRI);
+	xfs_syncd_stop(mp);
+	xfs_sync_inodes(mp, SYNC_ATTR|SYNC_DELWRI);
 
 #ifdef HAVE_DMAPI
 	if (mp->m_flags & XFS_MOUNT_DMAPI) {
@@ -1128,18 +1070,6 @@ xfs_fs_put_super(
 	xfs_filestream_unmount(mp);
 
 	XFS_bflush(mp->m_ddev_targp);
-	error = xfs_unmount_flush(mp, 0);
-	WARN_ON(error);
-
-	/*
-	 * If we're forcing a shutdown, typically because of a media error,
-	 * we want to make sure we invalidate dirty pages that belong to
-	 * referenced vnodes as well.
-	 */
-	if (XFS_FORCED_SHUTDOWN(mp)) {
-		error = xfs_sync(mp, SYNC_WAIT | SYNC_CLOSE);
-		ASSERT(error != EFSCORRUPTED);
-	}
 
 	if (mp->m_flags & XFS_MOUNT_DMAPI) {
 		XFS_SEND_UNMOUNT(mp, rip, DM_RIGHT_NULL, 0, 0,
@@ -1161,7 +1091,7 @@ xfs_fs_write_super(
 	struct super_block	*sb)
 {
 	if (!(sb->s_flags & MS_RDONLY))
-		xfs_sync(XFS_M(sb), SYNC_FSDATA);
+		xfs_sync_fsdata(XFS_M(sb), 0);
 	sb->s_dirt = 0;
 }
 
@@ -1172,7 +1102,6 @@ xfs_fs_sync_super(
 {
 	struct xfs_mount	*mp = XFS_M(sb);
 	int			error;
-	int			flags;
 
 	/*
 	 * Treat a sync operation like a freeze.  This is to work
@@ -1186,20 +1115,10 @@ xfs_fs_sync_super(
 	 * dirty the Linux inode until after the transaction I/O
 	 * completes.
 	 */
-	if (wait || unlikely(sb->s_frozen == SB_FREEZE_WRITE)) {
-		/*
-		 * First stage of freeze - no more writers will make progress
-		 * now we are here, so we flush delwri and delalloc buffers
-		 * here, then wait for all I/O to complete.  Data is frozen at
-		 * that point. Metadata is not frozen, transactions can still
-		 * occur here so don't bother flushing the buftarg (i.e
-		 * SYNC_QUIESCE) because it'll just get dirty again.
-		 */
-		flags = SYNC_DATA_QUIESCE;
-	} else
-		flags = SYNC_FSDATA;
-
-	error = xfs_sync(mp, flags);
+	if (wait || unlikely(sb->s_frozen == SB_FREEZE_WRITE))
+		error = xfs_quiesce_data(mp);
+	else
+		error = xfs_sync_fsdata(mp, 0);
 	sb->s_dirt = 0;
 
 	if (unlikely(laptop_mode)) {
@@ -1337,9 +1256,8 @@ xfs_fs_remount(
 
 	/* rw -> ro */
 	if (!(mp->m_flags & XFS_MOUNT_RDONLY) && (*flags & MS_RDONLY)) {
-		xfs_filestream_flush(mp);
-		xfs_sync(mp, SYNC_DATA_QUIESCE);
-		xfs_attr_quiesce(mp);
+		xfs_quiesce_data(mp);
+		xfs_quiesce_attr(mp);
 		mp->m_flags |= XFS_MOUNT_RDONLY;
 	}
 
@@ -1348,7 +1266,7 @@ xfs_fs_remount(
 
 /*
  * Second stage of a freeze. The data is already frozen so we only
- * need to take care of themetadata. Once that's done write a dummy
+ * need to take care of the metadata. Once that's done write a dummy
  * record to dirty the log in case of a crash while frozen.
  */
 STATIC void
@@ -1357,7 +1275,7 @@ xfs_fs_lockfs(
 {
 	struct xfs_mount	*mp = XFS_M(sb);
 
-	xfs_attr_quiesce(mp);
+	xfs_quiesce_attr(mp);
 	xfs_fs_log_dummy(mp);
 }
 
@@ -1422,175 +1340,28 @@ xfs_fs_setxquota(
 
 /*
  * This function fills in xfs_mount_t fields based on mount args.
- * Note: the superblock has _not_ yet been read in.
- */
-STATIC int
-xfs_start_flags(
-	struct xfs_mount_args	*ap,
-	struct xfs_mount	*mp)
-{
-	int			error;
-
-	/* Values are in BBs */
-	if ((ap->flags & XFSMNT_NOALIGN) != XFSMNT_NOALIGN) {
-		/*
-		 * At this point the superblock has not been read
-		 * in, therefore we do not know the block size.
-		 * Before the mount call ends we will convert
-		 * these to FSBs.
-		 */
-		mp->m_dalign = ap->sunit;
-		mp->m_swidth = ap->swidth;
-	}
-
-	if (ap->logbufs != -1 &&
-	    ap->logbufs != 0 &&
-	    (ap->logbufs < XLOG_MIN_ICLOGS ||
-	     ap->logbufs > XLOG_MAX_ICLOGS)) {
-		cmn_err(CE_WARN,
-			"XFS: invalid logbufs value: %d [not %d-%d]",
-			ap->logbufs, XLOG_MIN_ICLOGS, XLOG_MAX_ICLOGS);
-		return XFS_ERROR(EINVAL);
-	}
-	mp->m_logbufs = ap->logbufs;
-	if (ap->logbufsize != -1 &&
-	    ap->logbufsize !=  0 &&
-	    (ap->logbufsize < XLOG_MIN_RECORD_BSIZE ||
-	     ap->logbufsize > XLOG_MAX_RECORD_BSIZE ||
-	     !is_power_of_2(ap->logbufsize))) {
-		cmn_err(CE_WARN,
-	"XFS: invalid logbufsize: %d [not 16k,32k,64k,128k or 256k]",
-			ap->logbufsize);
-		return XFS_ERROR(EINVAL);
-	}
-
-	error = ENOMEM;
-
-	mp->m_logbsize = ap->logbufsize;
-	mp->m_fsname_len = strlen(ap->fsname) + 1;
-
-	mp->m_fsname = kstrdup(ap->fsname, GFP_KERNEL);
-	if (!mp->m_fsname)
-		goto out;
-
-	if (ap->rtname[0]) {
-		mp->m_rtname = kstrdup(ap->rtname, GFP_KERNEL);
-		if (!mp->m_rtname)
-			goto out_free_fsname;
-
-	}
-
-	if (ap->logname[0]) {
-		mp->m_logname = kstrdup(ap->logname, GFP_KERNEL);
-		if (!mp->m_logname)
-			goto out_free_rtname;
-	}
-
-	if (ap->flags & XFSMNT_WSYNC)
-		mp->m_flags |= XFS_MOUNT_WSYNC;
-#if XFS_BIG_INUMS
-	if (ap->flags & XFSMNT_INO64) {
-		mp->m_flags |= XFS_MOUNT_INO64;
-		mp->m_inoadd = XFS_INO64_OFFSET;
-	}
-#endif
-	if (ap->flags & XFSMNT_RETERR)
-		mp->m_flags |= XFS_MOUNT_RETERR;
-	if (ap->flags & XFSMNT_NOALIGN)
-		mp->m_flags |= XFS_MOUNT_NOALIGN;
-	if (ap->flags & XFSMNT_SWALLOC)
-		mp->m_flags |= XFS_MOUNT_SWALLOC;
-	if (ap->flags & XFSMNT_OSYNCISOSYNC)
-		mp->m_flags |= XFS_MOUNT_OSYNCISOSYNC;
-	if (ap->flags & XFSMNT_32BITINODES)
-		mp->m_flags |= XFS_MOUNT_32BITINODES;
-
-	if (ap->flags & XFSMNT_IOSIZE) {
-		if (ap->iosizelog > XFS_MAX_IO_LOG ||
-		    ap->iosizelog < XFS_MIN_IO_LOG) {
-			cmn_err(CE_WARN,
-		"XFS: invalid log iosize: %d [not %d-%d]",
-				ap->iosizelog, XFS_MIN_IO_LOG,
-				XFS_MAX_IO_LOG);
-			return XFS_ERROR(EINVAL);
-		}
-
-		mp->m_flags |= XFS_MOUNT_DFLT_IOSIZE;
-		mp->m_readio_log = mp->m_writeio_log = ap->iosizelog;
-	}
-
-	if (ap->flags & XFSMNT_IKEEP)
-		mp->m_flags |= XFS_MOUNT_IKEEP;
-	if (ap->flags & XFSMNT_DIRSYNC)
-		mp->m_flags |= XFS_MOUNT_DIRSYNC;
-	if (ap->flags & XFSMNT_ATTR2)
-		mp->m_flags |= XFS_MOUNT_ATTR2;
-	if (ap->flags & XFSMNT_NOATTR2)
-		mp->m_flags |= XFS_MOUNT_NOATTR2;
-
-	if (ap->flags2 & XFSMNT2_COMPAT_IOSIZE)
-		mp->m_flags |= XFS_MOUNT_COMPAT_IOSIZE;
-
-	/*
-	 * no recovery flag requires a read-only mount
-	 */
-	if (ap->flags & XFSMNT_NORECOVERY) {
-		if (!(mp->m_flags & XFS_MOUNT_RDONLY)) {
-			cmn_err(CE_WARN,
-	"XFS: tried to mount a FS read-write without recovery!");
-			return XFS_ERROR(EINVAL);
-		}
-		mp->m_flags |= XFS_MOUNT_NORECOVERY;
-	}
-
-	if (ap->flags & XFSMNT_NOUUID)
-		mp->m_flags |= XFS_MOUNT_NOUUID;
-	if (ap->flags & XFSMNT_BARRIER)
-		mp->m_flags |= XFS_MOUNT_BARRIER;
-	else
-		mp->m_flags &= ~XFS_MOUNT_BARRIER;
-
-	if (ap->flags2 & XFSMNT2_FILESTREAMS)
-		mp->m_flags |= XFS_MOUNT_FILESTREAMS;
-
-	if (ap->flags & XFSMNT_DMAPI)
-		mp->m_flags |= XFS_MOUNT_DMAPI;
-	return 0;
-
-
- out_free_rtname:
-	kfree(mp->m_rtname);
- out_free_fsname:
-	kfree(mp->m_fsname);
- out:
-	return error;
-}
-
-/*
- * This function fills in xfs_mount_t fields based on mount args.
  * Note: the superblock _has_ now been read in.
  */
 STATIC int
 xfs_finish_flags(
-	struct xfs_mount_args	*ap,
 	struct xfs_mount	*mp)
 {
 	int			ronly = (mp->m_flags & XFS_MOUNT_RDONLY);
 
 	/* Fail a mount where the logbuf is smaller then the log stripe */
 	if (xfs_sb_version_haslogv2(&mp->m_sb)) {
-		if ((ap->logbufsize <= 0) &&
-		    (mp->m_sb.sb_logsunit > XLOG_BIG_RECORD_BSIZE)) {
+		if (mp->m_logbsize <= 0 &&
+		    mp->m_sb.sb_logsunit > XLOG_BIG_RECORD_BSIZE) {
 			mp->m_logbsize = mp->m_sb.sb_logsunit;
-		} else if (ap->logbufsize > 0 &&
-			   ap->logbufsize < mp->m_sb.sb_logsunit) {
+		} else if (mp->m_logbsize > 0 &&
+			   mp->m_logbsize < mp->m_sb.sb_logsunit) {
 			cmn_err(CE_WARN,
 	"XFS: logbuf size must be greater than or equal to log stripe size");
 			return XFS_ERROR(EINVAL);
 		}
 	} else {
 		/* Fail a mount if the logbuf is larger than 32K */
-		if (ap->logbufsize > XLOG_BIG_RECORD_BSIZE) {
+		if (mp->m_logbsize > XLOG_BIG_RECORD_BSIZE) {
 			cmn_err(CE_WARN,
 	"XFS: logbuf size for version 1 logs must be 16K or 32K");
 			return XFS_ERROR(EINVAL);
@@ -1602,7 +1373,7 @@ xfs_finish_flags(
 	 * told by noattr2 to turn it off
 	 */
 	if (xfs_sb_version_hasattr2(&mp->m_sb) &&
-	    !(ap->flags & XFSMNT_NOATTR2))
+	    !(mp->m_flags & XFS_MOUNT_NOATTR2))
 		mp->m_flags |= XFS_MOUNT_ATTR2;
 
 	/*
@@ -1614,48 +1385,6 @@ xfs_finish_flags(
 		return XFS_ERROR(EROFS);
 	}
 
-	/*
-	 * check for shared mount.
-	 */
-	if (ap->flags & XFSMNT_SHARED) {
-		if (!xfs_sb_version_hasshared(&mp->m_sb))
-			return XFS_ERROR(EINVAL);
-
-		/*
-		 * For IRIX 6.5, shared mounts must have the shared
-		 * version bit set, have the persistent readonly
-		 * field set, must be version 0 and can only be mounted
-		 * read-only.
-		 */
-		if (!ronly || !(mp->m_sb.sb_flags & XFS_SBF_READONLY) ||
-		     (mp->m_sb.sb_shared_vn != 0))
-			return XFS_ERROR(EINVAL);
-
-		mp->m_flags |= XFS_MOUNT_SHARED;
-
-		/*
-		 * Shared XFS V0 can't deal with DMI.  Return EINVAL.
-		 */
-		if (mp->m_sb.sb_shared_vn == 0 && (ap->flags & XFSMNT_DMAPI))
-			return XFS_ERROR(EINVAL);
-	}
-
-	if (ap->flags & XFSMNT_UQUOTA) {
-		mp->m_qflags |= (XFS_UQUOTA_ACCT | XFS_UQUOTA_ACTIVE);
-		if (ap->flags & XFSMNT_UQUOTAENF)
-			mp->m_qflags |= XFS_UQUOTA_ENFD;
-	}
-
-	if (ap->flags & XFSMNT_GQUOTA) {
-		mp->m_qflags |= (XFS_GQUOTA_ACCT | XFS_GQUOTA_ACTIVE);
-		if (ap->flags & XFSMNT_GQUOTAENF)
-			mp->m_qflags |= XFS_OQUOTA_ENFD;
-	} else if (ap->flags & XFSMNT_PQUOTA) {
-		mp->m_qflags |= (XFS_PQUOTA_ACCT | XFS_PQUOTA_ACTIVE);
-		if (ap->flags & XFSMNT_PQUOTAENF)
-			mp->m_qflags |= XFS_OQUOTA_ENFD;
-	}
-
 	return 0;
 }
 
@@ -1667,19 +1396,14 @@ xfs_fs_fill_super(
 {
 	struct inode		*root;
 	struct xfs_mount	*mp = NULL;
-	struct xfs_mount_args	*args;
 	int			flags = 0, error = ENOMEM;
-
-	args = xfs_args_allocate(sb, silent);
-	if (!args)
-		return -ENOMEM;
+	char			*mtpt = NULL;
 
 	mp = kzalloc(sizeof(struct xfs_mount), GFP_KERNEL);
 	if (!mp)
-		goto out_free_args;
+		goto out;
 
 	spin_lock_init(&mp->m_sb_lock);
-	mutex_init(&mp->m_ilock);
 	mutex_init(&mp->m_growlock);
 	atomic_set(&mp->m_active_trans, 0);
 	INIT_LIST_HEAD(&mp->m_sync_list);
@@ -1689,12 +1413,9 @@ xfs_fs_fill_super(
 	mp->m_super = sb;
 	sb->s_fs_info = mp;
 
-	if (sb->s_flags & MS_RDONLY)
-		mp->m_flags |= XFS_MOUNT_RDONLY;
-
-	error = xfs_parseargs(mp, (char *)data, args, 0);
+	error = xfs_parseargs(mp, (char *)data, &mtpt);
 	if (error)
-		goto out_free_mp;
+		goto out_free_fsname;
 
 	sb_min_blocksize(sb, BBSIZE);
 	sb->s_xattr = xfs_xattr_handlers;
@@ -1702,33 +1423,28 @@ xfs_fs_fill_super(
 	sb->s_qcop = &xfs_quotactl_operations;
 	sb->s_op = &xfs_super_operations;
 
-	error = xfs_dmops_get(mp, args);
+	error = xfs_dmops_get(mp);
 	if (error)
-		goto out_free_mp;
-	error = xfs_qmops_get(mp, args);
+		goto out_free_fsname;
+	error = xfs_qmops_get(mp);
 	if (error)
 		goto out_put_dmops;
 
-	if (args->flags & XFSMNT_QUIET)
+	if (silent)
 		flags |= XFS_MFSI_QUIET;
 
-	error = xfs_open_devices(mp, args);
+	error = xfs_open_devices(mp);
 	if (error)
 		goto out_put_qmops;
 
 	if (xfs_icsb_init_counters(mp))
 		mp->m_flags |= XFS_MOUNT_NO_PERCPU_SB;
 
-	/*
-	 * Setup flags based on mount(2) options and then the superblock
-	 */
-	error = xfs_start_flags(args, mp);
-	if (error)
-		goto out_free_fsname;
 	error = xfs_readsb(mp, flags);
 	if (error)
-		goto out_free_fsname;
-	error = xfs_finish_flags(args, mp);
+		goto out_destroy_counters;
+
+	error = xfs_finish_flags(mp);
 	if (error)
 		goto out_free_sb;
 
@@ -1747,7 +1463,7 @@ xfs_fs_fill_super(
 	if (error)
 		goto out_filestream_unmount;
 
-	XFS_SEND_MOUNT(mp, DM_RIGHT_NULL, args->mtpt, args->fsname);
+	XFS_SEND_MOUNT(mp, DM_RIGHT_NULL, mtpt, mp->m_fsname);
 
 	sb->s_dirt = 1;
 	sb->s_magic = XFS_SB_MAGIC;
@@ -1772,35 +1488,31 @@ xfs_fs_fill_super(
 		goto fail_vnrele;
 	}
 
-	mp->m_sync_work.w_syncer = xfs_sync_worker;
-	mp->m_sync_work.w_mount = mp;
-	mp->m_sync_task = kthread_run(xfssyncd, mp, "xfssyncd");
-	if (IS_ERR(mp->m_sync_task)) {
-		error = -PTR_ERR(mp->m_sync_task);
+	error = xfs_syncd_init(mp);
+	if (error)
 		goto fail_vnrele;
-	}
 
-	xfs_itrace_exit(XFS_I(sb->s_root->d_inode));
+	kfree(mtpt);
 
-	kfree(args);
+	xfs_itrace_exit(XFS_I(sb->s_root->d_inode));
 	return 0;
 
  out_filestream_unmount:
 	xfs_filestream_unmount(mp);
  out_free_sb:
 	xfs_freesb(mp);
- out_free_fsname:
-	xfs_free_fsname(mp);
+ out_destroy_counters:
 	xfs_icsb_destroy_counters(mp);
 	xfs_close_devices(mp);
  out_put_qmops:
 	xfs_qmops_put(mp);
  out_put_dmops:
 	xfs_dmops_put(mp);
- out_free_mp:
+ out_free_fsname:
+	xfs_free_fsname(mp);
+	kfree(mtpt);
 	kfree(mp);
- out_free_args:
-	kfree(args);
+ out:
 	return -error;
 
  fail_vnrele:
@@ -1820,8 +1532,6 @@ xfs_fs_fill_super(
 	xfs_filestream_unmount(mp);
 
 	XFS_bflush(mp->m_ddev_targp);
-	error = xfs_unmount_flush(mp, 0);
-	WARN_ON(error);
 
 	xfs_unmountfs(mp);
 	goto out_free_sb;
@@ -1882,10 +1592,19 @@ xfs_alloc_trace_bufs(void)
 	if (!xfs_bmap_trace_buf)
 		goto out_free_alloc_trace;
 #endif
-#ifdef XFS_BMBT_TRACE
+#ifdef XFS_BTREE_TRACE
+	xfs_allocbt_trace_buf = ktrace_alloc(XFS_ALLOCBT_TRACE_SIZE,
+					     KM_MAYFAIL);
+	if (!xfs_allocbt_trace_buf)
+		goto out_free_bmap_trace;
+
+	xfs_inobt_trace_buf = ktrace_alloc(XFS_INOBT_TRACE_SIZE, KM_MAYFAIL);
+	if (!xfs_inobt_trace_buf)
+		goto out_free_allocbt_trace;
+
 	xfs_bmbt_trace_buf = ktrace_alloc(XFS_BMBT_TRACE_SIZE, KM_MAYFAIL);
 	if (!xfs_bmbt_trace_buf)
-		goto out_free_bmap_trace;
+		goto out_free_inobt_trace;
 #endif
 #ifdef XFS_ATTR_TRACE
 	xfs_attr_trace_buf = ktrace_alloc(XFS_ATTR_TRACE_SIZE, KM_MAYFAIL);
@@ -1907,8 +1626,12 @@ xfs_alloc_trace_bufs(void)
 	ktrace_free(xfs_attr_trace_buf);
  out_free_bmbt_trace:
 #endif
-#ifdef XFS_BMBT_TRACE
+#ifdef XFS_BTREE_TRACE
 	ktrace_free(xfs_bmbt_trace_buf);
+ out_free_inobt_trace:
+	ktrace_free(xfs_inobt_trace_buf);
+ out_free_allocbt_trace:
+	ktrace_free(xfs_allocbt_trace_buf);
  out_free_bmap_trace:
 #endif
 #ifdef XFS_BMAP_TRACE
@@ -1931,8 +1654,10 @@ xfs_free_trace_bufs(void)
 #ifdef XFS_ATTR_TRACE
 	ktrace_free(xfs_attr_trace_buf);
 #endif
-#ifdef XFS_BMBT_TRACE
+#ifdef XFS_BTREE_TRACE
 	ktrace_free(xfs_bmbt_trace_buf);
+	ktrace_free(xfs_inobt_trace_buf);
+	ktrace_free(xfs_allocbt_trace_buf);
 #endif
 #ifdef XFS_BMAP_TRACE
 	ktrace_free(xfs_bmap_trace_buf);
@@ -1945,16 +1670,10 @@ xfs_free_trace_bufs(void)
 STATIC int __init
 xfs_init_zones(void)
 {
-	xfs_vnode_zone = kmem_zone_init_flags(sizeof(struct inode), "xfs_vnode",
-					KM_ZONE_HWALIGN | KM_ZONE_RECLAIM |
-					KM_ZONE_SPREAD,
-					xfs_fs_inode_init_once);
-	if (!xfs_vnode_zone)
-		goto out;
 
 	xfs_ioend_zone = kmem_zone_init(sizeof(xfs_ioend_t), "xfs_ioend");
 	if (!xfs_ioend_zone)
-		goto out_destroy_vnode_zone;
+		goto out;
 
 	xfs_ioend_pool = mempool_create_slab_pool(4 * MAX_BUF_PER_PAGE,
 						  xfs_ioend_zone);
@@ -1970,6 +1689,7 @@ xfs_init_zones(void)
 						"xfs_bmap_free_item");
 	if (!xfs_bmap_free_item_zone)
 		goto out_destroy_log_ticket_zone;
+
 	xfs_btree_cur_zone = kmem_zone_init(sizeof(xfs_btree_cur_t),
 						"xfs_btree_cur");
 	if (!xfs_btree_cur_zone)
@@ -2017,8 +1737,8 @@ xfs_init_zones(void)
 
 	xfs_inode_zone =
 		kmem_zone_init_flags(sizeof(xfs_inode_t), "xfs_inode",
-					KM_ZONE_HWALIGN | KM_ZONE_RECLAIM |
-					KM_ZONE_SPREAD, NULL);
+			KM_ZONE_HWALIGN | KM_ZONE_RECLAIM | KM_ZONE_SPREAD,
+			xfs_fs_inode_init_once);
 	if (!xfs_inode_zone)
 		goto out_destroy_efi_zone;
 
@@ -2066,8 +1786,6 @@ xfs_init_zones(void)
 	mempool_destroy(xfs_ioend_pool);
  out_destroy_ioend_zone:
 	kmem_zone_destroy(xfs_ioend_zone);
- out_destroy_vnode_zone:
-	kmem_zone_destroy(xfs_vnode_zone);
  out:
 	return -ENOMEM;
 }
@@ -2092,7 +1810,6 @@ xfs_destroy_zones(void)
 	kmem_zone_destroy(xfs_log_ticket_zone);
 	mempool_destroy(xfs_ioend_pool);
 	kmem_zone_destroy(xfs_ioend_zone);
-	kmem_zone_destroy(xfs_vnode_zone);
 
 }
 
@@ -2100,13 +1817,12 @@ STATIC int __init
 init_xfs_fs(void)
 {
 	int			error;
-	static char		message[] __initdata = KERN_INFO \
-		XFS_VERSION_STRING " with " XFS_BUILD_OPTIONS " enabled\n";
 
-	printk(message);
+	printk(KERN_INFO XFS_VERSION_STRING " with "
+			 XFS_BUILD_OPTIONS " enabled\n");
 
 	ktrace_init(64);
-	vn_init();
+	xfs_ioend_init();
 	xfs_dir_startup();
 
 	error = xfs_init_zones();
diff --git a/fs/xfs/linux-2.6/xfs_super.h b/fs/xfs/linux-2.6/xfs_super.h
index fe2ef4e6a0f9..d5d776d4cd67 100644
--- a/fs/xfs/linux-2.6/xfs_super.h
+++ b/fs/xfs/linux-2.6/xfs_super.h
@@ -20,24 +20,12 @@
 
 #include <linux/exportfs.h>
 
-#ifdef CONFIG_XFS_DMAPI
-# define vfs_insertdmapi(vfs)	vfs_insertops(vfsp, &xfs_dmops)
-# define vfs_initdmapi()	dmapi_init()
-# define vfs_exitdmapi()	dmapi_uninit()
-#else
-# define vfs_insertdmapi(vfs)	do { } while (0)
-# define vfs_initdmapi()	do { } while (0)
-# define vfs_exitdmapi()	do { } while (0)
-#endif
-
 #ifdef CONFIG_XFS_QUOTA
-# define vfs_insertquota(vfs)	vfs_insertops(vfsp, &xfs_qmops)
 extern void xfs_qm_init(void);
 extern void xfs_qm_exit(void);
 # define vfs_initquota()	xfs_qm_init()
 # define vfs_exitquota()	xfs_qm_exit()
 #else
-# define vfs_insertquota(vfs)	do { } while (0)
 # define vfs_initquota()	do { } while (0)
 # define vfs_exitquota()	do { } while (0)
 #endif
@@ -101,9 +89,6 @@ struct block_device;
 
 extern __uint64_t xfs_max_file_offset(unsigned int);
 
-extern void xfs_flush_inode(struct xfs_inode *);
-extern void xfs_flush_device(struct xfs_inode *);
-
 extern void xfs_blkdev_issue_flush(struct xfs_buftarg *);
 
 extern const struct export_operations xfs_export_operations;
diff --git a/fs/xfs/linux-2.6/xfs_sync.c b/fs/xfs/linux-2.6/xfs_sync.c
new file mode 100644
index 000000000000..2ed035354c26
--- /dev/null
+++ b/fs/xfs/linux-2.6/xfs_sync.c
@@ -0,0 +1,762 @@
+/*
+ * Copyright (c) 2000-2005 Silicon Graphics, Inc.
+ * All Rights Reserved.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it would be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write the Free Software Foundation,
+ * Inc.,  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
+ */
+#include "xfs.h"
+#include "xfs_fs.h"
+#include "xfs_types.h"
+#include "xfs_bit.h"
+#include "xfs_log.h"
+#include "xfs_inum.h"
+#include "xfs_trans.h"
+#include "xfs_sb.h"
+#include "xfs_ag.h"
+#include "xfs_dir2.h"
+#include "xfs_dmapi.h"
+#include "xfs_mount.h"
+#include "xfs_bmap_btree.h"
+#include "xfs_alloc_btree.h"
+#include "xfs_ialloc_btree.h"
+#include "xfs_btree.h"
+#include "xfs_dir2_sf.h"
+#include "xfs_attr_sf.h"
+#include "xfs_inode.h"
+#include "xfs_dinode.h"
+#include "xfs_error.h"
+#include "xfs_mru_cache.h"
+#include "xfs_filestream.h"
+#include "xfs_vnodeops.h"
+#include "xfs_utils.h"
+#include "xfs_buf_item.h"
+#include "xfs_inode_item.h"
+#include "xfs_rw.h"
+
+#include <linux/kthread.h>
+#include <linux/freezer.h>
+
+/*
+ * Sync all the inodes in the given AG according to the
+ * direction given by the flags.
+ */
+STATIC int
+xfs_sync_inodes_ag(
+	xfs_mount_t	*mp,
+	int		ag,
+	int		flags)
+{
+	xfs_perag_t	*pag = &mp->m_perag[ag];
+	int		nr_found;
+	uint32_t	first_index = 0;
+	int		error = 0;
+	int		last_error = 0;
+	int		fflag = XFS_B_ASYNC;
+
+	if (flags & SYNC_DELWRI)
+		fflag = XFS_B_DELWRI;
+	if (flags & SYNC_WAIT)
+		fflag = 0;		/* synchronous overrides all */
+
+	do {
+		struct inode	*inode;
+		xfs_inode_t	*ip = NULL;
+		int		lock_flags = XFS_ILOCK_SHARED;
+
+		/*
+		 * use a gang lookup to find the next inode in the tree
+		 * as the tree is sparse and a gang lookup walks to find
+		 * the number of objects requested.
+		 */
+		read_lock(&pag->pag_ici_lock);
+		nr_found = radix_tree_gang_lookup(&pag->pag_ici_root,
+				(void**)&ip, first_index, 1);
+
+		if (!nr_found) {
+			read_unlock(&pag->pag_ici_lock);
+			break;
+		}
+
+		/*
+		 * Update the index for the next lookup. Catch overflows
+		 * into the next AG range which can occur if we have inodes
+		 * in the last block of the AG and we are currently
+		 * pointing to the last inode.
+		 */
+		first_index = XFS_INO_TO_AGINO(mp, ip->i_ino + 1);
+		if (first_index < XFS_INO_TO_AGINO(mp, ip->i_ino)) {
+			read_unlock(&pag->pag_ici_lock);
+			break;
+		}
+
+		/* nothing to sync during shutdown */
+		if (XFS_FORCED_SHUTDOWN(mp)) {
+			read_unlock(&pag->pag_ici_lock);
+			return 0;
+		}
+
+		/*
+		 * If we can't get a reference on the inode, it must be
+		 * in reclaim. Leave it for the reclaim code to flush.
+		 */
+		inode = VFS_I(ip);
+		if (!igrab(inode)) {
+			read_unlock(&pag->pag_ici_lock);
+			continue;
+		}
+		read_unlock(&pag->pag_ici_lock);
+
+		/* avoid new or bad inodes */
+		if (is_bad_inode(inode) ||
+		    xfs_iflags_test(ip, XFS_INEW)) {
+			IRELE(ip);
+			continue;
+		}
+
+		/*
+		 * If we have to flush data or wait for I/O completion
+		 * we need to hold the iolock.
+		 */
+		if ((flags & SYNC_DELWRI) && VN_DIRTY(inode)) {
+			xfs_ilock(ip, XFS_IOLOCK_SHARED);
+			lock_flags |= XFS_IOLOCK_SHARED;
+			error = xfs_flush_pages(ip, 0, -1, fflag, FI_NONE);
+			if (flags & SYNC_IOWAIT)
+				xfs_ioend_wait(ip);
+		}
+		xfs_ilock(ip, XFS_ILOCK_SHARED);
+
+		if ((flags & SYNC_ATTR) && !xfs_inode_clean(ip)) {
+			if (flags & SYNC_WAIT) {
+				xfs_iflock(ip);
+				if (!xfs_inode_clean(ip))
+					error = xfs_iflush(ip, XFS_IFLUSH_SYNC);
+				else
+					xfs_ifunlock(ip);
+			} else if (xfs_iflock_nowait(ip)) {
+				if (!xfs_inode_clean(ip))
+					error = xfs_iflush(ip, XFS_IFLUSH_DELWRI);
+				else
+					xfs_ifunlock(ip);
+			}
+		}
+		xfs_iput(ip, lock_flags);
+
+		if (error)
+			last_error = error;
+		/*
+		 * bail out if the filesystem is corrupted.
+		 */
+		if (error == EFSCORRUPTED)
+			return XFS_ERROR(error);
+
+	} while (nr_found);
+
+	return last_error;
+}
+
+int
+xfs_sync_inodes(
+	xfs_mount_t	*mp,
+	int		flags)
+{
+	int		error;
+	int		last_error;
+	int		i;
+	int		lflags = XFS_LOG_FORCE;
+
+	if (mp->m_flags & XFS_MOUNT_RDONLY)
+		return 0;
+	error = 0;
+	last_error = 0;
+
+	if (flags & SYNC_WAIT)
+		lflags |= XFS_LOG_SYNC;
+
+	for (i = 0; i < mp->m_sb.sb_agcount; i++) {
+		if (!mp->m_perag[i].pag_ici_init)
+			continue;
+		error = xfs_sync_inodes_ag(mp, i, flags);
+		if (error)
+			last_error = error;
+		if (error == EFSCORRUPTED)
+			break;
+	}
+	if (flags & SYNC_DELWRI)
+		xfs_log_force(mp, 0, lflags);
+
+	return XFS_ERROR(last_error);
+}
+
+STATIC int
+xfs_commit_dummy_trans(
+	struct xfs_mount	*mp,
+	uint			log_flags)
+{
+	struct xfs_inode	*ip = mp->m_rootip;
+	struct xfs_trans	*tp;
+	int			error;
+
+	/*
+	 * Put a dummy transaction in the log to tell recovery
+	 * that all others are OK.
+	 */
+	tp = xfs_trans_alloc(mp, XFS_TRANS_DUMMY1);
+	error = xfs_trans_reserve(tp, 0, XFS_ICHANGE_LOG_RES(mp), 0, 0, 0);
+	if (error) {
+		xfs_trans_cancel(tp, 0);
+		return error;
+	}
+
+	xfs_ilock(ip, XFS_ILOCK_EXCL);
+
+	xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
+	xfs_trans_ihold(tp, ip);
+	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
+	/* XXX(hch): ignoring the error here.. */
+	error = xfs_trans_commit(tp, 0);
+
+	xfs_iunlock(ip, XFS_ILOCK_EXCL);
+
+	xfs_log_force(mp, 0, log_flags);
+	return 0;
+}
+
+int
+xfs_sync_fsdata(
+	struct xfs_mount	*mp,
+	int			flags)
+{
+	struct xfs_buf		*bp;
+	struct xfs_buf_log_item	*bip;
+	int			error = 0;
+
+	/*
+	 * If this is xfssyncd() then only sync the superblock if we can
+	 * lock it without sleeping and it is not pinned.
+	 */
+	if (flags & SYNC_BDFLUSH) {
+		ASSERT(!(flags & SYNC_WAIT));
+
+		bp = xfs_getsb(mp, XFS_BUF_TRYLOCK);
+		if (!bp)
+			goto out;
+
+		bip = XFS_BUF_FSPRIVATE(bp, struct xfs_buf_log_item *);
+		if (!bip || !xfs_buf_item_dirty(bip) || XFS_BUF_ISPINNED(bp))
+			goto out_brelse;
+	} else {
+		bp = xfs_getsb(mp, 0);
+
+		/*
+		 * If the buffer is pinned then push on the log so we won't
+		 * get stuck waiting in the write for someone, maybe
+		 * ourselves, to flush the log.
+		 *
+		 * Even though we just pushed the log above, we did not have
+		 * the superblock buffer locked at that point so it can
+		 * become pinned in between there and here.
+		 */
+		if (XFS_BUF_ISPINNED(bp))
+			xfs_log_force(mp, 0, XFS_LOG_FORCE);
+	}
+
+
+	if (flags & SYNC_WAIT)
+		XFS_BUF_UNASYNC(bp);
+	else
+		XFS_BUF_ASYNC(bp);
+
+	return xfs_bwrite(mp, bp);
+
+ out_brelse:
+	xfs_buf_relse(bp);
+ out:
+	return error;
+}
+
+/*
+ * When remounting a filesystem read-only or freezing the filesystem, we have
+ * two phases to execute. This first phase is syncing the data before we
+ * quiesce the filesystem, and the second is flushing all the inodes out after
+ * we've waited for all the transactions created by the first phase to
+ * complete. The second phase ensures that the inodes are written to their
+ * location on disk rather than just existing in transactions in the log. This
+ * means after a quiesce there is no log replay required to write the inodes to
+ * disk (this is the main difference between a sync and a quiesce).
+ */
+/*
+ * First stage of freeze - no writers will make progress now we are here,
+ * so we flush delwri and delalloc buffers here, then wait for all I/O to
+ * complete.  Data is frozen at that point. Metadata is not frozen,
+ * transactions can still occur here so don't bother flushing the buftarg
+ * because it'll just get dirty again.
+ */
+int
+xfs_quiesce_data(
+	struct xfs_mount	*mp)
+{
+	int error;
+
+	/* push non-blocking */
+	xfs_sync_inodes(mp, SYNC_DELWRI|SYNC_BDFLUSH);
+	XFS_QM_DQSYNC(mp, SYNC_BDFLUSH);
+	xfs_filestream_flush(mp);
+
+	/* push and block */
+	xfs_sync_inodes(mp, SYNC_DELWRI|SYNC_WAIT|SYNC_IOWAIT);
+	XFS_QM_DQSYNC(mp, SYNC_WAIT);
+
+	/* write superblock and hoover up shutdown errors */
+	error = xfs_sync_fsdata(mp, 0);
+
+	/* flush data-only devices */
+	if (mp->m_rtdev_targp)
+		XFS_bflush(mp->m_rtdev_targp);
+
+	return error;
+}
+
+STATIC void
+xfs_quiesce_fs(
+	struct xfs_mount	*mp)
+{
+	int	count = 0, pincount;
+
+	xfs_flush_buftarg(mp->m_ddev_targp, 0);
+	xfs_reclaim_inodes(mp, 0, XFS_IFLUSH_DELWRI_ELSE_ASYNC);
+
+	/*
+	 * This loop must run at least twice.  The first instance of the loop
+	 * will flush most meta data but that will generate more meta data
+	 * (typically directory updates).  Which then must be flushed and
+	 * logged before we can write the unmount record.
+	 */
+	do {
+		xfs_sync_inodes(mp, SYNC_ATTR|SYNC_WAIT);
+		pincount = xfs_flush_buftarg(mp->m_ddev_targp, 1);
+		if (!pincount) {
+			delay(50);
+			count++;
+		}
+	} while (count < 2);
+}
+
+/*
+ * Second stage of a quiesce. The data is already synced, now we have to take
+ * care of the metadata. New transactions are already blocked, so we need to
+ * wait for any remaining transactions to drain out before proceding.
+ */
+void
+xfs_quiesce_attr(
+	struct xfs_mount	*mp)
+{
+	int	error = 0;
+
+	/* wait for all modifications to complete */
+	while (atomic_read(&mp->m_active_trans) > 0)
+		delay(100);
+
+	/* flush inodes and push all remaining buffers out to disk */
+	xfs_quiesce_fs(mp);
+
+	ASSERT_ALWAYS(atomic_read(&mp->m_active_trans) == 0);
+
+	/* Push the superblock and write an unmount record */
+	error = xfs_log_sbcount(mp, 1);
+	if (error)
+		xfs_fs_cmn_err(CE_WARN, mp,
+				"xfs_attr_quiesce: failed to log sb changes. "
+				"Frozen image may not be consistent.");
+	xfs_log_unmount_write(mp);
+	xfs_unmountfs_writesb(mp);
+}
+
+/*
+ * Enqueue a work item to be picked up by the vfs xfssyncd thread.
+ * Doing this has two advantages:
+ * - It saves on stack space, which is tight in certain situations
+ * - It can be used (with care) as a mechanism to avoid deadlocks.
+ * Flushing while allocating in a full filesystem requires both.
+ */
+STATIC void
+xfs_syncd_queue_work(
+	struct xfs_mount *mp,
+	void		*data,
+	void		(*syncer)(struct xfs_mount *, void *))
+{
+	struct bhv_vfs_sync_work *work;
+
+	work = kmem_alloc(sizeof(struct bhv_vfs_sync_work), KM_SLEEP);
+	INIT_LIST_HEAD(&work->w_list);
+	work->w_syncer = syncer;
+	work->w_data = data;
+	work->w_mount = mp;
+	spin_lock(&mp->m_sync_lock);
+	list_add_tail(&work->w_list, &mp->m_sync_list);
+	spin_unlock(&mp->m_sync_lock);
+	wake_up_process(mp->m_sync_task);
+}
+
+/*
+ * Flush delayed allocate data, attempting to free up reserved space
+ * from existing allocations.  At this point a new allocation attempt
+ * has failed with ENOSPC and we are in the process of scratching our
+ * heads, looking about for more room...
+ */
+STATIC void
+xfs_flush_inode_work(
+	struct xfs_mount *mp,
+	void		*arg)
+{
+	struct inode	*inode = arg;
+	filemap_flush(inode->i_mapping);
+	iput(inode);
+}
+
+void
+xfs_flush_inode(
+	xfs_inode_t	*ip)
+{
+	struct inode	*inode = VFS_I(ip);
+
+	igrab(inode);
+	xfs_syncd_queue_work(ip->i_mount, inode, xfs_flush_inode_work);
+	delay(msecs_to_jiffies(500));
+}
+
+/*
+ * This is the "bigger hammer" version of xfs_flush_inode_work...
+ * (IOW, "If at first you don't succeed, use a Bigger Hammer").
+ */
+STATIC void
+xfs_flush_device_work(
+	struct xfs_mount *mp,
+	void		*arg)
+{
+	struct inode	*inode = arg;
+	sync_blockdev(mp->m_super->s_bdev);
+	iput(inode);
+}
+
+void
+xfs_flush_device(
+	xfs_inode_t	*ip)
+{
+	struct inode	*inode = VFS_I(ip);
+
+	igrab(inode);
+	xfs_syncd_queue_work(ip->i_mount, inode, xfs_flush_device_work);
+	delay(msecs_to_jiffies(500));
+	xfs_log_force(ip->i_mount, (xfs_lsn_t)0, XFS_LOG_FORCE|XFS_LOG_SYNC);
+}
+
+/*
+ * Every sync period we need to unpin all items, reclaim inodes, sync
+ * quota and write out the superblock. We might need to cover the log
+ * to indicate it is idle.
+ */
+STATIC void
+xfs_sync_worker(
+	struct xfs_mount *mp,
+	void		*unused)
+{
+	int		error;
+
+	if (!(mp->m_flags & XFS_MOUNT_RDONLY)) {
+		xfs_log_force(mp, (xfs_lsn_t)0, XFS_LOG_FORCE);
+		xfs_reclaim_inodes(mp, 0, XFS_IFLUSH_DELWRI_ELSE_ASYNC);
+		/* dgc: errors ignored here */
+		error = XFS_QM_DQSYNC(mp, SYNC_BDFLUSH);
+		error = xfs_sync_fsdata(mp, SYNC_BDFLUSH);
+		if (xfs_log_need_covered(mp))
+			error = xfs_commit_dummy_trans(mp, XFS_LOG_FORCE);
+	}
+	mp->m_sync_seq++;
+	wake_up(&mp->m_wait_single_sync_task);
+}
+
+STATIC int
+xfssyncd(
+	void			*arg)
+{
+	struct xfs_mount	*mp = arg;
+	long			timeleft;
+	bhv_vfs_sync_work_t	*work, *n;
+	LIST_HEAD		(tmp);
+
+	set_freezable();
+	timeleft = xfs_syncd_centisecs * msecs_to_jiffies(10);
+	for (;;) {
+		timeleft = schedule_timeout_interruptible(timeleft);
+		/* swsusp */
+		try_to_freeze();
+		if (kthread_should_stop() && list_empty(&mp->m_sync_list))
+			break;
+
+		spin_lock(&mp->m_sync_lock);
+		/*
+		 * We can get woken by laptop mode, to do a sync -
+		 * that's the (only!) case where the list would be
+		 * empty with time remaining.
+		 */
+		if (!timeleft || list_empty(&mp->m_sync_list)) {
+			if (!timeleft)
+				timeleft = xfs_syncd_centisecs *
+							msecs_to_jiffies(10);
+			INIT_LIST_HEAD(&mp->m_sync_work.w_list);
+			list_add_tail(&mp->m_sync_work.w_list,
+					&mp->m_sync_list);
+		}
+		list_for_each_entry_safe(work, n, &mp->m_sync_list, w_list)
+			list_move(&work->w_list, &tmp);
+		spin_unlock(&mp->m_sync_lock);
+
+		list_for_each_entry_safe(work, n, &tmp, w_list) {
+			(*work->w_syncer)(mp, work->w_data);
+			list_del(&work->w_list);
+			if (work == &mp->m_sync_work)
+				continue;
+			kmem_free(work);
+		}
+	}
+
+	return 0;
+}
+
+int
+xfs_syncd_init(
+	struct xfs_mount	*mp)
+{
+	mp->m_sync_work.w_syncer = xfs_sync_worker;
+	mp->m_sync_work.w_mount = mp;
+	mp->m_sync_task = kthread_run(xfssyncd, mp, "xfssyncd");
+	if (IS_ERR(mp->m_sync_task))
+		return -PTR_ERR(mp->m_sync_task);
+	return 0;
+}
+
+void
+xfs_syncd_stop(
+	struct xfs_mount	*mp)
+{
+	kthread_stop(mp->m_sync_task);
+}
+
+int
+xfs_reclaim_inode(
+	xfs_inode_t	*ip,
+	int		locked,
+	int		sync_mode)
+{
+	xfs_perag_t	*pag = xfs_get_perag(ip->i_mount, ip->i_ino);
+
+	/* The hash lock here protects a thread in xfs_iget_core from
+	 * racing with us on linking the inode back with a vnode.
+	 * Once we have the XFS_IRECLAIM flag set it will not touch
+	 * us.
+	 */
+	write_lock(&pag->pag_ici_lock);
+	spin_lock(&ip->i_flags_lock);
+	if (__xfs_iflags_test(ip, XFS_IRECLAIM) ||
+	    !__xfs_iflags_test(ip, XFS_IRECLAIMABLE)) {
+		spin_unlock(&ip->i_flags_lock);
+		write_unlock(&pag->pag_ici_lock);
+		if (locked) {
+			xfs_ifunlock(ip);
+			xfs_iunlock(ip, XFS_ILOCK_EXCL);
+		}
+		return 1;
+	}
+	__xfs_iflags_set(ip, XFS_IRECLAIM);
+	spin_unlock(&ip->i_flags_lock);
+	write_unlock(&pag->pag_ici_lock);
+	xfs_put_perag(ip->i_mount, pag);
+
+	/*
+	 * If the inode is still dirty, then flush it out.  If the inode
+	 * is not in the AIL, then it will be OK to flush it delwri as
+	 * long as xfs_iflush() does not keep any references to the inode.
+	 * We leave that decision up to xfs_iflush() since it has the
+	 * knowledge of whether it's OK to simply do a delwri flush of
+	 * the inode or whether we need to wait until the inode is
+	 * pulled from the AIL.
+	 * We get the flush lock regardless, though, just to make sure
+	 * we don't free it while it is being flushed.
+	 */
+	if (!locked) {
+		xfs_ilock(ip, XFS_ILOCK_EXCL);
+		xfs_iflock(ip);
+	}
+
+	/*
+	 * In the case of a forced shutdown we rely on xfs_iflush() to
+	 * wait for the inode to be unpinned before returning an error.
+	 */
+	if (!is_bad_inode(VFS_I(ip)) && xfs_iflush(ip, sync_mode) == 0) {
+		/* synchronize with xfs_iflush_done */
+		xfs_iflock(ip);
+		xfs_ifunlock(ip);
+	}
+
+	xfs_iunlock(ip, XFS_ILOCK_EXCL);
+	xfs_ireclaim(ip);
+	return 0;
+}
+
+/*
+ * We set the inode flag atomically with the radix tree tag.
+ * Once we get tag lookups on the radix tree, this inode flag
+ * can go away.
+ */
+void
+xfs_inode_set_reclaim_tag(
+	xfs_inode_t	*ip)
+{
+	xfs_mount_t	*mp = ip->i_mount;
+	xfs_perag_t	*pag = xfs_get_perag(mp, ip->i_ino);
+
+	read_lock(&pag->pag_ici_lock);
+	spin_lock(&ip->i_flags_lock);
+	radix_tree_tag_set(&pag->pag_ici_root,
+			XFS_INO_TO_AGINO(mp, ip->i_ino), XFS_ICI_RECLAIM_TAG);
+	__xfs_iflags_set(ip, XFS_IRECLAIMABLE);
+	spin_unlock(&ip->i_flags_lock);
+	read_unlock(&pag->pag_ici_lock);
+	xfs_put_perag(mp, pag);
+}
+
+void
+__xfs_inode_clear_reclaim_tag(
+	xfs_mount_t	*mp,
+	xfs_perag_t	*pag,
+	xfs_inode_t	*ip)
+{
+	radix_tree_tag_clear(&pag->pag_ici_root,
+			XFS_INO_TO_AGINO(mp, ip->i_ino), XFS_ICI_RECLAIM_TAG);
+}
+
+void
+xfs_inode_clear_reclaim_tag(
+	xfs_inode_t	*ip)
+{
+	xfs_mount_t	*mp = ip->i_mount;
+	xfs_perag_t	*pag = xfs_get_perag(mp, ip->i_ino);
+
+	read_lock(&pag->pag_ici_lock);
+	spin_lock(&ip->i_flags_lock);
+	__xfs_inode_clear_reclaim_tag(mp, pag, ip);
+	spin_unlock(&ip->i_flags_lock);
+	read_unlock(&pag->pag_ici_lock);
+	xfs_put_perag(mp, pag);
+}
+
+
+STATIC void
+xfs_reclaim_inodes_ag(
+	xfs_mount_t	*mp,
+	int		ag,
+	int		noblock,
+	int		mode)
+{
+	xfs_inode_t	*ip = NULL;
+	xfs_perag_t	*pag = &mp->m_perag[ag];
+	int		nr_found;
+	uint32_t	first_index;
+	int		skipped;
+
+restart:
+	first_index = 0;
+	skipped = 0;
+	do {
+		/*
+		 * use a gang lookup to find the next inode in the tree
+		 * as the tree is sparse and a gang lookup walks to find
+		 * the number of objects requested.
+		 */
+		read_lock(&pag->pag_ici_lock);
+		nr_found = radix_tree_gang_lookup_tag(&pag->pag_ici_root,
+					(void**)&ip, first_index, 1,
+					XFS_ICI_RECLAIM_TAG);
+
+		if (!nr_found) {
+			read_unlock(&pag->pag_ici_lock);
+			break;
+		}
+
+		/*
+		 * Update the index for the next lookup. Catch overflows
+		 * into the next AG range which can occur if we have inodes
+		 * in the last block of the AG and we are currently
+		 * pointing to the last inode.
+		 */
+		first_index = XFS_INO_TO_AGINO(mp, ip->i_ino + 1);
+		if (first_index < XFS_INO_TO_AGINO(mp, ip->i_ino)) {
+			read_unlock(&pag->pag_ici_lock);
+			break;
+		}
+
+		/* ignore if already under reclaim */
+		if (xfs_iflags_test(ip, XFS_IRECLAIM)) {
+			read_unlock(&pag->pag_ici_lock);
+			continue;
+		}
+
+		if (noblock) {
+			if (!xfs_ilock_nowait(ip, XFS_ILOCK_EXCL)) {
+				read_unlock(&pag->pag_ici_lock);
+				continue;
+			}
+			if (xfs_ipincount(ip) ||
+			    !xfs_iflock_nowait(ip)) {
+				xfs_iunlock(ip, XFS_ILOCK_EXCL);
+				read_unlock(&pag->pag_ici_lock);
+				continue;
+			}
+		}
+		read_unlock(&pag->pag_ici_lock);
+
+		/*
+		 * hmmm - this is an inode already in reclaim. Do
+		 * we even bother catching it here?
+		 */
+		if (xfs_reclaim_inode(ip, noblock, mode))
+			skipped++;
+	} while (nr_found);
+
+	if (skipped) {
+		delay(1);
+		goto restart;
+	}
+	return;
+
+}
+
+int
+xfs_reclaim_inodes(
+	xfs_mount_t	*mp,
+	int		 noblock,
+	int		mode)
+{
+	int		i;
+
+	for (i = 0; i < mp->m_sb.sb_agcount; i++) {
+		if (!mp->m_perag[i].pag_ici_init)
+			continue;
+		xfs_reclaim_inodes_ag(mp, i, noblock, mode);
+	}
+	return 0;
+}
+
+
diff --git a/fs/xfs/linux-2.6/xfs_sync.h b/fs/xfs/linux-2.6/xfs_sync.h
new file mode 100644
index 000000000000..5f6de1efe1f6
--- /dev/null
+++ b/fs/xfs/linux-2.6/xfs_sync.h
@@ -0,0 +1,55 @@
+/*
+ * Copyright (c) 2000-2006 Silicon Graphics, Inc.
+ * All Rights Reserved.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it would be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write the Free Software Foundation,
+ * Inc.,  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
+ */
+#ifndef XFS_SYNC_H
+#define XFS_SYNC_H 1
+
+struct xfs_mount;
+
+typedef struct bhv_vfs_sync_work {
+	struct list_head	w_list;
+	struct xfs_mount	*w_mount;
+	void			*w_data;	/* syncer routine argument */
+	void			(*w_syncer)(struct xfs_mount *, void *);
+} bhv_vfs_sync_work_t;
+
+#define SYNC_ATTR		0x0001	/* sync attributes */
+#define SYNC_DELWRI		0x0002	/* look at delayed writes */
+#define SYNC_WAIT		0x0004	/* wait for i/o to complete */
+#define SYNC_BDFLUSH		0x0008	/* BDFLUSH is calling -- don't block */
+#define SYNC_IOWAIT		0x0010  /* wait for all I/O to complete */
+
+int xfs_syncd_init(struct xfs_mount *mp);
+void xfs_syncd_stop(struct xfs_mount *mp);
+
+int xfs_sync_inodes(struct xfs_mount *mp, int flags);
+int xfs_sync_fsdata(struct xfs_mount *mp, int flags);
+
+int xfs_quiesce_data(struct xfs_mount *mp);
+void xfs_quiesce_attr(struct xfs_mount *mp);
+
+void xfs_flush_inode(struct xfs_inode *ip);
+void xfs_flush_device(struct xfs_inode *ip);
+
+int xfs_reclaim_inode(struct xfs_inode *ip, int locked, int sync_mode);
+int xfs_reclaim_inodes(struct xfs_mount *mp, int noblock, int mode);
+
+void xfs_inode_set_reclaim_tag(struct xfs_inode *ip);
+void xfs_inode_clear_reclaim_tag(struct xfs_inode *ip);
+void __xfs_inode_clear_reclaim_tag(struct xfs_mount *mp, struct xfs_perag *pag,
+				struct xfs_inode *ip);
+#endif
diff --git a/fs/xfs/linux-2.6/xfs_sysctl.c b/fs/xfs/linux-2.6/xfs_sysctl.c
index 7dacb5bbde3f..916c0ffb6083 100644
--- a/fs/xfs/linux-2.6/xfs_sysctl.c
+++ b/fs/xfs/linux-2.6/xfs_sysctl.c
@@ -56,17 +56,6 @@ xfs_stats_clear_proc_handler(
 
 static ctl_table xfs_table[] = {
 	{
-		.ctl_name	= XFS_RESTRICT_CHOWN,
-		.procname	= "restrict_chown",
-		.data		= &xfs_params.restrict_chown.val,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= &proc_dointvec_minmax,
-		.strategy	= &sysctl_intvec,
-		.extra1		= &xfs_params.restrict_chown.min,
-		.extra2		= &xfs_params.restrict_chown.max
-	},
-	{
 		.ctl_name	= XFS_SGID_INHERIT,
 		.procname	= "irix_sgid_inherit",
 		.data		= &xfs_params.sgid_inherit.val,
diff --git a/fs/xfs/linux-2.6/xfs_sysctl.h b/fs/xfs/linux-2.6/xfs_sysctl.h
index 4aadb8056c37..b9937d450f8e 100644
--- a/fs/xfs/linux-2.6/xfs_sysctl.h
+++ b/fs/xfs/linux-2.6/xfs_sysctl.h
@@ -31,7 +31,6 @@ typedef struct xfs_sysctl_val {
 } xfs_sysctl_val_t;
 
 typedef struct xfs_param {
-	xfs_sysctl_val_t restrict_chown;/* Root/non-root can give away files.*/
 	xfs_sysctl_val_t sgid_inherit;	/* Inherit S_ISGID if process' GID is
 					 * not a member of parent dir GID. */
 	xfs_sysctl_val_t symlink_mode;	/* Link creat mode affected by umask */
@@ -68,7 +67,7 @@ typedef struct xfs_param {
 enum {
 	/* XFS_REFCACHE_SIZE = 1 */
 	/* XFS_REFCACHE_PURGE = 2 */
-	XFS_RESTRICT_CHOWN = 3,
+	/* XFS_RESTRICT_CHOWN = 3 */
 	XFS_SGID_INHERIT = 4,
 	XFS_SYMLINK_MODE = 5,
 	XFS_PANIC_MASK = 6,
diff --git a/fs/xfs/linux-2.6/xfs_vfs.h b/fs/xfs/linux-2.6/xfs_vfs.h
deleted file mode 100644
index 7e60c7776b1c..000000000000
--- a/fs/xfs/linux-2.6/xfs_vfs.h
+++ /dev/null
@@ -1,77 +0,0 @@
-/*
- * Copyright (c) 2000-2006 Silicon Graphics, Inc.
- * All Rights Reserved.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it would be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write the Free Software Foundation,
- * Inc.,  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
- */
-#ifndef __XFS_VFS_H__
-#define __XFS_VFS_H__
-
-#include <linux/vfs.h>
-#include "xfs_fs.h"
-
-struct inode;
-
-struct fid;
-struct cred;
-struct seq_file;
-struct super_block;
-struct xfs_inode;
-struct xfs_mount;
-struct xfs_mount_args;
-
-typedef struct kstatfs	bhv_statvfs_t;
-
-typedef struct bhv_vfs_sync_work {
-	struct list_head	w_list;
-	struct xfs_mount	*w_mount;
-	void			*w_data;	/* syncer routine argument */
-	void			(*w_syncer)(struct xfs_mount *, void *);
-} bhv_vfs_sync_work_t;
-
-#define SYNC_ATTR		0x0001	/* sync attributes */
-#define SYNC_CLOSE		0x0002	/* close file system down */
-#define SYNC_DELWRI		0x0004	/* look at delayed writes */
-#define SYNC_WAIT		0x0008	/* wait for i/o to complete */
-#define SYNC_BDFLUSH		0x0010	/* BDFLUSH is calling -- don't block */
-#define SYNC_FSDATA		0x0020	/* flush fs data (e.g. superblocks) */
-#define SYNC_REFCACHE		0x0040  /* prune some of the nfs ref cache */
-#define SYNC_REMOUNT		0x0080  /* remount readonly, no dummy LRs */
-#define SYNC_IOWAIT		0x0100  /* wait for all I/O to complete */
-
-/*
- * When remounting a filesystem read-only or freezing the filesystem,
- * we have two phases to execute. This first phase is syncing the data
- * before we quiesce the fielsystem, and the second is flushing all the
- * inodes out after we've waited for all the transactions created by
- * the first phase to complete. The second phase uses SYNC_INODE_QUIESCE
- * to ensure that the inodes are written to their location on disk
- * rather than just existing in transactions in the log. This means
- * after a quiesce there is no log replay required to write the inodes
- * to disk (this is the main difference between a sync and a quiesce).
- */
-#define SYNC_DATA_QUIESCE	(SYNC_DELWRI|SYNC_FSDATA|SYNC_WAIT|SYNC_IOWAIT)
-#define SYNC_INODE_QUIESCE	(SYNC_REMOUNT|SYNC_ATTR|SYNC_WAIT)
-
-#define SHUTDOWN_META_IO_ERROR	0x0001	/* write attempt to metadata failed */
-#define SHUTDOWN_LOG_IO_ERROR	0x0002	/* write attempt to the log failed */
-#define SHUTDOWN_FORCE_UMOUNT	0x0004	/* shutdown from a forced unmount */
-#define SHUTDOWN_CORRUPT_INCORE	0x0008	/* corrupt in-memory data structures */
-#define SHUTDOWN_REMOTE_REQ	0x0010	/* shutdown came from remote cell */
-#define SHUTDOWN_DEVICE_REQ	0x0020	/* failed all paths to the device */
-
-#define xfs_test_for_freeze(mp)		((mp)->m_super->s_frozen)
-#define xfs_wait_for_freeze(mp,l)	vfs_check_frozen((mp)->m_super, (l))
-
-#endif	/* __XFS_VFS_H__ */
diff --git a/fs/xfs/linux-2.6/xfs_vnode.c b/fs/xfs/linux-2.6/xfs_vnode.c
deleted file mode 100644
index b52528bbbfff..000000000000
--- a/fs/xfs/linux-2.6/xfs_vnode.c
+++ /dev/null
@@ -1,145 +0,0 @@
-/*
- * Copyright (c) 2000-2003,2005 Silicon Graphics, Inc.
- * All Rights Reserved.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it would be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write the Free Software Foundation,
- * Inc.,  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
- */
-#include "xfs.h"
-#include "xfs_vnodeops.h"
-#include "xfs_bmap_btree.h"
-#include "xfs_inode.h"
-
-/*
- * And this gunk is needed for xfs_mount.h"
- */
-#include "xfs_log.h"
-#include "xfs_trans.h"
-#include "xfs_sb.h"
-#include "xfs_dmapi.h"
-#include "xfs_inum.h"
-#include "xfs_ag.h"
-#include "xfs_mount.h"
-
-
-/*
- * Dedicated vnode inactive/reclaim sync wait queues.
- * Prime number of hash buckets since address is used as the key.
- */
-#define NVSYNC                  37
-#define vptosync(v)             (&vsync[((unsigned long)v) % NVSYNC])
-static wait_queue_head_t vsync[NVSYNC];
-
-void __init
-vn_init(void)
-{
-	int i;
-
-	for (i = 0; i < NVSYNC; i++)
-		init_waitqueue_head(&vsync[i]);
-}
-
-void
-vn_iowait(
-	xfs_inode_t	*ip)
-{
-	wait_queue_head_t *wq = vptosync(ip);
-
-	wait_event(*wq, (atomic_read(&ip->i_iocount) == 0));
-}
-
-void
-vn_iowake(
-	xfs_inode_t	*ip)
-{
-	if (atomic_dec_and_test(&ip->i_iocount))
-		wake_up(vptosync(ip));
-}
-
-/*
- * Volume managers supporting multiple paths can send back ENODEV when the
- * final path disappears.  In this case continuing to fill the page cache
- * with dirty data which cannot be written out is evil, so prevent that.
- */
-void
-vn_ioerror(
-	xfs_inode_t	*ip,
-	int		error,
-	char		*f,
-	int		l)
-{
-	if (unlikely(error == -ENODEV))
-		xfs_do_force_shutdown(ip->i_mount, SHUTDOWN_DEVICE_REQ, f, l);
-}
-
-#ifdef	XFS_INODE_TRACE
-
-/*
- * Reference count of Linux inode if present, -1 if the xfs_inode
- * has no associated Linux inode.
- */
-static inline int xfs_icount(struct xfs_inode *ip)
-{
-	struct inode *vp = VFS_I(ip);
-
-	if (vp)
-		return vn_count(vp);
-	return -1;
-}
-
-#define KTRACE_ENTER(ip, vk, s, line, ra)			\
-	ktrace_enter(	(ip)->i_trace,				\
-/*  0 */		(void *)(__psint_t)(vk),		\
-/*  1 */		(void *)(s),				\
-/*  2 */		(void *)(__psint_t) line,		\
-/*  3 */		(void *)(__psint_t)xfs_icount(ip),	\
-/*  4 */		(void *)(ra),				\
-/*  5 */		NULL,					\
-/*  6 */		(void *)(__psint_t)current_cpu(),	\
-/*  7 */		(void *)(__psint_t)current_pid(),	\
-/*  8 */		(void *)__return_address,		\
-/*  9 */		NULL, NULL, NULL, NULL, NULL, NULL, NULL)
-
-/*
- * Vnode tracing code.
- */
-void
-_xfs_itrace_entry(xfs_inode_t *ip, const char *func, inst_t *ra)
-{
-	KTRACE_ENTER(ip, INODE_KTRACE_ENTRY, func, 0, ra);
-}
-
-void
-_xfs_itrace_exit(xfs_inode_t *ip, const char *func, inst_t *ra)
-{
-	KTRACE_ENTER(ip, INODE_KTRACE_EXIT, func, 0, ra);
-}
-
-void
-xfs_itrace_hold(xfs_inode_t *ip, char *file, int line, inst_t *ra)
-{
-	KTRACE_ENTER(ip, INODE_KTRACE_HOLD, file, line, ra);
-}
-
-void
-_xfs_itrace_ref(xfs_inode_t *ip, char *file, int line, inst_t *ra)
-{
-	KTRACE_ENTER(ip, INODE_KTRACE_REF, file, line, ra);
-}
-
-void
-xfs_itrace_rele(xfs_inode_t *ip, char *file, int line, inst_t *ra)
-{
-	KTRACE_ENTER(ip, INODE_KTRACE_RELE, file, line, ra);
-}
-#endif	/* XFS_INODE_TRACE */
diff --git a/fs/xfs/linux-2.6/xfs_vnode.h b/fs/xfs/linux-2.6/xfs_vnode.h
index 683ce16210ff..f65983a230d3 100644
--- a/fs/xfs/linux-2.6/xfs_vnode.h
+++ b/fs/xfs/linux-2.6/xfs_vnode.h
@@ -18,7 +18,10 @@
 #ifndef __XFS_VNODE_H__
 #define __XFS_VNODE_H__
 
+#include "xfs_fs.h"
+
 struct file;
+struct xfs_inode;
 struct xfs_iomap;
 struct attrlist_cursor_kern;
 
@@ -51,40 +54,6 @@ struct attrlist_cursor_kern;
 					   Prevent VM access to the pages until
 					   the operation completes. */
 
-
-extern void	vn_init(void);
-
-/*
- * Yeah, these don't take vnode anymore at all, all this should be
- * cleaned up at some point.
- */
-extern void	vn_iowait(struct xfs_inode *ip);
-extern void	vn_iowake(struct xfs_inode *ip);
-extern void	vn_ioerror(struct xfs_inode *ip, int error, char *f, int l);
-
-static inline int vn_count(struct inode *vp)
-{
-	return atomic_read(&vp->i_count);
-}
-
-#define IHOLD(ip) \
-do { \
-	ASSERT(atomic_read(&VFS_I(ip)->i_count) > 0) ; \
-	atomic_inc(&(VFS_I(ip)->i_count)); \
-	xfs_itrace_hold((ip), __FILE__, __LINE__, (inst_t *)__return_address); \
-} while (0)
-
-#define IRELE(ip) \
-do { \
-	xfs_itrace_rele((ip), __FILE__, __LINE__, (inst_t *)__return_address); \
-	iput(VFS_I(ip)); \
-} while (0)
-
-static inline struct inode *vn_grab(struct inode *vp)
-{
-	return igrab(vp);
-}
-
 /*
  * Dealing with bad inodes
  */
@@ -121,39 +90,4 @@ static inline void vn_atime_to_time_t(struct inode *vp, time_t *tt)
 					PAGECACHE_TAG_DIRTY)
 
 
-/*
- * Tracking vnode activity.
- */
-#if defined(XFS_INODE_TRACE)
-
-#define	INODE_TRACE_SIZE	16		/* number of trace entries */
-#define	INODE_KTRACE_ENTRY	1
-#define	INODE_KTRACE_EXIT	2
-#define	INODE_KTRACE_HOLD	3
-#define	INODE_KTRACE_REF	4
-#define	INODE_KTRACE_RELE	5
-
-extern void _xfs_itrace_entry(struct xfs_inode *, const char *, inst_t *);
-extern void _xfs_itrace_exit(struct xfs_inode *, const char *, inst_t *);
-extern void xfs_itrace_hold(struct xfs_inode *, char *, int, inst_t *);
-extern void _xfs_itrace_ref(struct xfs_inode *, char *, int, inst_t *);
-extern void xfs_itrace_rele(struct xfs_inode *, char *, int, inst_t *);
-#define xfs_itrace_entry(ip)	\
-	_xfs_itrace_entry(ip, __func__, (inst_t *)__return_address)
-#define xfs_itrace_exit(ip)	\
-	_xfs_itrace_exit(ip, __func__, (inst_t *)__return_address)
-#define xfs_itrace_exit_tag(ip, tag)	\
-	_xfs_itrace_exit(ip, tag, (inst_t *)__return_address)
-#define xfs_itrace_ref(ip)	\
-	_xfs_itrace_ref(ip, __FILE__, __LINE__, (inst_t *)__return_address)
-
-#else
-#define	xfs_itrace_entry(a)
-#define	xfs_itrace_exit(a)
-#define	xfs_itrace_exit_tag(a, b)
-#define	xfs_itrace_hold(a, b, c, d)
-#define	xfs_itrace_ref(a)
-#define	xfs_itrace_rele(a, b, c, d)
-#endif
-
 #endif	/* __XFS_VNODE_H__ */
diff --git a/fs/xfs/quota/xfs_dquot.c b/fs/xfs/quota/xfs_dquot.c
index f2705f2fd43c..591ca6602bfb 100644
--- a/fs/xfs/quota/xfs_dquot.c
+++ b/fs/xfs/quota/xfs_dquot.c
@@ -101,7 +101,7 @@ xfs_qm_dqinit(
 	if (brandnewdquot) {
 		dqp->dq_flnext = dqp->dq_flprev = dqp;
 		mutex_init(&dqp->q_qlock);
-		sv_init(&dqp->q_pinwait, SV_DEFAULT, "pdq");
+		init_waitqueue_head(&dqp->q_pinwait);
 
 		/*
 		 * Because we want to use a counting completion, complete
@@ -131,7 +131,7 @@ xfs_qm_dqinit(
 		 dqp->q_res_bcount = 0;
 		 dqp->q_res_icount = 0;
 		 dqp->q_res_rtbcount = 0;
-		 dqp->q_pincount = 0;
+		 atomic_set(&dqp->q_pincount, 0);
 		 dqp->q_hash = NULL;
 		 ASSERT(dqp->dq_flnext == dqp->dq_flprev);
 
@@ -1221,16 +1221,14 @@ xfs_qm_dqflush(
 	xfs_dqtrace_entry(dqp, "DQFLUSH");
 
 	/*
-	 * If not dirty, nada.
+	 * If not dirty, or it's pinned and we are not supposed to
+	 * block, nada.
 	 */
-	if (!XFS_DQ_IS_DIRTY(dqp)) {
+	if (!XFS_DQ_IS_DIRTY(dqp) ||
+	    (!(flags & XFS_QMOPT_SYNC) && atomic_read(&dqp->q_pincount) > 0)) {
 		xfs_dqfunlock(dqp);
-		return (0);
+		return 0;
 	}
-
-	/*
-	 * Cant flush a pinned dquot. Wait for it.
-	 */
 	xfs_qm_dqunpin_wait(dqp);
 
 	/*
@@ -1274,10 +1272,8 @@ xfs_qm_dqflush(
 	dqp->dq_flags &= ~(XFS_DQ_DIRTY);
 	mp = dqp->q_mount;
 
-	/* lsn is 64 bits */
-	spin_lock(&mp->m_ail_lock);
-	dqp->q_logitem.qli_flush_lsn = dqp->q_logitem.qli_item.li_lsn;
-	spin_unlock(&mp->m_ail_lock);
+	xfs_trans_ail_copy_lsn(mp->m_ail, &dqp->q_logitem.qli_flush_lsn,
+					&dqp->q_logitem.qli_item.li_lsn);
 
 	/*
 	 * Attach an iodone routine so that we can remove this dquot from the
@@ -1323,8 +1319,10 @@ xfs_qm_dqflush_done(
 	xfs_dq_logitem_t	*qip)
 {
 	xfs_dquot_t		*dqp;
+	struct xfs_ail		*ailp;
 
 	dqp = qip->qli_dquot;
+	ailp = qip->qli_item.li_ailp;
 
 	/*
 	 * We only want to pull the item from the AIL if its
@@ -1337,15 +1335,12 @@ xfs_qm_dqflush_done(
 	if ((qip->qli_item.li_flags & XFS_LI_IN_AIL) &&
 	    qip->qli_item.li_lsn == qip->qli_flush_lsn) {
 
-		spin_lock(&dqp->q_mount->m_ail_lock);
-		/*
-		 * xfs_trans_delete_ail() drops the AIL lock.
-		 */
+		/* xfs_trans_ail_delete() drops the AIL lock. */
+		spin_lock(&ailp->xa_lock);
 		if (qip->qli_item.li_lsn == qip->qli_flush_lsn)
-			xfs_trans_delete_ail(dqp->q_mount,
-					     (xfs_log_item_t*)qip);
+			xfs_trans_ail_delete(ailp, (xfs_log_item_t*)qip);
 		else
-			spin_unlock(&dqp->q_mount->m_ail_lock);
+			spin_unlock(&ailp->xa_lock);
 	}
 
 	/*
@@ -1375,7 +1370,7 @@ xfs_dqunlock(
 	mutex_unlock(&(dqp->q_qlock));
 	if (dqp->q_logitem.qli_dquot == dqp) {
 		/* Once was dqp->q_mount, but might just have been cleared */
-		xfs_trans_unlocked_item(dqp->q_logitem.qli_item.li_mountp,
+		xfs_trans_unlocked_item(dqp->q_logitem.qli_item.li_ailp,
 					(xfs_log_item_t*)&(dqp->q_logitem));
 	}
 }
@@ -1489,7 +1484,7 @@ xfs_qm_dqpurge(
 				"xfs_qm_dqpurge: dquot %p flush failed", dqp);
 		xfs_dqflock(dqp);
 	}
-	ASSERT(dqp->q_pincount == 0);
+	ASSERT(atomic_read(&dqp->q_pincount) == 0);
 	ASSERT(XFS_FORCED_SHUTDOWN(mp) ||
 	       !(dqp->q_logitem.qli_item.li_flags & XFS_LI_IN_AIL));
 
diff --git a/fs/xfs/quota/xfs_dquot.h b/fs/xfs/quota/xfs_dquot.h
index 8958d0faf8d3..7e455337e2ba 100644
--- a/fs/xfs/quota/xfs_dquot.h
+++ b/fs/xfs/quota/xfs_dquot.h
@@ -83,8 +83,8 @@ typedef struct xfs_dquot {
 	xfs_qcnt_t	 q_res_rtbcount;/* total realtime blks used+reserved */
 	mutex_t		 q_qlock;	/* quota lock */
 	struct completion q_flush;	/* flush completion queue */
-	uint		 q_pincount;	/* pin count for this dquot */
-	sv_t		 q_pinwait;	/* sync var for pinning */
+	atomic_t          q_pincount;	/* dquot pin count */
+	wait_queue_head_t q_pinwait;	/* dquot pinning wait queue */
 #ifdef XFS_DQUOT_TRACE
 	struct ktrace	*q_trace;	/* trace header structure */
 #endif
diff --git a/fs/xfs/quota/xfs_dquot_item.c b/fs/xfs/quota/xfs_dquot_item.c
index f028644caa5e..1728f6a7c4f5 100644
--- a/fs/xfs/quota/xfs_dquot_item.c
+++ b/fs/xfs/quota/xfs_dquot_item.c
@@ -88,25 +88,22 @@ xfs_qm_dquot_logitem_format(
 
 /*
  * Increment the pin count of the given dquot.
- * This value is protected by pinlock spinlock in the xQM structure.
  */
 STATIC void
 xfs_qm_dquot_logitem_pin(
 	xfs_dq_logitem_t *logitem)
 {
-	xfs_dquot_t *dqp;
+	xfs_dquot_t *dqp = logitem->qli_dquot;
 
-	dqp = logitem->qli_dquot;
 	ASSERT(XFS_DQ_IS_LOCKED(dqp));
-	spin_lock(&(XFS_DQ_TO_QINF(dqp)->qi_pinlock));
-	dqp->q_pincount++;
-	spin_unlock(&(XFS_DQ_TO_QINF(dqp)->qi_pinlock));
+	atomic_inc(&dqp->q_pincount);
 }
 
 /*
  * Decrement the pin count of the given dquot, and wake up
  * anyone in xfs_dqwait_unpin() if the count goes to 0.	 The
- * dquot must have been previously pinned with a call to xfs_dqpin().
+ * dquot must have been previously pinned with a call to
+ * xfs_qm_dquot_logitem_pin().
  */
 /* ARGSUSED */
 STATIC void
@@ -114,16 +111,11 @@ xfs_qm_dquot_logitem_unpin(
 	xfs_dq_logitem_t *logitem,
 	int		  stale)
 {
-	xfs_dquot_t *dqp;
+	xfs_dquot_t *dqp = logitem->qli_dquot;
 
-	dqp = logitem->qli_dquot;
-	ASSERT(dqp->q_pincount > 0);
-	spin_lock(&(XFS_DQ_TO_QINF(dqp)->qi_pinlock));
-	dqp->q_pincount--;
-	if (dqp->q_pincount == 0) {
-		sv_broadcast(&dqp->q_pinwait);
-	}
-	spin_unlock(&(XFS_DQ_TO_QINF(dqp)->qi_pinlock));
+	ASSERT(atomic_read(&dqp->q_pincount) > 0);
+	if (atomic_dec_and_test(&dqp->q_pincount))
+		wake_up(&dqp->q_pinwait);
 }
 
 /* ARGSUSED */
@@ -193,21 +185,14 @@ xfs_qm_dqunpin_wait(
 	xfs_dquot_t	*dqp)
 {
 	ASSERT(XFS_DQ_IS_LOCKED(dqp));
-	if (dqp->q_pincount == 0) {
+	if (atomic_read(&dqp->q_pincount) == 0)
 		return;
-	}
 
 	/*
 	 * Give the log a push so we don't wait here too long.
 	 */
 	xfs_log_force(dqp->q_mount, (xfs_lsn_t)0, XFS_LOG_FORCE);
-	spin_lock(&(XFS_DQ_TO_QINF(dqp)->qi_pinlock));
-	if (dqp->q_pincount == 0) {
-		spin_unlock(&(XFS_DQ_TO_QINF(dqp)->qi_pinlock));
-		return;
-	}
-	sv_wait(&(dqp->q_pinwait), PINOD,
-		&(XFS_DQ_TO_QINF(dqp)->qi_pinlock), s);
+	wait_event(dqp->q_pinwait, (atomic_read(&dqp->q_pincount) == 0));
 }
 
 /*
@@ -310,7 +295,7 @@ xfs_qm_dquot_logitem_trylock(
 	uint			retval;
 
 	dqp = qip->qli_dquot;
-	if (dqp->q_pincount > 0)
+	if (atomic_read(&dqp->q_pincount) > 0)
 		return (XFS_ITEM_PINNED);
 
 	if (! xfs_qm_dqlock_nowait(dqp))
@@ -568,14 +553,16 @@ xfs_qm_qoffend_logitem_committed(
 	xfs_lsn_t lsn)
 {
 	xfs_qoff_logitem_t	*qfs;
+	struct xfs_ail		*ailp;
 
 	qfs = qfe->qql_start_lip;
-	spin_lock(&qfs->qql_item.li_mountp->m_ail_lock);
+	ailp = qfs->qql_item.li_ailp;
+	spin_lock(&ailp->xa_lock);
 	/*
 	 * Delete the qoff-start logitem from the AIL.
-	 * xfs_trans_delete_ail() drops the AIL lock.
+	 * xfs_trans_ail_delete() drops the AIL lock.
 	 */
-	xfs_trans_delete_ail(qfs->qql_item.li_mountp, (xfs_log_item_t *)qfs);
+	xfs_trans_ail_delete(ailp, (xfs_log_item_t *)qfs);
 	kmem_free(qfs);
 	kmem_free(qfe);
 	return (xfs_lsn_t)-1;
diff --git a/fs/xfs/quota/xfs_qm.c b/fs/xfs/quota/xfs_qm.c
index df0ffef9775a..6b13960cf318 100644
--- a/fs/xfs/quota/xfs_qm.c
+++ b/fs/xfs/quota/xfs_qm.c
@@ -20,7 +20,6 @@
 #include "xfs_bit.h"
 #include "xfs_log.h"
 #include "xfs_inum.h"
-#include "xfs_clnt.h"
 #include "xfs_trans.h"
 #include "xfs_sb.h"
 #include "xfs_ag.h"
@@ -396,13 +395,10 @@ xfs_qm_mount_quotas(
 /*
  * Called from the vfsops layer.
  */
-int
+void
 xfs_qm_unmount_quotas(
 	xfs_mount_t	*mp)
 {
-	xfs_inode_t	*uqp, *gqp;
-	int		error = 0;
-
 	/*
 	 * Release the dquots that root inode, et al might be holding,
 	 * before we flush quotas and blow away the quotainfo structure.
@@ -415,43 +411,18 @@ xfs_qm_unmount_quotas(
 		xfs_qm_dqdetach(mp->m_rsumip);
 
 	/*
-	 * Flush out the quota inodes.
+	 * Release the quota inodes.
 	 */
-	uqp = gqp = NULL;
 	if (mp->m_quotainfo) {
-		if ((uqp = mp->m_quotainfo->qi_uquotaip) != NULL) {
-			xfs_ilock(uqp, XFS_ILOCK_EXCL);
-			xfs_iflock(uqp);
-			error = xfs_iflush(uqp, XFS_IFLUSH_SYNC);
-			xfs_iunlock(uqp, XFS_ILOCK_EXCL);
-			if (unlikely(error == EFSCORRUPTED)) {
-				XFS_ERROR_REPORT("xfs_qm_unmount_quotas(1)",
-						 XFS_ERRLEVEL_LOW, mp);
-				goto out;
-			}
+		if (mp->m_quotainfo->qi_uquotaip) {
+			IRELE(mp->m_quotainfo->qi_uquotaip);
+			mp->m_quotainfo->qi_uquotaip = NULL;
 		}
-		if ((gqp = mp->m_quotainfo->qi_gquotaip) != NULL) {
-			xfs_ilock(gqp, XFS_ILOCK_EXCL);
-			xfs_iflock(gqp);
-			error = xfs_iflush(gqp, XFS_IFLUSH_SYNC);
-			xfs_iunlock(gqp, XFS_ILOCK_EXCL);
-			if (unlikely(error == EFSCORRUPTED)) {
-				XFS_ERROR_REPORT("xfs_qm_unmount_quotas(2)",
-						 XFS_ERRLEVEL_LOW, mp);
-				goto out;
-			}
+		if (mp->m_quotainfo->qi_gquotaip) {
+			IRELE(mp->m_quotainfo->qi_gquotaip);
+			mp->m_quotainfo->qi_gquotaip = NULL;
 		}
 	}
-	if (uqp) {
-		 IRELE(uqp);
-		 mp->m_quotainfo->qi_uquotaip = NULL;
-	}
-	if (gqp) {
-		IRELE(gqp);
-		mp->m_quotainfo->qi_gquotaip = NULL;
-	}
-out:
-	return XFS_ERROR(error);
 }
 
 /*
@@ -987,14 +958,10 @@ xfs_qm_dqdetach(
 }
 
 /*
- * This is called by VFS_SYNC and flags arg determines the caller,
- * and its motives, as done in xfs_sync.
- *
- * vfs_sync: SYNC_FSDATA|SYNC_ATTR|SYNC_BDFLUSH 0x31
- * syscall sync: SYNC_FSDATA|SYNC_ATTR|SYNC_DELWRI 0x25
- * umountroot : SYNC_WAIT | SYNC_CLOSE | SYNC_ATTR | SYNC_FSDATA
+ * This is called to sync quotas. We can be told to use non-blocking
+ * semantics by either the SYNC_BDFLUSH flag or the absence of the
+ * SYNC_WAIT flag.
  */
-
 int
 xfs_qm_sync(
 	xfs_mount_t	*mp,
@@ -1137,7 +1104,6 @@ xfs_qm_init_quotainfo(
 		return error;
 	}
 
-	spin_lock_init(&qinf->qi_pinlock);
 	xfs_qm_list_init(&qinf->qi_dqlist, "mpdqlist", 0);
 	qinf->qi_dqreclaims = 0;
 
@@ -1234,7 +1200,6 @@ xfs_qm_destroy_quotainfo(
 	 */
 	xfs_qm_rele_quotafs_ref(mp);
 
-	spinlock_destroy(&qi->qi_pinlock);
 	xfs_qm_list_destroy(&qi->qi_dqlist);
 
 	if (qi->qi_uquotaip) {
diff --git a/fs/xfs/quota/xfs_qm.h b/fs/xfs/quota/xfs_qm.h
index 44f25349e478..ddf09166387c 100644
--- a/fs/xfs/quota/xfs_qm.h
+++ b/fs/xfs/quota/xfs_qm.h
@@ -106,7 +106,6 @@ typedef struct xfs_qm {
 typedef struct xfs_quotainfo {
 	xfs_inode_t	*qi_uquotaip;	 /* user quota inode */
 	xfs_inode_t	*qi_gquotaip;	 /* group quota inode */
-	spinlock_t	 qi_pinlock;	 /* dquot pinning lock */
 	xfs_dqlist_t	 qi_dqlist;	 /* all dquots in filesys */
 	int		 qi_dqreclaims;	 /* a change here indicates
 					    a removal in the dqlist */
@@ -168,7 +167,7 @@ extern void		xfs_qm_destroy_quotainfo(xfs_mount_t *);
 extern void		xfs_qm_mount_quotas(xfs_mount_t *);
 extern int		xfs_qm_quotacheck(xfs_mount_t *);
 extern void		xfs_qm_unmount_quotadestroy(xfs_mount_t *);
-extern int		xfs_qm_unmount_quotas(xfs_mount_t *);
+extern void		xfs_qm_unmount_quotas(xfs_mount_t *);
 extern int		xfs_qm_write_sb_changes(xfs_mount_t *, __int64_t);
 extern int		xfs_qm_sync(xfs_mount_t *, int);
 
diff --git a/fs/xfs/quota/xfs_qm_bhv.c b/fs/xfs/quota/xfs_qm_bhv.c
index eea2e60b456b..bc6c5cca3e12 100644
--- a/fs/xfs/quota/xfs_qm_bhv.c
+++ b/fs/xfs/quota/xfs_qm_bhv.c
@@ -20,7 +20,6 @@
 #include "xfs_bit.h"
 #include "xfs_log.h"
 #include "xfs_inum.h"
-#include "xfs_clnt.h"
 #include "xfs_trans.h"
 #include "xfs_sb.h"
 #include "xfs_ag.h"
@@ -51,7 +50,7 @@
 
 STATIC void
 xfs_fill_statvfs_from_dquot(
-	bhv_statvfs_t		*statp,
+	struct kstatfs		*statp,
 	xfs_disk_dquot_t	*dp)
 {
 	__uint64_t		limit;
@@ -88,7 +87,7 @@ xfs_fill_statvfs_from_dquot(
 STATIC void
 xfs_qm_statvfs(
 	xfs_inode_t		*ip,
-	bhv_statvfs_t		*statp)
+	struct kstatfs		*statp)
 {
 	xfs_mount_t		*mp = ip->i_mount;
 	xfs_dquot_t		*dqp;
diff --git a/fs/xfs/quota/xfs_qm_syscalls.c b/fs/xfs/quota/xfs_qm_syscalls.c
index 1a3b803dfa55..68139b38aede 100644
--- a/fs/xfs/quota/xfs_qm_syscalls.c
+++ b/fs/xfs/quota/xfs_qm_syscalls.c
@@ -127,7 +127,7 @@ xfs_qm_quotactl(
 		break;
 
 	case Q_XQUOTASYNC:
-		return (xfs_sync_inodes(mp, SYNC_DELWRI, NULL));
+		return xfs_sync_inodes(mp, SYNC_DELWRI);
 
 	default:
 		break;
@@ -1022,101 +1022,104 @@ xfs_qm_export_flags(
 
 
 /*
- * Go thru all the inodes in the file system, releasing their dquots.
- * Note that the mount structure gets modified to indicate that quotas are off
- * AFTER this, in the case of quotaoff. This also gets called from
- * xfs_rootumount.
+ * Release all the dquots on the inodes in an AG.
  */
-void
-xfs_qm_dqrele_all_inodes(
-	struct xfs_mount *mp,
-	uint		 flags)
+STATIC void
+xfs_qm_dqrele_inodes_ag(
+	xfs_mount_t	*mp,
+	int		ag,
+	uint		flags)
 {
-	xfs_inode_t	*ip, *topino;
-	uint		ireclaims;
-	struct inode	*vp;
-	boolean_t	vnode_refd;
+	xfs_inode_t	*ip = NULL;
+	xfs_perag_t	*pag = &mp->m_perag[ag];
+	int		first_index = 0;
+	int		nr_found;
 
-	ASSERT(mp->m_quotainfo);
-
-	XFS_MOUNT_ILOCK(mp);
-again:
-	ip = mp->m_inodes;
-	if (ip == NULL) {
-		XFS_MOUNT_IUNLOCK(mp);
-		return;
-	}
 	do {
-		/* Skip markers inserted by xfs_sync */
-		if (ip->i_mount == NULL) {
-			ip = ip->i_mnext;
-			continue;
+		/*
+		 * use a gang lookup to find the next inode in the tree
+		 * as the tree is sparse and a gang lookup walks to find
+		 * the number of objects requested.
+		 */
+		read_lock(&pag->pag_ici_lock);
+		nr_found = radix_tree_gang_lookup(&pag->pag_ici_root,
+				(void**)&ip, first_index, 1);
+
+		if (!nr_found) {
+			read_unlock(&pag->pag_ici_lock);
+			break;
 		}
-		/* Root inode, rbmip and rsumip have associated blocks */
+
+		/*
+		 * Update the index for the next lookup. Catch overflows
+		 * into the next AG range which can occur if we have inodes
+		 * in the last block of the AG and we are currently
+		 * pointing to the last inode.
+		 */
+		first_index = XFS_INO_TO_AGINO(mp, ip->i_ino + 1);
+		if (first_index < XFS_INO_TO_AGINO(mp, ip->i_ino)) {
+			read_unlock(&pag->pag_ici_lock);
+			break;
+		}
+
+		/* skip quota inodes */
 		if (ip == XFS_QI_UQIP(mp) || ip == XFS_QI_GQIP(mp)) {
 			ASSERT(ip->i_udquot == NULL);
 			ASSERT(ip->i_gdquot == NULL);
-			ip = ip->i_mnext;
+			read_unlock(&pag->pag_ici_lock);
 			continue;
 		}
-		vp = VFS_I(ip);
-		if (!vp) {
-			ASSERT(ip->i_udquot == NULL);
-			ASSERT(ip->i_gdquot == NULL);
-			ip = ip->i_mnext;
+
+		/*
+		 * If we can't get a reference on the inode, it must be
+		 * in reclaim. Leave it for the reclaim code to flush.
+		 */
+		if (!igrab(VFS_I(ip))) {
+			read_unlock(&pag->pag_ici_lock);
 			continue;
 		}
-		vnode_refd = B_FALSE;
-		if (xfs_ilock_nowait(ip, XFS_ILOCK_EXCL) == 0) {
-			ireclaims = mp->m_ireclaims;
-			topino = mp->m_inodes;
-			vp = vn_grab(vp);
-			if (!vp)
-				goto again;
-
-			XFS_MOUNT_IUNLOCK(mp);
-			/* XXX restart limit ? */
-			xfs_ilock(ip, XFS_ILOCK_EXCL);
-			vnode_refd = B_TRUE;
-		} else {
-			ireclaims = mp->m_ireclaims;
-			topino = mp->m_inodes;
-			XFS_MOUNT_IUNLOCK(mp);
+		read_unlock(&pag->pag_ici_lock);
+
+		/* avoid new inodes though we shouldn't find any here */
+		if (xfs_iflags_test(ip, XFS_INEW)) {
+			IRELE(ip);
+			continue;
 		}
 
-		/*
-		 * We don't keep the mountlock across the dqrele() call,
-		 * since it can take a while..
-		 */
+		xfs_ilock(ip, XFS_ILOCK_EXCL);
 		if ((flags & XFS_UQUOTA_ACCT) && ip->i_udquot) {
 			xfs_qm_dqrele(ip->i_udquot);
 			ip->i_udquot = NULL;
 		}
-		if (flags & (XFS_PQUOTA_ACCT|XFS_GQUOTA_ACCT) && ip->i_gdquot) {
+		if (flags & (XFS_PQUOTA_ACCT|XFS_GQUOTA_ACCT) &&
+		    ip->i_gdquot) {
 			xfs_qm_dqrele(ip->i_gdquot);
 			ip->i_gdquot = NULL;
 		}
-		xfs_iunlock(ip, XFS_ILOCK_EXCL);
-		/*
-		 * Wait until we've dropped the ilock and mountlock to
-		 * do the vn_rele. Or be condemned to an eternity in the
-		 * inactive code in hell.
-		 */
-		if (vnode_refd)
-			IRELE(ip);
-		XFS_MOUNT_ILOCK(mp);
-		/*
-		 * If an inode was inserted or removed, we gotta
-		 * start over again.
-		 */
-		if (topino != mp->m_inodes || mp->m_ireclaims != ireclaims) {
-			/* XXX use a sentinel */
-			goto again;
-		}
-		ip = ip->i_mnext;
-	} while (ip != mp->m_inodes);
+		xfs_iput(ip, XFS_ILOCK_EXCL);
+
+	} while (nr_found);
+}
+
+/*
+ * Go thru all the inodes in the file system, releasing their dquots.
+ * Note that the mount structure gets modified to indicate that quotas are off
+ * AFTER this, in the case of quotaoff. This also gets called from
+ * xfs_rootumount.
+ */
+void
+xfs_qm_dqrele_all_inodes(
+	struct xfs_mount *mp,
+	uint		 flags)
+{
+	int		i;
 
-	XFS_MOUNT_IUNLOCK(mp);
+	ASSERT(mp->m_quotainfo);
+	for (i = 0; i < mp->m_sb.sb_agcount; i++) {
+		if (!mp->m_perag[i].pag_ici_init)
+			continue;
+		xfs_qm_dqrele_inodes_ag(mp, i, flags);
+	}
 }
 
 /*------------------------------------------------------------------------*/
diff --git a/fs/xfs/support/debug.c b/fs/xfs/support/debug.c
index c27abef7b84f..636104254cfd 100644
--- a/fs/xfs/support/debug.c
+++ b/fs/xfs/support/debug.c
@@ -84,5 +84,5 @@ assfail(char *expr, char *file, int line)
 void
 xfs_hex_dump(void *p, int length)
 {
-	print_hex_dump(KERN_ALERT, "", DUMP_PREFIX_OFFSET, 16, 1, p, length, 1);
+	print_hex_dump(KERN_ALERT, "", DUMP_PREFIX_ADDRESS, 16, 1, p, length, 1);
 }
diff --git a/fs/xfs/support/ktrace.c b/fs/xfs/support/ktrace.c
index a34ef05489b1..2d494c26717f 100644
--- a/fs/xfs/support/ktrace.c
+++ b/fs/xfs/support/ktrace.c
@@ -113,21 +113,16 @@ ktrace_alloc(int nentries, unsigned int __nocast sleep)
 void
 ktrace_free(ktrace_t *ktp)
 {
-	int     entries_size;
-
 	if (ktp == (ktrace_t *)NULL)
 		return;
 
 	/*
 	 * Special treatment for the Vnode trace buffer.
 	 */
-	if (ktp->kt_nentries == ktrace_zentries) {
+	if (ktp->kt_nentries == ktrace_zentries)
 		kmem_zone_free(ktrace_ent_zone, ktp->kt_entries);
-	} else {
-		entries_size = (int)(ktp->kt_nentries * sizeof(ktrace_entry_t));
-
+	else
 		kmem_free(ktp->kt_entries);
-	}
 
 	kmem_zone_free(ktrace_hdr_zone, ktp);
 }
diff --git a/fs/xfs/xfs.h b/fs/xfs/xfs.h
index 540e4c989825..17254b529c54 100644
--- a/fs/xfs/xfs.h
+++ b/fs/xfs/xfs.h
@@ -30,7 +30,7 @@
 #define XFS_ATTR_TRACE 1
 #define XFS_BLI_TRACE 1
 #define XFS_BMAP_TRACE 1
-#define XFS_BMBT_TRACE 1
+#define XFS_BTREE_TRACE 1
 #define XFS_DIR2_TRACE 1
 #define XFS_DQUOT_TRACE 1
 #define XFS_ILOCK_TRACE 1
diff --git a/fs/xfs/xfs_acl.c b/fs/xfs/xfs_acl.c
index b2f639a1416f..a8cdd73999a4 100644
--- a/fs/xfs/xfs_acl.c
+++ b/fs/xfs/xfs_acl.c
@@ -366,7 +366,7 @@ xfs_acl_allow_set(
 		return ENOTDIR;
 	if (vp->i_sb->s_flags & MS_RDONLY)
 		return EROFS;
-	if (XFS_I(vp)->i_d.di_uid != current->fsuid && !capable(CAP_FOWNER))
+	if (XFS_I(vp)->i_d.di_uid != current_fsuid() && !capable(CAP_FOWNER))
 		return EPERM;
 	return 0;
 }
@@ -413,13 +413,13 @@ xfs_acl_access(
 		switch (fap->acl_entry[i].ae_tag) {
 		case ACL_USER_OBJ:
 			seen_userobj = 1;
-			if (fuid != current->fsuid)
+			if (fuid != current_fsuid())
 				continue;
 			matched.ae_tag = ACL_USER_OBJ;
 			matched.ae_perm = allows;
 			break;
 		case ACL_USER:
-			if (fap->acl_entry[i].ae_id != current->fsuid)
+			if (fap->acl_entry[i].ae_id != current_fsuid())
 				continue;
 			matched.ae_tag = ACL_USER;
 			matched.ae_perm = allows;
@@ -758,7 +758,7 @@ xfs_acl_setmode(
 	if (gap && nomask)
 		iattr.ia_mode |= gap->ae_perm << 3;
 
-	return xfs_setattr(XFS_I(vp), &iattr, 0, sys_cred);
+	return xfs_setattr(XFS_I(vp), &iattr, 0);
 }
 
 /*
diff --git a/fs/xfs/xfs_ag.h b/fs/xfs/xfs_ag.h
index 61b292a9fb41..f2e21817a226 100644
--- a/fs/xfs/xfs_ag.h
+++ b/fs/xfs/xfs_ag.h
@@ -91,6 +91,8 @@ typedef struct xfs_agf {
 #define	XFS_AGF_BLOCK(mp)	XFS_HDR_BLOCK(mp, XFS_AGF_DADDR(mp))
 #define	XFS_BUF_TO_AGF(bp)	((xfs_agf_t *)XFS_BUF_PTR(bp))
 
+extern int xfs_read_agf(struct xfs_mount *mp, struct xfs_trans *tp,
+			xfs_agnumber_t agno, int flags, struct xfs_buf **bpp);
 
 /*
  * Size of the unlinked inode hash table in the agi.
@@ -142,6 +144,9 @@ typedef struct xfs_agi {
 #define	XFS_AGI_BLOCK(mp)	XFS_HDR_BLOCK(mp, XFS_AGI_DADDR(mp))
 #define	XFS_BUF_TO_AGI(bp)	((xfs_agi_t *)XFS_BUF_PTR(bp))
 
+extern int xfs_read_agi(struct xfs_mount *mp, struct xfs_trans *tp,
+				xfs_agnumber_t agno, struct xfs_buf **bpp);
+
 /*
  * The third a.g. block contains the a.g. freelist, an array
  * of block pointers to blocks owned by the allocation btree code.
@@ -192,17 +197,23 @@ typedef struct xfs_perag
 	xfs_agino_t	pagi_freecount;	/* number of free inodes */
 	xfs_agino_t	pagi_count;	/* number of allocated inodes */
 	int		pagb_count;	/* pagb slots in use */
+	xfs_perag_busy_t *pagb_list;	/* unstable blocks */
 #ifdef __KERNEL__
 	spinlock_t	pagb_lock;	/* lock for pagb_list */
-#endif
-	xfs_perag_busy_t *pagb_list;	/* unstable blocks */
+
 	atomic_t        pagf_fstrms;    /* # of filestreams active in this AG */
 
 	int		pag_ici_init;	/* incore inode cache initialised */
 	rwlock_t	pag_ici_lock;	/* incore inode lock */
 	struct radix_tree_root pag_ici_root;	/* incore inode cache root */
+#endif
 } xfs_perag_t;
 
+/*
+ * tags for inode radix tree
+ */
+#define XFS_ICI_RECLAIM_TAG	0	/* inode is to be reclaimed */
+
 #define	XFS_AG_MAXLEVELS(mp)		((mp)->m_ag_maxlevels)
 #define	XFS_MIN_FREELIST_RAW(bl,cl,mp)	\
 	(MIN(bl + 1, XFS_AG_MAXLEVELS(mp)) + MIN(cl + 1, XFS_AG_MAXLEVELS(mp)))
diff --git a/fs/xfs/xfs_alloc.c b/fs/xfs/xfs_alloc.c
index 1956f83489f1..028e44e58ea9 100644
--- a/fs/xfs/xfs_alloc.c
+++ b/fs/xfs/xfs_alloc.c
@@ -90,6 +90,92 @@ STATIC int xfs_alloc_ag_vextent_small(xfs_alloc_arg_t *,
  */
 
 /*
+ * Lookup the record equal to [bno, len] in the btree given by cur.
+ */
+STATIC int				/* error */
+xfs_alloc_lookup_eq(
+	struct xfs_btree_cur	*cur,	/* btree cursor */
+	xfs_agblock_t		bno,	/* starting block of extent */
+	xfs_extlen_t		len,	/* length of extent */
+	int			*stat)	/* success/failure */
+{
+	cur->bc_rec.a.ar_startblock = bno;
+	cur->bc_rec.a.ar_blockcount = len;
+	return xfs_btree_lookup(cur, XFS_LOOKUP_EQ, stat);
+}
+
+/*
+ * Lookup the first record greater than or equal to [bno, len]
+ * in the btree given by cur.
+ */
+STATIC int				/* error */
+xfs_alloc_lookup_ge(
+	struct xfs_btree_cur	*cur,	/* btree cursor */
+	xfs_agblock_t		bno,	/* starting block of extent */
+	xfs_extlen_t		len,	/* length of extent */
+	int			*stat)	/* success/failure */
+{
+	cur->bc_rec.a.ar_startblock = bno;
+	cur->bc_rec.a.ar_blockcount = len;
+	return xfs_btree_lookup(cur, XFS_LOOKUP_GE, stat);
+}
+
+/*
+ * Lookup the first record less than or equal to [bno, len]
+ * in the btree given by cur.
+ */
+STATIC int				/* error */
+xfs_alloc_lookup_le(
+	struct xfs_btree_cur	*cur,	/* btree cursor */
+	xfs_agblock_t		bno,	/* starting block of extent */
+	xfs_extlen_t		len,	/* length of extent */
+	int			*stat)	/* success/failure */
+{
+	cur->bc_rec.a.ar_startblock = bno;
+	cur->bc_rec.a.ar_blockcount = len;
+	return xfs_btree_lookup(cur, XFS_LOOKUP_LE, stat);
+}
+
+/*
+ * Update the record referred to by cur to the value given
+ * by [bno, len].
+ * This either works (return 0) or gets an EFSCORRUPTED error.
+ */
+STATIC int				/* error */
+xfs_alloc_update(
+	struct xfs_btree_cur	*cur,	/* btree cursor */
+	xfs_agblock_t		bno,	/* starting block of extent */
+	xfs_extlen_t		len)	/* length of extent */
+{
+	union xfs_btree_rec	rec;
+
+	rec.alloc.ar_startblock = cpu_to_be32(bno);
+	rec.alloc.ar_blockcount = cpu_to_be32(len);
+	return xfs_btree_update(cur, &rec);
+}
+
+/*
+ * Get the data from the pointed-to record.
+ */
+STATIC int				/* error */
+xfs_alloc_get_rec(
+	struct xfs_btree_cur	*cur,	/* btree cursor */
+	xfs_agblock_t		*bno,	/* output: starting block of extent */
+	xfs_extlen_t		*len,	/* output: length of extent */
+	int			*stat)	/* output: success/failure */
+{
+	union xfs_btree_rec	*rec;
+	int			error;
+
+	error = xfs_btree_get_rec(cur, &rec, stat);
+	if (!error && *stat == 1) {
+		*bno = be32_to_cpu(rec->alloc.ar_startblock);
+		*len = be32_to_cpu(rec->alloc.ar_blockcount);
+	}
+	return error;
+}
+
+/*
  * Compute aligned version of the found extent.
  * Takes alignment and min length into account.
  */
@@ -294,21 +380,20 @@ xfs_alloc_fixup_trees(
 			return error;
 		XFS_WANT_CORRUPTED_RETURN(i == 1);
 	}
+
 #ifdef DEBUG
-	{
-		xfs_alloc_block_t	*bnoblock;
-		xfs_alloc_block_t	*cntblock;
-
-		if (bno_cur->bc_nlevels == 1 &&
-		    cnt_cur->bc_nlevels == 1) {
-			bnoblock = XFS_BUF_TO_ALLOC_BLOCK(bno_cur->bc_bufs[0]);
-			cntblock = XFS_BUF_TO_ALLOC_BLOCK(cnt_cur->bc_bufs[0]);
-			XFS_WANT_CORRUPTED_RETURN(
-				be16_to_cpu(bnoblock->bb_numrecs) ==
-				be16_to_cpu(cntblock->bb_numrecs));
-		}
+	if (bno_cur->bc_nlevels == 1 && cnt_cur->bc_nlevels == 1) {
+		struct xfs_btree_block	*bnoblock;
+		struct xfs_btree_block	*cntblock;
+
+		bnoblock = XFS_BUF_TO_BLOCK(bno_cur->bc_bufs[0]);
+		cntblock = XFS_BUF_TO_BLOCK(cnt_cur->bc_bufs[0]);
+
+		XFS_WANT_CORRUPTED_RETURN(
+			bnoblock->bb_numrecs == cntblock->bb_numrecs);
 	}
 #endif
+
 	/*
 	 * Deal with all four cases: the allocated record is contained
 	 * within the freespace record, so we can have new freespace
@@ -333,7 +418,7 @@ xfs_alloc_fixup_trees(
 	/*
 	 * Delete the entry from the by-size btree.
 	 */
-	if ((error = xfs_alloc_delete(cnt_cur, &i)))
+	if ((error = xfs_btree_delete(cnt_cur, &i)))
 		return error;
 	XFS_WANT_CORRUPTED_RETURN(i == 1);
 	/*
@@ -343,7 +428,7 @@ xfs_alloc_fixup_trees(
 		if ((error = xfs_alloc_lookup_eq(cnt_cur, nfbno1, nflen1, &i)))
 			return error;
 		XFS_WANT_CORRUPTED_RETURN(i == 0);
-		if ((error = xfs_alloc_insert(cnt_cur, &i)))
+		if ((error = xfs_btree_insert(cnt_cur, &i)))
 			return error;
 		XFS_WANT_CORRUPTED_RETURN(i == 1);
 	}
@@ -351,7 +436,7 @@ xfs_alloc_fixup_trees(
 		if ((error = xfs_alloc_lookup_eq(cnt_cur, nfbno2, nflen2, &i)))
 			return error;
 		XFS_WANT_CORRUPTED_RETURN(i == 0);
-		if ((error = xfs_alloc_insert(cnt_cur, &i)))
+		if ((error = xfs_btree_insert(cnt_cur, &i)))
 			return error;
 		XFS_WANT_CORRUPTED_RETURN(i == 1);
 	}
@@ -362,7 +447,7 @@ xfs_alloc_fixup_trees(
 		/*
 		 * No remaining freespace, just delete the by-block tree entry.
 		 */
-		if ((error = xfs_alloc_delete(bno_cur, &i)))
+		if ((error = xfs_btree_delete(bno_cur, &i)))
 			return error;
 		XFS_WANT_CORRUPTED_RETURN(i == 1);
 	} else {
@@ -379,7 +464,7 @@ xfs_alloc_fixup_trees(
 		if ((error = xfs_alloc_lookup_eq(bno_cur, nfbno2, nflen2, &i)))
 			return error;
 		XFS_WANT_CORRUPTED_RETURN(i == 0);
-		if ((error = xfs_alloc_insert(bno_cur, &i)))
+		if ((error = xfs_btree_insert(bno_cur, &i)))
 			return error;
 		XFS_WANT_CORRUPTED_RETURN(i == 1);
 	}
@@ -640,8 +725,8 @@ xfs_alloc_ag_vextent_exact(
 	/*
 	 * Allocate/initialize a cursor for the by-number freespace btree.
 	 */
-	bno_cur = xfs_btree_init_cursor(args->mp, args->tp, args->agbp,
-		args->agno, XFS_BTNUM_BNO, NULL, 0);
+	bno_cur = xfs_allocbt_init_cursor(args->mp, args->tp, args->agbp,
+		args->agno, XFS_BTNUM_BNO);
 	/*
 	 * Lookup bno and minlen in the btree (minlen is irrelevant, really).
 	 * Look for the closest free block <= bno, it must contain bno
@@ -696,8 +781,8 @@ xfs_alloc_ag_vextent_exact(
 	 * We are allocating agbno for rlen [agbno .. end]
 	 * Allocate/initialize a cursor for the by-size btree.
 	 */
-	cnt_cur = xfs_btree_init_cursor(args->mp, args->tp, args->agbp,
-		args->agno, XFS_BTNUM_CNT, NULL, 0);
+	cnt_cur = xfs_allocbt_init_cursor(args->mp, args->tp, args->agbp,
+		args->agno, XFS_BTNUM_CNT);
 	ASSERT(args->agbno + args->len <=
 		be32_to_cpu(XFS_BUF_TO_AGF(args->agbp)->agf_length));
 	if ((error = xfs_alloc_fixup_trees(cnt_cur, bno_cur, fbno, flen,
@@ -759,8 +844,8 @@ xfs_alloc_ag_vextent_near(
 	/*
 	 * Get a cursor for the by-size btree.
 	 */
-	cnt_cur = xfs_btree_init_cursor(args->mp, args->tp, args->agbp,
-		args->agno, XFS_BTNUM_CNT, NULL, 0);
+	cnt_cur = xfs_allocbt_init_cursor(args->mp, args->tp, args->agbp,
+		args->agno, XFS_BTNUM_CNT);
 	ltlen = 0;
 	bno_cur_lt = bno_cur_gt = NULL;
 	/*
@@ -818,7 +903,7 @@ xfs_alloc_ag_vextent_near(
 				XFS_WANT_CORRUPTED_GOTO(i == 1, error0);
 				if (ltlen >= args->minlen)
 					break;
-				if ((error = xfs_alloc_increment(cnt_cur, 0, &i)))
+				if ((error = xfs_btree_increment(cnt_cur, 0, &i)))
 					goto error0;
 			} while (i);
 			ASSERT(ltlen >= args->minlen);
@@ -828,7 +913,7 @@ xfs_alloc_ag_vextent_near(
 		i = cnt_cur->bc_ptrs[0];
 		for (j = 1, blen = 0, bdiff = 0;
 		     !error && j && (blen < args->maxlen || bdiff > 0);
-		     error = xfs_alloc_increment(cnt_cur, 0, &j)) {
+		     error = xfs_btree_increment(cnt_cur, 0, &j)) {
 			/*
 			 * For each entry, decide if it's better than
 			 * the previous best entry.
@@ -886,8 +971,8 @@ xfs_alloc_ag_vextent_near(
 		/*
 		 * Set up a cursor for the by-bno tree.
 		 */
-		bno_cur_lt = xfs_btree_init_cursor(args->mp, args->tp,
-			args->agbp, args->agno, XFS_BTNUM_BNO, NULL, 0);
+		bno_cur_lt = xfs_allocbt_init_cursor(args->mp, args->tp,
+			args->agbp, args->agno, XFS_BTNUM_BNO);
 		/*
 		 * Fix up the btree entries.
 		 */
@@ -914,8 +999,8 @@ xfs_alloc_ag_vextent_near(
 	/*
 	 * Allocate and initialize the cursor for the leftward search.
 	 */
-	bno_cur_lt = xfs_btree_init_cursor(args->mp, args->tp, args->agbp,
-		args->agno, XFS_BTNUM_BNO, NULL, 0);
+	bno_cur_lt = xfs_allocbt_init_cursor(args->mp, args->tp, args->agbp,
+		args->agno, XFS_BTNUM_BNO);
 	/*
 	 * Lookup <= bno to find the leftward search's starting point.
 	 */
@@ -938,7 +1023,7 @@ xfs_alloc_ag_vextent_near(
 	 * Increment the cursor, so we will point at the entry just right
 	 * of the leftward entry if any, or to the leftmost entry.
 	 */
-	if ((error = xfs_alloc_increment(bno_cur_gt, 0, &i)))
+	if ((error = xfs_btree_increment(bno_cur_gt, 0, &i)))
 		goto error0;
 	if (!i) {
 		/*
@@ -961,7 +1046,7 @@ xfs_alloc_ag_vextent_near(
 					args->minlen, &ltbnoa, &ltlena);
 			if (ltlena >= args->minlen)
 				break;
-			if ((error = xfs_alloc_decrement(bno_cur_lt, 0, &i)))
+			if ((error = xfs_btree_decrement(bno_cur_lt, 0, &i)))
 				goto error0;
 			if (!i) {
 				xfs_btree_del_cursor(bno_cur_lt,
@@ -977,7 +1062,7 @@ xfs_alloc_ag_vextent_near(
 					args->minlen, &gtbnoa, &gtlena);
 			if (gtlena >= args->minlen)
 				break;
-			if ((error = xfs_alloc_increment(bno_cur_gt, 0, &i)))
+			if ((error = xfs_btree_increment(bno_cur_gt, 0, &i)))
 				goto error0;
 			if (!i) {
 				xfs_btree_del_cursor(bno_cur_gt,
@@ -1066,7 +1151,7 @@ xfs_alloc_ag_vextent_near(
 					/*
 					 * Fell off the right end.
 					 */
-					if ((error = xfs_alloc_increment(
+					if ((error = xfs_btree_increment(
 							bno_cur_gt, 0, &i)))
 						goto error0;
 					if (!i) {
@@ -1162,7 +1247,7 @@ xfs_alloc_ag_vextent_near(
 					/*
 					 * Fell off the left end.
 					 */
-					if ((error = xfs_alloc_decrement(
+					if ((error = xfs_btree_decrement(
 							bno_cur_lt, 0, &i)))
 						goto error0;
 					if (!i) {
@@ -1267,8 +1352,8 @@ xfs_alloc_ag_vextent_size(
 	/*
 	 * Allocate and initialize a cursor for the by-size btree.
 	 */
-	cnt_cur = xfs_btree_init_cursor(args->mp, args->tp, args->agbp,
-		args->agno, XFS_BTNUM_CNT, NULL, 0);
+	cnt_cur = xfs_allocbt_init_cursor(args->mp, args->tp, args->agbp,
+		args->agno, XFS_BTNUM_CNT);
 	bno_cur = NULL;
 	/*
 	 * Look for an entry >= maxlen+alignment-1 blocks.
@@ -1321,7 +1406,7 @@ xfs_alloc_ag_vextent_size(
 		bestflen = flen;
 		bestfbno = fbno;
 		for (;;) {
-			if ((error = xfs_alloc_decrement(cnt_cur, 0, &i)))
+			if ((error = xfs_btree_decrement(cnt_cur, 0, &i)))
 				goto error0;
 			if (i == 0)
 				break;
@@ -1372,8 +1457,8 @@ xfs_alloc_ag_vextent_size(
 	/*
 	 * Allocate and initialize a cursor for the by-block tree.
 	 */
-	bno_cur = xfs_btree_init_cursor(args->mp, args->tp, args->agbp,
-		args->agno, XFS_BTNUM_BNO, NULL, 0);
+	bno_cur = xfs_allocbt_init_cursor(args->mp, args->tp, args->agbp,
+		args->agno, XFS_BTNUM_BNO);
 	if ((error = xfs_alloc_fixup_trees(cnt_cur, bno_cur, fbno, flen,
 			rbno, rlen, XFSA_FIXUP_CNT_OK)))
 		goto error0;
@@ -1416,7 +1501,7 @@ xfs_alloc_ag_vextent_small(
 	xfs_extlen_t	flen;
 	int		i;
 
-	if ((error = xfs_alloc_decrement(ccur, 0, &i)))
+	if ((error = xfs_btree_decrement(ccur, 0, &i)))
 		goto error0;
 	if (i) {
 		if ((error = xfs_alloc_get_rec(ccur, &fbno, &flen, &i)))
@@ -1515,8 +1600,7 @@ xfs_free_ag_extent(
 	/*
 	 * Allocate and initialize a cursor for the by-block btree.
 	 */
-	bno_cur = xfs_btree_init_cursor(mp, tp, agbp, agno, XFS_BTNUM_BNO, NULL,
-		0);
+	bno_cur = xfs_allocbt_init_cursor(mp, tp, agbp, agno, XFS_BTNUM_BNO);
 	cnt_cur = NULL;
 	/*
 	 * Look for a neighboring block on the left (lower block numbers)
@@ -1549,7 +1633,7 @@ xfs_free_ag_extent(
 	 * Look for a neighboring block on the right (higher block numbers)
 	 * that is contiguous with this space.
 	 */
-	if ((error = xfs_alloc_increment(bno_cur, 0, &haveright)))
+	if ((error = xfs_btree_increment(bno_cur, 0, &haveright)))
 		goto error0;
 	if (haveright) {
 		/*
@@ -1575,8 +1659,7 @@ xfs_free_ag_extent(
 	/*
 	 * Now allocate and initialize a cursor for the by-size tree.
 	 */
-	cnt_cur = xfs_btree_init_cursor(mp, tp, agbp, agno, XFS_BTNUM_CNT, NULL,
-		0);
+	cnt_cur = xfs_allocbt_init_cursor(mp, tp, agbp, agno, XFS_BTNUM_CNT);
 	/*
 	 * Have both left and right contiguous neighbors.
 	 * Merge all three into a single free block.
@@ -1588,7 +1671,7 @@ xfs_free_ag_extent(
 		if ((error = xfs_alloc_lookup_eq(cnt_cur, ltbno, ltlen, &i)))
 			goto error0;
 		XFS_WANT_CORRUPTED_GOTO(i == 1, error0);
-		if ((error = xfs_alloc_delete(cnt_cur, &i)))
+		if ((error = xfs_btree_delete(cnt_cur, &i)))
 			goto error0;
 		XFS_WANT_CORRUPTED_GOTO(i == 1, error0);
 		/*
@@ -1597,19 +1680,19 @@ xfs_free_ag_extent(
 		if ((error = xfs_alloc_lookup_eq(cnt_cur, gtbno, gtlen, &i)))
 			goto error0;
 		XFS_WANT_CORRUPTED_GOTO(i == 1, error0);
-		if ((error = xfs_alloc_delete(cnt_cur, &i)))
+		if ((error = xfs_btree_delete(cnt_cur, &i)))
 			goto error0;
 		XFS_WANT_CORRUPTED_GOTO(i == 1, error0);
 		/*
 		 * Delete the old by-block entry for the right block.
 		 */
-		if ((error = xfs_alloc_delete(bno_cur, &i)))
+		if ((error = xfs_btree_delete(bno_cur, &i)))
 			goto error0;
 		XFS_WANT_CORRUPTED_GOTO(i == 1, error0);
 		/*
 		 * Move the by-block cursor back to the left neighbor.
 		 */
-		if ((error = xfs_alloc_decrement(bno_cur, 0, &i)))
+		if ((error = xfs_btree_decrement(bno_cur, 0, &i)))
 			goto error0;
 		XFS_WANT_CORRUPTED_GOTO(i == 1, error0);
 #ifdef DEBUG
@@ -1648,14 +1731,14 @@ xfs_free_ag_extent(
 		if ((error = xfs_alloc_lookup_eq(cnt_cur, ltbno, ltlen, &i)))
 			goto error0;
 		XFS_WANT_CORRUPTED_GOTO(i == 1, error0);
-		if ((error = xfs_alloc_delete(cnt_cur, &i)))
+		if ((error = xfs_btree_delete(cnt_cur, &i)))
 			goto error0;
 		XFS_WANT_CORRUPTED_GOTO(i == 1, error0);
 		/*
 		 * Back up the by-block cursor to the left neighbor, and
 		 * update its length.
 		 */
-		if ((error = xfs_alloc_decrement(bno_cur, 0, &i)))
+		if ((error = xfs_btree_decrement(bno_cur, 0, &i)))
 			goto error0;
 		XFS_WANT_CORRUPTED_GOTO(i == 1, error0);
 		nbno = ltbno;
@@ -1674,7 +1757,7 @@ xfs_free_ag_extent(
 		if ((error = xfs_alloc_lookup_eq(cnt_cur, gtbno, gtlen, &i)))
 			goto error0;
 		XFS_WANT_CORRUPTED_GOTO(i == 1, error0);
-		if ((error = xfs_alloc_delete(cnt_cur, &i)))
+		if ((error = xfs_btree_delete(cnt_cur, &i)))
 			goto error0;
 		XFS_WANT_CORRUPTED_GOTO(i == 1, error0);
 		/*
@@ -1693,7 +1776,7 @@ xfs_free_ag_extent(
 	else {
 		nbno = bno;
 		nlen = len;
-		if ((error = xfs_alloc_insert(bno_cur, &i)))
+		if ((error = xfs_btree_insert(bno_cur, &i)))
 			goto error0;
 		XFS_WANT_CORRUPTED_GOTO(i == 1, error0);
 	}
@@ -1705,7 +1788,7 @@ xfs_free_ag_extent(
 	if ((error = xfs_alloc_lookup_eq(cnt_cur, nbno, nlen, &i)))
 		goto error0;
 	XFS_WANT_CORRUPTED_GOTO(i == 0, error0);
-	if ((error = xfs_alloc_insert(cnt_cur, &i)))
+	if ((error = xfs_btree_insert(cnt_cur, &i)))
 		goto error0;
 	XFS_WANT_CORRUPTED_GOTO(i == 1, error0);
 	xfs_btree_del_cursor(cnt_cur, XFS_BTREE_NOERROR);
@@ -2150,51 +2233,83 @@ xfs_alloc_put_freelist(
  * Read in the allocation group header (free/alloc section).
  */
 int					/* error */
-xfs_alloc_read_agf(
-	xfs_mount_t	*mp,		/* mount point structure */
-	xfs_trans_t	*tp,		/* transaction pointer */
-	xfs_agnumber_t	agno,		/* allocation group number */
-	int		flags,		/* XFS_ALLOC_FLAG_... */
-	xfs_buf_t	**bpp)		/* buffer for the ag freelist header */
+xfs_read_agf(
+	struct xfs_mount	*mp,	/* mount point structure */
+	struct xfs_trans	*tp,	/* transaction pointer */
+	xfs_agnumber_t		agno,	/* allocation group number */
+	int			flags,	/* XFS_BUF_ */
+	struct xfs_buf		**bpp)	/* buffer for the ag freelist header */
 {
-	xfs_agf_t	*agf;		/* ag freelist header */
+	struct xfs_agf	*agf;		/* ag freelist header */
 	int		agf_ok;		/* set if agf is consistent */
-	xfs_buf_t	*bp;		/* return value */
-	xfs_perag_t	*pag;		/* per allocation group data */
 	int		error;
 
 	ASSERT(agno != NULLAGNUMBER);
 	error = xfs_trans_read_buf(
 			mp, tp, mp->m_ddev_targp,
 			XFS_AG_DADDR(mp, agno, XFS_AGF_DADDR(mp)),
-			XFS_FSS_TO_BB(mp, 1),
-			(flags & XFS_ALLOC_FLAG_TRYLOCK) ? XFS_BUF_TRYLOCK : 0U,
-			&bp);
+			XFS_FSS_TO_BB(mp, 1), flags, bpp);
 	if (error)
 		return error;
-	ASSERT(!bp || !XFS_BUF_GETERROR(bp));
-	if (!bp) {
-		*bpp = NULL;
+	if (!*bpp)
 		return 0;
-	}
+
+	ASSERT(!XFS_BUF_GETERROR(*bpp));
+	agf = XFS_BUF_TO_AGF(*bpp);
+
 	/*
 	 * Validate the magic number of the agf block.
 	 */
-	agf = XFS_BUF_TO_AGF(bp);
 	agf_ok =
 		be32_to_cpu(agf->agf_magicnum) == XFS_AGF_MAGIC &&
 		XFS_AGF_GOOD_VERSION(be32_to_cpu(agf->agf_versionnum)) &&
 		be32_to_cpu(agf->agf_freeblks) <= be32_to_cpu(agf->agf_length) &&
 		be32_to_cpu(agf->agf_flfirst) < XFS_AGFL_SIZE(mp) &&
 		be32_to_cpu(agf->agf_fllast) < XFS_AGFL_SIZE(mp) &&
-		be32_to_cpu(agf->agf_flcount) <= XFS_AGFL_SIZE(mp);
+		be32_to_cpu(agf->agf_flcount) <= XFS_AGFL_SIZE(mp) &&
+		be32_to_cpu(agf->agf_seqno) == agno;
+	if (xfs_sb_version_haslazysbcount(&mp->m_sb))
+		agf_ok = agf_ok && be32_to_cpu(agf->agf_btreeblks) <=
+						be32_to_cpu(agf->agf_length);
 	if (unlikely(XFS_TEST_ERROR(!agf_ok, mp, XFS_ERRTAG_ALLOC_READ_AGF,
 			XFS_RANDOM_ALLOC_READ_AGF))) {
 		XFS_CORRUPTION_ERROR("xfs_alloc_read_agf",
 				     XFS_ERRLEVEL_LOW, mp, agf);
-		xfs_trans_brelse(tp, bp);
+		xfs_trans_brelse(tp, *bpp);
 		return XFS_ERROR(EFSCORRUPTED);
 	}
+
+	XFS_BUF_SET_VTYPE_REF(*bpp, B_FS_AGF, XFS_AGF_REF);
+	return 0;
+}
+
+/*
+ * Read in the allocation group header (free/alloc section).
+ */
+int					/* error */
+xfs_alloc_read_agf(
+	struct xfs_mount	*mp,	/* mount point structure */
+	struct xfs_trans	*tp,	/* transaction pointer */
+	xfs_agnumber_t		agno,	/* allocation group number */
+	int			flags,	/* XFS_ALLOC_FLAG_... */
+	struct xfs_buf		**bpp)	/* buffer for the ag freelist header */
+{
+	struct xfs_agf		*agf;		/* ag freelist header */
+	struct xfs_perag	*pag;		/* per allocation group data */
+	int			error;
+
+	ASSERT(agno != NULLAGNUMBER);
+
+	error = xfs_read_agf(mp, tp, agno,
+			(flags & XFS_ALLOC_FLAG_TRYLOCK) ? XFS_BUF_TRYLOCK : 0,
+			bpp);
+	if (error)
+		return error;
+	if (!*bpp)
+		return 0;
+	ASSERT(!XFS_BUF_GETERROR(*bpp));
+
+	agf = XFS_BUF_TO_AGF(*bpp);
 	pag = &mp->m_perag[agno];
 	if (!pag->pagf_init) {
 		pag->pagf_freeblks = be32_to_cpu(agf->agf_freeblks);
@@ -2213,6 +2328,7 @@ xfs_alloc_read_agf(
 #ifdef DEBUG
 	else if (!XFS_FORCED_SHUTDOWN(mp)) {
 		ASSERT(pag->pagf_freeblks == be32_to_cpu(agf->agf_freeblks));
+		ASSERT(pag->pagf_btreeblks == be32_to_cpu(agf->agf_btreeblks));
 		ASSERT(pag->pagf_flcount == be32_to_cpu(agf->agf_flcount));
 		ASSERT(pag->pagf_longest == be32_to_cpu(agf->agf_longest));
 		ASSERT(pag->pagf_levels[XFS_BTNUM_BNOi] ==
@@ -2221,8 +2337,6 @@ xfs_alloc_read_agf(
 		       be32_to_cpu(agf->agf_levels[XFS_BTNUM_CNTi]));
 	}
 #endif
-	XFS_BUF_SET_VTYPE_REF(bp, B_FS_AGF, XFS_AGF_REF);
-	*bpp = bp;
 	return 0;
 }
 
diff --git a/fs/xfs/xfs_alloc.h b/fs/xfs/xfs_alloc.h
index 5aec15d0651e..588172796f7b 100644
--- a/fs/xfs/xfs_alloc.h
+++ b/fs/xfs/xfs_alloc.h
@@ -121,6 +121,19 @@ extern ktrace_t *xfs_alloc_trace_buf;
 #define	XFS_ALLOC_KTRACE_BUSYSEARCH	6
 #endif
 
+void
+xfs_alloc_mark_busy(xfs_trans_t *tp,
+		xfs_agnumber_t agno,
+		xfs_agblock_t bno,
+		xfs_extlen_t len);
+
+void
+xfs_alloc_clear_busy(xfs_trans_t *tp,
+		xfs_agnumber_t ag,
+		int idx);
+
+#endif	/* __KERNEL__ */
+
 /*
  * Compute and fill in value of m_ag_maxlevels.
  */
@@ -196,18 +209,4 @@ xfs_free_extent(
 	xfs_fsblock_t	bno,	/* starting block number of extent */
 	xfs_extlen_t	len);	/* length of extent */
 
-void
-xfs_alloc_mark_busy(xfs_trans_t *tp,
-		xfs_agnumber_t agno,
-		xfs_agblock_t bno,
-		xfs_extlen_t len);
-
-void
-xfs_alloc_clear_busy(xfs_trans_t *tp,
-		xfs_agnumber_t ag,
-		int idx);
-
-
-#endif	/* __KERNEL__ */
-
 #endif	/* __XFS_ALLOC_H__ */
diff --git a/fs/xfs/xfs_alloc_btree.c b/fs/xfs/xfs_alloc_btree.c
index 3ce2645508ae..733cb75a8c5d 100644
--- a/fs/xfs/xfs_alloc_btree.c
+++ b/fs/xfs/xfs_alloc_btree.c
@@ -35,2177 +35,464 @@
 #include "xfs_dinode.h"
 #include "xfs_inode.h"
 #include "xfs_btree.h"
+#include "xfs_btree_trace.h"
 #include "xfs_ialloc.h"
 #include "xfs_alloc.h"
 #include "xfs_error.h"
 
-/*
- * Prototypes for internal functions.
- */
 
-STATIC void xfs_alloc_log_block(xfs_trans_t *, xfs_buf_t *, int);
-STATIC void xfs_alloc_log_keys(xfs_btree_cur_t *, xfs_buf_t *, int, int);
-STATIC void xfs_alloc_log_ptrs(xfs_btree_cur_t *, xfs_buf_t *, int, int);
-STATIC void xfs_alloc_log_recs(xfs_btree_cur_t *, xfs_buf_t *, int, int);
-STATIC int xfs_alloc_lshift(xfs_btree_cur_t *, int, int *);
-STATIC int xfs_alloc_newroot(xfs_btree_cur_t *, int *);
-STATIC int xfs_alloc_rshift(xfs_btree_cur_t *, int, int *);
-STATIC int xfs_alloc_split(xfs_btree_cur_t *, int, xfs_agblock_t *,
-		xfs_alloc_key_t *, xfs_btree_cur_t **, int *);
-STATIC int xfs_alloc_updkey(xfs_btree_cur_t *, xfs_alloc_key_t *, int);
+STATIC struct xfs_btree_cur *
+xfs_allocbt_dup_cursor(
+	struct xfs_btree_cur	*cur)
+{
+	return xfs_allocbt_init_cursor(cur->bc_mp, cur->bc_tp,
+			cur->bc_private.a.agbp, cur->bc_private.a.agno,
+			cur->bc_btnum);
+}
 
-/*
- * Internal functions.
- */
+STATIC void
+xfs_allocbt_set_root(
+	struct xfs_btree_cur	*cur,
+	union xfs_btree_ptr	*ptr,
+	int			inc)
+{
+	struct xfs_buf		*agbp = cur->bc_private.a.agbp;
+	struct xfs_agf		*agf = XFS_BUF_TO_AGF(agbp);
+	xfs_agnumber_t		seqno = be32_to_cpu(agf->agf_seqno);
+	int			btnum = cur->bc_btnum;
 
-/*
- * Single level of the xfs_alloc_delete record deletion routine.
- * Delete record pointed to by cur/level.
- * Remove the record from its block then rebalance the tree.
- * Return 0 for error, 1 for done, 2 to go on to the next level.
- */
-STATIC int				/* error */
-xfs_alloc_delrec(
-	xfs_btree_cur_t		*cur,	/* btree cursor */
-	int			level,	/* level removing record from */
-	int			*stat)	/* fail/done/go-on */
+	ASSERT(ptr->s != 0);
+
+	agf->agf_roots[btnum] = ptr->s;
+	be32_add_cpu(&agf->agf_levels[btnum], inc);
+	cur->bc_mp->m_perag[seqno].pagf_levels[btnum] += inc;
+
+	xfs_alloc_log_agf(cur->bc_tp, agbp, XFS_AGF_ROOTS | XFS_AGF_LEVELS);
+}
+
+STATIC int
+xfs_allocbt_alloc_block(
+	struct xfs_btree_cur	*cur,
+	union xfs_btree_ptr	*start,
+	union xfs_btree_ptr	*new,
+	int			length,
+	int			*stat)
 {
-	xfs_agf_t		*agf;	/* allocation group freelist header */
-	xfs_alloc_block_t	*block;	/* btree block record/key lives in */
-	xfs_agblock_t		bno;	/* btree block number */
-	xfs_buf_t		*bp;	/* buffer for block */
-	int			error;	/* error return value */
-	int			i;	/* loop index */
-	xfs_alloc_key_t		key;	/* kp points here if block is level 0 */
-	xfs_agblock_t		lbno;	/* left block's block number */
-	xfs_buf_t		*lbp;	/* left block's buffer pointer */
-	xfs_alloc_block_t	*left;	/* left btree block */
-	xfs_alloc_key_t		*lkp=NULL;	/* left block key pointer */
-	xfs_alloc_ptr_t		*lpp=NULL;	/* left block address pointer */
-	int			lrecs=0;	/* number of records in left block */
-	xfs_alloc_rec_t		*lrp;	/* left block record pointer */
-	xfs_mount_t		*mp;	/* mount structure */
-	int			ptr;	/* index in btree block for this rec */
-	xfs_agblock_t		rbno;	/* right block's block number */
-	xfs_buf_t		*rbp;	/* right block's buffer pointer */
-	xfs_alloc_block_t	*right;	/* right btree block */
-	xfs_alloc_key_t		*rkp;	/* right block key pointer */
-	xfs_alloc_ptr_t		*rpp;	/* right block address pointer */
-	int			rrecs=0;	/* number of records in right block */
-	int			numrecs;
-	xfs_alloc_rec_t		*rrp;	/* right block record pointer */
-	xfs_btree_cur_t		*tcur;	/* temporary btree cursor */
+	int			error;
+	xfs_agblock_t		bno;
 
-	/*
-	 * Get the index of the entry being deleted, check for nothing there.
-	 */
-	ptr = cur->bc_ptrs[level];
-	if (ptr == 0) {
-		*stat = 0;
-		return 0;
-	}
-	/*
-	 * Get the buffer & block containing the record or key/ptr.
-	 */
-	bp = cur->bc_bufs[level];
-	block = XFS_BUF_TO_ALLOC_BLOCK(bp);
-#ifdef DEBUG
-	if ((error = xfs_btree_check_sblock(cur, block, level, bp)))
+	XFS_BTREE_TRACE_CURSOR(cur, XBT_ENTRY);
+
+	/* Allocate the new block from the freelist. If we can't, give up.  */
+	error = xfs_alloc_get_freelist(cur->bc_tp, cur->bc_private.a.agbp,
+				       &bno, 1);
+	if (error) {
+		XFS_BTREE_TRACE_CURSOR(cur, XBT_ERROR);
 		return error;
-#endif
-	/*
-	 * Fail if we're off the end of the block.
-	 */
-	numrecs = be16_to_cpu(block->bb_numrecs);
-	if (ptr > numrecs) {
+	}
+
+	if (bno == NULLAGBLOCK) {
+		XFS_BTREE_TRACE_CURSOR(cur, XBT_EXIT);
 		*stat = 0;
 		return 0;
 	}
-	XFS_STATS_INC(xs_abt_delrec);
-	/*
-	 * It's a nonleaf.  Excise the key and ptr being deleted, by
-	 * sliding the entries past them down one.
-	 * Log the changed areas of the block.
-	 */
-	if (level > 0) {
-		lkp = XFS_ALLOC_KEY_ADDR(block, 1, cur);
-		lpp = XFS_ALLOC_PTR_ADDR(block, 1, cur);
-#ifdef DEBUG
-		for (i = ptr; i < numrecs; i++) {
-			if ((error = xfs_btree_check_sptr(cur, be32_to_cpu(lpp[i]), level)))
-				return error;
-		}
-#endif
-		if (ptr < numrecs) {
-			memmove(&lkp[ptr - 1], &lkp[ptr],
-				(numrecs - ptr) * sizeof(*lkp));
-			memmove(&lpp[ptr - 1], &lpp[ptr],
-				(numrecs - ptr) * sizeof(*lpp));
-			xfs_alloc_log_ptrs(cur, bp, ptr, numrecs - 1);
-			xfs_alloc_log_keys(cur, bp, ptr, numrecs - 1);
-		}
-	}
-	/*
-	 * It's a leaf.  Excise the record being deleted, by sliding the
-	 * entries past it down one.  Log the changed areas of the block.
-	 */
-	else {
-		lrp = XFS_ALLOC_REC_ADDR(block, 1, cur);
-		if (ptr < numrecs) {
-			memmove(&lrp[ptr - 1], &lrp[ptr],
-				(numrecs - ptr) * sizeof(*lrp));
-			xfs_alloc_log_recs(cur, bp, ptr, numrecs - 1);
-		}
-		/*
-		 * If it's the first record in the block, we'll need a key
-		 * structure to pass up to the next level (updkey).
-		 */
-		if (ptr == 1) {
-			key.ar_startblock = lrp->ar_startblock;
-			key.ar_blockcount = lrp->ar_blockcount;
-			lkp = &key;
-		}
-	}
-	/*
-	 * Decrement and log the number of entries in the block.
-	 */
-	numrecs--;
-	block->bb_numrecs = cpu_to_be16(numrecs);
-	xfs_alloc_log_block(cur->bc_tp, bp, XFS_BB_NUMRECS);
-	/*
-	 * See if the longest free extent in the allocation group was
-	 * changed by this operation.  True if it's the by-size btree, and
-	 * this is the leaf level, and there is no right sibling block,
-	 * and this was the last record.
-	 */
-	agf = XFS_BUF_TO_AGF(cur->bc_private.a.agbp);
-	mp = cur->bc_mp;
 
-	if (level == 0 &&
-	    cur->bc_btnum == XFS_BTNUM_CNT &&
-	    be32_to_cpu(block->bb_rightsib) == NULLAGBLOCK &&
-	    ptr > numrecs) {
-		ASSERT(ptr == numrecs + 1);
-		/*
-		 * There are still records in the block.  Grab the size
-		 * from the last one.
-		 */
-		if (numrecs) {
-			rrp = XFS_ALLOC_REC_ADDR(block, numrecs, cur);
-			agf->agf_longest = rrp->ar_blockcount;
-		}
-		/*
-		 * No free extents left.
-		 */
-		else
-			agf->agf_longest = 0;
-		mp->m_perag[be32_to_cpu(agf->agf_seqno)].pagf_longest =
-			be32_to_cpu(agf->agf_longest);
-		xfs_alloc_log_agf(cur->bc_tp, cur->bc_private.a.agbp,
-			XFS_AGF_LONGEST);
-	}
-	/*
-	 * Is this the root level?  If so, we're almost done.
-	 */
-	if (level == cur->bc_nlevels - 1) {
-		/*
-		 * If this is the root level,
-		 * and there's only one entry left,
-		 * and it's NOT the leaf level,
-		 * then we can get rid of this level.
-		 */
-		if (numrecs == 1 && level > 0) {
-			/*
-			 * lpp is still set to the first pointer in the block.
-			 * Make it the new root of the btree.
-			 */
-			bno = be32_to_cpu(agf->agf_roots[cur->bc_btnum]);
-			agf->agf_roots[cur->bc_btnum] = *lpp;
-			be32_add_cpu(&agf->agf_levels[cur->bc_btnum], -1);
-			mp->m_perag[be32_to_cpu(agf->agf_seqno)].pagf_levels[cur->bc_btnum]--;
-			/*
-			 * Put this buffer/block on the ag's freelist.
-			 */
-			error = xfs_alloc_put_freelist(cur->bc_tp,
-					cur->bc_private.a.agbp, NULL, bno, 1);
-			if (error)
-				return error;
-			/*
-			 * Since blocks move to the free list without the
-			 * coordination used in xfs_bmap_finish, we can't allow
-			 * block to be available for reallocation and
-			 * non-transaction writing (user data) until we know
-			 * that the transaction that moved it to the free list
-			 * is permanently on disk. We track the blocks by
-			 * declaring these blocks as "busy"; the busy list is
-			 * maintained on a per-ag basis and each transaction
-			 * records which entries should be removed when the
-			 * iclog commits to disk. If a busy block is
-			 * allocated, the iclog is pushed up to the LSN
-			 * that freed the block.
-			 */
-			xfs_alloc_mark_busy(cur->bc_tp,
-				be32_to_cpu(agf->agf_seqno), bno, 1);
+	xfs_trans_agbtree_delta(cur->bc_tp, 1);
+	new->s = cpu_to_be32(bno);
 
-			xfs_trans_agbtree_delta(cur->bc_tp, -1);
-			xfs_alloc_log_agf(cur->bc_tp, cur->bc_private.a.agbp,
-				XFS_AGF_ROOTS | XFS_AGF_LEVELS);
-			/*
-			 * Update the cursor so there's one fewer level.
-			 */
-			xfs_btree_setbuf(cur, level, NULL);
-			cur->bc_nlevels--;
-		} else if (level > 0 &&
-			   (error = xfs_alloc_decrement(cur, level, &i)))
-			return error;
-		*stat = 1;
-		return 0;
-	}
-	/*
-	 * If we deleted the leftmost entry in the block, update the
-	 * key values above us in the tree.
-	 */
-	if (ptr == 1 && (error = xfs_alloc_updkey(cur, lkp, level + 1)))
-		return error;
-	/*
-	 * If the number of records remaining in the block is at least
-	 * the minimum, we're done.
-	 */
-	if (numrecs >= XFS_ALLOC_BLOCK_MINRECS(level, cur)) {
-		if (level > 0 && (error = xfs_alloc_decrement(cur, level, &i)))
-			return error;
-		*stat = 1;
-		return 0;
-	}
-	/*
-	 * Otherwise, we have to move some records around to keep the
-	 * tree balanced.  Look at the left and right sibling blocks to
-	 * see if we can re-balance by moving only one record.
-	 */
-	rbno = be32_to_cpu(block->bb_rightsib);
-	lbno = be32_to_cpu(block->bb_leftsib);
-	bno = NULLAGBLOCK;
-	ASSERT(rbno != NULLAGBLOCK || lbno != NULLAGBLOCK);
-	/*
-	 * Duplicate the cursor so our btree manipulations here won't
-	 * disrupt the next level up.
-	 */
-	if ((error = xfs_btree_dup_cursor(cur, &tcur)))
-		return error;
-	/*
-	 * If there's a right sibling, see if it's ok to shift an entry
-	 * out of it.
-	 */
-	if (rbno != NULLAGBLOCK) {
-		/*
-		 * Move the temp cursor to the last entry in the next block.
-		 * Actually any entry but the first would suffice.
-		 */
-		i = xfs_btree_lastrec(tcur, level);
-		XFS_WANT_CORRUPTED_GOTO(i == 1, error0);
-		if ((error = xfs_alloc_increment(tcur, level, &i)))
-			goto error0;
-		XFS_WANT_CORRUPTED_GOTO(i == 1, error0);
-		i = xfs_btree_lastrec(tcur, level);
-		XFS_WANT_CORRUPTED_GOTO(i == 1, error0);
-		/*
-		 * Grab a pointer to the block.
-		 */
-		rbp = tcur->bc_bufs[level];
-		right = XFS_BUF_TO_ALLOC_BLOCK(rbp);
-#ifdef DEBUG
-		if ((error = xfs_btree_check_sblock(cur, right, level, rbp)))
-			goto error0;
-#endif
-		/*
-		 * Grab the current block number, for future use.
-		 */
-		bno = be32_to_cpu(right->bb_leftsib);
-		/*
-		 * If right block is full enough so that removing one entry
-		 * won't make it too empty, and left-shifting an entry out
-		 * of right to us works, we're done.
-		 */
-		if (be16_to_cpu(right->bb_numrecs) - 1 >=
-		     XFS_ALLOC_BLOCK_MINRECS(level, cur)) {
-			if ((error = xfs_alloc_lshift(tcur, level, &i)))
-				goto error0;
-			if (i) {
-				ASSERT(be16_to_cpu(block->bb_numrecs) >=
-				       XFS_ALLOC_BLOCK_MINRECS(level, cur));
-				xfs_btree_del_cursor(tcur,
-						     XFS_BTREE_NOERROR);
-				if (level > 0 &&
-				    (error = xfs_alloc_decrement(cur, level,
-					    &i)))
-					return error;
-				*stat = 1;
-				return 0;
-			}
-		}
-		/*
-		 * Otherwise, grab the number of records in right for
-		 * future reference, and fix up the temp cursor to point
-		 * to our block again (last record).
-		 */
-		rrecs = be16_to_cpu(right->bb_numrecs);
-		if (lbno != NULLAGBLOCK) {
-			i = xfs_btree_firstrec(tcur, level);
-			XFS_WANT_CORRUPTED_GOTO(i == 1, error0);
-			if ((error = xfs_alloc_decrement(tcur, level, &i)))
-				goto error0;
-			XFS_WANT_CORRUPTED_GOTO(i == 1, error0);
-		}
-	}
-	/*
-	 * If there's a left sibling, see if it's ok to shift an entry
-	 * out of it.
-	 */
-	if (lbno != NULLAGBLOCK) {
-		/*
-		 * Move the temp cursor to the first entry in the
-		 * previous block.
-		 */
-		i = xfs_btree_firstrec(tcur, level);
-		XFS_WANT_CORRUPTED_GOTO(i == 1, error0);
-		if ((error = xfs_alloc_decrement(tcur, level, &i)))
-			goto error0;
-		XFS_WANT_CORRUPTED_GOTO(i == 1, error0);
-		xfs_btree_firstrec(tcur, level);
-		/*
-		 * Grab a pointer to the block.
-		 */
-		lbp = tcur->bc_bufs[level];
-		left = XFS_BUF_TO_ALLOC_BLOCK(lbp);
-#ifdef DEBUG
-		if ((error = xfs_btree_check_sblock(cur, left, level, lbp)))
-			goto error0;
-#endif
-		/*
-		 * Grab the current block number, for future use.
-		 */
-		bno = be32_to_cpu(left->bb_rightsib);
-		/*
-		 * If left block is full enough so that removing one entry
-		 * won't make it too empty, and right-shifting an entry out
-		 * of left to us works, we're done.
-		 */
-		if (be16_to_cpu(left->bb_numrecs) - 1 >=
-		     XFS_ALLOC_BLOCK_MINRECS(level, cur)) {
-			if ((error = xfs_alloc_rshift(tcur, level, &i)))
-				goto error0;
-			if (i) {
-				ASSERT(be16_to_cpu(block->bb_numrecs) >=
-				       XFS_ALLOC_BLOCK_MINRECS(level, cur));
-				xfs_btree_del_cursor(tcur,
-						     XFS_BTREE_NOERROR);
-				if (level == 0)
-					cur->bc_ptrs[0]++;
-				*stat = 1;
-				return 0;
-			}
-		}
-		/*
-		 * Otherwise, grab the number of records in right for
-		 * future reference.
-		 */
-		lrecs = be16_to_cpu(left->bb_numrecs);
-	}
-	/*
-	 * Delete the temp cursor, we're done with it.
-	 */
-	xfs_btree_del_cursor(tcur, XFS_BTREE_NOERROR);
-	/*
-	 * If here, we need to do a join to keep the tree balanced.
-	 */
-	ASSERT(bno != NULLAGBLOCK);
-	/*
-	 * See if we can join with the left neighbor block.
-	 */
-	if (lbno != NULLAGBLOCK &&
-	    lrecs + numrecs <= XFS_ALLOC_BLOCK_MAXRECS(level, cur)) {
-		/*
-		 * Set "right" to be the starting block,
-		 * "left" to be the left neighbor.
-		 */
-		rbno = bno;
-		right = block;
-		rrecs = be16_to_cpu(right->bb_numrecs);
-		rbp = bp;
-		if ((error = xfs_btree_read_bufs(mp, cur->bc_tp,
-				cur->bc_private.a.agno, lbno, 0, &lbp,
-				XFS_ALLOC_BTREE_REF)))
-			return error;
-		left = XFS_BUF_TO_ALLOC_BLOCK(lbp);
-		lrecs = be16_to_cpu(left->bb_numrecs);
-		if ((error = xfs_btree_check_sblock(cur, left, level, lbp)))
-			return error;
-	}
-	/*
-	 * If that won't work, see if we can join with the right neighbor block.
-	 */
-	else if (rbno != NULLAGBLOCK &&
-		 rrecs + numrecs <= XFS_ALLOC_BLOCK_MAXRECS(level, cur)) {
-		/*
-		 * Set "left" to be the starting block,
-		 * "right" to be the right neighbor.
-		 */
-		lbno = bno;
-		left = block;
-		lrecs = be16_to_cpu(left->bb_numrecs);
-		lbp = bp;
-		if ((error = xfs_btree_read_bufs(mp, cur->bc_tp,
-				cur->bc_private.a.agno, rbno, 0, &rbp,
-				XFS_ALLOC_BTREE_REF)))
-			return error;
-		right = XFS_BUF_TO_ALLOC_BLOCK(rbp);
-		rrecs = be16_to_cpu(right->bb_numrecs);
-		if ((error = xfs_btree_check_sblock(cur, right, level, rbp)))
-			return error;
-	}
-	/*
-	 * Otherwise, we can't fix the imbalance.
-	 * Just return.  This is probably a logic error, but it's not fatal.
-	 */
-	else {
-		if (level > 0 && (error = xfs_alloc_decrement(cur, level, &i)))
-			return error;
-		*stat = 1;
-		return 0;
-	}
-	/*
-	 * We're now going to join "left" and "right" by moving all the stuff
-	 * in "right" to "left" and deleting "right".
-	 */
-	if (level > 0) {
-		/*
-		 * It's a non-leaf.  Move keys and pointers.
-		 */
-		lkp = XFS_ALLOC_KEY_ADDR(left, lrecs + 1, cur);
-		lpp = XFS_ALLOC_PTR_ADDR(left, lrecs + 1, cur);
-		rkp = XFS_ALLOC_KEY_ADDR(right, 1, cur);
-		rpp = XFS_ALLOC_PTR_ADDR(right, 1, cur);
-#ifdef DEBUG
-		for (i = 0; i < rrecs; i++) {
-			if ((error = xfs_btree_check_sptr(cur, be32_to_cpu(rpp[i]), level)))
-				return error;
-		}
-#endif
-		memcpy(lkp, rkp, rrecs * sizeof(*lkp));
-		memcpy(lpp, rpp, rrecs * sizeof(*lpp));
-		xfs_alloc_log_keys(cur, lbp, lrecs + 1, lrecs + rrecs);
-		xfs_alloc_log_ptrs(cur, lbp, lrecs + 1, lrecs + rrecs);
-	} else {
-		/*
-		 * It's a leaf.  Move records.
-		 */
-		lrp = XFS_ALLOC_REC_ADDR(left, lrecs + 1, cur);
-		rrp = XFS_ALLOC_REC_ADDR(right, 1, cur);
-		memcpy(lrp, rrp, rrecs * sizeof(*lrp));
-		xfs_alloc_log_recs(cur, lbp, lrecs + 1, lrecs + rrecs);
-	}
-	/*
-	 * If we joined with the left neighbor, set the buffer in the
-	 * cursor to the left block, and fix up the index.
-	 */
-	if (bp != lbp) {
-		xfs_btree_setbuf(cur, level, lbp);
-		cur->bc_ptrs[level] += lrecs;
-	}
-	/*
-	 * If we joined with the right neighbor and there's a level above
-	 * us, increment the cursor at that level.
-	 */
-	else if (level + 1 < cur->bc_nlevels &&
-		 (error = xfs_alloc_increment(cur, level + 1, &i)))
-		return error;
-	/*
-	 * Fix up the number of records in the surviving block.
-	 */
-	lrecs += rrecs;
-	left->bb_numrecs = cpu_to_be16(lrecs);
-	/*
-	 * Fix up the right block pointer in the surviving block, and log it.
-	 */
-	left->bb_rightsib = right->bb_rightsib;
-	xfs_alloc_log_block(cur->bc_tp, lbp, XFS_BB_NUMRECS | XFS_BB_RIGHTSIB);
-	/*
-	 * If there is a right sibling now, make it point to the
-	 * remaining block.
-	 */
-	if (be32_to_cpu(left->bb_rightsib) != NULLAGBLOCK) {
-		xfs_alloc_block_t	*rrblock;
-		xfs_buf_t		*rrbp;
+	XFS_BTREE_TRACE_CURSOR(cur, XBT_EXIT);
+	*stat = 1;
+	return 0;
+}
 
-		if ((error = xfs_btree_read_bufs(mp, cur->bc_tp,
-				cur->bc_private.a.agno, be32_to_cpu(left->bb_rightsib), 0,
-				&rrbp, XFS_ALLOC_BTREE_REF)))
-			return error;
-		rrblock = XFS_BUF_TO_ALLOC_BLOCK(rrbp);
-		if ((error = xfs_btree_check_sblock(cur, rrblock, level, rrbp)))
-			return error;
-		rrblock->bb_leftsib = cpu_to_be32(lbno);
-		xfs_alloc_log_block(cur->bc_tp, rrbp, XFS_BB_LEFTSIB);
-	}
-	/*
-	 * Free the deleting block by putting it on the freelist.
-	 */
-	error = xfs_alloc_put_freelist(cur->bc_tp,
-					 cur->bc_private.a.agbp, NULL, rbno, 1);
+STATIC int
+xfs_allocbt_free_block(
+	struct xfs_btree_cur	*cur,
+	struct xfs_buf		*bp)
+{
+	struct xfs_buf		*agbp = cur->bc_private.a.agbp;
+	struct xfs_agf		*agf = XFS_BUF_TO_AGF(agbp);
+	xfs_agblock_t		bno;
+	int			error;
+
+	bno = XFS_DADDR_TO_AGBNO(cur->bc_mp, XFS_BUF_ADDR(bp));
+	error = xfs_alloc_put_freelist(cur->bc_tp, agbp, NULL, bno, 1);
 	if (error)
 		return error;
+
 	/*
-	 * Since blocks move to the free list without the coordination
-	 * used in xfs_bmap_finish, we can't allow block to be available
-	 * for reallocation and non-transaction writing (user data)
-	 * until we know that the transaction that moved it to the free
-	 * list is permanently on disk. We track the blocks by declaring
-	 * these blocks as "busy"; the busy list is maintained on a
-	 * per-ag basis and each transaction records which entries
-	 * should be removed when the iclog commits to disk. If a
-	 * busy block is allocated, the iclog is pushed up to the
+	 * Since blocks move to the free list without the coordination used in
+	 * xfs_bmap_finish, we can't allow block to be available for
+	 * reallocation and non-transaction writing (user data) until we know
+	 * that the transaction that moved it to the free list is permanently
+	 * on disk. We track the blocks by declaring these blocks as "busy";
+	 * the busy list is maintained on a per-ag basis and each transaction
+	 * records which entries should be removed when the iclog commits to
+	 * disk. If a busy block is allocated, the iclog is pushed up to the
 	 * LSN that freed the block.
 	 */
 	xfs_alloc_mark_busy(cur->bc_tp, be32_to_cpu(agf->agf_seqno), bno, 1);
 	xfs_trans_agbtree_delta(cur->bc_tp, -1);
-
-	/*
-	 * Adjust the current level's cursor so that we're left referring
-	 * to the right node, after we're done.
-	 * If this leaves the ptr value 0 our caller will fix it up.
-	 */
-	if (level > 0)
-		cur->bc_ptrs[level]--;
-	/*
-	 * Return value means the next level up has something to do.
-	 */
-	*stat = 2;
 	return 0;
-
-error0:
-	xfs_btree_del_cursor(tcur, XFS_BTREE_ERROR);
-	return error;
 }
 
 /*
- * Insert one record/level.  Return information to the caller
- * allowing the next level up to proceed if necessary.
+ * Update the longest extent in the AGF
  */
-STATIC int				/* error */
-xfs_alloc_insrec(
-	xfs_btree_cur_t		*cur,	/* btree cursor */
-	int			level,	/* level to insert record at */
-	xfs_agblock_t		*bnop,	/* i/o: block number inserted */
-	xfs_alloc_rec_t		*recp,	/* i/o: record data inserted */
-	xfs_btree_cur_t		**curp,	/* output: new cursor replacing cur */
-	int			*stat)	/* output: success/failure */
+STATIC void
+xfs_allocbt_update_lastrec(
+	struct xfs_btree_cur	*cur,
+	struct xfs_btree_block	*block,
+	union xfs_btree_rec	*rec,
+	int			ptr,
+	int			reason)
 {
-	xfs_agf_t		*agf;	/* allocation group freelist header */
-	xfs_alloc_block_t	*block;	/* btree block record/key lives in */
-	xfs_buf_t		*bp;	/* buffer for block */
-	int			error;	/* error return value */
-	int			i;	/* loop index */
-	xfs_alloc_key_t		key;	/* key value being inserted */
-	xfs_alloc_key_t		*kp;	/* pointer to btree keys */
-	xfs_agblock_t		nbno;	/* block number of allocated block */
-	xfs_btree_cur_t		*ncur;	/* new cursor to be used at next lvl */
-	xfs_alloc_key_t		nkey;	/* new key value, from split */
-	xfs_alloc_rec_t		nrec;	/* new record value, for caller */
+	struct xfs_agf		*agf = XFS_BUF_TO_AGF(cur->bc_private.a.agbp);
+	xfs_agnumber_t		seqno = be32_to_cpu(agf->agf_seqno);
+	__be32			len;
 	int			numrecs;
-	int			optr;	/* old ptr value */
-	xfs_alloc_ptr_t		*pp;	/* pointer to btree addresses */
-	int			ptr;	/* index in btree block for this rec */
-	xfs_alloc_rec_t		*rp;	/* pointer to btree records */
 
-	ASSERT(be32_to_cpu(recp->ar_blockcount) > 0);
+	ASSERT(cur->bc_btnum == XFS_BTNUM_CNT);
+
+	switch (reason) {
+	case LASTREC_UPDATE:
+		/*
+		 * If this is the last leaf block and it's the last record,
+		 * then update the size of the longest extent in the AG.
+		 */
+		if (ptr != xfs_btree_get_numrecs(block))
+			return;
+		len = rec->alloc.ar_blockcount;
+		break;
+	case LASTREC_INSREC:
+		if (be32_to_cpu(rec->alloc.ar_blockcount) <=
+		    be32_to_cpu(agf->agf_longest))
+			return;
+		len = rec->alloc.ar_blockcount;
+		break;
+	case LASTREC_DELREC:
+		numrecs = xfs_btree_get_numrecs(block);
+		if (ptr <= numrecs)
+			return;
+		ASSERT(ptr == numrecs + 1);
 
-	/*
-	 * GCC doesn't understand the (arguably complex) control flow in
-	 * this function and complains about uninitialized structure fields
-	 * without this.
-	 */
-	memset(&nrec, 0, sizeof(nrec));
+		if (numrecs) {
+			xfs_alloc_rec_t *rrp;
 
-	/*
-	 * If we made it to the root level, allocate a new root block
-	 * and we're done.
-	 */
-	if (level >= cur->bc_nlevels) {
-		XFS_STATS_INC(xs_abt_insrec);
-		if ((error = xfs_alloc_newroot(cur, &i)))
-			return error;
-		*bnop = NULLAGBLOCK;
-		*stat = i;
-		return 0;
-	}
-	/*
-	 * Make a key out of the record data to be inserted, and save it.
-	 */
-	key.ar_startblock = recp->ar_startblock;
-	key.ar_blockcount = recp->ar_blockcount;
-	optr = ptr = cur->bc_ptrs[level];
-	/*
-	 * If we're off the left edge, return failure.
-	 */
-	if (ptr == 0) {
-		*stat = 0;
-		return 0;
-	}
-	XFS_STATS_INC(xs_abt_insrec);
-	/*
-	 * Get pointers to the btree buffer and block.
-	 */
-	bp = cur->bc_bufs[level];
-	block = XFS_BUF_TO_ALLOC_BLOCK(bp);
-	numrecs = be16_to_cpu(block->bb_numrecs);
-#ifdef DEBUG
-	if ((error = xfs_btree_check_sblock(cur, block, level, bp)))
-		return error;
-	/*
-	 * Check that the new entry is being inserted in the right place.
-	 */
-	if (ptr <= numrecs) {
-		if (level == 0) {
-			rp = XFS_ALLOC_REC_ADDR(block, ptr, cur);
-			xfs_btree_check_rec(cur->bc_btnum, recp, rp);
+			rrp = XFS_ALLOC_REC_ADDR(cur->bc_mp, block, numrecs);
+			len = rrp->ar_blockcount;
 		} else {
-			kp = XFS_ALLOC_KEY_ADDR(block, ptr, cur);
-			xfs_btree_check_key(cur->bc_btnum, &key, kp);
-		}
-	}
-#endif
-	nbno = NULLAGBLOCK;
-	ncur = NULL;
-	/*
-	 * If the block is full, we can't insert the new entry until we
-	 * make the block un-full.
-	 */
-	if (numrecs == XFS_ALLOC_BLOCK_MAXRECS(level, cur)) {
-		/*
-		 * First, try shifting an entry to the right neighbor.
-		 */
-		if ((error = xfs_alloc_rshift(cur, level, &i)))
-			return error;
-		if (i) {
-			/* nothing */
-		}
-		/*
-		 * Next, try shifting an entry to the left neighbor.
-		 */
-		else {
-			if ((error = xfs_alloc_lshift(cur, level, &i)))
-				return error;
-			if (i)
-				optr = ptr = cur->bc_ptrs[level];
-			else {
-				/*
-				 * Next, try splitting the current block in
-				 * half. If this works we have to re-set our
-				 * variables because we could be in a
-				 * different block now.
-				 */
-				if ((error = xfs_alloc_split(cur, level, &nbno,
-						&nkey, &ncur, &i)))
-					return error;
-				if (i) {
-					bp = cur->bc_bufs[level];
-					block = XFS_BUF_TO_ALLOC_BLOCK(bp);
-#ifdef DEBUG
-					if ((error =
-						xfs_btree_check_sblock(cur,
-							block, level, bp)))
-						return error;
-#endif
-					ptr = cur->bc_ptrs[level];
-					nrec.ar_startblock = nkey.ar_startblock;
-					nrec.ar_blockcount = nkey.ar_blockcount;
-				}
-				/*
-				 * Otherwise the insert fails.
-				 */
-				else {
-					*stat = 0;
-					return 0;
-				}
-			}
-		}
-	}
-	/*
-	 * At this point we know there's room for our new entry in the block
-	 * we're pointing at.
-	 */
-	numrecs = be16_to_cpu(block->bb_numrecs);
-	if (level > 0) {
-		/*
-		 * It's a non-leaf entry.  Make a hole for the new data
-		 * in the key and ptr regions of the block.
-		 */
-		kp = XFS_ALLOC_KEY_ADDR(block, 1, cur);
-		pp = XFS_ALLOC_PTR_ADDR(block, 1, cur);
-#ifdef DEBUG
-		for (i = numrecs; i >= ptr; i--) {
-			if ((error = xfs_btree_check_sptr(cur, be32_to_cpu(pp[i - 1]), level)))
-				return error;
+			len = 0;
 		}
-#endif
-		memmove(&kp[ptr], &kp[ptr - 1],
-			(numrecs - ptr + 1) * sizeof(*kp));
-		memmove(&pp[ptr], &pp[ptr - 1],
-			(numrecs - ptr + 1) * sizeof(*pp));
-#ifdef DEBUG
-		if ((error = xfs_btree_check_sptr(cur, *bnop, level)))
-			return error;
-#endif
-		/*
-		 * Now stuff the new data in, bump numrecs and log the new data.
-		 */
-		kp[ptr - 1] = key;
-		pp[ptr - 1] = cpu_to_be32(*bnop);
-		numrecs++;
-		block->bb_numrecs = cpu_to_be16(numrecs);
-		xfs_alloc_log_keys(cur, bp, ptr, numrecs);
-		xfs_alloc_log_ptrs(cur, bp, ptr, numrecs);
-#ifdef DEBUG
-		if (ptr < numrecs)
-			xfs_btree_check_key(cur->bc_btnum, kp + ptr - 1,
-				kp + ptr);
-#endif
-	} else {
-		/*
-		 * It's a leaf entry.  Make a hole for the new record.
-		 */
-		rp = XFS_ALLOC_REC_ADDR(block, 1, cur);
-		memmove(&rp[ptr], &rp[ptr - 1],
-			(numrecs - ptr + 1) * sizeof(*rp));
-		/*
-		 * Now stuff the new record in, bump numrecs
-		 * and log the new data.
-		 */
-		rp[ptr - 1] = *recp;
-		numrecs++;
-		block->bb_numrecs = cpu_to_be16(numrecs);
-		xfs_alloc_log_recs(cur, bp, ptr, numrecs);
-#ifdef DEBUG
-		if (ptr < numrecs)
-			xfs_btree_check_rec(cur->bc_btnum, rp + ptr - 1,
-				rp + ptr);
-#endif
-	}
-	/*
-	 * Log the new number of records in the btree header.
-	 */
-	xfs_alloc_log_block(cur->bc_tp, bp, XFS_BB_NUMRECS);
-	/*
-	 * If we inserted at the start of a block, update the parents' keys.
-	 */
-	if (optr == 1 && (error = xfs_alloc_updkey(cur, &key, level + 1)))
-		return error;
-	/*
-	 * Look to see if the longest extent in the allocation group
-	 * needs to be updated.
-	 */
 
-	agf = XFS_BUF_TO_AGF(cur->bc_private.a.agbp);
-	if (level == 0 &&
-	    cur->bc_btnum == XFS_BTNUM_CNT &&
-	    be32_to_cpu(block->bb_rightsib) == NULLAGBLOCK &&
-	    be32_to_cpu(recp->ar_blockcount) > be32_to_cpu(agf->agf_longest)) {
-		/*
-		 * If this is a leaf in the by-size btree and there
-		 * is no right sibling block and this block is bigger
-		 * than the previous longest block, update it.
-		 */
-		agf->agf_longest = recp->ar_blockcount;
-		cur->bc_mp->m_perag[be32_to_cpu(agf->agf_seqno)].pagf_longest
-			= be32_to_cpu(recp->ar_blockcount);
-		xfs_alloc_log_agf(cur->bc_tp, cur->bc_private.a.agbp,
-			XFS_AGF_LONGEST);
+		break;
+	default:
+		ASSERT(0);
+		return;
 	}
-	/*
-	 * Return the new block number, if any.
-	 * If there is one, give back a record value and a cursor too.
-	 */
-	*bnop = nbno;
-	if (nbno != NULLAGBLOCK) {
-		*recp = nrec;
-		*curp = ncur;
-	}
-	*stat = 1;
-	return 0;
+
+	agf->agf_longest = len;
+	cur->bc_mp->m_perag[seqno].pagf_longest = be32_to_cpu(len);
+	xfs_alloc_log_agf(cur->bc_tp, cur->bc_private.a.agbp, XFS_AGF_LONGEST);
 }
 
-/*
- * Log header fields from a btree block.
- */
-STATIC void
-xfs_alloc_log_block(
-	xfs_trans_t		*tp,	/* transaction pointer */
-	xfs_buf_t		*bp,	/* buffer containing btree block */
-	int			fields)	/* mask of fields: XFS_BB_... */
+STATIC int
+xfs_allocbt_get_minrecs(
+	struct xfs_btree_cur	*cur,
+	int			level)
 {
-	int			first;	/* first byte offset logged */
-	int			last;	/* last byte offset logged */
-	static const short	offsets[] = {	/* table of offsets */
-		offsetof(xfs_alloc_block_t, bb_magic),
-		offsetof(xfs_alloc_block_t, bb_level),
-		offsetof(xfs_alloc_block_t, bb_numrecs),
-		offsetof(xfs_alloc_block_t, bb_leftsib),
-		offsetof(xfs_alloc_block_t, bb_rightsib),
-		sizeof(xfs_alloc_block_t)
-	};
+	return cur->bc_mp->m_alloc_mnr[level != 0];
+}
 
-	xfs_btree_offsets(fields, offsets, XFS_BB_NUM_BITS, &first, &last);
-	xfs_trans_log_buf(tp, bp, first, last);
+STATIC int
+xfs_allocbt_get_maxrecs(
+	struct xfs_btree_cur	*cur,
+	int			level)
+{
+	return cur->bc_mp->m_alloc_mxr[level != 0];
 }
 
-/*
- * Log keys from a btree block (nonleaf).
- */
 STATIC void
-xfs_alloc_log_keys(
-	xfs_btree_cur_t		*cur,	/* btree cursor */
-	xfs_buf_t		*bp,	/* buffer containing btree block */
-	int			kfirst,	/* index of first key to log */
-	int			klast)	/* index of last key to log */
+xfs_allocbt_init_key_from_rec(
+	union xfs_btree_key	*key,
+	union xfs_btree_rec	*rec)
 {
-	xfs_alloc_block_t	*block;	/* btree block to log from */
-	int			first;	/* first byte offset logged */
-	xfs_alloc_key_t		*kp;	/* key pointer in btree block */
-	int			last;	/* last byte offset logged */
+	ASSERT(rec->alloc.ar_startblock != 0);
 
-	block = XFS_BUF_TO_ALLOC_BLOCK(bp);
-	kp = XFS_ALLOC_KEY_ADDR(block, 1, cur);
-	first = (int)((xfs_caddr_t)&kp[kfirst - 1] - (xfs_caddr_t)block);
-	last = (int)(((xfs_caddr_t)&kp[klast] - 1) - (xfs_caddr_t)block);
-	xfs_trans_log_buf(cur->bc_tp, bp, first, last);
+	key->alloc.ar_startblock = rec->alloc.ar_startblock;
+	key->alloc.ar_blockcount = rec->alloc.ar_blockcount;
 }
 
-/*
- * Log block pointer fields from a btree block (nonleaf).
- */
 STATIC void
-xfs_alloc_log_ptrs(
-	xfs_btree_cur_t		*cur,	/* btree cursor */
-	xfs_buf_t		*bp,	/* buffer containing btree block */
-	int			pfirst,	/* index of first pointer to log */
-	int			plast)	/* index of last pointer to log */
+xfs_allocbt_init_rec_from_key(
+	union xfs_btree_key	*key,
+	union xfs_btree_rec	*rec)
 {
-	xfs_alloc_block_t	*block;	/* btree block to log from */
-	int			first;	/* first byte offset logged */
-	int			last;	/* last byte offset logged */
-	xfs_alloc_ptr_t		*pp;	/* block-pointer pointer in btree blk */
+	ASSERT(key->alloc.ar_startblock != 0);
 
-	block = XFS_BUF_TO_ALLOC_BLOCK(bp);
-	pp = XFS_ALLOC_PTR_ADDR(block, 1, cur);
-	first = (int)((xfs_caddr_t)&pp[pfirst - 1] - (xfs_caddr_t)block);
-	last = (int)(((xfs_caddr_t)&pp[plast] - 1) - (xfs_caddr_t)block);
-	xfs_trans_log_buf(cur->bc_tp, bp, first, last);
+	rec->alloc.ar_startblock = key->alloc.ar_startblock;
+	rec->alloc.ar_blockcount = key->alloc.ar_blockcount;
 }
 
-/*
- * Log records from a btree block (leaf).
- */
 STATIC void
-xfs_alloc_log_recs(
-	xfs_btree_cur_t		*cur,	/* btree cursor */
-	xfs_buf_t		*bp,	/* buffer containing btree block */
-	int			rfirst,	/* index of first record to log */
-	int			rlast)	/* index of last record to log */
+xfs_allocbt_init_rec_from_cur(
+	struct xfs_btree_cur	*cur,
+	union xfs_btree_rec	*rec)
 {
-	xfs_alloc_block_t	*block;	/* btree block to log from */
-	int			first;	/* first byte offset logged */
-	int			last;	/* last byte offset logged */
-	xfs_alloc_rec_t		*rp;	/* record pointer for btree block */
-
+	ASSERT(cur->bc_rec.a.ar_startblock != 0);
 
-	block = XFS_BUF_TO_ALLOC_BLOCK(bp);
-	rp = XFS_ALLOC_REC_ADDR(block, 1, cur);
-#ifdef DEBUG
-	{
-		xfs_agf_t	*agf;
-		xfs_alloc_rec_t	*p;
-
-		agf = XFS_BUF_TO_AGF(cur->bc_private.a.agbp);
-		for (p = &rp[rfirst - 1]; p <= &rp[rlast - 1]; p++)
-			ASSERT(be32_to_cpu(p->ar_startblock) +
-			       be32_to_cpu(p->ar_blockcount) <=
-			       be32_to_cpu(agf->agf_length));
-	}
-#endif
-	first = (int)((xfs_caddr_t)&rp[rfirst - 1] - (xfs_caddr_t)block);
-	last = (int)(((xfs_caddr_t)&rp[rlast] - 1) - (xfs_caddr_t)block);
-	xfs_trans_log_buf(cur->bc_tp, bp, first, last);
+	rec->alloc.ar_startblock = cpu_to_be32(cur->bc_rec.a.ar_startblock);
+	rec->alloc.ar_blockcount = cpu_to_be32(cur->bc_rec.a.ar_blockcount);
 }
 
-/*
- * Lookup the record.  The cursor is made to point to it, based on dir.
- * Return 0 if can't find any such record, 1 for success.
- */
-STATIC int				/* error */
-xfs_alloc_lookup(
-	xfs_btree_cur_t		*cur,	/* btree cursor */
-	xfs_lookup_t		dir,	/* <=, ==, or >= */
-	int			*stat)	/* success/failure */
+STATIC void
+xfs_allocbt_init_ptr_from_cur(
+	struct xfs_btree_cur	*cur,
+	union xfs_btree_ptr	*ptr)
 {
-	xfs_agblock_t		agbno;	/* a.g. relative btree block number */
-	xfs_agnumber_t		agno;	/* allocation group number */
-	xfs_alloc_block_t	*block=NULL;	/* current btree block */
-	int			diff;	/* difference for the current key */
-	int			error;	/* error return value */
-	int			keyno=0;	/* current key number */
-	int			level;	/* level in the btree */
-	xfs_mount_t		*mp;	/* file system mount point */
-
-	XFS_STATS_INC(xs_abt_lookup);
-	/*
-	 * Get the allocation group header, and the root block number.
-	 */
-	mp = cur->bc_mp;
-
-	{
-		xfs_agf_t	*agf;	/* a.g. freespace header */
-
-		agf = XFS_BUF_TO_AGF(cur->bc_private.a.agbp);
-		agno = be32_to_cpu(agf->agf_seqno);
-		agbno = be32_to_cpu(agf->agf_roots[cur->bc_btnum]);
-	}
-	/*
-	 * Iterate over each level in the btree, starting at the root.
-	 * For each level above the leaves, find the key we need, based
-	 * on the lookup record, then follow the corresponding block
-	 * pointer down to the next level.
-	 */
-	for (level = cur->bc_nlevels - 1, diff = 1; level >= 0; level--) {
-		xfs_buf_t	*bp;	/* buffer pointer for btree block */
-		xfs_daddr_t	d;	/* disk address of btree block */
-
-		/*
-		 * Get the disk address we're looking for.
-		 */
-		d = XFS_AGB_TO_DADDR(mp, agno, agbno);
-		/*
-		 * If the old buffer at this level is for a different block,
-		 * throw it away, otherwise just use it.
-		 */
-		bp = cur->bc_bufs[level];
-		if (bp && XFS_BUF_ADDR(bp) != d)
-			bp = NULL;
-		if (!bp) {
-			/*
-			 * Need to get a new buffer.  Read it, then
-			 * set it in the cursor, releasing the old one.
-			 */
-			if ((error = xfs_btree_read_bufs(mp, cur->bc_tp, agno,
-					agbno, 0, &bp, XFS_ALLOC_BTREE_REF)))
-				return error;
-			xfs_btree_setbuf(cur, level, bp);
-			/*
-			 * Point to the btree block, now that we have the buffer
-			 */
-			block = XFS_BUF_TO_ALLOC_BLOCK(bp);
-			if ((error = xfs_btree_check_sblock(cur, block, level,
-					bp)))
-				return error;
-		} else
-			block = XFS_BUF_TO_ALLOC_BLOCK(bp);
-		/*
-		 * If we already had a key match at a higher level, we know
-		 * we need to use the first entry in this block.
-		 */
-		if (diff == 0)
-			keyno = 1;
-		/*
-		 * Otherwise we need to search this block.  Do a binary search.
-		 */
-		else {
-			int		high;	/* high entry number */
-			xfs_alloc_key_t	*kkbase=NULL;/* base of keys in block */
-			xfs_alloc_rec_t	*krbase=NULL;/* base of records in block */
-			int		low;	/* low entry number */
-
-			/*
-			 * Get a pointer to keys or records.
-			 */
-			if (level > 0)
-				kkbase = XFS_ALLOC_KEY_ADDR(block, 1, cur);
-			else
-				krbase = XFS_ALLOC_REC_ADDR(block, 1, cur);
-			/*
-			 * Set low and high entry numbers, 1-based.
-			 */
-			low = 1;
-			if (!(high = be16_to_cpu(block->bb_numrecs))) {
-				/*
-				 * If the block is empty, the tree must
-				 * be an empty leaf.
-				 */
-				ASSERT(level == 0 && cur->bc_nlevels == 1);
-				cur->bc_ptrs[0] = dir != XFS_LOOKUP_LE;
-				*stat = 0;
-				return 0;
-			}
-			/*
-			 * Binary search the block.
-			 */
-			while (low <= high) {
-				xfs_extlen_t	blockcount;	/* key value */
-				xfs_agblock_t	startblock;	/* key value */
-
-				XFS_STATS_INC(xs_abt_compare);
-				/*
-				 * keyno is average of low and high.
-				 */
-				keyno = (low + high) >> 1;
-				/*
-				 * Get startblock & blockcount.
-				 */
-				if (level > 0) {
-					xfs_alloc_key_t	*kkp;
-
-					kkp = kkbase + keyno - 1;
-					startblock = be32_to_cpu(kkp->ar_startblock);
-					blockcount = be32_to_cpu(kkp->ar_blockcount);
-				} else {
-					xfs_alloc_rec_t	*krp;
+	struct xfs_agf		*agf = XFS_BUF_TO_AGF(cur->bc_private.a.agbp);
 
-					krp = krbase + keyno - 1;
-					startblock = be32_to_cpu(krp->ar_startblock);
-					blockcount = be32_to_cpu(krp->ar_blockcount);
-				}
-				/*
-				 * Compute difference to get next direction.
-				 */
-				if (cur->bc_btnum == XFS_BTNUM_BNO)
-					diff = (int)startblock -
-					       (int)cur->bc_rec.a.ar_startblock;
-				else if (!(diff = (int)blockcount -
-					    (int)cur->bc_rec.a.ar_blockcount))
-					diff = (int)startblock -
-					    (int)cur->bc_rec.a.ar_startblock;
-				/*
-				 * Less than, move right.
-				 */
-				if (diff < 0)
-					low = keyno + 1;
-				/*
-				 * Greater than, move left.
-				 */
-				else if (diff > 0)
-					high = keyno - 1;
-				/*
-				 * Equal, we're done.
-				 */
-				else
-					break;
-			}
-		}
-		/*
-		 * If there are more levels, set up for the next level
-		 * by getting the block number and filling in the cursor.
-		 */
-		if (level > 0) {
-			/*
-			 * If we moved left, need the previous key number,
-			 * unless there isn't one.
-			 */
-			if (diff > 0 && --keyno < 1)
-				keyno = 1;
-			agbno = be32_to_cpu(*XFS_ALLOC_PTR_ADDR(block, keyno, cur));
-#ifdef DEBUG
-			if ((error = xfs_btree_check_sptr(cur, agbno, level)))
-				return error;
-#endif
-			cur->bc_ptrs[level] = keyno;
-		}
-	}
-	/*
-	 * Done with the search.
-	 * See if we need to adjust the results.
-	 */
-	if (dir != XFS_LOOKUP_LE && diff < 0) {
-		keyno++;
-		/*
-		 * If ge search and we went off the end of the block, but it's
-		 * not the last block, we're in the wrong block.
-		 */
-		if (dir == XFS_LOOKUP_GE &&
-		    keyno > be16_to_cpu(block->bb_numrecs) &&
-		    be32_to_cpu(block->bb_rightsib) != NULLAGBLOCK) {
-			int	i;
+	ASSERT(cur->bc_private.a.agno == be32_to_cpu(agf->agf_seqno));
+	ASSERT(agf->agf_roots[cur->bc_btnum] != 0);
 
-			cur->bc_ptrs[0] = keyno;
-			if ((error = xfs_alloc_increment(cur, 0, &i)))
-				return error;
-			XFS_WANT_CORRUPTED_RETURN(i == 1);
-			*stat = 1;
-			return 0;
-		}
-	}
-	else if (dir == XFS_LOOKUP_LE && diff > 0)
-		keyno--;
-	cur->bc_ptrs[0] = keyno;
-	/*
-	 * Return if we succeeded or not.
-	 */
-	if (keyno == 0 || keyno > be16_to_cpu(block->bb_numrecs))
-		*stat = 0;
-	else
-		*stat = ((dir != XFS_LOOKUP_EQ) || (diff == 0));
-	return 0;
+	ptr->s = agf->agf_roots[cur->bc_btnum];
 }
 
-/*
- * Move 1 record left from cur/level if possible.
- * Update cur to reflect the new path.
- */
-STATIC int				/* error */
-xfs_alloc_lshift(
-	xfs_btree_cur_t		*cur,	/* btree cursor */
-	int			level,	/* level to shift record on */
-	int			*stat)	/* success/failure */
+STATIC __int64_t
+xfs_allocbt_key_diff(
+	struct xfs_btree_cur	*cur,
+	union xfs_btree_key	*key)
 {
-	int			error;	/* error return value */
-#ifdef DEBUG
-	int			i;	/* loop index */
-#endif
-	xfs_alloc_key_t		key;	/* key value for leaf level upward */
-	xfs_buf_t		*lbp;	/* buffer for left neighbor block */
-	xfs_alloc_block_t	*left;	/* left neighbor btree block */
-	int			nrec;	/* new number of left block entries */
-	xfs_buf_t		*rbp;	/* buffer for right (current) block */
-	xfs_alloc_block_t	*right;	/* right (current) btree block */
-	xfs_alloc_key_t		*rkp=NULL;	/* key pointer for right block */
-	xfs_alloc_ptr_t		*rpp=NULL;	/* address pointer for right block */
-	xfs_alloc_rec_t		*rrp=NULL;	/* record pointer for right block */
+	xfs_alloc_rec_incore_t	*rec = &cur->bc_rec.a;
+	xfs_alloc_key_t		*kp = &key->alloc;
+	__int64_t		diff;
 
-	/*
-	 * Set up variables for this block as "right".
-	 */
-	rbp = cur->bc_bufs[level];
-	right = XFS_BUF_TO_ALLOC_BLOCK(rbp);
-#ifdef DEBUG
-	if ((error = xfs_btree_check_sblock(cur, right, level, rbp)))
-		return error;
-#endif
-	/*
-	 * If we've got no left sibling then we can't shift an entry left.
-	 */
-	if (be32_to_cpu(right->bb_leftsib) == NULLAGBLOCK) {
-		*stat = 0;
-		return 0;
-	}
-	/*
-	 * If the cursor entry is the one that would be moved, don't
-	 * do it... it's too complicated.
-	 */
-	if (cur->bc_ptrs[level] <= 1) {
-		*stat = 0;
-		return 0;
-	}
-	/*
-	 * Set up the left neighbor as "left".
-	 */
-	if ((error = xfs_btree_read_bufs(cur->bc_mp, cur->bc_tp,
-			cur->bc_private.a.agno, be32_to_cpu(right->bb_leftsib),
-			0, &lbp, XFS_ALLOC_BTREE_REF)))
-		return error;
-	left = XFS_BUF_TO_ALLOC_BLOCK(lbp);
-	if ((error = xfs_btree_check_sblock(cur, left, level, lbp)))
-		return error;
-	/*
-	 * If it's full, it can't take another entry.
-	 */
-	if (be16_to_cpu(left->bb_numrecs) == XFS_ALLOC_BLOCK_MAXRECS(level, cur)) {
-		*stat = 0;
-		return 0;
+	if (cur->bc_btnum == XFS_BTNUM_BNO) {
+		return (__int64_t)be32_to_cpu(kp->ar_startblock) -
+				rec->ar_startblock;
 	}
-	nrec = be16_to_cpu(left->bb_numrecs) + 1;
-	/*
-	 * If non-leaf, copy a key and a ptr to the left block.
-	 */
-	if (level > 0) {
-		xfs_alloc_key_t	*lkp;	/* key pointer for left block */
-		xfs_alloc_ptr_t	*lpp;	/* address pointer for left block */
 
-		lkp = XFS_ALLOC_KEY_ADDR(left, nrec, cur);
-		rkp = XFS_ALLOC_KEY_ADDR(right, 1, cur);
-		*lkp = *rkp;
-		xfs_alloc_log_keys(cur, lbp, nrec, nrec);
-		lpp = XFS_ALLOC_PTR_ADDR(left, nrec, cur);
-		rpp = XFS_ALLOC_PTR_ADDR(right, 1, cur);
-#ifdef DEBUG
-		if ((error = xfs_btree_check_sptr(cur, be32_to_cpu(*rpp), level)))
-			return error;
-#endif
-		*lpp = *rpp;
-		xfs_alloc_log_ptrs(cur, lbp, nrec, nrec);
-		xfs_btree_check_key(cur->bc_btnum, lkp - 1, lkp);
-	}
-	/*
-	 * If leaf, copy a record to the left block.
-	 */
-	else {
-		xfs_alloc_rec_t	*lrp;	/* record pointer for left block */
+	diff = (__int64_t)be32_to_cpu(kp->ar_blockcount) - rec->ar_blockcount;
+	if (diff)
+		return diff;
 
-		lrp = XFS_ALLOC_REC_ADDR(left, nrec, cur);
-		rrp = XFS_ALLOC_REC_ADDR(right, 1, cur);
-		*lrp = *rrp;
-		xfs_alloc_log_recs(cur, lbp, nrec, nrec);
-		xfs_btree_check_rec(cur->bc_btnum, lrp - 1, lrp);
-	}
-	/*
-	 * Bump and log left's numrecs, decrement and log right's numrecs.
-	 */
-	be16_add_cpu(&left->bb_numrecs, 1);
-	xfs_alloc_log_block(cur->bc_tp, lbp, XFS_BB_NUMRECS);
-	be16_add_cpu(&right->bb_numrecs, -1);
-	xfs_alloc_log_block(cur->bc_tp, rbp, XFS_BB_NUMRECS);
-	/*
-	 * Slide the contents of right down one entry.
-	 */
-	if (level > 0) {
-#ifdef DEBUG
-		for (i = 0; i < be16_to_cpu(right->bb_numrecs); i++) {
-			if ((error = xfs_btree_check_sptr(cur, be32_to_cpu(rpp[i + 1]),
-					level)))
-				return error;
-		}
-#endif
-		memmove(rkp, rkp + 1, be16_to_cpu(right->bb_numrecs) * sizeof(*rkp));
-		memmove(rpp, rpp + 1, be16_to_cpu(right->bb_numrecs) * sizeof(*rpp));
-		xfs_alloc_log_keys(cur, rbp, 1, be16_to_cpu(right->bb_numrecs));
-		xfs_alloc_log_ptrs(cur, rbp, 1, be16_to_cpu(right->bb_numrecs));
-	} else {
-		memmove(rrp, rrp + 1, be16_to_cpu(right->bb_numrecs) * sizeof(*rrp));
-		xfs_alloc_log_recs(cur, rbp, 1, be16_to_cpu(right->bb_numrecs));
-		key.ar_startblock = rrp->ar_startblock;
-		key.ar_blockcount = rrp->ar_blockcount;
-		rkp = &key;
-	}
-	/*
-	 * Update the parent key values of right.
-	 */
-	if ((error = xfs_alloc_updkey(cur, rkp, level + 1)))
-		return error;
-	/*
-	 * Slide the cursor value left one.
-	 */
-	cur->bc_ptrs[level]--;
-	*stat = 1;
-	return 0;
+	return (__int64_t)be32_to_cpu(kp->ar_startblock) - rec->ar_startblock;
 }
 
-/*
- * Allocate a new root block, fill it in.
- */
-STATIC int				/* error */
-xfs_alloc_newroot(
-	xfs_btree_cur_t		*cur,	/* btree cursor */
-	int			*stat)	/* success/failure */
+STATIC int
+xfs_allocbt_kill_root(
+	struct xfs_btree_cur	*cur,
+	struct xfs_buf		*bp,
+	int			level,
+	union xfs_btree_ptr	*newroot)
 {
-	int			error;	/* error return value */
-	xfs_agblock_t		lbno;	/* left block number */
-	xfs_buf_t		*lbp;	/* left btree buffer */
-	xfs_alloc_block_t	*left;	/* left btree block */
-	xfs_mount_t		*mp;	/* mount structure */
-	xfs_agblock_t		nbno;	/* new block number */
-	xfs_buf_t		*nbp;	/* new (root) buffer */
-	xfs_alloc_block_t	*new;	/* new (root) btree block */
-	int			nptr;	/* new value for key index, 1 or 2 */
-	xfs_agblock_t		rbno;	/* right block number */
-	xfs_buf_t		*rbp;	/* right btree buffer */
-	xfs_alloc_block_t	*right;	/* right btree block */
-
-	mp = cur->bc_mp;
+	int			error;
 
-	ASSERT(cur->bc_nlevels < XFS_AG_MAXLEVELS(mp));
-	/*
-	 * Get a buffer from the freelist blocks, for the new root.
-	 */
-	error = xfs_alloc_get_freelist(cur->bc_tp,
-					cur->bc_private.a.agbp, &nbno, 1);
-	if (error)
-		return error;
-	/*
-	 * None available, we fail.
-	 */
-	if (nbno == NULLAGBLOCK) {
-		*stat = 0;
-		return 0;
-	}
-	xfs_trans_agbtree_delta(cur->bc_tp, 1);
-	nbp = xfs_btree_get_bufs(mp, cur->bc_tp, cur->bc_private.a.agno, nbno,
-		0);
-	new = XFS_BUF_TO_ALLOC_BLOCK(nbp);
-	/*
-	 * Set the root data in the a.g. freespace structure.
-	 */
-	{
-		xfs_agf_t	*agf;	/* a.g. freespace header */
-		xfs_agnumber_t	seqno;
+	XFS_BTREE_TRACE_CURSOR(cur, XBT_ENTRY);
+	XFS_BTREE_STATS_INC(cur, killroot);
 
-		agf = XFS_BUF_TO_AGF(cur->bc_private.a.agbp);
-		agf->agf_roots[cur->bc_btnum] = cpu_to_be32(nbno);
-		be32_add_cpu(&agf->agf_levels[cur->bc_btnum], 1);
-		seqno = be32_to_cpu(agf->agf_seqno);
-		mp->m_perag[seqno].pagf_levels[cur->bc_btnum]++;
-		xfs_alloc_log_agf(cur->bc_tp, cur->bc_private.a.agbp,
-			XFS_AGF_ROOTS | XFS_AGF_LEVELS);
-	}
 	/*
-	 * At the previous root level there are now two blocks: the old
-	 * root, and the new block generated when it was split.
-	 * We don't know which one the cursor is pointing at, so we
-	 * set up variables "left" and "right" for each case.
+	 * Update the root pointer, decreasing the level by 1 and then
+	 * free the old root.
 	 */
-	lbp = cur->bc_bufs[cur->bc_nlevels - 1];
-	left = XFS_BUF_TO_ALLOC_BLOCK(lbp);
-#ifdef DEBUG
-	if ((error = xfs_btree_check_sblock(cur, left, cur->bc_nlevels - 1, lbp)))
+	xfs_allocbt_set_root(cur, newroot, -1);
+	error = xfs_allocbt_free_block(cur, bp);
+	if (error) {
+		XFS_BTREE_TRACE_CURSOR(cur, XBT_ERROR);
 		return error;
-#endif
-	if (be32_to_cpu(left->bb_rightsib) != NULLAGBLOCK) {
-		/*
-		 * Our block is left, pick up the right block.
-		 */
-		lbno = XFS_DADDR_TO_AGBNO(mp, XFS_BUF_ADDR(lbp));
-		rbno = be32_to_cpu(left->bb_rightsib);
-		if ((error = xfs_btree_read_bufs(mp, cur->bc_tp,
-				cur->bc_private.a.agno, rbno, 0, &rbp,
-				XFS_ALLOC_BTREE_REF)))
-			return error;
-		right = XFS_BUF_TO_ALLOC_BLOCK(rbp);
-		if ((error = xfs_btree_check_sblock(cur, right,
-				cur->bc_nlevels - 1, rbp)))
-			return error;
-		nptr = 1;
-	} else {
-		/*
-		 * Our block is right, pick up the left block.
-		 */
-		rbp = lbp;
-		right = left;
-		rbno = XFS_DADDR_TO_AGBNO(mp, XFS_BUF_ADDR(rbp));
-		lbno = be32_to_cpu(right->bb_leftsib);
-		if ((error = xfs_btree_read_bufs(mp, cur->bc_tp,
-				cur->bc_private.a.agno, lbno, 0, &lbp,
-				XFS_ALLOC_BTREE_REF)))
-			return error;
-		left = XFS_BUF_TO_ALLOC_BLOCK(lbp);
-		if ((error = xfs_btree_check_sblock(cur, left,
-				cur->bc_nlevels - 1, lbp)))
-			return error;
-		nptr = 2;
 	}
-	/*
-	 * Fill in the new block's btree header and log it.
-	 */
-	new->bb_magic = cpu_to_be32(xfs_magics[cur->bc_btnum]);
-	new->bb_level = cpu_to_be16(cur->bc_nlevels);
-	new->bb_numrecs = cpu_to_be16(2);
-	new->bb_leftsib = cpu_to_be32(NULLAGBLOCK);
-	new->bb_rightsib = cpu_to_be32(NULLAGBLOCK);
-	xfs_alloc_log_block(cur->bc_tp, nbp, XFS_BB_ALL_BITS);
-	ASSERT(lbno != NULLAGBLOCK && rbno != NULLAGBLOCK);
-	/*
-	 * Fill in the key data in the new root.
-	 */
-	{
-		xfs_alloc_key_t		*kp;	/* btree key pointer */
 
-		kp = XFS_ALLOC_KEY_ADDR(new, 1, cur);
-		if (be16_to_cpu(left->bb_level) > 0) {
-			kp[0] = *XFS_ALLOC_KEY_ADDR(left, 1, cur);
-			kp[1] = *XFS_ALLOC_KEY_ADDR(right, 1, cur);
-		} else {
-			xfs_alloc_rec_t	*rp;	/* btree record pointer */
+	XFS_BTREE_STATS_INC(cur, free);
 
-			rp = XFS_ALLOC_REC_ADDR(left, 1, cur);
-			kp[0].ar_startblock = rp->ar_startblock;
-			kp[0].ar_blockcount = rp->ar_blockcount;
-			rp = XFS_ALLOC_REC_ADDR(right, 1, cur);
-			kp[1].ar_startblock = rp->ar_startblock;
-			kp[1].ar_blockcount = rp->ar_blockcount;
-		}
-	}
-	xfs_alloc_log_keys(cur, nbp, 1, 2);
-	/*
-	 * Fill in the pointer data in the new root.
-	 */
-	{
-		xfs_alloc_ptr_t		*pp;	/* btree address pointer */
+	xfs_btree_setbuf(cur, level, NULL);
+	cur->bc_nlevels--;
 
-		pp = XFS_ALLOC_PTR_ADDR(new, 1, cur);
-		pp[0] = cpu_to_be32(lbno);
-		pp[1] = cpu_to_be32(rbno);
-	}
-	xfs_alloc_log_ptrs(cur, nbp, 1, 2);
-	/*
-	 * Fix up the cursor.
-	 */
-	xfs_btree_setbuf(cur, cur->bc_nlevels, nbp);
-	cur->bc_ptrs[cur->bc_nlevels] = nptr;
-	cur->bc_nlevels++;
-	*stat = 1;
+	XFS_BTREE_TRACE_CURSOR(cur, XBT_EXIT);
 	return 0;
 }
 
-/*
- * Move 1 record right from cur/level if possible.
- * Update cur to reflect the new path.
- */
-STATIC int				/* error */
-xfs_alloc_rshift(
-	xfs_btree_cur_t		*cur,	/* btree cursor */
-	int			level,	/* level to shift record on */
-	int			*stat)	/* success/failure */
-{
-	int			error;	/* error return value */
-	int			i;	/* loop index */
-	xfs_alloc_key_t		key;	/* key value for leaf level upward */
-	xfs_buf_t		*lbp;	/* buffer for left (current) block */
-	xfs_alloc_block_t	*left;	/* left (current) btree block */
-	xfs_buf_t		*rbp;	/* buffer for right neighbor block */
-	xfs_alloc_block_t	*right;	/* right neighbor btree block */
-	xfs_alloc_key_t		*rkp;	/* key pointer for right block */
-	xfs_btree_cur_t		*tcur;	/* temporary cursor */
-
-	/*
-	 * Set up variables for this block as "left".
-	 */
-	lbp = cur->bc_bufs[level];
-	left = XFS_BUF_TO_ALLOC_BLOCK(lbp);
-#ifdef DEBUG
-	if ((error = xfs_btree_check_sblock(cur, left, level, lbp)))
-		return error;
-#endif
-	/*
-	 * If we've got no right sibling then we can't shift an entry right.
-	 */
-	if (be32_to_cpu(left->bb_rightsib) == NULLAGBLOCK) {
-		*stat = 0;
-		return 0;
-	}
-	/*
-	 * If the cursor entry is the one that would be moved, don't
-	 * do it... it's too complicated.
-	 */
-	if (cur->bc_ptrs[level] >= be16_to_cpu(left->bb_numrecs)) {
-		*stat = 0;
-		return 0;
-	}
-	/*
-	 * Set up the right neighbor as "right".
-	 */
-	if ((error = xfs_btree_read_bufs(cur->bc_mp, cur->bc_tp,
-			cur->bc_private.a.agno, be32_to_cpu(left->bb_rightsib),
-			0, &rbp, XFS_ALLOC_BTREE_REF)))
-		return error;
-	right = XFS_BUF_TO_ALLOC_BLOCK(rbp);
-	if ((error = xfs_btree_check_sblock(cur, right, level, rbp)))
-		return error;
-	/*
-	 * If it's full, it can't take another entry.
-	 */
-	if (be16_to_cpu(right->bb_numrecs) == XFS_ALLOC_BLOCK_MAXRECS(level, cur)) {
-		*stat = 0;
-		return 0;
-	}
-	/*
-	 * Make a hole at the start of the right neighbor block, then
-	 * copy the last left block entry to the hole.
-	 */
-	if (level > 0) {
-		xfs_alloc_key_t	*lkp;	/* key pointer for left block */
-		xfs_alloc_ptr_t	*lpp;	/* address pointer for left block */
-		xfs_alloc_ptr_t	*rpp;	/* address pointer for right block */
-
-		lkp = XFS_ALLOC_KEY_ADDR(left, be16_to_cpu(left->bb_numrecs), cur);
-		lpp = XFS_ALLOC_PTR_ADDR(left, be16_to_cpu(left->bb_numrecs), cur);
-		rkp = XFS_ALLOC_KEY_ADDR(right, 1, cur);
-		rpp = XFS_ALLOC_PTR_ADDR(right, 1, cur);
 #ifdef DEBUG
-		for (i = be16_to_cpu(right->bb_numrecs) - 1; i >= 0; i--) {
-			if ((error = xfs_btree_check_sptr(cur, be32_to_cpu(rpp[i]), level)))
-				return error;
-		}
-#endif
-		memmove(rkp + 1, rkp, be16_to_cpu(right->bb_numrecs) * sizeof(*rkp));
-		memmove(rpp + 1, rpp, be16_to_cpu(right->bb_numrecs) * sizeof(*rpp));
-#ifdef DEBUG
-		if ((error = xfs_btree_check_sptr(cur, be32_to_cpu(*lpp), level)))
-			return error;
-#endif
-		*rkp = *lkp;
-		*rpp = *lpp;
-		xfs_alloc_log_keys(cur, rbp, 1, be16_to_cpu(right->bb_numrecs) + 1);
-		xfs_alloc_log_ptrs(cur, rbp, 1, be16_to_cpu(right->bb_numrecs) + 1);
-		xfs_btree_check_key(cur->bc_btnum, rkp, rkp + 1);
+STATIC int
+xfs_allocbt_keys_inorder(
+	struct xfs_btree_cur	*cur,
+	union xfs_btree_key	*k1,
+	union xfs_btree_key	*k2)
+{
+	if (cur->bc_btnum == XFS_BTNUM_BNO) {
+		return be32_to_cpu(k1->alloc.ar_startblock) <
+		       be32_to_cpu(k2->alloc.ar_startblock);
 	} else {
-		xfs_alloc_rec_t	*lrp;	/* record pointer for left block */
-		xfs_alloc_rec_t	*rrp;	/* record pointer for right block */
-
-		lrp = XFS_ALLOC_REC_ADDR(left, be16_to_cpu(left->bb_numrecs), cur);
-		rrp = XFS_ALLOC_REC_ADDR(right, 1, cur);
-		memmove(rrp + 1, rrp, be16_to_cpu(right->bb_numrecs) * sizeof(*rrp));
-		*rrp = *lrp;
-		xfs_alloc_log_recs(cur, rbp, 1, be16_to_cpu(right->bb_numrecs) + 1);
-		key.ar_startblock = rrp->ar_startblock;
-		key.ar_blockcount = rrp->ar_blockcount;
-		rkp = &key;
-		xfs_btree_check_rec(cur->bc_btnum, rrp, rrp + 1);
+		return be32_to_cpu(k1->alloc.ar_blockcount) <
+			be32_to_cpu(k2->alloc.ar_blockcount) ||
+			(k1->alloc.ar_blockcount == k2->alloc.ar_blockcount &&
+			 be32_to_cpu(k1->alloc.ar_startblock) <
+			 be32_to_cpu(k2->alloc.ar_startblock));
 	}
-	/*
-	 * Decrement and log left's numrecs, bump and log right's numrecs.
-	 */
-	be16_add_cpu(&left->bb_numrecs, -1);
-	xfs_alloc_log_block(cur->bc_tp, lbp, XFS_BB_NUMRECS);
-	be16_add_cpu(&right->bb_numrecs, 1);
-	xfs_alloc_log_block(cur->bc_tp, rbp, XFS_BB_NUMRECS);
-	/*
-	 * Using a temporary cursor, update the parent key values of the
-	 * block on the right.
-	 */
-	if ((error = xfs_btree_dup_cursor(cur, &tcur)))
-		return error;
-	i = xfs_btree_lastrec(tcur, level);
-	XFS_WANT_CORRUPTED_GOTO(i == 1, error0);
-	if ((error = xfs_alloc_increment(tcur, level, &i)) ||
-	    (error = xfs_alloc_updkey(tcur, rkp, level + 1)))
-		goto error0;
-	xfs_btree_del_cursor(tcur, XFS_BTREE_NOERROR);
-	*stat = 1;
-	return 0;
-error0:
-	xfs_btree_del_cursor(tcur, XFS_BTREE_ERROR);
-	return error;
 }
 
-/*
- * Split cur/level block in half.
- * Return new block number and its first record (to be inserted into parent).
- */
-STATIC int				/* error */
-xfs_alloc_split(
-	xfs_btree_cur_t		*cur,	/* btree cursor */
-	int			level,	/* level to split */
-	xfs_agblock_t		*bnop,	/* output: block number allocated */
-	xfs_alloc_key_t		*keyp,	/* output: first key of new block */
-	xfs_btree_cur_t		**curp,	/* output: new cursor */
-	int			*stat)	/* success/failure */
+STATIC int
+xfs_allocbt_recs_inorder(
+	struct xfs_btree_cur	*cur,
+	union xfs_btree_rec	*r1,
+	union xfs_btree_rec	*r2)
 {
-	int			error;	/* error return value */
-	int			i;	/* loop index/record number */
-	xfs_agblock_t		lbno;	/* left (current) block number */
-	xfs_buf_t		*lbp;	/* buffer for left block */
-	xfs_alloc_block_t	*left;	/* left (current) btree block */
-	xfs_agblock_t		rbno;	/* right (new) block number */
-	xfs_buf_t		*rbp;	/* buffer for right block */
-	xfs_alloc_block_t	*right;	/* right (new) btree block */
-
-	/*
-	 * Allocate the new block from the freelist.
-	 * If we can't do it, we're toast.  Give up.
-	 */
-	error = xfs_alloc_get_freelist(cur->bc_tp,
-					 cur->bc_private.a.agbp, &rbno, 1);
-	if (error)
-		return error;
-	if (rbno == NULLAGBLOCK) {
-		*stat = 0;
-		return 0;
-	}
-	xfs_trans_agbtree_delta(cur->bc_tp, 1);
-	rbp = xfs_btree_get_bufs(cur->bc_mp, cur->bc_tp, cur->bc_private.a.agno,
-		rbno, 0);
-	/*
-	 * Set up the new block as "right".
-	 */
-	right = XFS_BUF_TO_ALLOC_BLOCK(rbp);
-	/*
-	 * "Left" is the current (according to the cursor) block.
-	 */
-	lbp = cur->bc_bufs[level];
-	left = XFS_BUF_TO_ALLOC_BLOCK(lbp);
-#ifdef DEBUG
-	if ((error = xfs_btree_check_sblock(cur, left, level, lbp)))
-		return error;
-#endif
-	/*
-	 * Fill in the btree header for the new block.
-	 */
-	right->bb_magic = cpu_to_be32(xfs_magics[cur->bc_btnum]);
-	right->bb_level = left->bb_level;
-	right->bb_numrecs = cpu_to_be16(be16_to_cpu(left->bb_numrecs) / 2);
-	/*
-	 * Make sure that if there's an odd number of entries now, that
-	 * each new block will have the same number of entries.
-	 */
-	if ((be16_to_cpu(left->bb_numrecs) & 1) &&
-	    cur->bc_ptrs[level] <= be16_to_cpu(right->bb_numrecs) + 1)
-		be16_add_cpu(&right->bb_numrecs, 1);
-	i = be16_to_cpu(left->bb_numrecs) - be16_to_cpu(right->bb_numrecs) + 1;
-	/*
-	 * For non-leaf blocks, copy keys and addresses over to the new block.
-	 */
-	if (level > 0) {
-		xfs_alloc_key_t	*lkp;	/* left btree key pointer */
-		xfs_alloc_ptr_t	*lpp;	/* left btree address pointer */
-		xfs_alloc_key_t	*rkp;	/* right btree key pointer */
-		xfs_alloc_ptr_t	*rpp;	/* right btree address pointer */
-
-		lkp = XFS_ALLOC_KEY_ADDR(left, i, cur);
-		lpp = XFS_ALLOC_PTR_ADDR(left, i, cur);
-		rkp = XFS_ALLOC_KEY_ADDR(right, 1, cur);
-		rpp = XFS_ALLOC_PTR_ADDR(right, 1, cur);
-#ifdef DEBUG
-		for (i = 0; i < be16_to_cpu(right->bb_numrecs); i++) {
-			if ((error = xfs_btree_check_sptr(cur, be32_to_cpu(lpp[i]), level)))
-				return error;
-		}
-#endif
-		memcpy(rkp, lkp, be16_to_cpu(right->bb_numrecs) * sizeof(*rkp));
-		memcpy(rpp, lpp, be16_to_cpu(right->bb_numrecs) * sizeof(*rpp));
-		xfs_alloc_log_keys(cur, rbp, 1, be16_to_cpu(right->bb_numrecs));
-		xfs_alloc_log_ptrs(cur, rbp, 1, be16_to_cpu(right->bb_numrecs));
-		*keyp = *rkp;
+	if (cur->bc_btnum == XFS_BTNUM_BNO) {
+		return be32_to_cpu(r1->alloc.ar_startblock) +
+			be32_to_cpu(r1->alloc.ar_blockcount) <=
+			be32_to_cpu(r2->alloc.ar_startblock);
+	} else {
+		return be32_to_cpu(r1->alloc.ar_blockcount) <
+			be32_to_cpu(r2->alloc.ar_blockcount) ||
+			(r1->alloc.ar_blockcount == r2->alloc.ar_blockcount &&
+			 be32_to_cpu(r1->alloc.ar_startblock) <
+			 be32_to_cpu(r2->alloc.ar_startblock));
 	}
-	/*
-	 * For leaf blocks, copy records over to the new block.
-	 */
-	else {
-		xfs_alloc_rec_t	*lrp;	/* left btree record pointer */
-		xfs_alloc_rec_t	*rrp;	/* right btree record pointer */
+}
+#endif	/* DEBUG */
 
-		lrp = XFS_ALLOC_REC_ADDR(left, i, cur);
-		rrp = XFS_ALLOC_REC_ADDR(right, 1, cur);
-		memcpy(rrp, lrp, be16_to_cpu(right->bb_numrecs) * sizeof(*rrp));
-		xfs_alloc_log_recs(cur, rbp, 1, be16_to_cpu(right->bb_numrecs));
-		keyp->ar_startblock = rrp->ar_startblock;
-		keyp->ar_blockcount = rrp->ar_blockcount;
-	}
-	/*
-	 * Find the left block number by looking in the buffer.
-	 * Adjust numrecs, sibling pointers.
-	 */
-	lbno = XFS_DADDR_TO_AGBNO(cur->bc_mp, XFS_BUF_ADDR(lbp));
-	be16_add_cpu(&left->bb_numrecs, -(be16_to_cpu(right->bb_numrecs)));
-	right->bb_rightsib = left->bb_rightsib;
-	left->bb_rightsib = cpu_to_be32(rbno);
-	right->bb_leftsib = cpu_to_be32(lbno);
-	xfs_alloc_log_block(cur->bc_tp, rbp, XFS_BB_ALL_BITS);
-	xfs_alloc_log_block(cur->bc_tp, lbp, XFS_BB_NUMRECS | XFS_BB_RIGHTSIB);
-	/*
-	 * If there's a block to the new block's right, make that block
-	 * point back to right instead of to left.
-	 */
-	if (be32_to_cpu(right->bb_rightsib) != NULLAGBLOCK) {
-		xfs_alloc_block_t	*rrblock;	/* rr btree block */
-		xfs_buf_t		*rrbp;		/* buffer for rrblock */
+#ifdef XFS_BTREE_TRACE
+ktrace_t	*xfs_allocbt_trace_buf;
 
-		if ((error = xfs_btree_read_bufs(cur->bc_mp, cur->bc_tp,
-				cur->bc_private.a.agno, be32_to_cpu(right->bb_rightsib), 0,
-				&rrbp, XFS_ALLOC_BTREE_REF)))
-			return error;
-		rrblock = XFS_BUF_TO_ALLOC_BLOCK(rrbp);
-		if ((error = xfs_btree_check_sblock(cur, rrblock, level, rrbp)))
-			return error;
-		rrblock->bb_leftsib = cpu_to_be32(rbno);
-		xfs_alloc_log_block(cur->bc_tp, rrbp, XFS_BB_LEFTSIB);
-	}
-	/*
-	 * If the cursor is really in the right block, move it there.
-	 * If it's just pointing past the last entry in left, then we'll
-	 * insert there, so don't change anything in that case.
-	 */
-	if (cur->bc_ptrs[level] > be16_to_cpu(left->bb_numrecs) + 1) {
-		xfs_btree_setbuf(cur, level, rbp);
-		cur->bc_ptrs[level] -= be16_to_cpu(left->bb_numrecs);
-	}
-	/*
-	 * If there are more levels, we'll need another cursor which refers to
-	 * the right block, no matter where this cursor was.
-	 */
-	if (level + 1 < cur->bc_nlevels) {
-		if ((error = xfs_btree_dup_cursor(cur, curp)))
-			return error;
-		(*curp)->bc_ptrs[level + 1]++;
-	}
-	*bnop = rbno;
-	*stat = 1;
-	return 0;
+STATIC void
+xfs_allocbt_trace_enter(
+	struct xfs_btree_cur	*cur,
+	const char		*func,
+	char			*s,
+	int			type,
+	int			line,
+	__psunsigned_t		a0,
+	__psunsigned_t		a1,
+	__psunsigned_t		a2,
+	__psunsigned_t		a3,
+	__psunsigned_t		a4,
+	__psunsigned_t		a5,
+	__psunsigned_t		a6,
+	__psunsigned_t		a7,
+	__psunsigned_t		a8,
+	__psunsigned_t		a9,
+	__psunsigned_t		a10)
+{
+	ktrace_enter(xfs_allocbt_trace_buf, (void *)(__psint_t)type,
+		(void *)func, (void *)s, NULL, (void *)cur,
+		(void *)a0, (void *)a1, (void *)a2, (void *)a3,
+		(void *)a4, (void *)a5, (void *)a6, (void *)a7,
+		(void *)a8, (void *)a9, (void *)a10);
 }
 
-/*
- * Update keys at all levels from here to the root along the cursor's path.
- */
-STATIC int				/* error */
-xfs_alloc_updkey(
-	xfs_btree_cur_t		*cur,	/* btree cursor */
-	xfs_alloc_key_t		*keyp,	/* new key value to update to */
-	int			level)	/* starting level for update */
+STATIC void
+xfs_allocbt_trace_cursor(
+	struct xfs_btree_cur	*cur,
+	__uint32_t		*s0,
+	__uint64_t		*l0,
+	__uint64_t		*l1)
 {
-	int			ptr;	/* index of key in block */
-
-	/*
-	 * Go up the tree from this level toward the root.
-	 * At each level, update the key value to the value input.
-	 * Stop when we reach a level where the cursor isn't pointing
-	 * at the first entry in the block.
-	 */
-	for (ptr = 1; ptr == 1 && level < cur->bc_nlevels; level++) {
-		xfs_alloc_block_t	*block;	/* btree block */
-		xfs_buf_t		*bp;	/* buffer for block */
-#ifdef DEBUG
-		int			error;	/* error return value */
-#endif
-		xfs_alloc_key_t		*kp;	/* ptr to btree block keys */
-
-		bp = cur->bc_bufs[level];
-		block = XFS_BUF_TO_ALLOC_BLOCK(bp);
-#ifdef DEBUG
-		if ((error = xfs_btree_check_sblock(cur, block, level, bp)))
-			return error;
-#endif
-		ptr = cur->bc_ptrs[level];
-		kp = XFS_ALLOC_KEY_ADDR(block, ptr, cur);
-		*kp = *keyp;
-		xfs_alloc_log_keys(cur, bp, ptr, ptr);
-	}
-	return 0;
+	*s0 = cur->bc_private.a.agno;
+	*l0 = cur->bc_rec.a.ar_startblock;
+	*l1 = cur->bc_rec.a.ar_blockcount;
 }
 
-/*
- * Externally visible routines.
- */
-
-/*
- * Decrement cursor by one record at the level.
- * For nonzero levels the leaf-ward information is untouched.
- */
-int					/* error */
-xfs_alloc_decrement(
-	xfs_btree_cur_t		*cur,	/* btree cursor */
-	int			level,	/* level in btree, 0 is leaf */
-	int			*stat)	/* success/failure */
+STATIC void
+xfs_allocbt_trace_key(
+	struct xfs_btree_cur	*cur,
+	union xfs_btree_key	*key,
+	__uint64_t		*l0,
+	__uint64_t		*l1)
 {
-	xfs_alloc_block_t	*block;	/* btree block */
-	int			error;	/* error return value */
-	int			lev;	/* btree level */
-
-	ASSERT(level < cur->bc_nlevels);
-	/*
-	 * Read-ahead to the left at this level.
-	 */
-	xfs_btree_readahead(cur, level, XFS_BTCUR_LEFTRA);
-	/*
-	 * Decrement the ptr at this level.  If we're still in the block
-	 * then we're done.
-	 */
-	if (--cur->bc_ptrs[level] > 0) {
-		*stat = 1;
-		return 0;
-	}
-	/*
-	 * Get a pointer to the btree block.
-	 */
-	block = XFS_BUF_TO_ALLOC_BLOCK(cur->bc_bufs[level]);
-#ifdef DEBUG
-	if ((error = xfs_btree_check_sblock(cur, block, level,
-			cur->bc_bufs[level])))
-		return error;
-#endif
-	/*
-	 * If we just went off the left edge of the tree, return failure.
-	 */
-	if (be32_to_cpu(block->bb_leftsib) == NULLAGBLOCK) {
-		*stat = 0;
-		return 0;
-	}
-	/*
-	 * March up the tree decrementing pointers.
-	 * Stop when we don't go off the left edge of a block.
-	 */
-	for (lev = level + 1; lev < cur->bc_nlevels; lev++) {
-		if (--cur->bc_ptrs[lev] > 0)
-			break;
-		/*
-		 * Read-ahead the left block, we're going to read it
-		 * in the next loop.
-		 */
-		xfs_btree_readahead(cur, lev, XFS_BTCUR_LEFTRA);
-	}
-	/*
-	 * If we went off the root then we are seriously confused.
-	 */
-	ASSERT(lev < cur->bc_nlevels);
-	/*
-	 * Now walk back down the tree, fixing up the cursor's buffer
-	 * pointers and key numbers.
-	 */
-	for (block = XFS_BUF_TO_ALLOC_BLOCK(cur->bc_bufs[lev]); lev > level; ) {
-		xfs_agblock_t	agbno;	/* block number of btree block */
-		xfs_buf_t	*bp;	/* buffer pointer for block */
-
-		agbno = be32_to_cpu(*XFS_ALLOC_PTR_ADDR(block, cur->bc_ptrs[lev], cur));
-		if ((error = xfs_btree_read_bufs(cur->bc_mp, cur->bc_tp,
-				cur->bc_private.a.agno, agbno, 0, &bp,
-				XFS_ALLOC_BTREE_REF)))
-			return error;
-		lev--;
-		xfs_btree_setbuf(cur, lev, bp);
-		block = XFS_BUF_TO_ALLOC_BLOCK(bp);
-		if ((error = xfs_btree_check_sblock(cur, block, lev, bp)))
-			return error;
-		cur->bc_ptrs[lev] = be16_to_cpu(block->bb_numrecs);
-	}
-	*stat = 1;
-	return 0;
+	*l0 = be32_to_cpu(key->alloc.ar_startblock);
+	*l1 = be32_to_cpu(key->alloc.ar_blockcount);
 }
 
-/*
- * Delete the record pointed to by cur.
- * The cursor refers to the place where the record was (could be inserted)
- * when the operation returns.
- */
-int					/* error */
-xfs_alloc_delete(
-	xfs_btree_cur_t	*cur,		/* btree cursor */
-	int		*stat)		/* success/failure */
+STATIC void
+xfs_allocbt_trace_record(
+	struct xfs_btree_cur	*cur,
+	union xfs_btree_rec	*rec,
+	__uint64_t		*l0,
+	__uint64_t		*l1,
+	__uint64_t		*l2)
 {
-	int		error;		/* error return value */
-	int		i;		/* result code */
-	int		level;		/* btree level */
-
-	/*
-	 * Go up the tree, starting at leaf level.
-	 * If 2 is returned then a join was done; go to the next level.
-	 * Otherwise we are done.
-	 */
-	for (level = 0, i = 2; i == 2; level++) {
-		if ((error = xfs_alloc_delrec(cur, level, &i)))
-			return error;
-	}
-	if (i == 0) {
-		for (level = 1; level < cur->bc_nlevels; level++) {
-			if (cur->bc_ptrs[level] == 0) {
-				if ((error = xfs_alloc_decrement(cur, level, &i)))
-					return error;
-				break;
-			}
-		}
-	}
-	*stat = i;
-	return 0;
+	*l0 = be32_to_cpu(rec->alloc.ar_startblock);
+	*l1 = be32_to_cpu(rec->alloc.ar_blockcount);
+	*l2 = 0;
 }
+#endif /* XFS_BTREE_TRACE */
+
+static const struct xfs_btree_ops xfs_allocbt_ops = {
+	.rec_len		= sizeof(xfs_alloc_rec_t),
+	.key_len		= sizeof(xfs_alloc_key_t),
+
+	.dup_cursor		= xfs_allocbt_dup_cursor,
+	.set_root		= xfs_allocbt_set_root,
+	.kill_root		= xfs_allocbt_kill_root,
+	.alloc_block		= xfs_allocbt_alloc_block,
+	.free_block		= xfs_allocbt_free_block,
+	.update_lastrec		= xfs_allocbt_update_lastrec,
+	.get_minrecs		= xfs_allocbt_get_minrecs,
+	.get_maxrecs		= xfs_allocbt_get_maxrecs,
+	.init_key_from_rec	= xfs_allocbt_init_key_from_rec,
+	.init_rec_from_key	= xfs_allocbt_init_rec_from_key,
+	.init_rec_from_cur	= xfs_allocbt_init_rec_from_cur,
+	.init_ptr_from_cur	= xfs_allocbt_init_ptr_from_cur,
+	.key_diff		= xfs_allocbt_key_diff,
 
-/*
- * Get the data from the pointed-to record.
- */
-int					/* error */
-xfs_alloc_get_rec(
-	xfs_btree_cur_t		*cur,	/* btree cursor */
-	xfs_agblock_t		*bno,	/* output: starting block of extent */
-	xfs_extlen_t		*len,	/* output: length of extent */
-	int			*stat)	/* output: success/failure */
-{
-	xfs_alloc_block_t	*block;	/* btree block */
 #ifdef DEBUG
-	int			error;	/* error return value */
+	.keys_inorder		= xfs_allocbt_keys_inorder,
+	.recs_inorder		= xfs_allocbt_recs_inorder,
 #endif
-	int			ptr;	/* record number */
 
-	ptr = cur->bc_ptrs[0];
-	block = XFS_BUF_TO_ALLOC_BLOCK(cur->bc_bufs[0]);
-#ifdef DEBUG
-	if ((error = xfs_btree_check_sblock(cur, block, 0, cur->bc_bufs[0])))
-		return error;
+#ifdef XFS_BTREE_TRACE
+	.trace_enter		= xfs_allocbt_trace_enter,
+	.trace_cursor		= xfs_allocbt_trace_cursor,
+	.trace_key		= xfs_allocbt_trace_key,
+	.trace_record		= xfs_allocbt_trace_record,
 #endif
-	/*
-	 * Off the right end or left end, return failure.
-	 */
-	if (ptr > be16_to_cpu(block->bb_numrecs) || ptr <= 0) {
-		*stat = 0;
-		return 0;
-	}
-	/*
-	 * Point to the record and extract its data.
-	 */
-	{
-		xfs_alloc_rec_t		*rec;	/* record data */
-
-		rec = XFS_ALLOC_REC_ADDR(block, ptr, cur);
-		*bno = be32_to_cpu(rec->ar_startblock);
-		*len = be32_to_cpu(rec->ar_blockcount);
-	}
-	*stat = 1;
-	return 0;
-}
+};
 
 /*
- * Increment cursor by one record at the level.
- * For nonzero levels the leaf-ward information is untouched.
+ * Allocate a new allocation btree cursor.
  */
-int					/* error */
-xfs_alloc_increment(
-	xfs_btree_cur_t		*cur,	/* btree cursor */
-	int			level,	/* level in btree, 0 is leaf */
-	int			*stat)	/* success/failure */
+struct xfs_btree_cur *			/* new alloc btree cursor */
+xfs_allocbt_init_cursor(
+	struct xfs_mount	*mp,		/* file system mount point */
+	struct xfs_trans	*tp,		/* transaction pointer */
+	struct xfs_buf		*agbp,		/* buffer for agf structure */
+	xfs_agnumber_t		agno,		/* allocation group number */
+	xfs_btnum_t		btnum)		/* btree identifier */
 {
-	xfs_alloc_block_t	*block;	/* btree block */
-	xfs_buf_t		*bp;	/* tree block buffer */
-	int			error;	/* error return value */
-	int			lev;	/* btree level */
-
-	ASSERT(level < cur->bc_nlevels);
-	/*
-	 * Read-ahead to the right at this level.
-	 */
-	xfs_btree_readahead(cur, level, XFS_BTCUR_RIGHTRA);
-	/*
-	 * Get a pointer to the btree block.
-	 */
-	bp = cur->bc_bufs[level];
-	block = XFS_BUF_TO_ALLOC_BLOCK(bp);
-#ifdef DEBUG
-	if ((error = xfs_btree_check_sblock(cur, block, level, bp)))
-		return error;
-#endif
-	/*
-	 * Increment the ptr at this level.  If we're still in the block
-	 * then we're done.
-	 */
-	if (++cur->bc_ptrs[level] <= be16_to_cpu(block->bb_numrecs)) {
-		*stat = 1;
-		return 0;
-	}
-	/*
-	 * If we just went off the right edge of the tree, return failure.
-	 */
-	if (be32_to_cpu(block->bb_rightsib) == NULLAGBLOCK) {
-		*stat = 0;
-		return 0;
-	}
-	/*
-	 * March up the tree incrementing pointers.
-	 * Stop when we don't go off the right edge of a block.
-	 */
-	for (lev = level + 1; lev < cur->bc_nlevels; lev++) {
-		bp = cur->bc_bufs[lev];
-		block = XFS_BUF_TO_ALLOC_BLOCK(bp);
-#ifdef DEBUG
-		if ((error = xfs_btree_check_sblock(cur, block, lev, bp)))
-			return error;
-#endif
-		if (++cur->bc_ptrs[lev] <= be16_to_cpu(block->bb_numrecs))
-			break;
-		/*
-		 * Read-ahead the right block, we're going to read it
-		 * in the next loop.
-		 */
-		xfs_btree_readahead(cur, lev, XFS_BTCUR_RIGHTRA);
-	}
-	/*
-	 * If we went off the root then we are seriously confused.
-	 */
-	ASSERT(lev < cur->bc_nlevels);
-	/*
-	 * Now walk back down the tree, fixing up the cursor's buffer
-	 * pointers and key numbers.
-	 */
-	for (bp = cur->bc_bufs[lev], block = XFS_BUF_TO_ALLOC_BLOCK(bp);
-	     lev > level; ) {
-		xfs_agblock_t	agbno;	/* block number of btree block */
+	struct xfs_agf		*agf = XFS_BUF_TO_AGF(agbp);
+	struct xfs_btree_cur	*cur;
 
-		agbno = be32_to_cpu(*XFS_ALLOC_PTR_ADDR(block, cur->bc_ptrs[lev], cur));
-		if ((error = xfs_btree_read_bufs(cur->bc_mp, cur->bc_tp,
-				cur->bc_private.a.agno, agbno, 0, &bp,
-				XFS_ALLOC_BTREE_REF)))
-			return error;
-		lev--;
-		xfs_btree_setbuf(cur, lev, bp);
-		block = XFS_BUF_TO_ALLOC_BLOCK(bp);
-		if ((error = xfs_btree_check_sblock(cur, block, lev, bp)))
-			return error;
-		cur->bc_ptrs[lev] = 1;
-	}
-	*stat = 1;
-	return 0;
-}
+	ASSERT(btnum == XFS_BTNUM_BNO || btnum == XFS_BTNUM_CNT);
 
-/*
- * Insert the current record at the point referenced by cur.
- * The cursor may be inconsistent on return if splits have been done.
- */
-int					/* error */
-xfs_alloc_insert(
-	xfs_btree_cur_t	*cur,		/* btree cursor */
-	int		*stat)		/* success/failure */
-{
-	int		error;		/* error return value */
-	int		i;		/* result value, 0 for failure */
-	int		level;		/* current level number in btree */
-	xfs_agblock_t	nbno;		/* new block number (split result) */
-	xfs_btree_cur_t	*ncur;		/* new cursor (split result) */
-	xfs_alloc_rec_t	nrec;		/* record being inserted this level */
-	xfs_btree_cur_t	*pcur;		/* previous level's cursor */
+	cur = kmem_zone_zalloc(xfs_btree_cur_zone, KM_SLEEP);
 
-	level = 0;
-	nbno = NULLAGBLOCK;
-	nrec.ar_startblock = cpu_to_be32(cur->bc_rec.a.ar_startblock);
-	nrec.ar_blockcount = cpu_to_be32(cur->bc_rec.a.ar_blockcount);
-	ncur = NULL;
-	pcur = cur;
-	/*
-	 * Loop going up the tree, starting at the leaf level.
-	 * Stop when we don't get a split block, that must mean that
-	 * the insert is finished with this level.
-	 */
-	do {
-		/*
-		 * Insert nrec/nbno into this level of the tree.
-		 * Note if we fail, nbno will be null.
-		 */
-		if ((error = xfs_alloc_insrec(pcur, level++, &nbno, &nrec, &ncur,
-				&i))) {
-			if (pcur != cur)
-				xfs_btree_del_cursor(pcur, XFS_BTREE_ERROR);
-			return error;
-		}
-		/*
-		 * See if the cursor we just used is trash.
-		 * Can't trash the caller's cursor, but otherwise we should
-		 * if ncur is a new cursor or we're about to be done.
-		 */
-		if (pcur != cur && (ncur || nbno == NULLAGBLOCK)) {
-			cur->bc_nlevels = pcur->bc_nlevels;
-			xfs_btree_del_cursor(pcur, XFS_BTREE_NOERROR);
-		}
-		/*
-		 * If we got a new cursor, switch to it.
-		 */
-		if (ncur) {
-			pcur = ncur;
-			ncur = NULL;
-		}
-	} while (nbno != NULLAGBLOCK);
-	*stat = i;
-	return 0;
-}
+	cur->bc_tp = tp;
+	cur->bc_mp = mp;
+	cur->bc_nlevels = be32_to_cpu(agf->agf_levels[btnum]);
+	cur->bc_btnum = btnum;
+	cur->bc_blocklog = mp->m_sb.sb_blocklog;
 
-/*
- * Lookup the record equal to [bno, len] in the btree given by cur.
- */
-int					/* error */
-xfs_alloc_lookup_eq(
-	xfs_btree_cur_t	*cur,		/* btree cursor */
-	xfs_agblock_t	bno,		/* starting block of extent */
-	xfs_extlen_t	len,		/* length of extent */
-	int		*stat)		/* success/failure */
-{
-	cur->bc_rec.a.ar_startblock = bno;
-	cur->bc_rec.a.ar_blockcount = len;
-	return xfs_alloc_lookup(cur, XFS_LOOKUP_EQ, stat);
-}
+	cur->bc_ops = &xfs_allocbt_ops;
+	if (btnum == XFS_BTNUM_CNT)
+		cur->bc_flags = XFS_BTREE_LASTREC_UPDATE;
 
-/*
- * Lookup the first record greater than or equal to [bno, len]
- * in the btree given by cur.
- */
-int					/* error */
-xfs_alloc_lookup_ge(
-	xfs_btree_cur_t	*cur,		/* btree cursor */
-	xfs_agblock_t	bno,		/* starting block of extent */
-	xfs_extlen_t	len,		/* length of extent */
-	int		*stat)		/* success/failure */
-{
-	cur->bc_rec.a.ar_startblock = bno;
-	cur->bc_rec.a.ar_blockcount = len;
-	return xfs_alloc_lookup(cur, XFS_LOOKUP_GE, stat);
-}
+	cur->bc_private.a.agbp = agbp;
+	cur->bc_private.a.agno = agno;
 
-/*
- * Lookup the first record less than or equal to [bno, len]
- * in the btree given by cur.
- */
-int					/* error */
-xfs_alloc_lookup_le(
-	xfs_btree_cur_t	*cur,		/* btree cursor */
-	xfs_agblock_t	bno,		/* starting block of extent */
-	xfs_extlen_t	len,		/* length of extent */
-	int		*stat)		/* success/failure */
-{
-	cur->bc_rec.a.ar_startblock = bno;
-	cur->bc_rec.a.ar_blockcount = len;
-	return xfs_alloc_lookup(cur, XFS_LOOKUP_LE, stat);
+	return cur;
 }
 
 /*
- * Update the record referred to by cur, to the value given by [bno, len].
- * This either works (return 0) or gets an EFSCORRUPTED error.
+ * Calculate number of records in an alloc btree block.
  */
-int					/* error */
-xfs_alloc_update(
-	xfs_btree_cur_t		*cur,	/* btree cursor */
-	xfs_agblock_t		bno,	/* starting block of extent */
-	xfs_extlen_t		len)	/* length of extent */
+int
+xfs_allocbt_maxrecs(
+	struct xfs_mount	*mp,
+	int			blocklen,
+	int			leaf)
 {
-	xfs_alloc_block_t	*block;	/* btree block to update */
-	int			error;	/* error return value */
-	int			ptr;	/* current record number (updating) */
+	blocklen -= XFS_ALLOC_BLOCK_LEN(mp);
 
-	ASSERT(len > 0);
-	/*
-	 * Pick up the a.g. freelist struct and the current block.
-	 */
-	block = XFS_BUF_TO_ALLOC_BLOCK(cur->bc_bufs[0]);
-#ifdef DEBUG
-	if ((error = xfs_btree_check_sblock(cur, block, 0, cur->bc_bufs[0])))
-		return error;
-#endif
-	/*
-	 * Get the address of the rec to be updated.
-	 */
-	ptr = cur->bc_ptrs[0];
-	{
-		xfs_alloc_rec_t		*rp;	/* pointer to updated record */
-
-		rp = XFS_ALLOC_REC_ADDR(block, ptr, cur);
-		/*
-		 * Fill in the new contents and log them.
-		 */
-		rp->ar_startblock = cpu_to_be32(bno);
-		rp->ar_blockcount = cpu_to_be32(len);
-		xfs_alloc_log_recs(cur, cur->bc_bufs[0], ptr, ptr);
-	}
-	/*
-	 * If it's the by-size btree and it's the last leaf block and
-	 * it's the last record... then update the size of the longest
-	 * extent in the a.g., which we cache in the a.g. freelist header.
-	 */
-	if (cur->bc_btnum == XFS_BTNUM_CNT &&
-	    be32_to_cpu(block->bb_rightsib) == NULLAGBLOCK &&
-	    ptr == be16_to_cpu(block->bb_numrecs)) {
-		xfs_agf_t	*agf;	/* a.g. freespace header */
-		xfs_agnumber_t	seqno;
-
-		agf = XFS_BUF_TO_AGF(cur->bc_private.a.agbp);
-		seqno = be32_to_cpu(agf->agf_seqno);
-		cur->bc_mp->m_perag[seqno].pagf_longest = len;
-		agf->agf_longest = cpu_to_be32(len);
-		xfs_alloc_log_agf(cur->bc_tp, cur->bc_private.a.agbp,
-			XFS_AGF_LONGEST);
-	}
-	/*
-	 * Updating first record in leaf. Pass new key value up to our parent.
-	 */
-	if (ptr == 1) {
-		xfs_alloc_key_t	key;	/* key containing [bno, len] */
-
-		key.ar_startblock = cpu_to_be32(bno);
-		key.ar_blockcount = cpu_to_be32(len);
-		if ((error = xfs_alloc_updkey(cur, &key, 1)))
-			return error;
-	}
-	return 0;
+	if (leaf)
+		return blocklen / sizeof(xfs_alloc_rec_t);
+	return blocklen / (sizeof(xfs_alloc_key_t) + sizeof(xfs_alloc_ptr_t));
 }
diff --git a/fs/xfs/xfs_alloc_btree.h b/fs/xfs/xfs_alloc_btree.h
index 5bd1a2c8bd07..a6caa0022c9b 100644
--- a/fs/xfs/xfs_alloc_btree.h
+++ b/fs/xfs/xfs_alloc_btree.h
@@ -24,7 +24,6 @@
 
 struct xfs_buf;
 struct xfs_btree_cur;
-struct xfs_btree_sblock;
 struct xfs_mount;
 
 /*
@@ -50,16 +49,6 @@ typedef struct xfs_alloc_rec_incore {
 
 /* btree pointer type */
 typedef __be32 xfs_alloc_ptr_t;
-/* btree block header type */
-typedef	struct xfs_btree_sblock xfs_alloc_block_t;
-
-#define	XFS_BUF_TO_ALLOC_BLOCK(bp)	((xfs_alloc_block_t *)XFS_BUF_PTR(bp))
-
-/*
- * Real block structures have a size equal to the disk block size.
- */
-#define	XFS_ALLOC_BLOCK_MAXRECS(lev,cur) ((cur)->bc_mp->m_alloc_mxr[lev != 0])
-#define	XFS_ALLOC_BLOCK_MINRECS(lev,cur) ((cur)->bc_mp->m_alloc_mnr[lev != 0])
 
 /*
  * Minimum and maximum blocksize and sectorsize.
@@ -83,73 +72,39 @@ typedef	struct xfs_btree_sblock xfs_alloc_block_t;
 #define	XFS_CNT_BLOCK(mp)	((xfs_agblock_t)(XFS_BNO_BLOCK(mp) + 1))
 
 /*
- * Record, key, and pointer address macros for btree blocks.
- */
-#define	XFS_ALLOC_REC_ADDR(bb,i,cur)	\
-	XFS_BTREE_REC_ADDR(xfs_alloc, bb, i)
-
-#define	XFS_ALLOC_KEY_ADDR(bb,i,cur)	\
-	XFS_BTREE_KEY_ADDR(xfs_alloc, bb, i)
-
-#define	XFS_ALLOC_PTR_ADDR(bb,i,cur)	\
-	XFS_BTREE_PTR_ADDR(xfs_alloc, bb, i, XFS_ALLOC_BLOCK_MAXRECS(1, cur))
-
-/*
- * Decrement cursor by one record at the level.
- * For nonzero levels the leaf-ward information is untouched.
- */
-extern int xfs_alloc_decrement(struct xfs_btree_cur *cur, int level, int *stat);
-
-/*
- * Delete the record pointed to by cur.
- * The cursor refers to the place where the record was (could be inserted)
- * when the operation returns.
- */
-extern int xfs_alloc_delete(struct xfs_btree_cur *cur, int *stat);
-
-/*
- * Get the data from the pointed-to record.
- */
-extern int xfs_alloc_get_rec(struct xfs_btree_cur *cur,	xfs_agblock_t *bno,
-				xfs_extlen_t *len, int *stat);
-
-/*
- * Increment cursor by one record at the level.
- * For nonzero levels the leaf-ward information is untouched.
- */
-extern int xfs_alloc_increment(struct xfs_btree_cur *cur, int level, int *stat);
-
-/*
- * Insert the current record at the point referenced by cur.
- * The cursor may be inconsistent on return if splits have been done.
- */
-extern int xfs_alloc_insert(struct xfs_btree_cur *cur, int *stat);
-
-/*
- * Lookup the record equal to [bno, len] in the btree given by cur.
- */
-extern int xfs_alloc_lookup_eq(struct xfs_btree_cur *cur, xfs_agblock_t bno,
-				xfs_extlen_t len, int *stat);
-
-/*
- * Lookup the first record greater than or equal to [bno, len]
- * in the btree given by cur.
- */
-extern int xfs_alloc_lookup_ge(struct xfs_btree_cur *cur, xfs_agblock_t bno,
-				xfs_extlen_t len, int *stat);
-
-/*
- * Lookup the first record less than or equal to [bno, len]
- * in the btree given by cur.
+ * Btree block header size depends on a superblock flag.
+ *
+ * (not quite yet, but soon)
  */
-extern int xfs_alloc_lookup_le(struct xfs_btree_cur *cur, xfs_agblock_t bno,
-				xfs_extlen_t len, int *stat);
+#define XFS_ALLOC_BLOCK_LEN(mp)	XFS_BTREE_SBLOCK_LEN
 
 /*
- * Update the record referred to by cur, to the value given by [bno, len].
- * This either works (return 0) or gets an EFSCORRUPTED error.
- */
-extern int xfs_alloc_update(struct xfs_btree_cur *cur, xfs_agblock_t bno,
-				xfs_extlen_t len);
+ * Record, key, and pointer address macros for btree blocks.
+ *
+ * (note that some of these may appear unused, but they are used in userspace)
+ */
+#define XFS_ALLOC_REC_ADDR(mp, block, index) \
+	((xfs_alloc_rec_t *) \
+		((char *)(block) + \
+		 XFS_ALLOC_BLOCK_LEN(mp) + \
+		 (((index) - 1) * sizeof(xfs_alloc_rec_t))))
+
+#define XFS_ALLOC_KEY_ADDR(mp, block, index) \
+	((xfs_alloc_key_t *) \
+		((char *)(block) + \
+		 XFS_ALLOC_BLOCK_LEN(mp) + \
+		 ((index) - 1) * sizeof(xfs_alloc_key_t)))
+
+#define XFS_ALLOC_PTR_ADDR(mp, block, index, maxrecs) \
+	((xfs_alloc_ptr_t *) \
+		((char *)(block) + \
+		 XFS_ALLOC_BLOCK_LEN(mp) + \
+		 (maxrecs) * sizeof(xfs_alloc_key_t) + \
+		 ((index) - 1) * sizeof(xfs_alloc_ptr_t)))
+
+extern struct xfs_btree_cur *xfs_allocbt_init_cursor(struct xfs_mount *,
+		struct xfs_trans *, struct xfs_buf *,
+		xfs_agnumber_t, xfs_btnum_t);
+extern int xfs_allocbt_maxrecs(struct xfs_mount *, int, int);
 
 #endif	/* __XFS_ALLOC_BTREE_H__ */
diff --git a/fs/xfs/xfs_arch.h b/fs/xfs/xfs_arch.h
index 0b3b5efe848c..53d5e70d1360 100644
--- a/fs/xfs/xfs_arch.h
+++ b/fs/xfs/xfs_arch.h
@@ -41,21 +41,36 @@
 #endif
 
 #ifdef XFS_NATIVE_HOST
-#define cpu_to_be16(val)	((__be16)(val))
-#define cpu_to_be32(val)	((__be32)(val))
-#define cpu_to_be64(val)	((__be64)(val))
-#define be16_to_cpu(val)	((__uint16_t)(val))
-#define be32_to_cpu(val)	((__uint32_t)(val))
-#define be64_to_cpu(val)	((__uint64_t)(val))
+#define cpu_to_be16(val)	((__force __be16)(__u16)(val))
+#define cpu_to_be32(val)	((__force __be32)(__u32)(val))
+#define cpu_to_be64(val)	((__force __be64)(__u64)(val))
+#define be16_to_cpu(val)	((__force __u16)(__be16)(val))
+#define be32_to_cpu(val)	((__force __u32)(__be32)(val))
+#define be64_to_cpu(val)	((__force __u64)(__be64)(val))
 #else
-#define cpu_to_be16(val)	(__swab16((__uint16_t)(val)))
-#define cpu_to_be32(val)	(__swab32((__uint32_t)(val)))
-#define cpu_to_be64(val)	(__swab64((__uint64_t)(val)))
-#define be16_to_cpu(val)	(__swab16((__be16)(val)))
-#define be32_to_cpu(val)	(__swab32((__be32)(val)))
-#define be64_to_cpu(val)	(__swab64((__be64)(val)))
+#define cpu_to_be16(val)	((__force __be16)__swab16((__u16)(val)))
+#define cpu_to_be32(val)	((__force __be32)__swab32((__u32)(val)))
+#define cpu_to_be64(val)	((__force __be64)__swab64((__u64)(val)))
+#define be16_to_cpu(val)	(__swab16((__force __u16)(__be16)(val)))
+#define be32_to_cpu(val)	(__swab32((__force __u32)(__be32)(val)))
+#define be64_to_cpu(val)	(__swab64((__force __u64)(__be64)(val)))
 #endif
 
+static inline void be16_add_cpu(__be16 *a, __s16 b)
+{
+	*a = cpu_to_be16(be16_to_cpu(*a) + b);
+}
+
+static inline void be32_add_cpu(__be32 *a, __s32 b)
+{
+	*a = cpu_to_be32(be32_to_cpu(*a) + b);
+}
+
+static inline void be64_add_cpu(__be64 *a, __s64 b)
+{
+	*a = cpu_to_be64(be64_to_cpu(*a) + b);
+}
+
 #endif	/* __KERNEL__ */
 
 /* do we need conversion? */
diff --git a/fs/xfs/xfs_bit.h b/fs/xfs/xfs_bit.h
index 8e0e463dae2d..bca7b243c319 100644
--- a/fs/xfs/xfs_bit.h
+++ b/fs/xfs/xfs_bit.h
@@ -61,8 +61,7 @@ static inline int xfs_highbit64(__uint64_t v)
 /* Get low bit set out of 32-bit argument, -1 if none set */
 static inline int xfs_lowbit32(__uint32_t v)
 {
-	unsigned long	t = v;
-	return (v) ? find_first_bit(&t, 32) : -1;
+	return ffs(v) - 1;
 }
 
 /* Get low bit set out of 64-bit argument, -1 if none set */
diff --git a/fs/xfs/xfs_bmap.c b/fs/xfs/xfs_bmap.c
index a1aab9275d5a..138308e70d14 100644
--- a/fs/xfs/xfs_bmap.c
+++ b/fs/xfs/xfs_bmap.c
@@ -393,8 +393,8 @@ xfs_bmap_count_leaves(
 
 STATIC void
 xfs_bmap_disk_count_leaves(
-	xfs_extnum_t		idx,
-	xfs_bmbt_block_t	*block,
+	struct xfs_mount	*mp,
+	struct xfs_btree_block	*block,
 	int			numrecs,
 	int			*count);
 
@@ -402,6 +402,53 @@ xfs_bmap_disk_count_leaves(
  * Bmap internal routines.
  */
 
+STATIC int				/* error */
+xfs_bmbt_lookup_eq(
+	struct xfs_btree_cur	*cur,
+	xfs_fileoff_t		off,
+	xfs_fsblock_t		bno,
+	xfs_filblks_t		len,
+	int			*stat)	/* success/failure */
+{
+	cur->bc_rec.b.br_startoff = off;
+	cur->bc_rec.b.br_startblock = bno;
+	cur->bc_rec.b.br_blockcount = len;
+	return xfs_btree_lookup(cur, XFS_LOOKUP_EQ, stat);
+}
+
+STATIC int				/* error */
+xfs_bmbt_lookup_ge(
+	struct xfs_btree_cur	*cur,
+	xfs_fileoff_t		off,
+	xfs_fsblock_t		bno,
+	xfs_filblks_t		len,
+	int			*stat)	/* success/failure */
+{
+	cur->bc_rec.b.br_startoff = off;
+	cur->bc_rec.b.br_startblock = bno;
+	cur->bc_rec.b.br_blockcount = len;
+	return xfs_btree_lookup(cur, XFS_LOOKUP_GE, stat);
+}
+
+/*
+* Update the record referred to by cur to the value given
+ * by [off, bno, len, state].
+ * This either works (return 0) or gets an EFSCORRUPTED error.
+ */
+STATIC int
+xfs_bmbt_update(
+	struct xfs_btree_cur	*cur,
+	xfs_fileoff_t		off,
+	xfs_fsblock_t		bno,
+	xfs_filblks_t		len,
+	xfs_exntst_t		state)
+{
+	union xfs_btree_rec	rec;
+
+	xfs_bmbt_disk_set_allf(&rec.bmbt, off, bno, len, state);
+	return xfs_btree_update(cur, &rec);
+}
+
 /*
  * Called from xfs_bmap_add_attrfork to handle btree format files.
  */
@@ -422,15 +469,14 @@ xfs_bmap_add_attrfork_btree(
 	if (ip->i_df.if_broot_bytes <= XFS_IFORK_DSIZE(ip))
 		*flags |= XFS_ILOG_DBROOT;
 	else {
-		cur = xfs_btree_init_cursor(mp, tp, NULL, 0, XFS_BTNUM_BMAP, ip,
-			XFS_DATA_FORK);
+		cur = xfs_bmbt_init_cursor(mp, tp, ip, XFS_DATA_FORK);
 		cur->bc_private.b.flist = flist;
 		cur->bc_private.b.firstblock = *firstblock;
 		if ((error = xfs_bmbt_lookup_ge(cur, 0, 0, 0, &stat)))
 			goto error0;
 		/* must be at least one entry */
 		XFS_WANT_CORRUPTED_GOTO(stat == 1, error0);
-		if ((error = xfs_bmbt_newroot(cur, flags, &stat)))
+		if ((error = xfs_btree_new_iroot(cur, flags, &stat)))
 			goto error0;
 		if (stat == 0) {
 			xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR);
@@ -818,10 +864,10 @@ xfs_bmap_add_extent_delay_real(
 					RIGHT.br_blockcount, &i)))
 				goto done;
 			XFS_WANT_CORRUPTED_GOTO(i == 1, done);
-			if ((error = xfs_bmbt_delete(cur, &i)))
+			if ((error = xfs_btree_delete(cur, &i)))
 				goto done;
 			XFS_WANT_CORRUPTED_GOTO(i == 1, done);
-			if ((error = xfs_bmbt_decrement(cur, 0, &i)))
+			if ((error = xfs_btree_decrement(cur, 0, &i)))
 				goto done;
 			XFS_WANT_CORRUPTED_GOTO(i == 1, done);
 			if ((error = xfs_bmbt_update(cur, LEFT.br_startoff,
@@ -931,7 +977,7 @@ xfs_bmap_add_extent_delay_real(
 				goto done;
 			XFS_WANT_CORRUPTED_GOTO(i == 0, done);
 			cur->bc_rec.b.br_state = XFS_EXT_NORM;
-			if ((error = xfs_bmbt_insert(cur, &i)))
+			if ((error = xfs_btree_insert(cur, &i)))
 				goto done;
 			XFS_WANT_CORRUPTED_GOTO(i == 1, done);
 		}
@@ -1007,7 +1053,7 @@ xfs_bmap_add_extent_delay_real(
 				goto done;
 			XFS_WANT_CORRUPTED_GOTO(i == 0, done);
 			cur->bc_rec.b.br_state = XFS_EXT_NORM;
-			if ((error = xfs_bmbt_insert(cur, &i)))
+			if ((error = xfs_btree_insert(cur, &i)))
 				goto done;
 			XFS_WANT_CORRUPTED_GOTO(i == 1, done);
 		}
@@ -1097,7 +1143,7 @@ xfs_bmap_add_extent_delay_real(
 				goto done;
 			XFS_WANT_CORRUPTED_GOTO(i == 0, done);
 			cur->bc_rec.b.br_state = XFS_EXT_NORM;
-			if ((error = xfs_bmbt_insert(cur, &i)))
+			if ((error = xfs_btree_insert(cur, &i)))
 				goto done;
 			XFS_WANT_CORRUPTED_GOTO(i == 1, done);
 		}
@@ -1152,7 +1198,7 @@ xfs_bmap_add_extent_delay_real(
 				goto done;
 			XFS_WANT_CORRUPTED_GOTO(i == 0, done);
 			cur->bc_rec.b.br_state = XFS_EXT_NORM;
-			if ((error = xfs_bmbt_insert(cur, &i)))
+			if ((error = xfs_btree_insert(cur, &i)))
 				goto done;
 			XFS_WANT_CORRUPTED_GOTO(i == 1, done);
 		}
@@ -1379,16 +1425,16 @@ xfs_bmap_add_extent_unwritten_real(
 					RIGHT.br_blockcount, &i)))
 				goto done;
 			XFS_WANT_CORRUPTED_GOTO(i == 1, done);
-			if ((error = xfs_bmbt_delete(cur, &i)))
+			if ((error = xfs_btree_delete(cur, &i)))
 				goto done;
 			XFS_WANT_CORRUPTED_GOTO(i == 1, done);
-			if ((error = xfs_bmbt_decrement(cur, 0, &i)))
+			if ((error = xfs_btree_decrement(cur, 0, &i)))
 				goto done;
 			XFS_WANT_CORRUPTED_GOTO(i == 1, done);
-			if ((error = xfs_bmbt_delete(cur, &i)))
+			if ((error = xfs_btree_delete(cur, &i)))
 				goto done;
 			XFS_WANT_CORRUPTED_GOTO(i == 1, done);
-			if ((error = xfs_bmbt_decrement(cur, 0, &i)))
+			if ((error = xfs_btree_decrement(cur, 0, &i)))
 				goto done;
 			XFS_WANT_CORRUPTED_GOTO(i == 1, done);
 			if ((error = xfs_bmbt_update(cur, LEFT.br_startoff,
@@ -1428,10 +1474,10 @@ xfs_bmap_add_extent_unwritten_real(
 					&i)))
 				goto done;
 			XFS_WANT_CORRUPTED_GOTO(i == 1, done);
-			if ((error = xfs_bmbt_delete(cur, &i)))
+			if ((error = xfs_btree_delete(cur, &i)))
 				goto done;
 			XFS_WANT_CORRUPTED_GOTO(i == 1, done);
-			if ((error = xfs_bmbt_decrement(cur, 0, &i)))
+			if ((error = xfs_btree_decrement(cur, 0, &i)))
 				goto done;
 			XFS_WANT_CORRUPTED_GOTO(i == 1, done);
 			if ((error = xfs_bmbt_update(cur, LEFT.br_startoff,
@@ -1471,10 +1517,10 @@ xfs_bmap_add_extent_unwritten_real(
 					RIGHT.br_blockcount, &i)))
 				goto done;
 			XFS_WANT_CORRUPTED_GOTO(i == 1, done);
-			if ((error = xfs_bmbt_delete(cur, &i)))
+			if ((error = xfs_btree_delete(cur, &i)))
 				goto done;
 			XFS_WANT_CORRUPTED_GOTO(i == 1, done);
-			if ((error = xfs_bmbt_decrement(cur, 0, &i)))
+			if ((error = xfs_btree_decrement(cur, 0, &i)))
 				goto done;
 			XFS_WANT_CORRUPTED_GOTO(i == 1, done);
 			if ((error = xfs_bmbt_update(cur, new->br_startoff,
@@ -1557,7 +1603,7 @@ xfs_bmap_add_extent_unwritten_real(
 				PREV.br_blockcount - new->br_blockcount,
 				oldext)))
 				goto done;
-			if ((error = xfs_bmbt_decrement(cur, 0, &i)))
+			if ((error = xfs_btree_decrement(cur, 0, &i)))
 				goto done;
 			if (xfs_bmbt_update(cur, LEFT.br_startoff,
 				LEFT.br_startblock,
@@ -1605,7 +1651,7 @@ xfs_bmap_add_extent_unwritten_real(
 				oldext)))
 				goto done;
 			cur->bc_rec.b = *new;
-			if ((error = xfs_bmbt_insert(cur, &i)))
+			if ((error = xfs_btree_insert(cur, &i)))
 				goto done;
 			XFS_WANT_CORRUPTED_GOTO(i == 1, done);
 		}
@@ -1647,7 +1693,7 @@ xfs_bmap_add_extent_unwritten_real(
 				PREV.br_blockcount - new->br_blockcount,
 				oldext)))
 				goto done;
-			if ((error = xfs_bmbt_increment(cur, 0, &i)))
+			if ((error = xfs_btree_increment(cur, 0, &i)))
 				goto done;
 			if ((error = xfs_bmbt_update(cur, new->br_startoff,
 				new->br_startblock,
@@ -1695,7 +1741,7 @@ xfs_bmap_add_extent_unwritten_real(
 				goto done;
 			XFS_WANT_CORRUPTED_GOTO(i == 0, done);
 			cur->bc_rec.b.br_state = XFS_EXT_NORM;
-			if ((error = xfs_bmbt_insert(cur, &i)))
+			if ((error = xfs_btree_insert(cur, &i)))
 				goto done;
 			XFS_WANT_CORRUPTED_GOTO(i == 1, done);
 		}
@@ -1743,7 +1789,7 @@ xfs_bmap_add_extent_unwritten_real(
 			cur->bc_rec.b = PREV;
 			cur->bc_rec.b.br_blockcount =
 				new->br_startoff - PREV.br_startoff;
-			if ((error = xfs_bmbt_insert(cur, &i)))
+			if ((error = xfs_btree_insert(cur, &i)))
 				goto done;
 			XFS_WANT_CORRUPTED_GOTO(i == 1, done);
 			/*
@@ -1758,7 +1804,7 @@ xfs_bmap_add_extent_unwritten_real(
 			XFS_WANT_CORRUPTED_GOTO(i == 0, done);
 			/* new middle extent - newext */
 			cur->bc_rec.b.br_state = new->br_state;
-			if ((error = xfs_bmbt_insert(cur, &i)))
+			if ((error = xfs_btree_insert(cur, &i)))
 				goto done;
 			XFS_WANT_CORRUPTED_GOTO(i == 1, done);
 		}
@@ -2106,10 +2152,10 @@ xfs_bmap_add_extent_hole_real(
 					right.br_blockcount, &i)))
 				goto done;
 			XFS_WANT_CORRUPTED_GOTO(i == 1, done);
-			if ((error = xfs_bmbt_delete(cur, &i)))
+			if ((error = xfs_btree_delete(cur, &i)))
 				goto done;
 			XFS_WANT_CORRUPTED_GOTO(i == 1, done);
-			if ((error = xfs_bmbt_decrement(cur, 0, &i)))
+			if ((error = xfs_btree_decrement(cur, 0, &i)))
 				goto done;
 			XFS_WANT_CORRUPTED_GOTO(i == 1, done);
 			if ((error = xfs_bmbt_update(cur, left.br_startoff,
@@ -2218,7 +2264,7 @@ xfs_bmap_add_extent_hole_real(
 				goto done;
 			XFS_WANT_CORRUPTED_GOTO(i == 0, done);
 			cur->bc_rec.b.br_state = new->br_state;
-			if ((error = xfs_bmbt_insert(cur, &i)))
+			if ((error = xfs_btree_insert(cur, &i)))
 				goto done;
 			XFS_WANT_CORRUPTED_GOTO(i == 1, done);
 		}
@@ -2996,24 +3042,24 @@ xfs_bmap_btree_to_extents(
 	int			whichfork)  /* data or attr fork */
 {
 	/* REFERENCED */
-	xfs_bmbt_block_t	*cblock;/* child btree block */
+	struct xfs_btree_block	*cblock;/* child btree block */
 	xfs_fsblock_t		cbno;	/* child block number */
 	xfs_buf_t		*cbp;	/* child block's buffer */
 	int			error;	/* error return value */
 	xfs_ifork_t		*ifp;	/* inode fork data */
 	xfs_mount_t		*mp;	/* mount point structure */
 	__be64			*pp;	/* ptr to block address */
-	xfs_bmbt_block_t	*rblock;/* root btree block */
+	struct xfs_btree_block	*rblock;/* root btree block */
 
+	mp = ip->i_mount;
 	ifp = XFS_IFORK_PTR(ip, whichfork);
 	ASSERT(ifp->if_flags & XFS_IFEXTENTS);
 	ASSERT(XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_BTREE);
 	rblock = ifp->if_broot;
 	ASSERT(be16_to_cpu(rblock->bb_level) == 1);
 	ASSERT(be16_to_cpu(rblock->bb_numrecs) == 1);
-	ASSERT(XFS_BMAP_BROOT_MAXRECS(ifp->if_broot_bytes) == 1);
-	mp = ip->i_mount;
-	pp = XFS_BMAP_BROOT_PTR_ADDR(rblock, 1, ifp->if_broot_bytes);
+	ASSERT(xfs_bmbt_maxrecs(mp, ifp->if_broot_bytes, 0) == 1);
+	pp = XFS_BMAP_BROOT_PTR_ADDR(mp, rblock, 1, ifp->if_broot_bytes);
 	cbno = be64_to_cpu(*pp);
 	*logflagsp = 0;
 #ifdef DEBUG
@@ -3023,8 +3069,8 @@ xfs_bmap_btree_to_extents(
 	if ((error = xfs_btree_read_bufl(mp, tp, cbno, 0, &cbp,
 			XFS_BMAP_BTREE_REF)))
 		return error;
-	cblock = XFS_BUF_TO_BMBT_BLOCK(cbp);
-	if ((error = xfs_btree_check_lblock(cur, cblock, 0, cbp)))
+	cblock = XFS_BUF_TO_BLOCK(cbp);
+	if ((error = xfs_btree_check_block(cur, cblock, 0, cbp)))
 		return error;
 	xfs_bmap_add_free(cbno, 1, cur->bc_private.b.flist, mp);
 	ip->i_d.di_nblocks--;
@@ -3170,7 +3216,7 @@ xfs_bmap_del_extent(
 			flags |= XFS_ILOG_FEXT(whichfork);
 			break;
 		}
-		if ((error = xfs_bmbt_delete(cur, &i)))
+		if ((error = xfs_btree_delete(cur, &i)))
 			goto done;
 		XFS_WANT_CORRUPTED_GOTO(i == 1, done);
 		break;
@@ -3254,10 +3300,10 @@ xfs_bmap_del_extent(
 						got.br_startblock, temp,
 						got.br_state)))
 					goto done;
-				if ((error = xfs_bmbt_increment(cur, 0, &i)))
+				if ((error = xfs_btree_increment(cur, 0, &i)))
 					goto done;
 				cur->bc_rec.b = new;
-				error = xfs_bmbt_insert(cur, &i);
+				error = xfs_btree_insert(cur, &i);
 				if (error && error != ENOSPC)
 					goto done;
 				/*
@@ -3404,11 +3450,11 @@ xfs_bmap_extents_to_btree(
 	int			*logflagsp,	/* inode logging flags */
 	int			whichfork)	/* data or attr fork */
 {
-	xfs_bmbt_block_t	*ablock;	/* allocated (child) bt block */
+	struct xfs_btree_block	*ablock;	/* allocated (child) bt block */
 	xfs_buf_t		*abp;		/* buffer for ablock */
 	xfs_alloc_arg_t		args;		/* allocation arguments */
 	xfs_bmbt_rec_t		*arp;		/* child record pointer */
-	xfs_bmbt_block_t	*block;		/* btree root block */
+	struct xfs_btree_block	*block;		/* btree root block */
 	xfs_btree_cur_t		*cur;		/* bmap btree cursor */
 	xfs_bmbt_rec_host_t	*ep;		/* extent record pointer */
 	int			error;		/* error return value */
@@ -3428,6 +3474,7 @@ xfs_bmap_extents_to_btree(
 	 */
 	xfs_iroot_realloc(ip, 1, whichfork);
 	ifp->if_flags |= XFS_IFBROOT;
+
 	/*
 	 * Fill in the root.
 	 */
@@ -3435,14 +3482,14 @@ xfs_bmap_extents_to_btree(
 	block->bb_magic = cpu_to_be32(XFS_BMAP_MAGIC);
 	block->bb_level = cpu_to_be16(1);
 	block->bb_numrecs = cpu_to_be16(1);
-	block->bb_leftsib = cpu_to_be64(NULLDFSBNO);
-	block->bb_rightsib = cpu_to_be64(NULLDFSBNO);
+	block->bb_u.l.bb_leftsib = cpu_to_be64(NULLDFSBNO);
+	block->bb_u.l.bb_rightsib = cpu_to_be64(NULLDFSBNO);
+
 	/*
 	 * Need a cursor.  Can't allocate until bb_level is filled in.
 	 */
 	mp = ip->i_mount;
-	cur = xfs_btree_init_cursor(mp, tp, NULL, 0, XFS_BTNUM_BMAP, ip,
-		whichfork);
+	cur = xfs_bmbt_init_cursor(mp, tp, ip, whichfork);
 	cur->bc_private.b.firstblock = *firstblock;
 	cur->bc_private.b.flist = flist;
 	cur->bc_private.b.flags = wasdel ? XFS_BTCUR_BPRV_WASDEL : 0;
@@ -3489,12 +3536,12 @@ xfs_bmap_extents_to_btree(
 	/*
 	 * Fill in the child block.
 	 */
-	ablock = XFS_BUF_TO_BMBT_BLOCK(abp);
+	ablock = XFS_BUF_TO_BLOCK(abp);
 	ablock->bb_magic = cpu_to_be32(XFS_BMAP_MAGIC);
 	ablock->bb_level = 0;
-	ablock->bb_leftsib = cpu_to_be64(NULLDFSBNO);
-	ablock->bb_rightsib = cpu_to_be64(NULLDFSBNO);
-	arp = XFS_BMAP_REC_IADDR(ablock, 1, cur);
+	ablock->bb_u.l.bb_leftsib = cpu_to_be64(NULLDFSBNO);
+	ablock->bb_u.l.bb_rightsib = cpu_to_be64(NULLDFSBNO);
+	arp = XFS_BMBT_REC_ADDR(mp, ablock, 1);
 	nextents = ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t);
 	for (cnt = i = 0; i < nextents; i++) {
 		ep = xfs_iext_get_ext(ifp, i);
@@ -3505,21 +3552,24 @@ xfs_bmap_extents_to_btree(
 		}
 	}
 	ASSERT(cnt == XFS_IFORK_NEXTENTS(ip, whichfork));
-	ablock->bb_numrecs = cpu_to_be16(cnt);
+	xfs_btree_set_numrecs(ablock, cnt);
+
 	/*
 	 * Fill in the root key and pointer.
 	 */
-	kp = XFS_BMAP_KEY_IADDR(block, 1, cur);
-	arp = XFS_BMAP_REC_IADDR(ablock, 1, cur);
+	kp = XFS_BMBT_KEY_ADDR(mp, block, 1);
+	arp = XFS_BMBT_REC_ADDR(mp, ablock, 1);
 	kp->br_startoff = cpu_to_be64(xfs_bmbt_disk_get_startoff(arp));
-	pp = XFS_BMAP_PTR_IADDR(block, 1, cur);
+	pp = XFS_BMBT_PTR_ADDR(mp, block, 1, xfs_bmbt_get_maxrecs(cur,
+						be16_to_cpu(block->bb_level)));
 	*pp = cpu_to_be64(args.fsbno);
+
 	/*
 	 * Do all this logging at the end so that
 	 * the root is at the right level.
 	 */
-	xfs_bmbt_log_block(cur, abp, XFS_BB_ALL_BITS);
-	xfs_bmbt_log_recs(cur, abp, 1, be16_to_cpu(ablock->bb_numrecs));
+	xfs_btree_log_block(cur, abp, XFS_BB_ALL_BITS);
+	xfs_btree_log_recs(cur, abp, 1, be16_to_cpu(ablock->bb_numrecs));
 	ASSERT(*curp == NULL);
 	*curp = cur;
 	*logflagsp = XFS_ILOG_CORE | XFS_ILOG_FBROOT(whichfork);
@@ -4176,7 +4226,7 @@ xfs_bmap_compute_maxlevels(
 		maxleafents = MAXAEXTNUM;
 		sz = XFS_BMDR_SPACE_CALC(MINABTPTRS);
 	}
-	maxrootrecs = (int)XFS_BTREE_BLOCK_MAXRECS(sz, xfs_bmdr, 0);
+	maxrootrecs = xfs_bmdr_maxrecs(mp, sz, 0);
 	minleafrecs = mp->m_bmap_dmnr[0];
 	minnoderecs = mp->m_bmap_dmnr[1];
 	maxblocks = (maxleafents + minleafrecs - 1) / minleafrecs;
@@ -4242,9 +4292,15 @@ xfs_bmap_finish(
 	 * We have a new transaction, so we should return committed=1,
 	 * even though we're returning an error.
 	 */
-	if (error) {
+	if (error)
 		return error;
-	}
+
+	/*
+	 * transaction commit worked ok so we can drop the extra ticket
+	 * reference that we gained in xfs_trans_dup()
+	 */
+	xfs_log_ticket_put(ntp->t_ticket);
+
 	if ((error = xfs_trans_reserve(ntp, 0, logres, 0, XFS_TRANS_PERM_LOG_RES,
 			logcount)))
 		return error;
@@ -4474,6 +4530,22 @@ xfs_bmap_one_block(
 	return rval;
 }
 
+STATIC int
+xfs_bmap_sanity_check(
+	struct xfs_mount	*mp,
+	struct xfs_buf		*bp,
+	int			level)
+{
+	struct xfs_btree_block  *block = XFS_BUF_TO_BLOCK(bp);
+
+	if (be32_to_cpu(block->bb_magic) != XFS_BMAP_MAGIC ||
+	    be16_to_cpu(block->bb_level) != level ||
+	    be16_to_cpu(block->bb_numrecs) == 0 ||
+	    be16_to_cpu(block->bb_numrecs) > mp->m_bmap_dmxr[level != 0])
+		return 0;
+	return 1;
+}
+
 /*
  * Read in the extents to if_extents.
  * All inode fields are set up by caller, we just traverse the btree
@@ -4486,7 +4558,7 @@ xfs_bmap_read_extents(
 	xfs_inode_t		*ip,	/* incore inode */
 	int			whichfork) /* data or attr fork */
 {
-	xfs_bmbt_block_t	*block;	/* current btree block */
+	struct xfs_btree_block	*block;	/* current btree block */
 	xfs_fsblock_t		bno;	/* block # of "block" */
 	xfs_buf_t		*bp;	/* buffer for "block" */
 	int			error;	/* error return value */
@@ -4510,7 +4582,7 @@ xfs_bmap_read_extents(
 	 */
 	level = be16_to_cpu(block->bb_level);
 	ASSERT(level > 0);
-	pp = XFS_BMAP_BROOT_PTR_ADDR(block, 1, ifp->if_broot_bytes);
+	pp = XFS_BMAP_BROOT_PTR_ADDR(mp, block, 1, ifp->if_broot_bytes);
 	bno = be64_to_cpu(*pp);
 	ASSERT(bno != NULLDFSBNO);
 	ASSERT(XFS_FSB_TO_AGNO(mp, bno) < mp->m_sb.sb_agcount);
@@ -4523,13 +4595,13 @@ xfs_bmap_read_extents(
 		if ((error = xfs_btree_read_bufl(mp, tp, bno, 0, &bp,
 				XFS_BMAP_BTREE_REF)))
 			return error;
-		block = XFS_BUF_TO_BMBT_BLOCK(bp);
+		block = XFS_BUF_TO_BLOCK(bp);
 		XFS_WANT_CORRUPTED_GOTO(
-			XFS_BMAP_SANITY_CHECK(mp, block, level),
+			xfs_bmap_sanity_check(mp, bp, level),
 			error0);
 		if (level == 0)
 			break;
-		pp = XFS_BTREE_PTR_ADDR(xfs_bmbt, block, 1, mp->m_bmap_dmxr[1]);
+		pp = XFS_BMBT_PTR_ADDR(mp, block, 1, mp->m_bmap_dmxr[1]);
 		bno = be64_to_cpu(*pp);
 		XFS_WANT_CORRUPTED_GOTO(XFS_FSB_SANITY_CHECK(mp, bno), error0);
 		xfs_trans_brelse(tp, bp);
@@ -4549,7 +4621,7 @@ xfs_bmap_read_extents(
 		xfs_extnum_t	start;
 
 
-		num_recs = be16_to_cpu(block->bb_numrecs);
+		num_recs = xfs_btree_get_numrecs(block);
 		if (unlikely(i + num_recs > room)) {
 			ASSERT(i + num_recs <= room);
 			xfs_fs_repair_cmn_err(CE_WARN, ip->i_mount,
@@ -4561,18 +4633,18 @@ xfs_bmap_read_extents(
 			goto error0;
 		}
 		XFS_WANT_CORRUPTED_GOTO(
-			XFS_BMAP_SANITY_CHECK(mp, block, 0),
+			xfs_bmap_sanity_check(mp, bp, 0),
 			error0);
 		/*
 		 * Read-ahead the next leaf block, if any.
 		 */
-		nextbno = be64_to_cpu(block->bb_rightsib);
+		nextbno = be64_to_cpu(block->bb_u.l.bb_rightsib);
 		if (nextbno != NULLFSBLOCK)
 			xfs_btree_reada_bufl(mp, nextbno, 1);
 		/*
 		 * Copy records into the extent records.
 		 */
-		frp = XFS_BTREE_REC_ADDR(xfs_bmbt, block, 1);
+		frp = XFS_BMBT_REC_ADDR(mp, block, 1);
 		start = i;
 		for (j = 0; j < num_recs; j++, i++, frp++) {
 			xfs_bmbt_rec_host_t *trp = xfs_iext_get_ext(ifp, i);
@@ -4603,7 +4675,7 @@ xfs_bmap_read_extents(
 		if ((error = xfs_btree_read_bufl(mp, tp, bno, 0, &bp,
 				XFS_BMAP_BTREE_REF)))
 			return error;
-		block = XFS_BUF_TO_BMBT_BLOCK(bp);
+		block = XFS_BUF_TO_BLOCK(bp);
 	}
 	ASSERT(i == (ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t)));
 	ASSERT(i == XFS_IFORK_NEXTENTS(ip, whichfork));
@@ -5029,8 +5101,7 @@ xfs_bmapi(
 				if (abno == NULLFSBLOCK)
 					break;
 				if ((ifp->if_flags & XFS_IFBROOT) && !cur) {
-					cur = xfs_btree_init_cursor(mp,
-						tp, NULL, 0, XFS_BTNUM_BMAP,
+					cur = xfs_bmbt_init_cursor(mp, tp,
 						ip, whichfork);
 					cur->bc_private.b.firstblock =
 						*firstblock;
@@ -5147,9 +5218,8 @@ xfs_bmapi(
 			 */
 			ASSERT(mval->br_blockcount <= len);
 			if ((ifp->if_flags & XFS_IFBROOT) && !cur) {
-				cur = xfs_btree_init_cursor(mp,
-					tp, NULL, 0, XFS_BTNUM_BMAP,
-					ip, whichfork);
+				cur = xfs_bmbt_init_cursor(mp,
+					tp, ip, whichfork);
 				cur->bc_private.b.firstblock =
 					*firstblock;
 				cur->bc_private.b.flist = flist;
@@ -5440,8 +5510,7 @@ xfs_bunmapi(
 	logflags = 0;
 	if (ifp->if_flags & XFS_IFBROOT) {
 		ASSERT(XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_BTREE);
-		cur = xfs_btree_init_cursor(mp, tp, NULL, 0, XFS_BTNUM_BMAP, ip,
-			whichfork);
+		cur = xfs_bmbt_init_cursor(mp, tp, ip, whichfork);
 		cur->bc_private.b.firstblock = *firstblock;
 		cur->bc_private.b.flist = flist;
 		cur->bc_private.b.flags = 0;
@@ -5742,14 +5811,17 @@ error0:
 STATIC int
 xfs_getbmapx_fix_eof_hole(
 	xfs_inode_t		*ip,		/* xfs incore inode pointer */
-	struct getbmap		*out,		/* output structure */
+	struct getbmapx		*out,		/* output structure */
 	int			prealloced,	/* this is a file with
-						* preallocated data space */
+						 * preallocated data space */
 	__int64_t		end,		/* last block requested */
 	xfs_fsblock_t		startblock)
 {
 	__int64_t		fixlen;
 	xfs_mount_t		*mp;		/* file system mount point */
+	xfs_ifork_t		*ifp;		/* inode fork pointer */
+	xfs_extnum_t		lastx;		/* last extent pointer */
+	xfs_fileoff_t		fileblock;
 
 	if (startblock == HOLESTARTBLOCK) {
 		mp = ip->i_mount;
@@ -5763,21 +5835,33 @@ xfs_getbmapx_fix_eof_hole(
 			out->bmv_length = fixlen;
 		}
 	} else {
-		out->bmv_block = XFS_FSB_TO_DB(ip, startblock);
+		if (startblock == DELAYSTARTBLOCK)
+			out->bmv_block = -2;
+		else
+			out->bmv_block = XFS_FSB_TO_DB(ip, startblock);
+		fileblock = XFS_BB_TO_FSB(ip->i_mount, out->bmv_offset);
+		ifp = XFS_IFORK_PTR(ip, XFS_DATA_FORK);
+		if (xfs_iext_bno_to_ext(ifp, fileblock, &lastx) &&
+		   (lastx == (ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t))-1))
+			out->bmv_oflags |= BMV_OF_LAST;
 	}
 
 	return 1;
 }
 
 /*
- * Fcntl interface to xfs_bmapi.
+ * Get inode's extents as described in bmv, and format for output.
+ * Calls formatter to fill the user's buffer until all extents
+ * are mapped, until the passed-in bmv->bmv_count slots have
+ * been filled, or until the formatter short-circuits the loop,
+ * if it is tracking filled-in extents on its own.
  */
 int						/* error code */
 xfs_getbmap(
 	xfs_inode_t		*ip,
-	struct getbmap		*bmv,		/* user bmap structure */
-	void			__user *ap,	/* pointer to user's array */
-	int			interface)	/* interface flags */
+	struct getbmapx		*bmv,		/* user bmap structure */
+	xfs_bmap_format_t	formatter,	/* format to user */
+	void			*arg)		/* formatter arg */
 {
 	__int64_t		bmvend;		/* last block requested */
 	int			error;		/* return value */
@@ -5790,19 +5874,17 @@ xfs_getbmap(
 	int			nexleft;	/* # of user extents left */
 	int			subnex;		/* # of bmapi's can do */
 	int			nmap;		/* number of map entries */
-	struct getbmap		out;		/* output structure */
+	struct getbmapx		out;		/* output structure */
 	int			whichfork;	/* data or attr fork */
 	int			prealloced;	/* this is a file with
 						 * preallocated data space */
-	int			sh_unwritten;	/* true, if unwritten */
-						/* extents listed separately */
+	int			iflags;		/* interface flags */
 	int			bmapi_flags;	/* flags for xfs_bmapi */
-	__int32_t		oflags;		/* getbmapx bmv_oflags field */
 
 	mp = ip->i_mount;
+	iflags = bmv->bmv_iflags;
 
-	whichfork = interface & BMV_IF_ATTRFORK ? XFS_ATTR_FORK : XFS_DATA_FORK;
-	sh_unwritten = (interface & BMV_IF_PREALLOC) != 0;
+	whichfork = iflags & BMV_IF_ATTRFORK ? XFS_ATTR_FORK : XFS_DATA_FORK;
 
 	/*	If the BMV_IF_NO_DMAPI_READ interface bit specified, do not
 	 *	generate a DMAPI read event.  Otherwise, if the DM_EVENT_READ
@@ -5817,7 +5899,7 @@ xfs_getbmap(
 	 *	could misinterpret holes in a DMAPI file as true holes,
 	 *	when in fact they may represent offline user data.
 	 */
-	if ((interface & BMV_IF_NO_DMAPI_READ) == 0 &&
+	if ((iflags & BMV_IF_NO_DMAPI_READ) == 0 &&
 	    DM_EVENT_ENABLED(ip, DM_EVENT_READ) &&
 	    whichfork == XFS_DATA_FORK) {
 		error = XFS_SEND_DATA(mp, DM_EVENT_READ, ip, 0, 0, 0, NULL);
@@ -5873,8 +5955,9 @@ xfs_getbmap(
 
 	xfs_ilock(ip, XFS_IOLOCK_SHARED);
 
-	if (whichfork == XFS_DATA_FORK &&
-		(ip->i_delayed_blks || ip->i_size > ip->i_d.di_size)) {
+	if (((iflags & BMV_IF_DELALLOC) == 0) &&
+	    (whichfork == XFS_DATA_FORK) &&
+	    (ip->i_delayed_blks || ip->i_size > ip->i_d.di_size)) {
 		/* xfs_fsize_t last_byte = xfs_file_last_byte(ip); */
 		error = xfs_flush_pages(ip, (xfs_off_t)0,
 					       -1, 0, FI_REMAPF);
@@ -5884,7 +5967,8 @@ xfs_getbmap(
 		}
 	}
 
-	ASSERT(whichfork == XFS_ATTR_FORK || ip->i_delayed_blks == 0);
+	ASSERT(whichfork == XFS_ATTR_FORK || (iflags & BMV_IF_DELALLOC) ||
+	       ip->i_delayed_blks == 0);
 
 	lock = xfs_ilock_map_shared(ip);
 
@@ -5896,7 +5980,7 @@ xfs_getbmap(
 		nex = XFS_IFORK_NEXTENTS(ip, whichfork) * 2 + 1;
 
 	bmapi_flags = XFS_BMAPI_AFLAG(whichfork) |
-			((sh_unwritten) ? 0 : XFS_BMAPI_IGSTATE);
+			((iflags & BMV_IF_PREALLOC) ? 0 : XFS_BMAPI_IGSTATE);
 
 	/*
 	 * Allocate enough space to handle "subnex" maps at a time.
@@ -5906,9 +5990,12 @@ xfs_getbmap(
 
 	bmv->bmv_entries = 0;
 
-	if (XFS_IFORK_NEXTENTS(ip, whichfork) == 0) {
-		error = 0;
-		goto unlock_and_return;
+	if ((XFS_IFORK_NEXTENTS(ip, whichfork) == 0)) {
+		if (((iflags & BMV_IF_DELALLOC) == 0) ||
+		    whichfork == XFS_ATTR_FORK) {
+			error = 0;
+			goto unlock_and_return;
+		}
 	}
 
 	nexleft = nex;
@@ -5924,52 +6011,40 @@ xfs_getbmap(
 		ASSERT(nmap <= subnex);
 
 		for (i = 0; i < nmap && nexleft && bmv->bmv_length; i++) {
-			nexleft--;
-			oflags = (map[i].br_state == XFS_EXT_UNWRITTEN) ?
-					BMV_OF_PREALLOC : 0;
+			out.bmv_oflags = 0;
+			if (map[i].br_state == XFS_EXT_UNWRITTEN)
+				out.bmv_oflags |= BMV_OF_PREALLOC;
+			else if (map[i].br_startblock == DELAYSTARTBLOCK)
+				out.bmv_oflags |= BMV_OF_DELALLOC;
 			out.bmv_offset = XFS_FSB_TO_BB(mp, map[i].br_startoff);
 			out.bmv_length = XFS_FSB_TO_BB(mp, map[i].br_blockcount);
-			ASSERT(map[i].br_startblock != DELAYSTARTBLOCK);
+			out.bmv_unused1 = out.bmv_unused2 = 0;
+			ASSERT(((iflags & BMV_IF_DELALLOC) != 0) ||
+			      (map[i].br_startblock != DELAYSTARTBLOCK));
                         if (map[i].br_startblock == HOLESTARTBLOCK &&
 			    whichfork == XFS_ATTR_FORK) {
 				/* came to the end of attribute fork */
+				out.bmv_oflags |= BMV_OF_LAST;
 				goto unlock_and_return;
 			} else {
+				int full = 0;	/* user array is full */
+
 				if (!xfs_getbmapx_fix_eof_hole(ip, &out,
 							prealloced, bmvend,
 							map[i].br_startblock)) {
 					goto unlock_and_return;
 				}
 
-				/* return either getbmap/getbmapx structure. */
-				if (interface & BMV_IF_EXTENDED) {
-					struct	getbmapx	outx;
-
-					GETBMAP_CONVERT(out,outx);
-					outx.bmv_oflags = oflags;
-					outx.bmv_unused1 = outx.bmv_unused2 = 0;
-					if (copy_to_user(ap, &outx,
-							sizeof(outx))) {
-						error = XFS_ERROR(EFAULT);
-						goto unlock_and_return;
-					}
-				} else {
-					if (copy_to_user(ap, &out,
-							sizeof(out))) {
-						error = XFS_ERROR(EFAULT);
-						goto unlock_and_return;
-					}
-				}
+				/* format results & advance arg */
+				error = formatter(&arg, &out, &full);
+				if (error || full)
+					goto unlock_and_return;
+				nexleft--;
 				bmv->bmv_offset =
 					out.bmv_offset + out.bmv_length;
 				bmv->bmv_length = MAX((__int64_t)0,
 					(__int64_t)(bmvend - bmv->bmv_offset));
 				bmv->bmv_entries++;
-				ap = (interface & BMV_IF_EXTENDED) ?
-						(void __user *)
-					((struct getbmapx __user *)ap + 1) :
-						(void __user *)
-					((struct getbmap __user *)ap + 1);
 			}
 		}
 	} while (nmap && nexleft && bmv->bmv_length);
@@ -6131,7 +6206,7 @@ xfs_bmap_get_bp(
 
 void
 xfs_check_block(
-	xfs_bmbt_block_t        *block,
+	struct xfs_btree_block	*block,
 	xfs_mount_t		*mp,
 	int			root,
 	short			sz)
@@ -6143,36 +6218,29 @@ xfs_check_block(
 	ASSERT(be16_to_cpu(block->bb_level) > 0);
 
 	prevp = NULL;
-	for( i = 1; i <= be16_to_cpu(block->bb_numrecs); i++) {
+	for( i = 1; i <= xfs_btree_get_numrecs(block); i++) {
 		dmxr = mp->m_bmap_dmxr[0];
-
-		if (root) {
-			keyp = XFS_BMAP_BROOT_KEY_ADDR(block, i, sz);
-		} else {
-			keyp = XFS_BTREE_KEY_ADDR(xfs_bmbt, block, i);
-		}
+		keyp = XFS_BMBT_KEY_ADDR(mp, block, i);
 
 		if (prevp) {
-			xfs_btree_check_key(XFS_BTNUM_BMAP, prevp, keyp);
+			ASSERT(be64_to_cpu(prevp->br_startoff) <
+			       be64_to_cpu(keyp->br_startoff));
 		}
 		prevp = keyp;
 
 		/*
 		 * Compare the block numbers to see if there are dups.
 		 */
+		if (root)
+			pp = XFS_BMAP_BROOT_PTR_ADDR(mp, block, i, sz);
+		else
+			pp = XFS_BMBT_PTR_ADDR(mp, block, i, dmxr);
 
-		if (root) {
-			pp = XFS_BMAP_BROOT_PTR_ADDR(block, i, sz);
-		} else {
-			pp = XFS_BTREE_PTR_ADDR(xfs_bmbt, block, i, dmxr);
-		}
 		for (j = i+1; j <= be16_to_cpu(block->bb_numrecs); j++) {
-			if (root) {
-				thispa = XFS_BMAP_BROOT_PTR_ADDR(block, j, sz);
-			} else {
-				thispa = XFS_BTREE_PTR_ADDR(xfs_bmbt, block, j,
-							    dmxr);
-			}
+			if (root)
+				thispa = XFS_BMAP_BROOT_PTR_ADDR(mp, block, j, sz);
+			else
+				thispa = XFS_BMBT_PTR_ADDR(mp, block, j, dmxr);
 			if (*thispa == *pp) {
 				cmn_err(CE_WARN, "%s: thispa(%d) == pp(%d) %Ld",
 					__func__, j, i,
@@ -6195,7 +6263,7 @@ xfs_bmap_check_leaf_extents(
 	xfs_inode_t		*ip,		/* incore inode pointer */
 	int			whichfork)	/* data or attr fork */
 {
-	xfs_bmbt_block_t	*block;	/* current btree block */
+	struct xfs_btree_block	*block;	/* current btree block */
 	xfs_fsblock_t		bno;	/* block # of "block" */
 	xfs_buf_t		*bp;	/* buffer for "block" */
 	int			error;	/* error return value */
@@ -6223,7 +6291,7 @@ xfs_bmap_check_leaf_extents(
 	level = be16_to_cpu(block->bb_level);
 	ASSERT(level > 0);
 	xfs_check_block(block, mp, 1, ifp->if_broot_bytes);
-	pp = XFS_BMAP_BROOT_PTR_ADDR(block, 1, ifp->if_broot_bytes);
+	pp = XFS_BMAP_BROOT_PTR_ADDR(mp, block, 1, ifp->if_broot_bytes);
 	bno = be64_to_cpu(*pp);
 
 	ASSERT(bno != NULLDFSBNO);
@@ -6245,9 +6313,9 @@ xfs_bmap_check_leaf_extents(
 		if (!bp && (error = xfs_btree_read_bufl(mp, NULL, bno, 0, &bp,
 				XFS_BMAP_BTREE_REF)))
 			goto error_norelse;
-		block = XFS_BUF_TO_BMBT_BLOCK(bp);
+		block = XFS_BUF_TO_BLOCK(bp);
 		XFS_WANT_CORRUPTED_GOTO(
-			XFS_BMAP_SANITY_CHECK(mp, block, level),
+			xfs_bmap_sanity_check(mp, bp, level),
 			error0);
 		if (level == 0)
 			break;
@@ -6258,7 +6326,7 @@ xfs_bmap_check_leaf_extents(
 		 */
 
 		xfs_check_block(block, mp, 0, 0);
-		pp = XFS_BTREE_PTR_ADDR(xfs_bmbt, block, 1, mp->m_bmap_dmxr[1]);
+		pp = XFS_BMBT_PTR_ADDR(mp, block, 1, mp->m_bmap_dmxr[1]);
 		bno = be64_to_cpu(*pp);
 		XFS_WANT_CORRUPTED_GOTO(XFS_FSB_SANITY_CHECK(mp, bno), error0);
 		if (bp_release) {
@@ -6280,13 +6348,13 @@ xfs_bmap_check_leaf_extents(
 		xfs_extnum_t	num_recs;
 
 
-		num_recs = be16_to_cpu(block->bb_numrecs);
+		num_recs = xfs_btree_get_numrecs(block);
 
 		/*
 		 * Read-ahead the next leaf block, if any.
 		 */
 
-		nextbno = be64_to_cpu(block->bb_rightsib);
+		nextbno = be64_to_cpu(block->bb_u.l.bb_rightsib);
 
 		/*
 		 * Check all the extents to make sure they are OK.
@@ -6294,13 +6362,17 @@ xfs_bmap_check_leaf_extents(
 		 * conform with the first entry in this one.
 		 */
 
-		ep = XFS_BTREE_REC_ADDR(xfs_bmbt, block, 1);
+		ep = XFS_BMBT_REC_ADDR(mp, block, 1);
 		if (i) {
-			xfs_btree_check_rec(XFS_BTNUM_BMAP, &last, ep);
+			ASSERT(xfs_bmbt_disk_get_startoff(&last) +
+			       xfs_bmbt_disk_get_blockcount(&last) <=
+			       xfs_bmbt_disk_get_startoff(ep));
 		}
 		for (j = 1; j < num_recs; j++) {
-			nextp = XFS_BTREE_REC_ADDR(xfs_bmbt, block, j + 1);
-			xfs_btree_check_rec(XFS_BTNUM_BMAP, ep, nextp);
+			nextp = XFS_BMBT_REC_ADDR(mp, block, j + 1);
+			ASSERT(xfs_bmbt_disk_get_startoff(ep) +
+			       xfs_bmbt_disk_get_blockcount(ep) <=
+			       xfs_bmbt_disk_get_startoff(nextp));
 			ep = nextp;
 		}
 
@@ -6326,7 +6398,7 @@ xfs_bmap_check_leaf_extents(
 		if (!bp && (error = xfs_btree_read_bufl(mp, NULL, bno, 0, &bp,
 				XFS_BMAP_BTREE_REF)))
 			goto error_norelse;
-		block = XFS_BUF_TO_BMBT_BLOCK(bp);
+		block = XFS_BUF_TO_BLOCK(bp);
 	}
 	if (bp_release) {
 		bp_release = 0;
@@ -6356,7 +6428,7 @@ xfs_bmap_count_blocks(
 	int			whichfork,	/* data or attr fork */
 	int			*count)		/* out: count of blocks */
 {
-	xfs_bmbt_block_t	*block;	/* current btree block */
+	struct xfs_btree_block	*block;	/* current btree block */
 	xfs_fsblock_t		bno;	/* block # of "block" */
 	xfs_ifork_t		*ifp;	/* fork structure */
 	int			level;	/* btree level, for checking */
@@ -6379,7 +6451,7 @@ xfs_bmap_count_blocks(
 	block = ifp->if_broot;
 	level = be16_to_cpu(block->bb_level);
 	ASSERT(level > 0);
-	pp = XFS_BMAP_BROOT_PTR_ADDR(block, 1, ifp->if_broot_bytes);
+	pp = XFS_BMAP_BROOT_PTR_ADDR(mp, block, 1, ifp->if_broot_bytes);
 	bno = be64_to_cpu(*pp);
 	ASSERT(bno != NULLDFSBNO);
 	ASSERT(XFS_FSB_TO_AGNO(mp, bno) < mp->m_sb.sb_agcount);
@@ -6413,29 +6485,29 @@ xfs_bmap_count_tree(
 	__be64			*pp;
 	xfs_fsblock_t           bno = blockno;
 	xfs_fsblock_t		nextbno;
-	xfs_bmbt_block_t        *block, *nextblock;
+	struct xfs_btree_block	*block, *nextblock;
 	int			numrecs;
 
 	if ((error = xfs_btree_read_bufl(mp, tp, bno, 0, &bp, XFS_BMAP_BTREE_REF)))
 		return error;
 	*count += 1;
-	block = XFS_BUF_TO_BMBT_BLOCK(bp);
+	block = XFS_BUF_TO_BLOCK(bp);
 
 	if (--level) {
 		/* Not at node above leafs, count this level of nodes */
-		nextbno = be64_to_cpu(block->bb_rightsib);
+		nextbno = be64_to_cpu(block->bb_u.l.bb_rightsib);
 		while (nextbno != NULLFSBLOCK) {
 			if ((error = xfs_btree_read_bufl(mp, tp, nextbno,
 				0, &nbp, XFS_BMAP_BTREE_REF)))
 				return error;
 			*count += 1;
-			nextblock = XFS_BUF_TO_BMBT_BLOCK(nbp);
-			nextbno = be64_to_cpu(nextblock->bb_rightsib);
+			nextblock = XFS_BUF_TO_BLOCK(nbp);
+			nextbno = be64_to_cpu(nextblock->bb_u.l.bb_rightsib);
 			xfs_trans_brelse(tp, nbp);
 		}
 
 		/* Dive to the next level */
-		pp = XFS_BTREE_PTR_ADDR(xfs_bmbt, block, 1, mp->m_bmap_dmxr[1]);
+		pp = XFS_BMBT_PTR_ADDR(mp, block, 1, mp->m_bmap_dmxr[1]);
 		bno = be64_to_cpu(*pp);
 		if (unlikely((error =
 		     xfs_bmap_count_tree(mp, tp, ifp, bno, level, count)) < 0)) {
@@ -6448,9 +6520,9 @@ xfs_bmap_count_tree(
 	} else {
 		/* count all level 1 nodes and their leaves */
 		for (;;) {
-			nextbno = be64_to_cpu(block->bb_rightsib);
+			nextbno = be64_to_cpu(block->bb_u.l.bb_rightsib);
 			numrecs = be16_to_cpu(block->bb_numrecs);
-			xfs_bmap_disk_count_leaves(0, block, numrecs, count);
+			xfs_bmap_disk_count_leaves(mp, block, numrecs, count);
 			xfs_trans_brelse(tp, bp);
 			if (nextbno == NULLFSBLOCK)
 				break;
@@ -6459,7 +6531,7 @@ xfs_bmap_count_tree(
 				XFS_BMAP_BTREE_REF)))
 				return error;
 			*count += 1;
-			block = XFS_BUF_TO_BMBT_BLOCK(bp);
+			block = XFS_BUF_TO_BLOCK(bp);
 		}
 	}
 	return 0;
@@ -6489,8 +6561,8 @@ xfs_bmap_count_leaves(
  */
 STATIC void
 xfs_bmap_disk_count_leaves(
-	xfs_extnum_t		idx,
-	xfs_bmbt_block_t	*block,
+	struct xfs_mount	*mp,
+	struct xfs_btree_block	*block,
 	int			numrecs,
 	int			*count)
 {
@@ -6498,7 +6570,7 @@ xfs_bmap_disk_count_leaves(
 	xfs_bmbt_rec_t	*frp;
 
 	for (b = 1; b <= numrecs; b++) {
-		frp = XFS_BTREE_REC_ADDR(xfs_bmbt, block, idx + b);
+		frp = XFS_BMBT_REC_ADDR(mp, block, b);
 		*count += xfs_bmbt_disk_get_blockcount(frp);
 	}
 }
diff --git a/fs/xfs/xfs_bmap.h b/fs/xfs/xfs_bmap.h
index 9f3e3a836d15..284571c05ed0 100644
--- a/fs/xfs/xfs_bmap.h
+++ b/fs/xfs/xfs_bmap.h
@@ -137,9 +137,7 @@ typedef struct xfs_bmalloca {
 	char			conv;	/* overwriting unwritten extents */
 } xfs_bmalloca_t;
 
-#ifdef __KERNEL__
-
-#if defined(XFS_BMAP_TRACE)
+#if defined(__KERNEL__) && defined(XFS_BMAP_TRACE)
 /*
  * Trace operations for bmap extent tracing
  */
@@ -163,9 +161,12 @@ xfs_bmap_trace_exlist(
 	int			whichfork);	/* data or attr fork */
 #define	XFS_BMAP_TRACE_EXLIST(ip,c,w)	\
 	xfs_bmap_trace_exlist(__func__,ip,c,w)
-#else
+
+#else	/* __KERNEL__ && XFS_BMAP_TRACE */
+
 #define	XFS_BMAP_TRACE_EXLIST(ip,c,w)
-#endif
+
+#endif	/* __KERNEL__ && XFS_BMAP_TRACE */
 
 /*
  * Convert inode from non-attributed to attributed.
@@ -206,20 +207,6 @@ xfs_bmap_compute_maxlevels(
 	int			whichfork);	/* data or attr fork */
 
 /*
- * Routine to be called at transaction's end by xfs_bmapi, xfs_bunmapi
- * caller.  Frees all the extents that need freeing, which must be done
- * last due to locking considerations.
- *
- * Return 1 if the given transaction was committed and a new one allocated,
- * and 0 otherwise.
- */
-int						/* error */
-xfs_bmap_finish(
-	struct xfs_trans	**tp,		/* transaction pointer addr */
-	xfs_bmap_free_t		*flist,		/* i/o: list extents to free */
-	int			*committed);	/* xact committed or not */
-
-/*
  * Returns the file-relative block number of the first unused block in the file.
  * This is the lowest-address hole if the file has holes, else the first block
  * past the end of file.
@@ -344,14 +331,43 @@ xfs_bunmapi(
 	int			*done);		/* set if not done yet */
 
 /*
- * Fcntl interface to xfs_bmapi.
+ * Check an extent list, which has just been read, for
+ * any bit in the extent flag field.
+ */
+int
+xfs_check_nostate_extents(
+	struct xfs_ifork	*ifp,
+	xfs_extnum_t		idx,
+	xfs_extnum_t		num);
+
+#ifdef __KERNEL__
+
+/*
+ * Routine to be called at transaction's end by xfs_bmapi, xfs_bunmapi
+ * caller.  Frees all the extents that need freeing, which must be done
+ * last due to locking considerations.
+ *
+ * Return 1 if the given transaction was committed and a new one allocated,
+ * and 0 otherwise.
+ */
+int						/* error */
+xfs_bmap_finish(
+	struct xfs_trans	**tp,		/* transaction pointer addr */
+	xfs_bmap_free_t		*flist,		/* i/o: list extents to free */
+	int			*committed);	/* xact committed or not */
+
+/* bmap to userspace formatter - copy to user & advance pointer */
+typedef int (*xfs_bmap_format_t)(void **, struct getbmapx *, int *);
+
+/*
+ * Get inode's extents as described in bmv, and format for output.
  */
 int						/* error code */
 xfs_getbmap(
 	xfs_inode_t		*ip,
-	struct getbmap		*bmv,		/* user bmap structure */
-	void			__user *ap,	/* pointer to user's array */
-	int			iflags);	/* interface flags */
+	struct getbmapx		*bmv,		/* user bmap structure */
+	xfs_bmap_format_t	formatter,	/* format to user */
+	void			*arg);		/* formatter arg */
 
 /*
  * Check if the endoff is outside the last extent. If so the caller will grow
@@ -375,16 +391,6 @@ xfs_bmap_count_blocks(
 	int			*count);
 
 /*
- * Check an extent list, which has just been read, for
- * any bit in the extent flag field.
- */
-int
-xfs_check_nostate_extents(
-	struct xfs_ifork	*ifp,
-	xfs_extnum_t		idx,
-	xfs_extnum_t		num);
-
-/*
  * Search the extent records for the entry containing block bno.
  * If bno lies in a hole, point to the next entry.  If bno lies
  * past eof, *eofp will be set, and *prevp will contain the last
diff --git a/fs/xfs/xfs_bmap_btree.c b/fs/xfs/xfs_bmap_btree.c
index 23efad29a5cd..e46e02b8e277 100644
--- a/fs/xfs/xfs_bmap_btree.c
+++ b/fs/xfs/xfs_bmap_btree.c
@@ -37,1406 +37,13 @@
 #include "xfs_inode_item.h"
 #include "xfs_alloc.h"
 #include "xfs_btree.h"
+#include "xfs_btree_trace.h"
 #include "xfs_ialloc.h"
 #include "xfs_itable.h"
 #include "xfs_bmap.h"
 #include "xfs_error.h"
 #include "xfs_quota.h"
 
-#if defined(XFS_BMBT_TRACE)
-ktrace_t	*xfs_bmbt_trace_buf;
-#endif
-
-/*
- * Prototypes for internal btree functions.
- */
-
-
-STATIC int xfs_bmbt_killroot(xfs_btree_cur_t *);
-STATIC void xfs_bmbt_log_keys(xfs_btree_cur_t *, xfs_buf_t *, int, int);
-STATIC void xfs_bmbt_log_ptrs(xfs_btree_cur_t *, xfs_buf_t *, int, int);
-STATIC int xfs_bmbt_lshift(xfs_btree_cur_t *, int, int *);
-STATIC int xfs_bmbt_rshift(xfs_btree_cur_t *, int, int *);
-STATIC int xfs_bmbt_split(xfs_btree_cur_t *, int, xfs_fsblock_t *,
-		__uint64_t *, xfs_btree_cur_t **, int *);
-STATIC int xfs_bmbt_updkey(xfs_btree_cur_t *, xfs_bmbt_key_t *, int);
-
-
-#if defined(XFS_BMBT_TRACE)
-
-static char	ARGS[] = "args";
-static char	ENTRY[] = "entry";
-static char	ERROR[] = "error";
-#undef EXIT
-static char	EXIT[] = "exit";
-
-/*
- * Add a trace buffer entry for the arguments given to the routine,
- * generic form.
- */
-STATIC void
-xfs_bmbt_trace_enter(
-	const char	*func,
-	xfs_btree_cur_t	*cur,
-	char		*s,
-	int		type,
-	int		line,
-	__psunsigned_t	a0,
-	__psunsigned_t	a1,
-	__psunsigned_t	a2,
-	__psunsigned_t	a3,
-	__psunsigned_t	a4,
-	__psunsigned_t	a5,
-	__psunsigned_t	a6,
-	__psunsigned_t	a7,
-	__psunsigned_t	a8,
-	__psunsigned_t	a9,
-	__psunsigned_t	a10)
-{
-	xfs_inode_t	*ip;
-	int		whichfork;
-
-	ip = cur->bc_private.b.ip;
-	whichfork = cur->bc_private.b.whichfork;
-	ktrace_enter(xfs_bmbt_trace_buf,
-		(void *)((__psint_t)type | (whichfork << 8) | (line << 16)),
-		(void *)func, (void *)s, (void *)ip, (void *)cur,
-		(void *)a0, (void *)a1, (void *)a2, (void *)a3,
-		(void *)a4, (void *)a5, (void *)a6, (void *)a7,
-		(void *)a8, (void *)a9, (void *)a10);
-	ASSERT(ip->i_btrace);
-	ktrace_enter(ip->i_btrace,
-		(void *)((__psint_t)type | (whichfork << 8) | (line << 16)),
-		(void *)func, (void *)s, (void *)ip, (void *)cur,
-		(void *)a0, (void *)a1, (void *)a2, (void *)a3,
-		(void *)a4, (void *)a5, (void *)a6, (void *)a7,
-		(void *)a8, (void *)a9, (void *)a10);
-}
-/*
- * Add a trace buffer entry for arguments, for a buffer & 1 integer arg.
- */
-STATIC void
-xfs_bmbt_trace_argbi(
-	const char	*func,
-	xfs_btree_cur_t	*cur,
-	xfs_buf_t	*b,
-	int		i,
-	int		line)
-{
-	xfs_bmbt_trace_enter(func, cur, ARGS, XFS_BMBT_KTRACE_ARGBI, line,
-		(__psunsigned_t)b, i, 0, 0,
-		0, 0, 0, 0,
-		0, 0, 0);
-}
-
-/*
- * Add a trace buffer entry for arguments, for a buffer & 2 integer args.
- */
-STATIC void
-xfs_bmbt_trace_argbii(
-	const char	*func,
-	xfs_btree_cur_t	*cur,
-	xfs_buf_t	*b,
-	int		i0,
-	int		i1,
-	int		line)
-{
-	xfs_bmbt_trace_enter(func, cur, ARGS, XFS_BMBT_KTRACE_ARGBII, line,
-		(__psunsigned_t)b, i0, i1, 0,
-		0, 0, 0, 0,
-		0, 0, 0);
-}
-
-/*
- * Add a trace buffer entry for arguments, for 3 block-length args
- * and an integer arg.
- */
-STATIC void
-xfs_bmbt_trace_argfffi(
-	const char		*func,
-	xfs_btree_cur_t		*cur,
-	xfs_dfiloff_t		o,
-	xfs_dfsbno_t		b,
-	xfs_dfilblks_t		i,
-	int			j,
-	int			line)
-{
-	xfs_bmbt_trace_enter(func, cur, ARGS, XFS_BMBT_KTRACE_ARGFFFI, line,
-		o >> 32, (int)o, b >> 32, (int)b,
-		i >> 32, (int)i, (int)j, 0,
-		0, 0, 0);
-}
-
-/*
- * Add a trace buffer entry for arguments, for one integer arg.
- */
-STATIC void
-xfs_bmbt_trace_argi(
-	const char	*func,
-	xfs_btree_cur_t	*cur,
-	int		i,
-	int		line)
-{
-	xfs_bmbt_trace_enter(func, cur, ARGS, XFS_BMBT_KTRACE_ARGI, line,
-		i, 0, 0, 0,
-		0, 0, 0, 0,
-		0, 0, 0);
-}
-
-/*
- * Add a trace buffer entry for arguments, for int, fsblock, key.
- */
-STATIC void
-xfs_bmbt_trace_argifk(
-	const char		*func,
-	xfs_btree_cur_t		*cur,
-	int			i,
-	xfs_fsblock_t		f,
-	xfs_dfiloff_t		o,
-	int			line)
-{
-	xfs_bmbt_trace_enter(func, cur, ARGS, XFS_BMBT_KTRACE_ARGIFK, line,
-		i, (xfs_dfsbno_t)f >> 32, (int)f, o >> 32,
-		(int)o, 0, 0, 0,
-		0, 0, 0);
-}
-
-/*
- * Add a trace buffer entry for arguments, for int, fsblock, rec.
- */
-STATIC void
-xfs_bmbt_trace_argifr(
-	const char		*func,
-	xfs_btree_cur_t		*cur,
-	int			i,
-	xfs_fsblock_t		f,
-	xfs_bmbt_rec_t		*r,
-	int			line)
-{
-	xfs_dfsbno_t		b;
-	xfs_dfilblks_t		c;
-	xfs_dfsbno_t		d;
-	xfs_dfiloff_t		o;
-	xfs_bmbt_irec_t		s;
-
-	d = (xfs_dfsbno_t)f;
-	xfs_bmbt_disk_get_all(r, &s);
-	o = (xfs_dfiloff_t)s.br_startoff;
-	b = (xfs_dfsbno_t)s.br_startblock;
-	c = s.br_blockcount;
-	xfs_bmbt_trace_enter(func, cur, ARGS, XFS_BMBT_KTRACE_ARGIFR, line,
-		i, d >> 32, (int)d, o >> 32,
-		(int)o, b >> 32, (int)b, c >> 32,
-		(int)c, 0, 0);
-}
-
-/*
- * Add a trace buffer entry for arguments, for int, key.
- */
-STATIC void
-xfs_bmbt_trace_argik(
-	const char		*func,
-	xfs_btree_cur_t		*cur,
-	int			i,
-	xfs_bmbt_key_t		*k,
-	int			line)
-{
-	xfs_dfiloff_t		o;
-
-	o = be64_to_cpu(k->br_startoff);
-	xfs_bmbt_trace_enter(func, cur, ARGS, XFS_BMBT_KTRACE_ARGIFK, line,
-		i, o >> 32, (int)o, 0,
-		0, 0, 0, 0,
-		0, 0, 0);
-}
-
-/*
- * Add a trace buffer entry for the cursor/operation.
- */
-STATIC void
-xfs_bmbt_trace_cursor(
-	const char	*func,
-	xfs_btree_cur_t	*cur,
-	char		*s,
-	int		line)
-{
-	xfs_bmbt_rec_host_t	r;
-
-	xfs_bmbt_set_all(&r, &cur->bc_rec.b);
-	xfs_bmbt_trace_enter(func, cur, s, XFS_BMBT_KTRACE_CUR, line,
-		(cur->bc_nlevels << 24) | (cur->bc_private.b.flags << 16) |
-		cur->bc_private.b.allocated,
-		r.l0 >> 32, (int)r.l0,
-		r.l1 >> 32, (int)r.l1,
-		(unsigned long)cur->bc_bufs[0], (unsigned long)cur->bc_bufs[1],
-		(unsigned long)cur->bc_bufs[2], (unsigned long)cur->bc_bufs[3],
-		(cur->bc_ptrs[0] << 16) | cur->bc_ptrs[1],
-		(cur->bc_ptrs[2] << 16) | cur->bc_ptrs[3]);
-}
-
-#define	XFS_BMBT_TRACE_ARGBI(c,b,i)	\
-	xfs_bmbt_trace_argbi(__func__, c, b, i, __LINE__)
-#define	XFS_BMBT_TRACE_ARGBII(c,b,i,j)	\
-	xfs_bmbt_trace_argbii(__func__, c, b, i, j, __LINE__)
-#define	XFS_BMBT_TRACE_ARGFFFI(c,o,b,i,j)	\
-	xfs_bmbt_trace_argfffi(__func__, c, o, b, i, j, __LINE__)
-#define	XFS_BMBT_TRACE_ARGI(c,i)	\
-	xfs_bmbt_trace_argi(__func__, c, i, __LINE__)
-#define	XFS_BMBT_TRACE_ARGIFK(c,i,f,s)	\
-	xfs_bmbt_trace_argifk(__func__, c, i, f, s, __LINE__)
-#define	XFS_BMBT_TRACE_ARGIFR(c,i,f,r)	\
-	xfs_bmbt_trace_argifr(__func__, c, i, f, r, __LINE__)
-#define	XFS_BMBT_TRACE_ARGIK(c,i,k)	\
-	xfs_bmbt_trace_argik(__func__, c, i, k, __LINE__)
-#define	XFS_BMBT_TRACE_CURSOR(c,s)	\
-	xfs_bmbt_trace_cursor(__func__, c, s, __LINE__)
-#else
-#define	XFS_BMBT_TRACE_ARGBI(c,b,i)
-#define	XFS_BMBT_TRACE_ARGBII(c,b,i,j)
-#define	XFS_BMBT_TRACE_ARGFFFI(c,o,b,i,j)
-#define	XFS_BMBT_TRACE_ARGI(c,i)
-#define	XFS_BMBT_TRACE_ARGIFK(c,i,f,s)
-#define	XFS_BMBT_TRACE_ARGIFR(c,i,f,r)
-#define	XFS_BMBT_TRACE_ARGIK(c,i,k)
-#define	XFS_BMBT_TRACE_CURSOR(c,s)
-#endif	/* XFS_BMBT_TRACE */
-
-
-/*
- * Internal functions.
- */
-
-/*
- * Delete record pointed to by cur/level.
- */
-STATIC int					/* error */
-xfs_bmbt_delrec(
-	xfs_btree_cur_t		*cur,
-	int			level,
-	int			*stat)		/* success/failure */
-{
-	xfs_bmbt_block_t	*block;		/* bmap btree block */
-	xfs_fsblock_t		bno;		/* fs-relative block number */
-	xfs_buf_t		*bp;		/* buffer for block */
-	int			error;		/* error return value */
-	int			i;		/* loop counter */
-	int			j;		/* temp state */
-	xfs_bmbt_key_t		key;		/* bmap btree key */
-	xfs_bmbt_key_t		*kp=NULL;	/* pointer to bmap btree key */
-	xfs_fsblock_t		lbno;		/* left sibling block number */
-	xfs_buf_t		*lbp;		/* left buffer pointer */
-	xfs_bmbt_block_t	*left;		/* left btree block */
-	xfs_bmbt_key_t		*lkp;		/* left btree key */
-	xfs_bmbt_ptr_t		*lpp;		/* left address pointer */
-	int			lrecs=0;	/* left record count */
-	xfs_bmbt_rec_t		*lrp;		/* left record pointer */
-	xfs_mount_t		*mp;		/* file system mount point */
-	xfs_bmbt_ptr_t		*pp;		/* pointer to bmap block addr */
-	int			ptr;		/* key/record index */
-	xfs_fsblock_t		rbno;		/* right sibling block number */
-	xfs_buf_t		*rbp;		/* right buffer pointer */
-	xfs_bmbt_block_t	*right;		/* right btree block */
-	xfs_bmbt_key_t		*rkp;		/* right btree key */
-	xfs_bmbt_rec_t		*rp;		/* pointer to bmap btree rec */
-	xfs_bmbt_ptr_t		*rpp;		/* right address pointer */
-	xfs_bmbt_block_t	*rrblock;	/* right-right btree block */
-	xfs_buf_t		*rrbp;		/* right-right buffer pointer */
-	int			rrecs=0;	/* right record count */
-	xfs_bmbt_rec_t		*rrp;		/* right record pointer */
-	xfs_btree_cur_t		*tcur;		/* temporary btree cursor */
-	int			numrecs;	/* temporary numrec count */
-	int			numlrecs, numrrecs;
-
-	XFS_BMBT_TRACE_CURSOR(cur, ENTRY);
-	XFS_BMBT_TRACE_ARGI(cur, level);
-	ptr = cur->bc_ptrs[level];
-	tcur = NULL;
-	if (ptr == 0) {
-		XFS_BMBT_TRACE_CURSOR(cur, EXIT);
-		*stat = 0;
-		return 0;
-	}
-	block = xfs_bmbt_get_block(cur, level, &bp);
-	numrecs = be16_to_cpu(block->bb_numrecs);
-#ifdef DEBUG
-	if ((error = xfs_btree_check_lblock(cur, block, level, bp))) {
-		XFS_BMBT_TRACE_CURSOR(cur, ERROR);
-		goto error0;
-	}
-#endif
-	if (ptr > numrecs) {
-		XFS_BMBT_TRACE_CURSOR(cur, EXIT);
-		*stat = 0;
-		return 0;
-	}
-	XFS_STATS_INC(xs_bmbt_delrec);
-	if (level > 0) {
-		kp = XFS_BMAP_KEY_IADDR(block, 1, cur);
-		pp = XFS_BMAP_PTR_IADDR(block, 1, cur);
-#ifdef DEBUG
-		for (i = ptr; i < numrecs; i++) {
-			if ((error = xfs_btree_check_lptr_disk(cur, pp[i], level))) {
-				XFS_BMBT_TRACE_CURSOR(cur, ERROR);
-				goto error0;
-			}
-		}
-#endif
-		if (ptr < numrecs) {
-			memmove(&kp[ptr - 1], &kp[ptr],
-				(numrecs - ptr) * sizeof(*kp));
-			memmove(&pp[ptr - 1], &pp[ptr],
-				(numrecs - ptr) * sizeof(*pp));
-			xfs_bmbt_log_ptrs(cur, bp, ptr, numrecs - 1);
-			xfs_bmbt_log_keys(cur, bp, ptr, numrecs - 1);
-		}
-	} else {
-		rp = XFS_BMAP_REC_IADDR(block, 1, cur);
-		if (ptr < numrecs) {
-			memmove(&rp[ptr - 1], &rp[ptr],
-				(numrecs - ptr) * sizeof(*rp));
-			xfs_bmbt_log_recs(cur, bp, ptr, numrecs - 1);
-		}
-		if (ptr == 1) {
-			key.br_startoff =
-				cpu_to_be64(xfs_bmbt_disk_get_startoff(rp));
-			kp = &key;
-		}
-	}
-	numrecs--;
-	block->bb_numrecs = cpu_to_be16(numrecs);
-	xfs_bmbt_log_block(cur, bp, XFS_BB_NUMRECS);
-	/*
-	 * We're at the root level.
-	 * First, shrink the root block in-memory.
-	 * Try to get rid of the next level down.
-	 * If we can't then there's nothing left to do.
-	 */
-	if (level == cur->bc_nlevels - 1) {
-		xfs_iroot_realloc(cur->bc_private.b.ip, -1,
-			cur->bc_private.b.whichfork);
-		if ((error = xfs_bmbt_killroot(cur))) {
-			XFS_BMBT_TRACE_CURSOR(cur, ERROR);
-			goto error0;
-		}
-		if (level > 0 && (error = xfs_bmbt_decrement(cur, level, &j))) {
-			XFS_BMBT_TRACE_CURSOR(cur, ERROR);
-			goto error0;
-		}
-		XFS_BMBT_TRACE_CURSOR(cur, EXIT);
-		*stat = 1;
-		return 0;
-	}
-	if (ptr == 1 && (error = xfs_bmbt_updkey(cur, kp, level + 1))) {
-		XFS_BMBT_TRACE_CURSOR(cur, ERROR);
-		goto error0;
-	}
-	if (numrecs >= XFS_BMAP_BLOCK_IMINRECS(level, cur)) {
-		if (level > 0 && (error = xfs_bmbt_decrement(cur, level, &j))) {
-			XFS_BMBT_TRACE_CURSOR(cur, ERROR);
-			goto error0;
-		}
-		XFS_BMBT_TRACE_CURSOR(cur, EXIT);
-		*stat = 1;
-		return 0;
-	}
-	rbno = be64_to_cpu(block->bb_rightsib);
-	lbno = be64_to_cpu(block->bb_leftsib);
-	/*
-	 * One child of root, need to get a chance to copy its contents
-	 * into the root and delete it. Can't go up to next level,
-	 * there's nothing to delete there.
-	 */
-	if (lbno == NULLFSBLOCK && rbno == NULLFSBLOCK &&
-	    level == cur->bc_nlevels - 2) {
-		if ((error = xfs_bmbt_killroot(cur))) {
-			XFS_BMBT_TRACE_CURSOR(cur, ERROR);
-			goto error0;
-		}
-		if (level > 0 && (error = xfs_bmbt_decrement(cur, level, &i))) {
-			XFS_BMBT_TRACE_CURSOR(cur, ERROR);
-			goto error0;
-		}
-		XFS_BMBT_TRACE_CURSOR(cur, EXIT);
-		*stat = 1;
-		return 0;
-	}
-	ASSERT(rbno != NULLFSBLOCK || lbno != NULLFSBLOCK);
-	if ((error = xfs_btree_dup_cursor(cur, &tcur))) {
-		XFS_BMBT_TRACE_CURSOR(cur, ERROR);
-		goto error0;
-	}
-	bno = NULLFSBLOCK;
-	if (rbno != NULLFSBLOCK) {
-		i = xfs_btree_lastrec(tcur, level);
-		XFS_WANT_CORRUPTED_GOTO(i == 1, error0);
-		if ((error = xfs_bmbt_increment(tcur, level, &i))) {
-			XFS_BMBT_TRACE_CURSOR(cur, ERROR);
-			goto error0;
-		}
-		XFS_WANT_CORRUPTED_GOTO(i == 1, error0);
-		i = xfs_btree_lastrec(tcur, level);
-		XFS_WANT_CORRUPTED_GOTO(i == 1, error0);
-		rbp = tcur->bc_bufs[level];
-		right = XFS_BUF_TO_BMBT_BLOCK(rbp);
-#ifdef DEBUG
-		if ((error = xfs_btree_check_lblock(cur, right, level, rbp))) {
-			XFS_BMBT_TRACE_CURSOR(cur, ERROR);
-			goto error0;
-		}
-#endif
-		bno = be64_to_cpu(right->bb_leftsib);
-		if (be16_to_cpu(right->bb_numrecs) - 1 >=
-		    XFS_BMAP_BLOCK_IMINRECS(level, cur)) {
-			if ((error = xfs_bmbt_lshift(tcur, level, &i))) {
-				XFS_BMBT_TRACE_CURSOR(cur, ERROR);
-				goto error0;
-			}
-			if (i) {
-				ASSERT(be16_to_cpu(block->bb_numrecs) >=
-				       XFS_BMAP_BLOCK_IMINRECS(level, tcur));
-				xfs_btree_del_cursor(tcur, XFS_BTREE_NOERROR);
-				tcur = NULL;
-				if (level > 0) {
-					if ((error = xfs_bmbt_decrement(cur,
-							level, &i))) {
-						XFS_BMBT_TRACE_CURSOR(cur,
-							ERROR);
-						goto error0;
-					}
-				}
-				XFS_BMBT_TRACE_CURSOR(cur, EXIT);
-				*stat = 1;
-				return 0;
-			}
-		}
-		rrecs = be16_to_cpu(right->bb_numrecs);
-		if (lbno != NULLFSBLOCK) {
-			i = xfs_btree_firstrec(tcur, level);
-			XFS_WANT_CORRUPTED_GOTO(i == 1, error0);
-			if ((error = xfs_bmbt_decrement(tcur, level, &i))) {
-				XFS_BMBT_TRACE_CURSOR(cur, ERROR);
-				goto error0;
-			}
-			XFS_WANT_CORRUPTED_GOTO(i == 1, error0);
-		}
-	}
-	if (lbno != NULLFSBLOCK) {
-		i = xfs_btree_firstrec(tcur, level);
-		XFS_WANT_CORRUPTED_GOTO(i == 1, error0);
-		/*
-		 * decrement to last in block
-		 */
-		if ((error = xfs_bmbt_decrement(tcur, level, &i))) {
-			XFS_BMBT_TRACE_CURSOR(cur, ERROR);
-			goto error0;
-		}
-		i = xfs_btree_firstrec(tcur, level);
-		XFS_WANT_CORRUPTED_GOTO(i == 1, error0);
-		lbp = tcur->bc_bufs[level];
-		left = XFS_BUF_TO_BMBT_BLOCK(lbp);
-#ifdef DEBUG
-		if ((error = xfs_btree_check_lblock(cur, left, level, lbp))) {
-			XFS_BMBT_TRACE_CURSOR(cur, ERROR);
-			goto error0;
-		}
-#endif
-		bno = be64_to_cpu(left->bb_rightsib);
-		if (be16_to_cpu(left->bb_numrecs) - 1 >=
-		    XFS_BMAP_BLOCK_IMINRECS(level, cur)) {
-			if ((error = xfs_bmbt_rshift(tcur, level, &i))) {
-				XFS_BMBT_TRACE_CURSOR(cur, ERROR);
-				goto error0;
-			}
-			if (i) {
-				ASSERT(be16_to_cpu(block->bb_numrecs) >=
-				       XFS_BMAP_BLOCK_IMINRECS(level, tcur));
-				xfs_btree_del_cursor(tcur, XFS_BTREE_NOERROR);
-				tcur = NULL;
-				if (level == 0)
-					cur->bc_ptrs[0]++;
-				XFS_BMBT_TRACE_CURSOR(cur, EXIT);
-				*stat = 1;
-				return 0;
-			}
-		}
-		lrecs = be16_to_cpu(left->bb_numrecs);
-	}
-	xfs_btree_del_cursor(tcur, XFS_BTREE_NOERROR);
-	tcur = NULL;
-	mp = cur->bc_mp;
-	ASSERT(bno != NULLFSBLOCK);
-	if (lbno != NULLFSBLOCK &&
-	    lrecs + be16_to_cpu(block->bb_numrecs) <= XFS_BMAP_BLOCK_IMAXRECS(level, cur)) {
-		rbno = bno;
-		right = block;
-		rbp = bp;
-		if ((error = xfs_btree_read_bufl(mp, cur->bc_tp, lbno, 0, &lbp,
-				XFS_BMAP_BTREE_REF))) {
-			XFS_BMBT_TRACE_CURSOR(cur, ERROR);
-			goto error0;
-		}
-		left = XFS_BUF_TO_BMBT_BLOCK(lbp);
-		if ((error = xfs_btree_check_lblock(cur, left, level, lbp))) {
-			XFS_BMBT_TRACE_CURSOR(cur, ERROR);
-			goto error0;
-		}
-	} else if (rbno != NULLFSBLOCK &&
-		   rrecs + be16_to_cpu(block->bb_numrecs) <=
-		   XFS_BMAP_BLOCK_IMAXRECS(level, cur)) {
-		lbno = bno;
-		left = block;
-		lbp = bp;
-		if ((error = xfs_btree_read_bufl(mp, cur->bc_tp, rbno, 0, &rbp,
-				XFS_BMAP_BTREE_REF))) {
-			XFS_BMBT_TRACE_CURSOR(cur, ERROR);
-			goto error0;
-		}
-		right = XFS_BUF_TO_BMBT_BLOCK(rbp);
-		if ((error = xfs_btree_check_lblock(cur, right, level, rbp))) {
-			XFS_BMBT_TRACE_CURSOR(cur, ERROR);
-			goto error0;
-		}
-		lrecs = be16_to_cpu(left->bb_numrecs);
-	} else {
-		if (level > 0 && (error = xfs_bmbt_decrement(cur, level, &i))) {
-			XFS_BMBT_TRACE_CURSOR(cur, ERROR);
-			goto error0;
-		}
-		XFS_BMBT_TRACE_CURSOR(cur, EXIT);
-		*stat = 1;
-		return 0;
-	}
-	numlrecs = be16_to_cpu(left->bb_numrecs);
-	numrrecs = be16_to_cpu(right->bb_numrecs);
-	if (level > 0) {
-		lkp = XFS_BMAP_KEY_IADDR(left, numlrecs + 1, cur);
-		lpp = XFS_BMAP_PTR_IADDR(left, numlrecs + 1, cur);
-		rkp = XFS_BMAP_KEY_IADDR(right, 1, cur);
-		rpp = XFS_BMAP_PTR_IADDR(right, 1, cur);
-#ifdef DEBUG
-		for (i = 0; i < numrrecs; i++) {
-			if ((error = xfs_btree_check_lptr_disk(cur, rpp[i], level))) {
-				XFS_BMBT_TRACE_CURSOR(cur, ERROR);
-				goto error0;
-			}
-		}
-#endif
-		memcpy(lkp, rkp, numrrecs * sizeof(*lkp));
-		memcpy(lpp, rpp, numrrecs * sizeof(*lpp));
-		xfs_bmbt_log_keys(cur, lbp, numlrecs + 1, numlrecs + numrrecs);
-		xfs_bmbt_log_ptrs(cur, lbp, numlrecs + 1, numlrecs + numrrecs);
-	} else {
-		lrp = XFS_BMAP_REC_IADDR(left, numlrecs + 1, cur);
-		rrp = XFS_BMAP_REC_IADDR(right, 1, cur);
-		memcpy(lrp, rrp, numrrecs * sizeof(*lrp));
-		xfs_bmbt_log_recs(cur, lbp, numlrecs + 1, numlrecs + numrrecs);
-	}
-	be16_add_cpu(&left->bb_numrecs, numrrecs);
-	left->bb_rightsib = right->bb_rightsib;
-	xfs_bmbt_log_block(cur, lbp, XFS_BB_RIGHTSIB | XFS_BB_NUMRECS);
-	if (be64_to_cpu(left->bb_rightsib) != NULLDFSBNO) {
-		if ((error = xfs_btree_read_bufl(mp, cur->bc_tp,
-				be64_to_cpu(left->bb_rightsib),
-				0, &rrbp, XFS_BMAP_BTREE_REF))) {
-			XFS_BMBT_TRACE_CURSOR(cur, ERROR);
-			goto error0;
-		}
-		rrblock = XFS_BUF_TO_BMBT_BLOCK(rrbp);
-		if ((error = xfs_btree_check_lblock(cur, rrblock, level, rrbp))) {
-			XFS_BMBT_TRACE_CURSOR(cur, ERROR);
-			goto error0;
-		}
-		rrblock->bb_leftsib = cpu_to_be64(lbno);
-		xfs_bmbt_log_block(cur, rrbp, XFS_BB_LEFTSIB);
-	}
-	xfs_bmap_add_free(XFS_DADDR_TO_FSB(mp, XFS_BUF_ADDR(rbp)), 1,
-		cur->bc_private.b.flist, mp);
-	cur->bc_private.b.ip->i_d.di_nblocks--;
-	xfs_trans_log_inode(cur->bc_tp, cur->bc_private.b.ip, XFS_ILOG_CORE);
-	XFS_TRANS_MOD_DQUOT_BYINO(mp, cur->bc_tp, cur->bc_private.b.ip,
-			XFS_TRANS_DQ_BCOUNT, -1L);
-	xfs_trans_binval(cur->bc_tp, rbp);
-	if (bp != lbp) {
-		cur->bc_bufs[level] = lbp;
-		cur->bc_ptrs[level] += lrecs;
-		cur->bc_ra[level] = 0;
-	} else if ((error = xfs_bmbt_increment(cur, level + 1, &i))) {
-		XFS_BMBT_TRACE_CURSOR(cur, ERROR);
-		goto error0;
-	}
-	if (level > 0)
-		cur->bc_ptrs[level]--;
-	XFS_BMBT_TRACE_CURSOR(cur, EXIT);
-	*stat = 2;
-	return 0;
-
-error0:
-	if (tcur)
-		xfs_btree_del_cursor(tcur, XFS_BTREE_ERROR);
-	return error;
-}
-
-/*
- * Insert one record/level.  Return information to the caller
- * allowing the next level up to proceed if necessary.
- */
-STATIC int					/* error */
-xfs_bmbt_insrec(
-	xfs_btree_cur_t		*cur,
-	int			level,
-	xfs_fsblock_t		*bnop,
-	xfs_bmbt_rec_t		*recp,
-	xfs_btree_cur_t		**curp,
-	int			*stat)		/* no-go/done/continue */
-{
-	xfs_bmbt_block_t	*block;		/* bmap btree block */
-	xfs_buf_t		*bp;		/* buffer for block */
-	int			error;		/* error return value */
-	int			i;		/* loop index */
-	xfs_bmbt_key_t		key;		/* bmap btree key */
-	xfs_bmbt_key_t		*kp=NULL;	/* pointer to bmap btree key */
-	int			logflags;	/* inode logging flags */
-	xfs_fsblock_t		nbno;		/* new block number */
-	struct xfs_btree_cur	*ncur;		/* new btree cursor */
-	__uint64_t		startoff;	/* new btree key value */
-	xfs_bmbt_rec_t		nrec;		/* new record count */
-	int			optr;		/* old key/record index */
-	xfs_bmbt_ptr_t		*pp;		/* pointer to bmap block addr */
-	int			ptr;		/* key/record index */
-	xfs_bmbt_rec_t		*rp=NULL;	/* pointer to bmap btree rec */
-	int			numrecs;
-
-	ASSERT(level < cur->bc_nlevels);
-	XFS_BMBT_TRACE_CURSOR(cur, ENTRY);
-	XFS_BMBT_TRACE_ARGIFR(cur, level, *bnop, recp);
-	ncur = NULL;
-	key.br_startoff = cpu_to_be64(xfs_bmbt_disk_get_startoff(recp));
-	optr = ptr = cur->bc_ptrs[level];
-	if (ptr == 0) {
-		XFS_BMBT_TRACE_CURSOR(cur, EXIT);
-		*stat = 0;
-		return 0;
-	}
-	XFS_STATS_INC(xs_bmbt_insrec);
-	block = xfs_bmbt_get_block(cur, level, &bp);
-	numrecs = be16_to_cpu(block->bb_numrecs);
-#ifdef DEBUG
-	if ((error = xfs_btree_check_lblock(cur, block, level, bp))) {
-		XFS_BMBT_TRACE_CURSOR(cur, ERROR);
-		return error;
-	}
-	if (ptr <= numrecs) {
-		if (level == 0) {
-			rp = XFS_BMAP_REC_IADDR(block, ptr, cur);
-			xfs_btree_check_rec(XFS_BTNUM_BMAP, recp, rp);
-		} else {
-			kp = XFS_BMAP_KEY_IADDR(block, ptr, cur);
-			xfs_btree_check_key(XFS_BTNUM_BMAP, &key, kp);
-		}
-	}
-#endif
-	nbno = NULLFSBLOCK;
-	if (numrecs == XFS_BMAP_BLOCK_IMAXRECS(level, cur)) {
-		if (numrecs < XFS_BMAP_BLOCK_DMAXRECS(level, cur)) {
-			/*
-			 * A root block, that can be made bigger.
-			 */
-			xfs_iroot_realloc(cur->bc_private.b.ip, 1,
-				cur->bc_private.b.whichfork);
-			block = xfs_bmbt_get_block(cur, level, &bp);
-		} else if (level == cur->bc_nlevels - 1) {
-			if ((error = xfs_bmbt_newroot(cur, &logflags, stat)) ||
-			    *stat == 0) {
-				XFS_BMBT_TRACE_CURSOR(cur, ERROR);
-				return error;
-			}
-			xfs_trans_log_inode(cur->bc_tp, cur->bc_private.b.ip,
-				logflags);
-			block = xfs_bmbt_get_block(cur, level, &bp);
-		} else {
-			if ((error = xfs_bmbt_rshift(cur, level, &i))) {
-				XFS_BMBT_TRACE_CURSOR(cur, ERROR);
-				return error;
-			}
-			if (i) {
-				/* nothing */
-			} else {
-				if ((error = xfs_bmbt_lshift(cur, level, &i))) {
-					XFS_BMBT_TRACE_CURSOR(cur, ERROR);
-					return error;
-				}
-				if (i) {
-					optr = ptr = cur->bc_ptrs[level];
-				} else {
-					if ((error = xfs_bmbt_split(cur, level,
-							&nbno, &startoff, &ncur,
-							&i))) {
-						XFS_BMBT_TRACE_CURSOR(cur,
-							ERROR);
-						return error;
-					}
-					if (i) {
-						block = xfs_bmbt_get_block(
-							    cur, level, &bp);
-#ifdef DEBUG
-						if ((error =
-						    xfs_btree_check_lblock(cur,
-							    block, level, bp))) {
-							XFS_BMBT_TRACE_CURSOR(
-								cur, ERROR);
-							return error;
-						}
-#endif
-						ptr = cur->bc_ptrs[level];
-						xfs_bmbt_disk_set_allf(&nrec,
-							startoff, 0, 0,
-							XFS_EXT_NORM);
-					} else {
-						XFS_BMBT_TRACE_CURSOR(cur,
-							EXIT);
-						*stat = 0;
-						return 0;
-					}
-				}
-			}
-		}
-	}
-	numrecs = be16_to_cpu(block->bb_numrecs);
-	if (level > 0) {
-		kp = XFS_BMAP_KEY_IADDR(block, 1, cur);
-		pp = XFS_BMAP_PTR_IADDR(block, 1, cur);
-#ifdef DEBUG
-		for (i = numrecs; i >= ptr; i--) {
-			if ((error = xfs_btree_check_lptr_disk(cur, pp[i - 1],
-					level))) {
-				XFS_BMBT_TRACE_CURSOR(cur, ERROR);
-				return error;
-			}
-		}
-#endif
-		memmove(&kp[ptr], &kp[ptr - 1],
-			(numrecs - ptr + 1) * sizeof(*kp));
-		memmove(&pp[ptr], &pp[ptr - 1],
-			(numrecs - ptr + 1) * sizeof(*pp));
-#ifdef DEBUG
-		if ((error = xfs_btree_check_lptr(cur, *bnop, level))) {
-			XFS_BMBT_TRACE_CURSOR(cur, ERROR);
-			return error;
-		}
-#endif
-		kp[ptr - 1] = key;
-		pp[ptr - 1] = cpu_to_be64(*bnop);
-		numrecs++;
-		block->bb_numrecs = cpu_to_be16(numrecs);
-		xfs_bmbt_log_keys(cur, bp, ptr, numrecs);
-		xfs_bmbt_log_ptrs(cur, bp, ptr, numrecs);
-	} else {
-		rp = XFS_BMAP_REC_IADDR(block, 1, cur);
-		memmove(&rp[ptr], &rp[ptr - 1],
-			(numrecs - ptr + 1) * sizeof(*rp));
-		rp[ptr - 1] = *recp;
-		numrecs++;
-		block->bb_numrecs = cpu_to_be16(numrecs);
-		xfs_bmbt_log_recs(cur, bp, ptr, numrecs);
-	}
-	xfs_bmbt_log_block(cur, bp, XFS_BB_NUMRECS);
-#ifdef DEBUG
-	if (ptr < numrecs) {
-		if (level == 0)
-			xfs_btree_check_rec(XFS_BTNUM_BMAP, rp + ptr - 1,
-				rp + ptr);
-		else
-			xfs_btree_check_key(XFS_BTNUM_BMAP, kp + ptr - 1,
-				kp + ptr);
-	}
-#endif
-	if (optr == 1 && (error = xfs_bmbt_updkey(cur, &key, level + 1))) {
-		XFS_BMBT_TRACE_CURSOR(cur, ERROR);
-		return error;
-	}
-	*bnop = nbno;
-	if (nbno != NULLFSBLOCK) {
-		*recp = nrec;
-		*curp = ncur;
-	}
-	XFS_BMBT_TRACE_CURSOR(cur, EXIT);
-	*stat = 1;
-	return 0;
-}
-
-STATIC int
-xfs_bmbt_killroot(
-	xfs_btree_cur_t		*cur)
-{
-	xfs_bmbt_block_t	*block;
-	xfs_bmbt_block_t	*cblock;
-	xfs_buf_t		*cbp;
-	xfs_bmbt_key_t		*ckp;
-	xfs_bmbt_ptr_t		*cpp;
-#ifdef DEBUG
-	int			error;
-#endif
-	int			i;
-	xfs_bmbt_key_t		*kp;
-	xfs_inode_t		*ip;
-	xfs_ifork_t		*ifp;
-	int			level;
-	xfs_bmbt_ptr_t		*pp;
-
-	XFS_BMBT_TRACE_CURSOR(cur, ENTRY);
-	level = cur->bc_nlevels - 1;
-	ASSERT(level >= 1);
-	/*
-	 * Don't deal with the root block needs to be a leaf case.
-	 * We're just going to turn the thing back into extents anyway.
-	 */
-	if (level == 1) {
-		XFS_BMBT_TRACE_CURSOR(cur, EXIT);
-		return 0;
-	}
-	block = xfs_bmbt_get_block(cur, level, &cbp);
-	/*
-	 * Give up if the root has multiple children.
-	 */
-	if (be16_to_cpu(block->bb_numrecs) != 1) {
-		XFS_BMBT_TRACE_CURSOR(cur, EXIT);
-		return 0;
-	}
-	/*
-	 * Only do this if the next level will fit.
-	 * Then the data must be copied up to the inode,
-	 * instead of freeing the root you free the next level.
-	 */
-	cbp = cur->bc_bufs[level - 1];
-	cblock = XFS_BUF_TO_BMBT_BLOCK(cbp);
-	if (be16_to_cpu(cblock->bb_numrecs) > XFS_BMAP_BLOCK_DMAXRECS(level, cur)) {
-		XFS_BMBT_TRACE_CURSOR(cur, EXIT);
-		return 0;
-	}
-	ASSERT(be64_to_cpu(cblock->bb_leftsib) == NULLDFSBNO);
-	ASSERT(be64_to_cpu(cblock->bb_rightsib) == NULLDFSBNO);
-	ip = cur->bc_private.b.ip;
-	ifp = XFS_IFORK_PTR(ip, cur->bc_private.b.whichfork);
-	ASSERT(XFS_BMAP_BLOCK_IMAXRECS(level, cur) ==
-	       XFS_BMAP_BROOT_MAXRECS(ifp->if_broot_bytes));
-	i = (int)(be16_to_cpu(cblock->bb_numrecs) - XFS_BMAP_BLOCK_IMAXRECS(level, cur));
-	if (i) {
-		xfs_iroot_realloc(ip, i, cur->bc_private.b.whichfork);
-		block = ifp->if_broot;
-	}
-	be16_add_cpu(&block->bb_numrecs, i);
-	ASSERT(block->bb_numrecs == cblock->bb_numrecs);
-	kp = XFS_BMAP_KEY_IADDR(block, 1, cur);
-	ckp = XFS_BMAP_KEY_IADDR(cblock, 1, cur);
-	memcpy(kp, ckp, be16_to_cpu(block->bb_numrecs) * sizeof(*kp));
-	pp = XFS_BMAP_PTR_IADDR(block, 1, cur);
-	cpp = XFS_BMAP_PTR_IADDR(cblock, 1, cur);
-#ifdef DEBUG
-	for (i = 0; i < be16_to_cpu(cblock->bb_numrecs); i++) {
-		if ((error = xfs_btree_check_lptr_disk(cur, cpp[i], level - 1))) {
-			XFS_BMBT_TRACE_CURSOR(cur, ERROR);
-			return error;
-		}
-	}
-#endif
-	memcpy(pp, cpp, be16_to_cpu(block->bb_numrecs) * sizeof(*pp));
-	xfs_bmap_add_free(XFS_DADDR_TO_FSB(cur->bc_mp, XFS_BUF_ADDR(cbp)), 1,
-			cur->bc_private.b.flist, cur->bc_mp);
-	ip->i_d.di_nblocks--;
-	XFS_TRANS_MOD_DQUOT_BYINO(cur->bc_mp, cur->bc_tp, ip,
-			XFS_TRANS_DQ_BCOUNT, -1L);
-	xfs_trans_binval(cur->bc_tp, cbp);
-	cur->bc_bufs[level - 1] = NULL;
-	be16_add_cpu(&block->bb_level, -1);
-	xfs_trans_log_inode(cur->bc_tp, ip,
-		XFS_ILOG_CORE | XFS_ILOG_FBROOT(cur->bc_private.b.whichfork));
-	cur->bc_nlevels--;
-	XFS_BMBT_TRACE_CURSOR(cur, EXIT);
-	return 0;
-}
-
-/*
- * Log key values from the btree block.
- */
-STATIC void
-xfs_bmbt_log_keys(
-	xfs_btree_cur_t	*cur,
-	xfs_buf_t	*bp,
-	int		kfirst,
-	int		klast)
-{
-	xfs_trans_t	*tp;
-
-	XFS_BMBT_TRACE_CURSOR(cur, ENTRY);
-	XFS_BMBT_TRACE_ARGBII(cur, bp, kfirst, klast);
-	tp = cur->bc_tp;
-	if (bp) {
-		xfs_bmbt_block_t	*block;
-		int			first;
-		xfs_bmbt_key_t		*kp;
-		int			last;
-
-		block = XFS_BUF_TO_BMBT_BLOCK(bp);
-		kp = XFS_BMAP_KEY_DADDR(block, 1, cur);
-		first = (int)((xfs_caddr_t)&kp[kfirst - 1] - (xfs_caddr_t)block);
-		last = (int)(((xfs_caddr_t)&kp[klast] - 1) - (xfs_caddr_t)block);
-		xfs_trans_log_buf(tp, bp, first, last);
-	} else {
-		xfs_inode_t		 *ip;
-
-		ip = cur->bc_private.b.ip;
-		xfs_trans_log_inode(tp, ip,
-			XFS_ILOG_FBROOT(cur->bc_private.b.whichfork));
-	}
-	XFS_BMBT_TRACE_CURSOR(cur, EXIT);
-}
-
-/*
- * Log pointer values from the btree block.
- */
-STATIC void
-xfs_bmbt_log_ptrs(
-	xfs_btree_cur_t	*cur,
-	xfs_buf_t	*bp,
-	int		pfirst,
-	int		plast)
-{
-	xfs_trans_t	*tp;
-
-	XFS_BMBT_TRACE_CURSOR(cur, ENTRY);
-	XFS_BMBT_TRACE_ARGBII(cur, bp, pfirst, plast);
-	tp = cur->bc_tp;
-	if (bp) {
-		xfs_bmbt_block_t	*block;
-		int			first;
-		int			last;
-		xfs_bmbt_ptr_t		*pp;
-
-		block = XFS_BUF_TO_BMBT_BLOCK(bp);
-		pp = XFS_BMAP_PTR_DADDR(block, 1, cur);
-		first = (int)((xfs_caddr_t)&pp[pfirst - 1] - (xfs_caddr_t)block);
-		last = (int)(((xfs_caddr_t)&pp[plast] - 1) - (xfs_caddr_t)block);
-		xfs_trans_log_buf(tp, bp, first, last);
-	} else {
-		xfs_inode_t		*ip;
-
-		ip = cur->bc_private.b.ip;
-		xfs_trans_log_inode(tp, ip,
-			XFS_ILOG_FBROOT(cur->bc_private.b.whichfork));
-	}
-	XFS_BMBT_TRACE_CURSOR(cur, EXIT);
-}
-
-/*
- * Lookup the record.  The cursor is made to point to it, based on dir.
- */
-STATIC int				/* error */
-xfs_bmbt_lookup(
-	xfs_btree_cur_t		*cur,
-	xfs_lookup_t		dir,
-	int			*stat)		/* success/failure */
-{
-	xfs_bmbt_block_t	*block=NULL;
-	xfs_buf_t		*bp;
-	xfs_daddr_t		d;
-	xfs_sfiloff_t		diff;
-	int			error;		/* error return value */
-	xfs_fsblock_t		fsbno=0;
-	int			high;
-	int			i;
-	int			keyno=0;
-	xfs_bmbt_key_t		*kkbase=NULL;
-	xfs_bmbt_key_t		*kkp;
-	xfs_bmbt_rec_t		*krbase=NULL;
-	xfs_bmbt_rec_t		*krp;
-	int			level;
-	int			low;
-	xfs_mount_t		*mp;
-	xfs_bmbt_ptr_t		*pp;
-	xfs_bmbt_irec_t		*rp;
-	xfs_fileoff_t		startoff;
-	xfs_trans_t		*tp;
-
-	XFS_STATS_INC(xs_bmbt_lookup);
-	XFS_BMBT_TRACE_CURSOR(cur, ENTRY);
-	XFS_BMBT_TRACE_ARGI(cur, (int)dir);
-	tp = cur->bc_tp;
-	mp = cur->bc_mp;
-	rp = &cur->bc_rec.b;
-	for (level = cur->bc_nlevels - 1, diff = 1; level >= 0; level--) {
-		if (level < cur->bc_nlevels - 1) {
-			d = XFS_FSB_TO_DADDR(mp, fsbno);
-			bp = cur->bc_bufs[level];
-			if (bp && XFS_BUF_ADDR(bp) != d)
-				bp = NULL;
-			if (!bp) {
-				if ((error = xfs_btree_read_bufl(mp, tp, fsbno,
-						0, &bp, XFS_BMAP_BTREE_REF))) {
-					XFS_BMBT_TRACE_CURSOR(cur, ERROR);
-					return error;
-				}
-				xfs_btree_setbuf(cur, level, bp);
-				block = XFS_BUF_TO_BMBT_BLOCK(bp);
-				if ((error = xfs_btree_check_lblock(cur, block,
-						level, bp))) {
-					XFS_BMBT_TRACE_CURSOR(cur, ERROR);
-					return error;
-				}
-			} else
-				block = XFS_BUF_TO_BMBT_BLOCK(bp);
-		} else
-			block = xfs_bmbt_get_block(cur, level, &bp);
-		if (diff == 0)
-			keyno = 1;
-		else {
-			if (level > 0)
-				kkbase = XFS_BMAP_KEY_IADDR(block, 1, cur);
-			else
-				krbase = XFS_BMAP_REC_IADDR(block, 1, cur);
-			low = 1;
-			if (!(high = be16_to_cpu(block->bb_numrecs))) {
-				ASSERT(level == 0);
-				cur->bc_ptrs[0] = dir != XFS_LOOKUP_LE;
-				XFS_BMBT_TRACE_CURSOR(cur, EXIT);
-				*stat = 0;
-				return 0;
-			}
-			while (low <= high) {
-				XFS_STATS_INC(xs_bmbt_compare);
-				keyno = (low + high) >> 1;
-				if (level > 0) {
-					kkp = kkbase + keyno - 1;
-					startoff = be64_to_cpu(kkp->br_startoff);
-				} else {
-					krp = krbase + keyno - 1;
-					startoff = xfs_bmbt_disk_get_startoff(krp);
-				}
-				diff = (xfs_sfiloff_t)
-						(startoff - rp->br_startoff);
-				if (diff < 0)
-					low = keyno + 1;
-				else if (diff > 0)
-					high = keyno - 1;
-				else
-					break;
-			}
-		}
-		if (level > 0) {
-			if (diff > 0 && --keyno < 1)
-				keyno = 1;
-			pp = XFS_BMAP_PTR_IADDR(block, keyno, cur);
-			fsbno = be64_to_cpu(*pp);
-#ifdef DEBUG
-			if ((error = xfs_btree_check_lptr(cur, fsbno, level))) {
-				XFS_BMBT_TRACE_CURSOR(cur, ERROR);
-				return error;
-			}
-#endif
-			cur->bc_ptrs[level] = keyno;
-		}
-	}
-	if (dir != XFS_LOOKUP_LE && diff < 0) {
-		keyno++;
-		/*
-		 * If ge search and we went off the end of the block, but it's
-		 * not the last block, we're in the wrong block.
-		 */
-		if (dir == XFS_LOOKUP_GE && keyno > be16_to_cpu(block->bb_numrecs) &&
-		    be64_to_cpu(block->bb_rightsib) != NULLDFSBNO) {
-			cur->bc_ptrs[0] = keyno;
-			if ((error = xfs_bmbt_increment(cur, 0, &i))) {
-				XFS_BMBT_TRACE_CURSOR(cur, ERROR);
-				return error;
-			}
-			XFS_WANT_CORRUPTED_RETURN(i == 1);
-			XFS_BMBT_TRACE_CURSOR(cur, EXIT);
-			*stat = 1;
-			return 0;
-		}
-	}
-	else if (dir == XFS_LOOKUP_LE && diff > 0)
-		keyno--;
-	cur->bc_ptrs[0] = keyno;
-	if (keyno == 0 || keyno > be16_to_cpu(block->bb_numrecs)) {
-		XFS_BMBT_TRACE_CURSOR(cur, EXIT);
-		*stat = 0;
-	} else {
-		XFS_BMBT_TRACE_CURSOR(cur, EXIT);
-		*stat = ((dir != XFS_LOOKUP_EQ) || (diff == 0));
-	}
-	return 0;
-}
-
-/*
- * Move 1 record left from cur/level if possible.
- * Update cur to reflect the new path.
- */
-STATIC int					/* error */
-xfs_bmbt_lshift(
-	xfs_btree_cur_t		*cur,
-	int			level,
-	int			*stat)		/* success/failure */
-{
-	int			error;		/* error return value */
-#ifdef DEBUG
-	int			i;		/* loop counter */
-#endif
-	xfs_bmbt_key_t		key;		/* bmap btree key */
-	xfs_buf_t		*lbp;		/* left buffer pointer */
-	xfs_bmbt_block_t	*left;		/* left btree block */
-	xfs_bmbt_key_t		*lkp=NULL;	/* left btree key */
-	xfs_bmbt_ptr_t		*lpp;		/* left address pointer */
-	int			lrecs;		/* left record count */
-	xfs_bmbt_rec_t		*lrp=NULL;	/* left record pointer */
-	xfs_mount_t		*mp;		/* file system mount point */
-	xfs_buf_t		*rbp;		/* right buffer pointer */
-	xfs_bmbt_block_t	*right;		/* right btree block */
-	xfs_bmbt_key_t		*rkp=NULL;	/* right btree key */
-	xfs_bmbt_ptr_t		*rpp=NULL;	/* right address pointer */
-	xfs_bmbt_rec_t		*rrp=NULL;	/* right record pointer */
-	int			rrecs;		/* right record count */
-
-	XFS_BMBT_TRACE_CURSOR(cur, ENTRY);
-	XFS_BMBT_TRACE_ARGI(cur, level);
-	if (level == cur->bc_nlevels - 1) {
-		XFS_BMBT_TRACE_CURSOR(cur, EXIT);
-		*stat = 0;
-		return 0;
-	}
-	rbp = cur->bc_bufs[level];
-	right = XFS_BUF_TO_BMBT_BLOCK(rbp);
-#ifdef DEBUG
-	if ((error = xfs_btree_check_lblock(cur, right, level, rbp))) {
-		XFS_BMBT_TRACE_CURSOR(cur, ERROR);
-		return error;
-	}
-#endif
-	if (be64_to_cpu(right->bb_leftsib) == NULLDFSBNO) {
-		XFS_BMBT_TRACE_CURSOR(cur, EXIT);
-		*stat = 0;
-		return 0;
-	}
-	if (cur->bc_ptrs[level] <= 1) {
-		XFS_BMBT_TRACE_CURSOR(cur, EXIT);
-		*stat = 0;
-		return 0;
-	}
-	mp = cur->bc_mp;
-	if ((error = xfs_btree_read_bufl(mp, cur->bc_tp, be64_to_cpu(right->bb_leftsib), 0,
-			&lbp, XFS_BMAP_BTREE_REF))) {
-		XFS_BMBT_TRACE_CURSOR(cur, ERROR);
-		return error;
-	}
-	left = XFS_BUF_TO_BMBT_BLOCK(lbp);
-	if ((error = xfs_btree_check_lblock(cur, left, level, lbp))) {
-		XFS_BMBT_TRACE_CURSOR(cur, ERROR);
-		return error;
-	}
-	if (be16_to_cpu(left->bb_numrecs) == XFS_BMAP_BLOCK_IMAXRECS(level, cur)) {
-		XFS_BMBT_TRACE_CURSOR(cur, EXIT);
-		*stat = 0;
-		return 0;
-	}
-	lrecs = be16_to_cpu(left->bb_numrecs) + 1;
-	if (level > 0) {
-		lkp = XFS_BMAP_KEY_IADDR(left, lrecs, cur);
-		rkp = XFS_BMAP_KEY_IADDR(right, 1, cur);
-		*lkp = *rkp;
-		xfs_bmbt_log_keys(cur, lbp, lrecs, lrecs);
-		lpp = XFS_BMAP_PTR_IADDR(left, lrecs, cur);
-		rpp = XFS_BMAP_PTR_IADDR(right, 1, cur);
-#ifdef DEBUG
-		if ((error = xfs_btree_check_lptr_disk(cur, *rpp, level))) {
-			XFS_BMBT_TRACE_CURSOR(cur, ERROR);
-			return error;
-		}
-#endif
-		*lpp = *rpp;
-		xfs_bmbt_log_ptrs(cur, lbp, lrecs, lrecs);
-	} else {
-		lrp = XFS_BMAP_REC_IADDR(left, lrecs, cur);
-		rrp = XFS_BMAP_REC_IADDR(right, 1, cur);
-		*lrp = *rrp;
-		xfs_bmbt_log_recs(cur, lbp, lrecs, lrecs);
-	}
-	left->bb_numrecs = cpu_to_be16(lrecs);
-	xfs_bmbt_log_block(cur, lbp, XFS_BB_NUMRECS);
-#ifdef DEBUG
-	if (level > 0)
-		xfs_btree_check_key(XFS_BTNUM_BMAP, lkp - 1, lkp);
-	else
-		xfs_btree_check_rec(XFS_BTNUM_BMAP, lrp - 1, lrp);
-#endif
-	rrecs = be16_to_cpu(right->bb_numrecs) - 1;
-	right->bb_numrecs = cpu_to_be16(rrecs);
-	xfs_bmbt_log_block(cur, rbp, XFS_BB_NUMRECS);
-	if (level > 0) {
-#ifdef DEBUG
-		for (i = 0; i < rrecs; i++) {
-			if ((error = xfs_btree_check_lptr_disk(cur, rpp[i + 1],
-					level))) {
-				XFS_BMBT_TRACE_CURSOR(cur, ERROR);
-				return error;
-			}
-		}
-#endif
-		memmove(rkp, rkp + 1, rrecs * sizeof(*rkp));
-		memmove(rpp, rpp + 1, rrecs * sizeof(*rpp));
-		xfs_bmbt_log_keys(cur, rbp, 1, rrecs);
-		xfs_bmbt_log_ptrs(cur, rbp, 1, rrecs);
-	} else {
-		memmove(rrp, rrp + 1, rrecs * sizeof(*rrp));
-		xfs_bmbt_log_recs(cur, rbp, 1, rrecs);
-		key.br_startoff = cpu_to_be64(xfs_bmbt_disk_get_startoff(rrp));
-		rkp = &key;
-	}
-	if ((error = xfs_bmbt_updkey(cur, rkp, level + 1))) {
-		XFS_BMBT_TRACE_CURSOR(cur, ERROR);
-		return error;
-	}
-	cur->bc_ptrs[level]--;
-	XFS_BMBT_TRACE_CURSOR(cur, EXIT);
-	*stat = 1;
-	return 0;
-}
-
-/*
- * Move 1 record right from cur/level if possible.
- * Update cur to reflect the new path.
- */
-STATIC int					/* error */
-xfs_bmbt_rshift(
-	xfs_btree_cur_t		*cur,
-	int			level,
-	int			*stat)		/* success/failure */
-{
-	int			error;		/* error return value */
-	int			i;		/* loop counter */
-	xfs_bmbt_key_t		key;		/* bmap btree key */
-	xfs_buf_t		*lbp;		/* left buffer pointer */
-	xfs_bmbt_block_t	*left;		/* left btree block */
-	xfs_bmbt_key_t		*lkp;		/* left btree key */
-	xfs_bmbt_ptr_t		*lpp;		/* left address pointer */
-	xfs_bmbt_rec_t		*lrp;		/* left record pointer */
-	xfs_mount_t		*mp;		/* file system mount point */
-	xfs_buf_t		*rbp;		/* right buffer pointer */
-	xfs_bmbt_block_t	*right;		/* right btree block */
-	xfs_bmbt_key_t		*rkp;		/* right btree key */
-	xfs_bmbt_ptr_t		*rpp;		/* right address pointer */
-	xfs_bmbt_rec_t		*rrp=NULL;	/* right record pointer */
-	struct xfs_btree_cur	*tcur;		/* temporary btree cursor */
-
-	XFS_BMBT_TRACE_CURSOR(cur, ENTRY);
-	XFS_BMBT_TRACE_ARGI(cur, level);
-	if (level == cur->bc_nlevels - 1) {
-		XFS_BMBT_TRACE_CURSOR(cur, EXIT);
-		*stat = 0;
-		return 0;
-	}
-	lbp = cur->bc_bufs[level];
-	left = XFS_BUF_TO_BMBT_BLOCK(lbp);
-#ifdef DEBUG
-	if ((error = xfs_btree_check_lblock(cur, left, level, lbp))) {
-		XFS_BMBT_TRACE_CURSOR(cur, ERROR);
-		return error;
-	}
-#endif
-	if (be64_to_cpu(left->bb_rightsib) == NULLDFSBNO) {
-		XFS_BMBT_TRACE_CURSOR(cur, EXIT);
-		*stat = 0;
-		return 0;
-	}
-	if (cur->bc_ptrs[level] >= be16_to_cpu(left->bb_numrecs)) {
-		XFS_BMBT_TRACE_CURSOR(cur, EXIT);
-		*stat = 0;
-		return 0;
-	}
-	mp = cur->bc_mp;
-	if ((error = xfs_btree_read_bufl(mp, cur->bc_tp, be64_to_cpu(left->bb_rightsib), 0,
-			&rbp, XFS_BMAP_BTREE_REF))) {
-		XFS_BMBT_TRACE_CURSOR(cur, ERROR);
-		return error;
-	}
-	right = XFS_BUF_TO_BMBT_BLOCK(rbp);
-	if ((error = xfs_btree_check_lblock(cur, right, level, rbp))) {
-		XFS_BMBT_TRACE_CURSOR(cur, ERROR);
-		return error;
-	}
-	if (be16_to_cpu(right->bb_numrecs) == XFS_BMAP_BLOCK_IMAXRECS(level, cur)) {
-		XFS_BMBT_TRACE_CURSOR(cur, EXIT);
-		*stat = 0;
-		return 0;
-	}
-	if (level > 0) {
-		lkp = XFS_BMAP_KEY_IADDR(left, be16_to_cpu(left->bb_numrecs), cur);
-		lpp = XFS_BMAP_PTR_IADDR(left, be16_to_cpu(left->bb_numrecs), cur);
-		rkp = XFS_BMAP_KEY_IADDR(right, 1, cur);
-		rpp = XFS_BMAP_PTR_IADDR(right, 1, cur);
-#ifdef DEBUG
-		for (i = be16_to_cpu(right->bb_numrecs) - 1; i >= 0; i--) {
-			if ((error = xfs_btree_check_lptr_disk(cur, rpp[i], level))) {
-				XFS_BMBT_TRACE_CURSOR(cur, ERROR);
-				return error;
-			}
-		}
-#endif
-		memmove(rkp + 1, rkp, be16_to_cpu(right->bb_numrecs) * sizeof(*rkp));
-		memmove(rpp + 1, rpp, be16_to_cpu(right->bb_numrecs) * sizeof(*rpp));
-#ifdef DEBUG
-		if ((error = xfs_btree_check_lptr_disk(cur, *lpp, level))) {
-			XFS_BMBT_TRACE_CURSOR(cur, ERROR);
-			return error;
-		}
-#endif
-		*rkp = *lkp;
-		*rpp = *lpp;
-		xfs_bmbt_log_keys(cur, rbp, 1, be16_to_cpu(right->bb_numrecs) + 1);
-		xfs_bmbt_log_ptrs(cur, rbp, 1, be16_to_cpu(right->bb_numrecs) + 1);
-	} else {
-		lrp = XFS_BMAP_REC_IADDR(left, be16_to_cpu(left->bb_numrecs), cur);
-		rrp = XFS_BMAP_REC_IADDR(right, 1, cur);
-		memmove(rrp + 1, rrp, be16_to_cpu(right->bb_numrecs) * sizeof(*rrp));
-		*rrp = *lrp;
-		xfs_bmbt_log_recs(cur, rbp, 1, be16_to_cpu(right->bb_numrecs) + 1);
-		key.br_startoff = cpu_to_be64(xfs_bmbt_disk_get_startoff(rrp));
-		rkp = &key;
-	}
-	be16_add_cpu(&left->bb_numrecs, -1);
-	xfs_bmbt_log_block(cur, lbp, XFS_BB_NUMRECS);
-	be16_add_cpu(&right->bb_numrecs, 1);
-#ifdef DEBUG
-	if (level > 0)
-		xfs_btree_check_key(XFS_BTNUM_BMAP, rkp, rkp + 1);
-	else
-		xfs_btree_check_rec(XFS_BTNUM_BMAP, rrp, rrp + 1);
-#endif
-	xfs_bmbt_log_block(cur, rbp, XFS_BB_NUMRECS);
-	if ((error = xfs_btree_dup_cursor(cur, &tcur))) {
-		XFS_BMBT_TRACE_CURSOR(cur, ERROR);
-		return error;
-	}
-	i = xfs_btree_lastrec(tcur, level);
-	XFS_WANT_CORRUPTED_GOTO(i == 1, error0);
-	if ((error = xfs_bmbt_increment(tcur, level, &i))) {
-		XFS_BMBT_TRACE_CURSOR(tcur, ERROR);
-		goto error1;
-	}
-	XFS_WANT_CORRUPTED_GOTO(i == 1, error0);
-	if ((error = xfs_bmbt_updkey(tcur, rkp, level + 1))) {
-		XFS_BMBT_TRACE_CURSOR(tcur, ERROR);
-		goto error1;
-	}
-	xfs_btree_del_cursor(tcur, XFS_BTREE_NOERROR);
-	XFS_BMBT_TRACE_CURSOR(cur, EXIT);
-	*stat = 1;
-	return 0;
-error0:
-	XFS_BMBT_TRACE_CURSOR(cur, ERROR);
-error1:
-	xfs_btree_del_cursor(tcur, XFS_BTREE_ERROR);
-	return error;
-}
-
 /*
  * Determine the extent state.
  */
@@ -1453,229 +60,15 @@ xfs_extent_state(
 	return XFS_EXT_NORM;
 }
 
-
-/*
- * Split cur/level block in half.
- * Return new block number and its first record (to be inserted into parent).
- */
-STATIC int					/* error */
-xfs_bmbt_split(
-	xfs_btree_cur_t		*cur,
-	int			level,
-	xfs_fsblock_t		*bnop,
-	__uint64_t		*startoff,
-	xfs_btree_cur_t		**curp,
-	int			*stat)		/* success/failure */
-{
-	xfs_alloc_arg_t		args;		/* block allocation args */
-	int			error;		/* error return value */
-	int			i;		/* loop counter */
-	xfs_fsblock_t		lbno;		/* left sibling block number */
-	xfs_buf_t		*lbp;		/* left buffer pointer */
-	xfs_bmbt_block_t	*left;		/* left btree block */
-	xfs_bmbt_key_t		*lkp;		/* left btree key */
-	xfs_bmbt_ptr_t		*lpp;		/* left address pointer */
-	xfs_bmbt_rec_t		*lrp;		/* left record pointer */
-	xfs_buf_t		*rbp;		/* right buffer pointer */
-	xfs_bmbt_block_t	*right;		/* right btree block */
-	xfs_bmbt_key_t		*rkp;		/* right btree key */
-	xfs_bmbt_ptr_t		*rpp;		/* right address pointer */
-	xfs_bmbt_block_t	*rrblock;	/* right-right btree block */
-	xfs_buf_t		*rrbp;		/* right-right buffer pointer */
-	xfs_bmbt_rec_t		*rrp;		/* right record pointer */
-
-	XFS_BMBT_TRACE_CURSOR(cur, ENTRY);
-	XFS_BMBT_TRACE_ARGIFK(cur, level, *bnop, *startoff);
-	args.tp = cur->bc_tp;
-	args.mp = cur->bc_mp;
-	lbp = cur->bc_bufs[level];
-	lbno = XFS_DADDR_TO_FSB(args.mp, XFS_BUF_ADDR(lbp));
-	left = XFS_BUF_TO_BMBT_BLOCK(lbp);
-	args.fsbno = cur->bc_private.b.firstblock;
-	args.firstblock = args.fsbno;
-	args.minleft = 0;
-	if (args.fsbno == NULLFSBLOCK) {
-		args.fsbno = lbno;
-		args.type = XFS_ALLOCTYPE_START_BNO;
-		/*
-		 * Make sure there is sufficient room left in the AG to
-		 * complete a full tree split for an extent insert.  If
-		 * we are converting the middle part of an extent then
-		 * we may need space for two tree splits.
-		 *
-		 * We are relying on the caller to make the correct block
-		 * reservation for this operation to succeed.  If the
-		 * reservation amount is insufficient then we may fail a
-		 * block allocation here and corrupt the filesystem.
-		 */
-		args.minleft = xfs_trans_get_block_res(args.tp);
-	} else if (cur->bc_private.b.flist->xbf_low)
-		args.type = XFS_ALLOCTYPE_START_BNO;
-	else
-		args.type = XFS_ALLOCTYPE_NEAR_BNO;
-	args.mod = args.alignment = args.total = args.isfl =
-		args.userdata = args.minalignslop = 0;
-	args.minlen = args.maxlen = args.prod = 1;
-	args.wasdel = cur->bc_private.b.flags & XFS_BTCUR_BPRV_WASDEL;
-	if (!args.wasdel && xfs_trans_get_block_res(args.tp) == 0) {
-		XFS_BMBT_TRACE_CURSOR(cur, ERROR);
-		return XFS_ERROR(ENOSPC);
-	}
-	if ((error = xfs_alloc_vextent(&args))) {
-		XFS_BMBT_TRACE_CURSOR(cur, ERROR);
-		return error;
-	}
-	if (args.fsbno == NULLFSBLOCK && args.minleft) {
-		/*
-		 * Could not find an AG with enough free space to satisfy
-		 * a full btree split.  Try again without minleft and if
-		 * successful activate the lowspace algorithm.
-		 */
-		args.fsbno = 0;
-		args.type = XFS_ALLOCTYPE_FIRST_AG;
-		args.minleft = 0;
-		if ((error = xfs_alloc_vextent(&args))) {
-			XFS_BMBT_TRACE_CURSOR(cur, ERROR);
-			return error;
-		}
-		cur->bc_private.b.flist->xbf_low = 1;
-	}
-	if (args.fsbno == NULLFSBLOCK) {
-		XFS_BMBT_TRACE_CURSOR(cur, EXIT);
-		*stat = 0;
-		return 0;
-	}
-	ASSERT(args.len == 1);
-	cur->bc_private.b.firstblock = args.fsbno;
-	cur->bc_private.b.allocated++;
-	cur->bc_private.b.ip->i_d.di_nblocks++;
-	xfs_trans_log_inode(args.tp, cur->bc_private.b.ip, XFS_ILOG_CORE);
-	XFS_TRANS_MOD_DQUOT_BYINO(args.mp, args.tp, cur->bc_private.b.ip,
-			XFS_TRANS_DQ_BCOUNT, 1L);
-	rbp = xfs_btree_get_bufl(args.mp, args.tp, args.fsbno, 0);
-	right = XFS_BUF_TO_BMBT_BLOCK(rbp);
-#ifdef DEBUG
-	if ((error = xfs_btree_check_lblock(cur, left, level, rbp))) {
-		XFS_BMBT_TRACE_CURSOR(cur, ERROR);
-		return error;
-	}
-#endif
-	right->bb_magic = cpu_to_be32(XFS_BMAP_MAGIC);
-	right->bb_level = left->bb_level;
-	right->bb_numrecs = cpu_to_be16(be16_to_cpu(left->bb_numrecs) / 2);
-	if ((be16_to_cpu(left->bb_numrecs) & 1) &&
-	    cur->bc_ptrs[level] <= be16_to_cpu(right->bb_numrecs) + 1)
-		be16_add_cpu(&right->bb_numrecs, 1);
-	i = be16_to_cpu(left->bb_numrecs) - be16_to_cpu(right->bb_numrecs) + 1;
-	if (level > 0) {
-		lkp = XFS_BMAP_KEY_IADDR(left, i, cur);
-		lpp = XFS_BMAP_PTR_IADDR(left, i, cur);
-		rkp = XFS_BMAP_KEY_IADDR(right, 1, cur);
-		rpp = XFS_BMAP_PTR_IADDR(right, 1, cur);
-#ifdef DEBUG
-		for (i = 0; i < be16_to_cpu(right->bb_numrecs); i++) {
-			if ((error = xfs_btree_check_lptr_disk(cur, lpp[i], level))) {
-				XFS_BMBT_TRACE_CURSOR(cur, ERROR);
-				return error;
-			}
-		}
-#endif
-		memcpy(rkp, lkp, be16_to_cpu(right->bb_numrecs) * sizeof(*rkp));
-		memcpy(rpp, lpp, be16_to_cpu(right->bb_numrecs) * sizeof(*rpp));
-		xfs_bmbt_log_keys(cur, rbp, 1, be16_to_cpu(right->bb_numrecs));
-		xfs_bmbt_log_ptrs(cur, rbp, 1, be16_to_cpu(right->bb_numrecs));
-		*startoff = be64_to_cpu(rkp->br_startoff);
-	} else {
-		lrp = XFS_BMAP_REC_IADDR(left, i, cur);
-		rrp = XFS_BMAP_REC_IADDR(right, 1, cur);
-		memcpy(rrp, lrp, be16_to_cpu(right->bb_numrecs) * sizeof(*rrp));
-		xfs_bmbt_log_recs(cur, rbp, 1, be16_to_cpu(right->bb_numrecs));
-		*startoff = xfs_bmbt_disk_get_startoff(rrp);
-	}
-	be16_add_cpu(&left->bb_numrecs, -(be16_to_cpu(right->bb_numrecs)));
-	right->bb_rightsib = left->bb_rightsib;
-	left->bb_rightsib = cpu_to_be64(args.fsbno);
-	right->bb_leftsib = cpu_to_be64(lbno);
-	xfs_bmbt_log_block(cur, rbp, XFS_BB_ALL_BITS);
-	xfs_bmbt_log_block(cur, lbp, XFS_BB_NUMRECS | XFS_BB_RIGHTSIB);
-	if (be64_to_cpu(right->bb_rightsib) != NULLDFSBNO) {
-		if ((error = xfs_btree_read_bufl(args.mp, args.tp,
-				be64_to_cpu(right->bb_rightsib), 0, &rrbp,
-				XFS_BMAP_BTREE_REF))) {
-			XFS_BMBT_TRACE_CURSOR(cur, ERROR);
-			return error;
-		}
-		rrblock = XFS_BUF_TO_BMBT_BLOCK(rrbp);
-		if ((error = xfs_btree_check_lblock(cur, rrblock, level, rrbp))) {
-			XFS_BMBT_TRACE_CURSOR(cur, ERROR);
-			return error;
-		}
-		rrblock->bb_leftsib = cpu_to_be64(args.fsbno);
-		xfs_bmbt_log_block(cur, rrbp, XFS_BB_LEFTSIB);
-	}
-	if (cur->bc_ptrs[level] > be16_to_cpu(left->bb_numrecs) + 1) {
-		xfs_btree_setbuf(cur, level, rbp);
-		cur->bc_ptrs[level] -= be16_to_cpu(left->bb_numrecs);
-	}
-	if (level + 1 < cur->bc_nlevels) {
-		if ((error = xfs_btree_dup_cursor(cur, curp))) {
-			XFS_BMBT_TRACE_CURSOR(cur, ERROR);
-			return error;
-		}
-		(*curp)->bc_ptrs[level + 1]++;
-	}
-	*bnop = args.fsbno;
-	XFS_BMBT_TRACE_CURSOR(cur, EXIT);
-	*stat = 1;
-	return 0;
-}
-
-
-/*
- * Update keys for the record.
- */
-STATIC int
-xfs_bmbt_updkey(
-	xfs_btree_cur_t		*cur,
-	xfs_bmbt_key_t		*keyp,	/* on-disk format */
-	int			level)
-{
-	xfs_bmbt_block_t	*block;
-	xfs_buf_t		*bp;
-#ifdef DEBUG
-	int			error;
-#endif
-	xfs_bmbt_key_t		*kp;
-	int			ptr;
-
-	ASSERT(level >= 1);
-	XFS_BMBT_TRACE_CURSOR(cur, ENTRY);
-	XFS_BMBT_TRACE_ARGIK(cur, level, keyp);
-	for (ptr = 1; ptr == 1 && level < cur->bc_nlevels; level++) {
-		block = xfs_bmbt_get_block(cur, level, &bp);
-#ifdef DEBUG
-		if ((error = xfs_btree_check_lblock(cur, block, level, bp))) {
-			XFS_BMBT_TRACE_CURSOR(cur, ERROR);
-			return error;
-		}
-#endif
-		ptr = cur->bc_ptrs[level];
-		kp = XFS_BMAP_KEY_IADDR(block, ptr, cur);
-		*kp = *keyp;
-		xfs_bmbt_log_keys(cur, bp, ptr, ptr);
-	}
-	XFS_BMBT_TRACE_CURSOR(cur, EXIT);
-	return 0;
-}
-
 /*
  * Convert on-disk form of btree root to in-memory form.
  */
 void
 xfs_bmdr_to_bmbt(
+	struct xfs_mount	*mp,
 	xfs_bmdr_block_t	*dblock,
 	int			dblocklen,
-	xfs_bmbt_block_t	*rblock,
+	struct xfs_btree_block	*rblock,
 	int			rblocklen)
 {
 	int			dmxr;
@@ -1688,129 +81,19 @@ xfs_bmdr_to_bmbt(
 	rblock->bb_level = dblock->bb_level;
 	ASSERT(be16_to_cpu(rblock->bb_level) > 0);
 	rblock->bb_numrecs = dblock->bb_numrecs;
-	rblock->bb_leftsib = cpu_to_be64(NULLDFSBNO);
-	rblock->bb_rightsib = cpu_to_be64(NULLDFSBNO);
-	dmxr = (int)XFS_BTREE_BLOCK_MAXRECS(dblocklen, xfs_bmdr, 0);
-	fkp = XFS_BTREE_KEY_ADDR(xfs_bmdr, dblock, 1);
-	tkp = XFS_BMAP_BROOT_KEY_ADDR(rblock, 1, rblocklen);
-	fpp = XFS_BTREE_PTR_ADDR(xfs_bmdr, dblock, 1, dmxr);
-	tpp = XFS_BMAP_BROOT_PTR_ADDR(rblock, 1, rblocklen);
+	rblock->bb_u.l.bb_leftsib = cpu_to_be64(NULLDFSBNO);
+	rblock->bb_u.l.bb_rightsib = cpu_to_be64(NULLDFSBNO);
+	dmxr = xfs_bmdr_maxrecs(mp, dblocklen, 0);
+	fkp = XFS_BMDR_KEY_ADDR(dblock, 1);
+	tkp = XFS_BMBT_KEY_ADDR(mp, rblock, 1);
+	fpp = XFS_BMDR_PTR_ADDR(dblock, 1, dmxr);
+	tpp = XFS_BMAP_BROOT_PTR_ADDR(mp, rblock, 1, rblocklen);
 	dmxr = be16_to_cpu(dblock->bb_numrecs);
 	memcpy(tkp, fkp, sizeof(*fkp) * dmxr);
 	memcpy(tpp, fpp, sizeof(*fpp) * dmxr);
 }
 
 /*
- * Decrement cursor by one record at the level.
- * For nonzero levels the leaf-ward information is untouched.
- */
-int						/* error */
-xfs_bmbt_decrement(
-	xfs_btree_cur_t		*cur,
-	int			level,
-	int			*stat)		/* success/failure */
-{
-	xfs_bmbt_block_t	*block;
-	xfs_buf_t		*bp;
-	int			error;		/* error return value */
-	xfs_fsblock_t		fsbno;
-	int			lev;
-	xfs_mount_t		*mp;
-	xfs_trans_t		*tp;
-
-	XFS_BMBT_TRACE_CURSOR(cur, ENTRY);
-	XFS_BMBT_TRACE_ARGI(cur, level);
-	ASSERT(level < cur->bc_nlevels);
-	if (level < cur->bc_nlevels - 1)
-		xfs_btree_readahead(cur, level, XFS_BTCUR_LEFTRA);
-	if (--cur->bc_ptrs[level] > 0) {
-		XFS_BMBT_TRACE_CURSOR(cur, EXIT);
-		*stat = 1;
-		return 0;
-	}
-	block = xfs_bmbt_get_block(cur, level, &bp);
-#ifdef DEBUG
-	if ((error = xfs_btree_check_lblock(cur, block, level, bp))) {
-		XFS_BMBT_TRACE_CURSOR(cur, ERROR);
-		return error;
-	}
-#endif
-	if (be64_to_cpu(block->bb_leftsib) == NULLDFSBNO) {
-		XFS_BMBT_TRACE_CURSOR(cur, EXIT);
-		*stat = 0;
-		return 0;
-	}
-	for (lev = level + 1; lev < cur->bc_nlevels; lev++) {
-		if (--cur->bc_ptrs[lev] > 0)
-			break;
-		if (lev < cur->bc_nlevels - 1)
-			xfs_btree_readahead(cur, lev, XFS_BTCUR_LEFTRA);
-	}
-	if (lev == cur->bc_nlevels) {
-		XFS_BMBT_TRACE_CURSOR(cur, EXIT);
-		*stat = 0;
-		return 0;
-	}
-	tp = cur->bc_tp;
-	mp = cur->bc_mp;
-	for (block = xfs_bmbt_get_block(cur, lev, &bp); lev > level; ) {
-		fsbno = be64_to_cpu(*XFS_BMAP_PTR_IADDR(block, cur->bc_ptrs[lev], cur));
-		if ((error = xfs_btree_read_bufl(mp, tp, fsbno, 0, &bp,
-				XFS_BMAP_BTREE_REF))) {
-			XFS_BMBT_TRACE_CURSOR(cur, ERROR);
-			return error;
-		}
-		lev--;
-		xfs_btree_setbuf(cur, lev, bp);
-		block = XFS_BUF_TO_BMBT_BLOCK(bp);
-		if ((error = xfs_btree_check_lblock(cur, block, lev, bp))) {
-			XFS_BMBT_TRACE_CURSOR(cur, ERROR);
-			return error;
-		}
-		cur->bc_ptrs[lev] = be16_to_cpu(block->bb_numrecs);
-	}
-	XFS_BMBT_TRACE_CURSOR(cur, EXIT);
-	*stat = 1;
-	return 0;
-}
-
-/*
- * Delete the record pointed to by cur.
- */
-int					/* error */
-xfs_bmbt_delete(
-	xfs_btree_cur_t	*cur,
-	int		*stat)		/* success/failure */
-{
-	int		error;		/* error return value */
-	int		i;
-	int		level;
-
-	XFS_BMBT_TRACE_CURSOR(cur, ENTRY);
-	for (level = 0, i = 2; i == 2; level++) {
-		if ((error = xfs_bmbt_delrec(cur, level, &i))) {
-			XFS_BMBT_TRACE_CURSOR(cur, ERROR);
-			return error;
-		}
-	}
-	if (i == 0) {
-		for (level = 1; level < cur->bc_nlevels; level++) {
-			if (cur->bc_ptrs[level] == 0) {
-				if ((error = xfs_bmbt_decrement(cur, level,
-						&i))) {
-					XFS_BMBT_TRACE_CURSOR(cur, ERROR);
-					return error;
-				}
-				break;
-			}
-		}
-	}
-	XFS_BMBT_TRACE_CURSOR(cur, EXIT);
-	*stat = i;
-	return 0;
-}
-
-/*
  * Convert a compressed bmap extent record to an uncompressed form.
  * This code must be in sync with the routines xfs_bmbt_get_startoff,
  * xfs_bmbt_get_startblock, xfs_bmbt_get_blockcount and xfs_bmbt_get_state.
@@ -1864,31 +147,6 @@ xfs_bmbt_get_all(
 }
 
 /*
- * Get the block pointer for the given level of the cursor.
- * Fill in the buffer pointer, if applicable.
- */
-xfs_bmbt_block_t *
-xfs_bmbt_get_block(
-	xfs_btree_cur_t		*cur,
-	int			level,
-	xfs_buf_t		**bpp)
-{
-	xfs_ifork_t		*ifp;
-	xfs_bmbt_block_t	*rval;
-
-	if (level < cur->bc_nlevels - 1) {
-		*bpp = cur->bc_bufs[level];
-		rval = XFS_BUF_TO_BMBT_BLOCK(*bpp);
-	} else {
-		*bpp = NULL;
-		ifp = XFS_IFORK_PTR(cur->bc_private.b.ip,
-			cur->bc_private.b.whichfork);
-		rval = ifp->if_broot;
-	}
-	return rval;
-}
-
-/*
  * Extract the blockcount field from an in memory bmap extent record.
  */
 xfs_filblks_t
@@ -1974,348 +232,6 @@ xfs_bmbt_disk_get_startoff(
 		 XFS_MASK64LO(64 - BMBT_EXNTFLAG_BITLEN)) >> 9;
 }
 
-/*
- * Increment cursor by one record at the level.
- * For nonzero levels the leaf-ward information is untouched.
- */
-int						/* error */
-xfs_bmbt_increment(
-	xfs_btree_cur_t		*cur,
-	int			level,
-	int			*stat)		/* success/failure */
-{
-	xfs_bmbt_block_t	*block;
-	xfs_buf_t		*bp;
-	int			error;		/* error return value */
-	xfs_fsblock_t		fsbno;
-	int			lev;
-	xfs_mount_t		*mp;
-	xfs_trans_t		*tp;
-
-	XFS_BMBT_TRACE_CURSOR(cur, ENTRY);
-	XFS_BMBT_TRACE_ARGI(cur, level);
-	ASSERT(level < cur->bc_nlevels);
-	if (level < cur->bc_nlevels - 1)
-		xfs_btree_readahead(cur, level, XFS_BTCUR_RIGHTRA);
-	block = xfs_bmbt_get_block(cur, level, &bp);
-#ifdef DEBUG
-	if ((error = xfs_btree_check_lblock(cur, block, level, bp))) {
-		XFS_BMBT_TRACE_CURSOR(cur, ERROR);
-		return error;
-	}
-#endif
-	if (++cur->bc_ptrs[level] <= be16_to_cpu(block->bb_numrecs)) {
-		XFS_BMBT_TRACE_CURSOR(cur, EXIT);
-		*stat = 1;
-		return 0;
-	}
-	if (be64_to_cpu(block->bb_rightsib) == NULLDFSBNO) {
-		XFS_BMBT_TRACE_CURSOR(cur, EXIT);
-		*stat = 0;
-		return 0;
-	}
-	for (lev = level + 1; lev < cur->bc_nlevels; lev++) {
-		block = xfs_bmbt_get_block(cur, lev, &bp);
-#ifdef DEBUG
-		if ((error = xfs_btree_check_lblock(cur, block, lev, bp))) {
-			XFS_BMBT_TRACE_CURSOR(cur, ERROR);
-			return error;
-		}
-#endif
-		if (++cur->bc_ptrs[lev] <= be16_to_cpu(block->bb_numrecs))
-			break;
-		if (lev < cur->bc_nlevels - 1)
-			xfs_btree_readahead(cur, lev, XFS_BTCUR_RIGHTRA);
-	}
-	if (lev == cur->bc_nlevels) {
-		XFS_BMBT_TRACE_CURSOR(cur, EXIT);
-		*stat = 0;
-		return 0;
-	}
-	tp = cur->bc_tp;
-	mp = cur->bc_mp;
-	for (block = xfs_bmbt_get_block(cur, lev, &bp); lev > level; ) {
-		fsbno = be64_to_cpu(*XFS_BMAP_PTR_IADDR(block, cur->bc_ptrs[lev], cur));
-		if ((error = xfs_btree_read_bufl(mp, tp, fsbno, 0, &bp,
-				XFS_BMAP_BTREE_REF))) {
-			XFS_BMBT_TRACE_CURSOR(cur, ERROR);
-			return error;
-		}
-		lev--;
-		xfs_btree_setbuf(cur, lev, bp);
-		block = XFS_BUF_TO_BMBT_BLOCK(bp);
-		if ((error = xfs_btree_check_lblock(cur, block, lev, bp))) {
-			XFS_BMBT_TRACE_CURSOR(cur, ERROR);
-			return error;
-		}
-		cur->bc_ptrs[lev] = 1;
-	}
-	XFS_BMBT_TRACE_CURSOR(cur, EXIT);
-	*stat = 1;
-	return 0;
-}
-
-/*
- * Insert the current record at the point referenced by cur.
- *
- * A multi-level split of the tree on insert will invalidate the original
- * cursor.  All callers of this function should assume that the cursor is
- * no longer valid and revalidate it.
- */
-int					/* error */
-xfs_bmbt_insert(
-	xfs_btree_cur_t	*cur,
-	int		*stat)		/* success/failure */
-{
-	int		error;		/* error return value */
-	int		i;
-	int		level;
-	xfs_fsblock_t	nbno;
-	xfs_btree_cur_t	*ncur;
-	xfs_bmbt_rec_t	nrec;
-	xfs_btree_cur_t	*pcur;
-
-	XFS_BMBT_TRACE_CURSOR(cur, ENTRY);
-	level = 0;
-	nbno = NULLFSBLOCK;
-	xfs_bmbt_disk_set_all(&nrec, &cur->bc_rec.b);
-	ncur = NULL;
-	pcur = cur;
-	do {
-		if ((error = xfs_bmbt_insrec(pcur, level++, &nbno, &nrec, &ncur,
-				&i))) {
-			if (pcur != cur)
-				xfs_btree_del_cursor(pcur, XFS_BTREE_ERROR);
-			XFS_BMBT_TRACE_CURSOR(cur, ERROR);
-			return error;
-		}
-		XFS_WANT_CORRUPTED_GOTO(i == 1, error0);
-		if (pcur != cur && (ncur || nbno == NULLFSBLOCK)) {
-			cur->bc_nlevels = pcur->bc_nlevels;
-			cur->bc_private.b.allocated +=
-				pcur->bc_private.b.allocated;
-			pcur->bc_private.b.allocated = 0;
-			ASSERT((cur->bc_private.b.firstblock != NULLFSBLOCK) ||
-			       XFS_IS_REALTIME_INODE(cur->bc_private.b.ip));
-			cur->bc_private.b.firstblock =
-				pcur->bc_private.b.firstblock;
-			ASSERT(cur->bc_private.b.flist ==
-			       pcur->bc_private.b.flist);
-			xfs_btree_del_cursor(pcur, XFS_BTREE_NOERROR);
-		}
-		if (ncur) {
-			pcur = ncur;
-			ncur = NULL;
-		}
-	} while (nbno != NULLFSBLOCK);
-	XFS_BMBT_TRACE_CURSOR(cur, EXIT);
-	*stat = i;
-	return 0;
-error0:
-	XFS_BMBT_TRACE_CURSOR(cur, ERROR);
-	return error;
-}
-
-/*
- * Log fields from the btree block header.
- */
-void
-xfs_bmbt_log_block(
-	xfs_btree_cur_t		*cur,
-	xfs_buf_t		*bp,
-	int			fields)
-{
-	int			first;
-	int			last;
-	xfs_trans_t		*tp;
-	static const short	offsets[] = {
-		offsetof(xfs_bmbt_block_t, bb_magic),
-		offsetof(xfs_bmbt_block_t, bb_level),
-		offsetof(xfs_bmbt_block_t, bb_numrecs),
-		offsetof(xfs_bmbt_block_t, bb_leftsib),
-		offsetof(xfs_bmbt_block_t, bb_rightsib),
-		sizeof(xfs_bmbt_block_t)
-	};
-
-	XFS_BMBT_TRACE_CURSOR(cur, ENTRY);
-	XFS_BMBT_TRACE_ARGBI(cur, bp, fields);
-	tp = cur->bc_tp;
-	if (bp) {
-		xfs_btree_offsets(fields, offsets, XFS_BB_NUM_BITS, &first,
-				  &last);
-		xfs_trans_log_buf(tp, bp, first, last);
-	} else
-		xfs_trans_log_inode(tp, cur->bc_private.b.ip,
-			XFS_ILOG_FBROOT(cur->bc_private.b.whichfork));
-	XFS_BMBT_TRACE_CURSOR(cur, EXIT);
-}
-
-/*
- * Log record values from the btree block.
- */
-void
-xfs_bmbt_log_recs(
-	xfs_btree_cur_t		*cur,
-	xfs_buf_t		*bp,
-	int			rfirst,
-	int			rlast)
-{
-	xfs_bmbt_block_t	*block;
-	int			first;
-	int			last;
-	xfs_bmbt_rec_t		*rp;
-	xfs_trans_t		*tp;
-
-	XFS_BMBT_TRACE_CURSOR(cur, ENTRY);
-	XFS_BMBT_TRACE_ARGBII(cur, bp, rfirst, rlast);
-	ASSERT(bp);
-	tp = cur->bc_tp;
-	block = XFS_BUF_TO_BMBT_BLOCK(bp);
-	rp = XFS_BMAP_REC_DADDR(block, 1, cur);
-	first = (int)((xfs_caddr_t)&rp[rfirst - 1] - (xfs_caddr_t)block);
-	last = (int)(((xfs_caddr_t)&rp[rlast] - 1) - (xfs_caddr_t)block);
-	xfs_trans_log_buf(tp, bp, first, last);
-	XFS_BMBT_TRACE_CURSOR(cur, EXIT);
-}
-
-int					/* error */
-xfs_bmbt_lookup_eq(
-	xfs_btree_cur_t	*cur,
-	xfs_fileoff_t	off,
-	xfs_fsblock_t	bno,
-	xfs_filblks_t	len,
-	int		*stat)		/* success/failure */
-{
-	cur->bc_rec.b.br_startoff = off;
-	cur->bc_rec.b.br_startblock = bno;
-	cur->bc_rec.b.br_blockcount = len;
-	return xfs_bmbt_lookup(cur, XFS_LOOKUP_EQ, stat);
-}
-
-int					/* error */
-xfs_bmbt_lookup_ge(
-	xfs_btree_cur_t	*cur,
-	xfs_fileoff_t	off,
-	xfs_fsblock_t	bno,
-	xfs_filblks_t	len,
-	int		*stat)		/* success/failure */
-{
-	cur->bc_rec.b.br_startoff = off;
-	cur->bc_rec.b.br_startblock = bno;
-	cur->bc_rec.b.br_blockcount = len;
-	return xfs_bmbt_lookup(cur, XFS_LOOKUP_GE, stat);
-}
-
-/*
- * Give the bmap btree a new root block.  Copy the old broot contents
- * down into a real block and make the broot point to it.
- */
-int						/* error */
-xfs_bmbt_newroot(
-	xfs_btree_cur_t		*cur,		/* btree cursor */
-	int			*logflags,	/* logging flags for inode */
-	int			*stat)		/* return status - 0 fail */
-{
-	xfs_alloc_arg_t		args;		/* allocation arguments */
-	xfs_bmbt_block_t	*block;		/* bmap btree block */
-	xfs_buf_t		*bp;		/* buffer for block */
-	xfs_bmbt_block_t	*cblock;	/* child btree block */
-	xfs_bmbt_key_t		*ckp;		/* child key pointer */
-	xfs_bmbt_ptr_t		*cpp;		/* child ptr pointer */
-	int			error;		/* error return code */
-#ifdef DEBUG
-	int			i;		/* loop counter */
-#endif
-	xfs_bmbt_key_t		*kp;		/* pointer to bmap btree key */
-	int			level;		/* btree level */
-	xfs_bmbt_ptr_t		*pp;		/* pointer to bmap block addr */
-
-	XFS_BMBT_TRACE_CURSOR(cur, ENTRY);
-	level = cur->bc_nlevels - 1;
-	block = xfs_bmbt_get_block(cur, level, &bp);
-	/*
-	 * Copy the root into a real block.
-	 */
-	args.mp = cur->bc_mp;
-	pp = XFS_BMAP_PTR_IADDR(block, 1, cur);
-	args.tp = cur->bc_tp;
-	args.fsbno = cur->bc_private.b.firstblock;
-	args.mod = args.minleft = args.alignment = args.total = args.isfl =
-		args.userdata = args.minalignslop = 0;
-	args.minlen = args.maxlen = args.prod = 1;
-	args.wasdel = cur->bc_private.b.flags & XFS_BTCUR_BPRV_WASDEL;
-	args.firstblock = args.fsbno;
-	if (args.fsbno == NULLFSBLOCK) {
-#ifdef DEBUG
-		if ((error = xfs_btree_check_lptr_disk(cur, *pp, level))) {
-			XFS_BMBT_TRACE_CURSOR(cur, ERROR);
-			return error;
-		}
-#endif
-		args.fsbno = be64_to_cpu(*pp);
-		args.type = XFS_ALLOCTYPE_START_BNO;
-	} else if (cur->bc_private.b.flist->xbf_low)
-		args.type = XFS_ALLOCTYPE_START_BNO;
-	else
-		args.type = XFS_ALLOCTYPE_NEAR_BNO;
-	if ((error = xfs_alloc_vextent(&args))) {
-		XFS_BMBT_TRACE_CURSOR(cur, ERROR);
-		return error;
-	}
-	if (args.fsbno == NULLFSBLOCK) {
-		XFS_BMBT_TRACE_CURSOR(cur, EXIT);
-		*stat = 0;
-		return 0;
-	}
-	ASSERT(args.len == 1);
-	cur->bc_private.b.firstblock = args.fsbno;
-	cur->bc_private.b.allocated++;
-	cur->bc_private.b.ip->i_d.di_nblocks++;
-	XFS_TRANS_MOD_DQUOT_BYINO(args.mp, args.tp, cur->bc_private.b.ip,
-			  XFS_TRANS_DQ_BCOUNT, 1L);
-	bp = xfs_btree_get_bufl(args.mp, cur->bc_tp, args.fsbno, 0);
-	cblock = XFS_BUF_TO_BMBT_BLOCK(bp);
-	*cblock = *block;
-	be16_add_cpu(&block->bb_level, 1);
-	block->bb_numrecs = cpu_to_be16(1);
-	cur->bc_nlevels++;
-	cur->bc_ptrs[level + 1] = 1;
-	kp = XFS_BMAP_KEY_IADDR(block, 1, cur);
-	ckp = XFS_BMAP_KEY_IADDR(cblock, 1, cur);
-	memcpy(ckp, kp, be16_to_cpu(cblock->bb_numrecs) * sizeof(*kp));
-	cpp = XFS_BMAP_PTR_IADDR(cblock, 1, cur);
-#ifdef DEBUG
-	for (i = 0; i < be16_to_cpu(cblock->bb_numrecs); i++) {
-		if ((error = xfs_btree_check_lptr_disk(cur, pp[i], level))) {
-			XFS_BMBT_TRACE_CURSOR(cur, ERROR);
-			return error;
-		}
-	}
-#endif
-	memcpy(cpp, pp, be16_to_cpu(cblock->bb_numrecs) * sizeof(*pp));
-#ifdef DEBUG
-	if ((error = xfs_btree_check_lptr(cur, args.fsbno, level))) {
-		XFS_BMBT_TRACE_CURSOR(cur, ERROR);
-		return error;
-	}
-#endif
-	*pp = cpu_to_be64(args.fsbno);
-	xfs_iroot_realloc(cur->bc_private.b.ip, 1 - be16_to_cpu(cblock->bb_numrecs),
-		cur->bc_private.b.whichfork);
-	xfs_btree_setbuf(cur, level, bp);
-	/*
-	 * Do all this logging at the end so that
-	 * the root is at the right level.
-	 */
-	xfs_bmbt_log_block(cur, bp, XFS_BB_ALL_BITS);
-	xfs_bmbt_log_keys(cur, bp, 1, be16_to_cpu(cblock->bb_numrecs));
-	xfs_bmbt_log_ptrs(cur, bp, 1, be16_to_cpu(cblock->bb_numrecs));
-	XFS_BMBT_TRACE_CURSOR(cur, EXIT);
-	*logflags |=
-		XFS_ILOG_CORE | XFS_ILOG_FBROOT(cur->bc_private.b.whichfork);
-	*stat = 1;
-	return 0;
-}
 
 /*
  * Set all the fields in a bmap extent record from the arguments.
@@ -2512,7 +428,8 @@ xfs_bmbt_set_state(
  */
 void
 xfs_bmbt_to_bmdr(
-	xfs_bmbt_block_t	*rblock,
+	struct xfs_mount	*mp,
+	struct xfs_btree_block	*rblock,
 	int			rblocklen,
 	xfs_bmdr_block_t	*dblock,
 	int			dblocklen)
@@ -2524,67 +441,22 @@ xfs_bmbt_to_bmdr(
 	__be64			*tpp;
 
 	ASSERT(be32_to_cpu(rblock->bb_magic) == XFS_BMAP_MAGIC);
-	ASSERT(be64_to_cpu(rblock->bb_leftsib) == NULLDFSBNO);
-	ASSERT(be64_to_cpu(rblock->bb_rightsib) == NULLDFSBNO);
+	ASSERT(be64_to_cpu(rblock->bb_u.l.bb_leftsib) == NULLDFSBNO);
+	ASSERT(be64_to_cpu(rblock->bb_u.l.bb_rightsib) == NULLDFSBNO);
 	ASSERT(be16_to_cpu(rblock->bb_level) > 0);
 	dblock->bb_level = rblock->bb_level;
 	dblock->bb_numrecs = rblock->bb_numrecs;
-	dmxr = (int)XFS_BTREE_BLOCK_MAXRECS(dblocklen, xfs_bmdr, 0);
-	fkp = XFS_BMAP_BROOT_KEY_ADDR(rblock, 1, rblocklen);
-	tkp = XFS_BTREE_KEY_ADDR(xfs_bmdr, dblock, 1);
-	fpp = XFS_BMAP_BROOT_PTR_ADDR(rblock, 1, rblocklen);
-	tpp = XFS_BTREE_PTR_ADDR(xfs_bmdr, dblock, 1, dmxr);
+	dmxr = xfs_bmdr_maxrecs(mp, dblocklen, 0);
+	fkp = XFS_BMBT_KEY_ADDR(mp, rblock, 1);
+	tkp = XFS_BMDR_KEY_ADDR(dblock, 1);
+	fpp = XFS_BMAP_BROOT_PTR_ADDR(mp, rblock, 1, rblocklen);
+	tpp = XFS_BMDR_PTR_ADDR(dblock, 1, dmxr);
 	dmxr = be16_to_cpu(dblock->bb_numrecs);
 	memcpy(tkp, fkp, sizeof(*fkp) * dmxr);
 	memcpy(tpp, fpp, sizeof(*fpp) * dmxr);
 }
 
 /*
- * Update the record to the passed values.
- */
-int
-xfs_bmbt_update(
-	xfs_btree_cur_t		*cur,
-	xfs_fileoff_t		off,
-	xfs_fsblock_t		bno,
-	xfs_filblks_t		len,
-	xfs_exntst_t		state)
-{
-	xfs_bmbt_block_t	*block;
-	xfs_buf_t		*bp;
-	int			error;
-	xfs_bmbt_key_t		key;
-	int			ptr;
-	xfs_bmbt_rec_t		*rp;
-
-	XFS_BMBT_TRACE_CURSOR(cur, ENTRY);
-	XFS_BMBT_TRACE_ARGFFFI(cur, (xfs_dfiloff_t)off, (xfs_dfsbno_t)bno,
-		(xfs_dfilblks_t)len, (int)state);
-	block = xfs_bmbt_get_block(cur, 0, &bp);
-#ifdef DEBUG
-	if ((error = xfs_btree_check_lblock(cur, block, 0, bp))) {
-		XFS_BMBT_TRACE_CURSOR(cur, ERROR);
-		return error;
-	}
-#endif
-	ptr = cur->bc_ptrs[0];
-	rp = XFS_BMAP_REC_IADDR(block, ptr, cur);
-	xfs_bmbt_disk_set_allf(rp, off, bno, len, state);
-	xfs_bmbt_log_recs(cur, bp, ptr, ptr);
-	if (ptr > 1) {
-		XFS_BMBT_TRACE_CURSOR(cur, EXIT);
-		return 0;
-	}
-	key.br_startoff = cpu_to_be64(off);
-	if ((error = xfs_bmbt_updkey(cur, &key, 1))) {
-		XFS_BMBT_TRACE_CURSOR(cur, ERROR);
-		return error;
-	}
-	XFS_BMBT_TRACE_CURSOR(cur, EXIT);
-	return 0;
-}
-
-/*
  * Check extent records, which have just been read, for
  * any bit in the extent flag field. ASSERT on debug
  * kernels, as this condition should not occur.
@@ -2608,3 +480,451 @@ xfs_check_nostate_extents(
 	}
 	return 0;
 }
+
+
+STATIC struct xfs_btree_cur *
+xfs_bmbt_dup_cursor(
+	struct xfs_btree_cur	*cur)
+{
+	struct xfs_btree_cur	*new;
+
+	new = xfs_bmbt_init_cursor(cur->bc_mp, cur->bc_tp,
+			cur->bc_private.b.ip, cur->bc_private.b.whichfork);
+
+	/*
+	 * Copy the firstblock, flist, and flags values,
+	 * since init cursor doesn't get them.
+	 */
+	new->bc_private.b.firstblock = cur->bc_private.b.firstblock;
+	new->bc_private.b.flist = cur->bc_private.b.flist;
+	new->bc_private.b.flags = cur->bc_private.b.flags;
+
+	return new;
+}
+
+STATIC void
+xfs_bmbt_update_cursor(
+	struct xfs_btree_cur	*src,
+	struct xfs_btree_cur	*dst)
+{
+	ASSERT((dst->bc_private.b.firstblock != NULLFSBLOCK) ||
+	       (dst->bc_private.b.ip->i_d.di_flags & XFS_DIFLAG_REALTIME));
+	ASSERT(dst->bc_private.b.flist == src->bc_private.b.flist);
+
+	dst->bc_private.b.allocated += src->bc_private.b.allocated;
+	dst->bc_private.b.firstblock = src->bc_private.b.firstblock;
+
+	src->bc_private.b.allocated = 0;
+}
+
+STATIC int
+xfs_bmbt_alloc_block(
+	struct xfs_btree_cur	*cur,
+	union xfs_btree_ptr	*start,
+	union xfs_btree_ptr	*new,
+	int			length,
+	int			*stat)
+{
+	xfs_alloc_arg_t		args;		/* block allocation args */
+	int			error;		/* error return value */
+
+	memset(&args, 0, sizeof(args));
+	args.tp = cur->bc_tp;
+	args.mp = cur->bc_mp;
+	args.fsbno = cur->bc_private.b.firstblock;
+	args.firstblock = args.fsbno;
+
+	if (args.fsbno == NULLFSBLOCK) {
+		args.fsbno = be64_to_cpu(start->l);
+		args.type = XFS_ALLOCTYPE_START_BNO;
+		/*
+		 * Make sure there is sufficient room left in the AG to
+		 * complete a full tree split for an extent insert.  If
+		 * we are converting the middle part of an extent then
+		 * we may need space for two tree splits.
+		 *
+		 * We are relying on the caller to make the correct block
+		 * reservation for this operation to succeed.  If the
+		 * reservation amount is insufficient then we may fail a
+		 * block allocation here and corrupt the filesystem.
+		 */
+		args.minleft = xfs_trans_get_block_res(args.tp);
+	} else if (cur->bc_private.b.flist->xbf_low) {
+		args.type = XFS_ALLOCTYPE_START_BNO;
+	} else {
+		args.type = XFS_ALLOCTYPE_NEAR_BNO;
+	}
+
+	args.minlen = args.maxlen = args.prod = 1;
+	args.wasdel = cur->bc_private.b.flags & XFS_BTCUR_BPRV_WASDEL;
+	if (!args.wasdel && xfs_trans_get_block_res(args.tp) == 0) {
+		error = XFS_ERROR(ENOSPC);
+		goto error0;
+	}
+	error = xfs_alloc_vextent(&args);
+	if (error)
+		goto error0;
+
+	if (args.fsbno == NULLFSBLOCK && args.minleft) {
+		/*
+		 * Could not find an AG with enough free space to satisfy
+		 * a full btree split.  Try again without minleft and if
+		 * successful activate the lowspace algorithm.
+		 */
+		args.fsbno = 0;
+		args.type = XFS_ALLOCTYPE_FIRST_AG;
+		args.minleft = 0;
+		error = xfs_alloc_vextent(&args);
+		if (error)
+			goto error0;
+		cur->bc_private.b.flist->xbf_low = 1;
+	}
+	if (args.fsbno == NULLFSBLOCK) {
+		XFS_BTREE_TRACE_CURSOR(cur, XBT_EXIT);
+		*stat = 0;
+		return 0;
+	}
+	ASSERT(args.len == 1);
+	cur->bc_private.b.firstblock = args.fsbno;
+	cur->bc_private.b.allocated++;
+	cur->bc_private.b.ip->i_d.di_nblocks++;
+	xfs_trans_log_inode(args.tp, cur->bc_private.b.ip, XFS_ILOG_CORE);
+	XFS_TRANS_MOD_DQUOT_BYINO(args.mp, args.tp, cur->bc_private.b.ip,
+			XFS_TRANS_DQ_BCOUNT, 1L);
+
+	new->l = cpu_to_be64(args.fsbno);
+
+	XFS_BTREE_TRACE_CURSOR(cur, XBT_EXIT);
+	*stat = 1;
+	return 0;
+
+ error0:
+	XFS_BTREE_TRACE_CURSOR(cur, XBT_ERROR);
+	return error;
+}
+
+STATIC int
+xfs_bmbt_free_block(
+	struct xfs_btree_cur	*cur,
+	struct xfs_buf		*bp)
+{
+	struct xfs_mount	*mp = cur->bc_mp;
+	struct xfs_inode	*ip = cur->bc_private.b.ip;
+	struct xfs_trans	*tp = cur->bc_tp;
+	xfs_fsblock_t		fsbno = XFS_DADDR_TO_FSB(mp, XFS_BUF_ADDR(bp));
+
+	xfs_bmap_add_free(fsbno, 1, cur->bc_private.b.flist, mp);
+	ip->i_d.di_nblocks--;
+
+	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
+	XFS_TRANS_MOD_DQUOT_BYINO(mp, tp, ip, XFS_TRANS_DQ_BCOUNT, -1L);
+	xfs_trans_binval(tp, bp);
+	return 0;
+}
+
+STATIC int
+xfs_bmbt_get_minrecs(
+	struct xfs_btree_cur	*cur,
+	int			level)
+{
+	if (level == cur->bc_nlevels - 1) {
+		struct xfs_ifork	*ifp;
+
+		ifp = XFS_IFORK_PTR(cur->bc_private.b.ip,
+				    cur->bc_private.b.whichfork);
+
+		return xfs_bmbt_maxrecs(cur->bc_mp,
+					ifp->if_broot_bytes, level == 0) / 2;
+	}
+
+	return cur->bc_mp->m_bmap_dmnr[level != 0];
+}
+
+int
+xfs_bmbt_get_maxrecs(
+	struct xfs_btree_cur	*cur,
+	int			level)
+{
+	if (level == cur->bc_nlevels - 1) {
+		struct xfs_ifork	*ifp;
+
+		ifp = XFS_IFORK_PTR(cur->bc_private.b.ip,
+				    cur->bc_private.b.whichfork);
+
+		return xfs_bmbt_maxrecs(cur->bc_mp,
+					ifp->if_broot_bytes, level == 0);
+	}
+
+	return cur->bc_mp->m_bmap_dmxr[level != 0];
+
+}
+
+/*
+ * Get the maximum records we could store in the on-disk format.
+ *
+ * For non-root nodes this is equivalent to xfs_bmbt_get_maxrecs, but
+ * for the root node this checks the available space in the dinode fork
+ * so that we can resize the in-memory buffer to match it.  After a
+ * resize to the maximum size this function returns the same value
+ * as xfs_bmbt_get_maxrecs for the root node, too.
+ */
+STATIC int
+xfs_bmbt_get_dmaxrecs(
+	struct xfs_btree_cur	*cur,
+	int			level)
+{
+	if (level != cur->bc_nlevels - 1)
+		return cur->bc_mp->m_bmap_dmxr[level != 0];
+	return xfs_bmdr_maxrecs(cur->bc_mp, cur->bc_private.b.forksize,
+				level == 0);
+}
+
+STATIC void
+xfs_bmbt_init_key_from_rec(
+	union xfs_btree_key	*key,
+	union xfs_btree_rec	*rec)
+{
+	key->bmbt.br_startoff =
+		cpu_to_be64(xfs_bmbt_disk_get_startoff(&rec->bmbt));
+}
+
+STATIC void
+xfs_bmbt_init_rec_from_key(
+	union xfs_btree_key	*key,
+	union xfs_btree_rec	*rec)
+{
+	ASSERT(key->bmbt.br_startoff != 0);
+
+	xfs_bmbt_disk_set_allf(&rec->bmbt, be64_to_cpu(key->bmbt.br_startoff),
+			       0, 0, XFS_EXT_NORM);
+}
+
+STATIC void
+xfs_bmbt_init_rec_from_cur(
+	struct xfs_btree_cur	*cur,
+	union xfs_btree_rec	*rec)
+{
+	xfs_bmbt_disk_set_all(&rec->bmbt, &cur->bc_rec.b);
+}
+
+STATIC void
+xfs_bmbt_init_ptr_from_cur(
+	struct xfs_btree_cur	*cur,
+	union xfs_btree_ptr	*ptr)
+{
+	ptr->l = 0;
+}
+
+STATIC __int64_t
+xfs_bmbt_key_diff(
+	struct xfs_btree_cur	*cur,
+	union xfs_btree_key	*key)
+{
+	return (__int64_t)be64_to_cpu(key->bmbt.br_startoff) -
+				      cur->bc_rec.b.br_startoff;
+}
+
+#ifdef DEBUG
+STATIC int
+xfs_bmbt_keys_inorder(
+	struct xfs_btree_cur	*cur,
+	union xfs_btree_key	*k1,
+	union xfs_btree_key	*k2)
+{
+	return be64_to_cpu(k1->bmbt.br_startoff) <
+		be64_to_cpu(k2->bmbt.br_startoff);
+}
+
+STATIC int
+xfs_bmbt_recs_inorder(
+	struct xfs_btree_cur	*cur,
+	union xfs_btree_rec	*r1,
+	union xfs_btree_rec	*r2)
+{
+	return xfs_bmbt_disk_get_startoff(&r1->bmbt) +
+		xfs_bmbt_disk_get_blockcount(&r1->bmbt) <=
+		xfs_bmbt_disk_get_startoff(&r2->bmbt);
+}
+#endif	/* DEBUG */
+
+#ifdef XFS_BTREE_TRACE
+ktrace_t	*xfs_bmbt_trace_buf;
+
+STATIC void
+xfs_bmbt_trace_enter(
+	struct xfs_btree_cur	*cur,
+	const char		*func,
+	char			*s,
+	int			type,
+	int			line,
+	__psunsigned_t		a0,
+	__psunsigned_t		a1,
+	__psunsigned_t		a2,
+	__psunsigned_t		a3,
+	__psunsigned_t		a4,
+	__psunsigned_t		a5,
+	__psunsigned_t		a6,
+	__psunsigned_t		a7,
+	__psunsigned_t		a8,
+	__psunsigned_t		a9,
+	__psunsigned_t		a10)
+{
+	struct xfs_inode	*ip = cur->bc_private.b.ip;
+	int			whichfork = cur->bc_private.b.whichfork;
+
+	ktrace_enter(xfs_bmbt_trace_buf,
+		(void *)((__psint_t)type | (whichfork << 8) | (line << 16)),
+		(void *)func, (void *)s, (void *)ip, (void *)cur,
+		(void *)a0, (void *)a1, (void *)a2, (void *)a3,
+		(void *)a4, (void *)a5, (void *)a6, (void *)a7,
+		(void *)a8, (void *)a9, (void *)a10);
+	ktrace_enter(ip->i_btrace,
+		(void *)((__psint_t)type | (whichfork << 8) | (line << 16)),
+		(void *)func, (void *)s, (void *)ip, (void *)cur,
+		(void *)a0, (void *)a1, (void *)a2, (void *)a3,
+		(void *)a4, (void *)a5, (void *)a6, (void *)a7,
+		(void *)a8, (void *)a9, (void *)a10);
+}
+
+STATIC void
+xfs_bmbt_trace_cursor(
+	struct xfs_btree_cur	*cur,
+	__uint32_t		*s0,
+	__uint64_t		*l0,
+	__uint64_t		*l1)
+{
+	struct xfs_bmbt_rec_host r;
+
+	xfs_bmbt_set_all(&r, &cur->bc_rec.b);
+
+	*s0 = (cur->bc_nlevels << 24) |
+	      (cur->bc_private.b.flags << 16) |
+	       cur->bc_private.b.allocated;
+	*l0 = r.l0;
+	*l1 = r.l1;
+}
+
+STATIC void
+xfs_bmbt_trace_key(
+	struct xfs_btree_cur	*cur,
+	union xfs_btree_key	*key,
+	__uint64_t		*l0,
+	__uint64_t		*l1)
+{
+	*l0 = be64_to_cpu(key->bmbt.br_startoff);
+	*l1 = 0;
+}
+
+STATIC void
+xfs_bmbt_trace_record(
+	struct xfs_btree_cur	*cur,
+	union xfs_btree_rec	*rec,
+	__uint64_t		*l0,
+	__uint64_t		*l1,
+	__uint64_t		*l2)
+{
+	struct xfs_bmbt_irec	irec;
+
+	xfs_bmbt_disk_get_all(&rec->bmbt, &irec);
+	*l0 = irec.br_startoff;
+	*l1 = irec.br_startblock;
+	*l2 = irec.br_blockcount;
+}
+#endif /* XFS_BTREE_TRACE */
+
+static const struct xfs_btree_ops xfs_bmbt_ops = {
+	.rec_len		= sizeof(xfs_bmbt_rec_t),
+	.key_len		= sizeof(xfs_bmbt_key_t),
+
+	.dup_cursor		= xfs_bmbt_dup_cursor,
+	.update_cursor		= xfs_bmbt_update_cursor,
+	.alloc_block		= xfs_bmbt_alloc_block,
+	.free_block		= xfs_bmbt_free_block,
+	.get_maxrecs		= xfs_bmbt_get_maxrecs,
+	.get_minrecs		= xfs_bmbt_get_minrecs,
+	.get_dmaxrecs		= xfs_bmbt_get_dmaxrecs,
+	.init_key_from_rec	= xfs_bmbt_init_key_from_rec,
+	.init_rec_from_key	= xfs_bmbt_init_rec_from_key,
+	.init_rec_from_cur	= xfs_bmbt_init_rec_from_cur,
+	.init_ptr_from_cur	= xfs_bmbt_init_ptr_from_cur,
+	.key_diff		= xfs_bmbt_key_diff,
+
+#ifdef DEBUG
+	.keys_inorder		= xfs_bmbt_keys_inorder,
+	.recs_inorder		= xfs_bmbt_recs_inorder,
+#endif
+
+#ifdef XFS_BTREE_TRACE
+	.trace_enter		= xfs_bmbt_trace_enter,
+	.trace_cursor		= xfs_bmbt_trace_cursor,
+	.trace_key		= xfs_bmbt_trace_key,
+	.trace_record		= xfs_bmbt_trace_record,
+#endif
+};
+
+/*
+ * Allocate a new bmap btree cursor.
+ */
+struct xfs_btree_cur *				/* new bmap btree cursor */
+xfs_bmbt_init_cursor(
+	struct xfs_mount	*mp,		/* file system mount point */
+	struct xfs_trans	*tp,		/* transaction pointer */
+	struct xfs_inode	*ip,		/* inode owning the btree */
+	int			whichfork)	/* data or attr fork */
+{
+	struct xfs_ifork	*ifp = XFS_IFORK_PTR(ip, whichfork);
+	struct xfs_btree_cur	*cur;
+
+	cur = kmem_zone_zalloc(xfs_btree_cur_zone, KM_SLEEP);
+
+	cur->bc_tp = tp;
+	cur->bc_mp = mp;
+	cur->bc_nlevels = be16_to_cpu(ifp->if_broot->bb_level) + 1;
+	cur->bc_btnum = XFS_BTNUM_BMAP;
+	cur->bc_blocklog = mp->m_sb.sb_blocklog;
+
+	cur->bc_ops = &xfs_bmbt_ops;
+	cur->bc_flags = XFS_BTREE_LONG_PTRS | XFS_BTREE_ROOT_IN_INODE;
+
+	cur->bc_private.b.forksize = XFS_IFORK_SIZE(ip, whichfork);
+	cur->bc_private.b.ip = ip;
+	cur->bc_private.b.firstblock = NULLFSBLOCK;
+	cur->bc_private.b.flist = NULL;
+	cur->bc_private.b.allocated = 0;
+	cur->bc_private.b.flags = 0;
+	cur->bc_private.b.whichfork = whichfork;
+
+	return cur;
+}
+
+/*
+ * Calculate number of records in a bmap btree block.
+ */
+int
+xfs_bmbt_maxrecs(
+	struct xfs_mount	*mp,
+	int			blocklen,
+	int			leaf)
+{
+	blocklen -= XFS_BMBT_BLOCK_LEN(mp);
+
+	if (leaf)
+		return blocklen / sizeof(xfs_bmbt_rec_t);
+	return blocklen / (sizeof(xfs_bmbt_key_t) + sizeof(xfs_bmbt_ptr_t));
+}
+
+/*
+ * Calculate number of records in a bmap btree inode root.
+ */
+int
+xfs_bmdr_maxrecs(
+	struct xfs_mount	*mp,
+	int			blocklen,
+	int			leaf)
+{
+	blocklen -= sizeof(xfs_bmdr_block_t);
+
+	if (leaf)
+		return blocklen / sizeof(xfs_bmdr_rec_t);
+	return blocklen / (sizeof(xfs_bmdr_key_t) + sizeof(xfs_bmdr_ptr_t));
+}
diff --git a/fs/xfs/xfs_bmap_btree.h b/fs/xfs/xfs_bmap_btree.h
index cd0d4b4bb816..a4555abb6622 100644
--- a/fs/xfs/xfs_bmap_btree.h
+++ b/fs/xfs/xfs_bmap_btree.h
@@ -21,9 +21,10 @@
 #define XFS_BMAP_MAGIC	0x424d4150	/* 'BMAP' */
 
 struct xfs_btree_cur;
-struct xfs_btree_lblock;
+struct xfs_btree_block;
 struct xfs_mount;
 struct xfs_inode;
+struct xfs_trans;
 
 /*
  * Bmap root header, on-disk form only.
@@ -145,71 +146,60 @@ typedef struct xfs_bmbt_key {
 /* btree pointer type */
 typedef __be64 xfs_bmbt_ptr_t, xfs_bmdr_ptr_t;
 
-/* btree block header type */
-typedef struct xfs_btree_lblock xfs_bmbt_block_t;
-
-#define XFS_BUF_TO_BMBT_BLOCK(bp)	((xfs_bmbt_block_t *)XFS_BUF_PTR(bp))
-
-#define XFS_BMAP_RBLOCK_DSIZE(lev,cur)	((cur)->bc_private.b.forksize)
-#define XFS_BMAP_RBLOCK_ISIZE(lev,cur)	\
-	((int)XFS_IFORK_PTR((cur)->bc_private.b.ip, \
-		    (cur)->bc_private.b.whichfork)->if_broot_bytes)
-
-#define XFS_BMAP_BLOCK_DMAXRECS(lev,cur) \
-	(((lev) == (cur)->bc_nlevels - 1 ? \
-		XFS_BTREE_BLOCK_MAXRECS(XFS_BMAP_RBLOCK_DSIZE(lev,cur), \
-			xfs_bmdr, (lev) == 0) : \
-		((cur)->bc_mp->m_bmap_dmxr[(lev) != 0])))
-#define XFS_BMAP_BLOCK_IMAXRECS(lev,cur) \
-	(((lev) == (cur)->bc_nlevels - 1 ? \
-			XFS_BTREE_BLOCK_MAXRECS(XFS_BMAP_RBLOCK_ISIZE(lev,cur),\
-				xfs_bmbt, (lev) == 0) : \
-			((cur)->bc_mp->m_bmap_dmxr[(lev) != 0])))
-
-#define XFS_BMAP_BLOCK_DMINRECS(lev,cur) \
-	(((lev) == (cur)->bc_nlevels - 1 ? \
-			XFS_BTREE_BLOCK_MINRECS(XFS_BMAP_RBLOCK_DSIZE(lev,cur),\
-				xfs_bmdr, (lev) == 0) : \
-			((cur)->bc_mp->m_bmap_dmnr[(lev) != 0])))
-#define XFS_BMAP_BLOCK_IMINRECS(lev,cur) \
-	(((lev) == (cur)->bc_nlevels - 1 ? \
-			XFS_BTREE_BLOCK_MINRECS(XFS_BMAP_RBLOCK_ISIZE(lev,cur),\
-				xfs_bmbt, (lev) == 0) : \
-			((cur)->bc_mp->m_bmap_dmnr[(lev) != 0])))
-
-#define XFS_BMAP_REC_DADDR(bb,i,cur)	(XFS_BTREE_REC_ADDR(xfs_bmbt, bb, i))
-
-#define XFS_BMAP_REC_IADDR(bb,i,cur)	(XFS_BTREE_REC_ADDR(xfs_bmbt, bb, i))
-
-#define XFS_BMAP_KEY_DADDR(bb,i,cur)	\
-	(XFS_BTREE_KEY_ADDR(xfs_bmbt, bb, i))
-
-#define XFS_BMAP_KEY_IADDR(bb,i,cur)	\
-	(XFS_BTREE_KEY_ADDR(xfs_bmbt, bb, i))
-
-#define XFS_BMAP_PTR_DADDR(bb,i,cur)	\
-	(XFS_BTREE_PTR_ADDR(xfs_bmbt, bb, i, XFS_BMAP_BLOCK_DMAXRECS(	\
-				be16_to_cpu((bb)->bb_level), cur)))
-#define XFS_BMAP_PTR_IADDR(bb,i,cur)	\
-	(XFS_BTREE_PTR_ADDR(xfs_bmbt, bb, i, XFS_BMAP_BLOCK_IMAXRECS(	\
-				be16_to_cpu((bb)->bb_level), cur)))
+/*
+ * Btree block header size depends on a superblock flag.
+ *
+ * (not quite yet, but soon)
+ */
+#define XFS_BMBT_BLOCK_LEN(mp)	XFS_BTREE_LBLOCK_LEN
+
+#define XFS_BMBT_REC_ADDR(mp, block, index) \
+	((xfs_bmbt_rec_t *) \
+		((char *)(block) + \
+		 XFS_BMBT_BLOCK_LEN(mp) + \
+		 ((index) - 1) * sizeof(xfs_bmbt_rec_t)))
+
+#define XFS_BMBT_KEY_ADDR(mp, block, index) \
+	((xfs_bmbt_key_t *) \
+		((char *)(block) + \
+		 XFS_BMBT_BLOCK_LEN(mp) + \
+		 ((index) - 1) * sizeof(xfs_bmbt_key_t)))
+
+#define XFS_BMBT_PTR_ADDR(mp, block, index, maxrecs) \
+	((xfs_bmbt_ptr_t *) \
+		((char *)(block) + \
+		 XFS_BMBT_BLOCK_LEN(mp) + \
+		 (maxrecs) * sizeof(xfs_bmbt_key_t) + \
+		 ((index) - 1) * sizeof(xfs_bmbt_ptr_t)))
+
+#define XFS_BMDR_REC_ADDR(block, index) \
+	((xfs_bmdr_rec_t *) \
+		((char *)(block) + \
+		 sizeof(struct xfs_bmdr_block) + \
+	         ((index) - 1) * sizeof(xfs_bmdr_rec_t)))
+
+#define XFS_BMDR_KEY_ADDR(block, index) \
+	((xfs_bmdr_key_t *) \
+		((char *)(block) + \
+		 sizeof(struct xfs_bmdr_block) + \
+		 ((index) - 1) * sizeof(xfs_bmdr_key_t)))
+
+#define XFS_BMDR_PTR_ADDR(block, index, maxrecs) \
+	((xfs_bmdr_ptr_t *) \
+		((char *)(block) + \
+		 sizeof(struct xfs_bmdr_block) + \
+		 (maxrecs) * sizeof(xfs_bmdr_key_t) + \
+		 ((index) - 1) * sizeof(xfs_bmdr_ptr_t)))
 
 /*
  * These are to be used when we know the size of the block and
  * we don't have a cursor.
  */
-#define XFS_BMAP_BROOT_REC_ADDR(bb,i,sz) \
-	(XFS_BTREE_REC_ADDR(xfs_bmbt,bb,i))
-#define XFS_BMAP_BROOT_KEY_ADDR(bb,i,sz) \
-	(XFS_BTREE_KEY_ADDR(xfs_bmbt,bb,i))
-#define XFS_BMAP_BROOT_PTR_ADDR(bb,i,sz) \
-	(XFS_BTREE_PTR_ADDR(xfs_bmbt,bb,i,XFS_BMAP_BROOT_MAXRECS(sz)))
-
-#define XFS_BMAP_BROOT_NUMRECS(bb)	be16_to_cpu((bb)->bb_numrecs)
-#define XFS_BMAP_BROOT_MAXRECS(sz)	XFS_BTREE_BLOCK_MAXRECS(sz,xfs_bmbt,0)
+#define XFS_BMAP_BROOT_PTR_ADDR(mp, bb, i, sz) \
+	XFS_BMBT_PTR_ADDR(mp, bb, i, xfs_bmbt_maxrecs(mp, sz, 0))
 
 #define XFS_BMAP_BROOT_SPACE_CALC(nrecs) \
-	(int)(sizeof(xfs_bmbt_block_t) + \
+	(int)(XFS_BTREE_LBLOCK_LEN + \
 	       ((nrecs) * (sizeof(xfs_bmbt_key_t) + sizeof(xfs_bmbt_ptr_t))))
 
 #define XFS_BMAP_BROOT_SPACE(bb) \
@@ -223,42 +213,12 @@ typedef struct xfs_btree_lblock xfs_bmbt_block_t;
  */
 #define XFS_BM_MAXLEVELS(mp,w)		((mp)->m_bm_maxlevels[(w)])
 
-#define XFS_BMAP_SANITY_CHECK(mp,bb,level) \
-	(be32_to_cpu((bb)->bb_magic) == XFS_BMAP_MAGIC && \
-	 be16_to_cpu((bb)->bb_level) == level && \
-	 be16_to_cpu((bb)->bb_numrecs) > 0 && \
-	 be16_to_cpu((bb)->bb_numrecs) <= (mp)->m_bmap_dmxr[(level) != 0])
-
-
-#ifdef __KERNEL__
-
-#if defined(XFS_BMBT_TRACE)
-/*
- * Trace buffer entry types.
- */
-#define XFS_BMBT_KTRACE_ARGBI	1
-#define XFS_BMBT_KTRACE_ARGBII	2
-#define XFS_BMBT_KTRACE_ARGFFFI 3
-#define XFS_BMBT_KTRACE_ARGI	4
-#define XFS_BMBT_KTRACE_ARGIFK	5
-#define XFS_BMBT_KTRACE_ARGIFR	6
-#define XFS_BMBT_KTRACE_ARGIK	7
-#define XFS_BMBT_KTRACE_CUR	8
-
-#define XFS_BMBT_TRACE_SIZE	4096	/* size of global trace buffer */
-#define XFS_BMBT_KTRACE_SIZE	32	/* size of per-inode trace buffer */
-extern ktrace_t	*xfs_bmbt_trace_buf;
-#endif
-
 /*
  * Prototypes for xfs_bmap.c to call.
  */
-extern void xfs_bmdr_to_bmbt(xfs_bmdr_block_t *, int, xfs_bmbt_block_t *, int);
-extern int xfs_bmbt_decrement(struct xfs_btree_cur *, int, int *);
-extern int xfs_bmbt_delete(struct xfs_btree_cur *, int *);
+extern void xfs_bmdr_to_bmbt(struct xfs_mount *, xfs_bmdr_block_t *, int,
+			struct xfs_btree_block *, int);
 extern void xfs_bmbt_get_all(xfs_bmbt_rec_host_t *r, xfs_bmbt_irec_t *s);
-extern xfs_bmbt_block_t *xfs_bmbt_get_block(struct xfs_btree_cur *cur,
-						int, struct xfs_buf **bpp);
 extern xfs_filblks_t xfs_bmbt_get_blockcount(xfs_bmbt_rec_host_t *r);
 extern xfs_fsblock_t xfs_bmbt_get_startblock(xfs_bmbt_rec_host_t *r);
 extern xfs_fileoff_t xfs_bmbt_get_startoff(xfs_bmbt_rec_host_t *r);
@@ -268,22 +228,6 @@ extern void xfs_bmbt_disk_get_all(xfs_bmbt_rec_t *r, xfs_bmbt_irec_t *s);
 extern xfs_filblks_t xfs_bmbt_disk_get_blockcount(xfs_bmbt_rec_t *r);
 extern xfs_fileoff_t xfs_bmbt_disk_get_startoff(xfs_bmbt_rec_t *r);
 
-extern int xfs_bmbt_increment(struct xfs_btree_cur *, int, int *);
-extern int xfs_bmbt_insert(struct xfs_btree_cur *, int *);
-extern void xfs_bmbt_log_block(struct xfs_btree_cur *, struct xfs_buf *, int);
-extern void xfs_bmbt_log_recs(struct xfs_btree_cur *, struct xfs_buf *, int,
-				int);
-extern int xfs_bmbt_lookup_eq(struct xfs_btree_cur *, xfs_fileoff_t,
-				xfs_fsblock_t, xfs_filblks_t, int *);
-extern int xfs_bmbt_lookup_ge(struct xfs_btree_cur *, xfs_fileoff_t,
-				xfs_fsblock_t, xfs_filblks_t, int *);
-
-/*
- * Give the bmap btree a new root block.  Copy the old broot contents
- * down into a real block and make the broot point to it.
- */
-extern int xfs_bmbt_newroot(struct xfs_btree_cur *cur, int *lflags, int *stat);
-
 extern void xfs_bmbt_set_all(xfs_bmbt_rec_host_t *r, xfs_bmbt_irec_t *s);
 extern void xfs_bmbt_set_allf(xfs_bmbt_rec_host_t *r, xfs_fileoff_t o,
 			xfs_fsblock_t b, xfs_filblks_t c, xfs_exntst_t v);
@@ -296,10 +240,15 @@ extern void xfs_bmbt_disk_set_all(xfs_bmbt_rec_t *r, xfs_bmbt_irec_t *s);
 extern void xfs_bmbt_disk_set_allf(xfs_bmbt_rec_t *r, xfs_fileoff_t o,
 			xfs_fsblock_t b, xfs_filblks_t c, xfs_exntst_t v);
 
-extern void xfs_bmbt_to_bmdr(xfs_bmbt_block_t *, int, xfs_bmdr_block_t *, int);
-extern int xfs_bmbt_update(struct xfs_btree_cur *, xfs_fileoff_t,
-				xfs_fsblock_t, xfs_filblks_t, xfs_exntst_t);
+extern void xfs_bmbt_to_bmdr(struct xfs_mount *, struct xfs_btree_block *, int,
+			xfs_bmdr_block_t *, int);
+
+extern int xfs_bmbt_get_maxrecs(struct xfs_btree_cur *, int level);
+extern int xfs_bmdr_maxrecs(struct xfs_mount *, int blocklen, int leaf);
+extern int xfs_bmbt_maxrecs(struct xfs_mount *, int blocklen, int leaf);
+
+extern struct xfs_btree_cur *xfs_bmbt_init_cursor(struct xfs_mount *,
+		struct xfs_trans *, struct xfs_inode *, int);
 
-#endif	/* __KERNEL__ */
 
 #endif	/* __XFS_BMAP_BTREE_H__ */
diff --git a/fs/xfs/xfs_btree.c b/fs/xfs/xfs_btree.c
index cc593a84c345..7ed59267420d 100644
--- a/fs/xfs/xfs_btree.c
+++ b/fs/xfs/xfs_btree.c
@@ -34,7 +34,9 @@
 #include "xfs_attr_sf.h"
 #include "xfs_dinode.h"
 #include "xfs_inode.h"
+#include "xfs_inode_item.h"
 #include "xfs_btree.h"
+#include "xfs_btree_trace.h"
 #include "xfs_ialloc.h"
 #include "xfs_error.h"
 
@@ -50,135 +52,33 @@ const __uint32_t xfs_magics[XFS_BTNUM_MAX] = {
 	XFS_ABTB_MAGIC, XFS_ABTC_MAGIC, XFS_BMAP_MAGIC, XFS_IBT_MAGIC
 };
 
-/*
- * Checking routine: return maxrecs for the block.
- */
-STATIC int				/* number of records fitting in block */
-xfs_btree_maxrecs(
-	xfs_btree_cur_t		*cur,	/* btree cursor */
-	xfs_btree_block_t	*block)	/* generic btree block pointer */
-{
-	switch (cur->bc_btnum) {
-	case XFS_BTNUM_BNO:
-	case XFS_BTNUM_CNT:
-		return (int)XFS_ALLOC_BLOCK_MAXRECS(
-				be16_to_cpu(block->bb_h.bb_level), cur);
-	case XFS_BTNUM_BMAP:
-		return (int)XFS_BMAP_BLOCK_IMAXRECS(
-				be16_to_cpu(block->bb_h.bb_level), cur);
-	case XFS_BTNUM_INO:
-		return (int)XFS_INOBT_BLOCK_MAXRECS(
-				be16_to_cpu(block->bb_h.bb_level), cur);
-	default:
-		ASSERT(0);
-		return 0;
-	}
-}
-
-/*
- * External routines.
- */
-
-#ifdef DEBUG
-/*
- * Debug routine: check that block header is ok.
- */
-void
-xfs_btree_check_block(
-	xfs_btree_cur_t		*cur,	/* btree cursor */
-	xfs_btree_block_t	*block,	/* generic btree block pointer */
-	int			level,	/* level of the btree block */
-	xfs_buf_t		*bp)	/* buffer containing block, if any */
-{
-	if (XFS_BTREE_LONG_PTRS(cur->bc_btnum))
-		xfs_btree_check_lblock(cur, (xfs_btree_lblock_t *)block, level,
-			bp);
-	else
-		xfs_btree_check_sblock(cur, (xfs_btree_sblock_t *)block, level,
-			bp);
-}
-
-/*
- * Debug routine: check that keys are in the right order.
- */
-void
-xfs_btree_check_key(
-	xfs_btnum_t	btnum,		/* btree identifier */
-	void		*ak1,		/* pointer to left (lower) key */
-	void		*ak2)		/* pointer to right (higher) key */
-{
-	switch (btnum) {
-	case XFS_BTNUM_BNO: {
-		xfs_alloc_key_t	*k1;
-		xfs_alloc_key_t	*k2;
-
-		k1 = ak1;
-		k2 = ak2;
-		ASSERT(be32_to_cpu(k1->ar_startblock) < be32_to_cpu(k2->ar_startblock));
-		break;
-	    }
-	case XFS_BTNUM_CNT: {
-		xfs_alloc_key_t	*k1;
-		xfs_alloc_key_t	*k2;
-
-		k1 = ak1;
-		k2 = ak2;
-		ASSERT(be32_to_cpu(k1->ar_blockcount) < be32_to_cpu(k2->ar_blockcount) ||
-		       (k1->ar_blockcount == k2->ar_blockcount &&
-			be32_to_cpu(k1->ar_startblock) < be32_to_cpu(k2->ar_startblock)));
-		break;
-	    }
-	case XFS_BTNUM_BMAP: {
-		xfs_bmbt_key_t	*k1;
-		xfs_bmbt_key_t	*k2;
-
-		k1 = ak1;
-		k2 = ak2;
-		ASSERT(be64_to_cpu(k1->br_startoff) < be64_to_cpu(k2->br_startoff));
-		break;
-	    }
-	case XFS_BTNUM_INO: {
-		xfs_inobt_key_t	*k1;
-		xfs_inobt_key_t	*k2;
-
-		k1 = ak1;
-		k2 = ak2;
-		ASSERT(be32_to_cpu(k1->ir_startino) < be32_to_cpu(k2->ir_startino));
-		break;
-	    }
-	default:
-		ASSERT(0);
-	}
-}
-#endif	/* DEBUG */
 
-/*
- * Checking routine: check that long form block header is ok.
- */
-/* ARGSUSED */
-int					/* error (0 or EFSCORRUPTED) */
+STATIC int				/* error (0 or EFSCORRUPTED) */
 xfs_btree_check_lblock(
-	xfs_btree_cur_t		*cur,	/* btree cursor */
-	xfs_btree_lblock_t	*block,	/* btree long form block pointer */
+	struct xfs_btree_cur	*cur,	/* btree cursor */
+	struct xfs_btree_block	*block,	/* btree long form block pointer */
 	int			level,	/* level of the btree block */
-	xfs_buf_t		*bp)	/* buffer for block, if any */
+	struct xfs_buf		*bp)	/* buffer for block, if any */
 {
 	int			lblock_ok; /* block passes checks */
-	xfs_mount_t		*mp;	/* file system mount point */
+	struct xfs_mount	*mp;	/* file system mount point */
 
 	mp = cur->bc_mp;
 	lblock_ok =
 		be32_to_cpu(block->bb_magic) == xfs_magics[cur->bc_btnum] &&
 		be16_to_cpu(block->bb_level) == level &&
 		be16_to_cpu(block->bb_numrecs) <=
-			xfs_btree_maxrecs(cur, (xfs_btree_block_t *)block) &&
-		block->bb_leftsib &&
-		(be64_to_cpu(block->bb_leftsib) == NULLDFSBNO ||
-		 XFS_FSB_SANITY_CHECK(mp, be64_to_cpu(block->bb_leftsib))) &&
-		block->bb_rightsib &&
-		(be64_to_cpu(block->bb_rightsib) == NULLDFSBNO ||
-		 XFS_FSB_SANITY_CHECK(mp, be64_to_cpu(block->bb_rightsib)));
-	if (unlikely(XFS_TEST_ERROR(!lblock_ok, mp, XFS_ERRTAG_BTREE_CHECK_LBLOCK,
+			cur->bc_ops->get_maxrecs(cur, level) &&
+		block->bb_u.l.bb_leftsib &&
+		(be64_to_cpu(block->bb_u.l.bb_leftsib) == NULLDFSBNO ||
+		 XFS_FSB_SANITY_CHECK(mp,
+		 	be64_to_cpu(block->bb_u.l.bb_leftsib))) &&
+		block->bb_u.l.bb_rightsib &&
+		(be64_to_cpu(block->bb_u.l.bb_rightsib) == NULLDFSBNO ||
+		 XFS_FSB_SANITY_CHECK(mp,
+		 	be64_to_cpu(block->bb_u.l.bb_rightsib)));
+	if (unlikely(XFS_TEST_ERROR(!lblock_ok, mp,
+			XFS_ERRTAG_BTREE_CHECK_LBLOCK,
 			XFS_RANDOM_BTREE_CHECK_LBLOCK))) {
 		if (bp)
 			xfs_buftrace("LBTREE ERROR", bp);
@@ -189,98 +89,15 @@ xfs_btree_check_lblock(
 	return 0;
 }
 
-/*
- * Checking routine: check that (long) pointer is ok.
- */
-int					/* error (0 or EFSCORRUPTED) */
-xfs_btree_check_lptr(
-	xfs_btree_cur_t	*cur,		/* btree cursor */
-	xfs_dfsbno_t	ptr,		/* btree block disk address */
-	int		level)		/* btree block level */
-{
-	xfs_mount_t	*mp;		/* file system mount point */
-
-	mp = cur->bc_mp;
-	XFS_WANT_CORRUPTED_RETURN(
-		level > 0 &&
-		ptr != NULLDFSBNO &&
-		XFS_FSB_SANITY_CHECK(mp, ptr));
-	return 0;
-}
-
-#ifdef DEBUG
-/*
- * Debug routine: check that records are in the right order.
- */
-void
-xfs_btree_check_rec(
-	xfs_btnum_t	btnum,		/* btree identifier */
-	void		*ar1,		/* pointer to left (lower) record */
-	void		*ar2)		/* pointer to right (higher) record */
-{
-	switch (btnum) {
-	case XFS_BTNUM_BNO: {
-		xfs_alloc_rec_t	*r1;
-		xfs_alloc_rec_t	*r2;
-
-		r1 = ar1;
-		r2 = ar2;
-		ASSERT(be32_to_cpu(r1->ar_startblock) +
-		       be32_to_cpu(r1->ar_blockcount) <=
-		       be32_to_cpu(r2->ar_startblock));
-		break;
-	    }
-	case XFS_BTNUM_CNT: {
-		xfs_alloc_rec_t	*r1;
-		xfs_alloc_rec_t	*r2;
-
-		r1 = ar1;
-		r2 = ar2;
-		ASSERT(be32_to_cpu(r1->ar_blockcount) < be32_to_cpu(r2->ar_blockcount) ||
-		       (r1->ar_blockcount == r2->ar_blockcount &&
-			be32_to_cpu(r1->ar_startblock) < be32_to_cpu(r2->ar_startblock)));
-		break;
-	    }
-	case XFS_BTNUM_BMAP: {
-		xfs_bmbt_rec_t	*r1;
-		xfs_bmbt_rec_t	*r2;
-
-		r1 = ar1;
-		r2 = ar2;
-		ASSERT(xfs_bmbt_disk_get_startoff(r1) +
-		       xfs_bmbt_disk_get_blockcount(r1) <=
-		       xfs_bmbt_disk_get_startoff(r2));
-		break;
-	    }
-	case XFS_BTNUM_INO: {
-		xfs_inobt_rec_t	*r1;
-		xfs_inobt_rec_t	*r2;
-
-		r1 = ar1;
-		r2 = ar2;
-		ASSERT(be32_to_cpu(r1->ir_startino) + XFS_INODES_PER_CHUNK <=
-		       be32_to_cpu(r2->ir_startino));
-		break;
-	    }
-	default:
-		ASSERT(0);
-	}
-}
-#endif	/* DEBUG */
-
-/*
- * Checking routine: check that block header is ok.
- */
-/* ARGSUSED */
-int					/* error (0 or EFSCORRUPTED) */
+STATIC int				/* error (0 or EFSCORRUPTED) */
 xfs_btree_check_sblock(
-	xfs_btree_cur_t		*cur,	/* btree cursor */
-	xfs_btree_sblock_t	*block,	/* btree short form block pointer */
+	struct xfs_btree_cur	*cur,	/* btree cursor */
+	struct xfs_btree_block	*block,	/* btree short form block pointer */
 	int			level,	/* level of the btree block */
-	xfs_buf_t		*bp)	/* buffer containing block */
+	struct xfs_buf		*bp)	/* buffer containing block */
 {
-	xfs_buf_t		*agbp;	/* buffer for ag. freespace struct */
-	xfs_agf_t		*agf;	/* ag. freespace structure */
+	struct xfs_buf		*agbp;	/* buffer for ag. freespace struct */
+	struct xfs_agf		*agf;	/* ag. freespace structure */
 	xfs_agblock_t		agflen;	/* native ag. freespace length */
 	int			sblock_ok; /* block passes checks */
 
@@ -291,13 +108,13 @@ xfs_btree_check_sblock(
 		be32_to_cpu(block->bb_magic) == xfs_magics[cur->bc_btnum] &&
 		be16_to_cpu(block->bb_level) == level &&
 		be16_to_cpu(block->bb_numrecs) <=
-			xfs_btree_maxrecs(cur, (xfs_btree_block_t *)block) &&
-		(be32_to_cpu(block->bb_leftsib) == NULLAGBLOCK ||
-		 be32_to_cpu(block->bb_leftsib) < agflen) &&
-		block->bb_leftsib &&
-		(be32_to_cpu(block->bb_rightsib) == NULLAGBLOCK ||
-		 be32_to_cpu(block->bb_rightsib) < agflen) &&
-		block->bb_rightsib;
+			cur->bc_ops->get_maxrecs(cur, level) &&
+		(be32_to_cpu(block->bb_u.s.bb_leftsib) == NULLAGBLOCK ||
+		 be32_to_cpu(block->bb_u.s.bb_leftsib) < agflen) &&
+		block->bb_u.s.bb_leftsib &&
+		(be32_to_cpu(block->bb_u.s.bb_rightsib) == NULLAGBLOCK ||
+		 be32_to_cpu(block->bb_u.s.bb_rightsib) < agflen) &&
+		block->bb_u.s.bb_rightsib;
 	if (unlikely(XFS_TEST_ERROR(!sblock_ok, cur->bc_mp,
 			XFS_ERRTAG_BTREE_CHECK_SBLOCK,
 			XFS_RANDOM_BTREE_CHECK_SBLOCK))) {
@@ -311,27 +128,78 @@ xfs_btree_check_sblock(
 }
 
 /*
- * Checking routine: check that (short) pointer is ok.
+ * Debug routine: check that block header is ok.
+ */
+int
+xfs_btree_check_block(
+	struct xfs_btree_cur	*cur,	/* btree cursor */
+	struct xfs_btree_block	*block,	/* generic btree block pointer */
+	int			level,	/* level of the btree block */
+	struct xfs_buf		*bp)	/* buffer containing block, if any */
+{
+	if (cur->bc_flags & XFS_BTREE_LONG_PTRS)
+		return xfs_btree_check_lblock(cur, block, level, bp);
+	else
+		return xfs_btree_check_sblock(cur, block, level, bp);
+}
+
+/*
+ * Check that (long) pointer is ok.
  */
 int					/* error (0 or EFSCORRUPTED) */
+xfs_btree_check_lptr(
+	struct xfs_btree_cur	*cur,	/* btree cursor */
+	xfs_dfsbno_t		bno,	/* btree block disk address */
+	int			level)	/* btree block level */
+{
+	XFS_WANT_CORRUPTED_RETURN(
+		level > 0 &&
+		bno != NULLDFSBNO &&
+		XFS_FSB_SANITY_CHECK(cur->bc_mp, bno));
+	return 0;
+}
+
+#ifdef DEBUG
+/*
+ * Check that (short) pointer is ok.
+ */
+STATIC int				/* error (0 or EFSCORRUPTED) */
 xfs_btree_check_sptr(
-	xfs_btree_cur_t	*cur,		/* btree cursor */
-	xfs_agblock_t	ptr,		/* btree block disk address */
-	int		level)		/* btree block level */
+	struct xfs_btree_cur	*cur,	/* btree cursor */
+	xfs_agblock_t		bno,	/* btree block disk address */
+	int			level)	/* btree block level */
 {
-	xfs_buf_t	*agbp;		/* buffer for ag. freespace struct */
-	xfs_agf_t	*agf;		/* ag. freespace structure */
+	xfs_agblock_t		agblocks = cur->bc_mp->m_sb.sb_agblocks;
 
-	agbp = cur->bc_private.a.agbp;
-	agf = XFS_BUF_TO_AGF(agbp);
 	XFS_WANT_CORRUPTED_RETURN(
 		level > 0 &&
-		ptr != NULLAGBLOCK && ptr != 0 &&
-		ptr < be32_to_cpu(agf->agf_length));
+		bno != NULLAGBLOCK &&
+		bno != 0 &&
+		bno < agblocks);
 	return 0;
 }
 
 /*
+ * Check that block ptr is ok.
+ */
+STATIC int				/* error (0 or EFSCORRUPTED) */
+xfs_btree_check_ptr(
+	struct xfs_btree_cur	*cur,	/* btree cursor */
+	union xfs_btree_ptr	*ptr,	/* btree block disk address */
+	int			index,	/* offset from ptr to check */
+	int			level)	/* btree block level */
+{
+	if (cur->bc_flags & XFS_BTREE_LONG_PTRS) {
+		return xfs_btree_check_lptr(cur,
+				be64_to_cpu((&ptr->l)[index]), level);
+	} else {
+		return xfs_btree_check_sptr(cur,
+				be32_to_cpu((&ptr->s)[index]), level);
+	}
+}
+#endif
+
+/*
  * Delete the btree cursor.
  */
 void
@@ -387,16 +255,17 @@ xfs_btree_dup_cursor(
 
 	tp = cur->bc_tp;
 	mp = cur->bc_mp;
+
 	/*
 	 * Allocate a new cursor like the old one.
 	 */
-	new = xfs_btree_init_cursor(mp, tp, cur->bc_private.a.agbp,
-		cur->bc_private.a.agno, cur->bc_btnum, cur->bc_private.b.ip,
-		cur->bc_private.b.whichfork);
+	new = cur->bc_ops->dup_cursor(cur);
+
 	/*
 	 * Copy the record currently in the cursor.
 	 */
 	new->bc_rec = cur->bc_rec;
+
 	/*
 	 * For each level current, re-get the buffer and copy the ptr value.
 	 */
@@ -416,46 +285,174 @@ xfs_btree_dup_cursor(
 		} else
 			new->bc_bufs[i] = NULL;
 	}
-	/*
-	 * For bmap btrees, copy the firstblock, flist, and flags values,
-	 * since init cursor doesn't get them.
-	 */
-	if (new->bc_btnum == XFS_BTNUM_BMAP) {
-		new->bc_private.b.firstblock = cur->bc_private.b.firstblock;
-		new->bc_private.b.flist = cur->bc_private.b.flist;
-		new->bc_private.b.flags = cur->bc_private.b.flags;
-	}
 	*ncur = new;
 	return 0;
 }
 
 /*
+ * XFS btree block layout and addressing:
+ *
+ * There are two types of blocks in the btree: leaf and non-leaf blocks.
+ *
+ * The leaf record start with a header then followed by records containing
+ * the values.  A non-leaf block also starts with the same header, and
+ * then first contains lookup keys followed by an equal number of pointers
+ * to the btree blocks at the previous level.
+ *
+ *		+--------+-------+-------+-------+-------+-------+-------+
+ * Leaf:	| header | rec 1 | rec 2 | rec 3 | rec 4 | rec 5 | rec N |
+ *		+--------+-------+-------+-------+-------+-------+-------+
+ *
+ *		+--------+-------+-------+-------+-------+-------+-------+
+ * Non-Leaf:	| header | key 1 | key 2 | key N | ptr 1 | ptr 2 | ptr N |
+ *		+--------+-------+-------+-------+-------+-------+-------+
+ *
+ * The header is called struct xfs_btree_block for reasons better left unknown
+ * and comes in different versions for short (32bit) and long (64bit) block
+ * pointers.  The record and key structures are defined by the btree instances
+ * and opaque to the btree core.  The block pointers are simple disk endian
+ * integers, available in a short (32bit) and long (64bit) variant.
+ *
+ * The helpers below calculate the offset of a given record, key or pointer
+ * into a btree block (xfs_btree_*_offset) or return a pointer to the given
+ * record, key or pointer (xfs_btree_*_addr).  Note that all addressing
+ * inside the btree block is done using indices starting at one, not zero!
+ */
+
+/*
+ * Return size of the btree block header for this btree instance.
+ */
+static inline size_t xfs_btree_block_len(struct xfs_btree_cur *cur)
+{
+	return (cur->bc_flags & XFS_BTREE_LONG_PTRS) ?
+		XFS_BTREE_LBLOCK_LEN :
+		XFS_BTREE_SBLOCK_LEN;
+}
+
+/*
+ * Return size of btree block pointers for this btree instance.
+ */
+static inline size_t xfs_btree_ptr_len(struct xfs_btree_cur *cur)
+{
+	return (cur->bc_flags & XFS_BTREE_LONG_PTRS) ?
+		sizeof(__be64) : sizeof(__be32);
+}
+
+/*
+ * Calculate offset of the n-th record in a btree block.
+ */
+STATIC size_t
+xfs_btree_rec_offset(
+	struct xfs_btree_cur	*cur,
+	int			n)
+{
+	return xfs_btree_block_len(cur) +
+		(n - 1) * cur->bc_ops->rec_len;
+}
+
+/*
+ * Calculate offset of the n-th key in a btree block.
+ */
+STATIC size_t
+xfs_btree_key_offset(
+	struct xfs_btree_cur	*cur,
+	int			n)
+{
+	return xfs_btree_block_len(cur) +
+		(n - 1) * cur->bc_ops->key_len;
+}
+
+/*
+ * Calculate offset of the n-th block pointer in a btree block.
+ */
+STATIC size_t
+xfs_btree_ptr_offset(
+	struct xfs_btree_cur	*cur,
+	int			n,
+	int			level)
+{
+	return xfs_btree_block_len(cur) +
+		cur->bc_ops->get_maxrecs(cur, level) * cur->bc_ops->key_len +
+		(n - 1) * xfs_btree_ptr_len(cur);
+}
+
+/*
+ * Return a pointer to the n-th record in the btree block.
+ */
+STATIC union xfs_btree_rec *
+xfs_btree_rec_addr(
+	struct xfs_btree_cur	*cur,
+	int			n,
+	struct xfs_btree_block	*block)
+{
+	return (union xfs_btree_rec *)
+		((char *)block + xfs_btree_rec_offset(cur, n));
+}
+
+/*
+ * Return a pointer to the n-th key in the btree block.
+ */
+STATIC union xfs_btree_key *
+xfs_btree_key_addr(
+	struct xfs_btree_cur	*cur,
+	int			n,
+	struct xfs_btree_block	*block)
+{
+	return (union xfs_btree_key *)
+		((char *)block + xfs_btree_key_offset(cur, n));
+}
+
+/*
+ * Return a pointer to the n-th block pointer in the btree block.
+ */
+STATIC union xfs_btree_ptr *
+xfs_btree_ptr_addr(
+	struct xfs_btree_cur	*cur,
+	int			n,
+	struct xfs_btree_block	*block)
+{
+	int			level = xfs_btree_get_level(block);
+
+	ASSERT(block->bb_level != 0);
+
+	return (union xfs_btree_ptr *)
+		((char *)block + xfs_btree_ptr_offset(cur, n, level));
+}
+
+/*
+ * Get a the root block which is stored in the inode.
+ *
+ * For now this btree implementation assumes the btree root is always
+ * stored in the if_broot field of an inode fork.
+ */
+STATIC struct xfs_btree_block *
+xfs_btree_get_iroot(
+       struct xfs_btree_cur    *cur)
+{
+       struct xfs_ifork        *ifp;
+
+       ifp = XFS_IFORK_PTR(cur->bc_private.b.ip, cur->bc_private.b.whichfork);
+       return (struct xfs_btree_block *)ifp->if_broot;
+}
+
+/*
  * Retrieve the block pointer from the cursor at the given level.
- * This may be a bmap btree root or from a buffer.
+ * This may be an inode btree root or from a buffer.
  */
-STATIC xfs_btree_block_t *		/* generic btree block pointer */
+STATIC struct xfs_btree_block *		/* generic btree block pointer */
 xfs_btree_get_block(
-	xfs_btree_cur_t		*cur,	/* btree cursor */
+	struct xfs_btree_cur	*cur,	/* btree cursor */
 	int			level,	/* level in btree */
-	xfs_buf_t		**bpp)	/* buffer containing the block */
-{
-	xfs_btree_block_t	*block;	/* return value */
-	xfs_buf_t		*bp;	/* return buffer */
-	xfs_ifork_t		*ifp;	/* inode fork pointer */
-	int			whichfork; /* data or attr fork */
-
-	if (cur->bc_btnum == XFS_BTNUM_BMAP && level == cur->bc_nlevels - 1) {
-		whichfork = cur->bc_private.b.whichfork;
-		ifp = XFS_IFORK_PTR(cur->bc_private.b.ip, whichfork);
-		block = (xfs_btree_block_t *)ifp->if_broot;
-		bp = NULL;
-	} else {
-		bp = cur->bc_bufs[level];
-		block = XFS_BUF_TO_BLOCK(bp);
+	struct xfs_buf		**bpp)	/* buffer containing the block */
+{
+	if ((cur->bc_flags & XFS_BTREE_ROOT_IN_INODE) &&
+	    (level == cur->bc_nlevels - 1)) {
+		*bpp = NULL;
+		return xfs_btree_get_iroot(cur);
 	}
-	ASSERT(block != NULL);
-	*bpp = bp;
-	return block;
+
+	*bpp = cur->bc_bufs[level];
+	return XFS_BUF_TO_BLOCK(*bpp);
 }
 
 /*
@@ -505,97 +502,6 @@ xfs_btree_get_bufs(
 }
 
 /*
- * Allocate a new btree cursor.
- * The cursor is either for allocation (A) or bmap (B) or inodes (I).
- */
-xfs_btree_cur_t *			/* new btree cursor */
-xfs_btree_init_cursor(
-	xfs_mount_t	*mp,		/* file system mount point */
-	xfs_trans_t	*tp,		/* transaction pointer */
-	xfs_buf_t	*agbp,		/* (A only) buffer for agf structure */
-					/* (I only) buffer for agi structure */
-	xfs_agnumber_t	agno,		/* (AI only) allocation group number */
-	xfs_btnum_t	btnum,		/* btree identifier */
-	xfs_inode_t	*ip,		/* (B only) inode owning the btree */
-	int		whichfork)	/* (B only) data or attr fork */
-{
-	xfs_agf_t	*agf;		/* (A) allocation group freespace */
-	xfs_agi_t	*agi;		/* (I) allocation group inodespace */
-	xfs_btree_cur_t	*cur;		/* return value */
-	xfs_ifork_t	*ifp;		/* (I) inode fork pointer */
-	int		nlevels=0;	/* number of levels in the btree */
-
-	ASSERT(xfs_btree_cur_zone != NULL);
-	/*
-	 * Allocate a new cursor.
-	 */
-	cur = kmem_zone_zalloc(xfs_btree_cur_zone, KM_SLEEP);
-	/*
-	 * Deduce the number of btree levels from the arguments.
-	 */
-	switch (btnum) {
-	case XFS_BTNUM_BNO:
-	case XFS_BTNUM_CNT:
-		agf = XFS_BUF_TO_AGF(agbp);
-		nlevels = be32_to_cpu(agf->agf_levels[btnum]);
-		break;
-	case XFS_BTNUM_BMAP:
-		ifp = XFS_IFORK_PTR(ip, whichfork);
-		nlevels = be16_to_cpu(ifp->if_broot->bb_level) + 1;
-		break;
-	case XFS_BTNUM_INO:
-		agi = XFS_BUF_TO_AGI(agbp);
-		nlevels = be32_to_cpu(agi->agi_level);
-		break;
-	default:
-		ASSERT(0);
-	}
-	/*
-	 * Fill in the common fields.
-	 */
-	cur->bc_tp = tp;
-	cur->bc_mp = mp;
-	cur->bc_nlevels = nlevels;
-	cur->bc_btnum = btnum;
-	cur->bc_blocklog = mp->m_sb.sb_blocklog;
-	/*
-	 * Fill in private fields.
-	 */
-	switch (btnum) {
-	case XFS_BTNUM_BNO:
-	case XFS_BTNUM_CNT:
-		/*
-		 * Allocation btree fields.
-		 */
-		cur->bc_private.a.agbp = agbp;
-		cur->bc_private.a.agno = agno;
-		break;
-	case XFS_BTNUM_INO:
-		/*
-		 * Inode allocation btree fields.
-		 */
-		cur->bc_private.a.agbp = agbp;
-		cur->bc_private.a.agno = agno;
-		break;
-	case XFS_BTNUM_BMAP:
-		/*
-		 * Bmap btree fields.
-		 */
-		cur->bc_private.b.forksize = XFS_IFORK_SIZE(ip, whichfork);
-		cur->bc_private.b.ip = ip;
-		cur->bc_private.b.firstblock = NULLFSBLOCK;
-		cur->bc_private.b.flist = NULL;
-		cur->bc_private.b.allocated = 0;
-		cur->bc_private.b.flags = 0;
-		cur->bc_private.b.whichfork = whichfork;
-		break;
-	default:
-		ASSERT(0);
-	}
-	return cur;
-}
-
-/*
  * Check for the cursor referring to the last block at the given level.
  */
 int					/* 1=is last block, 0=not last block */
@@ -603,12 +509,12 @@ xfs_btree_islastblock(
 	xfs_btree_cur_t		*cur,	/* btree cursor */
 	int			level)	/* level to check */
 {
-	xfs_btree_block_t	*block;	/* generic btree block pointer */
+	struct xfs_btree_block	*block;	/* generic btree block pointer */
 	xfs_buf_t		*bp;	/* buffer containing block */
 
 	block = xfs_btree_get_block(cur, level, &bp);
 	xfs_btree_check_block(cur, block, level, bp);
-	if (XFS_BTREE_LONG_PTRS(cur->bc_btnum))
+	if (cur->bc_flags & XFS_BTREE_LONG_PTRS)
 		return be64_to_cpu(block->bb_u.l.bb_rightsib) == NULLDFSBNO;
 	else
 		return be32_to_cpu(block->bb_u.s.bb_rightsib) == NULLAGBLOCK;
@@ -618,12 +524,12 @@ xfs_btree_islastblock(
  * Change the cursor to point to the first record at the given level.
  * Other levels are unaffected.
  */
-int					/* success=1, failure=0 */
+STATIC int				/* success=1, failure=0 */
 xfs_btree_firstrec(
 	xfs_btree_cur_t		*cur,	/* btree cursor */
 	int			level)	/* level to change */
 {
-	xfs_btree_block_t	*block;	/* generic btree block pointer */
+	struct xfs_btree_block	*block;	/* generic btree block pointer */
 	xfs_buf_t		*bp;	/* buffer containing block */
 
 	/*
@@ -634,7 +540,7 @@ xfs_btree_firstrec(
 	/*
 	 * It's empty, there is no such record.
 	 */
-	if (!block->bb_h.bb_numrecs)
+	if (!block->bb_numrecs)
 		return 0;
 	/*
 	 * Set the ptr value to 1, that's the first record/key.
@@ -647,12 +553,12 @@ xfs_btree_firstrec(
  * Change the cursor to point to the last record in the current block
  * at the given level.  Other levels are unaffected.
  */
-int					/* success=1, failure=0 */
+STATIC int				/* success=1, failure=0 */
 xfs_btree_lastrec(
 	xfs_btree_cur_t		*cur,	/* btree cursor */
 	int			level)	/* level to change */
 {
-	xfs_btree_block_t	*block;	/* generic btree block pointer */
+	struct xfs_btree_block	*block;	/* generic btree block pointer */
 	xfs_buf_t		*bp;	/* buffer containing block */
 
 	/*
@@ -663,12 +569,12 @@ xfs_btree_lastrec(
 	/*
 	 * It's empty, there is no such record.
 	 */
-	if (!block->bb_h.bb_numrecs)
+	if (!block->bb_numrecs)
 		return 0;
 	/*
 	 * Set the ptr value to numrecs, that's the last record/key.
 	 */
-	cur->bc_ptrs[level] = be16_to_cpu(block->bb_h.bb_numrecs);
+	cur->bc_ptrs[level] = be16_to_cpu(block->bb_numrecs);
 	return 1;
 }
 
@@ -817,66 +723,84 @@ xfs_btree_reada_bufs(
 	xfs_baread(mp->m_ddev_targp, d, mp->m_bsize * count);
 }
 
+STATIC int
+xfs_btree_readahead_lblock(
+	struct xfs_btree_cur	*cur,
+	int			lr,
+	struct xfs_btree_block	*block)
+{
+	int			rval = 0;
+	xfs_fsblock_t		left = be64_to_cpu(block->bb_u.l.bb_leftsib);
+	xfs_fsblock_t		right = be64_to_cpu(block->bb_u.l.bb_rightsib);
+
+	if ((lr & XFS_BTCUR_LEFTRA) && left != NULLDFSBNO) {
+		xfs_btree_reada_bufl(cur->bc_mp, left, 1);
+		rval++;
+	}
+
+	if ((lr & XFS_BTCUR_RIGHTRA) && right != NULLDFSBNO) {
+		xfs_btree_reada_bufl(cur->bc_mp, right, 1);
+		rval++;
+	}
+
+	return rval;
+}
+
+STATIC int
+xfs_btree_readahead_sblock(
+	struct xfs_btree_cur	*cur,
+	int			lr,
+	struct xfs_btree_block *block)
+{
+	int			rval = 0;
+	xfs_agblock_t		left = be32_to_cpu(block->bb_u.s.bb_leftsib);
+	xfs_agblock_t		right = be32_to_cpu(block->bb_u.s.bb_rightsib);
+
+
+	if ((lr & XFS_BTCUR_LEFTRA) && left != NULLAGBLOCK) {
+		xfs_btree_reada_bufs(cur->bc_mp, cur->bc_private.a.agno,
+				     left, 1);
+		rval++;
+	}
+
+	if ((lr & XFS_BTCUR_RIGHTRA) && right != NULLAGBLOCK) {
+		xfs_btree_reada_bufs(cur->bc_mp, cur->bc_private.a.agno,
+				     right, 1);
+		rval++;
+	}
+
+	return rval;
+}
+
 /*
  * Read-ahead btree blocks, at the given level.
  * Bits in lr are set from XFS_BTCUR_{LEFT,RIGHT}RA.
  */
-int
-xfs_btree_readahead_core(
-	xfs_btree_cur_t		*cur,		/* btree cursor */
+STATIC int
+xfs_btree_readahead(
+	struct xfs_btree_cur	*cur,		/* btree cursor */
 	int			lev,		/* level in btree */
 	int			lr)		/* left/right bits */
 {
-	xfs_alloc_block_t	*a;
-	xfs_bmbt_block_t	*b;
-	xfs_inobt_block_t	*i;
-	int			rval = 0;
+	struct xfs_btree_block	*block;
+
+	/*
+	 * No readahead needed if we are at the root level and the
+	 * btree root is stored in the inode.
+	 */
+	if ((cur->bc_flags & XFS_BTREE_ROOT_IN_INODE) &&
+	    (lev == cur->bc_nlevels - 1))
+		return 0;
+
+	if ((cur->bc_ra[lev] | lr) == cur->bc_ra[lev])
+		return 0;
 
-	ASSERT(cur->bc_bufs[lev] != NULL);
 	cur->bc_ra[lev] |= lr;
-	switch (cur->bc_btnum) {
-	case XFS_BTNUM_BNO:
-	case XFS_BTNUM_CNT:
-		a = XFS_BUF_TO_ALLOC_BLOCK(cur->bc_bufs[lev]);
-		if ((lr & XFS_BTCUR_LEFTRA) && be32_to_cpu(a->bb_leftsib) != NULLAGBLOCK) {
-			xfs_btree_reada_bufs(cur->bc_mp, cur->bc_private.a.agno,
-				be32_to_cpu(a->bb_leftsib), 1);
-			rval++;
-		}
-		if ((lr & XFS_BTCUR_RIGHTRA) && be32_to_cpu(a->bb_rightsib) != NULLAGBLOCK) {
-			xfs_btree_reada_bufs(cur->bc_mp, cur->bc_private.a.agno,
-				be32_to_cpu(a->bb_rightsib), 1);
-			rval++;
-		}
-		break;
-	case XFS_BTNUM_BMAP:
-		b = XFS_BUF_TO_BMBT_BLOCK(cur->bc_bufs[lev]);
-		if ((lr & XFS_BTCUR_LEFTRA) && be64_to_cpu(b->bb_leftsib) != NULLDFSBNO) {
-			xfs_btree_reada_bufl(cur->bc_mp, be64_to_cpu(b->bb_leftsib), 1);
-			rval++;
-		}
-		if ((lr & XFS_BTCUR_RIGHTRA) && be64_to_cpu(b->bb_rightsib) != NULLDFSBNO) {
-			xfs_btree_reada_bufl(cur->bc_mp, be64_to_cpu(b->bb_rightsib), 1);
-			rval++;
-		}
-		break;
-	case XFS_BTNUM_INO:
-		i = XFS_BUF_TO_INOBT_BLOCK(cur->bc_bufs[lev]);
-		if ((lr & XFS_BTCUR_LEFTRA) && be32_to_cpu(i->bb_leftsib) != NULLAGBLOCK) {
-			xfs_btree_reada_bufs(cur->bc_mp, cur->bc_private.a.agno,
-				be32_to_cpu(i->bb_leftsib), 1);
-			rval++;
-		}
-		if ((lr & XFS_BTCUR_RIGHTRA) && be32_to_cpu(i->bb_rightsib) != NULLAGBLOCK) {
-			xfs_btree_reada_bufs(cur->bc_mp, cur->bc_private.a.agno,
-				be32_to_cpu(i->bb_rightsib), 1);
-			rval++;
-		}
-		break;
-	default:
-		ASSERT(0);
-	}
-	return rval;
+	block = XFS_BUF_TO_BLOCK(cur->bc_bufs[lev]);
+
+	if (cur->bc_flags & XFS_BTREE_LONG_PTRS)
+		return xfs_btree_readahead_lblock(cur, lr, block);
+	return xfs_btree_readahead_sblock(cur, lr, block);
 }
 
 /*
@@ -889,7 +813,7 @@ xfs_btree_setbuf(
 	int			lev,	/* level in btree */
 	xfs_buf_t		*bp)	/* new buffer to set */
 {
-	xfs_btree_block_t	*b;	/* btree block */
+	struct xfs_btree_block	*b;	/* btree block */
 	xfs_buf_t		*obp;	/* old buffer pointer */
 
 	obp = cur->bc_bufs[lev];
@@ -900,7 +824,7 @@ xfs_btree_setbuf(
 	if (!bp)
 		return;
 	b = XFS_BUF_TO_BLOCK(bp);
-	if (XFS_BTREE_LONG_PTRS(cur->bc_btnum)) {
+	if (cur->bc_flags & XFS_BTREE_LONG_PTRS) {
 		if (be64_to_cpu(b->bb_u.l.bb_leftsib) == NULLDFSBNO)
 			cur->bc_ra[lev] |= XFS_BTCUR_LEFTRA;
 		if (be64_to_cpu(b->bb_u.l.bb_rightsib) == NULLDFSBNO)
@@ -912,3 +836,2855 @@ xfs_btree_setbuf(
 			cur->bc_ra[lev] |= XFS_BTCUR_RIGHTRA;
 	}
 }
+
+STATIC int
+xfs_btree_ptr_is_null(
+	struct xfs_btree_cur	*cur,
+	union xfs_btree_ptr	*ptr)
+{
+	if (cur->bc_flags & XFS_BTREE_LONG_PTRS)
+		return be64_to_cpu(ptr->l) == NULLFSBLOCK;
+	else
+		return be32_to_cpu(ptr->s) == NULLAGBLOCK;
+}
+
+STATIC void
+xfs_btree_set_ptr_null(
+	struct xfs_btree_cur	*cur,
+	union xfs_btree_ptr	*ptr)
+{
+	if (cur->bc_flags & XFS_BTREE_LONG_PTRS)
+		ptr->l = cpu_to_be64(NULLFSBLOCK);
+	else
+		ptr->s = cpu_to_be32(NULLAGBLOCK);
+}
+
+/*
+ * Get/set/init sibling pointers
+ */
+STATIC void
+xfs_btree_get_sibling(
+	struct xfs_btree_cur	*cur,
+	struct xfs_btree_block	*block,
+	union xfs_btree_ptr	*ptr,
+	int			lr)
+{
+	ASSERT(lr == XFS_BB_LEFTSIB || lr == XFS_BB_RIGHTSIB);
+
+	if (cur->bc_flags & XFS_BTREE_LONG_PTRS) {
+		if (lr == XFS_BB_RIGHTSIB)
+			ptr->l = block->bb_u.l.bb_rightsib;
+		else
+			ptr->l = block->bb_u.l.bb_leftsib;
+	} else {
+		if (lr == XFS_BB_RIGHTSIB)
+			ptr->s = block->bb_u.s.bb_rightsib;
+		else
+			ptr->s = block->bb_u.s.bb_leftsib;
+	}
+}
+
+STATIC void
+xfs_btree_set_sibling(
+	struct xfs_btree_cur	*cur,
+	struct xfs_btree_block	*block,
+	union xfs_btree_ptr	*ptr,
+	int			lr)
+{
+	ASSERT(lr == XFS_BB_LEFTSIB || lr == XFS_BB_RIGHTSIB);
+
+	if (cur->bc_flags & XFS_BTREE_LONG_PTRS) {
+		if (lr == XFS_BB_RIGHTSIB)
+			block->bb_u.l.bb_rightsib = ptr->l;
+		else
+			block->bb_u.l.bb_leftsib = ptr->l;
+	} else {
+		if (lr == XFS_BB_RIGHTSIB)
+			block->bb_u.s.bb_rightsib = ptr->s;
+		else
+			block->bb_u.s.bb_leftsib = ptr->s;
+	}
+}
+
+STATIC void
+xfs_btree_init_block(
+	struct xfs_btree_cur	*cur,
+	int			level,
+	int			numrecs,
+	struct xfs_btree_block	*new)	/* new block */
+{
+	new->bb_magic = cpu_to_be32(xfs_magics[cur->bc_btnum]);
+	new->bb_level = cpu_to_be16(level);
+	new->bb_numrecs = cpu_to_be16(numrecs);
+
+	if (cur->bc_flags & XFS_BTREE_LONG_PTRS) {
+		new->bb_u.l.bb_leftsib = cpu_to_be64(NULLFSBLOCK);
+		new->bb_u.l.bb_rightsib = cpu_to_be64(NULLFSBLOCK);
+	} else {
+		new->bb_u.s.bb_leftsib = cpu_to_be32(NULLAGBLOCK);
+		new->bb_u.s.bb_rightsib = cpu_to_be32(NULLAGBLOCK);
+	}
+}
+
+/*
+ * Return true if ptr is the last record in the btree and
+ * we need to track updateѕ to this record.  The decision
+ * will be further refined in the update_lastrec method.
+ */
+STATIC int
+xfs_btree_is_lastrec(
+	struct xfs_btree_cur	*cur,
+	struct xfs_btree_block	*block,
+	int			level)
+{
+	union xfs_btree_ptr	ptr;
+
+	if (level > 0)
+		return 0;
+	if (!(cur->bc_flags & XFS_BTREE_LASTREC_UPDATE))
+		return 0;
+
+	xfs_btree_get_sibling(cur, block, &ptr, XFS_BB_RIGHTSIB);
+	if (!xfs_btree_ptr_is_null(cur, &ptr))
+		return 0;
+	return 1;
+}
+
+STATIC void
+xfs_btree_buf_to_ptr(
+	struct xfs_btree_cur	*cur,
+	struct xfs_buf		*bp,
+	union xfs_btree_ptr	*ptr)
+{
+	if (cur->bc_flags & XFS_BTREE_LONG_PTRS)
+		ptr->l = cpu_to_be64(XFS_DADDR_TO_FSB(cur->bc_mp,
+					XFS_BUF_ADDR(bp)));
+	else {
+		ptr->s = cpu_to_be32(XFS_DADDR_TO_AGBNO(cur->bc_mp,
+					XFS_BUF_ADDR(bp)));
+	}
+}
+
+STATIC xfs_daddr_t
+xfs_btree_ptr_to_daddr(
+	struct xfs_btree_cur	*cur,
+	union xfs_btree_ptr	*ptr)
+{
+	if (cur->bc_flags & XFS_BTREE_LONG_PTRS) {
+		ASSERT(be64_to_cpu(ptr->l) != NULLFSBLOCK);
+
+		return XFS_FSB_TO_DADDR(cur->bc_mp, be64_to_cpu(ptr->l));
+	} else {
+		ASSERT(cur->bc_private.a.agno != NULLAGNUMBER);
+		ASSERT(be32_to_cpu(ptr->s) != NULLAGBLOCK);
+
+		return XFS_AGB_TO_DADDR(cur->bc_mp, cur->bc_private.a.agno,
+					be32_to_cpu(ptr->s));
+	}
+}
+
+STATIC void
+xfs_btree_set_refs(
+	struct xfs_btree_cur	*cur,
+	struct xfs_buf		*bp)
+{
+	switch (cur->bc_btnum) {
+	case XFS_BTNUM_BNO:
+	case XFS_BTNUM_CNT:
+		XFS_BUF_SET_VTYPE_REF(*bpp, B_FS_MAP, XFS_ALLOC_BTREE_REF);
+		break;
+	case XFS_BTNUM_INO:
+		XFS_BUF_SET_VTYPE_REF(*bpp, B_FS_INOMAP, XFS_INO_BTREE_REF);
+		break;
+	case XFS_BTNUM_BMAP:
+		XFS_BUF_SET_VTYPE_REF(*bpp, B_FS_MAP, XFS_BMAP_BTREE_REF);
+		break;
+	default:
+		ASSERT(0);
+	}
+}
+
+STATIC int
+xfs_btree_get_buf_block(
+	struct xfs_btree_cur	*cur,
+	union xfs_btree_ptr	*ptr,
+	int			flags,
+	struct xfs_btree_block	**block,
+	struct xfs_buf		**bpp)
+{
+	struct xfs_mount	*mp = cur->bc_mp;
+	xfs_daddr_t		d;
+
+	/* need to sort out how callers deal with failures first */
+	ASSERT(!(flags & XFS_BUF_TRYLOCK));
+
+	d = xfs_btree_ptr_to_daddr(cur, ptr);
+	*bpp = xfs_trans_get_buf(cur->bc_tp, mp->m_ddev_targp, d,
+				 mp->m_bsize, flags);
+
+	ASSERT(*bpp);
+	ASSERT(!XFS_BUF_GETERROR(*bpp));
+
+	*block = XFS_BUF_TO_BLOCK(*bpp);
+	return 0;
+}
+
+/*
+ * Read in the buffer at the given ptr and return the buffer and
+ * the block pointer within the buffer.
+ */
+STATIC int
+xfs_btree_read_buf_block(
+	struct xfs_btree_cur	*cur,
+	union xfs_btree_ptr	*ptr,
+	int			level,
+	int			flags,
+	struct xfs_btree_block	**block,
+	struct xfs_buf		**bpp)
+{
+	struct xfs_mount	*mp = cur->bc_mp;
+	xfs_daddr_t		d;
+	int			error;
+
+	/* need to sort out how callers deal with failures first */
+	ASSERT(!(flags & XFS_BUF_TRYLOCK));
+
+	d = xfs_btree_ptr_to_daddr(cur, ptr);
+	error = xfs_trans_read_buf(mp, cur->bc_tp, mp->m_ddev_targp, d,
+				   mp->m_bsize, flags, bpp);
+	if (error)
+		return error;
+
+	ASSERT(*bpp != NULL);
+	ASSERT(!XFS_BUF_GETERROR(*bpp));
+
+	xfs_btree_set_refs(cur, *bpp);
+	*block = XFS_BUF_TO_BLOCK(*bpp);
+
+	error = xfs_btree_check_block(cur, *block, level, *bpp);
+	if (error)
+		xfs_trans_brelse(cur->bc_tp, *bpp);
+	return error;
+}
+
+/*
+ * Copy keys from one btree block to another.
+ */
+STATIC void
+xfs_btree_copy_keys(
+	struct xfs_btree_cur	*cur,
+	union xfs_btree_key	*dst_key,
+	union xfs_btree_key	*src_key,
+	int			numkeys)
+{
+	ASSERT(numkeys >= 0);
+	memcpy(dst_key, src_key, numkeys * cur->bc_ops->key_len);
+}
+
+/*
+ * Copy records from one btree block to another.
+ */
+STATIC void
+xfs_btree_copy_recs(
+	struct xfs_btree_cur	*cur,
+	union xfs_btree_rec	*dst_rec,
+	union xfs_btree_rec	*src_rec,
+	int			numrecs)
+{
+	ASSERT(numrecs >= 0);
+	memcpy(dst_rec, src_rec, numrecs * cur->bc_ops->rec_len);
+}
+
+/*
+ * Copy block pointers from one btree block to another.
+ */
+STATIC void
+xfs_btree_copy_ptrs(
+	struct xfs_btree_cur	*cur,
+	union xfs_btree_ptr	*dst_ptr,
+	union xfs_btree_ptr	*src_ptr,
+	int			numptrs)
+{
+	ASSERT(numptrs >= 0);
+	memcpy(dst_ptr, src_ptr, numptrs * xfs_btree_ptr_len(cur));
+}
+
+/*
+ * Shift keys one index left/right inside a single btree block.
+ */
+STATIC void
+xfs_btree_shift_keys(
+	struct xfs_btree_cur	*cur,
+	union xfs_btree_key	*key,
+	int			dir,
+	int			numkeys)
+{
+	char			*dst_key;
+
+	ASSERT(numkeys >= 0);
+	ASSERT(dir == 1 || dir == -1);
+
+	dst_key = (char *)key + (dir * cur->bc_ops->key_len);
+	memmove(dst_key, key, numkeys * cur->bc_ops->key_len);
+}
+
+/*
+ * Shift records one index left/right inside a single btree block.
+ */
+STATIC void
+xfs_btree_shift_recs(
+	struct xfs_btree_cur	*cur,
+	union xfs_btree_rec	*rec,
+	int			dir,
+	int			numrecs)
+{
+	char			*dst_rec;
+
+	ASSERT(numrecs >= 0);
+	ASSERT(dir == 1 || dir == -1);
+
+	dst_rec = (char *)rec + (dir * cur->bc_ops->rec_len);
+	memmove(dst_rec, rec, numrecs * cur->bc_ops->rec_len);
+}
+
+/*
+ * Shift block pointers one index left/right inside a single btree block.
+ */
+STATIC void
+xfs_btree_shift_ptrs(
+	struct xfs_btree_cur	*cur,
+	union xfs_btree_ptr	*ptr,
+	int			dir,
+	int			numptrs)
+{
+	char			*dst_ptr;
+
+	ASSERT(numptrs >= 0);
+	ASSERT(dir == 1 || dir == -1);
+
+	dst_ptr = (char *)ptr + (dir * xfs_btree_ptr_len(cur));
+	memmove(dst_ptr, ptr, numptrs * xfs_btree_ptr_len(cur));
+}
+
+/*
+ * Log key values from the btree block.
+ */
+STATIC void
+xfs_btree_log_keys(
+	struct xfs_btree_cur	*cur,
+	struct xfs_buf		*bp,
+	int			first,
+	int			last)
+{
+	XFS_BTREE_TRACE_CURSOR(cur, XBT_ENTRY);
+	XFS_BTREE_TRACE_ARGBII(cur, bp, first, last);
+
+	if (bp) {
+		xfs_trans_log_buf(cur->bc_tp, bp,
+				  xfs_btree_key_offset(cur, first),
+				  xfs_btree_key_offset(cur, last + 1) - 1);
+	} else {
+		xfs_trans_log_inode(cur->bc_tp, cur->bc_private.b.ip,
+				xfs_ilog_fbroot(cur->bc_private.b.whichfork));
+	}
+
+	XFS_BTREE_TRACE_CURSOR(cur, XBT_EXIT);
+}
+
+/*
+ * Log record values from the btree block.
+ */
+void
+xfs_btree_log_recs(
+	struct xfs_btree_cur	*cur,
+	struct xfs_buf		*bp,
+	int			first,
+	int			last)
+{
+	XFS_BTREE_TRACE_CURSOR(cur, XBT_ENTRY);
+	XFS_BTREE_TRACE_ARGBII(cur, bp, first, last);
+
+	xfs_trans_log_buf(cur->bc_tp, bp,
+			  xfs_btree_rec_offset(cur, first),
+			  xfs_btree_rec_offset(cur, last + 1) - 1);
+
+	XFS_BTREE_TRACE_CURSOR(cur, XBT_EXIT);
+}
+
+/*
+ * Log block pointer fields from a btree block (nonleaf).
+ */
+STATIC void
+xfs_btree_log_ptrs(
+	struct xfs_btree_cur	*cur,	/* btree cursor */
+	struct xfs_buf		*bp,	/* buffer containing btree block */
+	int			first,	/* index of first pointer to log */
+	int			last)	/* index of last pointer to log */
+{
+	XFS_BTREE_TRACE_CURSOR(cur, XBT_ENTRY);
+	XFS_BTREE_TRACE_ARGBII(cur, bp, first, last);
+
+	if (bp) {
+		struct xfs_btree_block	*block = XFS_BUF_TO_BLOCK(bp);
+		int			level = xfs_btree_get_level(block);
+
+		xfs_trans_log_buf(cur->bc_tp, bp,
+				xfs_btree_ptr_offset(cur, first, level),
+				xfs_btree_ptr_offset(cur, last + 1, level) - 1);
+	} else {
+		xfs_trans_log_inode(cur->bc_tp, cur->bc_private.b.ip,
+			xfs_ilog_fbroot(cur->bc_private.b.whichfork));
+	}
+
+	XFS_BTREE_TRACE_CURSOR(cur, XBT_EXIT);
+}
+
+/*
+ * Log fields from a btree block header.
+ */
+void
+xfs_btree_log_block(
+	struct xfs_btree_cur	*cur,	/* btree cursor */
+	struct xfs_buf		*bp,	/* buffer containing btree block */
+	int			fields)	/* mask of fields: XFS_BB_... */
+{
+	int			first;	/* first byte offset logged */
+	int			last;	/* last byte offset logged */
+	static const short	soffsets[] = {	/* table of offsets (short) */
+		offsetof(struct xfs_btree_block, bb_magic),
+		offsetof(struct xfs_btree_block, bb_level),
+		offsetof(struct xfs_btree_block, bb_numrecs),
+		offsetof(struct xfs_btree_block, bb_u.s.bb_leftsib),
+		offsetof(struct xfs_btree_block, bb_u.s.bb_rightsib),
+		XFS_BTREE_SBLOCK_LEN
+	};
+	static const short	loffsets[] = {	/* table of offsets (long) */
+		offsetof(struct xfs_btree_block, bb_magic),
+		offsetof(struct xfs_btree_block, bb_level),
+		offsetof(struct xfs_btree_block, bb_numrecs),
+		offsetof(struct xfs_btree_block, bb_u.l.bb_leftsib),
+		offsetof(struct xfs_btree_block, bb_u.l.bb_rightsib),
+		XFS_BTREE_LBLOCK_LEN
+	};
+
+	XFS_BTREE_TRACE_CURSOR(cur, XBT_ENTRY);
+	XFS_BTREE_TRACE_ARGBI(cur, bp, fields);
+
+	if (bp) {
+		xfs_btree_offsets(fields,
+				  (cur->bc_flags & XFS_BTREE_LONG_PTRS) ?
+					loffsets : soffsets,
+				  XFS_BB_NUM_BITS, &first, &last);
+		xfs_trans_log_buf(cur->bc_tp, bp, first, last);
+	} else {
+		xfs_trans_log_inode(cur->bc_tp, cur->bc_private.b.ip,
+			xfs_ilog_fbroot(cur->bc_private.b.whichfork));
+	}
+
+	XFS_BTREE_TRACE_CURSOR(cur, XBT_EXIT);
+}
+
+/*
+ * Increment cursor by one record at the level.
+ * For nonzero levels the leaf-ward information is untouched.
+ */
+int						/* error */
+xfs_btree_increment(
+	struct xfs_btree_cur	*cur,
+	int			level,
+	int			*stat)		/* success/failure */
+{
+	struct xfs_btree_block	*block;
+	union xfs_btree_ptr	ptr;
+	struct xfs_buf		*bp;
+	int			error;		/* error return value */
+	int			lev;
+
+	XFS_BTREE_TRACE_CURSOR(cur, XBT_ENTRY);
+	XFS_BTREE_TRACE_ARGI(cur, level);
+
+	ASSERT(level < cur->bc_nlevels);
+
+	/* Read-ahead to the right at this level. */
+	xfs_btree_readahead(cur, level, XFS_BTCUR_RIGHTRA);
+
+	/* Get a pointer to the btree block. */
+	block = xfs_btree_get_block(cur, level, &bp);
+
+#ifdef DEBUG
+	error = xfs_btree_check_block(cur, block, level, bp);
+	if (error)
+		goto error0;
+#endif
+
+	/* We're done if we remain in the block after the increment. */
+	if (++cur->bc_ptrs[level] <= xfs_btree_get_numrecs(block))
+		goto out1;
+
+	/* Fail if we just went off the right edge of the tree. */
+	xfs_btree_get_sibling(cur, block, &ptr, XFS_BB_RIGHTSIB);
+	if (xfs_btree_ptr_is_null(cur, &ptr))
+		goto out0;
+
+	XFS_BTREE_STATS_INC(cur, increment);
+
+	/*
+	 * March up the tree incrementing pointers.
+	 * Stop when we don't go off the right edge of a block.
+	 */
+	for (lev = level + 1; lev < cur->bc_nlevels; lev++) {
+		block = xfs_btree_get_block(cur, lev, &bp);
+
+#ifdef DEBUG
+		error = xfs_btree_check_block(cur, block, lev, bp);
+		if (error)
+			goto error0;
+#endif
+
+		if (++cur->bc_ptrs[lev] <= xfs_btree_get_numrecs(block))
+			break;
+
+		/* Read-ahead the right block for the next loop. */
+		xfs_btree_readahead(cur, lev, XFS_BTCUR_RIGHTRA);
+	}
+
+	/*
+	 * If we went off the root then we are either seriously
+	 * confused or have the tree root in an inode.
+	 */
+	if (lev == cur->bc_nlevels) {
+		if (cur->bc_flags & XFS_BTREE_ROOT_IN_INODE)
+			goto out0;
+		ASSERT(0);
+		error = EFSCORRUPTED;
+		goto error0;
+	}
+	ASSERT(lev < cur->bc_nlevels);
+
+	/*
+	 * Now walk back down the tree, fixing up the cursor's buffer
+	 * pointers and key numbers.
+	 */
+	for (block = xfs_btree_get_block(cur, lev, &bp); lev > level; ) {
+		union xfs_btree_ptr	*ptrp;
+
+		ptrp = xfs_btree_ptr_addr(cur, cur->bc_ptrs[lev], block);
+		error = xfs_btree_read_buf_block(cur, ptrp, --lev,
+							0, &block, &bp);
+		if (error)
+			goto error0;
+
+		xfs_btree_setbuf(cur, lev, bp);
+		cur->bc_ptrs[lev] = 1;
+	}
+out1:
+	XFS_BTREE_TRACE_CURSOR(cur, XBT_EXIT);
+	*stat = 1;
+	return 0;
+
+out0:
+	XFS_BTREE_TRACE_CURSOR(cur, XBT_EXIT);
+	*stat = 0;
+	return 0;
+
+error0:
+	XFS_BTREE_TRACE_CURSOR(cur, XBT_ERROR);
+	return error;
+}
+
+/*
+ * Decrement cursor by one record at the level.
+ * For nonzero levels the leaf-ward information is untouched.
+ */
+int						/* error */
+xfs_btree_decrement(
+	struct xfs_btree_cur	*cur,
+	int			level,
+	int			*stat)		/* success/failure */
+{
+	struct xfs_btree_block	*block;
+	xfs_buf_t		*bp;
+	int			error;		/* error return value */
+	int			lev;
+	union xfs_btree_ptr	ptr;
+
+	XFS_BTREE_TRACE_CURSOR(cur, XBT_ENTRY);
+	XFS_BTREE_TRACE_ARGI(cur, level);
+
+	ASSERT(level < cur->bc_nlevels);
+
+	/* Read-ahead to the left at this level. */
+	xfs_btree_readahead(cur, level, XFS_BTCUR_LEFTRA);
+
+	/* We're done if we remain in the block after the decrement. */
+	if (--cur->bc_ptrs[level] > 0)
+		goto out1;
+
+	/* Get a pointer to the btree block. */
+	block = xfs_btree_get_block(cur, level, &bp);
+
+#ifdef DEBUG
+	error = xfs_btree_check_block(cur, block, level, bp);
+	if (error)
+		goto error0;
+#endif
+
+	/* Fail if we just went off the left edge of the tree. */
+	xfs_btree_get_sibling(cur, block, &ptr, XFS_BB_LEFTSIB);
+	if (xfs_btree_ptr_is_null(cur, &ptr))
+		goto out0;
+
+	XFS_BTREE_STATS_INC(cur, decrement);
+
+	/*
+	 * March up the tree decrementing pointers.
+	 * Stop when we don't go off the left edge of a block.
+	 */
+	for (lev = level + 1; lev < cur->bc_nlevels; lev++) {
+		if (--cur->bc_ptrs[lev] > 0)
+			break;
+		/* Read-ahead the left block for the next loop. */
+		xfs_btree_readahead(cur, lev, XFS_BTCUR_LEFTRA);
+	}
+
+	/*
+	 * If we went off the root then we are seriously confused.
+	 * or the root of the tree is in an inode.
+	 */
+	if (lev == cur->bc_nlevels) {
+		if (cur->bc_flags & XFS_BTREE_ROOT_IN_INODE)
+			goto out0;
+		ASSERT(0);
+		error = EFSCORRUPTED;
+		goto error0;
+	}
+	ASSERT(lev < cur->bc_nlevels);
+
+	/*
+	 * Now walk back down the tree, fixing up the cursor's buffer
+	 * pointers and key numbers.
+	 */
+	for (block = xfs_btree_get_block(cur, lev, &bp); lev > level; ) {
+		union xfs_btree_ptr	*ptrp;
+
+		ptrp = xfs_btree_ptr_addr(cur, cur->bc_ptrs[lev], block);
+		error = xfs_btree_read_buf_block(cur, ptrp, --lev,
+							0, &block, &bp);
+		if (error)
+			goto error0;
+		xfs_btree_setbuf(cur, lev, bp);
+		cur->bc_ptrs[lev] = xfs_btree_get_numrecs(block);
+	}
+out1:
+	XFS_BTREE_TRACE_CURSOR(cur, XBT_EXIT);
+	*stat = 1;
+	return 0;
+
+out0:
+	XFS_BTREE_TRACE_CURSOR(cur, XBT_EXIT);
+	*stat = 0;
+	return 0;
+
+error0:
+	XFS_BTREE_TRACE_CURSOR(cur, XBT_ERROR);
+	return error;
+}
+
+STATIC int
+xfs_btree_lookup_get_block(
+	struct xfs_btree_cur	*cur,	/* btree cursor */
+	int			level,	/* level in the btree */
+	union xfs_btree_ptr	*pp,	/* ptr to btree block */
+	struct xfs_btree_block	**blkp) /* return btree block */
+{
+	struct xfs_buf		*bp;	/* buffer pointer for btree block */
+	int			error = 0;
+
+	/* special case the root block if in an inode */
+	if ((cur->bc_flags & XFS_BTREE_ROOT_IN_INODE) &&
+	    (level == cur->bc_nlevels - 1)) {
+		*blkp = xfs_btree_get_iroot(cur);
+		return 0;
+	}
+
+	/*
+	 * If the old buffer at this level for the disk address we are
+	 * looking for re-use it.
+	 *
+	 * Otherwise throw it away and get a new one.
+	 */
+	bp = cur->bc_bufs[level];
+	if (bp && XFS_BUF_ADDR(bp) == xfs_btree_ptr_to_daddr(cur, pp)) {
+		*blkp = XFS_BUF_TO_BLOCK(bp);
+		return 0;
+	}
+
+	error = xfs_btree_read_buf_block(cur, pp, level, 0, blkp, &bp);
+	if (error)
+		return error;
+
+	xfs_btree_setbuf(cur, level, bp);
+	return 0;
+}
+
+/*
+ * Get current search key.  For level 0 we don't actually have a key
+ * structure so we make one up from the record.  For all other levels
+ * we just return the right key.
+ */
+STATIC union xfs_btree_key *
+xfs_lookup_get_search_key(
+	struct xfs_btree_cur	*cur,
+	int			level,
+	int			keyno,
+	struct xfs_btree_block	*block,
+	union xfs_btree_key	*kp)
+{
+	if (level == 0) {
+		cur->bc_ops->init_key_from_rec(kp,
+				xfs_btree_rec_addr(cur, keyno, block));
+		return kp;
+	}
+
+	return xfs_btree_key_addr(cur, keyno, block);
+}
+
+/*
+ * Lookup the record.  The cursor is made to point to it, based on dir.
+ * Return 0 if can't find any such record, 1 for success.
+ */
+int					/* error */
+xfs_btree_lookup(
+	struct xfs_btree_cur	*cur,	/* btree cursor */
+	xfs_lookup_t		dir,	/* <=, ==, or >= */
+	int			*stat)	/* success/failure */
+{
+	struct xfs_btree_block	*block;	/* current btree block */
+	__int64_t		diff;	/* difference for the current key */
+	int			error;	/* error return value */
+	int			keyno;	/* current key number */
+	int			level;	/* level in the btree */
+	union xfs_btree_ptr	*pp;	/* ptr to btree block */
+	union xfs_btree_ptr	ptr;	/* ptr to btree block */
+
+	XFS_BTREE_TRACE_CURSOR(cur, XBT_ENTRY);
+	XFS_BTREE_TRACE_ARGI(cur, dir);
+
+	XFS_BTREE_STATS_INC(cur, lookup);
+
+	block = NULL;
+	keyno = 0;
+
+	/* initialise start pointer from cursor */
+	cur->bc_ops->init_ptr_from_cur(cur, &ptr);
+	pp = &ptr;
+
+	/*
+	 * Iterate over each level in the btree, starting at the root.
+	 * For each level above the leaves, find the key we need, based
+	 * on the lookup record, then follow the corresponding block
+	 * pointer down to the next level.
+	 */
+	for (level = cur->bc_nlevels - 1, diff = 1; level >= 0; level--) {
+		/* Get the block we need to do the lookup on. */
+		error = xfs_btree_lookup_get_block(cur, level, pp, &block);
+		if (error)
+			goto error0;
+
+		if (diff == 0) {
+			/*
+			 * If we already had a key match at a higher level, we
+			 * know we need to use the first entry in this block.
+			 */
+			keyno = 1;
+		} else {
+			/* Otherwise search this block. Do a binary search. */
+
+			int	high;	/* high entry number */
+			int	low;	/* low entry number */
+
+			/* Set low and high entry numbers, 1-based. */
+			low = 1;
+			high = xfs_btree_get_numrecs(block);
+			if (!high) {
+				/* Block is empty, must be an empty leaf. */
+				ASSERT(level == 0 && cur->bc_nlevels == 1);
+
+				cur->bc_ptrs[0] = dir != XFS_LOOKUP_LE;
+				XFS_BTREE_TRACE_CURSOR(cur, XBT_EXIT);
+				*stat = 0;
+				return 0;
+			}
+
+			/* Binary search the block. */
+			while (low <= high) {
+				union xfs_btree_key	key;
+				union xfs_btree_key	*kp;
+
+				XFS_BTREE_STATS_INC(cur, compare);
+
+				/* keyno is average of low and high. */
+				keyno = (low + high) >> 1;
+
+				/* Get current search key */
+				kp = xfs_lookup_get_search_key(cur, level,
+						keyno, block, &key);
+
+				/*
+				 * Compute difference to get next direction:
+				 *  - less than, move right
+				 *  - greater than, move left
+				 *  - equal, we're done
+				 */
+				diff = cur->bc_ops->key_diff(cur, kp);
+				if (diff < 0)
+					low = keyno + 1;
+				else if (diff > 0)
+					high = keyno - 1;
+				else
+					break;
+			}
+		}
+
+		/*
+		 * If there are more levels, set up for the next level
+		 * by getting the block number and filling in the cursor.
+		 */
+		if (level > 0) {
+			/*
+			 * If we moved left, need the previous key number,
+			 * unless there isn't one.
+			 */
+			if (diff > 0 && --keyno < 1)
+				keyno = 1;
+			pp = xfs_btree_ptr_addr(cur, keyno, block);
+
+#ifdef DEBUG
+			error = xfs_btree_check_ptr(cur, pp, 0, level);
+			if (error)
+				goto error0;
+#endif
+			cur->bc_ptrs[level] = keyno;
+		}
+	}
+
+	/* Done with the search. See if we need to adjust the results. */
+	if (dir != XFS_LOOKUP_LE && diff < 0) {
+		keyno++;
+		/*
+		 * If ge search and we went off the end of the block, but it's
+		 * not the last block, we're in the wrong block.
+		 */
+		xfs_btree_get_sibling(cur, block, &ptr, XFS_BB_RIGHTSIB);
+		if (dir == XFS_LOOKUP_GE &&
+		    keyno > xfs_btree_get_numrecs(block) &&
+		    !xfs_btree_ptr_is_null(cur, &ptr)) {
+			int	i;
+
+			cur->bc_ptrs[0] = keyno;
+			error = xfs_btree_increment(cur, 0, &i);
+			if (error)
+				goto error0;
+			XFS_WANT_CORRUPTED_RETURN(i == 1);
+			XFS_BTREE_TRACE_CURSOR(cur, XBT_EXIT);
+			*stat = 1;
+			return 0;
+		}
+	} else if (dir == XFS_LOOKUP_LE && diff > 0)
+		keyno--;
+	cur->bc_ptrs[0] = keyno;
+
+	/* Return if we succeeded or not. */
+	if (keyno == 0 || keyno > xfs_btree_get_numrecs(block))
+		*stat = 0;
+	else if (dir != XFS_LOOKUP_EQ || diff == 0)
+		*stat = 1;
+	else
+		*stat = 0;
+	XFS_BTREE_TRACE_CURSOR(cur, XBT_EXIT);
+	return 0;
+
+error0:
+	XFS_BTREE_TRACE_CURSOR(cur, XBT_ERROR);
+	return error;
+}
+
+/*
+ * Update keys at all levels from here to the root along the cursor's path.
+ */
+STATIC int
+xfs_btree_updkey(
+	struct xfs_btree_cur	*cur,
+	union xfs_btree_key	*keyp,
+	int			level)
+{
+	struct xfs_btree_block	*block;
+	struct xfs_buf		*bp;
+	union xfs_btree_key	*kp;
+	int			ptr;
+
+	XFS_BTREE_TRACE_CURSOR(cur, XBT_ENTRY);
+	XFS_BTREE_TRACE_ARGIK(cur, level, keyp);
+
+	ASSERT(!(cur->bc_flags & XFS_BTREE_ROOT_IN_INODE) || level >= 1);
+
+	/*
+	 * Go up the tree from this level toward the root.
+	 * At each level, update the key value to the value input.
+	 * Stop when we reach a level where the cursor isn't pointing
+	 * at the first entry in the block.
+	 */
+	for (ptr = 1; ptr == 1 && level < cur->bc_nlevels; level++) {
+#ifdef DEBUG
+		int		error;
+#endif
+		block = xfs_btree_get_block(cur, level, &bp);
+#ifdef DEBUG
+		error = xfs_btree_check_block(cur, block, level, bp);
+		if (error) {
+			XFS_BTREE_TRACE_CURSOR(cur, XBT_ERROR);
+			return error;
+		}
+#endif
+		ptr = cur->bc_ptrs[level];
+		kp = xfs_btree_key_addr(cur, ptr, block);
+		xfs_btree_copy_keys(cur, kp, keyp, 1);
+		xfs_btree_log_keys(cur, bp, ptr, ptr);
+	}
+
+	XFS_BTREE_TRACE_CURSOR(cur, XBT_EXIT);
+	return 0;
+}
+
+/*
+ * Update the record referred to by cur to the value in the
+ * given record. This either works (return 0) or gets an
+ * EFSCORRUPTED error.
+ */
+int
+xfs_btree_update(
+	struct xfs_btree_cur	*cur,
+	union xfs_btree_rec	*rec)
+{
+	struct xfs_btree_block	*block;
+	struct xfs_buf		*bp;
+	int			error;
+	int			ptr;
+	union xfs_btree_rec	*rp;
+
+	XFS_BTREE_TRACE_CURSOR(cur, XBT_ENTRY);
+	XFS_BTREE_TRACE_ARGR(cur, rec);
+
+	/* Pick up the current block. */
+	block = xfs_btree_get_block(cur, 0, &bp);
+
+#ifdef DEBUG
+	error = xfs_btree_check_block(cur, block, 0, bp);
+	if (error)
+		goto error0;
+#endif
+	/* Get the address of the rec to be updated. */
+	ptr = cur->bc_ptrs[0];
+	rp = xfs_btree_rec_addr(cur, ptr, block);
+
+	/* Fill in the new contents and log them. */
+	xfs_btree_copy_recs(cur, rp, rec, 1);
+	xfs_btree_log_recs(cur, bp, ptr, ptr);
+
+	/*
+	 * If we are tracking the last record in the tree and
+	 * we are at the far right edge of the tree, update it.
+	 */
+	if (xfs_btree_is_lastrec(cur, block, 0)) {
+		cur->bc_ops->update_lastrec(cur, block, rec,
+					    ptr, LASTREC_UPDATE);
+	}
+
+	/* Updating first rec in leaf. Pass new key value up to our parent. */
+	if (ptr == 1) {
+		union xfs_btree_key	key;
+
+		cur->bc_ops->init_key_from_rec(&key, rec);
+		error = xfs_btree_updkey(cur, &key, 1);
+		if (error)
+			goto error0;
+	}
+
+	XFS_BTREE_TRACE_CURSOR(cur, XBT_EXIT);
+	return 0;
+
+error0:
+	XFS_BTREE_TRACE_CURSOR(cur, XBT_ERROR);
+	return error;
+}
+
+/*
+ * Move 1 record left from cur/level if possible.
+ * Update cur to reflect the new path.
+ */
+STATIC int					/* error */
+xfs_btree_lshift(
+	struct xfs_btree_cur	*cur,
+	int			level,
+	int			*stat)		/* success/failure */
+{
+	union xfs_btree_key	key;		/* btree key */
+	struct xfs_buf		*lbp;		/* left buffer pointer */
+	struct xfs_btree_block	*left;		/* left btree block */
+	int			lrecs;		/* left record count */
+	struct xfs_buf		*rbp;		/* right buffer pointer */
+	struct xfs_btree_block	*right;		/* right btree block */
+	int			rrecs;		/* right record count */
+	union xfs_btree_ptr	lptr;		/* left btree pointer */
+	union xfs_btree_key	*rkp = NULL;	/* right btree key */
+	union xfs_btree_ptr	*rpp = NULL;	/* right address pointer */
+	union xfs_btree_rec	*rrp = NULL;	/* right record pointer */
+	int			error;		/* error return value */
+
+	XFS_BTREE_TRACE_CURSOR(cur, XBT_ENTRY);
+	XFS_BTREE_TRACE_ARGI(cur, level);
+
+	if ((cur->bc_flags & XFS_BTREE_ROOT_IN_INODE) &&
+	    level == cur->bc_nlevels - 1)
+		goto out0;
+
+	/* Set up variables for this block as "right". */
+	right = xfs_btree_get_block(cur, level, &rbp);
+
+#ifdef DEBUG
+	error = xfs_btree_check_block(cur, right, level, rbp);
+	if (error)
+		goto error0;
+#endif
+
+	/* If we've got no left sibling then we can't shift an entry left. */
+	xfs_btree_get_sibling(cur, right, &lptr, XFS_BB_LEFTSIB);
+	if (xfs_btree_ptr_is_null(cur, &lptr))
+		goto out0;
+
+	/*
+	 * If the cursor entry is the one that would be moved, don't
+	 * do it... it's too complicated.
+	 */
+	if (cur->bc_ptrs[level] <= 1)
+		goto out0;
+
+	/* Set up the left neighbor as "left". */
+	error = xfs_btree_read_buf_block(cur, &lptr, level, 0, &left, &lbp);
+	if (error)
+		goto error0;
+
+	/* If it's full, it can't take another entry. */
+	lrecs = xfs_btree_get_numrecs(left);
+	if (lrecs == cur->bc_ops->get_maxrecs(cur, level))
+		goto out0;
+
+	rrecs = xfs_btree_get_numrecs(right);
+
+	/*
+	 * We add one entry to the left side and remove one for the right side.
+	 * Accout for it here, the changes will be updated on disk and logged
+	 * later.
+	 */
+	lrecs++;
+	rrecs--;
+
+	XFS_BTREE_STATS_INC(cur, lshift);
+	XFS_BTREE_STATS_ADD(cur, moves, 1);
+
+	/*
+	 * If non-leaf, copy a key and a ptr to the left block.
+	 * Log the changes to the left block.
+	 */
+	if (level > 0) {
+		/* It's a non-leaf.  Move keys and pointers. */
+		union xfs_btree_key	*lkp;	/* left btree key */
+		union xfs_btree_ptr	*lpp;	/* left address pointer */
+
+		lkp = xfs_btree_key_addr(cur, lrecs, left);
+		rkp = xfs_btree_key_addr(cur, 1, right);
+
+		lpp = xfs_btree_ptr_addr(cur, lrecs, left);
+		rpp = xfs_btree_ptr_addr(cur, 1, right);
+#ifdef DEBUG
+		error = xfs_btree_check_ptr(cur, rpp, 0, level);
+		if (error)
+			goto error0;
+#endif
+		xfs_btree_copy_keys(cur, lkp, rkp, 1);
+		xfs_btree_copy_ptrs(cur, lpp, rpp, 1);
+
+		xfs_btree_log_keys(cur, lbp, lrecs, lrecs);
+		xfs_btree_log_ptrs(cur, lbp, lrecs, lrecs);
+
+		ASSERT(cur->bc_ops->keys_inorder(cur,
+			xfs_btree_key_addr(cur, lrecs - 1, left), lkp));
+	} else {
+		/* It's a leaf.  Move records.  */
+		union xfs_btree_rec	*lrp;	/* left record pointer */
+
+		lrp = xfs_btree_rec_addr(cur, lrecs, left);
+		rrp = xfs_btree_rec_addr(cur, 1, right);
+
+		xfs_btree_copy_recs(cur, lrp, rrp, 1);
+		xfs_btree_log_recs(cur, lbp, lrecs, lrecs);
+
+		ASSERT(cur->bc_ops->recs_inorder(cur,
+			xfs_btree_rec_addr(cur, lrecs - 1, left), lrp));
+	}
+
+	xfs_btree_set_numrecs(left, lrecs);
+	xfs_btree_log_block(cur, lbp, XFS_BB_NUMRECS);
+
+	xfs_btree_set_numrecs(right, rrecs);
+	xfs_btree_log_block(cur, rbp, XFS_BB_NUMRECS);
+
+	/*
+	 * Slide the contents of right down one entry.
+	 */
+	XFS_BTREE_STATS_ADD(cur, moves, rrecs - 1);
+	if (level > 0) {
+		/* It's a nonleaf. operate on keys and ptrs */
+#ifdef DEBUG
+		int			i;		/* loop index */
+
+		for (i = 0; i < rrecs; i++) {
+			error = xfs_btree_check_ptr(cur, rpp, i + 1, level);
+			if (error)
+				goto error0;
+		}
+#endif
+		xfs_btree_shift_keys(cur,
+				xfs_btree_key_addr(cur, 2, right),
+				-1, rrecs);
+		xfs_btree_shift_ptrs(cur,
+				xfs_btree_ptr_addr(cur, 2, right),
+				-1, rrecs);
+
+		xfs_btree_log_keys(cur, rbp, 1, rrecs);
+		xfs_btree_log_ptrs(cur, rbp, 1, rrecs);
+	} else {
+		/* It's a leaf. operate on records */
+		xfs_btree_shift_recs(cur,
+			xfs_btree_rec_addr(cur, 2, right),
+			-1, rrecs);
+		xfs_btree_log_recs(cur, rbp, 1, rrecs);
+
+		/*
+		 * If it's the first record in the block, we'll need a key
+		 * structure to pass up to the next level (updkey).
+		 */
+		cur->bc_ops->init_key_from_rec(&key,
+			xfs_btree_rec_addr(cur, 1, right));
+		rkp = &key;
+	}
+
+	/* Update the parent key values of right. */
+	error = xfs_btree_updkey(cur, rkp, level + 1);
+	if (error)
+		goto error0;
+
+	/* Slide the cursor value left one. */
+	cur->bc_ptrs[level]--;
+
+	XFS_BTREE_TRACE_CURSOR(cur, XBT_EXIT);
+	*stat = 1;
+	return 0;
+
+out0:
+	XFS_BTREE_TRACE_CURSOR(cur, XBT_EXIT);
+	*stat = 0;
+	return 0;
+
+error0:
+	XFS_BTREE_TRACE_CURSOR(cur, XBT_ERROR);
+	return error;
+}
+
+/*
+ * Move 1 record right from cur/level if possible.
+ * Update cur to reflect the new path.
+ */
+STATIC int					/* error */
+xfs_btree_rshift(
+	struct xfs_btree_cur	*cur,
+	int			level,
+	int			*stat)		/* success/failure */
+{
+	union xfs_btree_key	key;		/* btree key */
+	struct xfs_buf		*lbp;		/* left buffer pointer */
+	struct xfs_btree_block	*left;		/* left btree block */
+	struct xfs_buf		*rbp;		/* right buffer pointer */
+	struct xfs_btree_block	*right;		/* right btree block */
+	struct xfs_btree_cur	*tcur;		/* temporary btree cursor */
+	union xfs_btree_ptr	rptr;		/* right block pointer */
+	union xfs_btree_key	*rkp;		/* right btree key */
+	int			rrecs;		/* right record count */
+	int			lrecs;		/* left record count */
+	int			error;		/* error return value */
+	int			i;		/* loop counter */
+
+	XFS_BTREE_TRACE_CURSOR(cur, XBT_ENTRY);
+	XFS_BTREE_TRACE_ARGI(cur, level);
+
+	if ((cur->bc_flags & XFS_BTREE_ROOT_IN_INODE) &&
+	    (level == cur->bc_nlevels - 1))
+		goto out0;
+
+	/* Set up variables for this block as "left". */
+	left = xfs_btree_get_block(cur, level, &lbp);
+
+#ifdef DEBUG
+	error = xfs_btree_check_block(cur, left, level, lbp);
+	if (error)
+		goto error0;
+#endif
+
+	/* If we've got no right sibling then we can't shift an entry right. */
+	xfs_btree_get_sibling(cur, left, &rptr, XFS_BB_RIGHTSIB);
+	if (xfs_btree_ptr_is_null(cur, &rptr))
+		goto out0;
+
+	/*
+	 * If the cursor entry is the one that would be moved, don't
+	 * do it... it's too complicated.
+	 */
+	lrecs = xfs_btree_get_numrecs(left);
+	if (cur->bc_ptrs[level] >= lrecs)
+		goto out0;
+
+	/* Set up the right neighbor as "right". */
+	error = xfs_btree_read_buf_block(cur, &rptr, level, 0, &right, &rbp);
+	if (error)
+		goto error0;
+
+	/* If it's full, it can't take another entry. */
+	rrecs = xfs_btree_get_numrecs(right);
+	if (rrecs == cur->bc_ops->get_maxrecs(cur, level))
+		goto out0;
+
+	XFS_BTREE_STATS_INC(cur, rshift);
+	XFS_BTREE_STATS_ADD(cur, moves, rrecs);
+
+	/*
+	 * Make a hole at the start of the right neighbor block, then
+	 * copy the last left block entry to the hole.
+	 */
+	if (level > 0) {
+		/* It's a nonleaf. make a hole in the keys and ptrs */
+		union xfs_btree_key	*lkp;
+		union xfs_btree_ptr	*lpp;
+		union xfs_btree_ptr	*rpp;
+
+		lkp = xfs_btree_key_addr(cur, lrecs, left);
+		lpp = xfs_btree_ptr_addr(cur, lrecs, left);
+		rkp = xfs_btree_key_addr(cur, 1, right);
+		rpp = xfs_btree_ptr_addr(cur, 1, right);
+
+#ifdef DEBUG
+		for (i = rrecs - 1; i >= 0; i--) {
+			error = xfs_btree_check_ptr(cur, rpp, i, level);
+			if (error)
+				goto error0;
+		}
+#endif
+
+		xfs_btree_shift_keys(cur, rkp, 1, rrecs);
+		xfs_btree_shift_ptrs(cur, rpp, 1, rrecs);
+
+#ifdef DEBUG
+		error = xfs_btree_check_ptr(cur, lpp, 0, level);
+		if (error)
+			goto error0;
+#endif
+
+		/* Now put the new data in, and log it. */
+		xfs_btree_copy_keys(cur, rkp, lkp, 1);
+		xfs_btree_copy_ptrs(cur, rpp, lpp, 1);
+
+		xfs_btree_log_keys(cur, rbp, 1, rrecs + 1);
+		xfs_btree_log_ptrs(cur, rbp, 1, rrecs + 1);
+
+		ASSERT(cur->bc_ops->keys_inorder(cur, rkp,
+			xfs_btree_key_addr(cur, 2, right)));
+	} else {
+		/* It's a leaf. make a hole in the records */
+		union xfs_btree_rec	*lrp;
+		union xfs_btree_rec	*rrp;
+
+		lrp = xfs_btree_rec_addr(cur, lrecs, left);
+		rrp = xfs_btree_rec_addr(cur, 1, right);
+
+		xfs_btree_shift_recs(cur, rrp, 1, rrecs);
+
+		/* Now put the new data in, and log it. */
+		xfs_btree_copy_recs(cur, rrp, lrp, 1);
+		xfs_btree_log_recs(cur, rbp, 1, rrecs + 1);
+
+		cur->bc_ops->init_key_from_rec(&key, rrp);
+		rkp = &key;
+
+		ASSERT(cur->bc_ops->recs_inorder(cur, rrp,
+			xfs_btree_rec_addr(cur, 2, right)));
+	}
+
+	/*
+	 * Decrement and log left's numrecs, bump and log right's numrecs.
+	 */
+	xfs_btree_set_numrecs(left, --lrecs);
+	xfs_btree_log_block(cur, lbp, XFS_BB_NUMRECS);
+
+	xfs_btree_set_numrecs(right, ++rrecs);
+	xfs_btree_log_block(cur, rbp, XFS_BB_NUMRECS);
+
+	/*
+	 * Using a temporary cursor, update the parent key values of the
+	 * block on the right.
+	 */
+	error = xfs_btree_dup_cursor(cur, &tcur);
+	if (error)
+		goto error0;
+	i = xfs_btree_lastrec(tcur, level);
+	XFS_WANT_CORRUPTED_GOTO(i == 1, error0);
+
+	error = xfs_btree_increment(tcur, level, &i);
+	if (error)
+		goto error1;
+
+	error = xfs_btree_updkey(tcur, rkp, level + 1);
+	if (error)
+		goto error1;
+
+	xfs_btree_del_cursor(tcur, XFS_BTREE_NOERROR);
+
+	XFS_BTREE_TRACE_CURSOR(cur, XBT_EXIT);
+	*stat = 1;
+	return 0;
+
+out0:
+	XFS_BTREE_TRACE_CURSOR(cur, XBT_EXIT);
+	*stat = 0;
+	return 0;
+
+error0:
+	XFS_BTREE_TRACE_CURSOR(cur, XBT_ERROR);
+	return error;
+
+error1:
+	XFS_BTREE_TRACE_CURSOR(tcur, XBT_ERROR);
+	xfs_btree_del_cursor(tcur, XFS_BTREE_ERROR);
+	return error;
+}
+
+/*
+ * Split cur/level block in half.
+ * Return new block number and the key to its first
+ * record (to be inserted into parent).
+ */
+STATIC int					/* error */
+xfs_btree_split(
+	struct xfs_btree_cur	*cur,
+	int			level,
+	union xfs_btree_ptr	*ptrp,
+	union xfs_btree_key	*key,
+	struct xfs_btree_cur	**curp,
+	int			*stat)		/* success/failure */
+{
+	union xfs_btree_ptr	lptr;		/* left sibling block ptr */
+	struct xfs_buf		*lbp;		/* left buffer pointer */
+	struct xfs_btree_block	*left;		/* left btree block */
+	union xfs_btree_ptr	rptr;		/* right sibling block ptr */
+	struct xfs_buf		*rbp;		/* right buffer pointer */
+	struct xfs_btree_block	*right;		/* right btree block */
+	union xfs_btree_ptr	rrptr;		/* right-right sibling ptr */
+	struct xfs_buf		*rrbp;		/* right-right buffer pointer */
+	struct xfs_btree_block	*rrblock;	/* right-right btree block */
+	int			lrecs;
+	int			rrecs;
+	int			src_index;
+	int			error;		/* error return value */
+#ifdef DEBUG
+	int			i;
+#endif
+
+	XFS_BTREE_TRACE_CURSOR(cur, XBT_ENTRY);
+	XFS_BTREE_TRACE_ARGIPK(cur, level, *ptrp, key);
+
+	XFS_BTREE_STATS_INC(cur, split);
+
+	/* Set up left block (current one). */
+	left = xfs_btree_get_block(cur, level, &lbp);
+
+#ifdef DEBUG
+	error = xfs_btree_check_block(cur, left, level, lbp);
+	if (error)
+		goto error0;
+#endif
+
+	xfs_btree_buf_to_ptr(cur, lbp, &lptr);
+
+	/* Allocate the new block. If we can't do it, we're toast. Give up. */
+	error = cur->bc_ops->alloc_block(cur, &lptr, &rptr, 1, stat);
+	if (error)
+		goto error0;
+	if (*stat == 0)
+		goto out0;
+	XFS_BTREE_STATS_INC(cur, alloc);
+
+	/* Set up the new block as "right". */
+	error = xfs_btree_get_buf_block(cur, &rptr, 0, &right, &rbp);
+	if (error)
+		goto error0;
+
+	/* Fill in the btree header for the new right block. */
+	xfs_btree_init_block(cur, xfs_btree_get_level(left), 0, right);
+
+	/*
+	 * Split the entries between the old and the new block evenly.
+	 * Make sure that if there's an odd number of entries now, that
+	 * each new block will have the same number of entries.
+	 */
+	lrecs = xfs_btree_get_numrecs(left);
+	rrecs = lrecs / 2;
+	if ((lrecs & 1) && cur->bc_ptrs[level] <= rrecs + 1)
+		rrecs++;
+	src_index = (lrecs - rrecs + 1);
+
+	XFS_BTREE_STATS_ADD(cur, moves, rrecs);
+
+	/*
+	 * Copy btree block entries from the left block over to the
+	 * new block, the right. Update the right block and log the
+	 * changes.
+	 */
+	if (level > 0) {
+		/* It's a non-leaf.  Move keys and pointers. */
+		union xfs_btree_key	*lkp;	/* left btree key */
+		union xfs_btree_ptr	*lpp;	/* left address pointer */
+		union xfs_btree_key	*rkp;	/* right btree key */
+		union xfs_btree_ptr	*rpp;	/* right address pointer */
+
+		lkp = xfs_btree_key_addr(cur, src_index, left);
+		lpp = xfs_btree_ptr_addr(cur, src_index, left);
+		rkp = xfs_btree_key_addr(cur, 1, right);
+		rpp = xfs_btree_ptr_addr(cur, 1, right);
+
+#ifdef DEBUG
+		for (i = src_index; i < rrecs; i++) {
+			error = xfs_btree_check_ptr(cur, lpp, i, level);
+			if (error)
+				goto error0;
+		}
+#endif
+
+		xfs_btree_copy_keys(cur, rkp, lkp, rrecs);
+		xfs_btree_copy_ptrs(cur, rpp, lpp, rrecs);
+
+		xfs_btree_log_keys(cur, rbp, 1, rrecs);
+		xfs_btree_log_ptrs(cur, rbp, 1, rrecs);
+
+		/* Grab the keys to the entries moved to the right block */
+		xfs_btree_copy_keys(cur, key, rkp, 1);
+	} else {
+		/* It's a leaf.  Move records.  */
+		union xfs_btree_rec	*lrp;	/* left record pointer */
+		union xfs_btree_rec	*rrp;	/* right record pointer */
+
+		lrp = xfs_btree_rec_addr(cur, src_index, left);
+		rrp = xfs_btree_rec_addr(cur, 1, right);
+
+		xfs_btree_copy_recs(cur, rrp, lrp, rrecs);
+		xfs_btree_log_recs(cur, rbp, 1, rrecs);
+
+		cur->bc_ops->init_key_from_rec(key,
+			xfs_btree_rec_addr(cur, 1, right));
+	}
+
+
+	/*
+	 * Find the left block number by looking in the buffer.
+	 * Adjust numrecs, sibling pointers.
+	 */
+	xfs_btree_get_sibling(cur, left, &rrptr, XFS_BB_RIGHTSIB);
+	xfs_btree_set_sibling(cur, right, &rrptr, XFS_BB_RIGHTSIB);
+	xfs_btree_set_sibling(cur, right, &lptr, XFS_BB_LEFTSIB);
+	xfs_btree_set_sibling(cur, left, &rptr, XFS_BB_RIGHTSIB);
+
+	lrecs -= rrecs;
+	xfs_btree_set_numrecs(left, lrecs);
+	xfs_btree_set_numrecs(right, xfs_btree_get_numrecs(right) + rrecs);
+
+	xfs_btree_log_block(cur, rbp, XFS_BB_ALL_BITS);
+	xfs_btree_log_block(cur, lbp, XFS_BB_NUMRECS | XFS_BB_RIGHTSIB);
+
+	/*
+	 * If there's a block to the new block's right, make that block
+	 * point back to right instead of to left.
+	 */
+	if (!xfs_btree_ptr_is_null(cur, &rrptr)) {
+		error = xfs_btree_read_buf_block(cur, &rrptr, level,
+							0, &rrblock, &rrbp);
+		if (error)
+			goto error0;
+		xfs_btree_set_sibling(cur, rrblock, &rptr, XFS_BB_LEFTSIB);
+		xfs_btree_log_block(cur, rrbp, XFS_BB_LEFTSIB);
+	}
+	/*
+	 * If the cursor is really in the right block, move it there.
+	 * If it's just pointing past the last entry in left, then we'll
+	 * insert there, so don't change anything in that case.
+	 */
+	if (cur->bc_ptrs[level] > lrecs + 1) {
+		xfs_btree_setbuf(cur, level, rbp);
+		cur->bc_ptrs[level] -= lrecs;
+	}
+	/*
+	 * If there are more levels, we'll need another cursor which refers
+	 * the right block, no matter where this cursor was.
+	 */
+	if (level + 1 < cur->bc_nlevels) {
+		error = xfs_btree_dup_cursor(cur, curp);
+		if (error)
+			goto error0;
+		(*curp)->bc_ptrs[level + 1]++;
+	}
+	*ptrp = rptr;
+	XFS_BTREE_TRACE_CURSOR(cur, XBT_EXIT);
+	*stat = 1;
+	return 0;
+out0:
+	XFS_BTREE_TRACE_CURSOR(cur, XBT_EXIT);
+	*stat = 0;
+	return 0;
+
+error0:
+	XFS_BTREE_TRACE_CURSOR(cur, XBT_ERROR);
+	return error;
+}
+
+/*
+ * Copy the old inode root contents into a real block and make the
+ * broot point to it.
+ */
+int						/* error */
+xfs_btree_new_iroot(
+	struct xfs_btree_cur	*cur,		/* btree cursor */
+	int			*logflags,	/* logging flags for inode */
+	int			*stat)		/* return status - 0 fail */
+{
+	struct xfs_buf		*cbp;		/* buffer for cblock */
+	struct xfs_btree_block	*block;		/* btree block */
+	struct xfs_btree_block	*cblock;	/* child btree block */
+	union xfs_btree_key	*ckp;		/* child key pointer */
+	union xfs_btree_ptr	*cpp;		/* child ptr pointer */
+	union xfs_btree_key	*kp;		/* pointer to btree key */
+	union xfs_btree_ptr	*pp;		/* pointer to block addr */
+	union xfs_btree_ptr	nptr;		/* new block addr */
+	int			level;		/* btree level */
+	int			error;		/* error return code */
+#ifdef DEBUG
+	int			i;		/* loop counter */
+#endif
+
+	XFS_BTREE_TRACE_CURSOR(cur, XBT_ENTRY);
+	XFS_BTREE_STATS_INC(cur, newroot);
+
+	ASSERT(cur->bc_flags & XFS_BTREE_ROOT_IN_INODE);
+
+	level = cur->bc_nlevels - 1;
+
+	block = xfs_btree_get_iroot(cur);
+	pp = xfs_btree_ptr_addr(cur, 1, block);
+
+	/* Allocate the new block. If we can't do it, we're toast. Give up. */
+	error = cur->bc_ops->alloc_block(cur, pp, &nptr, 1, stat);
+	if (error)
+		goto error0;
+	if (*stat == 0) {
+		XFS_BTREE_TRACE_CURSOR(cur, XBT_EXIT);
+		return 0;
+	}
+	XFS_BTREE_STATS_INC(cur, alloc);
+
+	/* Copy the root into a real block. */
+	error = xfs_btree_get_buf_block(cur, &nptr, 0, &cblock, &cbp);
+	if (error)
+		goto error0;
+
+	memcpy(cblock, block, xfs_btree_block_len(cur));
+
+	be16_add_cpu(&block->bb_level, 1);
+	xfs_btree_set_numrecs(block, 1);
+	cur->bc_nlevels++;
+	cur->bc_ptrs[level + 1] = 1;
+
+	kp = xfs_btree_key_addr(cur, 1, block);
+	ckp = xfs_btree_key_addr(cur, 1, cblock);
+	xfs_btree_copy_keys(cur, ckp, kp, xfs_btree_get_numrecs(cblock));
+
+	cpp = xfs_btree_ptr_addr(cur, 1, cblock);
+#ifdef DEBUG
+	for (i = 0; i < be16_to_cpu(cblock->bb_numrecs); i++) {
+		error = xfs_btree_check_ptr(cur, pp, i, level);
+		if (error)
+			goto error0;
+	}
+#endif
+	xfs_btree_copy_ptrs(cur, cpp, pp, xfs_btree_get_numrecs(cblock));
+
+#ifdef DEBUG
+	error = xfs_btree_check_ptr(cur, &nptr, 0, level);
+	if (error)
+		goto error0;
+#endif
+	xfs_btree_copy_ptrs(cur, pp, &nptr, 1);
+
+	xfs_iroot_realloc(cur->bc_private.b.ip,
+			  1 - xfs_btree_get_numrecs(cblock),
+			  cur->bc_private.b.whichfork);
+
+	xfs_btree_setbuf(cur, level, cbp);
+
+	/*
+	 * Do all this logging at the end so that
+	 * the root is at the right level.
+	 */
+	xfs_btree_log_block(cur, cbp, XFS_BB_ALL_BITS);
+	xfs_btree_log_keys(cur, cbp, 1, be16_to_cpu(cblock->bb_numrecs));
+	xfs_btree_log_ptrs(cur, cbp, 1, be16_to_cpu(cblock->bb_numrecs));
+
+	*logflags |=
+		XFS_ILOG_CORE | XFS_ILOG_FBROOT(cur->bc_private.b.whichfork);
+	*stat = 1;
+	XFS_BTREE_TRACE_CURSOR(cur, XBT_EXIT);
+	return 0;
+error0:
+	XFS_BTREE_TRACE_CURSOR(cur, XBT_ERROR);
+	return error;
+}
+
+/*
+ * Allocate a new root block, fill it in.
+ */
+STATIC int				/* error */
+xfs_btree_new_root(
+	struct xfs_btree_cur	*cur,	/* btree cursor */
+	int			*stat)	/* success/failure */
+{
+	struct xfs_btree_block	*block;	/* one half of the old root block */
+	struct xfs_buf		*bp;	/* buffer containing block */
+	int			error;	/* error return value */
+	struct xfs_buf		*lbp;	/* left buffer pointer */
+	struct xfs_btree_block	*left;	/* left btree block */
+	struct xfs_buf		*nbp;	/* new (root) buffer */
+	struct xfs_btree_block	*new;	/* new (root) btree block */
+	int			nptr;	/* new value for key index, 1 or 2 */
+	struct xfs_buf		*rbp;	/* right buffer pointer */
+	struct xfs_btree_block	*right;	/* right btree block */
+	union xfs_btree_ptr	rptr;
+	union xfs_btree_ptr	lptr;
+
+	XFS_BTREE_TRACE_CURSOR(cur, XBT_ENTRY);
+	XFS_BTREE_STATS_INC(cur, newroot);
+
+	/* initialise our start point from the cursor */
+	cur->bc_ops->init_ptr_from_cur(cur, &rptr);
+
+	/* Allocate the new block. If we can't do it, we're toast. Give up. */
+	error = cur->bc_ops->alloc_block(cur, &rptr, &lptr, 1, stat);
+	if (error)
+		goto error0;
+	if (*stat == 0)
+		goto out0;
+	XFS_BTREE_STATS_INC(cur, alloc);
+
+	/* Set up the new block. */
+	error = xfs_btree_get_buf_block(cur, &lptr, 0, &new, &nbp);
+	if (error)
+		goto error0;
+
+	/* Set the root in the holding structure  increasing the level by 1. */
+	cur->bc_ops->set_root(cur, &lptr, 1);
+
+	/*
+	 * At the previous root level there are now two blocks: the old root,
+	 * and the new block generated when it was split.  We don't know which
+	 * one the cursor is pointing at, so we set up variables "left" and
+	 * "right" for each case.
+	 */
+	block = xfs_btree_get_block(cur, cur->bc_nlevels - 1, &bp);
+
+#ifdef DEBUG
+	error = xfs_btree_check_block(cur, block, cur->bc_nlevels - 1, bp);
+	if (error)
+		goto error0;
+#endif
+
+	xfs_btree_get_sibling(cur, block, &rptr, XFS_BB_RIGHTSIB);
+	if (!xfs_btree_ptr_is_null(cur, &rptr)) {
+		/* Our block is left, pick up the right block. */
+		lbp = bp;
+		xfs_btree_buf_to_ptr(cur, lbp, &lptr);
+		left = block;
+		error = xfs_btree_read_buf_block(cur, &rptr,
+					cur->bc_nlevels - 1, 0, &right, &rbp);
+		if (error)
+			goto error0;
+		bp = rbp;
+		nptr = 1;
+	} else {
+		/* Our block is right, pick up the left block. */
+		rbp = bp;
+		xfs_btree_buf_to_ptr(cur, rbp, &rptr);
+		right = block;
+		xfs_btree_get_sibling(cur, right, &lptr, XFS_BB_LEFTSIB);
+		error = xfs_btree_read_buf_block(cur, &lptr,
+					cur->bc_nlevels - 1, 0, &left, &lbp);
+		if (error)
+			goto error0;
+		bp = lbp;
+		nptr = 2;
+	}
+	/* Fill in the new block's btree header and log it. */
+	xfs_btree_init_block(cur, cur->bc_nlevels, 2, new);
+	xfs_btree_log_block(cur, nbp, XFS_BB_ALL_BITS);
+	ASSERT(!xfs_btree_ptr_is_null(cur, &lptr) &&
+			!xfs_btree_ptr_is_null(cur, &rptr));
+
+	/* Fill in the key data in the new root. */
+	if (xfs_btree_get_level(left) > 0) {
+		xfs_btree_copy_keys(cur,
+				xfs_btree_key_addr(cur, 1, new),
+				xfs_btree_key_addr(cur, 1, left), 1);
+		xfs_btree_copy_keys(cur,
+				xfs_btree_key_addr(cur, 2, new),
+				xfs_btree_key_addr(cur, 1, right), 1);
+	} else {
+		cur->bc_ops->init_key_from_rec(
+				xfs_btree_key_addr(cur, 1, new),
+				xfs_btree_rec_addr(cur, 1, left));
+		cur->bc_ops->init_key_from_rec(
+				xfs_btree_key_addr(cur, 2, new),
+				xfs_btree_rec_addr(cur, 1, right));
+	}
+	xfs_btree_log_keys(cur, nbp, 1, 2);
+
+	/* Fill in the pointer data in the new root. */
+	xfs_btree_copy_ptrs(cur,
+		xfs_btree_ptr_addr(cur, 1, new), &lptr, 1);
+	xfs_btree_copy_ptrs(cur,
+		xfs_btree_ptr_addr(cur, 2, new), &rptr, 1);
+	xfs_btree_log_ptrs(cur, nbp, 1, 2);
+
+	/* Fix up the cursor. */
+	xfs_btree_setbuf(cur, cur->bc_nlevels, nbp);
+	cur->bc_ptrs[cur->bc_nlevels] = nptr;
+	cur->bc_nlevels++;
+	XFS_BTREE_TRACE_CURSOR(cur, XBT_EXIT);
+	*stat = 1;
+	return 0;
+error0:
+	XFS_BTREE_TRACE_CURSOR(cur, XBT_ERROR);
+	return error;
+out0:
+	XFS_BTREE_TRACE_CURSOR(cur, XBT_EXIT);
+	*stat = 0;
+	return 0;
+}
+
+STATIC int
+xfs_btree_make_block_unfull(
+	struct xfs_btree_cur	*cur,	/* btree cursor */
+	int			level,	/* btree level */
+	int			numrecs,/* # of recs in block */
+	int			*oindex,/* old tree index */
+	int			*index,	/* new tree index */
+	union xfs_btree_ptr	*nptr,	/* new btree ptr */
+	struct xfs_btree_cur	**ncur,	/* new btree cursor */
+	union xfs_btree_rec	*nrec,	/* new record */
+	int			*stat)
+{
+	union xfs_btree_key	key;	/* new btree key value */
+	int			error = 0;
+
+	if ((cur->bc_flags & XFS_BTREE_ROOT_IN_INODE) &&
+	    level == cur->bc_nlevels - 1) {
+	    	struct xfs_inode *ip = cur->bc_private.b.ip;
+
+		if (numrecs < cur->bc_ops->get_dmaxrecs(cur, level)) {
+			/* A root block that can be made bigger. */
+
+			xfs_iroot_realloc(ip, 1, cur->bc_private.b.whichfork);
+		} else {
+			/* A root block that needs replacing */
+			int	logflags = 0;
+
+			error = xfs_btree_new_iroot(cur, &logflags, stat);
+			if (error || *stat == 0)
+				return error;
+
+			xfs_trans_log_inode(cur->bc_tp, ip, logflags);
+		}
+
+		return 0;
+	}
+
+	/* First, try shifting an entry to the right neighbor. */
+	error = xfs_btree_rshift(cur, level, stat);
+	if (error || *stat)
+		return error;
+
+	/* Next, try shifting an entry to the left neighbor. */
+	error = xfs_btree_lshift(cur, level, stat);
+	if (error)
+		return error;
+
+	if (*stat) {
+		*oindex = *index = cur->bc_ptrs[level];
+		return 0;
+	}
+
+	/*
+	 * Next, try splitting the current block in half.
+	 *
+	 * If this works we have to re-set our variables because we
+	 * could be in a different block now.
+	 */
+	error = xfs_btree_split(cur, level, nptr, &key, ncur, stat);
+	if (error || *stat == 0)
+		return error;
+
+
+	*index = cur->bc_ptrs[level];
+	cur->bc_ops->init_rec_from_key(&key, nrec);
+	return 0;
+}
+
+/*
+ * Insert one record/level.  Return information to the caller
+ * allowing the next level up to proceed if necessary.
+ */
+STATIC int
+xfs_btree_insrec(
+	struct xfs_btree_cur	*cur,	/* btree cursor */
+	int			level,	/* level to insert record at */
+	union xfs_btree_ptr	*ptrp,	/* i/o: block number inserted */
+	union xfs_btree_rec	*recp,	/* i/o: record data inserted */
+	struct xfs_btree_cur	**curp,	/* output: new cursor replacing cur */
+	int			*stat)	/* success/failure */
+{
+	struct xfs_btree_block	*block;	/* btree block */
+	struct xfs_buf		*bp;	/* buffer for block */
+	union xfs_btree_key	key;	/* btree key */
+	union xfs_btree_ptr	nptr;	/* new block ptr */
+	struct xfs_btree_cur	*ncur;	/* new btree cursor */
+	union xfs_btree_rec	nrec;	/* new record count */
+	int			optr;	/* old key/record index */
+	int			ptr;	/* key/record index */
+	int			numrecs;/* number of records */
+	int			error;	/* error return value */
+#ifdef DEBUG
+	int			i;
+#endif
+
+	XFS_BTREE_TRACE_CURSOR(cur, XBT_ENTRY);
+	XFS_BTREE_TRACE_ARGIPR(cur, level, *ptrp, recp);
+
+	ncur = NULL;
+
+	/*
+	 * If we have an external root pointer, and we've made it to the
+	 * root level, allocate a new root block and we're done.
+	 */
+	if (!(cur->bc_flags & XFS_BTREE_ROOT_IN_INODE) &&
+	    (level >= cur->bc_nlevels)) {
+		error = xfs_btree_new_root(cur, stat);
+		xfs_btree_set_ptr_null(cur, ptrp);
+
+		XFS_BTREE_TRACE_CURSOR(cur, XBT_EXIT);
+		return error;
+	}
+
+	/* If we're off the left edge, return failure. */
+	ptr = cur->bc_ptrs[level];
+	if (ptr == 0) {
+		XFS_BTREE_TRACE_CURSOR(cur, XBT_EXIT);
+		*stat = 0;
+		return 0;
+	}
+
+	/* Make a key out of the record data to be inserted, and save it. */
+	cur->bc_ops->init_key_from_rec(&key, recp);
+
+	optr = ptr;
+
+	XFS_BTREE_STATS_INC(cur, insrec);
+
+	/* Get pointers to the btree buffer and block. */
+	block = xfs_btree_get_block(cur, level, &bp);
+	numrecs = xfs_btree_get_numrecs(block);
+
+#ifdef DEBUG
+	error = xfs_btree_check_block(cur, block, level, bp);
+	if (error)
+		goto error0;
+
+	/* Check that the new entry is being inserted in the right place. */
+	if (ptr <= numrecs) {
+		if (level == 0) {
+			ASSERT(cur->bc_ops->recs_inorder(cur, recp,
+				xfs_btree_rec_addr(cur, ptr, block)));
+		} else {
+			ASSERT(cur->bc_ops->keys_inorder(cur, &key,
+				xfs_btree_key_addr(cur, ptr, block)));
+		}
+	}
+#endif
+
+	/*
+	 * If the block is full, we can't insert the new entry until we
+	 * make the block un-full.
+	 */
+	xfs_btree_set_ptr_null(cur, &nptr);
+	if (numrecs == cur->bc_ops->get_maxrecs(cur, level)) {
+		error = xfs_btree_make_block_unfull(cur, level, numrecs,
+					&optr, &ptr, &nptr, &ncur, &nrec, stat);
+		if (error || *stat == 0)
+			goto error0;
+	}
+
+	/*
+	 * The current block may have changed if the block was
+	 * previously full and we have just made space in it.
+	 */
+	block = xfs_btree_get_block(cur, level, &bp);
+	numrecs = xfs_btree_get_numrecs(block);
+
+#ifdef DEBUG
+	error = xfs_btree_check_block(cur, block, level, bp);
+	if (error)
+		return error;
+#endif
+
+	/*
+	 * At this point we know there's room for our new entry in the block
+	 * we're pointing at.
+	 */
+	XFS_BTREE_STATS_ADD(cur, moves, numrecs - ptr + 1);
+
+	if (level > 0) {
+		/* It's a nonleaf. make a hole in the keys and ptrs */
+		union xfs_btree_key	*kp;
+		union xfs_btree_ptr	*pp;
+
+		kp = xfs_btree_key_addr(cur, ptr, block);
+		pp = xfs_btree_ptr_addr(cur, ptr, block);
+
+#ifdef DEBUG
+		for (i = numrecs - ptr; i >= 0; i--) {
+			error = xfs_btree_check_ptr(cur, pp, i, level);
+			if (error)
+				return error;
+		}
+#endif
+
+		xfs_btree_shift_keys(cur, kp, 1, numrecs - ptr + 1);
+		xfs_btree_shift_ptrs(cur, pp, 1, numrecs - ptr + 1);
+
+#ifdef DEBUG
+		error = xfs_btree_check_ptr(cur, ptrp, 0, level);
+		if (error)
+			goto error0;
+#endif
+
+		/* Now put the new data in, bump numrecs and log it. */
+		xfs_btree_copy_keys(cur, kp, &key, 1);
+		xfs_btree_copy_ptrs(cur, pp, ptrp, 1);
+		numrecs++;
+		xfs_btree_set_numrecs(block, numrecs);
+		xfs_btree_log_ptrs(cur, bp, ptr, numrecs);
+		xfs_btree_log_keys(cur, bp, ptr, numrecs);
+#ifdef DEBUG
+		if (ptr < numrecs) {
+			ASSERT(cur->bc_ops->keys_inorder(cur, kp,
+				xfs_btree_key_addr(cur, ptr + 1, block)));
+		}
+#endif
+	} else {
+		/* It's a leaf. make a hole in the records */
+		union xfs_btree_rec             *rp;
+
+		rp = xfs_btree_rec_addr(cur, ptr, block);
+
+		xfs_btree_shift_recs(cur, rp, 1, numrecs - ptr + 1);
+
+		/* Now put the new data in, bump numrecs and log it. */
+		xfs_btree_copy_recs(cur, rp, recp, 1);
+		xfs_btree_set_numrecs(block, ++numrecs);
+		xfs_btree_log_recs(cur, bp, ptr, numrecs);
+#ifdef DEBUG
+		if (ptr < numrecs) {
+			ASSERT(cur->bc_ops->recs_inorder(cur, rp,
+				xfs_btree_rec_addr(cur, ptr + 1, block)));
+		}
+#endif
+	}
+
+	/* Log the new number of records in the btree header. */
+	xfs_btree_log_block(cur, bp, XFS_BB_NUMRECS);
+
+	/* If we inserted at the start of a block, update the parents' keys. */
+	if (optr == 1) {
+		error = xfs_btree_updkey(cur, &key, level + 1);
+		if (error)
+			goto error0;
+	}
+
+	/*
+	 * If we are tracking the last record in the tree and
+	 * we are at the far right edge of the tree, update it.
+	 */
+	if (xfs_btree_is_lastrec(cur, block, level)) {
+		cur->bc_ops->update_lastrec(cur, block, recp,
+					    ptr, LASTREC_INSREC);
+	}
+
+	/*
+	 * Return the new block number, if any.
+	 * If there is one, give back a record value and a cursor too.
+	 */
+	*ptrp = nptr;
+	if (!xfs_btree_ptr_is_null(cur, &nptr)) {
+		*recp = nrec;
+		*curp = ncur;
+	}
+
+	XFS_BTREE_TRACE_CURSOR(cur, XBT_EXIT);
+	*stat = 1;
+	return 0;
+
+error0:
+	XFS_BTREE_TRACE_CURSOR(cur, XBT_ERROR);
+	return error;
+}
+
+/*
+ * Insert the record at the point referenced by cur.
+ *
+ * A multi-level split of the tree on insert will invalidate the original
+ * cursor.  All callers of this function should assume that the cursor is
+ * no longer valid and revalidate it.
+ */
+int
+xfs_btree_insert(
+	struct xfs_btree_cur	*cur,
+	int			*stat)
+{
+	int			error;	/* error return value */
+	int			i;	/* result value, 0 for failure */
+	int			level;	/* current level number in btree */
+	union xfs_btree_ptr	nptr;	/* new block number (split result) */
+	struct xfs_btree_cur	*ncur;	/* new cursor (split result) */
+	struct xfs_btree_cur	*pcur;	/* previous level's cursor */
+	union xfs_btree_rec	rec;	/* record to insert */
+
+	level = 0;
+	ncur = NULL;
+	pcur = cur;
+
+	xfs_btree_set_ptr_null(cur, &nptr);
+	cur->bc_ops->init_rec_from_cur(cur, &rec);
+
+	/*
+	 * Loop going up the tree, starting at the leaf level.
+	 * Stop when we don't get a split block, that must mean that
+	 * the insert is finished with this level.
+	 */
+	do {
+		/*
+		 * Insert nrec/nptr into this level of the tree.
+		 * Note if we fail, nptr will be null.
+		 */
+		error = xfs_btree_insrec(pcur, level, &nptr, &rec, &ncur, &i);
+		if (error) {
+			if (pcur != cur)
+				xfs_btree_del_cursor(pcur, XFS_BTREE_ERROR);
+			goto error0;
+		}
+
+		XFS_WANT_CORRUPTED_GOTO(i == 1, error0);
+		level++;
+
+		/*
+		 * See if the cursor we just used is trash.
+		 * Can't trash the caller's cursor, but otherwise we should
+		 * if ncur is a new cursor or we're about to be done.
+		 */
+		if (pcur != cur &&
+		    (ncur || xfs_btree_ptr_is_null(cur, &nptr))) {
+			/* Save the state from the cursor before we trash it */
+			if (cur->bc_ops->update_cursor)
+				cur->bc_ops->update_cursor(pcur, cur);
+			cur->bc_nlevels = pcur->bc_nlevels;
+			xfs_btree_del_cursor(pcur, XFS_BTREE_NOERROR);
+		}
+		/* If we got a new cursor, switch to it. */
+		if (ncur) {
+			pcur = ncur;
+			ncur = NULL;
+		}
+	} while (!xfs_btree_ptr_is_null(cur, &nptr));
+
+	XFS_BTREE_TRACE_CURSOR(cur, XBT_EXIT);
+	*stat = i;
+	return 0;
+error0:
+	XFS_BTREE_TRACE_CURSOR(cur, XBT_ERROR);
+	return error;
+}
+
+/*
+ * Try to merge a non-leaf block back into the inode root.
+ *
+ * Note: the killroot names comes from the fact that we're effectively
+ * killing the old root block.  But because we can't just delete the
+ * inode we have to copy the single block it was pointing to into the
+ * inode.
+ */
+int
+xfs_btree_kill_iroot(
+	struct xfs_btree_cur	*cur)
+{
+	int			whichfork = cur->bc_private.b.whichfork;
+	struct xfs_inode	*ip = cur->bc_private.b.ip;
+	struct xfs_ifork	*ifp = XFS_IFORK_PTR(ip, whichfork);
+	struct xfs_btree_block	*block;
+	struct xfs_btree_block	*cblock;
+	union xfs_btree_key	*kp;
+	union xfs_btree_key	*ckp;
+	union xfs_btree_ptr	*pp;
+	union xfs_btree_ptr	*cpp;
+	struct xfs_buf		*cbp;
+	int			level;
+	int			index;
+	int			numrecs;
+#ifdef DEBUG
+	union xfs_btree_ptr	ptr;
+	int			i;
+#endif
+
+	XFS_BTREE_TRACE_CURSOR(cur, XBT_ENTRY);
+
+	ASSERT(cur->bc_flags & XFS_BTREE_ROOT_IN_INODE);
+	ASSERT(cur->bc_nlevels > 1);
+
+	/*
+	 * Don't deal with the root block needs to be a leaf case.
+	 * We're just going to turn the thing back into extents anyway.
+	 */
+	level = cur->bc_nlevels - 1;
+	if (level == 1)
+		goto out0;
+
+	/*
+	 * Give up if the root has multiple children.
+	 */
+	block = xfs_btree_get_iroot(cur);
+	if (xfs_btree_get_numrecs(block) != 1)
+		goto out0;
+
+	cblock = xfs_btree_get_block(cur, level - 1, &cbp);
+	numrecs = xfs_btree_get_numrecs(cblock);
+
+	/*
+	 * Only do this if the next level will fit.
+	 * Then the data must be copied up to the inode,
+	 * instead of freeing the root you free the next level.
+	 */
+	if (numrecs > cur->bc_ops->get_dmaxrecs(cur, level))
+		goto out0;
+
+	XFS_BTREE_STATS_INC(cur, killroot);
+
+#ifdef DEBUG
+	xfs_btree_get_sibling(cur, block, &ptr, XFS_BB_LEFTSIB);
+	ASSERT(xfs_btree_ptr_is_null(cur, &ptr));
+	xfs_btree_get_sibling(cur, block, &ptr, XFS_BB_RIGHTSIB);
+	ASSERT(xfs_btree_ptr_is_null(cur, &ptr));
+#endif
+
+	index = numrecs - cur->bc_ops->get_maxrecs(cur, level);
+	if (index) {
+		xfs_iroot_realloc(cur->bc_private.b.ip, index,
+				  cur->bc_private.b.whichfork);
+		block = ifp->if_broot;
+	}
+
+	be16_add_cpu(&block->bb_numrecs, index);
+	ASSERT(block->bb_numrecs == cblock->bb_numrecs);
+
+	kp = xfs_btree_key_addr(cur, 1, block);
+	ckp = xfs_btree_key_addr(cur, 1, cblock);
+	xfs_btree_copy_keys(cur, kp, ckp, numrecs);
+
+	pp = xfs_btree_ptr_addr(cur, 1, block);
+	cpp = xfs_btree_ptr_addr(cur, 1, cblock);
+#ifdef DEBUG
+	for (i = 0; i < numrecs; i++) {
+		int		error;
+
+		error = xfs_btree_check_ptr(cur, cpp, i, level - 1);
+		if (error) {
+			XFS_BTREE_TRACE_CURSOR(cur, XBT_ERROR);
+			return error;
+		}
+	}
+#endif
+	xfs_btree_copy_ptrs(cur, pp, cpp, numrecs);
+
+	cur->bc_ops->free_block(cur, cbp);
+	XFS_BTREE_STATS_INC(cur, free);
+
+	cur->bc_bufs[level - 1] = NULL;
+	be16_add_cpu(&block->bb_level, -1);
+	xfs_trans_log_inode(cur->bc_tp, ip,
+		XFS_ILOG_CORE | XFS_ILOG_FBROOT(cur->bc_private.b.whichfork));
+	cur->bc_nlevels--;
+out0:
+	XFS_BTREE_TRACE_CURSOR(cur, XBT_EXIT);
+	return 0;
+}
+
+STATIC int
+xfs_btree_dec_cursor(
+	struct xfs_btree_cur	*cur,
+	int			level,
+	int			*stat)
+{
+	int			error;
+	int			i;
+
+	if (level > 0) {
+		error = xfs_btree_decrement(cur, level, &i);
+		if (error)
+			return error;
+	}
+
+	XFS_BTREE_TRACE_CURSOR(cur, XBT_EXIT);
+	*stat = 1;
+	return 0;
+}
+
+/*
+ * Single level of the btree record deletion routine.
+ * Delete record pointed to by cur/level.
+ * Remove the record from its block then rebalance the tree.
+ * Return 0 for error, 1 for done, 2 to go on to the next level.
+ */
+STATIC int					/* error */
+xfs_btree_delrec(
+	struct xfs_btree_cur	*cur,		/* btree cursor */
+	int			level,		/* level removing record from */
+	int			*stat)		/* fail/done/go-on */
+{
+	struct xfs_btree_block	*block;		/* btree block */
+	union xfs_btree_ptr	cptr;		/* current block ptr */
+	struct xfs_buf		*bp;		/* buffer for block */
+	int			error;		/* error return value */
+	int			i;		/* loop counter */
+	union xfs_btree_key	key;		/* storage for keyp */
+	union xfs_btree_key	*keyp = &key;	/* passed to the next level */
+	union xfs_btree_ptr	lptr;		/* left sibling block ptr */
+	struct xfs_buf		*lbp;		/* left buffer pointer */
+	struct xfs_btree_block	*left;		/* left btree block */
+	int			lrecs = 0;	/* left record count */
+	int			ptr;		/* key/record index */
+	union xfs_btree_ptr	rptr;		/* right sibling block ptr */
+	struct xfs_buf		*rbp;		/* right buffer pointer */
+	struct xfs_btree_block	*right;		/* right btree block */
+	struct xfs_btree_block	*rrblock;	/* right-right btree block */
+	struct xfs_buf		*rrbp;		/* right-right buffer pointer */
+	int			rrecs = 0;	/* right record count */
+	struct xfs_btree_cur	*tcur;		/* temporary btree cursor */
+	int			numrecs;	/* temporary numrec count */
+
+	XFS_BTREE_TRACE_CURSOR(cur, XBT_ENTRY);
+	XFS_BTREE_TRACE_ARGI(cur, level);
+
+	tcur = NULL;
+
+	/* Get the index of the entry being deleted, check for nothing there. */
+	ptr = cur->bc_ptrs[level];
+	if (ptr == 0) {
+		XFS_BTREE_TRACE_CURSOR(cur, XBT_EXIT);
+		*stat = 0;
+		return 0;
+	}
+
+	/* Get the buffer & block containing the record or key/ptr. */
+	block = xfs_btree_get_block(cur, level, &bp);
+	numrecs = xfs_btree_get_numrecs(block);
+
+#ifdef DEBUG
+	error = xfs_btree_check_block(cur, block, level, bp);
+	if (error)
+		goto error0;
+#endif
+
+	/* Fail if we're off the end of the block. */
+	if (ptr > numrecs) {
+		XFS_BTREE_TRACE_CURSOR(cur, XBT_EXIT);
+		*stat = 0;
+		return 0;
+	}
+
+	XFS_BTREE_STATS_INC(cur, delrec);
+	XFS_BTREE_STATS_ADD(cur, moves, numrecs - ptr);
+
+	/* Excise the entries being deleted. */
+	if (level > 0) {
+		/* It's a nonleaf. operate on keys and ptrs */
+		union xfs_btree_key	*lkp;
+		union xfs_btree_ptr	*lpp;
+
+		lkp = xfs_btree_key_addr(cur, ptr + 1, block);
+		lpp = xfs_btree_ptr_addr(cur, ptr + 1, block);
+
+#ifdef DEBUG
+		for (i = 0; i < numrecs - ptr; i++) {
+			error = xfs_btree_check_ptr(cur, lpp, i, level);
+			if (error)
+				goto error0;
+		}
+#endif
+
+		if (ptr < numrecs) {
+			xfs_btree_shift_keys(cur, lkp, -1, numrecs - ptr);
+			xfs_btree_shift_ptrs(cur, lpp, -1, numrecs - ptr);
+			xfs_btree_log_keys(cur, bp, ptr, numrecs - 1);
+			xfs_btree_log_ptrs(cur, bp, ptr, numrecs - 1);
+		}
+
+		/*
+		 * If it's the first record in the block, we'll need to pass a
+		 * key up to the next level (updkey).
+		 */
+		if (ptr == 1)
+			keyp = xfs_btree_key_addr(cur, 1, block);
+	} else {
+		/* It's a leaf. operate on records */
+		if (ptr < numrecs) {
+			xfs_btree_shift_recs(cur,
+				xfs_btree_rec_addr(cur, ptr + 1, block),
+				-1, numrecs - ptr);
+			xfs_btree_log_recs(cur, bp, ptr, numrecs - 1);
+		}
+
+		/*
+		 * If it's the first record in the block, we'll need a key
+		 * structure to pass up to the next level (updkey).
+		 */
+		if (ptr == 1) {
+			cur->bc_ops->init_key_from_rec(&key,
+					xfs_btree_rec_addr(cur, 1, block));
+			keyp = &key;
+		}
+	}
+
+	/*
+	 * Decrement and log the number of entries in the block.
+	 */
+	xfs_btree_set_numrecs(block, --numrecs);
+	xfs_btree_log_block(cur, bp, XFS_BB_NUMRECS);
+
+	/*
+	 * If we are tracking the last record in the tree and
+	 * we are at the far right edge of the tree, update it.
+	 */
+	if (xfs_btree_is_lastrec(cur, block, level)) {
+		cur->bc_ops->update_lastrec(cur, block, NULL,
+					    ptr, LASTREC_DELREC);
+	}
+
+	/*
+	 * We're at the root level.  First, shrink the root block in-memory.
+	 * Try to get rid of the next level down.  If we can't then there's
+	 * nothing left to do.
+	 */
+	if (level == cur->bc_nlevels - 1) {
+		if (cur->bc_flags & XFS_BTREE_ROOT_IN_INODE) {
+			xfs_iroot_realloc(cur->bc_private.b.ip, -1,
+					  cur->bc_private.b.whichfork);
+
+			error = xfs_btree_kill_iroot(cur);
+			if (error)
+				goto error0;
+
+			error = xfs_btree_dec_cursor(cur, level, stat);
+			if (error)
+				goto error0;
+			*stat = 1;
+			return 0;
+		}
+
+		/*
+		 * If this is the root level, and there's only one entry left,
+		 * and it's NOT the leaf level, then we can get rid of this
+		 * level.
+		 */
+		if (numrecs == 1 && level > 0) {
+			union xfs_btree_ptr	*pp;
+			/*
+			 * pp is still set to the first pointer in the block.
+			 * Make it the new root of the btree.
+			 */
+			pp = xfs_btree_ptr_addr(cur, 1, block);
+			error = cur->bc_ops->kill_root(cur, bp, level, pp);
+			if (error)
+				goto error0;
+		} else if (level > 0) {
+			error = xfs_btree_dec_cursor(cur, level, stat);
+			if (error)
+				goto error0;
+		}
+		*stat = 1;
+		return 0;
+	}
+
+	/*
+	 * If we deleted the leftmost entry in the block, update the
+	 * key values above us in the tree.
+	 */
+	if (ptr == 1) {
+		error = xfs_btree_updkey(cur, keyp, level + 1);
+		if (error)
+			goto error0;
+	}
+
+	/*
+	 * If the number of records remaining in the block is at least
+	 * the minimum, we're done.
+	 */
+	if (numrecs >= cur->bc_ops->get_minrecs(cur, level)) {
+		error = xfs_btree_dec_cursor(cur, level, stat);
+		if (error)
+			goto error0;
+		return 0;
+	}
+
+	/*
+	 * Otherwise, we have to move some records around to keep the
+	 * tree balanced.  Look at the left and right sibling blocks to
+	 * see if we can re-balance by moving only one record.
+	 */
+	xfs_btree_get_sibling(cur, block, &rptr, XFS_BB_RIGHTSIB);
+	xfs_btree_get_sibling(cur, block, &lptr, XFS_BB_LEFTSIB);
+
+	if (cur->bc_flags & XFS_BTREE_ROOT_IN_INODE) {
+		/*
+		 * One child of root, need to get a chance to copy its contents
+		 * into the root and delete it. Can't go up to next level,
+		 * there's nothing to delete there.
+		 */
+		if (xfs_btree_ptr_is_null(cur, &rptr) &&
+		    xfs_btree_ptr_is_null(cur, &lptr) &&
+		    level == cur->bc_nlevels - 2) {
+			error = xfs_btree_kill_iroot(cur);
+			if (!error)
+				error = xfs_btree_dec_cursor(cur, level, stat);
+			if (error)
+				goto error0;
+			return 0;
+		}
+	}
+
+	ASSERT(!xfs_btree_ptr_is_null(cur, &rptr) ||
+	       !xfs_btree_ptr_is_null(cur, &lptr));
+
+	/*
+	 * Duplicate the cursor so our btree manipulations here won't
+	 * disrupt the next level up.
+	 */
+	error = xfs_btree_dup_cursor(cur, &tcur);
+	if (error)
+		goto error0;
+
+	/*
+	 * If there's a right sibling, see if it's ok to shift an entry
+	 * out of it.
+	 */
+	if (!xfs_btree_ptr_is_null(cur, &rptr)) {
+		/*
+		 * Move the temp cursor to the last entry in the next block.
+		 * Actually any entry but the first would suffice.
+		 */
+		i = xfs_btree_lastrec(tcur, level);
+		XFS_WANT_CORRUPTED_GOTO(i == 1, error0);
+
+		error = xfs_btree_increment(tcur, level, &i);
+		if (error)
+			goto error0;
+		XFS_WANT_CORRUPTED_GOTO(i == 1, error0);
+
+		i = xfs_btree_lastrec(tcur, level);
+		XFS_WANT_CORRUPTED_GOTO(i == 1, error0);
+
+		/* Grab a pointer to the block. */
+		right = xfs_btree_get_block(tcur, level, &rbp);
+#ifdef DEBUG
+		error = xfs_btree_check_block(tcur, right, level, rbp);
+		if (error)
+			goto error0;
+#endif
+		/* Grab the current block number, for future use. */
+		xfs_btree_get_sibling(tcur, right, &cptr, XFS_BB_LEFTSIB);
+
+		/*
+		 * If right block is full enough so that removing one entry
+		 * won't make it too empty, and left-shifting an entry out
+		 * of right to us works, we're done.
+		 */
+		if (xfs_btree_get_numrecs(right) - 1 >=
+		    cur->bc_ops->get_minrecs(tcur, level)) {
+			error = xfs_btree_lshift(tcur, level, &i);
+			if (error)
+				goto error0;
+			if (i) {
+				ASSERT(xfs_btree_get_numrecs(block) >=
+				       cur->bc_ops->get_minrecs(tcur, level));
+
+				xfs_btree_del_cursor(tcur, XFS_BTREE_NOERROR);
+				tcur = NULL;
+
+				error = xfs_btree_dec_cursor(cur, level, stat);
+				if (error)
+					goto error0;
+				return 0;
+			}
+		}
+
+		/*
+		 * Otherwise, grab the number of records in right for
+		 * future reference, and fix up the temp cursor to point
+		 * to our block again (last record).
+		 */
+		rrecs = xfs_btree_get_numrecs(right);
+		if (!xfs_btree_ptr_is_null(cur, &lptr)) {
+			i = xfs_btree_firstrec(tcur, level);
+			XFS_WANT_CORRUPTED_GOTO(i == 1, error0);
+
+			error = xfs_btree_decrement(tcur, level, &i);
+			if (error)
+				goto error0;
+			XFS_WANT_CORRUPTED_GOTO(i == 1, error0);
+		}
+	}
+
+	/*
+	 * If there's a left sibling, see if it's ok to shift an entry
+	 * out of it.
+	 */
+	if (!xfs_btree_ptr_is_null(cur, &lptr)) {
+		/*
+		 * Move the temp cursor to the first entry in the
+		 * previous block.
+		 */
+		i = xfs_btree_firstrec(tcur, level);
+		XFS_WANT_CORRUPTED_GOTO(i == 1, error0);
+
+		error = xfs_btree_decrement(tcur, level, &i);
+		if (error)
+			goto error0;
+		i = xfs_btree_firstrec(tcur, level);
+		XFS_WANT_CORRUPTED_GOTO(i == 1, error0);
+
+		/* Grab a pointer to the block. */
+		left = xfs_btree_get_block(tcur, level, &lbp);
+#ifdef DEBUG
+		error = xfs_btree_check_block(cur, left, level, lbp);
+		if (error)
+			goto error0;
+#endif
+		/* Grab the current block number, for future use. */
+		xfs_btree_get_sibling(tcur, left, &cptr, XFS_BB_RIGHTSIB);
+
+		/*
+		 * If left block is full enough so that removing one entry
+		 * won't make it too empty, and right-shifting an entry out
+		 * of left to us works, we're done.
+		 */
+		if (xfs_btree_get_numrecs(left) - 1 >=
+		    cur->bc_ops->get_minrecs(tcur, level)) {
+			error = xfs_btree_rshift(tcur, level, &i);
+			if (error)
+				goto error0;
+			if (i) {
+				ASSERT(xfs_btree_get_numrecs(block) >=
+				       cur->bc_ops->get_minrecs(tcur, level));
+				xfs_btree_del_cursor(tcur, XFS_BTREE_NOERROR);
+				tcur = NULL;
+				if (level == 0)
+					cur->bc_ptrs[0]++;
+				XFS_BTREE_TRACE_CURSOR(cur, XBT_EXIT);
+				*stat = 1;
+				return 0;
+			}
+		}
+
+		/*
+		 * Otherwise, grab the number of records in right for
+		 * future reference.
+		 */
+		lrecs = xfs_btree_get_numrecs(left);
+	}
+
+	/* Delete the temp cursor, we're done with it. */
+	xfs_btree_del_cursor(tcur, XFS_BTREE_NOERROR);
+	tcur = NULL;
+
+	/* If here, we need to do a join to keep the tree balanced. */
+	ASSERT(!xfs_btree_ptr_is_null(cur, &cptr));
+
+	if (!xfs_btree_ptr_is_null(cur, &lptr) &&
+	    lrecs + xfs_btree_get_numrecs(block) <=
+			cur->bc_ops->get_maxrecs(cur, level)) {
+		/*
+		 * Set "right" to be the starting block,
+		 * "left" to be the left neighbor.
+		 */
+		rptr = cptr;
+		right = block;
+		rbp = bp;
+		error = xfs_btree_read_buf_block(cur, &lptr, level,
+							0, &left, &lbp);
+		if (error)
+			goto error0;
+
+	/*
+	 * If that won't work, see if we can join with the right neighbor block.
+	 */
+	} else if (!xfs_btree_ptr_is_null(cur, &rptr) &&
+		   rrecs + xfs_btree_get_numrecs(block) <=
+			cur->bc_ops->get_maxrecs(cur, level)) {
+		/*
+		 * Set "left" to be the starting block,
+		 * "right" to be the right neighbor.
+		 */
+		lptr = cptr;
+		left = block;
+		lbp = bp;
+		error = xfs_btree_read_buf_block(cur, &rptr, level,
+							0, &right, &rbp);
+		if (error)
+			goto error0;
+
+	/*
+	 * Otherwise, we can't fix the imbalance.
+	 * Just return.  This is probably a logic error, but it's not fatal.
+	 */
+	} else {
+		error = xfs_btree_dec_cursor(cur, level, stat);
+		if (error)
+			goto error0;
+		return 0;
+	}
+
+	rrecs = xfs_btree_get_numrecs(right);
+	lrecs = xfs_btree_get_numrecs(left);
+
+	/*
+	 * We're now going to join "left" and "right" by moving all the stuff
+	 * in "right" to "left" and deleting "right".
+	 */
+	XFS_BTREE_STATS_ADD(cur, moves, rrecs);
+	if (level > 0) {
+		/* It's a non-leaf.  Move keys and pointers. */
+		union xfs_btree_key	*lkp;	/* left btree key */
+		union xfs_btree_ptr	*lpp;	/* left address pointer */
+		union xfs_btree_key	*rkp;	/* right btree key */
+		union xfs_btree_ptr	*rpp;	/* right address pointer */
+
+		lkp = xfs_btree_key_addr(cur, lrecs + 1, left);
+		lpp = xfs_btree_ptr_addr(cur, lrecs + 1, left);
+		rkp = xfs_btree_key_addr(cur, 1, right);
+		rpp = xfs_btree_ptr_addr(cur, 1, right);
+#ifdef DEBUG
+		for (i = 1; i < rrecs; i++) {
+			error = xfs_btree_check_ptr(cur, rpp, i, level);
+			if (error)
+				goto error0;
+		}
+#endif
+		xfs_btree_copy_keys(cur, lkp, rkp, rrecs);
+		xfs_btree_copy_ptrs(cur, lpp, rpp, rrecs);
+
+		xfs_btree_log_keys(cur, lbp, lrecs + 1, lrecs + rrecs);
+		xfs_btree_log_ptrs(cur, lbp, lrecs + 1, lrecs + rrecs);
+	} else {
+		/* It's a leaf.  Move records.  */
+		union xfs_btree_rec	*lrp;	/* left record pointer */
+		union xfs_btree_rec	*rrp;	/* right record pointer */
+
+		lrp = xfs_btree_rec_addr(cur, lrecs + 1, left);
+		rrp = xfs_btree_rec_addr(cur, 1, right);
+
+		xfs_btree_copy_recs(cur, lrp, rrp, rrecs);
+		xfs_btree_log_recs(cur, lbp, lrecs + 1, lrecs + rrecs);
+	}
+
+	XFS_BTREE_STATS_INC(cur, join);
+
+	/*
+	 * Fix up the the number of records and right block pointer in the
+	 * surviving block, and log it.
+	 */
+	xfs_btree_set_numrecs(left, lrecs + rrecs);
+	xfs_btree_get_sibling(cur, right, &cptr, XFS_BB_RIGHTSIB),
+	xfs_btree_set_sibling(cur, left, &cptr, XFS_BB_RIGHTSIB);
+	xfs_btree_log_block(cur, lbp, XFS_BB_NUMRECS | XFS_BB_RIGHTSIB);
+
+	/* If there is a right sibling, point it to the remaining block. */
+	xfs_btree_get_sibling(cur, left, &cptr, XFS_BB_RIGHTSIB);
+	if (!xfs_btree_ptr_is_null(cur, &cptr)) {
+		error = xfs_btree_read_buf_block(cur, &cptr, level,
+							0, &rrblock, &rrbp);
+		if (error)
+			goto error0;
+		xfs_btree_set_sibling(cur, rrblock, &lptr, XFS_BB_LEFTSIB);
+		xfs_btree_log_block(cur, rrbp, XFS_BB_LEFTSIB);
+	}
+
+	/* Free the deleted block. */
+	error = cur->bc_ops->free_block(cur, rbp);
+	if (error)
+		goto error0;
+	XFS_BTREE_STATS_INC(cur, free);
+
+	/*
+	 * If we joined with the left neighbor, set the buffer in the
+	 * cursor to the left block, and fix up the index.
+	 */
+	if (bp != lbp) {
+		cur->bc_bufs[level] = lbp;
+		cur->bc_ptrs[level] += lrecs;
+		cur->bc_ra[level] = 0;
+	}
+	/*
+	 * If we joined with the right neighbor and there's a level above
+	 * us, increment the cursor at that level.
+	 */
+	else if ((cur->bc_flags & XFS_BTREE_ROOT_IN_INODE) ||
+		   (level + 1 < cur->bc_nlevels)) {
+		error = xfs_btree_increment(cur, level + 1, &i);
+		if (error)
+			goto error0;
+	}
+
+	/*
+	 * Readjust the ptr at this level if it's not a leaf, since it's
+	 * still pointing at the deletion point, which makes the cursor
+	 * inconsistent.  If this makes the ptr 0, the caller fixes it up.
+	 * We can't use decrement because it would change the next level up.
+	 */
+	if (level > 0)
+		cur->bc_ptrs[level]--;
+
+	XFS_BTREE_TRACE_CURSOR(cur, XBT_EXIT);
+	/* Return value means the next level up has something to do. */
+	*stat = 2;
+	return 0;
+
+error0:
+	XFS_BTREE_TRACE_CURSOR(cur, XBT_ERROR);
+	if (tcur)
+		xfs_btree_del_cursor(tcur, XFS_BTREE_ERROR);
+	return error;
+}
+
+/*
+ * Delete the record pointed to by cur.
+ * The cursor refers to the place where the record was (could be inserted)
+ * when the operation returns.
+ */
+int					/* error */
+xfs_btree_delete(
+	struct xfs_btree_cur	*cur,
+	int			*stat)	/* success/failure */
+{
+	int			error;	/* error return value */
+	int			level;
+	int			i;
+
+	XFS_BTREE_TRACE_CURSOR(cur, XBT_ENTRY);
+
+	/*
+	 * Go up the tree, starting at leaf level.
+	 *
+	 * If 2 is returned then a join was done; go to the next level.
+	 * Otherwise we are done.
+	 */
+	for (level = 0, i = 2; i == 2; level++) {
+		error = xfs_btree_delrec(cur, level, &i);
+		if (error)
+			goto error0;
+	}
+
+	if (i == 0) {
+		for (level = 1; level < cur->bc_nlevels; level++) {
+			if (cur->bc_ptrs[level] == 0) {
+				error = xfs_btree_decrement(cur, level, &i);
+				if (error)
+					goto error0;
+				break;
+			}
+		}
+	}
+
+	XFS_BTREE_TRACE_CURSOR(cur, XBT_EXIT);
+	*stat = i;
+	return 0;
+error0:
+	XFS_BTREE_TRACE_CURSOR(cur, XBT_ERROR);
+	return error;
+}
+
+/*
+ * Get the data from the pointed-to record.
+ */
+int					/* error */
+xfs_btree_get_rec(
+	struct xfs_btree_cur	*cur,	/* btree cursor */
+	union xfs_btree_rec	**recp,	/* output: btree record */
+	int			*stat)	/* output: success/failure */
+{
+	struct xfs_btree_block	*block;	/* btree block */
+	struct xfs_buf		*bp;	/* buffer pointer */
+	int			ptr;	/* record number */
+#ifdef DEBUG
+	int			error;	/* error return value */
+#endif
+
+	ptr = cur->bc_ptrs[0];
+	block = xfs_btree_get_block(cur, 0, &bp);
+
+#ifdef DEBUG
+	error = xfs_btree_check_block(cur, block, 0, bp);
+	if (error)
+		return error;
+#endif
+
+	/*
+	 * Off the right end or left end, return failure.
+	 */
+	if (ptr > xfs_btree_get_numrecs(block) || ptr <= 0) {
+		*stat = 0;
+		return 0;
+	}
+
+	/*
+	 * Point to the record and extract its data.
+	 */
+	*recp = xfs_btree_rec_addr(cur, ptr, block);
+	*stat = 1;
+	return 0;
+}
diff --git a/fs/xfs/xfs_btree.h b/fs/xfs/xfs_btree.h
index 1f528a2a3754..789fffdf8b2f 100644
--- a/fs/xfs/xfs_btree.h
+++ b/fs/xfs/xfs_btree.h
@@ -39,39 +39,19 @@ extern kmem_zone_t	*xfs_btree_cur_zone;
 #define	XFS_BTNUM_INO	((xfs_btnum_t)XFS_BTNUM_INOi)
 
 /*
- * Short form header: space allocation btrees.
- */
-typedef struct xfs_btree_sblock {
-	__be32		bb_magic;	/* magic number for block type */
-	__be16		bb_level;	/* 0 is a leaf */
-	__be16		bb_numrecs;	/* current # of data records */
-	__be32		bb_leftsib;	/* left sibling block or NULLAGBLOCK */
-	__be32		bb_rightsib;	/* right sibling block or NULLAGBLOCK */
-} xfs_btree_sblock_t;
-
-/*
- * Long form header: bmap btrees.
- */
-typedef struct xfs_btree_lblock {
-	__be32		bb_magic;	/* magic number for block type */
-	__be16		bb_level;	/* 0 is a leaf */
-	__be16		bb_numrecs;	/* current # of data records */
-	__be64		bb_leftsib;	/* left sibling block or NULLDFSBNO */
-	__be64		bb_rightsib;	/* right sibling block or NULLDFSBNO */
-} xfs_btree_lblock_t;
-
-/*
- * Combined header and structure, used by common code.
+ * Generic btree header.
+ *
+ * This is a comination of the actual format used on disk for short and long
+ * format btrees.  The first three fields are shared by both format, but
+ * the pointers are different and should be used with care.
+ *
+ * To get the size of the actual short or long form headers please use
+ * the size macros below.  Never use sizeof(xfs_btree_block).
  */
-typedef struct xfs_btree_hdr
-{
+struct xfs_btree_block {
 	__be32		bb_magic;	/* magic number for block type */
 	__be16		bb_level;	/* 0 is a leaf */
 	__be16		bb_numrecs;	/* current # of data records */
-} xfs_btree_hdr_t;
-
-typedef struct xfs_btree_block {
-	xfs_btree_hdr_t	bb_h;		/* header */
 	union {
 		struct {
 			__be32		bb_leftsib;
@@ -82,7 +62,36 @@ typedef struct xfs_btree_block {
 			__be64		bb_rightsib;
 		} l;			/* long form pointers */
 	} bb_u;				/* rest */
-} xfs_btree_block_t;
+};
+
+#define XFS_BTREE_SBLOCK_LEN	16	/* size of a short form block */
+#define XFS_BTREE_LBLOCK_LEN	24	/* size of a long form block */
+
+
+/*
+ * Generic key, ptr and record wrapper structures.
+ *
+ * These are disk format structures, and are converted where necessary
+ * by the btree specific code that needs to interpret them.
+ */
+union xfs_btree_ptr {
+	__be32			s;	/* short form ptr */
+	__be64			l;	/* long form ptr */
+};
+
+union xfs_btree_key {
+	xfs_bmbt_key_t		bmbt;
+	xfs_bmdr_key_t		bmbr;	/* bmbt root block */
+	xfs_alloc_key_t		alloc;
+	xfs_inobt_key_t		inobt;
+};
+
+union xfs_btree_rec {
+	xfs_bmbt_rec_t		bmbt;
+	xfs_bmdr_rec_t		bmbr;	/* bmbt root block */
+	xfs_alloc_rec_t		alloc;
+	xfs_inobt_rec_t		inobt;
+};
 
 /*
  * For logging record fields.
@@ -96,46 +105,131 @@ typedef struct xfs_btree_block {
 #define	XFS_BB_ALL_BITS		((1 << XFS_BB_NUM_BITS) - 1)
 
 /*
- * Boolean to select which form of xfs_btree_block_t.bb_u to use.
- */
-#define	XFS_BTREE_LONG_PTRS(btnum)	((btnum) == XFS_BTNUM_BMAP)
-
-/*
  * Magic numbers for btree blocks.
  */
 extern const __uint32_t	xfs_magics[];
 
 /*
- * Maximum and minimum records in a btree block.
- * Given block size, type prefix, and leaf flag (0 or 1).
- * The divisor below is equivalent to lf ? (e1) : (e2) but that produces
- * compiler warnings.
- */
-#define	XFS_BTREE_BLOCK_MAXRECS(bsz,t,lf)	\
-	((int)(((bsz) - (uint)sizeof(t ## _block_t)) / \
-	 (((lf) * (uint)sizeof(t ## _rec_t)) + \
-	  ((1 - (lf)) * \
-	   ((uint)sizeof(t ## _key_t) + (uint)sizeof(t ## _ptr_t))))))
-#define	XFS_BTREE_BLOCK_MINRECS(bsz,t,lf)	\
-	(XFS_BTREE_BLOCK_MAXRECS(bsz,t,lf) / 2)
-
-/*
- * Record, key, and pointer address calculation macros.
- * Given block size, type prefix, block pointer, and index of requested entry
- * (first entry numbered 1).
- */
-#define	XFS_BTREE_REC_ADDR(t,bb,i)	\
-	((t ## _rec_t *)((char *)(bb) + sizeof(t ## _block_t) + \
-	 ((i) - 1) * sizeof(t ## _rec_t)))
-#define	XFS_BTREE_KEY_ADDR(t,bb,i)	\
-	((t ## _key_t *)((char *)(bb) + sizeof(t ## _block_t) + \
-	 ((i) - 1) * sizeof(t ## _key_t)))
-#define	XFS_BTREE_PTR_ADDR(t,bb,i,mxr)	\
-	((t ## _ptr_t *)((char *)(bb) + sizeof(t ## _block_t) + \
-	 (mxr) * sizeof(t ## _key_t) + ((i) - 1) * sizeof(t ## _ptr_t)))
+ * Generic stats interface
+ */
+#define __XFS_BTREE_STATS_INC(type, stat) \
+	XFS_STATS_INC(xs_ ## type ## _2_ ## stat)
+#define XFS_BTREE_STATS_INC(cur, stat)  \
+do {    \
+	switch (cur->bc_btnum) {  \
+	case XFS_BTNUM_BNO: __XFS_BTREE_STATS_INC(abtb, stat); break;	\
+	case XFS_BTNUM_CNT: __XFS_BTREE_STATS_INC(abtc, stat); break;	\
+	case XFS_BTNUM_BMAP: __XFS_BTREE_STATS_INC(bmbt, stat); break;	\
+	case XFS_BTNUM_INO: __XFS_BTREE_STATS_INC(ibt, stat); break;	\
+	case XFS_BTNUM_MAX: ASSERT(0); /* fucking gcc */ ; break;	\
+	}       \
+} while (0)
+
+#define __XFS_BTREE_STATS_ADD(type, stat, val) \
+	XFS_STATS_ADD(xs_ ## type ## _2_ ## stat, val)
+#define XFS_BTREE_STATS_ADD(cur, stat, val)  \
+do {    \
+	switch (cur->bc_btnum) {  \
+	case XFS_BTNUM_BNO: __XFS_BTREE_STATS_ADD(abtb, stat, val); break; \
+	case XFS_BTNUM_CNT: __XFS_BTREE_STATS_ADD(abtc, stat, val); break; \
+	case XFS_BTNUM_BMAP: __XFS_BTREE_STATS_ADD(bmbt, stat, val); break; \
+	case XFS_BTNUM_INO: __XFS_BTREE_STATS_ADD(ibt, stat, val); break; \
+	case XFS_BTNUM_MAX: ASSERT(0); /* fucking gcc */ ; break;	\
+	}       \
+} while (0)
 
 #define	XFS_BTREE_MAXLEVELS	8	/* max of all btrees */
 
+struct xfs_btree_ops {
+	/* size of the key and record structures */
+	size_t	key_len;
+	size_t	rec_len;
+
+	/* cursor operations */
+	struct xfs_btree_cur *(*dup_cursor)(struct xfs_btree_cur *);
+	void	(*update_cursor)(struct xfs_btree_cur *src,
+				 struct xfs_btree_cur *dst);
+
+	/* update btree root pointer */
+	void	(*set_root)(struct xfs_btree_cur *cur,
+				union xfs_btree_ptr *nptr, int level_change);
+	int	(*kill_root)(struct xfs_btree_cur *cur, struct xfs_buf *bp,
+				int level, union xfs_btree_ptr *newroot);
+
+	/* block allocation / freeing */
+	int	(*alloc_block)(struct xfs_btree_cur *cur,
+			       union xfs_btree_ptr *start_bno,
+			       union xfs_btree_ptr *new_bno,
+			       int length, int *stat);
+	int	(*free_block)(struct xfs_btree_cur *cur, struct xfs_buf *bp);
+
+	/* update last record information */
+	void	(*update_lastrec)(struct xfs_btree_cur *cur,
+				  struct xfs_btree_block *block,
+				  union xfs_btree_rec *rec,
+				  int ptr, int reason);
+
+	/* records in block/level */
+	int	(*get_minrecs)(struct xfs_btree_cur *cur, int level);
+	int	(*get_maxrecs)(struct xfs_btree_cur *cur, int level);
+
+	/* records on disk.  Matter for the root in inode case. */
+	int	(*get_dmaxrecs)(struct xfs_btree_cur *cur, int level);
+
+	/* init values of btree structures */
+	void	(*init_key_from_rec)(union xfs_btree_key *key,
+				     union xfs_btree_rec *rec);
+	void	(*init_rec_from_key)(union xfs_btree_key *key,
+				     union xfs_btree_rec *rec);
+	void	(*init_rec_from_cur)(struct xfs_btree_cur *cur,
+				     union xfs_btree_rec *rec);
+	void	(*init_ptr_from_cur)(struct xfs_btree_cur *cur,
+				     union xfs_btree_ptr *ptr);
+
+	/* difference between key value and cursor value */
+	__int64_t (*key_diff)(struct xfs_btree_cur *cur,
+			      union xfs_btree_key *key);
+
+#ifdef DEBUG
+	/* check that k1 is lower than k2 */
+	int	(*keys_inorder)(struct xfs_btree_cur *cur,
+				union xfs_btree_key *k1,
+				union xfs_btree_key *k2);
+
+	/* check that r1 is lower than r2 */
+	int	(*recs_inorder)(struct xfs_btree_cur *cur,
+				union xfs_btree_rec *r1,
+				union xfs_btree_rec *r2);
+#endif
+
+	/* btree tracing */
+#ifdef XFS_BTREE_TRACE
+	void		(*trace_enter)(struct xfs_btree_cur *, const char *,
+				       char *, int, int, __psunsigned_t,
+				       __psunsigned_t, __psunsigned_t,
+				       __psunsigned_t, __psunsigned_t,
+				       __psunsigned_t, __psunsigned_t,
+				       __psunsigned_t, __psunsigned_t,
+				       __psunsigned_t, __psunsigned_t);
+	void		(*trace_cursor)(struct xfs_btree_cur *, __uint32_t *,
+					__uint64_t *, __uint64_t *);
+	void		(*trace_key)(struct xfs_btree_cur *,
+				     union xfs_btree_key *, __uint64_t *,
+				     __uint64_t *);
+	void		(*trace_record)(struct xfs_btree_cur *,
+					union xfs_btree_rec *, __uint64_t *,
+					__uint64_t *, __uint64_t *);
+#endif
+};
+
+/*
+ * Reasons for the update_lastrec method to be called.
+ */
+#define LASTREC_UPDATE	0
+#define LASTREC_INSREC	1
+#define LASTREC_DELREC	2
+
+
 /*
  * Btree cursor structure.
  * This collects all information needed by the btree code in one place.
@@ -144,6 +238,8 @@ typedef struct xfs_btree_cur
 {
 	struct xfs_trans	*bc_tp;	/* transaction we're in, if any */
 	struct xfs_mount	*bc_mp;	/* file system mount struct */
+	const struct xfs_btree_ops *bc_ops;
+	uint			bc_flags; /* btree features - below */
 	union {
 		xfs_alloc_rec_incore_t	a;
 		xfs_bmbt_irec_t		b;
@@ -175,94 +271,40 @@ typedef struct xfs_btree_cur
 	}		bc_private;	/* per-btree type data */
 } xfs_btree_cur_t;
 
+/* cursor flags */
+#define XFS_BTREE_LONG_PTRS		(1<<0)	/* pointers are 64bits long */
+#define XFS_BTREE_ROOT_IN_INODE		(1<<1)	/* root may be variable size */
+#define XFS_BTREE_LASTREC_UPDATE	(1<<2)	/* track last rec externally */
+
+
 #define	XFS_BTREE_NOERROR	0
 #define	XFS_BTREE_ERROR		1
 
 /*
  * Convert from buffer to btree block header.
  */
-#define	XFS_BUF_TO_BLOCK(bp)	((xfs_btree_block_t *)XFS_BUF_PTR(bp))
-#define	XFS_BUF_TO_LBLOCK(bp)	((xfs_btree_lblock_t *)XFS_BUF_PTR(bp))
-#define	XFS_BUF_TO_SBLOCK(bp)	((xfs_btree_sblock_t *)XFS_BUF_PTR(bp))
+#define	XFS_BUF_TO_BLOCK(bp)	((struct xfs_btree_block *)XFS_BUF_PTR(bp))
 
 
-#ifdef __KERNEL__
-
-#ifdef DEBUG
 /*
- * Debug routine: check that block header is ok.
+ * Check that block header is ok.
  */
-void
+int
 xfs_btree_check_block(
-	xfs_btree_cur_t		*cur,	/* btree cursor */
-	xfs_btree_block_t	*block,	/* generic btree block pointer */
-	int			level,	/* level of the btree block */
-	struct xfs_buf		*bp);	/* buffer containing block, if any */
-
-/*
- * Debug routine: check that keys are in the right order.
- */
-void
-xfs_btree_check_key(
-	xfs_btnum_t		btnum,	/* btree identifier */
-	void			*ak1,	/* pointer to left (lower) key */
-	void			*ak2);	/* pointer to right (higher) key */
-
-/*
- * Debug routine: check that records are in the right order.
- */
-void
-xfs_btree_check_rec(
-	xfs_btnum_t		btnum,	/* btree identifier */
-	void			*ar1,	/* pointer to left (lower) record */
-	void			*ar2);	/* pointer to right (higher) record */
-#else
-#define	xfs_btree_check_block(a,b,c,d)
-#define	xfs_btree_check_key(a,b,c)
-#define	xfs_btree_check_rec(a,b,c)
-#endif	/* DEBUG */
-
-/*
- * Checking routine: check that long form block header is ok.
- */
-int					/* error (0 or EFSCORRUPTED) */
-xfs_btree_check_lblock(
-	xfs_btree_cur_t		*cur,	/* btree cursor */
-	xfs_btree_lblock_t	*block,	/* btree long form block pointer */
+	struct xfs_btree_cur	*cur,	/* btree cursor */
+	struct xfs_btree_block	*block,	/* generic btree block pointer */
 	int			level,	/* level of the btree block */
 	struct xfs_buf		*bp);	/* buffer containing block, if any */
 
 /*
- * Checking routine: check that (long) pointer is ok.
+ * Check that (long) pointer is ok.
  */
 int					/* error (0 or EFSCORRUPTED) */
 xfs_btree_check_lptr(
-	xfs_btree_cur_t		*cur,	/* btree cursor */
+	struct xfs_btree_cur	*cur,	/* btree cursor */
 	xfs_dfsbno_t		ptr,	/* btree block disk address */
 	int			level);	/* btree block level */
 
-#define xfs_btree_check_lptr_disk(cur, ptr, level) \
-	xfs_btree_check_lptr(cur, be64_to_cpu(ptr), level)
-
-/*
- * Checking routine: check that short form block header is ok.
- */
-int					/* error (0 or EFSCORRUPTED) */
-xfs_btree_check_sblock(
-	xfs_btree_cur_t		*cur,	/* btree cursor */
-	xfs_btree_sblock_t	*block,	/* btree short form block pointer */
-	int			level,	/* level of the btree block */
-	struct xfs_buf		*bp);	/* buffer containing block */
-
-/*
- * Checking routine: check that (short) pointer is ok.
- */
-int					/* error (0 or EFSCORRUPTED) */
-xfs_btree_check_sptr(
-	xfs_btree_cur_t		*cur,	/* btree cursor */
-	xfs_agblock_t		ptr,	/* btree block disk address */
-	int			level);	/* btree block level */
-
 /*
  * Delete the btree cursor.
  */
@@ -281,15 +323,6 @@ xfs_btree_dup_cursor(
 	xfs_btree_cur_t		**ncur);/* output cursor */
 
 /*
- * Change the cursor to point to the first record in the current block
- * at the given level.  Other levels are unaffected.
- */
-int					/* success=1, failure=0 */
-xfs_btree_firstrec(
-	xfs_btree_cur_t		*cur,	/* btree cursor */
-	int			level);	/* level to change */
-
-/*
  * Get a buffer for the block, return it with no data read.
  * Long-form addressing.
  */
@@ -313,20 +346,6 @@ xfs_btree_get_bufs(
 	uint			lock);	/* lock flags for get_buf */
 
 /*
- * Allocate a new btree cursor.
- * The cursor is either for allocation (A) or bmap (B).
- */
-xfs_btree_cur_t *			/* new btree cursor */
-xfs_btree_init_cursor(
-	struct xfs_mount	*mp,	/* file system mount point */
-	struct xfs_trans	*tp,	/* transaction pointer */
-	struct xfs_buf		*agbp,	/* (A only) buffer for agf structure */
-	xfs_agnumber_t		agno,	/* (A only) allocation group number */
-	xfs_btnum_t		btnum,	/* btree identifier */
-	struct xfs_inode	*ip,	/* (B only) inode owning the btree */
-	int			whichfork); /* (B only) data/attr fork */
-
-/*
  * Check for the cursor referring to the last block at the given level.
  */
 int					/* 1=is last block, 0=not last block */
@@ -335,15 +354,6 @@ xfs_btree_islastblock(
 	int			level);	/* level to check */
 
 /*
- * Change the cursor to point to the last record in the current block
- * at the given level.  Other levels are unaffected.
- */
-int					/* success=1, failure=0 */
-xfs_btree_lastrec(
-	xfs_btree_cur_t		*cur,	/* btree cursor */
-	int			level);	/* level to change */
-
-/*
  * Compute first and last byte offsets for the fields given.
  * Interprets the offsets table, which contains struct field offsets.
  */
@@ -404,39 +414,53 @@ xfs_btree_reada_bufs(
 	xfs_extlen_t		count);	/* count of filesystem blocks */
 
 /*
- * Read-ahead btree blocks, at the given level.
- * Bits in lr are set from XFS_BTCUR_{LEFT,RIGHT}RA.
+ * Set the buffer for level "lev" in the cursor to bp, releasing
+ * any previous buffer.
  */
-int					/* readahead block count */
-xfs_btree_readahead_core(
+void
+xfs_btree_setbuf(
 	xfs_btree_cur_t		*cur,	/* btree cursor */
 	int			lev,	/* level in btree */
-	int			lr);	/* left/right bits */
+	struct xfs_buf		*bp);	/* new buffer to set */
 
-static inline int			/* readahead block count */
-xfs_btree_readahead(
-	xfs_btree_cur_t		*cur,	/* btree cursor */
-	int			lev,	/* level in btree */
-	int			lr)	/* left/right bits */
-{
-	if ((cur->bc_ra[lev] | lr) == cur->bc_ra[lev])
-		return 0;
 
-	return xfs_btree_readahead_core(cur, lev, lr);
-}
+/*
+ * Common btree core entry points.
+ */
+int xfs_btree_increment(struct xfs_btree_cur *, int, int *);
+int xfs_btree_decrement(struct xfs_btree_cur *, int, int *);
+int xfs_btree_lookup(struct xfs_btree_cur *, xfs_lookup_t, int *);
+int xfs_btree_update(struct xfs_btree_cur *, union xfs_btree_rec *);
+int xfs_btree_new_iroot(struct xfs_btree_cur *, int *, int *);
+int xfs_btree_kill_iroot(struct xfs_btree_cur *);
+int xfs_btree_insert(struct xfs_btree_cur *, int *);
+int xfs_btree_delete(struct xfs_btree_cur *, int *);
+int xfs_btree_get_rec(struct xfs_btree_cur *, union xfs_btree_rec **, int *);
 
+/*
+ * Internal btree helpers also used by xfs_bmap.c.
+ */
+void xfs_btree_log_block(struct xfs_btree_cur *, struct xfs_buf *, int);
+void xfs_btree_log_recs(struct xfs_btree_cur *, struct xfs_buf *, int, int);
 
 /*
- * Set the buffer for level "lev" in the cursor to bp, releasing
- * any previous buffer.
+ * Helpers.
  */
-void
-xfs_btree_setbuf(
-	xfs_btree_cur_t		*cur,	/* btree cursor */
-	int			lev,	/* level in btree */
-	struct xfs_buf		*bp);	/* new buffer to set */
+static inline int xfs_btree_get_numrecs(struct xfs_btree_block *block)
+{
+	return be16_to_cpu(block->bb_numrecs);
+}
+
+static inline void xfs_btree_set_numrecs(struct xfs_btree_block *block,
+		__uint16_t numrecs)
+{
+	block->bb_numrecs = cpu_to_be16(numrecs);
+}
 
-#endif	/* __KERNEL__ */
+static inline int xfs_btree_get_level(struct xfs_btree_block *block)
+{
+	return be16_to_cpu(block->bb_level);
+}
 
 
 /*
diff --git a/fs/xfs/xfs_btree_trace.c b/fs/xfs/xfs_btree_trace.c
new file mode 100644
index 000000000000..44ff942a0fda
--- /dev/null
+++ b/fs/xfs/xfs_btree_trace.c
@@ -0,0 +1,249 @@
+/*
+ * Copyright (c) 2008 Silicon Graphics, Inc.
+ * All Rights Reserved.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it would be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write the Free Software Foundation,
+ * Inc.,  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
+ */
+#include "xfs.h"
+#include "xfs_types.h"
+#include "xfs_inum.h"
+#include "xfs_bmap_btree.h"
+#include "xfs_alloc_btree.h"
+#include "xfs_ialloc_btree.h"
+#include "xfs_inode.h"
+#include "xfs_btree.h"
+#include "xfs_btree_trace.h"
+
+STATIC void
+xfs_btree_trace_ptr(
+	struct xfs_btree_cur	*cur,
+	union xfs_btree_ptr	ptr,
+	__psunsigned_t		*high,
+	__psunsigned_t		*low)
+{
+	if (cur->bc_flags & XFS_BTREE_LONG_PTRS) {
+		__u64 val = be64_to_cpu(ptr.l);
+		*high = val >> 32;
+		*low = (int)val;
+	} else {
+		*high = 0;
+		*low = be32_to_cpu(ptr.s);
+	}
+}
+
+/*
+ * Add a trace buffer entry for arguments, for a buffer & 1 integer arg.
+ */
+void
+xfs_btree_trace_argbi(
+	const char		*func,
+	struct xfs_btree_cur	*cur,
+	struct xfs_buf		*b,
+	int			i,
+	int			line)
+{
+	cur->bc_ops->trace_enter(cur, func, XBT_ARGS, XFS_BTREE_KTRACE_ARGBI,
+				 line, (__psunsigned_t)b, i, 0, 0, 0, 0, 0,
+				 0, 0, 0, 0);
+}
+
+/*
+ * Add a trace buffer entry for arguments, for a buffer & 2 integer args.
+ */
+void
+xfs_btree_trace_argbii(
+	const char		*func,
+	struct xfs_btree_cur	*cur,
+	struct xfs_buf		*b,
+	int			i0,
+	int			i1,
+	int			line)
+{
+	cur->bc_ops->trace_enter(cur, func, XBT_ARGS, XFS_BTREE_KTRACE_ARGBII,
+				 line, (__psunsigned_t)b, i0, i1, 0, 0, 0, 0,
+				 0, 0, 0, 0);
+}
+
+/*
+ * Add a trace buffer entry for arguments, for 3 block-length args
+ * and an integer arg.
+ */
+void
+xfs_btree_trace_argfffi(
+	const char		*func,
+	struct xfs_btree_cur	*cur,
+	xfs_dfiloff_t		o,
+	xfs_dfsbno_t		b,
+	xfs_dfilblks_t		i,
+	int			j,
+	int			line)
+{
+	cur->bc_ops->trace_enter(cur, func, XBT_ARGS, XFS_BTREE_KTRACE_ARGFFFI,
+				 line,
+				 o >> 32, (int)o,
+				 b >> 32, (int)b,
+				 i >> 32, (int)i,
+				 (int)j, 0, 0, 0, 0);
+}
+
+/*
+ * Add a trace buffer entry for arguments, for one integer arg.
+ */
+void
+xfs_btree_trace_argi(
+	const char		*func,
+	struct xfs_btree_cur	*cur,
+	int			i,
+	int			line)
+{
+	cur->bc_ops->trace_enter(cur, func, XBT_ARGS, XFS_BTREE_KTRACE_ARGI,
+				 line, i, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0);
+}
+
+/*
+ * Add a trace buffer entry for arguments, for int, fsblock, key.
+ */
+void
+xfs_btree_trace_argipk(
+	const char		*func,
+	struct xfs_btree_cur	*cur,
+	int			i,
+	union xfs_btree_ptr	ptr,
+	union xfs_btree_key	*key,
+	int			line)
+{
+	__psunsigned_t		high, low;
+	__uint64_t		l0, l1;
+
+	xfs_btree_trace_ptr(cur, ptr, &high, &low);
+	cur->bc_ops->trace_key(cur, key, &l0, &l1);
+	cur->bc_ops->trace_enter(cur, func, XBT_ARGS, XFS_BTREE_KTRACE_ARGIPK,
+				 line, i, high, low,
+				 l0 >> 32, (int)l0,
+				 l1 >> 32, (int)l1,
+				 0, 0, 0, 0);
+}
+
+/*
+ * Add a trace buffer entry for arguments, for int, fsblock, rec.
+ */
+void
+xfs_btree_trace_argipr(
+	const char		*func,
+	struct xfs_btree_cur	*cur,
+	int			i,
+	union xfs_btree_ptr	ptr,
+	union xfs_btree_rec	*rec,
+	int			line)
+{
+	__psunsigned_t		high, low;
+	__uint64_t		l0, l1, l2;
+
+	xfs_btree_trace_ptr(cur, ptr, &high, &low);
+	cur->bc_ops->trace_record(cur, rec, &l0, &l1, &l2);
+	cur->bc_ops->trace_enter(cur, func, XBT_ARGS, XFS_BTREE_KTRACE_ARGIPR,
+			      line, i,
+			      high, low,
+			      l0 >> 32, (int)l0,
+			      l1 >> 32, (int)l1,
+			      l2 >> 32, (int)l2,
+			      0, 0);
+}
+
+/*
+ * Add a trace buffer entry for arguments, for int, key.
+ */
+void
+xfs_btree_trace_argik(
+	const char		*func,
+	struct xfs_btree_cur	*cur,
+	int			i,
+	union xfs_btree_key	*key,
+	int			line)
+{
+	__uint64_t		l0, l1;
+
+	cur->bc_ops->trace_key(cur, key, &l0, &l1);
+	cur->bc_ops->trace_enter(cur, func, XBT_ARGS, XFS_BTREE_KTRACE_ARGIK,
+				 line, i,
+				 l0 >> 32, (int)l0,
+				 l1 >> 32, (int)l1,
+				 0, 0, 0, 0, 0, 0);
+}
+
+/*
+ * Add a trace buffer entry for arguments, for record.
+ */
+void
+xfs_btree_trace_argr(
+	const char		*func,
+	struct xfs_btree_cur	*cur,
+	union xfs_btree_rec	*rec,
+	int			line)
+{
+	__uint64_t		l0, l1, l2;
+
+	cur->bc_ops->trace_record(cur, rec, &l0, &l1, &l2);
+	cur->bc_ops->trace_enter(cur, func, XBT_ARGS, XFS_BTREE_KTRACE_ARGR,
+			      line,
+			      l0 >> 32, (int)l0,
+			      l1 >> 32, (int)l1,
+			      l2 >> 32, (int)l2,
+			      0, 0, 0, 0, 0);
+}
+
+/*
+ * Add a trace buffer entry for the cursor/operation.
+ */
+void
+xfs_btree_trace_cursor(
+	const char		*func,
+	struct xfs_btree_cur	*cur,
+	int			type,
+	int			line)
+{
+	__uint32_t		s0;
+	__uint64_t		l0, l1;
+	char			*s;
+
+	switch (type) {
+	case XBT_ARGS:
+		s = "args";
+		break;
+	case XBT_ENTRY:
+		s = "entry";
+		break;
+	case XBT_ERROR:
+		s = "error";
+		break;
+	case XBT_EXIT:
+		s = "exit";
+		break;
+	default:
+		s = "unknown";
+		break;
+	}
+
+	cur->bc_ops->trace_cursor(cur, &s0, &l0, &l1);
+	cur->bc_ops->trace_enter(cur, func, s, XFS_BTREE_KTRACE_CUR, line,
+				 s0,
+				 l0 >> 32, (int)l0,
+				 l1 >> 32, (int)l1,
+				 (__psunsigned_t)cur->bc_bufs[0],
+				 (__psunsigned_t)cur->bc_bufs[1],
+				 (__psunsigned_t)cur->bc_bufs[2],
+				 (__psunsigned_t)cur->bc_bufs[3],
+				 (cur->bc_ptrs[0] << 16) | cur->bc_ptrs[1],
+				 (cur->bc_ptrs[2] << 16) | cur->bc_ptrs[3]);
+}
diff --git a/fs/xfs/xfs_btree_trace.h b/fs/xfs/xfs_btree_trace.h
new file mode 100644
index 000000000000..b3f5eb3c3c6c
--- /dev/null
+++ b/fs/xfs/xfs_btree_trace.h
@@ -0,0 +1,116 @@
+/*
+ * Copyright (c) 2008 Silicon Graphics, Inc.
+ * All Rights Reserved.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it would be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write the Free Software Foundation,
+ * Inc.,  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
+ */
+#ifndef __XFS_BTREE_TRACE_H__
+#define	__XFS_BTREE_TRACE_H__
+
+struct xfs_btree_cur;
+struct xfs_buf;
+
+
+/*
+ * Trace hooks.
+ * i,j = integer (32 bit)
+ * b = btree block buffer (xfs_buf_t)
+ * p = btree ptr
+ * r = btree record
+ * k = btree key
+ */
+
+#ifdef XFS_BTREE_TRACE
+
+/*
+ * Trace buffer entry types.
+ */
+#define XFS_BTREE_KTRACE_ARGBI   1
+#define XFS_BTREE_KTRACE_ARGBII  2
+#define XFS_BTREE_KTRACE_ARGFFFI 3
+#define XFS_BTREE_KTRACE_ARGI    4
+#define XFS_BTREE_KTRACE_ARGIPK  5
+#define XFS_BTREE_KTRACE_ARGIPR  6
+#define XFS_BTREE_KTRACE_ARGIK   7
+#define XFS_BTREE_KTRACE_ARGR	 8
+#define XFS_BTREE_KTRACE_CUR     9
+
+/*
+ * Sub-types for cursor traces.
+ */
+#define XBT_ARGS	0
+#define XBT_ENTRY	1
+#define XBT_ERROR	2
+#define XBT_EXIT	3
+
+void xfs_btree_trace_argbi(const char *, struct xfs_btree_cur *,
+		struct xfs_buf *, int, int);
+void xfs_btree_trace_argbii(const char *, struct xfs_btree_cur *,
+		struct xfs_buf *, int, int, int);
+void xfs_btree_trace_argfffi(const char *, struct xfs_btree_cur *,
+		xfs_dfiloff_t, xfs_dfsbno_t, xfs_dfilblks_t, int, int);
+void xfs_btree_trace_argi(const char *, struct xfs_btree_cur *, int, int);
+void xfs_btree_trace_argipk(const char *, struct xfs_btree_cur *, int,
+		union xfs_btree_ptr, union xfs_btree_key *, int);
+void xfs_btree_trace_argipr(const char *, struct xfs_btree_cur *, int,
+		union xfs_btree_ptr, union xfs_btree_rec *, int);
+void xfs_btree_trace_argik(const char *, struct xfs_btree_cur *, int,
+		union xfs_btree_key *, int);
+void xfs_btree_trace_argr(const char *, struct xfs_btree_cur *,
+		union xfs_btree_rec *, int);
+void xfs_btree_trace_cursor(const char *, struct xfs_btree_cur *, int, int);
+
+
+#define XFS_ALLOCBT_TRACE_SIZE	4096	/* size of global trace buffer */
+extern ktrace_t	*xfs_allocbt_trace_buf;
+
+#define XFS_INOBT_TRACE_SIZE	4096	/* size of global trace buffer */
+extern ktrace_t	*xfs_inobt_trace_buf;
+
+#define XFS_BMBT_TRACE_SIZE	4096	/* size of global trace buffer */
+#define XFS_BMBT_KTRACE_SIZE	32	/* size of per-inode trace buffer */
+extern ktrace_t	*xfs_bmbt_trace_buf;
+
+
+#define	XFS_BTREE_TRACE_ARGBI(c, b, i)	\
+	xfs_btree_trace_argbi(__func__, c, b, i, __LINE__)
+#define	XFS_BTREE_TRACE_ARGBII(c, b, i, j)	\
+	xfs_btree_trace_argbii(__func__, c, b, i, j, __LINE__)
+#define	XFS_BTREE_TRACE_ARGFFFI(c, o, b, i, j)	\
+	xfs_btree_trace_argfffi(__func__, c, o, b, i, j, __LINE__)
+#define	XFS_BTREE_TRACE_ARGI(c, i)	\
+	xfs_btree_trace_argi(__func__, c, i, __LINE__)
+#define	XFS_BTREE_TRACE_ARGIPK(c, i, p, k)	\
+	xfs_btree_trace_argipk(__func__, c, i, p, k, __LINE__)
+#define	XFS_BTREE_TRACE_ARGIPR(c, i, p, r)	\
+	xfs_btree_trace_argipr(__func__, c, i, p, r, __LINE__)
+#define	XFS_BTREE_TRACE_ARGIK(c, i, k)	\
+	xfs_btree_trace_argik(__func__, c, i, k, __LINE__)
+#define XFS_BTREE_TRACE_ARGR(c, r)	\
+	xfs_btree_trace_argr(__func__, c, r, __LINE__)
+#define	XFS_BTREE_TRACE_CURSOR(c, t)	\
+	xfs_btree_trace_cursor(__func__, c, t, __LINE__)
+#else
+#define	XFS_BTREE_TRACE_ARGBI(c, b, i)
+#define	XFS_BTREE_TRACE_ARGBII(c, b, i, j)
+#define	XFS_BTREE_TRACE_ARGFFFI(c, o, b, i, j)
+#define	XFS_BTREE_TRACE_ARGI(c, i)
+#define	XFS_BTREE_TRACE_ARGIPK(c, i, p, s)
+#define	XFS_BTREE_TRACE_ARGIPR(c, i, p, r)
+#define	XFS_BTREE_TRACE_ARGIK(c, i, k)
+#define XFS_BTREE_TRACE_ARGR(c, r)
+#define	XFS_BTREE_TRACE_CURSOR(c, t)
+#endif	/* XFS_BTREE_TRACE */
+
+#endif /* __XFS_BTREE_TRACE_H__ */
diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c
index 002fc2617c8e..d245d04e10ca 100644
--- a/fs/xfs/xfs_buf_item.c
+++ b/fs/xfs/xfs_buf_item.c
@@ -375,7 +375,7 @@ xfs_buf_item_unpin(
 	xfs_buf_log_item_t	*bip,
 	int			stale)
 {
-	xfs_mount_t	*mp;
+	struct xfs_ail	*ailp;
 	xfs_buf_t	*bp;
 	int		freed;
 
@@ -387,7 +387,7 @@ xfs_buf_item_unpin(
 	xfs_buftrace("XFS_UNPIN", bp);
 
 	freed = atomic_dec_and_test(&bip->bli_refcount);
-	mp = bip->bli_item.li_mountp;
+	ailp = bip->bli_item.li_ailp;
 	xfs_bunpin(bp);
 	if (freed && stale) {
 		ASSERT(bip->bli_flags & XFS_BLI_STALE);
@@ -399,17 +399,17 @@ xfs_buf_item_unpin(
 		xfs_buftrace("XFS_UNPIN STALE", bp);
 		/*
 		 * If we get called here because of an IO error, we may
-		 * or may not have the item on the AIL. xfs_trans_delete_ail()
+		 * or may not have the item on the AIL. xfs_trans_ail_delete()
 		 * will take care of that situation.
-		 * xfs_trans_delete_ail() drops the AIL lock.
+		 * xfs_trans_ail_delete() drops the AIL lock.
 		 */
 		if (bip->bli_flags & XFS_BLI_STALE_INODE) {
 			xfs_buf_do_callbacks(bp, (xfs_log_item_t *)bip);
 			XFS_BUF_SET_FSPRIVATE(bp, NULL);
 			XFS_BUF_CLR_IODONE_FUNC(bp);
 		} else {
-			spin_lock(&mp->m_ail_lock);
-			xfs_trans_delete_ail(mp, (xfs_log_item_t *)bip);
+			spin_lock(&ailp->xa_lock);
+			xfs_trans_ail_delete(ailp, (xfs_log_item_t *)bip);
 			xfs_buf_item_relse(bp);
 			ASSERT(XFS_BUF_FSPRIVATE(bp, void *) == NULL);
 		}
@@ -731,6 +731,7 @@ xfs_buf_item_init(
 	bip->bli_item.li_type = XFS_LI_BUF;
 	bip->bli_item.li_ops = &xfs_buf_item_ops;
 	bip->bli_item.li_mountp = mp;
+	bip->bli_item.li_ailp = mp->m_ail;
 	bip->bli_buf = bp;
 	xfs_buf_hold(bp);
 	bip->bli_format.blf_type = XFS_LI_BUF;
@@ -1122,27 +1123,23 @@ xfs_buf_iodone(
 	xfs_buf_t		*bp,
 	xfs_buf_log_item_t	*bip)
 {
-	struct xfs_mount	*mp;
+	struct xfs_ail		*ailp = bip->bli_item.li_ailp;
 
 	ASSERT(bip->bli_buf == bp);
 
 	xfs_buf_rele(bp);
-	mp = bip->bli_item.li_mountp;
 
 	/*
 	 * If we are forcibly shutting down, this may well be
 	 * off the AIL already. That's because we simulate the
 	 * log-committed callbacks to unpin these buffers. Or we may never
 	 * have put this item on AIL because of the transaction was
-	 * aborted forcibly. xfs_trans_delete_ail() takes care of these.
+	 * aborted forcibly. xfs_trans_ail_delete() takes care of these.
 	 *
 	 * Either way, AIL is useless if we're forcing a shutdown.
 	 */
-	spin_lock(&mp->m_ail_lock);
-	/*
-	 * xfs_trans_delete_ail() drops the AIL lock.
-	 */
-	xfs_trans_delete_ail(mp, (xfs_log_item_t *)bip);
+	spin_lock(&ailp->xa_lock);
+	xfs_trans_ail_delete(ailp, (xfs_log_item_t *)bip);
 	xfs_buf_item_free(bip);
 }
 
diff --git a/fs/xfs/xfs_clnt.h b/fs/xfs/xfs_clnt.h
deleted file mode 100644
index d2ce5dd70d87..000000000000
--- a/fs/xfs/xfs_clnt.h
+++ /dev/null
@@ -1,105 +0,0 @@
-/*
- * Copyright (c) 2000-2005 Silicon Graphics, Inc.
- * All Rights Reserved.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it would be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write the Free Software Foundation,
- * Inc.,  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
- */
-#ifndef __XFS_CLNT_H__
-#define __XFS_CLNT_H__
-
-/*
- * XFS arguments structure, constructed from the arguments we
- * are passed via the mount system call.
- *
- * NOTE: The mount system call is handled differently between
- * Linux and IRIX.  In IRIX we worked work with a binary data
- * structure coming in across the syscall interface from user
- * space (the mount userspace knows about each filesystem type
- * and the set of valid options for it, and converts the users
- * argument string into a binary structure _before_ making the
- * system call), and the ABI issues that this implies.
- *
- * In Linux, we are passed a comma separated set of options;
- * ie. a NULL terminated string of characters.  Userspace mount
- * code does not have any knowledge of mount options expected by
- * each filesystem type and so each filesystem parses its mount
- * options in kernel space.
- *
- * For the Linux port, we kept this structure pretty much intact
- * and use it internally (because the existing code groks it).
- */
-struct xfs_mount_args {
-	int	flags;		/* flags -> see XFSMNT_... macros below */
-	int	flags2;		/* flags -> see XFSMNT2_... macros below */
-	int	logbufs;	/* Number of log buffers, -1 to default */
-	int	logbufsize;	/* Size of log buffers, -1 to default */
-	char	fsname[MAXNAMELEN+1];	/* data device name */
-	char	rtname[MAXNAMELEN+1];	/* realtime device filename */
-	char	logname[MAXNAMELEN+1];	/* journal device filename */
-	char	mtpt[MAXNAMELEN+1];	/* filesystem mount point */
-	int	sunit;		/* stripe unit (BBs) */
-	int	swidth;		/* stripe width (BBs), multiple of sunit */
-	uchar_t iosizelog;	/* log2 of the preferred I/O size */
-	int	ihashsize;	/* inode hash table size (buckets) */
-};
-
-/*
- * XFS mount option flags -- args->flags1
- */
-#define	XFSMNT_ATTR2		0x00000001	/* allow ATTR2 EA format */
-#define	XFSMNT_WSYNC		0x00000002	/* safe mode nfs mount
-						 * compatible */
-#define	XFSMNT_INO64		0x00000004	/* move inode numbers up
-						 * past 2^32 */
-#define XFSMNT_UQUOTA		0x00000008	/* user quota accounting */
-#define XFSMNT_PQUOTA		0x00000010	/* IRIX prj quota accounting */
-#define XFSMNT_UQUOTAENF	0x00000020	/* user quota limit
-						 * enforcement */
-#define XFSMNT_PQUOTAENF	0x00000040	/* IRIX project quota limit
-						 * enforcement */
-#define XFSMNT_QUIET		0x00000080	/* don't report mount errors */
-#define XFSMNT_NOALIGN		0x00000200	/* don't allocate at
-						 * stripe boundaries*/
-#define XFSMNT_RETERR		0x00000400	/* return error to user */
-#define XFSMNT_NORECOVERY	0x00000800	/* no recovery, implies
-						 * read-only mount */
-#define XFSMNT_SHARED		0x00001000	/* shared XFS mount */
-#define XFSMNT_IOSIZE		0x00002000	/* optimize for I/O size */
-#define XFSMNT_OSYNCISOSYNC	0x00004000	/* o_sync is REALLY o_sync */
-						/* (osyncisdsync is default) */
-#define XFSMNT_NOATTR2		0x00008000	/* turn off ATTR2 EA format */
-#define XFSMNT_32BITINODES	0x00200000	/* restrict inodes to 32
-						 * bits of address space */
-#define XFSMNT_GQUOTA		0x00400000	/* group quota accounting */
-#define XFSMNT_GQUOTAENF	0x00800000	/* group quota limit
-						 * enforcement */
-#define XFSMNT_NOUUID		0x01000000	/* Ignore fs uuid */
-#define XFSMNT_DMAPI		0x02000000	/* enable dmapi/xdsm */
-#define XFSMNT_BARRIER		0x04000000	/* use write barriers */
-#define XFSMNT_IKEEP		0x08000000	/* inode cluster delete */
-#define XFSMNT_SWALLOC		0x10000000	/* turn on stripe width
-						 * allocation */
-#define XFSMNT_DIRSYNC		0x40000000	/* sync creat,link,unlink,rename
-						 * symlink,mkdir,rmdir,mknod */
-#define XFSMNT_FLAGS2		0x80000000	/* more flags set in flags2 */
-
-/*
- * XFS mount option flags -- args->flags2
- */
-#define XFSMNT2_COMPAT_IOSIZE	0x00000001	/* don't report large preferred
-						 * I/O size in stat(2) */
-#define XFSMNT2_FILESTREAMS	0x00000002	/* enable the filestreams
-						 * allocator */
-
-#endif	/* __XFS_CLNT_H__ */
diff --git a/fs/xfs/xfs_da_btree.h b/fs/xfs/xfs_da_btree.h
index 8be0b00ede9a..70b710c1792d 100644
--- a/fs/xfs/xfs_da_btree.h
+++ b/fs/xfs/xfs_da_btree.h
@@ -72,27 +72,7 @@ typedef struct xfs_da_intnode {
 typedef struct xfs_da_node_hdr xfs_da_node_hdr_t;
 typedef struct xfs_da_node_entry xfs_da_node_entry_t;
 
-#define XFS_DA_MAXHASH	((xfs_dahash_t)-1) /* largest valid hash value */
-
 #define	XFS_LBSIZE(mp)	(mp)->m_sb.sb_blocksize
-#define	XFS_LBLOG(mp)	(mp)->m_sb.sb_blocklog
-
-#define	XFS_DA_MAKE_BNOENTRY(mp,bno,entry)	\
-	(((bno) << (mp)->m_dircook_elog) | (entry))
-#define	XFS_DA_MAKE_COOKIE(mp,bno,entry,hash)	\
-	(((xfs_off_t)XFS_DA_MAKE_BNOENTRY(mp, bno, entry) << 32) | (hash))
-#define	XFS_DA_COOKIE_HASH(mp,cookie)		((xfs_dahash_t)cookie)
-#define	XFS_DA_COOKIE_BNO(mp,cookie)		\
-	((((xfs_off_t)(cookie) >> 31) == -1LL ? \
-		(xfs_dablk_t)0 : \
-		(xfs_dablk_t)((xfs_off_t)(cookie) >> \
-				((mp)->m_dircook_elog + 32))))
-#define	XFS_DA_COOKIE_ENTRY(mp,cookie)		\
-	((((xfs_off_t)(cookie) >> 31) == -1LL ?	\
-		(xfs_dablk_t)0 : \
-		(xfs_dablk_t)(((xfs_off_t)(cookie) >> 32) & \
-				((1 << (mp)->m_dircook_elog) - 1))))
-
 
 /*========================================================================
  * Btree searching and modification structure definitions.
@@ -226,9 +206,8 @@ struct xfs_nameops {
 };
 
 
-#ifdef __KERNEL__
 /*========================================================================
- * Function prototypes for the kernel.
+ * Function prototypes.
  *========================================================================*/
 
 /*
@@ -289,6 +268,5 @@ xfs_daddr_t xfs_da_blkno(xfs_dabuf_t *dabuf);
 
 extern struct kmem_zone *xfs_da_state_zone;
 extern struct kmem_zone *xfs_dabuf_zone;
-#endif	/* __KERNEL__ */
 
 #endif	/* __XFS_DA_BTREE_H__ */
diff --git a/fs/xfs/xfs_dfrag.c b/fs/xfs/xfs_dfrag.c
index 75b0cd4da0ea..b4c1ee713492 100644
--- a/fs/xfs/xfs_dfrag.c
+++ b/fs/xfs/xfs_dfrag.c
@@ -49,9 +49,8 @@
  */
 int
 xfs_swapext(
-	xfs_swapext_t	__user *sxu)
+	xfs_swapext_t	*sxp)
 {
-	xfs_swapext_t	*sxp;
 	xfs_inode_t     *ip, *tip;
 	struct file	*file, *target_file;
 	int		error = 0;
@@ -62,11 +61,6 @@ xfs_swapext(
 		goto out;
 	}
 
-	if (copy_from_user(sxp, sxu, sizeof(xfs_swapext_t))) {
-		error = XFS_ERROR(EFAULT);
-		goto out_free_sxp;
-	}
-
 	/* Pull information for the target fd */
 	file = fget((int)sxp->sx_fdtarget);
 	if (!file) {
diff --git a/fs/xfs/xfs_dfrag.h b/fs/xfs/xfs_dfrag.h
index da178205be68..4f55a6306558 100644
--- a/fs/xfs/xfs_dfrag.h
+++ b/fs/xfs/xfs_dfrag.h
@@ -46,7 +46,7 @@ typedef struct xfs_swapext
 /*
  * Syscall interface for xfs_swapext
  */
-int	xfs_swapext(struct xfs_swapext __user *sx);
+int	xfs_swapext(struct xfs_swapext *sx);
 
 int	xfs_swap_extents(struct xfs_inode *ip, struct xfs_inode *tip,
 		struct xfs_swapext *sxp);
diff --git a/fs/xfs/xfs_dinode.h b/fs/xfs/xfs_dinode.h
index c9065eaf2a4d..162e8726df5e 100644
--- a/fs/xfs/xfs_dinode.h
+++ b/fs/xfs/xfs_dinode.h
@@ -18,32 +18,29 @@
 #ifndef __XFS_DINODE_H__
 #define	__XFS_DINODE_H__
 
-struct xfs_buf;
-struct xfs_mount;
+#define	XFS_DINODE_MAGIC		0x494e	/* 'IN' */
+#define XFS_DINODE_GOOD_VERSION(v)	(((v) == 1 || (v) == 2))
 
-#define	XFS_DINODE_VERSION_1	1
-#define	XFS_DINODE_VERSION_2	2
-#define XFS_DINODE_GOOD_VERSION(v)	\
-	(((v) == XFS_DINODE_VERSION_1 || (v) == XFS_DINODE_VERSION_2))
-#define	XFS_DINODE_MAGIC	0x494e	/* 'IN' */
-
-/*
- * Disk inode structure.
- * This is just the header; the inode is expanded to fill a variable size
- * with the last field expanding.  It is split into the core and "other"
- * because we only need the core part in the in-core inode.
- */
 typedef struct xfs_timestamp {
 	__be32		t_sec;		/* timestamp seconds */
 	__be32		t_nsec;		/* timestamp nanoseconds */
 } xfs_timestamp_t;
 
 /*
- * Note: Coordinate changes to this structure with the XFS_DI_* #defines
- * below, the offsets table in xfs_ialloc_log_di() and struct xfs_icdinode
- * in xfs_inode.h.
+ * On-disk inode structure.
+ *
+ * This is just the header or "dinode core", the inode is expanded to fill a
+ * variable size the leftover area split into a data and an attribute fork.
+ * The format of the data and attribute fork depends on the format of the
+ * inode as indicated by di_format and di_aformat.  To access the data and
+ * attribute use the XFS_DFORK_PTR, XFS_DFORK_DPTR, and XFS_DFORK_PTR macros
+ * below.
+ *
+ * There is a very similar struct icdinode in xfs_inode which matches the
+ * layout of the first 96 bytes of this structure, but is kept in native
+ * format instead of big endian.
  */
-typedef struct xfs_dinode_core {
+typedef struct xfs_dinode {
 	__be16		di_magic;	/* inode magic # = XFS_DINODE_MAGIC */
 	__be16		di_mode;	/* mode and type of file */
 	__u8		di_version;	/* inode version */
@@ -69,34 +66,12 @@ typedef struct xfs_dinode_core {
 	__be16		di_dmstate;	/* DMIG state info */
 	__be16		di_flags;	/* random flags, XFS_DIFLAG_... */
 	__be32		di_gen;		/* generation number */
-} xfs_dinode_core_t;
 
-#define DI_MAX_FLUSH 0xffff
+	/* di_next_unlinked is the only non-core field in the old dinode */
+	__be32		di_next_unlinked;/* agi unlinked list ptr */
+} __attribute__((packed)) xfs_dinode_t;
 
-typedef struct xfs_dinode
-{
-	xfs_dinode_core_t	di_core;
-	/*
-	 * In adding anything between the core and the union, be
-	 * sure to update the macros like XFS_LITINO below and
-	 * XFS_BMAP_RBLOCK_DSIZE in xfs_bmap_btree.h.
-	 */
-	__be32			di_next_unlinked;/* agi unlinked list ptr */
-	union {
-		xfs_bmdr_block_t di_bmbt;	/* btree root block */
-		xfs_bmbt_rec_32_t di_bmx[1];	/* extent list */
-		xfs_dir2_sf_t	di_dir2sf;	/* shortform directory v2 */
-		char		di_c[1];	/* local contents */
-		__be32		di_dev;		/* device for S_IFCHR/S_IFBLK */
-		uuid_t		di_muuid;	/* mount point value */
-		char		di_symlink[1];	/* local symbolic link */
-	}		di_u;
-	union {
-		xfs_bmdr_block_t di_abmbt;	/* btree root block */
-		xfs_bmbt_rec_32_t di_abmx[1];	/* extent list */
-		xfs_attr_shortform_t di_attrsf;	/* shortform attribute list */
-	}		di_a;
-} xfs_dinode_t;
+#define DI_MAX_FLUSH 0xffff
 
 /*
  * The 32 bit link count in the inode theoretically maxes out at UINT_MAX.
@@ -107,50 +82,14 @@ typedef struct xfs_dinode
 #define	XFS_MAXLINK_1		65535U
 
 /*
- * Bit names for logging disk inodes only
- */
-#define	XFS_DI_MAGIC		0x0000001
-#define	XFS_DI_MODE		0x0000002
-#define	XFS_DI_VERSION		0x0000004
-#define	XFS_DI_FORMAT		0x0000008
-#define	XFS_DI_ONLINK		0x0000010
-#define	XFS_DI_UID		0x0000020
-#define	XFS_DI_GID		0x0000040
-#define	XFS_DI_NLINK		0x0000080
-#define	XFS_DI_PROJID		0x0000100
-#define	XFS_DI_PAD		0x0000200
-#define	XFS_DI_ATIME		0x0000400
-#define	XFS_DI_MTIME		0x0000800
-#define	XFS_DI_CTIME		0x0001000
-#define	XFS_DI_SIZE		0x0002000
-#define	XFS_DI_NBLOCKS		0x0004000
-#define	XFS_DI_EXTSIZE		0x0008000
-#define	XFS_DI_NEXTENTS		0x0010000
-#define	XFS_DI_NAEXTENTS	0x0020000
-#define	XFS_DI_FORKOFF		0x0040000
-#define	XFS_DI_AFORMAT		0x0080000
-#define	XFS_DI_DMEVMASK		0x0100000
-#define	XFS_DI_DMSTATE		0x0200000
-#define	XFS_DI_FLAGS		0x0400000
-#define	XFS_DI_GEN		0x0800000
-#define	XFS_DI_NEXT_UNLINKED	0x1000000
-#define	XFS_DI_U		0x2000000
-#define	XFS_DI_A		0x4000000
-#define	XFS_DI_NUM_BITS		27
-#define	XFS_DI_ALL_BITS		((1 << XFS_DI_NUM_BITS) - 1)
-#define	XFS_DI_CORE_BITS	(XFS_DI_ALL_BITS & ~(XFS_DI_U|XFS_DI_A))
-
-/*
  * Values for di_format
  */
-typedef enum xfs_dinode_fmt
-{
-	XFS_DINODE_FMT_DEV,		/* CHR, BLK: di_dev */
-	XFS_DINODE_FMT_LOCAL,		/* DIR, REG: di_c */
-					/* LNK: di_symlink */
-	XFS_DINODE_FMT_EXTENTS,		/* DIR, REG, LNK: di_bmx */
-	XFS_DINODE_FMT_BTREE,		/* DIR, REG, LNK: di_bmbt */
-	XFS_DINODE_FMT_UUID		/* MNT: di_uuid */
+typedef enum xfs_dinode_fmt {
+	XFS_DINODE_FMT_DEV,		/* xfs_dev_t */
+	XFS_DINODE_FMT_LOCAL,		/* bulk data */
+	XFS_DINODE_FMT_EXTENTS,		/* struct xfs_bmbt_rec */
+	XFS_DINODE_FMT_BTREE,		/* struct xfs_bmdr_block */
+	XFS_DINODE_FMT_UUID		/* uuid_t */
 } xfs_dinode_fmt_t;
 
 /*
@@ -166,13 +105,13 @@ typedef enum xfs_dinode_fmt
  */
 #define	XFS_LITINO(mp)	((mp)->m_litino)
 #define	XFS_BROOT_SIZE_ADJ	\
-	(sizeof(xfs_bmbt_block_t) - sizeof(xfs_bmdr_block_t))
+	(XFS_BTREE_LBLOCK_LEN - sizeof(xfs_bmdr_block_t))
 
 /*
  * Inode data & attribute fork sizes, per inode.
  */
-#define XFS_DFORK_Q(dip)		((dip)->di_core.di_forkoff != 0)
-#define XFS_DFORK_BOFF(dip)		((int)((dip)->di_core.di_forkoff << 3))
+#define XFS_DFORK_Q(dip)		((dip)->di_forkoff != 0)
+#define XFS_DFORK_BOFF(dip)		((int)((dip)->di_forkoff << 3))
 
 #define XFS_DFORK_DSIZE(dip,mp) \
 	(XFS_DFORK_Q(dip) ? \
@@ -187,23 +126,42 @@ typedef enum xfs_dinode_fmt
 		XFS_DFORK_DSIZE(dip, mp) : \
 		XFS_DFORK_ASIZE(dip, mp))
 
-#define XFS_DFORK_DPTR(dip)		    ((dip)->di_u.di_c)
+/*
+ * Return pointers to the data or attribute forks.
+ */
+#define XFS_DFORK_DPTR(dip) \
+	((char *)(dip) + sizeof(struct xfs_dinode))
 #define XFS_DFORK_APTR(dip)	\
-	((dip)->di_u.di_c + XFS_DFORK_BOFF(dip))
+	(XFS_DFORK_DPTR(dip) + XFS_DFORK_BOFF(dip))
 #define XFS_DFORK_PTR(dip,w)	\
 	((w) == XFS_DATA_FORK ? XFS_DFORK_DPTR(dip) : XFS_DFORK_APTR(dip))
+
 #define XFS_DFORK_FORMAT(dip,w) \
 	((w) == XFS_DATA_FORK ? \
-		(dip)->di_core.di_format : \
-		(dip)->di_core.di_aformat)
+		(dip)->di_format : \
+		(dip)->di_aformat)
 #define XFS_DFORK_NEXTENTS(dip,w) \
 	((w) == XFS_DATA_FORK ? \
-	 	be32_to_cpu((dip)->di_core.di_nextents) : \
-	 	be16_to_cpu((dip)->di_core.di_anextents))
+		be32_to_cpu((dip)->di_nextents) : \
+		be16_to_cpu((dip)->di_anextents))
 
 #define	XFS_BUF_TO_DINODE(bp)	((xfs_dinode_t *)XFS_BUF_PTR(bp))
 
 /*
+ * For block and character special files the 32bit dev_t is stored at the
+ * beginning of the data fork.
+ */
+static inline xfs_dev_t xfs_dinode_get_rdev(struct xfs_dinode *dip)
+{
+	return be32_to_cpu(*(__be32 *)XFS_DFORK_DPTR(dip));
+}
+
+static inline void xfs_dinode_put_rdev(struct xfs_dinode *dip, xfs_dev_t rdev)
+{
+	*(__be32 *)XFS_DFORK_DPTR(dip) = cpu_to_be32(rdev);
+}
+
+/*
  * Values for di_flags
  * There should be a one-to-one correspondence between these flags and the
  * XFS_XFLAG_s.
diff --git a/fs/xfs/xfs_dir2_sf.h b/fs/xfs/xfs_dir2_sf.h
index deecc9d238f8..6ac44b550d39 100644
--- a/fs/xfs/xfs_dir2_sf.h
+++ b/fs/xfs/xfs_dir2_sf.h
@@ -34,13 +34,6 @@ struct xfs_mount;
 struct xfs_trans;
 
 /*
- * Maximum size of a shortform directory.
- */
-#define	XFS_DIR2_SF_MAX_SIZE	\
-	(XFS_DINODE_MAX_SIZE - (uint)sizeof(xfs_dinode_core_t) - \
-	 (uint)sizeof(xfs_agino_t))
-
-/*
  * Inode number stored as 8 8-bit values.
  */
 typedef	struct { __uint8_t i[8]; } xfs_dir2_ino8_t;
diff --git a/fs/xfs/xfs_dmops.c b/fs/xfs/xfs_dmops.c
index a1e55fb9d5dd..e71e2581c0c3 100644
--- a/fs/xfs/xfs_dmops.c
+++ b/fs/xfs/xfs_dmops.c
@@ -25,7 +25,6 @@
 #include "xfs_inum.h"
 #include "xfs_ag.h"
 #include "xfs_mount.h"
-#include "xfs_clnt.h"
 
 
 static struct xfs_dmops xfs_dmcore_stub = {
@@ -38,9 +37,9 @@ static struct xfs_dmops xfs_dmcore_stub = {
 };
 
 int
-xfs_dmops_get(struct xfs_mount *mp, struct xfs_mount_args *args)
+xfs_dmops_get(struct xfs_mount *mp)
 {
-	if (args->flags & XFSMNT_DMAPI) {
+	if (mp->m_flags & XFS_MOUNT_DMAPI) {
 		cmn_err(CE_WARN,
 			"XFS: dmapi support not available in this kernel.");
 		return EINVAL;
diff --git a/fs/xfs/xfs_extfree_item.c b/fs/xfs/xfs_extfree_item.c
index 8aa28f751b2a..05a4bdd4be39 100644
--- a/fs/xfs/xfs_extfree_item.c
+++ b/fs/xfs/xfs_extfree_item.c
@@ -108,19 +108,16 @@ xfs_efi_item_pin(xfs_efi_log_item_t *efip)
 STATIC void
 xfs_efi_item_unpin(xfs_efi_log_item_t *efip, int stale)
 {
-	xfs_mount_t	*mp;
+	struct xfs_ail		*ailp = efip->efi_item.li_ailp;
 
-	mp = efip->efi_item.li_mountp;
-	spin_lock(&mp->m_ail_lock);
+	spin_lock(&ailp->xa_lock);
 	if (efip->efi_flags & XFS_EFI_CANCELED) {
-		/*
-		 * xfs_trans_delete_ail() drops the AIL lock.
-		 */
-		xfs_trans_delete_ail(mp, (xfs_log_item_t *)efip);
+		/* xfs_trans_ail_delete() drops the AIL lock. */
+		xfs_trans_ail_delete(ailp, (xfs_log_item_t *)efip);
 		xfs_efi_item_free(efip);
 	} else {
 		efip->efi_flags |= XFS_EFI_COMMITTED;
-		spin_unlock(&mp->m_ail_lock);
+		spin_unlock(&ailp->xa_lock);
 	}
 }
 
@@ -134,26 +131,23 @@ xfs_efi_item_unpin(xfs_efi_log_item_t *efip, int stale)
 STATIC void
 xfs_efi_item_unpin_remove(xfs_efi_log_item_t *efip, xfs_trans_t *tp)
 {
-	xfs_mount_t	*mp;
+	struct xfs_ail		*ailp = efip->efi_item.li_ailp;
 	xfs_log_item_desc_t	*lidp;
 
-	mp = efip->efi_item.li_mountp;
-	spin_lock(&mp->m_ail_lock);
+	spin_lock(&ailp->xa_lock);
 	if (efip->efi_flags & XFS_EFI_CANCELED) {
 		/*
 		 * free the xaction descriptor pointing to this item
 		 */
 		lidp = xfs_trans_find_item(tp, (xfs_log_item_t *) efip);
 		xfs_trans_free_item(tp, lidp);
-		/*
-		 * pull the item off the AIL.
-		 * xfs_trans_delete_ail() drops the AIL lock.
-		 */
-		xfs_trans_delete_ail(mp, (xfs_log_item_t *)efip);
+
+		/* xfs_trans_ail_delete() drops the AIL lock. */
+		xfs_trans_ail_delete(ailp, (xfs_log_item_t *)efip);
 		xfs_efi_item_free(efip);
 	} else {
 		efip->efi_flags |= XFS_EFI_COMMITTED;
-		spin_unlock(&mp->m_ail_lock);
+		spin_unlock(&ailp->xa_lock);
 	}
 }
 
@@ -268,6 +262,7 @@ xfs_efi_init(xfs_mount_t	*mp,
 	efip->efi_item.li_type = XFS_LI_EFI;
 	efip->efi_item.li_ops = &xfs_efi_item_ops;
 	efip->efi_item.li_mountp = mp;
+	efip->efi_item.li_ailp = mp->m_ail;
 	efip->efi_format.efi_nextents = nextents;
 	efip->efi_format.efi_id = (__psint_t)(void*)efip;
 
@@ -345,25 +340,22 @@ void
 xfs_efi_release(xfs_efi_log_item_t	*efip,
 		uint			nextents)
 {
-	xfs_mount_t	*mp;
-	int		extents_left;
+	struct xfs_ail		*ailp = efip->efi_item.li_ailp;
+	int			extents_left;
 
-	mp = efip->efi_item.li_mountp;
 	ASSERT(efip->efi_next_extent > 0);
 	ASSERT(efip->efi_flags & XFS_EFI_COMMITTED);
 
-	spin_lock(&mp->m_ail_lock);
+	spin_lock(&ailp->xa_lock);
 	ASSERT(efip->efi_next_extent >= nextents);
 	efip->efi_next_extent -= nextents;
 	extents_left = efip->efi_next_extent;
 	if (extents_left == 0) {
-		/*
-		 * xfs_trans_delete_ail() drops the AIL lock.
-		 */
-		xfs_trans_delete_ail(mp, (xfs_log_item_t *)efip);
+		/* xfs_trans_ail_delete() drops the AIL lock. */
+		xfs_trans_ail_delete(ailp, (xfs_log_item_t *)efip);
 		xfs_efi_item_free(efip);
 	} else {
-		spin_unlock(&mp->m_ail_lock);
+		spin_unlock(&ailp->xa_lock);
 	}
 }
 
@@ -565,6 +557,7 @@ xfs_efd_init(xfs_mount_t	*mp,
 	efdp->efd_item.li_type = XFS_LI_EFD;
 	efdp->efd_item.li_ops = &xfs_efd_item_ops;
 	efdp->efd_item.li_mountp = mp;
+	efdp->efd_item.li_ailp = mp->m_ail;
 	efdp->efd_efip = efip;
 	efdp->efd_format.efd_nextents = nextents;
 	efdp->efd_format.efd_efi_id = efip->efi_format.efi_id;
diff --git a/fs/xfs/xfs_fs.h b/fs/xfs/xfs_fs.h
index 01c0cc88d3f3..589c41c38446 100644
--- a/fs/xfs/xfs_fs.h
+++ b/fs/xfs/xfs_fs.h
@@ -113,22 +113,14 @@ struct getbmapx {
 #define BMV_IF_ATTRFORK		0x1	/* return attr fork rather than data */
 #define BMV_IF_NO_DMAPI_READ	0x2	/* Do not generate DMAPI read event  */
 #define BMV_IF_PREALLOC		0x4	/* rtn status BMV_OF_PREALLOC if req */
-#define BMV_IF_VALID	(BMV_IF_ATTRFORK|BMV_IF_NO_DMAPI_READ|BMV_IF_PREALLOC)
-#ifdef __KERNEL__
-#define BMV_IF_EXTENDED 0x40000000	/* getpmapx if set */
-#endif
+#define BMV_IF_DELALLOC		0x8	/* rtn status BMV_OF_DELALLOC if req */
+#define BMV_IF_VALID	\
+	(BMV_IF_ATTRFORK|BMV_IF_NO_DMAPI_READ|BMV_IF_PREALLOC|BMV_IF_DELALLOC)
 
 /*	bmv_oflags values - returned for for each non-header segment */
 #define BMV_OF_PREALLOC		0x1	/* segment = unwritten pre-allocation */
-
-/*	Convert getbmap <-> getbmapx - move fields from p1 to p2. */
-#define GETBMAP_CONVERT(p1,p2) {	\
-	p2.bmv_offset = p1.bmv_offset;	\
-	p2.bmv_block = p1.bmv_block;	\
-	p2.bmv_length = p1.bmv_length;	\
-	p2.bmv_count = p1.bmv_count;	\
-	p2.bmv_entries = p1.bmv_entries;  }
-
+#define BMV_OF_DELALLOC		0x2	/* segment = delayed allocation */
+#define BMV_OF_LAST		0x4	/* segment is the last in the file */
 
 /*
  * Structure for XFS_IOC_FSSETDM.
@@ -426,10 +418,6 @@ typedef struct xfs_handle {
 #define XFS_IOC_GETXFLAGS	FS_IOC_GETFLAGS
 #define XFS_IOC_SETXFLAGS	FS_IOC_SETFLAGS
 #define XFS_IOC_GETVERSION	FS_IOC_GETVERSION
-/* 32-bit compat counterparts */
-#define XFS_IOC32_GETXFLAGS	FS_IOC32_GETFLAGS
-#define XFS_IOC32_SETXFLAGS	FS_IOC32_SETFLAGS
-#define XFS_IOC32_GETVERSION	FS_IOC32_GETVERSION
 
 /*
  * ioctl commands that replace IRIX fcntl()'s
diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c
index 84583cf73db3..852b6d32e8d0 100644
--- a/fs/xfs/xfs_fsops.c
+++ b/fs/xfs/xfs_fsops.c
@@ -126,7 +126,7 @@ xfs_growfs_data_private(
 	xfs_extlen_t		agsize;
 	xfs_extlen_t		tmpsize;
 	xfs_alloc_rec_t		*arec;
-	xfs_btree_sblock_t	*block;
+	struct xfs_btree_block	*block;
 	xfs_buf_t		*bp;
 	int			bucket;
 	int			dpct;
@@ -251,14 +251,14 @@ xfs_growfs_data_private(
 		bp = xfs_buf_get(mp->m_ddev_targp,
 			XFS_AGB_TO_DADDR(mp, agno, XFS_BNO_BLOCK(mp)),
 			BTOBB(mp->m_sb.sb_blocksize), 0);
-		block = XFS_BUF_TO_SBLOCK(bp);
+		block = XFS_BUF_TO_BLOCK(bp);
 		memset(block, 0, mp->m_sb.sb_blocksize);
 		block->bb_magic = cpu_to_be32(XFS_ABTB_MAGIC);
 		block->bb_level = 0;
 		block->bb_numrecs = cpu_to_be16(1);
-		block->bb_leftsib = cpu_to_be32(NULLAGBLOCK);
-		block->bb_rightsib = cpu_to_be32(NULLAGBLOCK);
-		arec = XFS_BTREE_REC_ADDR(xfs_alloc, block, 1);
+		block->bb_u.s.bb_leftsib = cpu_to_be32(NULLAGBLOCK);
+		block->bb_u.s.bb_rightsib = cpu_to_be32(NULLAGBLOCK);
+		arec = XFS_ALLOC_REC_ADDR(mp, block, 1);
 		arec->ar_startblock = cpu_to_be32(XFS_PREALLOC_BLOCKS(mp));
 		arec->ar_blockcount = cpu_to_be32(
 			agsize - be32_to_cpu(arec->ar_startblock));
@@ -272,14 +272,14 @@ xfs_growfs_data_private(
 		bp = xfs_buf_get(mp->m_ddev_targp,
 			XFS_AGB_TO_DADDR(mp, agno, XFS_CNT_BLOCK(mp)),
 			BTOBB(mp->m_sb.sb_blocksize), 0);
-		block = XFS_BUF_TO_SBLOCK(bp);
+		block = XFS_BUF_TO_BLOCK(bp);
 		memset(block, 0, mp->m_sb.sb_blocksize);
 		block->bb_magic = cpu_to_be32(XFS_ABTC_MAGIC);
 		block->bb_level = 0;
 		block->bb_numrecs = cpu_to_be16(1);
-		block->bb_leftsib = cpu_to_be32(NULLAGBLOCK);
-		block->bb_rightsib = cpu_to_be32(NULLAGBLOCK);
-		arec = XFS_BTREE_REC_ADDR(xfs_alloc, block, 1);
+		block->bb_u.s.bb_leftsib = cpu_to_be32(NULLAGBLOCK);
+		block->bb_u.s.bb_rightsib = cpu_to_be32(NULLAGBLOCK);
+		arec = XFS_ALLOC_REC_ADDR(mp, block, 1);
 		arec->ar_startblock = cpu_to_be32(XFS_PREALLOC_BLOCKS(mp));
 		arec->ar_blockcount = cpu_to_be32(
 			agsize - be32_to_cpu(arec->ar_startblock));
@@ -294,13 +294,13 @@ xfs_growfs_data_private(
 		bp = xfs_buf_get(mp->m_ddev_targp,
 			XFS_AGB_TO_DADDR(mp, agno, XFS_IBT_BLOCK(mp)),
 			BTOBB(mp->m_sb.sb_blocksize), 0);
-		block = XFS_BUF_TO_SBLOCK(bp);
+		block = XFS_BUF_TO_BLOCK(bp);
 		memset(block, 0, mp->m_sb.sb_blocksize);
 		block->bb_magic = cpu_to_be32(XFS_IBT_MAGIC);
 		block->bb_level = 0;
 		block->bb_numrecs = 0;
-		block->bb_leftsib = cpu_to_be32(NULLAGBLOCK);
-		block->bb_rightsib = cpu_to_be32(NULLAGBLOCK);
+		block->bb_u.s.bb_leftsib = cpu_to_be32(NULLAGBLOCK);
+		block->bb_u.s.bb_rightsib = cpu_to_be32(NULLAGBLOCK);
 		error = xfs_bwrite(mp, bp);
 		if (error) {
 			goto error0;
@@ -435,6 +435,9 @@ xfs_growfs_data(
 	xfs_growfs_data_t	*in)
 {
 	int error;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return XFS_ERROR(EPERM);
 	if (!mutex_trylock(&mp->m_growlock))
 		return XFS_ERROR(EWOULDBLOCK);
 	error = xfs_growfs_data_private(mp, in);
@@ -448,6 +451,9 @@ xfs_growfs_log(
 	xfs_growfs_log_t	*in)
 {
 	int error;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return XFS_ERROR(EPERM);
 	if (!mutex_trylock(&mp->m_growlock))
 		return XFS_ERROR(EWOULDBLOCK);
 	error = xfs_growfs_log_private(mp, in);
diff --git a/fs/xfs/xfs_ialloc.c b/fs/xfs/xfs_ialloc.c
index aad8c5da38af..e6ebbaeb4dc6 100644
--- a/fs/xfs/xfs_ialloc.c
+++ b/fs/xfs/xfs_ialloc.c
@@ -41,68 +41,6 @@
 #include "xfs_error.h"
 #include "xfs_bmap.h"
 
-/*
- * Log specified fields for the inode given by bp and off.
- */
-STATIC void
-xfs_ialloc_log_di(
-	xfs_trans_t	*tp,		/* transaction pointer */
-	xfs_buf_t	*bp,		/* inode buffer */
-	int		off,		/* index of inode in buffer */
-	int		fields)		/* bitmask of fields to log */
-{
-	int			first;		/* first byte number */
-	int			ioffset;	/* off in bytes */
-	int			last;		/* last byte number */
-	xfs_mount_t		*mp;		/* mount point structure */
-	static const short	offsets[] = {	/* field offsets */
-						/* keep in sync with bits */
-		offsetof(xfs_dinode_core_t, di_magic),
-		offsetof(xfs_dinode_core_t, di_mode),
-		offsetof(xfs_dinode_core_t, di_version),
-		offsetof(xfs_dinode_core_t, di_format),
-		offsetof(xfs_dinode_core_t, di_onlink),
-		offsetof(xfs_dinode_core_t, di_uid),
-		offsetof(xfs_dinode_core_t, di_gid),
-		offsetof(xfs_dinode_core_t, di_nlink),
-		offsetof(xfs_dinode_core_t, di_projid),
-		offsetof(xfs_dinode_core_t, di_pad),
-		offsetof(xfs_dinode_core_t, di_atime),
-		offsetof(xfs_dinode_core_t, di_mtime),
-		offsetof(xfs_dinode_core_t, di_ctime),
-		offsetof(xfs_dinode_core_t, di_size),
-		offsetof(xfs_dinode_core_t, di_nblocks),
-		offsetof(xfs_dinode_core_t, di_extsize),
-		offsetof(xfs_dinode_core_t, di_nextents),
-		offsetof(xfs_dinode_core_t, di_anextents),
-		offsetof(xfs_dinode_core_t, di_forkoff),
-		offsetof(xfs_dinode_core_t, di_aformat),
-		offsetof(xfs_dinode_core_t, di_dmevmask),
-		offsetof(xfs_dinode_core_t, di_dmstate),
-		offsetof(xfs_dinode_core_t, di_flags),
-		offsetof(xfs_dinode_core_t, di_gen),
-		offsetof(xfs_dinode_t, di_next_unlinked),
-		offsetof(xfs_dinode_t, di_u),
-		offsetof(xfs_dinode_t, di_a),
-		sizeof(xfs_dinode_t)
-	};
-
-
-	ASSERT(offsetof(xfs_dinode_t, di_core) == 0);
-	ASSERT((fields & (XFS_DI_U|XFS_DI_A)) == 0);
-	mp = tp->t_mountp;
-	/*
-	 * Get the inode-relative first and last bytes for these fields
-	 */
-	xfs_btree_offsets(fields, offsets, XFS_DI_NUM_BITS, &first, &last);
-	/*
-	 * Convert to buffer offsets and log it.
-	 */
-	ioffset = off << mp->m_sb.sb_inodelog;
-	first += ioffset;
-	last += ioffset;
-	xfs_trans_log_buf(tp, bp, first, last);
-}
 
 /*
  * Allocation group level functions.
@@ -119,6 +57,102 @@ xfs_ialloc_cluster_alignment(
 }
 
 /*
+ * Lookup the record equal to ino in the btree given by cur.
+ */
+STATIC int				/* error */
+xfs_inobt_lookup_eq(
+	struct xfs_btree_cur	*cur,	/* btree cursor */
+	xfs_agino_t		ino,	/* starting inode of chunk */
+	__int32_t		fcnt,	/* free inode count */
+	xfs_inofree_t		free,	/* free inode mask */
+	int			*stat)	/* success/failure */
+{
+	cur->bc_rec.i.ir_startino = ino;
+	cur->bc_rec.i.ir_freecount = fcnt;
+	cur->bc_rec.i.ir_free = free;
+	return xfs_btree_lookup(cur, XFS_LOOKUP_EQ, stat);
+}
+
+/*
+ * Lookup the first record greater than or equal to ino
+ * in the btree given by cur.
+ */
+int					/* error */
+xfs_inobt_lookup_ge(
+	struct xfs_btree_cur	*cur,	/* btree cursor */
+	xfs_agino_t		ino,	/* starting inode of chunk */
+	__int32_t		fcnt,	/* free inode count */
+	xfs_inofree_t		free,	/* free inode mask */
+	int			*stat)	/* success/failure */
+{
+	cur->bc_rec.i.ir_startino = ino;
+	cur->bc_rec.i.ir_freecount = fcnt;
+	cur->bc_rec.i.ir_free = free;
+	return xfs_btree_lookup(cur, XFS_LOOKUP_GE, stat);
+}
+
+/*
+ * Lookup the first record less than or equal to ino
+ * in the btree given by cur.
+ */
+int					/* error */
+xfs_inobt_lookup_le(
+	struct xfs_btree_cur	*cur,	/* btree cursor */
+	xfs_agino_t		ino,	/* starting inode of chunk */
+	__int32_t		fcnt,	/* free inode count */
+	xfs_inofree_t		free,	/* free inode mask */
+	int			*stat)	/* success/failure */
+{
+	cur->bc_rec.i.ir_startino = ino;
+	cur->bc_rec.i.ir_freecount = fcnt;
+	cur->bc_rec.i.ir_free = free;
+	return xfs_btree_lookup(cur, XFS_LOOKUP_LE, stat);
+}
+
+/*
+ * Update the record referred to by cur to the value given
+ * by [ino, fcnt, free].
+ * This either works (return 0) or gets an EFSCORRUPTED error.
+ */
+STATIC int				/* error */
+xfs_inobt_update(
+	struct xfs_btree_cur	*cur,	/* btree cursor */
+	xfs_agino_t		ino,	/* starting inode of chunk */
+	__int32_t		fcnt,	/* free inode count */
+	xfs_inofree_t		free)	/* free inode mask */
+{
+	union xfs_btree_rec	rec;
+
+	rec.inobt.ir_startino = cpu_to_be32(ino);
+	rec.inobt.ir_freecount = cpu_to_be32(fcnt);
+	rec.inobt.ir_free = cpu_to_be64(free);
+	return xfs_btree_update(cur, &rec);
+}
+
+/*
+ * Get the data from the pointed-to record.
+ */
+int					/* error */
+xfs_inobt_get_rec(
+	struct xfs_btree_cur	*cur,	/* btree cursor */
+	xfs_agino_t		*ino,	/* output: starting inode of chunk */
+	__int32_t		*fcnt,	/* output: number of free inodes */
+	xfs_inofree_t		*free,	/* output: free inode mask */
+	int			*stat)	/* output: success/failure */
+{
+	union xfs_btree_rec	*rec;
+	int			error;
+
+	error = xfs_btree_get_rec(cur, &rec, stat);
+	if (!error && *stat == 1) {
+		*ino = be32_to_cpu(rec->inobt.ir_startino);
+		*fcnt = be32_to_cpu(rec->inobt.ir_freecount);
+		*free = be64_to_cpu(rec->inobt.ir_free);
+	}
+	return error;
+}
+
+/*
  * Allocate new inodes in the allocation group specified by agbp.
  * Return 0 for success, else error code.
  */
@@ -287,9 +321,9 @@ xfs_ialloc_ag_alloc(
 	 * able to use the file system.
 	 */
 	if (xfs_sb_version_hasnlink(&args.mp->m_sb))
-		version = XFS_DINODE_VERSION_2;
+		version = 2;
 	else
-		version = XFS_DINODE_VERSION_1;
+		version = 1;
 
 	/*
 	 * Seed the new inode cluster with a random generation number. This
@@ -310,18 +344,25 @@ xfs_ialloc_ag_alloc(
 					 XFS_BUF_LOCK);
 		ASSERT(fbuf);
 		ASSERT(!XFS_BUF_GETERROR(fbuf));
+
 		/*
-		 * Set initial values for the inodes in this buffer.
+		 * Initialize all inodes in this buffer and then log them.
+		 *
+		 * XXX: It would be much better if we had just one transaction to
+		 *      log a whole cluster of inodes instead of all the indivdual
+		 *      transactions causing a lot of log traffic.
 		 */
 		xfs_biozero(fbuf, 0, ninodes << args.mp->m_sb.sb_inodelog);
 		for (i = 0; i < ninodes; i++) {
+			int	ioffset = i << args.mp->m_sb.sb_inodelog;
+			uint	isize = sizeof(struct xfs_dinode);
+
 			free = XFS_MAKE_IPTR(args.mp, fbuf, i);
-			free->di_core.di_magic = cpu_to_be16(XFS_DINODE_MAGIC);
-			free->di_core.di_version = version;
-			free->di_core.di_gen = cpu_to_be32(gen);
+			free->di_magic = cpu_to_be16(XFS_DINODE_MAGIC);
+			free->di_version = version;
+			free->di_gen = cpu_to_be32(gen);
 			free->di_next_unlinked = cpu_to_be32(NULLAGINO);
-			xfs_ialloc_log_di(tp, fbuf, i,
-				XFS_DI_CORE_BITS | XFS_DI_NEXT_UNLINKED);
+			xfs_trans_log_buf(tp, fbuf, ioffset, ioffset + isize - 1);
 		}
 		xfs_trans_inode_alloc_buf(tp, fbuf);
 	}
@@ -335,8 +376,7 @@ xfs_ialloc_ag_alloc(
 	/*
 	 * Insert records describing the new inode chunk into the btree.
 	 */
-	cur = xfs_btree_init_cursor(args.mp, tp, agbp, agno,
-			XFS_BTNUM_INO, (xfs_inode_t *)0, 0);
+	cur = xfs_inobt_init_cursor(args.mp, tp, agbp, agno);
 	for (thisino = newino;
 	     thisino < newino + newlen;
 	     thisino += XFS_INODES_PER_CHUNK) {
@@ -346,7 +386,7 @@ xfs_ialloc_ag_alloc(
 			return error;
 		}
 		ASSERT(i == 0);
-		if ((error = xfs_inobt_insert(cur, &i))) {
+		if ((error = xfs_btree_insert(cur, &i))) {
 			xfs_btree_del_cursor(cur, XFS_BTREE_ERROR);
 			return error;
 		}
@@ -676,8 +716,7 @@ nextag:
 	 */
 	agno = tagno;
 	*IO_agbp = NULL;
-	cur = xfs_btree_init_cursor(mp, tp, agbp, be32_to_cpu(agi->agi_seqno),
-				    XFS_BTNUM_INO, (xfs_inode_t *)0, 0);
+	cur = xfs_inobt_init_cursor(mp, tp, agbp, be32_to_cpu(agi->agi_seqno));
 	/*
 	 * If pagino is 0 (this is the root inode allocation) use newino.
 	 * This must work because we've just allocated some.
@@ -697,7 +736,7 @@ nextag:
 				goto error0;
 			XFS_WANT_CORRUPTED_GOTO(i == 1, error0);
 			freecount += rec.ir_freecount;
-			if ((error = xfs_inobt_increment(cur, 0, &i)))
+			if ((error = xfs_btree_increment(cur, 0, &i)))
 				goto error0;
 		} while (i == 1);
 
@@ -741,7 +780,7 @@ nextag:
 			/*
 			 * Search left with tcur, back up 1 record.
 			 */
-			if ((error = xfs_inobt_decrement(tcur, 0, &i)))
+			if ((error = xfs_btree_decrement(tcur, 0, &i)))
 				goto error1;
 			doneleft = !i;
 			if (!doneleft) {
@@ -755,7 +794,7 @@ nextag:
 			/*
 			 * Search right with cur, go forward 1 record.
 			 */
-			if ((error = xfs_inobt_increment(cur, 0, &i)))
+			if ((error = xfs_btree_increment(cur, 0, &i)))
 				goto error1;
 			doneright = !i;
 			if (!doneright) {
@@ -817,7 +856,7 @@ nextag:
 				 * further left.
 				 */
 				if (useleft) {
-					if ((error = xfs_inobt_decrement(tcur, 0,
+					if ((error = xfs_btree_decrement(tcur, 0,
 							&i)))
 						goto error1;
 					doneleft = !i;
@@ -837,7 +876,7 @@ nextag:
 				 * further right.
 				 */
 				else {
-					if ((error = xfs_inobt_increment(cur, 0,
+					if ((error = xfs_btree_increment(cur, 0,
 							&i)))
 						goto error1;
 					doneright = !i;
@@ -892,7 +931,7 @@ nextag:
 				XFS_WANT_CORRUPTED_GOTO(i == 1, error0);
 				if (rec.ir_freecount > 0)
 					break;
-				if ((error = xfs_inobt_increment(cur, 0, &i)))
+				if ((error = xfs_btree_increment(cur, 0, &i)))
 					goto error0;
 				XFS_WANT_CORRUPTED_GOTO(i == 1, error0);
 			}
@@ -926,7 +965,7 @@ nextag:
 				goto error0;
 			XFS_WANT_CORRUPTED_GOTO(i == 1, error0);
 			freecount += rec.ir_freecount;
-			if ((error = xfs_inobt_increment(cur, 0, &i)))
+			if ((error = xfs_btree_increment(cur, 0, &i)))
 				goto error0;
 		} while (i == 1);
 		ASSERT(freecount == be32_to_cpu(agi->agi_freecount) ||
@@ -1022,8 +1061,7 @@ xfs_difree(
 	/*
 	 * Initialize the cursor.
 	 */
-	cur = xfs_btree_init_cursor(mp, tp, agbp, agno, XFS_BTNUM_INO,
-		(xfs_inode_t *)0, 0);
+	cur = xfs_inobt_init_cursor(mp, tp, agbp, agno);
 #ifdef DEBUG
 	if (cur->bc_nlevels == 1) {
 		int freecount = 0;
@@ -1036,7 +1074,7 @@ xfs_difree(
 				goto error0;
 			if (i) {
 				freecount += rec.ir_freecount;
-				if ((error = xfs_inobt_increment(cur, 0, &i)))
+				if ((error = xfs_btree_increment(cur, 0, &i)))
 					goto error0;
 			}
 		} while (i == 1);
@@ -1098,8 +1136,8 @@ xfs_difree(
 		xfs_trans_mod_sb(tp, XFS_TRANS_SB_ICOUNT, -ilen);
 		xfs_trans_mod_sb(tp, XFS_TRANS_SB_IFREE, -(ilen - 1));
 
-		if ((error = xfs_inobt_delete(cur, &i))) {
-			cmn_err(CE_WARN, "xfs_difree: xfs_inobt_delete returned an error %d on %s.\n",
+		if ((error = xfs_btree_delete(cur, &i))) {
+			cmn_err(CE_WARN, "xfs_difree: xfs_btree_delete returned an error %d on %s.\n",
 				error, mp->m_fsname);
 			goto error0;
 		}
@@ -1141,7 +1179,7 @@ xfs_difree(
 				goto error0;
 			if (i) {
 				freecount += rec.ir_freecount;
-				if ((error = xfs_inobt_increment(cur, 0, &i)))
+				if ((error = xfs_btree_increment(cur, 0, &i)))
 					goto error0;
 			}
 		} while (i == 1);
@@ -1158,36 +1196,28 @@ error0:
 }
 
 /*
- * Return the location of the inode in bno/off, for mapping it into a buffer.
+ * Return the location of the inode in imap, for mapping it into a buffer.
  */
-/*ARGSUSED*/
 int
-xfs_dilocate(
-	xfs_mount_t	*mp,	/* file system mount structure */
-	xfs_trans_t	*tp,	/* transaction pointer */
+xfs_imap(
+	xfs_mount_t	 *mp,	/* file system mount structure */
+	xfs_trans_t	 *tp,	/* transaction pointer */
 	xfs_ino_t	ino,	/* inode to locate */
-	xfs_fsblock_t	*bno,	/* output: block containing inode */
-	int		*len,	/* output: num blocks in inode cluster */
-	int		*off,	/* output: index in block of inode */
-	uint		flags)	/* flags concerning inode lookup */
+	struct xfs_imap	*imap,	/* location map structure */
+	uint		flags)	/* flags for inode btree lookup */
 {
 	xfs_agblock_t	agbno;	/* block number of inode in the alloc group */
-	xfs_buf_t	*agbp;	/* agi buffer */
 	xfs_agino_t	agino;	/* inode number within alloc group */
 	xfs_agnumber_t	agno;	/* allocation group number */
 	int		blks_per_cluster; /* num blocks per inode cluster */
 	xfs_agblock_t	chunk_agbno;	/* first block in inode chunk */
-	xfs_agino_t	chunk_agino;	/* first agino in inode chunk */
-	__int32_t	chunk_cnt;	/* count of free inodes in chunk */
-	xfs_inofree_t	chunk_free;	/* mask of free inodes in chunk */
 	xfs_agblock_t	cluster_agbno;	/* first block in inode cluster */
-	xfs_btree_cur_t	*cur;	/* inode btree cursor */
 	int		error;	/* error code */
-	int		i;	/* temp state */
 	int		offset;	/* index of inode in its buffer */
 	int		offset_agbno;	/* blks from chunk start to inode */
 
 	ASSERT(ino != NULLFSINO);
+
 	/*
 	 * Split up the inode number into its parts.
 	 */
@@ -1198,24 +1228,24 @@ xfs_dilocate(
 	    ino != XFS_AGINO_TO_INO(mp, agno, agino)) {
 #ifdef DEBUG
 		/* no diagnostics for bulkstat, ino comes from userspace */
-		if (flags & XFS_IMAP_BULKSTAT)
+		if (flags & XFS_IGET_BULKSTAT)
 			return XFS_ERROR(EINVAL);
 		if (agno >= mp->m_sb.sb_agcount) {
 			xfs_fs_cmn_err(CE_ALERT, mp,
-					"xfs_dilocate: agno (%d) >= "
+					"xfs_imap: agno (%d) >= "
 					"mp->m_sb.sb_agcount (%d)",
 					agno,  mp->m_sb.sb_agcount);
 		}
 		if (agbno >= mp->m_sb.sb_agblocks) {
 			xfs_fs_cmn_err(CE_ALERT, mp,
-					"xfs_dilocate: agbno (0x%llx) >= "
+					"xfs_imap: agbno (0x%llx) >= "
 					"mp->m_sb.sb_agblocks (0x%lx)",
 					(unsigned long long) agbno,
 					(unsigned long) mp->m_sb.sb_agblocks);
 		}
 		if (ino != XFS_AGINO_TO_INO(mp, agno, agino)) {
 			xfs_fs_cmn_err(CE_ALERT, mp,
-					"xfs_dilocate: ino (0x%llx) != "
+					"xfs_imap: ino (0x%llx) != "
 					"XFS_AGINO_TO_INO(mp, agno, agino) "
 					"(0x%llx)",
 					ino, XFS_AGINO_TO_INO(mp, agno, agino));
@@ -1224,65 +1254,89 @@ xfs_dilocate(
 #endif /* DEBUG */
 		return XFS_ERROR(EINVAL);
 	}
-	if ((mp->m_sb.sb_blocksize >= XFS_INODE_CLUSTER_SIZE(mp)) ||
-	    !(flags & XFS_IMAP_LOOKUP)) {
+
+	/*
+	 * If the inode cluster size is the same as the blocksize or
+	 * smaller we get to the buffer by simple arithmetics.
+	 */
+	if (XFS_INODE_CLUSTER_SIZE(mp) <= mp->m_sb.sb_blocksize) {
 		offset = XFS_INO_TO_OFFSET(mp, ino);
 		ASSERT(offset < mp->m_sb.sb_inopblock);
-		*bno = XFS_AGB_TO_FSB(mp, agno, agbno);
-		*off = offset;
-		*len = 1;
+
+		imap->im_blkno = XFS_AGB_TO_DADDR(mp, agno, agbno);
+		imap->im_len = XFS_FSB_TO_BB(mp, 1);
+		imap->im_boffset = (ushort)(offset << mp->m_sb.sb_inodelog);
 		return 0;
 	}
+
 	blks_per_cluster = XFS_INODE_CLUSTER_SIZE(mp) >> mp->m_sb.sb_blocklog;
-	if (*bno != NULLFSBLOCK) {
+
+	/*
+	 * If we get a block number passed from bulkstat we can use it to
+	 * find the buffer easily.
+	 */
+	if (imap->im_blkno) {
 		offset = XFS_INO_TO_OFFSET(mp, ino);
 		ASSERT(offset < mp->m_sb.sb_inopblock);
-		cluster_agbno = XFS_FSB_TO_AGBNO(mp, *bno);
-		*off = ((agbno - cluster_agbno) * mp->m_sb.sb_inopblock) +
-			offset;
-		*len = blks_per_cluster;
+
+		cluster_agbno = XFS_DADDR_TO_AGBNO(mp, imap->im_blkno);
+		offset += (agbno - cluster_agbno) * mp->m_sb.sb_inopblock;
+
+		imap->im_len = XFS_FSB_TO_BB(mp, blks_per_cluster);
+		imap->im_boffset = (ushort)(offset << mp->m_sb.sb_inodelog);
 		return 0;
 	}
+
+	/*
+	 * If the inode chunks are aligned then use simple maths to
+	 * find the location. Otherwise we have to do a btree
+	 * lookup to find the location.
+	 */
 	if (mp->m_inoalign_mask) {
 		offset_agbno = agbno & mp->m_inoalign_mask;
 		chunk_agbno = agbno - offset_agbno;
 	} else {
+		xfs_btree_cur_t	*cur;	/* inode btree cursor */
+		xfs_agino_t	chunk_agino; /* first agino in inode chunk */
+		__int32_t	chunk_cnt; /* count of free inodes in chunk */
+		xfs_inofree_t	chunk_free; /* mask of free inodes in chunk */
+		xfs_buf_t	*agbp;	/* agi buffer */
+		int		i;	/* temp state */
+
 		down_read(&mp->m_peraglock);
 		error = xfs_ialloc_read_agi(mp, tp, agno, &agbp);
 		up_read(&mp->m_peraglock);
 		if (error) {
-#ifdef DEBUG
-			xfs_fs_cmn_err(CE_ALERT, mp, "xfs_dilocate: "
+			xfs_fs_cmn_err(CE_ALERT, mp, "xfs_imap: "
 					"xfs_ialloc_read_agi() returned "
 					"error %d, agno %d",
 					error, agno);
-#endif /* DEBUG */
 			return error;
 		}
-		cur = xfs_btree_init_cursor(mp, tp, agbp, agno, XFS_BTNUM_INO,
-			(xfs_inode_t *)0, 0);
-		if ((error = xfs_inobt_lookup_le(cur, agino, 0, 0, &i))) {
-#ifdef DEBUG
-			xfs_fs_cmn_err(CE_ALERT, mp, "xfs_dilocate: "
+
+		cur = xfs_inobt_init_cursor(mp, tp, agbp, agno);
+		error = xfs_inobt_lookup_le(cur, agino, 0, 0, &i);
+		if (error) {
+			xfs_fs_cmn_err(CE_ALERT, mp, "xfs_imap: "
 					"xfs_inobt_lookup_le() failed");
-#endif /* DEBUG */
 			goto error0;
 		}
-		if ((error = xfs_inobt_get_rec(cur, &chunk_agino, &chunk_cnt,
-				&chunk_free, &i))) {
-#ifdef DEBUG
-			xfs_fs_cmn_err(CE_ALERT, mp, "xfs_dilocate: "
+
+		error = xfs_inobt_get_rec(cur, &chunk_agino, &chunk_cnt,
+				&chunk_free, &i);
+		if (error) {
+			xfs_fs_cmn_err(CE_ALERT, mp, "xfs_imap: "
 					"xfs_inobt_get_rec() failed");
-#endif /* DEBUG */
 			goto error0;
 		}
 		if (i == 0) {
 #ifdef DEBUG
-			xfs_fs_cmn_err(CE_ALERT, mp, "xfs_dilocate: "
+			xfs_fs_cmn_err(CE_ALERT, mp, "xfs_imap: "
 					"xfs_inobt_get_rec() failed");
 #endif /* DEBUG */
 			error = XFS_ERROR(EINVAL);
 		}
+ error0:
 		xfs_trans_brelse(tp, agbp);
 		xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR);
 		if (error)
@@ -1290,19 +1344,35 @@ xfs_dilocate(
 		chunk_agbno = XFS_AGINO_TO_AGBNO(mp, chunk_agino);
 		offset_agbno = agbno - chunk_agbno;
 	}
+
 	ASSERT(agbno >= chunk_agbno);
 	cluster_agbno = chunk_agbno +
 		((offset_agbno / blks_per_cluster) * blks_per_cluster);
 	offset = ((agbno - cluster_agbno) * mp->m_sb.sb_inopblock) +
 		XFS_INO_TO_OFFSET(mp, ino);
-	*bno = XFS_AGB_TO_FSB(mp, agno, cluster_agbno);
-	*off = offset;
-	*len = blks_per_cluster;
+
+	imap->im_blkno = XFS_AGB_TO_DADDR(mp, agno, cluster_agbno);
+	imap->im_len = XFS_FSB_TO_BB(mp, blks_per_cluster);
+	imap->im_boffset = (ushort)(offset << mp->m_sb.sb_inodelog);
+
+	/*
+	 * If the inode number maps to a block outside the bounds
+	 * of the file system then return NULL rather than calling
+	 * read_buf and panicing when we get an error from the
+	 * driver.
+	 */
+	if ((imap->im_blkno + imap->im_len) >
+	    XFS_FSB_TO_BB(mp, mp->m_sb.sb_dblocks)) {
+		xfs_fs_cmn_err(CE_ALERT, mp, "xfs_imap: "
+			"(imap->im_blkno (0x%llx) + imap->im_len (0x%llx)) > "
+			" XFS_FSB_TO_BB(mp, mp->m_sb.sb_dblocks) (0x%llx)",
+			(unsigned long long) imap->im_blkno,
+			(unsigned long long) imap->im_len,
+			XFS_FSB_TO_BB(mp, mp->m_sb.sb_dblocks));
+		return XFS_ERROR(EINVAL);
+	}
+
 	return 0;
-error0:
-	xfs_trans_brelse(tp, agbp);
-	xfs_btree_del_cursor(cur, XFS_BTREE_ERROR);
-	return error;
 }
 
 /*
@@ -1370,70 +1440,95 @@ xfs_ialloc_log_agi(
 	xfs_trans_log_buf(tp, bp, first, last);
 }
 
+#ifdef DEBUG
+STATIC void
+xfs_check_agi_unlinked(
+	struct xfs_agi		*agi)
+{
+	int			i;
+
+	for (i = 0; i < XFS_AGI_UNLINKED_BUCKETS; i++)
+		ASSERT(agi->agi_unlinked[i]);
+}
+#else
+#define xfs_check_agi_unlinked(agi)
+#endif
+
 /*
  * Read in the allocation group header (inode allocation section)
  */
 int
-xfs_ialloc_read_agi(
-	xfs_mount_t	*mp,		/* file system mount structure */
-	xfs_trans_t	*tp,		/* transaction pointer */
-	xfs_agnumber_t	agno,		/* allocation group number */
-	xfs_buf_t	**bpp)		/* allocation group hdr buf */
+xfs_read_agi(
+	struct xfs_mount	*mp,	/* file system mount structure */
+	struct xfs_trans	*tp,	/* transaction pointer */
+	xfs_agnumber_t		agno,	/* allocation group number */
+	struct xfs_buf		**bpp)	/* allocation group hdr buf */
 {
-	xfs_agi_t	*agi;		/* allocation group header */
-	int		agi_ok;		/* agi is consistent */
-	xfs_buf_t	*bp;		/* allocation group hdr buf */
-	xfs_perag_t	*pag;		/* per allocation group data */
-	int		error;
+	struct xfs_agi		*agi;	/* allocation group header */
+	int			agi_ok;	/* agi is consistent */
+	int			error;
 
 	ASSERT(agno != NULLAGNUMBER);
-	error = xfs_trans_read_buf(
-			mp, tp, mp->m_ddev_targp,
+
+	error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp,
 			XFS_AG_DADDR(mp, agno, XFS_AGI_DADDR(mp)),
-			XFS_FSS_TO_BB(mp, 1), 0, &bp);
+			XFS_FSS_TO_BB(mp, 1), 0, bpp);
 	if (error)
 		return error;
-	ASSERT(bp && !XFS_BUF_GETERROR(bp));
+
+	ASSERT(*bpp && !XFS_BUF_GETERROR(*bpp));
+	agi = XFS_BUF_TO_AGI(*bpp);
 
 	/*
 	 * Validate the magic number of the agi block.
 	 */
-	agi = XFS_BUF_TO_AGI(bp);
-	agi_ok =
-		be32_to_cpu(agi->agi_magicnum) == XFS_AGI_MAGIC &&
-		XFS_AGI_GOOD_VERSION(be32_to_cpu(agi->agi_versionnum));
+	agi_ok = be32_to_cpu(agi->agi_magicnum) == XFS_AGI_MAGIC &&
+		XFS_AGI_GOOD_VERSION(be32_to_cpu(agi->agi_versionnum)) &&
+		be32_to_cpu(agi->agi_seqno) == agno;
 	if (unlikely(XFS_TEST_ERROR(!agi_ok, mp, XFS_ERRTAG_IALLOC_READ_AGI,
 			XFS_RANDOM_IALLOC_READ_AGI))) {
-		XFS_CORRUPTION_ERROR("xfs_ialloc_read_agi", XFS_ERRLEVEL_LOW,
+		XFS_CORRUPTION_ERROR("xfs_read_agi", XFS_ERRLEVEL_LOW,
 				     mp, agi);
-		xfs_trans_brelse(tp, bp);
+		xfs_trans_brelse(tp, *bpp);
 		return XFS_ERROR(EFSCORRUPTED);
 	}
+
+	XFS_BUF_SET_VTYPE_REF(*bpp, B_FS_AGI, XFS_AGI_REF);
+
+	xfs_check_agi_unlinked(agi);
+	return 0;
+}
+
+int
+xfs_ialloc_read_agi(
+	struct xfs_mount	*mp,	/* file system mount structure */
+	struct xfs_trans	*tp,	/* transaction pointer */
+	xfs_agnumber_t		agno,	/* allocation group number */
+	struct xfs_buf		**bpp)	/* allocation group hdr buf */
+{
+	struct xfs_agi		*agi;	/* allocation group header */
+	struct xfs_perag	*pag;	/* per allocation group data */
+	int			error;
+
+	error = xfs_read_agi(mp, tp, agno, bpp);
+	if (error)
+		return error;
+
+	agi = XFS_BUF_TO_AGI(*bpp);
 	pag = &mp->m_perag[agno];
+
 	if (!pag->pagi_init) {
 		pag->pagi_freecount = be32_to_cpu(agi->agi_freecount);
 		pag->pagi_count = be32_to_cpu(agi->agi_count);
 		pag->pagi_init = 1;
-	} else {
-		/*
-		 * It's possible for these to be out of sync if
-		 * we are in the middle of a forced shutdown.
-		 */
-		ASSERT(pag->pagi_freecount == be32_to_cpu(agi->agi_freecount) ||
-			XFS_FORCED_SHUTDOWN(mp));
 	}
 
-#ifdef DEBUG
-	{
-		int	i;
-
-		for (i = 0; i < XFS_AGI_UNLINKED_BUCKETS; i++)
-			ASSERT(agi->agi_unlinked[i]);
-	}
-#endif
-
-	XFS_BUF_SET_VTYPE_REF(bp, B_FS_AGI, XFS_AGI_REF);
-	*bpp = bp;
+	/*
+	 * It's possible for these to be out of sync if
+	 * we are in the middle of a forced shutdown.
+	 */
+	ASSERT(pag->pagi_freecount == be32_to_cpu(agi->agi_freecount) ||
+		XFS_FORCED_SHUTDOWN(mp));
 	return 0;
 }
 
diff --git a/fs/xfs/xfs_ialloc.h b/fs/xfs/xfs_ialloc.h
index 4e30ec1d13bc..50f558a4e0a8 100644
--- a/fs/xfs/xfs_ialloc.h
+++ b/fs/xfs/xfs_ialloc.h
@@ -20,6 +20,7 @@
 
 struct xfs_buf;
 struct xfs_dinode;
+struct xfs_imap;
 struct xfs_mount;
 struct xfs_trans;
 
@@ -56,7 +57,6 @@ static inline int xfs_ialloc_find_free(xfs_inofree_t *fp)
 }
 
 
-#ifdef __KERNEL__
 /*
  * Allocate an inode on disk.
  * Mode is used to tell whether the new inode will need space, and whether
@@ -105,17 +105,14 @@ xfs_difree(
 	xfs_ino_t	*first_ino);	/* first inode in deleted cluster */
 
 /*
- * Return the location of the inode in bno/len/off,
- * for mapping it into a buffer.
+ * Return the location of the inode in imap, for mapping it into a buffer.
  */
 int
-xfs_dilocate(
+xfs_imap(
 	struct xfs_mount *mp,		/* file system mount structure */
 	struct xfs_trans *tp,		/* transaction pointer */
 	xfs_ino_t	ino,		/* inode to locate */
-	xfs_fsblock_t	*bno,		/* output: block containing inode */
-	int		*len,		/* output: num blocks in cluster*/
-	int		*off,		/* output: index in block of inode */
+	struct xfs_imap	*imap,		/* location map structure */
 	uint		flags);		/* flags for inode btree lookup */
 
 /*
@@ -154,6 +151,24 @@ xfs_ialloc_pagi_init(
 	struct xfs_trans *tp,		/* transaction pointer */
         xfs_agnumber_t  agno);		/* allocation group number */
 
-#endif	/* __KERNEL__ */
+/*
+ * Lookup the first record greater than or equal to ino
+ * in the btree given by cur.
+ */
+int xfs_inobt_lookup_ge(struct xfs_btree_cur *cur, xfs_agino_t ino,
+		__int32_t fcnt,	xfs_inofree_t free, int *stat);
+
+/*
+ * Lookup the first record less than or equal to ino
+ * in the btree given by cur.
+ */
+int xfs_inobt_lookup_le(struct xfs_btree_cur *cur, xfs_agino_t ino,
+		__int32_t fcnt,	xfs_inofree_t free, int *stat);
+
+/*
+ * Get the data from the pointed-to record.
+ */
+extern int xfs_inobt_get_rec(struct xfs_btree_cur *cur, xfs_agino_t *ino,
+			     __int32_t *fcnt, xfs_inofree_t *free, int *stat);
 
 #endif	/* __XFS_IALLOC_H__ */
diff --git a/fs/xfs/xfs_ialloc_btree.c b/fs/xfs/xfs_ialloc_btree.c
index 83502f3edef0..99f2408e8d8e 100644
--- a/fs/xfs/xfs_ialloc_btree.c
+++ b/fs/xfs/xfs_ialloc_btree.c
@@ -35,2044 +35,349 @@
 #include "xfs_dinode.h"
 #include "xfs_inode.h"
 #include "xfs_btree.h"
+#include "xfs_btree_trace.h"
 #include "xfs_ialloc.h"
 #include "xfs_alloc.h"
 #include "xfs_error.h"
 
-STATIC void xfs_inobt_log_block(xfs_trans_t *, xfs_buf_t *, int);
-STATIC void xfs_inobt_log_keys(xfs_btree_cur_t *, xfs_buf_t *, int, int);
-STATIC void xfs_inobt_log_ptrs(xfs_btree_cur_t *, xfs_buf_t *, int, int);
-STATIC void xfs_inobt_log_recs(xfs_btree_cur_t *, xfs_buf_t *, int, int);
-STATIC int xfs_inobt_lshift(xfs_btree_cur_t *, int, int *);
-STATIC int xfs_inobt_newroot(xfs_btree_cur_t *, int *);
-STATIC int xfs_inobt_rshift(xfs_btree_cur_t *, int, int *);
-STATIC int xfs_inobt_split(xfs_btree_cur_t *, int, xfs_agblock_t *,
-		xfs_inobt_key_t *, xfs_btree_cur_t **, int *);
-STATIC int xfs_inobt_updkey(xfs_btree_cur_t *, xfs_inobt_key_t *, int);
 
-/*
- * Single level of the xfs_inobt_delete record deletion routine.
- * Delete record pointed to by cur/level.
- * Remove the record from its block then rebalance the tree.
- * Return 0 for error, 1 for done, 2 to go on to the next level.
- */
-STATIC int				/* error */
-xfs_inobt_delrec(
-	xfs_btree_cur_t		*cur,	/* btree cursor */
-	int			level,	/* level removing record from */
-	int			*stat)	/* fail/done/go-on */
+STATIC int
+xfs_inobt_get_minrecs(
+	struct xfs_btree_cur	*cur,
+	int			level)
 {
-	xfs_buf_t		*agbp;	/* buffer for a.g. inode header */
-	xfs_mount_t		*mp;	/* mount structure */
-	xfs_agi_t		*agi;	/* allocation group inode header */
-	xfs_inobt_block_t	*block;	/* btree block record/key lives in */
-	xfs_agblock_t		bno;	/* btree block number */
-	xfs_buf_t		*bp;	/* buffer for block */
-	int			error;	/* error return value */
-	int			i;	/* loop index */
-	xfs_inobt_key_t		key;	/* kp points here if block is level 0 */
-	xfs_inobt_key_t		*kp = NULL;	/* pointer to btree keys */
-	xfs_agblock_t		lbno;	/* left block's block number */
-	xfs_buf_t		*lbp;	/* left block's buffer pointer */
-	xfs_inobt_block_t	*left;	/* left btree block */
-	xfs_inobt_key_t		*lkp;	/* left block key pointer */
-	xfs_inobt_ptr_t		*lpp;	/* left block address pointer */
-	int			lrecs = 0;	/* number of records in left block */
-	xfs_inobt_rec_t		*lrp;	/* left block record pointer */
-	xfs_inobt_ptr_t		*pp = NULL;	/* pointer to btree addresses */
-	int			ptr;	/* index in btree block for this rec */
-	xfs_agblock_t		rbno;	/* right block's block number */
-	xfs_buf_t		*rbp;	/* right block's buffer pointer */
-	xfs_inobt_block_t	*right;	/* right btree block */
-	xfs_inobt_key_t		*rkp;	/* right block key pointer */
-	xfs_inobt_rec_t		*rp;	/* pointer to btree records */
-	xfs_inobt_ptr_t		*rpp;	/* right block address pointer */
-	int			rrecs = 0;	/* number of records in right block */
-	int			numrecs;
-	xfs_inobt_rec_t		*rrp;	/* right block record pointer */
-	xfs_btree_cur_t		*tcur;	/* temporary btree cursor */
-
-	mp = cur->bc_mp;
-
-	/*
-	 * Get the index of the entry being deleted, check for nothing there.
-	 */
-	ptr = cur->bc_ptrs[level];
-	if (ptr == 0) {
-		*stat = 0;
-		return 0;
-	}
-
-	/*
-	 * Get the buffer & block containing the record or key/ptr.
-	 */
-	bp = cur->bc_bufs[level];
-	block = XFS_BUF_TO_INOBT_BLOCK(bp);
-#ifdef DEBUG
-	if ((error = xfs_btree_check_sblock(cur, block, level, bp)))
-		return error;
-#endif
-	/*
-	 * Fail if we're off the end of the block.
-	 */
+	return cur->bc_mp->m_inobt_mnr[level != 0];
+}
 
-	numrecs = be16_to_cpu(block->bb_numrecs);
-	if (ptr > numrecs) {
-		*stat = 0;
-		return 0;
-	}
-	/*
-	 * It's a nonleaf.  Excise the key and ptr being deleted, by
-	 * sliding the entries past them down one.
-	 * Log the changed areas of the block.
-	 */
-	if (level > 0) {
-		kp = XFS_INOBT_KEY_ADDR(block, 1, cur);
-		pp = XFS_INOBT_PTR_ADDR(block, 1, cur);
-#ifdef DEBUG
-		for (i = ptr; i < numrecs; i++) {
-			if ((error = xfs_btree_check_sptr(cur, be32_to_cpu(pp[i]), level)))
-				return error;
-		}
-#endif
-		if (ptr < numrecs) {
-			memmove(&kp[ptr - 1], &kp[ptr],
-				(numrecs - ptr) * sizeof(*kp));
-			memmove(&pp[ptr - 1], &pp[ptr],
-				(numrecs - ptr) * sizeof(*kp));
-			xfs_inobt_log_keys(cur, bp, ptr, numrecs - 1);
-			xfs_inobt_log_ptrs(cur, bp, ptr, numrecs - 1);
-		}
-	}
-	/*
-	 * It's a leaf.  Excise the record being deleted, by sliding the
-	 * entries past it down one.  Log the changed areas of the block.
-	 */
-	else {
-		rp = XFS_INOBT_REC_ADDR(block, 1, cur);
-		if (ptr < numrecs) {
-			memmove(&rp[ptr - 1], &rp[ptr],
-				(numrecs - ptr) * sizeof(*rp));
-			xfs_inobt_log_recs(cur, bp, ptr, numrecs - 1);
-		}
-		/*
-		 * If it's the first record in the block, we'll need a key
-		 * structure to pass up to the next level (updkey).
-		 */
-		if (ptr == 1) {
-			key.ir_startino = rp->ir_startino;
-			kp = &key;
-		}
-	}
-	/*
-	 * Decrement and log the number of entries in the block.
-	 */
-	numrecs--;
-	block->bb_numrecs = cpu_to_be16(numrecs);
-	xfs_inobt_log_block(cur->bc_tp, bp, XFS_BB_NUMRECS);
-	/*
-	 * Is this the root level?  If so, we're almost done.
-	 */
-	if (level == cur->bc_nlevels - 1) {
-		/*
-		 * If this is the root level,
-		 * and there's only one entry left,
-		 * and it's NOT the leaf level,
-		 * then we can get rid of this level.
-		 */
-		if (numrecs == 1 && level > 0) {
-			agbp = cur->bc_private.a.agbp;
-			agi = XFS_BUF_TO_AGI(agbp);
-			/*
-			 * pp is still set to the first pointer in the block.
-			 * Make it the new root of the btree.
-			 */
-			bno = be32_to_cpu(agi->agi_root);
-			agi->agi_root = *pp;
-			be32_add_cpu(&agi->agi_level, -1);
-			/*
-			 * Free the block.
-			 */
-			if ((error = xfs_free_extent(cur->bc_tp,
-				XFS_AGB_TO_FSB(mp, cur->bc_private.a.agno, bno), 1)))
-				return error;
-			xfs_trans_binval(cur->bc_tp, bp);
-			xfs_ialloc_log_agi(cur->bc_tp, agbp,
-				XFS_AGI_ROOT | XFS_AGI_LEVEL);
-			/*
-			 * Update the cursor so there's one fewer level.
-			 */
-			cur->bc_bufs[level] = NULL;
-			cur->bc_nlevels--;
-		} else if (level > 0 &&
-			   (error = xfs_inobt_decrement(cur, level, &i)))
-			return error;
-		*stat = 1;
-		return 0;
-	}
-	/*
-	 * If we deleted the leftmost entry in the block, update the
-	 * key values above us in the tree.
-	 */
-	if (ptr == 1 && (error = xfs_inobt_updkey(cur, kp, level + 1)))
-		return error;
-	/*
-	 * If the number of records remaining in the block is at least
-	 * the minimum, we're done.
-	 */
-	if (numrecs >= XFS_INOBT_BLOCK_MINRECS(level, cur)) {
-		if (level > 0 &&
-		    (error = xfs_inobt_decrement(cur, level, &i)))
-			return error;
-		*stat = 1;
-		return 0;
-	}
-	/*
-	 * Otherwise, we have to move some records around to keep the
-	 * tree balanced.  Look at the left and right sibling blocks to
-	 * see if we can re-balance by moving only one record.
-	 */
-	rbno = be32_to_cpu(block->bb_rightsib);
-	lbno = be32_to_cpu(block->bb_leftsib);
-	bno = NULLAGBLOCK;
-	ASSERT(rbno != NULLAGBLOCK || lbno != NULLAGBLOCK);
-	/*
-	 * Duplicate the cursor so our btree manipulations here won't
-	 * disrupt the next level up.
-	 */
-	if ((error = xfs_btree_dup_cursor(cur, &tcur)))
-		return error;
-	/*
-	 * If there's a right sibling, see if it's ok to shift an entry
-	 * out of it.
-	 */
-	if (rbno != NULLAGBLOCK) {
-		/*
-		 * Move the temp cursor to the last entry in the next block.
-		 * Actually any entry but the first would suffice.
-		 */
-		i = xfs_btree_lastrec(tcur, level);
-		XFS_WANT_CORRUPTED_GOTO(i == 1, error0);
-		if ((error = xfs_inobt_increment(tcur, level, &i)))
-			goto error0;
-		XFS_WANT_CORRUPTED_GOTO(i == 1, error0);
-		i = xfs_btree_lastrec(tcur, level);
-		XFS_WANT_CORRUPTED_GOTO(i == 1, error0);
-		/*
-		 * Grab a pointer to the block.
-		 */
-		rbp = tcur->bc_bufs[level];
-		right = XFS_BUF_TO_INOBT_BLOCK(rbp);
-#ifdef DEBUG
-		if ((error = xfs_btree_check_sblock(cur, right, level, rbp)))
-			goto error0;
-#endif
-		/*
-		 * Grab the current block number, for future use.
-		 */
-		bno = be32_to_cpu(right->bb_leftsib);
-		/*
-		 * If right block is full enough so that removing one entry
-		 * won't make it too empty, and left-shifting an entry out
-		 * of right to us works, we're done.
-		 */
-		if (be16_to_cpu(right->bb_numrecs) - 1 >=
-		     XFS_INOBT_BLOCK_MINRECS(level, cur)) {
-			if ((error = xfs_inobt_lshift(tcur, level, &i)))
-				goto error0;
-			if (i) {
-				ASSERT(be16_to_cpu(block->bb_numrecs) >=
-				       XFS_INOBT_BLOCK_MINRECS(level, cur));
-				xfs_btree_del_cursor(tcur,
-						     XFS_BTREE_NOERROR);
-				if (level > 0 &&
-				    (error = xfs_inobt_decrement(cur, level,
-						&i)))
-					return error;
-				*stat = 1;
-				return 0;
-			}
-		}
-		/*
-		 * Otherwise, grab the number of records in right for
-		 * future reference, and fix up the temp cursor to point
-		 * to our block again (last record).
-		 */
-		rrecs = be16_to_cpu(right->bb_numrecs);
-		if (lbno != NULLAGBLOCK) {
-			xfs_btree_firstrec(tcur, level);
-			if ((error = xfs_inobt_decrement(tcur, level, &i)))
-				goto error0;
-		}
-	}
-	/*
-	 * If there's a left sibling, see if it's ok to shift an entry
-	 * out of it.
-	 */
-	if (lbno != NULLAGBLOCK) {
-		/*
-		 * Move the temp cursor to the first entry in the
-		 * previous block.
-		 */
-		xfs_btree_firstrec(tcur, level);
-		if ((error = xfs_inobt_decrement(tcur, level, &i)))
-			goto error0;
-		xfs_btree_firstrec(tcur, level);
-		/*
-		 * Grab a pointer to the block.
-		 */
-		lbp = tcur->bc_bufs[level];
-		left = XFS_BUF_TO_INOBT_BLOCK(lbp);
-#ifdef DEBUG
-		if ((error = xfs_btree_check_sblock(cur, left, level, lbp)))
-			goto error0;
-#endif
-		/*
-		 * Grab the current block number, for future use.
-		 */
-		bno = be32_to_cpu(left->bb_rightsib);
-		/*
-		 * If left block is full enough so that removing one entry
-		 * won't make it too empty, and right-shifting an entry out
-		 * of left to us works, we're done.
-		 */
-		if (be16_to_cpu(left->bb_numrecs) - 1 >=
-		     XFS_INOBT_BLOCK_MINRECS(level, cur)) {
-			if ((error = xfs_inobt_rshift(tcur, level, &i)))
-				goto error0;
-			if (i) {
-				ASSERT(be16_to_cpu(block->bb_numrecs) >=
-				       XFS_INOBT_BLOCK_MINRECS(level, cur));
-				xfs_btree_del_cursor(tcur,
-						     XFS_BTREE_NOERROR);
-				if (level == 0)
-					cur->bc_ptrs[0]++;
-				*stat = 1;
-				return 0;
-			}
-		}
-		/*
-		 * Otherwise, grab the number of records in right for
-		 * future reference.
-		 */
-		lrecs = be16_to_cpu(left->bb_numrecs);
-	}
-	/*
-	 * Delete the temp cursor, we're done with it.
-	 */
-	xfs_btree_del_cursor(tcur, XFS_BTREE_NOERROR);
-	/*
-	 * If here, we need to do a join to keep the tree balanced.
-	 */
-	ASSERT(bno != NULLAGBLOCK);
-	/*
-	 * See if we can join with the left neighbor block.
-	 */
-	if (lbno != NULLAGBLOCK &&
-	    lrecs + numrecs <= XFS_INOBT_BLOCK_MAXRECS(level, cur)) {
-		/*
-		 * Set "right" to be the starting block,
-		 * "left" to be the left neighbor.
-		 */
-		rbno = bno;
-		right = block;
-		rrecs = be16_to_cpu(right->bb_numrecs);
-		rbp = bp;
-		if ((error = xfs_btree_read_bufs(mp, cur->bc_tp,
-				cur->bc_private.a.agno, lbno, 0, &lbp,
-				XFS_INO_BTREE_REF)))
-			return error;
-		left = XFS_BUF_TO_INOBT_BLOCK(lbp);
-		lrecs = be16_to_cpu(left->bb_numrecs);
-		if ((error = xfs_btree_check_sblock(cur, left, level, lbp)))
-			return error;
-	}
-	/*
-	 * If that won't work, see if we can join with the right neighbor block.
-	 */
-	else if (rbno != NULLAGBLOCK &&
-		 rrecs + numrecs <= XFS_INOBT_BLOCK_MAXRECS(level, cur)) {
-		/*
-		 * Set "left" to be the starting block,
-		 * "right" to be the right neighbor.
-		 */
-		lbno = bno;
-		left = block;
-		lrecs = be16_to_cpu(left->bb_numrecs);
-		lbp = bp;
-		if ((error = xfs_btree_read_bufs(mp, cur->bc_tp,
-				cur->bc_private.a.agno, rbno, 0, &rbp,
-				XFS_INO_BTREE_REF)))
-			return error;
-		right = XFS_BUF_TO_INOBT_BLOCK(rbp);
-		rrecs = be16_to_cpu(right->bb_numrecs);
-		if ((error = xfs_btree_check_sblock(cur, right, level, rbp)))
-			return error;
-	}
-	/*
-	 * Otherwise, we can't fix the imbalance.
-	 * Just return.  This is probably a logic error, but it's not fatal.
-	 */
-	else {
-		if (level > 0 && (error = xfs_inobt_decrement(cur, level, &i)))
-			return error;
-		*stat = 1;
-		return 0;
-	}
-	/*
-	 * We're now going to join "left" and "right" by moving all the stuff
-	 * in "right" to "left" and deleting "right".
-	 */
-	if (level > 0) {
-		/*
-		 * It's a non-leaf.  Move keys and pointers.
-		 */
-		lkp = XFS_INOBT_KEY_ADDR(left, lrecs + 1, cur);
-		lpp = XFS_INOBT_PTR_ADDR(left, lrecs + 1, cur);
-		rkp = XFS_INOBT_KEY_ADDR(right, 1, cur);
-		rpp = XFS_INOBT_PTR_ADDR(right, 1, cur);
-#ifdef DEBUG
-		for (i = 0; i < rrecs; i++) {
-			if ((error = xfs_btree_check_sptr(cur, be32_to_cpu(rpp[i]), level)))
-				return error;
-		}
-#endif
-		memcpy(lkp, rkp, rrecs * sizeof(*lkp));
-		memcpy(lpp, rpp, rrecs * sizeof(*lpp));
-		xfs_inobt_log_keys(cur, lbp, lrecs + 1, lrecs + rrecs);
-		xfs_inobt_log_ptrs(cur, lbp, lrecs + 1, lrecs + rrecs);
-	} else {
-		/*
-		 * It's a leaf.  Move records.
-		 */
-		lrp = XFS_INOBT_REC_ADDR(left, lrecs + 1, cur);
-		rrp = XFS_INOBT_REC_ADDR(right, 1, cur);
-		memcpy(lrp, rrp, rrecs * sizeof(*lrp));
-		xfs_inobt_log_recs(cur, lbp, lrecs + 1, lrecs + rrecs);
-	}
-	/*
-	 * If we joined with the left neighbor, set the buffer in the
-	 * cursor to the left block, and fix up the index.
-	 */
-	if (bp != lbp) {
-		xfs_btree_setbuf(cur, level, lbp);
-		cur->bc_ptrs[level] += lrecs;
-	}
-	/*
-	 * If we joined with the right neighbor and there's a level above
-	 * us, increment the cursor at that level.
-	 */
-	else if (level + 1 < cur->bc_nlevels &&
-		 (error = xfs_alloc_increment(cur, level + 1, &i)))
-		return error;
-	/*
-	 * Fix up the number of records in the surviving block.
-	 */
-	lrecs += rrecs;
-	left->bb_numrecs = cpu_to_be16(lrecs);
-	/*
-	 * Fix up the right block pointer in the surviving block, and log it.
-	 */
-	left->bb_rightsib = right->bb_rightsib;
-	xfs_inobt_log_block(cur->bc_tp, lbp, XFS_BB_NUMRECS | XFS_BB_RIGHTSIB);
-	/*
-	 * If there is a right sibling now, make it point to the
-	 * remaining block.
-	 */
-	if (be32_to_cpu(left->bb_rightsib) != NULLAGBLOCK) {
-		xfs_inobt_block_t	*rrblock;
-		xfs_buf_t		*rrbp;
+STATIC struct xfs_btree_cur *
+xfs_inobt_dup_cursor(
+	struct xfs_btree_cur	*cur)
+{
+	return xfs_inobt_init_cursor(cur->bc_mp, cur->bc_tp,
+			cur->bc_private.a.agbp, cur->bc_private.a.agno);
+}
 
-		if ((error = xfs_btree_read_bufs(mp, cur->bc_tp,
-				cur->bc_private.a.agno, be32_to_cpu(left->bb_rightsib), 0,
-				&rrbp, XFS_INO_BTREE_REF)))
-			return error;
-		rrblock = XFS_BUF_TO_INOBT_BLOCK(rrbp);
-		if ((error = xfs_btree_check_sblock(cur, rrblock, level, rrbp)))
-			return error;
-		rrblock->bb_leftsib = cpu_to_be32(lbno);
-		xfs_inobt_log_block(cur->bc_tp, rrbp, XFS_BB_LEFTSIB);
-	}
-	/*
-	 * Free the deleting block.
-	 */
-	if ((error = xfs_free_extent(cur->bc_tp, XFS_AGB_TO_FSB(mp,
-				     cur->bc_private.a.agno, rbno), 1)))
-		return error;
-	xfs_trans_binval(cur->bc_tp, rbp);
-	/*
-	 * Readjust the ptr at this level if it's not a leaf, since it's
-	 * still pointing at the deletion point, which makes the cursor
-	 * inconsistent.  If this makes the ptr 0, the caller fixes it up.
-	 * We can't use decrement because it would change the next level up.
-	 */
-	if (level > 0)
-		cur->bc_ptrs[level]--;
-	/*
-	 * Return value means the next level up has something to do.
-	 */
-	*stat = 2;
-	return 0;
+STATIC void
+xfs_inobt_set_root(
+	struct xfs_btree_cur	*cur,
+	union xfs_btree_ptr	*nptr,
+	int			inc)	/* level change */
+{
+	struct xfs_buf		*agbp = cur->bc_private.a.agbp;
+	struct xfs_agi		*agi = XFS_BUF_TO_AGI(agbp);
 
-error0:
-	xfs_btree_del_cursor(tcur, XFS_BTREE_ERROR);
-	return error;
+	agi->agi_root = nptr->s;
+	be32_add_cpu(&agi->agi_level, inc);
+	xfs_ialloc_log_agi(cur->bc_tp, agbp, XFS_AGI_ROOT | XFS_AGI_LEVEL);
 }
 
-/*
- * Insert one record/level.  Return information to the caller
- * allowing the next level up to proceed if necessary.
- */
-STATIC int				/* error */
-xfs_inobt_insrec(
-	xfs_btree_cur_t		*cur,	/* btree cursor */
-	int			level,	/* level to insert record at */
-	xfs_agblock_t		*bnop,	/* i/o: block number inserted */
-	xfs_inobt_rec_t		*recp,	/* i/o: record data inserted */
-	xfs_btree_cur_t		**curp,	/* output: new cursor replacing cur */
-	int			*stat)	/* success/failure */
+STATIC int
+xfs_inobt_alloc_block(
+	struct xfs_btree_cur	*cur,
+	union xfs_btree_ptr	*start,
+	union xfs_btree_ptr	*new,
+	int			length,
+	int			*stat)
 {
-	xfs_inobt_block_t	*block;	/* btree block record/key lives in */
-	xfs_buf_t		*bp;	/* buffer for block */
-	int			error;	/* error return value */
-	int			i;	/* loop index */
-	xfs_inobt_key_t		key;	/* key value being inserted */
-	xfs_inobt_key_t		*kp=NULL;	/* pointer to btree keys */
-	xfs_agblock_t		nbno;	/* block number of allocated block */
-	xfs_btree_cur_t		*ncur;	/* new cursor to be used at next lvl */
-	xfs_inobt_key_t		nkey;	/* new key value, from split */
-	xfs_inobt_rec_t		nrec;	/* new record value, for caller */
-	int			numrecs;
-	int			optr;	/* old ptr value */
-	xfs_inobt_ptr_t		*pp;	/* pointer to btree addresses */
-	int			ptr;	/* index in btree block for this rec */
-	xfs_inobt_rec_t		*rp=NULL;	/* pointer to btree records */
+	xfs_alloc_arg_t		args;		/* block allocation args */
+	int			error;		/* error return value */
+	xfs_agblock_t		sbno = be32_to_cpu(start->s);
 
-	/*
-	 * GCC doesn't understand the (arguably complex) control flow in
-	 * this function and complains about uninitialized structure fields
-	 * without this.
-	 */
-	memset(&nrec, 0, sizeof(nrec));
+	XFS_BTREE_TRACE_CURSOR(cur, XBT_ENTRY);
 
-	/*
-	 * If we made it to the root level, allocate a new root block
-	 * and we're done.
-	 */
-	if (level >= cur->bc_nlevels) {
-		error = xfs_inobt_newroot(cur, &i);
-		*bnop = NULLAGBLOCK;
-		*stat = i;
+	memset(&args, 0, sizeof(args));
+	args.tp = cur->bc_tp;
+	args.mp = cur->bc_mp;
+	args.fsbno = XFS_AGB_TO_FSB(args.mp, cur->bc_private.a.agno, sbno);
+	args.minlen = 1;
+	args.maxlen = 1;
+	args.prod = 1;
+	args.type = XFS_ALLOCTYPE_NEAR_BNO;
+
+	error = xfs_alloc_vextent(&args);
+	if (error) {
+		XFS_BTREE_TRACE_CURSOR(cur, XBT_ERROR);
 		return error;
 	}
-	/*
-	 * Make a key out of the record data to be inserted, and save it.
-	 */
-	key.ir_startino = recp->ir_startino;
-	optr = ptr = cur->bc_ptrs[level];
-	/*
-	 * If we're off the left edge, return failure.
-	 */
-	if (ptr == 0) {
+	if (args.fsbno == NULLFSBLOCK) {
+		XFS_BTREE_TRACE_CURSOR(cur, XBT_EXIT);
 		*stat = 0;
 		return 0;
 	}
-	/*
-	 * Get pointers to the btree buffer and block.
-	 */
-	bp = cur->bc_bufs[level];
-	block = XFS_BUF_TO_INOBT_BLOCK(bp);
-	numrecs = be16_to_cpu(block->bb_numrecs);
-#ifdef DEBUG
-	if ((error = xfs_btree_check_sblock(cur, block, level, bp)))
-		return error;
-	/*
-	 * Check that the new entry is being inserted in the right place.
-	 */
-	if (ptr <= numrecs) {
-		if (level == 0) {
-			rp = XFS_INOBT_REC_ADDR(block, ptr, cur);
-			xfs_btree_check_rec(cur->bc_btnum, recp, rp);
-		} else {
-			kp = XFS_INOBT_KEY_ADDR(block, ptr, cur);
-			xfs_btree_check_key(cur->bc_btnum, &key, kp);
-		}
-	}
-#endif
-	nbno = NULLAGBLOCK;
-	ncur = NULL;
-	/*
-	 * If the block is full, we can't insert the new entry until we
-	 * make the block un-full.
-	 */
-	if (numrecs == XFS_INOBT_BLOCK_MAXRECS(level, cur)) {
-		/*
-		 * First, try shifting an entry to the right neighbor.
-		 */
-		if ((error = xfs_inobt_rshift(cur, level, &i)))
-			return error;
-		if (i) {
-			/* nothing */
-		}
-		/*
-		 * Next, try shifting an entry to the left neighbor.
-		 */
-		else {
-			if ((error = xfs_inobt_lshift(cur, level, &i)))
-				return error;
-			if (i) {
-				optr = ptr = cur->bc_ptrs[level];
-			} else {
-				/*
-				 * Next, try splitting the current block
-				 * in half. If this works we have to
-				 * re-set our variables because
-				 * we could be in a different block now.
-				 */
-				if ((error = xfs_inobt_split(cur, level, &nbno,
-						&nkey, &ncur, &i)))
-					return error;
-				if (i) {
-					bp = cur->bc_bufs[level];
-					block = XFS_BUF_TO_INOBT_BLOCK(bp);
-#ifdef DEBUG
-					if ((error = xfs_btree_check_sblock(cur,
-							block, level, bp)))
-						return error;
-#endif
-					ptr = cur->bc_ptrs[level];
-					nrec.ir_startino = nkey.ir_startino;
-				} else {
-					/*
-					 * Otherwise the insert fails.
-					 */
-					*stat = 0;
-					return 0;
-				}
-			}
-		}
-	}
-	/*
-	 * At this point we know there's room for our new entry in the block
-	 * we're pointing at.
-	 */
-	numrecs = be16_to_cpu(block->bb_numrecs);
-	if (level > 0) {
-		/*
-		 * It's a non-leaf entry.  Make a hole for the new data
-		 * in the key and ptr regions of the block.
-		 */
-		kp = XFS_INOBT_KEY_ADDR(block, 1, cur);
-		pp = XFS_INOBT_PTR_ADDR(block, 1, cur);
-#ifdef DEBUG
-		for (i = numrecs; i >= ptr; i--) {
-			if ((error = xfs_btree_check_sptr(cur, be32_to_cpu(pp[i - 1]), level)))
-				return error;
-		}
-#endif
-		memmove(&kp[ptr], &kp[ptr - 1],
-			(numrecs - ptr + 1) * sizeof(*kp));
-		memmove(&pp[ptr], &pp[ptr - 1],
-			(numrecs - ptr + 1) * sizeof(*pp));
-		/*
-		 * Now stuff the new data in, bump numrecs and log the new data.
-		 */
-#ifdef DEBUG
-		if ((error = xfs_btree_check_sptr(cur, *bnop, level)))
-			return error;
-#endif
-		kp[ptr - 1] = key;
-		pp[ptr - 1] = cpu_to_be32(*bnop);
-		numrecs++;
-		block->bb_numrecs = cpu_to_be16(numrecs);
-		xfs_inobt_log_keys(cur, bp, ptr, numrecs);
-		xfs_inobt_log_ptrs(cur, bp, ptr, numrecs);
-	} else {
-		/*
-		 * It's a leaf entry.  Make a hole for the new record.
-		 */
-		rp = XFS_INOBT_REC_ADDR(block, 1, cur);
-		memmove(&rp[ptr], &rp[ptr - 1],
-			(numrecs - ptr + 1) * sizeof(*rp));
-		/*
-		 * Now stuff the new record in, bump numrecs
-		 * and log the new data.
-		 */
-		rp[ptr - 1] = *recp;
-		numrecs++;
-		block->bb_numrecs = cpu_to_be16(numrecs);
-		xfs_inobt_log_recs(cur, bp, ptr, numrecs);
-	}
-	/*
-	 * Log the new number of records in the btree header.
-	 */
-	xfs_inobt_log_block(cur->bc_tp, bp, XFS_BB_NUMRECS);
-#ifdef DEBUG
-	/*
-	 * Check that the key/record is in the right place, now.
-	 */
-	if (ptr < numrecs) {
-		if (level == 0)
-			xfs_btree_check_rec(cur->bc_btnum, rp + ptr - 1,
-				rp + ptr);
-		else
-			xfs_btree_check_key(cur->bc_btnum, kp + ptr - 1,
-				kp + ptr);
-	}
-#endif
-	/*
-	 * If we inserted at the start of a block, update the parents' keys.
-	 */
-	if (optr == 1 && (error = xfs_inobt_updkey(cur, &key, level + 1)))
-		return error;
-	/*
-	 * Return the new block number, if any.
-	 * If there is one, give back a record value and a cursor too.
-	 */
-	*bnop = nbno;
-	if (nbno != NULLAGBLOCK) {
-		*recp = nrec;
-		*curp = ncur;
-	}
+	ASSERT(args.len == 1);
+	XFS_BTREE_TRACE_CURSOR(cur, XBT_EXIT);
+
+	new->s = cpu_to_be32(XFS_FSB_TO_AGBNO(args.mp, args.fsbno));
 	*stat = 1;
 	return 0;
 }
 
-/*
- * Log header fields from a btree block.
- */
-STATIC void
-xfs_inobt_log_block(
-	xfs_trans_t		*tp,	/* transaction pointer */
-	xfs_buf_t		*bp,	/* buffer containing btree block */
-	int			fields)	/* mask of fields: XFS_BB_... */
+STATIC int
+xfs_inobt_free_block(
+	struct xfs_btree_cur	*cur,
+	struct xfs_buf		*bp)
 {
-	int			first;	/* first byte offset logged */
-	int			last;	/* last byte offset logged */
-	static const short	offsets[] = {	/* table of offsets */
-		offsetof(xfs_inobt_block_t, bb_magic),
-		offsetof(xfs_inobt_block_t, bb_level),
-		offsetof(xfs_inobt_block_t, bb_numrecs),
-		offsetof(xfs_inobt_block_t, bb_leftsib),
-		offsetof(xfs_inobt_block_t, bb_rightsib),
-		sizeof(xfs_inobt_block_t)
-	};
+	xfs_fsblock_t		fsbno;
+	int			error;
 
-	xfs_btree_offsets(fields, offsets, XFS_BB_NUM_BITS, &first, &last);
-	xfs_trans_log_buf(tp, bp, first, last);
+	fsbno = XFS_DADDR_TO_FSB(cur->bc_mp, XFS_BUF_ADDR(bp));
+	error = xfs_free_extent(cur->bc_tp, fsbno, 1);
+	if (error)
+		return error;
+
+	xfs_trans_binval(cur->bc_tp, bp);
+	return error;
 }
 
-/*
- * Log keys from a btree block (nonleaf).
- */
-STATIC void
-xfs_inobt_log_keys(
-	xfs_btree_cur_t		*cur,	/* btree cursor */
-	xfs_buf_t		*bp,	/* buffer containing btree block */
-	int			kfirst,	/* index of first key to log */
-	int			klast)	/* index of last key to log */
+STATIC int
+xfs_inobt_get_maxrecs(
+	struct xfs_btree_cur	*cur,
+	int			level)
 {
-	xfs_inobt_block_t	*block;	/* btree block to log from */
-	int			first;	/* first byte offset logged */
-	xfs_inobt_key_t		*kp;	/* key pointer in btree block */
-	int			last;	/* last byte offset logged */
-
-	block = XFS_BUF_TO_INOBT_BLOCK(bp);
-	kp = XFS_INOBT_KEY_ADDR(block, 1, cur);
-	first = (int)((xfs_caddr_t)&kp[kfirst - 1] - (xfs_caddr_t)block);
-	last = (int)(((xfs_caddr_t)&kp[klast] - 1) - (xfs_caddr_t)block);
-	xfs_trans_log_buf(cur->bc_tp, bp, first, last);
+	return cur->bc_mp->m_inobt_mxr[level != 0];
 }
 
-/*
- * Log block pointer fields from a btree block (nonleaf).
- */
 STATIC void
-xfs_inobt_log_ptrs(
-	xfs_btree_cur_t		*cur,	/* btree cursor */
-	xfs_buf_t		*bp,	/* buffer containing btree block */
-	int			pfirst,	/* index of first pointer to log */
-	int			plast)	/* index of last pointer to log */
+xfs_inobt_init_key_from_rec(
+	union xfs_btree_key	*key,
+	union xfs_btree_rec	*rec)
 {
-	xfs_inobt_block_t	*block;	/* btree block to log from */
-	int			first;	/* first byte offset logged */
-	int			last;	/* last byte offset logged */
-	xfs_inobt_ptr_t		*pp;	/* block-pointer pointer in btree blk */
-
-	block = XFS_BUF_TO_INOBT_BLOCK(bp);
-	pp = XFS_INOBT_PTR_ADDR(block, 1, cur);
-	first = (int)((xfs_caddr_t)&pp[pfirst - 1] - (xfs_caddr_t)block);
-	last = (int)(((xfs_caddr_t)&pp[plast] - 1) - (xfs_caddr_t)block);
-	xfs_trans_log_buf(cur->bc_tp, bp, first, last);
+	key->inobt.ir_startino = rec->inobt.ir_startino;
 }
 
-/*
- * Log records from a btree block (leaf).
- */
 STATIC void
-xfs_inobt_log_recs(
-	xfs_btree_cur_t		*cur,	/* btree cursor */
-	xfs_buf_t		*bp,	/* buffer containing btree block */
-	int			rfirst,	/* index of first record to log */
-	int			rlast)	/* index of last record to log */
+xfs_inobt_init_rec_from_key(
+	union xfs_btree_key	*key,
+	union xfs_btree_rec	*rec)
 {
-	xfs_inobt_block_t	*block;	/* btree block to log from */
-	int			first;	/* first byte offset logged */
-	int			last;	/* last byte offset logged */
-	xfs_inobt_rec_t		*rp;	/* record pointer for btree block */
+	rec->inobt.ir_startino = key->inobt.ir_startino;
+}
 
-	block = XFS_BUF_TO_INOBT_BLOCK(bp);
-	rp = XFS_INOBT_REC_ADDR(block, 1, cur);
-	first = (int)((xfs_caddr_t)&rp[rfirst - 1] - (xfs_caddr_t)block);
-	last = (int)(((xfs_caddr_t)&rp[rlast] - 1) - (xfs_caddr_t)block);
-	xfs_trans_log_buf(cur->bc_tp, bp, first, last);
+STATIC void
+xfs_inobt_init_rec_from_cur(
+	struct xfs_btree_cur	*cur,
+	union xfs_btree_rec	*rec)
+{
+	rec->inobt.ir_startino = cpu_to_be32(cur->bc_rec.i.ir_startino);
+	rec->inobt.ir_freecount = cpu_to_be32(cur->bc_rec.i.ir_freecount);
+	rec->inobt.ir_free = cpu_to_be64(cur->bc_rec.i.ir_free);
 }
 
 /*
- * Lookup the record.  The cursor is made to point to it, based on dir.
- * Return 0 if can't find any such record, 1 for success.
+ * intial value of ptr for lookup
  */
-STATIC int				/* error */
-xfs_inobt_lookup(
-	xfs_btree_cur_t		*cur,	/* btree cursor */
-	xfs_lookup_t		dir,	/* <=, ==, or >= */
-	int			*stat)	/* success/failure */
+STATIC void
+xfs_inobt_init_ptr_from_cur(
+	struct xfs_btree_cur	*cur,
+	union xfs_btree_ptr	*ptr)
 {
-	xfs_agblock_t		agbno;	/* a.g. relative btree block number */
-	xfs_agnumber_t		agno;	/* allocation group number */
-	xfs_inobt_block_t	*block=NULL;	/* current btree block */
-	__int64_t		diff;	/* difference for the current key */
-	int			error;	/* error return value */
-	int			keyno=0;	/* current key number */
-	int			level;	/* level in the btree */
-	xfs_mount_t		*mp;	/* file system mount point */
-
-	/*
-	 * Get the allocation group header, and the root block number.
-	 */
-	mp = cur->bc_mp;
-	{
-		xfs_agi_t	*agi;	/* a.g. inode header */
-
-		agi = XFS_BUF_TO_AGI(cur->bc_private.a.agbp);
-		agno = be32_to_cpu(agi->agi_seqno);
-		agbno = be32_to_cpu(agi->agi_root);
-	}
-	/*
-	 * Iterate over each level in the btree, starting at the root.
-	 * For each level above the leaves, find the key we need, based
-	 * on the lookup record, then follow the corresponding block
-	 * pointer down to the next level.
-	 */
-	for (level = cur->bc_nlevels - 1, diff = 1; level >= 0; level--) {
-		xfs_buf_t	*bp;	/* buffer pointer for btree block */
-		xfs_daddr_t	d;	/* disk address of btree block */
-
-		/*
-		 * Get the disk address we're looking for.
-		 */
-		d = XFS_AGB_TO_DADDR(mp, agno, agbno);
-		/*
-		 * If the old buffer at this level is for a different block,
-		 * throw it away, otherwise just use it.
-		 */
-		bp = cur->bc_bufs[level];
-		if (bp && XFS_BUF_ADDR(bp) != d)
-			bp = NULL;
-		if (!bp) {
-			/*
-			 * Need to get a new buffer.  Read it, then
-			 * set it in the cursor, releasing the old one.
-			 */
-			if ((error = xfs_btree_read_bufs(mp, cur->bc_tp,
-					agno, agbno, 0, &bp, XFS_INO_BTREE_REF)))
-				return error;
-			xfs_btree_setbuf(cur, level, bp);
-			/*
-			 * Point to the btree block, now that we have the buffer
-			 */
-			block = XFS_BUF_TO_INOBT_BLOCK(bp);
-			if ((error = xfs_btree_check_sblock(cur, block, level,
-					bp)))
-				return error;
-		} else
-			block = XFS_BUF_TO_INOBT_BLOCK(bp);
-		/*
-		 * If we already had a key match at a higher level, we know
-		 * we need to use the first entry in this block.
-		 */
-		if (diff == 0)
-			keyno = 1;
-		/*
-		 * Otherwise we need to search this block.  Do a binary search.
-		 */
-		else {
-			int		high;	/* high entry number */
-			xfs_inobt_key_t	*kkbase=NULL;/* base of keys in block */
-			xfs_inobt_rec_t	*krbase=NULL;/* base of records in block */
-			int		low;	/* low entry number */
+	struct xfs_agi		*agi = XFS_BUF_TO_AGI(cur->bc_private.a.agbp);
 
-			/*
-			 * Get a pointer to keys or records.
-			 */
-			if (level > 0)
-				kkbase = XFS_INOBT_KEY_ADDR(block, 1, cur);
-			else
-				krbase = XFS_INOBT_REC_ADDR(block, 1, cur);
-			/*
-			 * Set low and high entry numbers, 1-based.
-			 */
-			low = 1;
-			if (!(high = be16_to_cpu(block->bb_numrecs))) {
-				/*
-				 * If the block is empty, the tree must
-				 * be an empty leaf.
-				 */
-				ASSERT(level == 0 && cur->bc_nlevels == 1);
-				cur->bc_ptrs[0] = dir != XFS_LOOKUP_LE;
-				*stat = 0;
-				return 0;
-			}
-			/*
-			 * Binary search the block.
-			 */
-			while (low <= high) {
-				xfs_agino_t	startino;	/* key value */
-
-				/*
-				 * keyno is average of low and high.
-				 */
-				keyno = (low + high) >> 1;
-				/*
-				 * Get startino.
-				 */
-				if (level > 0) {
-					xfs_inobt_key_t	*kkp;
-
-					kkp = kkbase + keyno - 1;
-					startino = be32_to_cpu(kkp->ir_startino);
-				} else {
-					xfs_inobt_rec_t	*krp;
-
-					krp = krbase + keyno - 1;
-					startino = be32_to_cpu(krp->ir_startino);
-				}
-				/*
-				 * Compute difference to get next direction.
-				 */
-				diff = (__int64_t)
-					startino - cur->bc_rec.i.ir_startino;
-				/*
-				 * Less than, move right.
-				 */
-				if (diff < 0)
-					low = keyno + 1;
-				/*
-				 * Greater than, move left.
-				 */
-				else if (diff > 0)
-					high = keyno - 1;
-				/*
-				 * Equal, we're done.
-				 */
-				else
-					break;
-			}
-		}
-		/*
-		 * If there are more levels, set up for the next level
-		 * by getting the block number and filling in the cursor.
-		 */
-		if (level > 0) {
-			/*
-			 * If we moved left, need the previous key number,
-			 * unless there isn't one.
-			 */
-			if (diff > 0 && --keyno < 1)
-				keyno = 1;
-			agbno = be32_to_cpu(*XFS_INOBT_PTR_ADDR(block, keyno, cur));
-#ifdef DEBUG
-			if ((error = xfs_btree_check_sptr(cur, agbno, level)))
-				return error;
-#endif
-			cur->bc_ptrs[level] = keyno;
-		}
-	}
-	/*
-	 * Done with the search.
-	 * See if we need to adjust the results.
-	 */
-	if (dir != XFS_LOOKUP_LE && diff < 0) {
-		keyno++;
-		/*
-		 * If ge search and we went off the end of the block, but it's
-		 * not the last block, we're in the wrong block.
-		 */
-		if (dir == XFS_LOOKUP_GE &&
-		    keyno > be16_to_cpu(block->bb_numrecs) &&
-		    be32_to_cpu(block->bb_rightsib) != NULLAGBLOCK) {
-			int	i;
+	ASSERT(cur->bc_private.a.agno == be32_to_cpu(agi->agi_seqno));
 
-			cur->bc_ptrs[0] = keyno;
-			if ((error = xfs_inobt_increment(cur, 0, &i)))
-				return error;
-			ASSERT(i == 1);
-			*stat = 1;
-			return 0;
-		}
-	}
-	else if (dir == XFS_LOOKUP_LE && diff > 0)
-		keyno--;
-	cur->bc_ptrs[0] = keyno;
-	/*
-	 * Return if we succeeded or not.
-	 */
-	if (keyno == 0 || keyno > be16_to_cpu(block->bb_numrecs))
-		*stat = 0;
-	else
-		*stat = ((dir != XFS_LOOKUP_EQ) || (diff == 0));
-	return 0;
+	ptr->s = agi->agi_root;
 }
 
-/*
- * Move 1 record left from cur/level if possible.
- * Update cur to reflect the new path.
- */
-STATIC int				/* error */
-xfs_inobt_lshift(
-	xfs_btree_cur_t		*cur,	/* btree cursor */
-	int			level,	/* level to shift record on */
-	int			*stat)	/* success/failure */
+STATIC __int64_t
+xfs_inobt_key_diff(
+	struct xfs_btree_cur	*cur,
+	union xfs_btree_key	*key)
 {
-	int			error;	/* error return value */
-#ifdef DEBUG
-	int			i;	/* loop index */
-#endif
-	xfs_inobt_key_t		key;	/* key value for leaf level upward */
-	xfs_buf_t		*lbp;	/* buffer for left neighbor block */
-	xfs_inobt_block_t	*left;	/* left neighbor btree block */
-	xfs_inobt_key_t		*lkp=NULL;	/* key pointer for left block */
-	xfs_inobt_ptr_t		*lpp;	/* address pointer for left block */
-	xfs_inobt_rec_t		*lrp=NULL;	/* record pointer for left block */
-	int			nrec;	/* new number of left block entries */
-	xfs_buf_t		*rbp;	/* buffer for right (current) block */
-	xfs_inobt_block_t	*right;	/* right (current) btree block */
-	xfs_inobt_key_t		*rkp=NULL;	/* key pointer for right block */
-	xfs_inobt_ptr_t		*rpp=NULL;	/* address pointer for right block */
-	xfs_inobt_rec_t		*rrp=NULL;	/* record pointer for right block */
-
-	/*
-	 * Set up variables for this block as "right".
-	 */
-	rbp = cur->bc_bufs[level];
-	right = XFS_BUF_TO_INOBT_BLOCK(rbp);
-#ifdef DEBUG
-	if ((error = xfs_btree_check_sblock(cur, right, level, rbp)))
-		return error;
-#endif
-	/*
-	 * If we've got no left sibling then we can't shift an entry left.
-	 */
-	if (be32_to_cpu(right->bb_leftsib) == NULLAGBLOCK) {
-		*stat = 0;
-		return 0;
-	}
-	/*
-	 * If the cursor entry is the one that would be moved, don't
-	 * do it... it's too complicated.
-	 */
-	if (cur->bc_ptrs[level] <= 1) {
-		*stat = 0;
-		return 0;
-	}
-	/*
-	 * Set up the left neighbor as "left".
-	 */
-	if ((error = xfs_btree_read_bufs(cur->bc_mp, cur->bc_tp,
-			cur->bc_private.a.agno, be32_to_cpu(right->bb_leftsib),
-			0, &lbp, XFS_INO_BTREE_REF)))
-		return error;
-	left = XFS_BUF_TO_INOBT_BLOCK(lbp);
-	if ((error = xfs_btree_check_sblock(cur, left, level, lbp)))
-		return error;
-	/*
-	 * If it's full, it can't take another entry.
-	 */
-	if (be16_to_cpu(left->bb_numrecs) == XFS_INOBT_BLOCK_MAXRECS(level, cur)) {
-		*stat = 0;
-		return 0;
-	}
-	nrec = be16_to_cpu(left->bb_numrecs) + 1;
-	/*
-	 * If non-leaf, copy a key and a ptr to the left block.
-	 */
-	if (level > 0) {
-		lkp = XFS_INOBT_KEY_ADDR(left, nrec, cur);
-		rkp = XFS_INOBT_KEY_ADDR(right, 1, cur);
-		*lkp = *rkp;
-		xfs_inobt_log_keys(cur, lbp, nrec, nrec);
-		lpp = XFS_INOBT_PTR_ADDR(left, nrec, cur);
-		rpp = XFS_INOBT_PTR_ADDR(right, 1, cur);
-#ifdef DEBUG
-		if ((error = xfs_btree_check_sptr(cur, be32_to_cpu(*rpp), level)))
-			return error;
-#endif
-		*lpp = *rpp;
-		xfs_inobt_log_ptrs(cur, lbp, nrec, nrec);
-	}
-	/*
-	 * If leaf, copy a record to the left block.
-	 */
-	else {
-		lrp = XFS_INOBT_REC_ADDR(left, nrec, cur);
-		rrp = XFS_INOBT_REC_ADDR(right, 1, cur);
-		*lrp = *rrp;
-		xfs_inobt_log_recs(cur, lbp, nrec, nrec);
-	}
-	/*
-	 * Bump and log left's numrecs, decrement and log right's numrecs.
-	 */
-	be16_add_cpu(&left->bb_numrecs, 1);
-	xfs_inobt_log_block(cur->bc_tp, lbp, XFS_BB_NUMRECS);
-#ifdef DEBUG
-	if (level > 0)
-		xfs_btree_check_key(cur->bc_btnum, lkp - 1, lkp);
-	else
-		xfs_btree_check_rec(cur->bc_btnum, lrp - 1, lrp);
-#endif
-	be16_add_cpu(&right->bb_numrecs, -1);
-	xfs_inobt_log_block(cur->bc_tp, rbp, XFS_BB_NUMRECS);
-	/*
-	 * Slide the contents of right down one entry.
-	 */
-	if (level > 0) {
-#ifdef DEBUG
-		for (i = 0; i < be16_to_cpu(right->bb_numrecs); i++) {
-			if ((error = xfs_btree_check_sptr(cur, be32_to_cpu(rpp[i + 1]),
-					level)))
-				return error;
-		}
-#endif
-		memmove(rkp, rkp + 1, be16_to_cpu(right->bb_numrecs) * sizeof(*rkp));
-		memmove(rpp, rpp + 1, be16_to_cpu(right->bb_numrecs) * sizeof(*rpp));
-		xfs_inobt_log_keys(cur, rbp, 1, be16_to_cpu(right->bb_numrecs));
-		xfs_inobt_log_ptrs(cur, rbp, 1, be16_to_cpu(right->bb_numrecs));
-	} else {
-		memmove(rrp, rrp + 1, be16_to_cpu(right->bb_numrecs) * sizeof(*rrp));
-		xfs_inobt_log_recs(cur, rbp, 1, be16_to_cpu(right->bb_numrecs));
-		key.ir_startino = rrp->ir_startino;
-		rkp = &key;
-	}
-	/*
-	 * Update the parent key values of right.
-	 */
-	if ((error = xfs_inobt_updkey(cur, rkp, level + 1)))
-		return error;
-	/*
-	 * Slide the cursor value left one.
-	 */
-	cur->bc_ptrs[level]--;
-	*stat = 1;
-	return 0;
+	return (__int64_t)be32_to_cpu(key->inobt.ir_startino) -
+			  cur->bc_rec.i.ir_startino;
 }
 
-/*
- * Allocate a new root block, fill it in.
- */
-STATIC int				/* error */
-xfs_inobt_newroot(
-	xfs_btree_cur_t		*cur,	/* btree cursor */
-	int			*stat)	/* success/failure */
+STATIC int
+xfs_inobt_kill_root(
+	struct xfs_btree_cur	*cur,
+	struct xfs_buf		*bp,
+	int			level,
+	union xfs_btree_ptr	*newroot)
 {
-	xfs_agi_t		*agi;	/* a.g. inode header */
-	xfs_alloc_arg_t		args;	/* allocation argument structure */
-	xfs_inobt_block_t	*block;	/* one half of the old root block */
-	xfs_buf_t		*bp;	/* buffer containing block */
-	int			error;	/* error return value */
-	xfs_inobt_key_t		*kp;	/* btree key pointer */
-	xfs_agblock_t		lbno;	/* left block number */
-	xfs_buf_t		*lbp;	/* left buffer pointer */
-	xfs_inobt_block_t	*left;	/* left btree block */
-	xfs_buf_t		*nbp;	/* new (root) buffer */
-	xfs_inobt_block_t	*new;	/* new (root) btree block */
-	int			nptr;	/* new value for key index, 1 or 2 */
-	xfs_inobt_ptr_t		*pp;	/* btree address pointer */
-	xfs_agblock_t		rbno;	/* right block number */
-	xfs_buf_t		*rbp;	/* right buffer pointer */
-	xfs_inobt_block_t	*right;	/* right btree block */
-	xfs_inobt_rec_t		*rp;	/* btree record pointer */
+	int			error;
 
-	ASSERT(cur->bc_nlevels < XFS_IN_MAXLEVELS(cur->bc_mp));
+	XFS_BTREE_TRACE_CURSOR(cur, XBT_ENTRY);
+	XFS_BTREE_STATS_INC(cur, killroot);
 
 	/*
-	 * Get a block & a buffer.
+	 * Update the root pointer, decreasing the level by 1 and then
+	 * free the old root.
 	 */
-	agi = XFS_BUF_TO_AGI(cur->bc_private.a.agbp);
-	args.tp = cur->bc_tp;
-	args.mp = cur->bc_mp;
-	args.fsbno = XFS_AGB_TO_FSB(args.mp, cur->bc_private.a.agno,
-		be32_to_cpu(agi->agi_root));
-	args.mod = args.minleft = args.alignment = args.total = args.wasdel =
-		args.isfl = args.userdata = args.minalignslop = 0;
-	args.minlen = args.maxlen = args.prod = 1;
-	args.type = XFS_ALLOCTYPE_NEAR_BNO;
-	if ((error = xfs_alloc_vextent(&args)))
+	xfs_inobt_set_root(cur, newroot, -1);
+	error = xfs_inobt_free_block(cur, bp);
+	if (error) {
+		XFS_BTREE_TRACE_CURSOR(cur, XBT_ERROR);
 		return error;
-	/*
-	 * None available, we fail.
-	 */
-	if (args.fsbno == NULLFSBLOCK) {
-		*stat = 0;
-		return 0;
-	}
-	ASSERT(args.len == 1);
-	nbp = xfs_btree_get_bufs(args.mp, args.tp, args.agno, args.agbno, 0);
-	new = XFS_BUF_TO_INOBT_BLOCK(nbp);
-	/*
-	 * Set the root data in the a.g. inode structure.
-	 */
-	agi->agi_root = cpu_to_be32(args.agbno);
-	be32_add_cpu(&agi->agi_level, 1);
-	xfs_ialloc_log_agi(args.tp, cur->bc_private.a.agbp,
-		XFS_AGI_ROOT | XFS_AGI_LEVEL);
-	/*
-	 * At the previous root level there are now two blocks: the old
-	 * root, and the new block generated when it was split.
-	 * We don't know which one the cursor is pointing at, so we
-	 * set up variables "left" and "right" for each case.
-	 */
-	bp = cur->bc_bufs[cur->bc_nlevels - 1];
-	block = XFS_BUF_TO_INOBT_BLOCK(bp);
-#ifdef DEBUG
-	if ((error = xfs_btree_check_sblock(cur, block, cur->bc_nlevels - 1, bp)))
-		return error;
-#endif
-	if (be32_to_cpu(block->bb_rightsib) != NULLAGBLOCK) {
-		/*
-		 * Our block is left, pick up the right block.
-		 */
-		lbp = bp;
-		lbno = XFS_DADDR_TO_AGBNO(args.mp, XFS_BUF_ADDR(lbp));
-		left = block;
-		rbno = be32_to_cpu(left->bb_rightsib);
-		if ((error = xfs_btree_read_bufs(args.mp, args.tp, args.agno,
-				rbno, 0, &rbp, XFS_INO_BTREE_REF)))
-			return error;
-		bp = rbp;
-		right = XFS_BUF_TO_INOBT_BLOCK(rbp);
-		if ((error = xfs_btree_check_sblock(cur, right,
-				cur->bc_nlevels - 1, rbp)))
-			return error;
-		nptr = 1;
-	} else {
-		/*
-		 * Our block is right, pick up the left block.
-		 */
-		rbp = bp;
-		rbno = XFS_DADDR_TO_AGBNO(args.mp, XFS_BUF_ADDR(rbp));
-		right = block;
-		lbno = be32_to_cpu(right->bb_leftsib);
-		if ((error = xfs_btree_read_bufs(args.mp, args.tp, args.agno,
-				lbno, 0, &lbp, XFS_INO_BTREE_REF)))
-			return error;
-		bp = lbp;
-		left = XFS_BUF_TO_INOBT_BLOCK(lbp);
-		if ((error = xfs_btree_check_sblock(cur, left,
-				cur->bc_nlevels - 1, lbp)))
-			return error;
-		nptr = 2;
-	}
-	/*
-	 * Fill in the new block's btree header and log it.
-	 */
-	new->bb_magic = cpu_to_be32(xfs_magics[cur->bc_btnum]);
-	new->bb_level = cpu_to_be16(cur->bc_nlevels);
-	new->bb_numrecs = cpu_to_be16(2);
-	new->bb_leftsib = cpu_to_be32(NULLAGBLOCK);
-	new->bb_rightsib = cpu_to_be32(NULLAGBLOCK);
-	xfs_inobt_log_block(args.tp, nbp, XFS_BB_ALL_BITS);
-	ASSERT(lbno != NULLAGBLOCK && rbno != NULLAGBLOCK);
-	/*
-	 * Fill in the key data in the new root.
-	 */
-	kp = XFS_INOBT_KEY_ADDR(new, 1, cur);
-	if (be16_to_cpu(left->bb_level) > 0) {
-		kp[0] = *XFS_INOBT_KEY_ADDR(left, 1, cur);
-		kp[1] = *XFS_INOBT_KEY_ADDR(right, 1, cur);
-	} else {
-		rp = XFS_INOBT_REC_ADDR(left, 1, cur);
-		kp[0].ir_startino = rp->ir_startino;
-		rp = XFS_INOBT_REC_ADDR(right, 1, cur);
-		kp[1].ir_startino = rp->ir_startino;
 	}
-	xfs_inobt_log_keys(cur, nbp, 1, 2);
-	/*
-	 * Fill in the pointer data in the new root.
-	 */
-	pp = XFS_INOBT_PTR_ADDR(new, 1, cur);
-	pp[0] = cpu_to_be32(lbno);
-	pp[1] = cpu_to_be32(rbno);
-	xfs_inobt_log_ptrs(cur, nbp, 1, 2);
-	/*
-	 * Fix up the cursor.
-	 */
-	xfs_btree_setbuf(cur, cur->bc_nlevels, nbp);
-	cur->bc_ptrs[cur->bc_nlevels] = nptr;
-	cur->bc_nlevels++;
-	*stat = 1;
-	return 0;
-}
 
-/*
- * Move 1 record right from cur/level if possible.
- * Update cur to reflect the new path.
- */
-STATIC int				/* error */
-xfs_inobt_rshift(
-	xfs_btree_cur_t		*cur,	/* btree cursor */
-	int			level,	/* level to shift record on */
-	int			*stat)	/* success/failure */
-{
-	int			error;	/* error return value */
-	int			i;	/* loop index */
-	xfs_inobt_key_t		key;	/* key value for leaf level upward */
-	xfs_buf_t		*lbp;	/* buffer for left (current) block */
-	xfs_inobt_block_t	*left;	/* left (current) btree block */
-	xfs_inobt_key_t		*lkp;	/* key pointer for left block */
-	xfs_inobt_ptr_t		*lpp;	/* address pointer for left block */
-	xfs_inobt_rec_t		*lrp;	/* record pointer for left block */
-	xfs_buf_t		*rbp;	/* buffer for right neighbor block */
-	xfs_inobt_block_t	*right;	/* right neighbor btree block */
-	xfs_inobt_key_t		*rkp;	/* key pointer for right block */
-	xfs_inobt_ptr_t		*rpp;	/* address pointer for right block */
-	xfs_inobt_rec_t		*rrp=NULL;	/* record pointer for right block */
-	xfs_btree_cur_t		*tcur;	/* temporary cursor */
+	XFS_BTREE_STATS_INC(cur, free);
 
-	/*
-	 * Set up variables for this block as "left".
-	 */
-	lbp = cur->bc_bufs[level];
-	left = XFS_BUF_TO_INOBT_BLOCK(lbp);
-#ifdef DEBUG
-	if ((error = xfs_btree_check_sblock(cur, left, level, lbp)))
-		return error;
-#endif
-	/*
-	 * If we've got no right sibling then we can't shift an entry right.
-	 */
-	if (be32_to_cpu(left->bb_rightsib) == NULLAGBLOCK) {
-		*stat = 0;
-		return 0;
-	}
-	/*
-	 * If the cursor entry is the one that would be moved, don't
-	 * do it... it's too complicated.
-	 */
-	if (cur->bc_ptrs[level] >= be16_to_cpu(left->bb_numrecs)) {
-		*stat = 0;
-		return 0;
-	}
-	/*
-	 * Set up the right neighbor as "right".
-	 */
-	if ((error = xfs_btree_read_bufs(cur->bc_mp, cur->bc_tp,
-			cur->bc_private.a.agno, be32_to_cpu(left->bb_rightsib),
-			0, &rbp, XFS_INO_BTREE_REF)))
-		return error;
-	right = XFS_BUF_TO_INOBT_BLOCK(rbp);
-	if ((error = xfs_btree_check_sblock(cur, right, level, rbp)))
-		return error;
-	/*
-	 * If it's full, it can't take another entry.
-	 */
-	if (be16_to_cpu(right->bb_numrecs) == XFS_INOBT_BLOCK_MAXRECS(level, cur)) {
-		*stat = 0;
-		return 0;
-	}
-	/*
-	 * Make a hole at the start of the right neighbor block, then
-	 * copy the last left block entry to the hole.
-	 */
-	if (level > 0) {
-		lkp = XFS_INOBT_KEY_ADDR(left, be16_to_cpu(left->bb_numrecs), cur);
-		lpp = XFS_INOBT_PTR_ADDR(left, be16_to_cpu(left->bb_numrecs), cur);
-		rkp = XFS_INOBT_KEY_ADDR(right, 1, cur);
-		rpp = XFS_INOBT_PTR_ADDR(right, 1, cur);
-#ifdef DEBUG
-		for (i = be16_to_cpu(right->bb_numrecs) - 1; i >= 0; i--) {
-			if ((error = xfs_btree_check_sptr(cur, be32_to_cpu(rpp[i]), level)))
-				return error;
-		}
-#endif
-		memmove(rkp + 1, rkp, be16_to_cpu(right->bb_numrecs) * sizeof(*rkp));
-		memmove(rpp + 1, rpp, be16_to_cpu(right->bb_numrecs) * sizeof(*rpp));
-#ifdef DEBUG
-		if ((error = xfs_btree_check_sptr(cur, be32_to_cpu(*lpp), level)))
-			return error;
-#endif
-		*rkp = *lkp;
-		*rpp = *lpp;
-		xfs_inobt_log_keys(cur, rbp, 1, be16_to_cpu(right->bb_numrecs) + 1);
-		xfs_inobt_log_ptrs(cur, rbp, 1, be16_to_cpu(right->bb_numrecs) + 1);
-	} else {
-		lrp = XFS_INOBT_REC_ADDR(left, be16_to_cpu(left->bb_numrecs), cur);
-		rrp = XFS_INOBT_REC_ADDR(right, 1, cur);
-		memmove(rrp + 1, rrp, be16_to_cpu(right->bb_numrecs) * sizeof(*rrp));
-		*rrp = *lrp;
-		xfs_inobt_log_recs(cur, rbp, 1, be16_to_cpu(right->bb_numrecs) + 1);
-		key.ir_startino = rrp->ir_startino;
-		rkp = &key;
-	}
-	/*
-	 * Decrement and log left's numrecs, bump and log right's numrecs.
-	 */
-	be16_add_cpu(&left->bb_numrecs, -1);
-	xfs_inobt_log_block(cur->bc_tp, lbp, XFS_BB_NUMRECS);
-	be16_add_cpu(&right->bb_numrecs, 1);
-#ifdef DEBUG
-	if (level > 0)
-		xfs_btree_check_key(cur->bc_btnum, rkp, rkp + 1);
-	else
-		xfs_btree_check_rec(cur->bc_btnum, rrp, rrp + 1);
-#endif
-	xfs_inobt_log_block(cur->bc_tp, rbp, XFS_BB_NUMRECS);
-	/*
-	 * Using a temporary cursor, update the parent key values of the
-	 * block on the right.
-	 */
-	if ((error = xfs_btree_dup_cursor(cur, &tcur)))
-		return error;
-	xfs_btree_lastrec(tcur, level);
-	if ((error = xfs_inobt_increment(tcur, level, &i)) ||
-	    (error = xfs_inobt_updkey(tcur, rkp, level + 1))) {
-		xfs_btree_del_cursor(tcur, XFS_BTREE_ERROR);
-		return error;
-	}
-	xfs_btree_del_cursor(tcur, XFS_BTREE_NOERROR);
-	*stat = 1;
+	cur->bc_bufs[level] = NULL;
+	cur->bc_nlevels--;
+
+	XFS_BTREE_TRACE_CURSOR(cur, XBT_EXIT);
 	return 0;
 }
 
-/*
- * Split cur/level block in half.
- * Return new block number and its first record (to be inserted into parent).
- */
-STATIC int				/* error */
-xfs_inobt_split(
-	xfs_btree_cur_t		*cur,	/* btree cursor */
-	int			level,	/* level to split */
-	xfs_agblock_t		*bnop,	/* output: block number allocated */
-	xfs_inobt_key_t		*keyp,	/* output: first key of new block */
-	xfs_btree_cur_t		**curp,	/* output: new cursor */
-	int			*stat)	/* success/failure */
-{
-	xfs_alloc_arg_t		args;	/* allocation argument structure */
-	int			error;	/* error return value */
-	int			i;	/* loop index/record number */
-	xfs_agblock_t		lbno;	/* left (current) block number */
-	xfs_buf_t		*lbp;	/* buffer for left block */
-	xfs_inobt_block_t	*left;	/* left (current) btree block */
-	xfs_inobt_key_t		*lkp;	/* left btree key pointer */
-	xfs_inobt_ptr_t		*lpp;	/* left btree address pointer */
-	xfs_inobt_rec_t		*lrp;	/* left btree record pointer */
-	xfs_buf_t		*rbp;	/* buffer for right block */
-	xfs_inobt_block_t	*right;	/* right (new) btree block */
-	xfs_inobt_key_t		*rkp;	/* right btree key pointer */
-	xfs_inobt_ptr_t		*rpp;	/* right btree address pointer */
-	xfs_inobt_rec_t		*rrp;	/* right btree record pointer */
-
-	/*
-	 * Set up left block (current one).
-	 */
-	lbp = cur->bc_bufs[level];
-	args.tp = cur->bc_tp;
-	args.mp = cur->bc_mp;
-	lbno = XFS_DADDR_TO_AGBNO(args.mp, XFS_BUF_ADDR(lbp));
-	/*
-	 * Allocate the new block.
-	 * If we can't do it, we're toast.  Give up.
-	 */
-	args.fsbno = XFS_AGB_TO_FSB(args.mp, cur->bc_private.a.agno, lbno);
-	args.mod = args.minleft = args.alignment = args.total = args.wasdel =
-		args.isfl = args.userdata = args.minalignslop = 0;
-	args.minlen = args.maxlen = args.prod = 1;
-	args.type = XFS_ALLOCTYPE_NEAR_BNO;
-	if ((error = xfs_alloc_vextent(&args)))
-		return error;
-	if (args.fsbno == NULLFSBLOCK) {
-		*stat = 0;
-		return 0;
-	}
-	ASSERT(args.len == 1);
-	rbp = xfs_btree_get_bufs(args.mp, args.tp, args.agno, args.agbno, 0);
-	/*
-	 * Set up the new block as "right".
-	 */
-	right = XFS_BUF_TO_INOBT_BLOCK(rbp);
-	/*
-	 * "Left" is the current (according to the cursor) block.
-	 */
-	left = XFS_BUF_TO_INOBT_BLOCK(lbp);
 #ifdef DEBUG
-	if ((error = xfs_btree_check_sblock(cur, left, level, lbp)))
-		return error;
-#endif
-	/*
-	 * Fill in the btree header for the new block.
-	 */
-	right->bb_magic = cpu_to_be32(xfs_magics[cur->bc_btnum]);
-	right->bb_level = left->bb_level;
-	right->bb_numrecs = cpu_to_be16(be16_to_cpu(left->bb_numrecs) / 2);
-	/*
-	 * Make sure that if there's an odd number of entries now, that
-	 * each new block will have the same number of entries.
-	 */
-	if ((be16_to_cpu(left->bb_numrecs) & 1) &&
-	    cur->bc_ptrs[level] <= be16_to_cpu(right->bb_numrecs) + 1)
-		be16_add_cpu(&right->bb_numrecs, 1);
-	i = be16_to_cpu(left->bb_numrecs) - be16_to_cpu(right->bb_numrecs) + 1;
-	/*
-	 * For non-leaf blocks, copy keys and addresses over to the new block.
-	 */
-	if (level > 0) {
-		lkp = XFS_INOBT_KEY_ADDR(left, i, cur);
-		lpp = XFS_INOBT_PTR_ADDR(left, i, cur);
-		rkp = XFS_INOBT_KEY_ADDR(right, 1, cur);
-		rpp = XFS_INOBT_PTR_ADDR(right, 1, cur);
-#ifdef DEBUG
-		for (i = 0; i < be16_to_cpu(right->bb_numrecs); i++) {
-			if ((error = xfs_btree_check_sptr(cur, be32_to_cpu(lpp[i]), level)))
-				return error;
-		}
-#endif
-		memcpy(rkp, lkp, be16_to_cpu(right->bb_numrecs) * sizeof(*rkp));
-		memcpy(rpp, lpp, be16_to_cpu(right->bb_numrecs) * sizeof(*rpp));
-		xfs_inobt_log_keys(cur, rbp, 1, be16_to_cpu(right->bb_numrecs));
-		xfs_inobt_log_ptrs(cur, rbp, 1, be16_to_cpu(right->bb_numrecs));
-		*keyp = *rkp;
-	}
-	/*
-	 * For leaf blocks, copy records over to the new block.
-	 */
-	else {
-		lrp = XFS_INOBT_REC_ADDR(left, i, cur);
-		rrp = XFS_INOBT_REC_ADDR(right, 1, cur);
-		memcpy(rrp, lrp, be16_to_cpu(right->bb_numrecs) * sizeof(*rrp));
-		xfs_inobt_log_recs(cur, rbp, 1, be16_to_cpu(right->bb_numrecs));
-		keyp->ir_startino = rrp->ir_startino;
-	}
-	/*
-	 * Find the left block number by looking in the buffer.
-	 * Adjust numrecs, sibling pointers.
-	 */
-	be16_add_cpu(&left->bb_numrecs, -(be16_to_cpu(right->bb_numrecs)));
-	right->bb_rightsib = left->bb_rightsib;
-	left->bb_rightsib = cpu_to_be32(args.agbno);
-	right->bb_leftsib = cpu_to_be32(lbno);
-	xfs_inobt_log_block(args.tp, rbp, XFS_BB_ALL_BITS);
-	xfs_inobt_log_block(args.tp, lbp, XFS_BB_NUMRECS | XFS_BB_RIGHTSIB);
-	/*
-	 * If there's a block to the new block's right, make that block
-	 * point back to right instead of to left.
-	 */
-	if (be32_to_cpu(right->bb_rightsib) != NULLAGBLOCK) {
-		xfs_inobt_block_t	*rrblock;	/* rr btree block */
-		xfs_buf_t		*rrbp;		/* buffer for rrblock */
-
-		if ((error = xfs_btree_read_bufs(args.mp, args.tp, args.agno,
-				be32_to_cpu(right->bb_rightsib), 0, &rrbp,
-				XFS_INO_BTREE_REF)))
-			return error;
-		rrblock = XFS_BUF_TO_INOBT_BLOCK(rrbp);
-		if ((error = xfs_btree_check_sblock(cur, rrblock, level, rrbp)))
-			return error;
-		rrblock->bb_leftsib = cpu_to_be32(args.agbno);
-		xfs_inobt_log_block(args.tp, rrbp, XFS_BB_LEFTSIB);
-	}
-	/*
-	 * If the cursor is really in the right block, move it there.
-	 * If it's just pointing past the last entry in left, then we'll
-	 * insert there, so don't change anything in that case.
-	 */
-	if (cur->bc_ptrs[level] > be16_to_cpu(left->bb_numrecs) + 1) {
-		xfs_btree_setbuf(cur, level, rbp);
-		cur->bc_ptrs[level] -= be16_to_cpu(left->bb_numrecs);
-	}
-	/*
-	 * If there are more levels, we'll need another cursor which refers
-	 * the right block, no matter where this cursor was.
-	 */
-	if (level + 1 < cur->bc_nlevels) {
-		if ((error = xfs_btree_dup_cursor(cur, curp)))
-			return error;
-		(*curp)->bc_ptrs[level + 1]++;
-	}
-	*bnop = args.agbno;
-	*stat = 1;
-	return 0;
+STATIC int
+xfs_inobt_keys_inorder(
+	struct xfs_btree_cur	*cur,
+	union xfs_btree_key	*k1,
+	union xfs_btree_key	*k2)
+{
+	return be32_to_cpu(k1->inobt.ir_startino) <
+		be32_to_cpu(k2->inobt.ir_startino);
 }
 
-/*
- * Update keys at all levels from here to the root along the cursor's path.
- */
-STATIC int				/* error */
-xfs_inobt_updkey(
-	xfs_btree_cur_t		*cur,	/* btree cursor */
-	xfs_inobt_key_t		*keyp,	/* new key value to update to */
-	int			level)	/* starting level for update */
+STATIC int
+xfs_inobt_recs_inorder(
+	struct xfs_btree_cur	*cur,
+	union xfs_btree_rec	*r1,
+	union xfs_btree_rec	*r2)
 {
-	int			ptr;	/* index of key in block */
-
-	/*
-	 * Go up the tree from this level toward the root.
-	 * At each level, update the key value to the value input.
-	 * Stop when we reach a level where the cursor isn't pointing
-	 * at the first entry in the block.
-	 */
-	for (ptr = 1; ptr == 1 && level < cur->bc_nlevels; level++) {
-		xfs_buf_t		*bp;	/* buffer for block */
-		xfs_inobt_block_t	*block;	/* btree block */
-#ifdef DEBUG
-		int			error;	/* error return value */
-#endif
-		xfs_inobt_key_t		*kp;	/* ptr to btree block keys */
-
-		bp = cur->bc_bufs[level];
-		block = XFS_BUF_TO_INOBT_BLOCK(bp);
-#ifdef DEBUG
-		if ((error = xfs_btree_check_sblock(cur, block, level, bp)))
-			return error;
-#endif
-		ptr = cur->bc_ptrs[level];
-		kp = XFS_INOBT_KEY_ADDR(block, ptr, cur);
-		*kp = *keyp;
-		xfs_inobt_log_keys(cur, bp, ptr, ptr);
-	}
-	return 0;
+	return be32_to_cpu(r1->inobt.ir_startino) + XFS_INODES_PER_CHUNK <=
+		be32_to_cpu(r2->inobt.ir_startino);
 }
+#endif	/* DEBUG */
 
-/*
- * Externally visible routines.
- */
+#ifdef XFS_BTREE_TRACE
+ktrace_t	*xfs_inobt_trace_buf;
 
-/*
- * Decrement cursor by one record at the level.
- * For nonzero levels the leaf-ward information is untouched.
- */
-int					/* error */
-xfs_inobt_decrement(
-	xfs_btree_cur_t		*cur,	/* btree cursor */
-	int			level,	/* level in btree, 0 is leaf */
-	int			*stat)	/* success/failure */
+STATIC void
+xfs_inobt_trace_enter(
+	struct xfs_btree_cur	*cur,
+	const char		*func,
+	char			*s,
+	int			type,
+	int			line,
+	__psunsigned_t		a0,
+	__psunsigned_t		a1,
+	__psunsigned_t		a2,
+	__psunsigned_t		a3,
+	__psunsigned_t		a4,
+	__psunsigned_t		a5,
+	__psunsigned_t		a6,
+	__psunsigned_t		a7,
+	__psunsigned_t		a8,
+	__psunsigned_t		a9,
+	__psunsigned_t		a10)
 {
-	xfs_inobt_block_t	*block;	/* btree block */
-	int			error;
-	int			lev;	/* btree level */
-
-	ASSERT(level < cur->bc_nlevels);
-	/*
-	 * Read-ahead to the left at this level.
-	 */
-	xfs_btree_readahead(cur, level, XFS_BTCUR_LEFTRA);
-	/*
-	 * Decrement the ptr at this level.  If we're still in the block
-	 * then we're done.
-	 */
-	if (--cur->bc_ptrs[level] > 0) {
-		*stat = 1;
-		return 0;
-	}
-	/*
-	 * Get a pointer to the btree block.
-	 */
-	block = XFS_BUF_TO_INOBT_BLOCK(cur->bc_bufs[level]);
-#ifdef DEBUG
-	if ((error = xfs_btree_check_sblock(cur, block, level,
-			cur->bc_bufs[level])))
-		return error;
-#endif
-	/*
-	 * If we just went off the left edge of the tree, return failure.
-	 */
-	if (be32_to_cpu(block->bb_leftsib) == NULLAGBLOCK) {
-		*stat = 0;
-		return 0;
-	}
-	/*
-	 * March up the tree decrementing pointers.
-	 * Stop when we don't go off the left edge of a block.
-	 */
-	for (lev = level + 1; lev < cur->bc_nlevels; lev++) {
-		if (--cur->bc_ptrs[lev] > 0)
-			break;
-		/*
-		 * Read-ahead the left block, we're going to read it
-		 * in the next loop.
-		 */
-		xfs_btree_readahead(cur, lev, XFS_BTCUR_LEFTRA);
-	}
-	/*
-	 * If we went off the root then we are seriously confused.
-	 */
-	ASSERT(lev < cur->bc_nlevels);
-	/*
-	 * Now walk back down the tree, fixing up the cursor's buffer
-	 * pointers and key numbers.
-	 */
-	for (block = XFS_BUF_TO_INOBT_BLOCK(cur->bc_bufs[lev]); lev > level; ) {
-		xfs_agblock_t	agbno;	/* block number of btree block */
-		xfs_buf_t	*bp;	/* buffer containing btree block */
-
-		agbno = be32_to_cpu(*XFS_INOBT_PTR_ADDR(block, cur->bc_ptrs[lev], cur));
-		if ((error = xfs_btree_read_bufs(cur->bc_mp, cur->bc_tp,
-				cur->bc_private.a.agno, agbno, 0, &bp,
-				XFS_INO_BTREE_REF)))
-			return error;
-		lev--;
-		xfs_btree_setbuf(cur, lev, bp);
-		block = XFS_BUF_TO_INOBT_BLOCK(bp);
-		if ((error = xfs_btree_check_sblock(cur, block, lev, bp)))
-			return error;
-		cur->bc_ptrs[lev] = be16_to_cpu(block->bb_numrecs);
-	}
-	*stat = 1;
-	return 0;
+	ktrace_enter(xfs_inobt_trace_buf, (void *)(__psint_t)type,
+		(void *)func, (void *)s, NULL, (void *)cur,
+		(void *)a0, (void *)a1, (void *)a2, (void *)a3,
+		(void *)a4, (void *)a5, (void *)a6, (void *)a7,
+		(void *)a8, (void *)a9, (void *)a10);
 }
 
-/*
- * Delete the record pointed to by cur.
- * The cursor refers to the place where the record was (could be inserted)
- * when the operation returns.
- */
-int					/* error */
-xfs_inobt_delete(
-	xfs_btree_cur_t	*cur,		/* btree cursor */
-	int		*stat)		/* success/failure */
+STATIC void
+xfs_inobt_trace_cursor(
+	struct xfs_btree_cur	*cur,
+	__uint32_t		*s0,
+	__uint64_t		*l0,
+	__uint64_t		*l1)
 {
-	int		error;
-	int		i;		/* result code */
-	int		level;		/* btree level */
-
-	/*
-	 * Go up the tree, starting at leaf level.
-	 * If 2 is returned then a join was done; go to the next level.
-	 * Otherwise we are done.
-	 */
-	for (level = 0, i = 2; i == 2; level++) {
-		if ((error = xfs_inobt_delrec(cur, level, &i)))
-			return error;
-	}
-	if (i == 0) {
-		for (level = 1; level < cur->bc_nlevels; level++) {
-			if (cur->bc_ptrs[level] == 0) {
-				if ((error = xfs_inobt_decrement(cur, level, &i)))
-					return error;
-				break;
-			}
-		}
-	}
-	*stat = i;
-	return 0;
+	*s0 = cur->bc_private.a.agno;
+	*l0 = cur->bc_rec.i.ir_startino;
+	*l1 = cur->bc_rec.i.ir_free;
 }
 
-
-/*
- * Get the data from the pointed-to record.
- */
-int					/* error */
-xfs_inobt_get_rec(
-	xfs_btree_cur_t		*cur,	/* btree cursor */
-	xfs_agino_t		*ino,	/* output: starting inode of chunk */
-	__int32_t		*fcnt,	/* output: number of free inodes */
-	xfs_inofree_t		*free,	/* output: free inode mask */
-	int			*stat)	/* output: success/failure */
+STATIC void
+xfs_inobt_trace_key(
+	struct xfs_btree_cur	*cur,
+	union xfs_btree_key	*key,
+	__uint64_t		*l0,
+	__uint64_t		*l1)
 {
-	xfs_inobt_block_t	*block;	/* btree block */
-	xfs_buf_t		*bp;	/* buffer containing btree block */
-#ifdef DEBUG
-	int			error;	/* error return value */
-#endif
-	int			ptr;	/* record number */
-	xfs_inobt_rec_t		*rec;	/* record data */
-
-	bp = cur->bc_bufs[0];
-	ptr = cur->bc_ptrs[0];
-	block = XFS_BUF_TO_INOBT_BLOCK(bp);
-#ifdef DEBUG
-	if ((error = xfs_btree_check_sblock(cur, block, 0, bp)))
-		return error;
-#endif
-	/*
-	 * Off the right end or left end, return failure.
-	 */
-	if (ptr > be16_to_cpu(block->bb_numrecs) || ptr <= 0) {
-		*stat = 0;
-		return 0;
-	}
-	/*
-	 * Point to the record and extract its data.
-	 */
-	rec = XFS_INOBT_REC_ADDR(block, ptr, cur);
-	*ino = be32_to_cpu(rec->ir_startino);
-	*fcnt = be32_to_cpu(rec->ir_freecount);
-	*free = be64_to_cpu(rec->ir_free);
-	*stat = 1;
-	return 0;
+	*l0 = be32_to_cpu(key->inobt.ir_startino);
+	*l1 = 0;
 }
 
-/*
- * Increment cursor by one record at the level.
- * For nonzero levels the leaf-ward information is untouched.
- */
-int					/* error */
-xfs_inobt_increment(
-	xfs_btree_cur_t		*cur,	/* btree cursor */
-	int			level,	/* level in btree, 0 is leaf */
-	int			*stat)	/* success/failure */
+STATIC void
+xfs_inobt_trace_record(
+	struct xfs_btree_cur	*cur,
+	union xfs_btree_rec	*rec,
+	__uint64_t		*l0,
+	__uint64_t		*l1,
+	__uint64_t		*l2)
 {
-	xfs_inobt_block_t	*block;	/* btree block */
-	xfs_buf_t		*bp;	/* buffer containing btree block */
-	int			error;	/* error return value */
-	int			lev;	/* btree level */
+	*l0 = be32_to_cpu(rec->inobt.ir_startino);
+	*l1 = be32_to_cpu(rec->inobt.ir_freecount);
+	*l2 = be64_to_cpu(rec->inobt.ir_free);
+}
+#endif /* XFS_BTREE_TRACE */
+
+static const struct xfs_btree_ops xfs_inobt_ops = {
+	.rec_len		= sizeof(xfs_inobt_rec_t),
+	.key_len		= sizeof(xfs_inobt_key_t),
+
+	.dup_cursor		= xfs_inobt_dup_cursor,
+	.set_root		= xfs_inobt_set_root,
+	.kill_root		= xfs_inobt_kill_root,
+	.alloc_block		= xfs_inobt_alloc_block,
+	.free_block		= xfs_inobt_free_block,
+	.get_minrecs		= xfs_inobt_get_minrecs,
+	.get_maxrecs		= xfs_inobt_get_maxrecs,
+	.init_key_from_rec	= xfs_inobt_init_key_from_rec,
+	.init_rec_from_key	= xfs_inobt_init_rec_from_key,
+	.init_rec_from_cur	= xfs_inobt_init_rec_from_cur,
+	.init_ptr_from_cur	= xfs_inobt_init_ptr_from_cur,
+	.key_diff		= xfs_inobt_key_diff,
 
-	ASSERT(level < cur->bc_nlevels);
-	/*
-	 * Read-ahead to the right at this level.
-	 */
-	xfs_btree_readahead(cur, level, XFS_BTCUR_RIGHTRA);
-	/*
-	 * Get a pointer to the btree block.
-	 */
-	bp = cur->bc_bufs[level];
-	block = XFS_BUF_TO_INOBT_BLOCK(bp);
-#ifdef DEBUG
-	if ((error = xfs_btree_check_sblock(cur, block, level, bp)))
-		return error;
-#endif
-	/*
-	 * Increment the ptr at this level.  If we're still in the block
-	 * then we're done.
-	 */
-	if (++cur->bc_ptrs[level] <= be16_to_cpu(block->bb_numrecs)) {
-		*stat = 1;
-		return 0;
-	}
-	/*
-	 * If we just went off the right edge of the tree, return failure.
-	 */
-	if (be32_to_cpu(block->bb_rightsib) == NULLAGBLOCK) {
-		*stat = 0;
-		return 0;
-	}
-	/*
-	 * March up the tree incrementing pointers.
-	 * Stop when we don't go off the right edge of a block.
-	 */
-	for (lev = level + 1; lev < cur->bc_nlevels; lev++) {
-		bp = cur->bc_bufs[lev];
-		block = XFS_BUF_TO_INOBT_BLOCK(bp);
 #ifdef DEBUG
-		if ((error = xfs_btree_check_sblock(cur, block, lev, bp)))
-			return error;
+	.keys_inorder		= xfs_inobt_keys_inorder,
+	.recs_inorder		= xfs_inobt_recs_inorder,
 #endif
-		if (++cur->bc_ptrs[lev] <= be16_to_cpu(block->bb_numrecs))
-			break;
-		/*
-		 * Read-ahead the right block, we're going to read it
-		 * in the next loop.
-		 */
-		xfs_btree_readahead(cur, lev, XFS_BTCUR_RIGHTRA);
-	}
-	/*
-	 * If we went off the root then we are seriously confused.
-	 */
-	ASSERT(lev < cur->bc_nlevels);
-	/*
-	 * Now walk back down the tree, fixing up the cursor's buffer
-	 * pointers and key numbers.
-	 */
-	for (bp = cur->bc_bufs[lev], block = XFS_BUF_TO_INOBT_BLOCK(bp);
-	     lev > level; ) {
-		xfs_agblock_t	agbno;	/* block number of btree block */
 
-		agbno = be32_to_cpu(*XFS_INOBT_PTR_ADDR(block, cur->bc_ptrs[lev], cur));
-		if ((error = xfs_btree_read_bufs(cur->bc_mp, cur->bc_tp,
-				cur->bc_private.a.agno, agbno, 0, &bp,
-				XFS_INO_BTREE_REF)))
-			return error;
-		lev--;
-		xfs_btree_setbuf(cur, lev, bp);
-		block = XFS_BUF_TO_INOBT_BLOCK(bp);
-		if ((error = xfs_btree_check_sblock(cur, block, lev, bp)))
-			return error;
-		cur->bc_ptrs[lev] = 1;
-	}
-	*stat = 1;
-	return 0;
-}
+#ifdef XFS_BTREE_TRACE
+	.trace_enter		= xfs_inobt_trace_enter,
+	.trace_cursor		= xfs_inobt_trace_cursor,
+	.trace_key		= xfs_inobt_trace_key,
+	.trace_record		= xfs_inobt_trace_record,
+#endif
+};
 
 /*
- * Insert the current record at the point referenced by cur.
- * The cursor may be inconsistent on return if splits have been done.
+ * Allocate a new inode btree cursor.
  */
-int					/* error */
-xfs_inobt_insert(
-	xfs_btree_cur_t	*cur,		/* btree cursor */
-	int		*stat)		/* success/failure */
+struct xfs_btree_cur *				/* new inode btree cursor */
+xfs_inobt_init_cursor(
+	struct xfs_mount	*mp,		/* file system mount point */
+	struct xfs_trans	*tp,		/* transaction pointer */
+	struct xfs_buf		*agbp,		/* buffer for agi structure */
+	xfs_agnumber_t		agno)		/* allocation group number */
 {
-	int		error;		/* error return value */
-	int		i;		/* result value, 0 for failure */
-	int		level;		/* current level number in btree */
-	xfs_agblock_t	nbno;		/* new block number (split result) */
-	xfs_btree_cur_t	*ncur;		/* new cursor (split result) */
-	xfs_inobt_rec_t	nrec;		/* record being inserted this level */
-	xfs_btree_cur_t	*pcur;		/* previous level's cursor */
+	struct xfs_agi		*agi = XFS_BUF_TO_AGI(agbp);
+	struct xfs_btree_cur	*cur;
 
-	level = 0;
-	nbno = NULLAGBLOCK;
-	nrec.ir_startino = cpu_to_be32(cur->bc_rec.i.ir_startino);
-	nrec.ir_freecount = cpu_to_be32(cur->bc_rec.i.ir_freecount);
-	nrec.ir_free = cpu_to_be64(cur->bc_rec.i.ir_free);
-	ncur = NULL;
-	pcur = cur;
-	/*
-	 * Loop going up the tree, starting at the leaf level.
-	 * Stop when we don't get a split block, that must mean that
-	 * the insert is finished with this level.
-	 */
-	do {
-		/*
-		 * Insert nrec/nbno into this level of the tree.
-		 * Note if we fail, nbno will be null.
-		 */
-		if ((error = xfs_inobt_insrec(pcur, level++, &nbno, &nrec, &ncur,
-				&i))) {
-			if (pcur != cur)
-				xfs_btree_del_cursor(pcur, XFS_BTREE_ERROR);
-			return error;
-		}
-		/*
-		 * See if the cursor we just used is trash.
-		 * Can't trash the caller's cursor, but otherwise we should
-		 * if ncur is a new cursor or we're about to be done.
-		 */
-		if (pcur != cur && (ncur || nbno == NULLAGBLOCK)) {
-			cur->bc_nlevels = pcur->bc_nlevels;
-			xfs_btree_del_cursor(pcur, XFS_BTREE_NOERROR);
-		}
-		/*
-		 * If we got a new cursor, switch to it.
-		 */
-		if (ncur) {
-			pcur = ncur;
-			ncur = NULL;
-		}
-	} while (nbno != NULLAGBLOCK);
-	*stat = i;
-	return 0;
-}
+	cur = kmem_zone_zalloc(xfs_btree_cur_zone, KM_SLEEP);
 
-/*
- * Lookup the record equal to ino in the btree given by cur.
- */
-int					/* error */
-xfs_inobt_lookup_eq(
-	xfs_btree_cur_t	*cur,		/* btree cursor */
-	xfs_agino_t	ino,		/* starting inode of chunk */
-	__int32_t	fcnt,		/* free inode count */
-	xfs_inofree_t	free,		/* free inode mask */
-	int		*stat)		/* success/failure */
-{
-	cur->bc_rec.i.ir_startino = ino;
-	cur->bc_rec.i.ir_freecount = fcnt;
-	cur->bc_rec.i.ir_free = free;
-	return xfs_inobt_lookup(cur, XFS_LOOKUP_EQ, stat);
-}
+	cur->bc_tp = tp;
+	cur->bc_mp = mp;
+	cur->bc_nlevels = be32_to_cpu(agi->agi_level);
+	cur->bc_btnum = XFS_BTNUM_INO;
+	cur->bc_blocklog = mp->m_sb.sb_blocklog;
 
-/*
- * Lookup the first record greater than or equal to ino
- * in the btree given by cur.
- */
-int					/* error */
-xfs_inobt_lookup_ge(
-	xfs_btree_cur_t	*cur,		/* btree cursor */
-	xfs_agino_t	ino,		/* starting inode of chunk */
-	__int32_t	fcnt,		/* free inode count */
-	xfs_inofree_t	free,		/* free inode mask */
-	int		*stat)		/* success/failure */
-{
-	cur->bc_rec.i.ir_startino = ino;
-	cur->bc_rec.i.ir_freecount = fcnt;
-	cur->bc_rec.i.ir_free = free;
-	return xfs_inobt_lookup(cur, XFS_LOOKUP_GE, stat);
-}
+	cur->bc_ops = &xfs_inobt_ops;
 
-/*
- * Lookup the first record less than or equal to ino
- * in the btree given by cur.
- */
-int					/* error */
-xfs_inobt_lookup_le(
-	xfs_btree_cur_t	*cur,		/* btree cursor */
-	xfs_agino_t	ino,		/* starting inode of chunk */
-	__int32_t	fcnt,		/* free inode count */
-	xfs_inofree_t	free,		/* free inode mask */
-	int		*stat)		/* success/failure */
-{
-	cur->bc_rec.i.ir_startino = ino;
-	cur->bc_rec.i.ir_freecount = fcnt;
-	cur->bc_rec.i.ir_free = free;
-	return xfs_inobt_lookup(cur, XFS_LOOKUP_LE, stat);
+	cur->bc_private.a.agbp = agbp;
+	cur->bc_private.a.agno = agno;
+
+	return cur;
 }
 
 /*
- * Update the record referred to by cur, to the value given
- * by [ino, fcnt, free].
- * This either works (return 0) or gets an EFSCORRUPTED error.
+ * Calculate number of records in an inobt btree block.
  */
-int					/* error */
-xfs_inobt_update(
-	xfs_btree_cur_t		*cur,	/* btree cursor */
-	xfs_agino_t		ino,	/* starting inode of chunk */
-	__int32_t		fcnt,	/* free inode count */
-	xfs_inofree_t		free)	/* free inode mask */
+int
+xfs_inobt_maxrecs(
+	struct xfs_mount	*mp,
+	int			blocklen,
+	int			leaf)
 {
-	xfs_inobt_block_t	*block;	/* btree block to update */
-	xfs_buf_t		*bp;	/* buffer containing btree block */
-	int			error;	/* error return value */
-	int			ptr;	/* current record number (updating) */
-	xfs_inobt_rec_t		*rp;	/* pointer to updated record */
+	blocklen -= XFS_INOBT_BLOCK_LEN(mp);
 
-	/*
-	 * Pick up the current block.
-	 */
-	bp = cur->bc_bufs[0];
-	block = XFS_BUF_TO_INOBT_BLOCK(bp);
-#ifdef DEBUG
-	if ((error = xfs_btree_check_sblock(cur, block, 0, bp)))
-		return error;
-#endif
-	/*
-	 * Get the address of the rec to be updated.
-	 */
-	ptr = cur->bc_ptrs[0];
-	rp = XFS_INOBT_REC_ADDR(block, ptr, cur);
-	/*
-	 * Fill in the new contents and log them.
-	 */
-	rp->ir_startino = cpu_to_be32(ino);
-	rp->ir_freecount = cpu_to_be32(fcnt);
-	rp->ir_free = cpu_to_be64(free);
-	xfs_inobt_log_recs(cur, bp, ptr, ptr);
-	/*
-	 * Updating first record in leaf. Pass new key value up to our parent.
-	 */
-	if (ptr == 1) {
-		xfs_inobt_key_t	key;	/* key containing [ino] */
-
-		key.ir_startino = cpu_to_be32(ino);
-		if ((error = xfs_inobt_updkey(cur, &key, 1)))
-			return error;
-	}
-	return 0;
+	if (leaf)
+		return blocklen / sizeof(xfs_inobt_rec_t);
+	return blocklen / (sizeof(xfs_inobt_key_t) + sizeof(xfs_inobt_ptr_t));
 }
diff --git a/fs/xfs/xfs_ialloc_btree.h b/fs/xfs/xfs_ialloc_btree.h
index 8efc4a5b8b92..37e5dd01a577 100644
--- a/fs/xfs/xfs_ialloc_btree.h
+++ b/fs/xfs/xfs_ialloc_btree.h
@@ -24,7 +24,6 @@
 
 struct xfs_buf;
 struct xfs_btree_cur;
-struct xfs_btree_sblock;
 struct xfs_mount;
 
 /*
@@ -70,11 +69,6 @@ typedef struct xfs_inobt_key {
 /* btree pointer type */
 typedef __be32 xfs_inobt_ptr_t;
 
-/* btree block header type */
-typedef	struct xfs_btree_sblock xfs_inobt_block_t;
-
-#define	XFS_BUF_TO_INOBT_BLOCK(bp)	((xfs_inobt_block_t *)XFS_BUF_PTR(bp))
-
 /*
  * Bit manipulations for ir_free.
  */
@@ -85,14 +79,6 @@ typedef	struct xfs_btree_sblock xfs_inobt_block_t;
 #define	XFS_INOBT_CLR_FREE(rp,i)	((rp)->ir_free &= ~XFS_INOBT_MASK(i))
 
 /*
- * Real block structures have a size equal to the disk block size.
- */
-#define	XFS_INOBT_BLOCK_MAXRECS(lev,cur) ((cur)->bc_mp->m_inobt_mxr[lev != 0])
-#define	XFS_INOBT_BLOCK_MINRECS(lev,cur) ((cur)->bc_mp->m_inobt_mnr[lev != 0])
-#define	XFS_INOBT_IS_LAST_REC(cur)	\
-	((cur)->bc_ptrs[0] == be16_to_cpu(XFS_BUF_TO_INOBT_BLOCK((cur)->bc_bufs[0])->bb_numrecs))
-
-/*
  * Maximum number of inode btree levels.
  */
 #define	XFS_IN_MAXLEVELS(mp)		((mp)->m_in_maxlevels)
@@ -104,75 +90,38 @@ typedef	struct xfs_btree_sblock xfs_inobt_block_t;
 #define	XFS_PREALLOC_BLOCKS(mp)		((xfs_agblock_t)(XFS_IBT_BLOCK(mp) + 1))
 
 /*
- * Record, key, and pointer address macros for btree blocks.
- */
-#define XFS_INOBT_REC_ADDR(bb,i,cur) \
-	(XFS_BTREE_REC_ADDR(xfs_inobt, bb, i))
-
-#define	XFS_INOBT_KEY_ADDR(bb,i,cur) \
-	(XFS_BTREE_KEY_ADDR(xfs_inobt, bb, i))
-
-#define	XFS_INOBT_PTR_ADDR(bb,i,cur) \
-	(XFS_BTREE_PTR_ADDR(xfs_inobt, bb, \
-				i, XFS_INOBT_BLOCK_MAXRECS(1, cur)))
-
-/*
- * Decrement cursor by one record at the level.
- * For nonzero levels the leaf-ward information is untouched.
- */
-extern int xfs_inobt_decrement(struct xfs_btree_cur *cur, int level, int *stat);
-
-/*
- * Delete the record pointed to by cur.
- * The cursor refers to the place where the record was (could be inserted)
- * when the operation returns.
- */
-extern int xfs_inobt_delete(struct xfs_btree_cur *cur, int *stat);
-
-/*
- * Get the data from the pointed-to record.
- */
-extern int xfs_inobt_get_rec(struct xfs_btree_cur *cur, xfs_agino_t *ino,
-			     __int32_t *fcnt, xfs_inofree_t *free, int *stat);
-
-/*
- * Increment cursor by one record at the level.
- * For nonzero levels the leaf-ward information is untouched.
- */
-extern int xfs_inobt_increment(struct xfs_btree_cur *cur, int level, int *stat);
-
-/*
- * Insert the current record at the point referenced by cur.
- * The cursor may be inconsistent on return if splits have been done.
- */
-extern int xfs_inobt_insert(struct xfs_btree_cur *cur, int *stat);
-
-/*
- * Lookup the record equal to ino in the btree given by cur.
- */
-extern int xfs_inobt_lookup_eq(struct xfs_btree_cur *cur, xfs_agino_t ino,
-				__int32_t fcnt, xfs_inofree_t free, int *stat);
-
-/*
- * Lookup the first record greater than or equal to ino
- * in the btree given by cur.
- */
-extern int xfs_inobt_lookup_ge(struct xfs_btree_cur *cur, xfs_agino_t ino,
-				__int32_t fcnt,	xfs_inofree_t free, int *stat);
-
-/*
- * Lookup the first record less than or equal to ino
- * in the btree given by cur.
+ * Btree block header size depends on a superblock flag.
+ *
+ * (not quite yet, but soon)
  */
-extern int xfs_inobt_lookup_le(struct xfs_btree_cur *cur, xfs_agino_t ino,
-				__int32_t fcnt,	xfs_inofree_t free, int *stat);
+#define XFS_INOBT_BLOCK_LEN(mp)	XFS_BTREE_SBLOCK_LEN
 
 /*
- * Update the record referred to by cur, to the value given
- * by [ino, fcnt, free].
- * This either works (return 0) or gets an EFSCORRUPTED error.
- */
-extern int xfs_inobt_update(struct xfs_btree_cur *cur, xfs_agino_t ino,
-				__int32_t fcnt, xfs_inofree_t free);
+ * Record, key, and pointer address macros for btree blocks.
+ *
+ * (note that some of these may appear unused, but they are used in userspace)
+ */
+#define XFS_INOBT_REC_ADDR(mp, block, index) \
+	((xfs_inobt_rec_t *) \
+		((char *)(block) + \
+		 XFS_INOBT_BLOCK_LEN(mp) + \
+		 (((index) - 1) * sizeof(xfs_inobt_rec_t))))
+
+#define XFS_INOBT_KEY_ADDR(mp, block, index) \
+	((xfs_inobt_key_t *) \
+		((char *)(block) + \
+		 XFS_INOBT_BLOCK_LEN(mp) + \
+		 ((index) - 1) * sizeof(xfs_inobt_key_t)))
+
+#define XFS_INOBT_PTR_ADDR(mp, block, index, maxrecs) \
+	((xfs_inobt_ptr_t *) \
+		((char *)(block) + \
+		 XFS_INOBT_BLOCK_LEN(mp) + \
+		 (maxrecs) * sizeof(xfs_inobt_key_t) + \
+		 ((index) - 1) * sizeof(xfs_inobt_ptr_t)))
+
+extern struct xfs_btree_cur *xfs_inobt_init_cursor(struct xfs_mount *,
+		struct xfs_trans *, struct xfs_buf *, xfs_agnumber_t);
+extern int xfs_inobt_maxrecs(struct xfs_mount *, int, int);
 
 #endif	/* __XFS_IALLOC_BTREE_H__ */
diff --git a/fs/xfs/xfs_iget.c b/fs/xfs/xfs_iget.c
index e229e9e001c2..e2fb6210d4c5 100644
--- a/fs/xfs/xfs_iget.c
+++ b/fs/xfs/xfs_iget.c
@@ -38,281 +38,283 @@
 #include "xfs_ialloc.h"
 #include "xfs_quota.h"
 #include "xfs_utils.h"
+#include "xfs_trans_priv.h"
+#include "xfs_inode_item.h"
+#include "xfs_bmap.h"
+#include "xfs_btree_trace.h"
+#include "xfs_dir2_trace.h"
+
 
 /*
- * Look up an inode by number in the given file system.
- * The inode is looked up in the cache held in each AG.
- * If the inode is found in the cache, attach it to the provided
- * vnode.
- *
- * If it is not in core, read it in from the file system's device,
- * add it to the cache and attach the provided vnode.
- *
- * The inode is locked according to the value of the lock_flags parameter.
- * This flag parameter indicates how and if the inode's IO lock and inode lock
- * should be taken.
- *
- * mp -- the mount point structure for the current file system.  It points
- *       to the inode hash table.
- * tp -- a pointer to the current transaction if there is one.  This is
- *       simply passed through to the xfs_iread() call.
- * ino -- the number of the inode desired.  This is the unique identifier
- *        within the file system for the inode being requested.
- * lock_flags -- flags indicating how to lock the inode.  See the comment
- *		 for xfs_ilock() for a list of valid values.
- * bno -- the block number starting the buffer containing the inode,
- *	  if known (as by bulkstat), else 0.
+ * Allocate and initialise an xfs_inode.
  */
-STATIC int
-xfs_iget_core(
-	struct inode	*inode,
-	xfs_mount_t	*mp,
-	xfs_trans_t	*tp,
-	xfs_ino_t	ino,
-	uint		flags,
-	uint		lock_flags,
-	xfs_inode_t	**ipp,
-	xfs_daddr_t	bno)
+STATIC struct xfs_inode *
+xfs_inode_alloc(
+	struct xfs_mount	*mp,
+	xfs_ino_t		ino)
 {
-	struct inode	*old_inode;
-	xfs_inode_t	*ip;
-	xfs_inode_t	*iq;
-	int		error;
-	unsigned long	first_index, mask;
-	xfs_perag_t	*pag;
-	xfs_agino_t	agino;
+	struct xfs_inode	*ip;
 
-	/* the radix tree exists only in inode capable AGs */
-	if (XFS_INO_TO_AGNO(mp, ino) >= mp->m_maxagi)
-		return EINVAL;
+	/*
+	 * if this didn't occur in transactions, we could use
+	 * KM_MAYFAIL and return NULL here on ENOMEM. Set the
+	 * code up to do this anyway.
+	 */
+	ip = kmem_zone_alloc(xfs_inode_zone, KM_SLEEP);
+	if (!ip)
+		return NULL;
 
-	/* get the perag structure and ensure that it's inode capable */
-	pag = xfs_get_perag(mp, ino);
-	if (!pag->pagi_inodeok)
-		return EINVAL;
-	ASSERT(pag->pag_ici_init);
-	agino = XFS_INO_TO_AGINO(mp, ino);
+	ASSERT(atomic_read(&ip->i_iocount) == 0);
+	ASSERT(atomic_read(&ip->i_pincount) == 0);
+	ASSERT(!spin_is_locked(&ip->i_flags_lock));
+	ASSERT(completion_done(&ip->i_flush));
 
-again:
-	read_lock(&pag->pag_ici_lock);
-	ip = radix_tree_lookup(&pag->pag_ici_root, agino);
+	/*
+	 * initialise the VFS inode here to get failures
+	 * out of the way early.
+	 */
+	if (!inode_init_always(mp->m_super, VFS_I(ip))) {
+		kmem_zone_free(xfs_inode_zone, ip);
+		return NULL;
+	}
+
+	/* initialise the xfs inode */
+	ip->i_ino = ino;
+	ip->i_mount = mp;
+	memset(&ip->i_imap, 0, sizeof(struct xfs_imap));
+	ip->i_afp = NULL;
+	memset(&ip->i_df, 0, sizeof(xfs_ifork_t));
+	ip->i_flags = 0;
+	ip->i_update_core = 0;
+	ip->i_update_size = 0;
+	ip->i_delayed_blks = 0;
+	memset(&ip->i_d, 0, sizeof(xfs_icdinode_t));
+	ip->i_size = 0;
+	ip->i_new_size = 0;
+
+	/*
+	 * Initialize inode's trace buffers.
+	 */
+#ifdef	XFS_INODE_TRACE
+	ip->i_trace = ktrace_alloc(INODE_TRACE_SIZE, KM_NOFS);
+#endif
+#ifdef XFS_BMAP_TRACE
+	ip->i_xtrace = ktrace_alloc(XFS_BMAP_KTRACE_SIZE, KM_NOFS);
+#endif
+#ifdef XFS_BTREE_TRACE
+	ip->i_btrace = ktrace_alloc(XFS_BMBT_KTRACE_SIZE, KM_NOFS);
+#endif
+#ifdef XFS_RW_TRACE
+	ip->i_rwtrace = ktrace_alloc(XFS_RW_KTRACE_SIZE, KM_NOFS);
+#endif
+#ifdef XFS_ILOCK_TRACE
+	ip->i_lock_trace = ktrace_alloc(XFS_ILOCK_KTRACE_SIZE, KM_NOFS);
+#endif
+#ifdef XFS_DIR2_TRACE
+	ip->i_dir_trace = ktrace_alloc(XFS_DIR2_KTRACE_SIZE, KM_NOFS);
+#endif
+
+	return ip;
+}
+
+/*
+ * Check the validity of the inode we just found it the cache
+ */
+static int
+xfs_iget_cache_hit(
+	struct xfs_perag	*pag,
+	struct xfs_inode	*ip,
+	int			flags,
+	int			lock_flags) __releases(pag->pag_ici_lock)
+{
+	struct xfs_mount	*mp = ip->i_mount;
+	int			error = EAGAIN;
+
+	/*
+	 * If INEW is set this inode is being set up
+	 * If IRECLAIM is set this inode is being torn down
+	 * Pause and try again.
+	 */
+	if (xfs_iflags_test(ip, (XFS_INEW|XFS_IRECLAIM))) {
+		XFS_STATS_INC(xs_ig_frecycle);
+		goto out_error;
+	}
+
+	/* If IRECLAIMABLE is set, we've torn down the vfs inode part */
+	if (xfs_iflags_test(ip, XFS_IRECLAIMABLE)) {
 
-	if (ip != NULL) {
 		/*
-		 * If INEW is set this inode is being set up
-		 * we need to pause and try again.
+		 * If lookup is racing with unlink, then we should return an
+		 * error immediately so we don't remove it from the reclaim
+		 * list and potentially leak the inode.
 		 */
-		if (xfs_iflags_test(ip, XFS_INEW)) {
-			read_unlock(&pag->pag_ici_lock);
-			delay(1);
-			XFS_STATS_INC(xs_ig_frecycle);
-
-			goto again;
+		if ((ip->i_d.di_mode == 0) && !(flags & XFS_IGET_CREATE)) {
+			error = ENOENT;
+			goto out_error;
 		}
 
-		old_inode = ip->i_vnode;
-		if (old_inode == NULL) {
-			/*
-			 * If IRECLAIM is set this inode is
-			 * on its way out of the system,
-			 * we need to pause and try again.
-			 */
-			if (xfs_iflags_test(ip, XFS_IRECLAIM)) {
-				read_unlock(&pag->pag_ici_lock);
-				delay(1);
-				XFS_STATS_INC(xs_ig_frecycle);
-
-				goto again;
-			}
-			ASSERT(xfs_iflags_test(ip, XFS_IRECLAIMABLE));
-
-			/*
-			 * If lookup is racing with unlink, then we
-			 * should return an error immediately so we
-			 * don't remove it from the reclaim list and
-			 * potentially leak the inode.
-			 */
-			if ((ip->i_d.di_mode == 0) &&
-			    !(flags & XFS_IGET_CREATE)) {
-				read_unlock(&pag->pag_ici_lock);
-				xfs_put_perag(mp, pag);
-				return ENOENT;
-			}
-
-			xfs_itrace_exit_tag(ip, "xfs_iget.alloc");
-
-			XFS_STATS_INC(xs_ig_found);
-			xfs_iflags_clear(ip, XFS_IRECLAIMABLE);
-			read_unlock(&pag->pag_ici_lock);
-
-			XFS_MOUNT_ILOCK(mp);
-			list_del_init(&ip->i_reclaim);
-			XFS_MOUNT_IUNLOCK(mp);
-
-			goto finish_inode;
-
-		} else if (inode != old_inode) {
-			/* The inode is being torn down, pause and
-			 * try again.
-			 */
-			if (old_inode->i_state & (I_FREEING | I_CLEAR)) {
-				read_unlock(&pag->pag_ici_lock);
-				delay(1);
-				XFS_STATS_INC(xs_ig_frecycle);
-
-				goto again;
-			}
-/* Chances are the other vnode (the one in the inode) is being torn
-* down right now, and we landed on top of it. Question is, what do
-* we do? Unhook the old inode and hook up the new one?
-*/
-			cmn_err(CE_PANIC,
-		"xfs_iget_core: ambiguous vns: vp/0x%p, invp/0x%p",
-					old_inode, inode);
-		}
+		xfs_itrace_exit_tag(ip, "xfs_iget.alloc");
 
 		/*
-		 * Inode cache hit
+		 * We need to re-initialise the VFS inode as it has been
+		 * 'freed' by the VFS. Do this here so we can deal with
+		 * errors cleanly, then tag it so it can be set up correctly
+		 * later.
 		 */
-		read_unlock(&pag->pag_ici_lock);
-		XFS_STATS_INC(xs_ig_found);
-
-finish_inode:
-		if (ip->i_d.di_mode == 0 && !(flags & XFS_IGET_CREATE)) {
-			xfs_put_perag(mp, pag);
-			return ENOENT;
+		if (!inode_init_always(mp->m_super, VFS_I(ip))) {
+			error = ENOMEM;
+			goto out_error;
 		}
 
-		if (lock_flags != 0)
-			xfs_ilock(ip, lock_flags);
+		/*
+		 * We must set the XFS_INEW flag before clearing the
+		 * XFS_IRECLAIMABLE flag so that if a racing lookup does
+		 * not find the XFS_IRECLAIMABLE above but has the igrab()
+		 * below succeed we can safely check XFS_INEW to detect
+		 * that this inode is still being initialised.
+		 */
+		xfs_iflags_set(ip, XFS_INEW);
+		xfs_iflags_clear(ip, XFS_IRECLAIMABLE);
+
+		/* clear the radix tree reclaim flag as well. */
+		__xfs_inode_clear_reclaim_tag(mp, pag, ip);
+	} else if (!igrab(VFS_I(ip))) {
+		/* If the VFS inode is being torn down, pause and try again. */
+		XFS_STATS_INC(xs_ig_frecycle);
+		goto out_error;
+	} else if (xfs_iflags_test(ip, XFS_INEW)) {
+		/*
+		 * We are racing with another cache hit that is
+		 * currently recycling this inode out of the XFS_IRECLAIMABLE
+		 * state. Wait for the initialisation to complete before
+		 * continuing.
+		 */
+		wait_on_inode(VFS_I(ip));
+	}
 
-		xfs_iflags_clear(ip, XFS_ISTALE);
-		xfs_itrace_exit_tag(ip, "xfs_iget.found");
-		goto return_ip;
+	if (ip->i_d.di_mode == 0 && !(flags & XFS_IGET_CREATE)) {
+		error = ENOENT;
+		iput(VFS_I(ip));
+		goto out_error;
 	}
 
-	/*
-	 * Inode cache miss
-	 */
+	/* We've got a live one. */
 	read_unlock(&pag->pag_ici_lock);
-	XFS_STATS_INC(xs_ig_missed);
 
-	/*
-	 * Read the disk inode attributes into a new inode structure and get
-	 * a new vnode for it. This should also initialize i_ino and i_mount.
-	 */
-	error = xfs_iread(mp, tp, ino, &ip, bno,
-			  (flags & XFS_IGET_BULKSTAT) ? XFS_IMAP_BULKSTAT : 0);
-	if (error) {
-		xfs_put_perag(mp, pag);
-		return error;
-	}
+	if (lock_flags != 0)
+		xfs_ilock(ip, lock_flags);
 
-	xfs_itrace_exit_tag(ip, "xfs_iget.alloc");
+	xfs_iflags_clear(ip, XFS_ISTALE);
+	xfs_itrace_exit_tag(ip, "xfs_iget.found");
+	XFS_STATS_INC(xs_ig_found);
+	return 0;
+
+out_error:
+	read_unlock(&pag->pag_ici_lock);
+	return error;
+}
 
 
-	mrlock_init(&ip->i_lock, MRLOCK_ALLOW_EQUAL_PRI|MRLOCK_BARRIER,
-		     "xfsino", ip->i_ino);
-	mrlock_init(&ip->i_iolock, MRLOCK_BARRIER, "xfsio", ip->i_ino);
-	init_waitqueue_head(&ip->i_ipin_wait);
-	atomic_set(&ip->i_pincount, 0);
+static int
+xfs_iget_cache_miss(
+	struct xfs_mount	*mp,
+	struct xfs_perag	*pag,
+	xfs_trans_t		*tp,
+	xfs_ino_t		ino,
+	struct xfs_inode	**ipp,
+	xfs_daddr_t		bno,
+	int			flags,
+	int			lock_flags) __releases(pag->pag_ici_lock)
+{
+	struct xfs_inode	*ip;
+	int			error;
+	unsigned long		first_index, mask;
+	xfs_agino_t		agino = XFS_INO_TO_AGINO(mp, ino);
 
-	/*
-	 * Because we want to use a counting completion, complete
-	 * the flush completion once to allow a single access to
-	 * the flush completion without blocking.
-	 */
-	init_completion(&ip->i_flush);
-	complete(&ip->i_flush);
+	ip = xfs_inode_alloc(mp, ino);
+	if (!ip)
+		return ENOMEM;
 
-	if (lock_flags)
-		xfs_ilock(ip, lock_flags);
+	error = xfs_iread(mp, tp, ip, bno, flags);
+	if (error)
+		goto out_destroy;
+
+	xfs_itrace_exit_tag(ip, "xfs_iget.alloc");
 
 	if ((ip->i_d.di_mode == 0) && !(flags & XFS_IGET_CREATE)) {
-		xfs_idestroy(ip);
-		xfs_put_perag(mp, pag);
-		return ENOENT;
+		error = ENOENT;
+		goto out_destroy;
 	}
 
+	if (lock_flags)
+		xfs_ilock(ip, lock_flags);
+
 	/*
 	 * Preload the radix tree so we can insert safely under the
-	 * write spinlock.
+	 * write spinlock. Note that we cannot sleep inside the preload
+	 * region.
 	 */
 	if (radix_tree_preload(GFP_KERNEL)) {
-		xfs_idestroy(ip);
-		delay(1);
-		goto again;
+		error = EAGAIN;
+		goto out_unlock;
 	}
+
 	mask = ~(((XFS_INODE_CLUSTER_SIZE(mp) >> mp->m_sb.sb_inodelog)) - 1);
 	first_index = agino & mask;
 	write_lock(&pag->pag_ici_lock);
-	/*
-	 * insert the new inode
-	 */
+
+	/* insert the new inode */
 	error = radix_tree_insert(&pag->pag_ici_root, agino, ip);
 	if (unlikely(error)) {
-		BUG_ON(error != -EEXIST);
-		write_unlock(&pag->pag_ici_lock);
-		radix_tree_preload_end();
-		xfs_idestroy(ip);
+		WARN_ON(error != -EEXIST);
 		XFS_STATS_INC(xs_ig_dup);
-		goto again;
+		error = EAGAIN;
+		goto out_preload_end;
 	}
 
-	/*
-	 * These values _must_ be set before releasing the radix tree lock!
-	 */
+	/* These values _must_ be set before releasing the radix tree lock! */
 	ip->i_udquot = ip->i_gdquot = NULL;
 	xfs_iflags_set(ip, XFS_INEW);
 
 	write_unlock(&pag->pag_ici_lock);
 	radix_tree_preload_end();
-
-	/*
-	 * Link ip to its mount and thread it on the mount's inode list.
-	 */
-	XFS_MOUNT_ILOCK(mp);
-	if ((iq = mp->m_inodes)) {
-		ASSERT(iq->i_mprev->i_mnext == iq);
-		ip->i_mprev = iq->i_mprev;
-		iq->i_mprev->i_mnext = ip;
-		iq->i_mprev = ip;
-		ip->i_mnext = iq;
-	} else {
-		ip->i_mnext = ip;
-		ip->i_mprev = ip;
-	}
-	mp->m_inodes = ip;
-
-	XFS_MOUNT_IUNLOCK(mp);
-	xfs_put_perag(mp, pag);
-
- return_ip:
-	ASSERT(ip->i_df.if_ext_max ==
-	       XFS_IFORK_DSIZE(ip) / sizeof(xfs_bmbt_rec_t));
-
-	xfs_iflags_set(ip, XFS_IMODIFIED);
 	*ipp = ip;
-
-	/*
-	 * Set up the Linux with the Linux inode.
-	 */
-	ip->i_vnode = inode;
-	inode->i_private = ip;
-
-	/*
-	 * If we have a real type for an on-disk inode, we can set ops(&unlock)
-	 * now.	 If it's a new inode being created, xfs_ialloc will handle it.
-	 */
-	if (ip->i_d.di_mode != 0)
-		xfs_setup_inode(ip);
 	return 0;
-}
 
+out_preload_end:
+	write_unlock(&pag->pag_ici_lock);
+	radix_tree_preload_end();
+out_unlock:
+	if (lock_flags)
+		xfs_iunlock(ip, lock_flags);
+out_destroy:
+	xfs_destroy_inode(ip);
+	return error;
+}
 
 /*
- * The 'normal' internal xfs_iget, if needed it will
- * 'allocate', or 'get', the vnode.
+ * Look up an inode by number in the given file system.
+ * The inode is looked up in the cache held in each AG.
+ * If the inode is found in the cache, initialise the vfs inode
+ * if necessary.
+ *
+ * If it is not in core, read it in from the file system's device,
+ * add it to the cache and initialise the vfs inode.
+ *
+ * The inode is locked according to the value of the lock_flags parameter.
+ * This flag parameter indicates how and if the inode's IO lock and inode lock
+ * should be taken.
+ *
+ * mp -- the mount point structure for the current file system.  It points
+ *       to the inode hash table.
+ * tp -- a pointer to the current transaction if there is one.  This is
+ *       simply passed through to the xfs_iread() call.
+ * ino -- the number of the inode desired.  This is the unique identifier
+ *        within the file system for the inode being requested.
+ * lock_flags -- flags indicating how to lock the inode.  See the comment
+ *		 for xfs_ilock() for a list of valid values.
+ * bno -- the block number starting the buffer containing the inode,
+ *	  if known (as by bulkstat), else 0.
  */
 int
 xfs_iget(
@@ -324,61 +326,64 @@ xfs_iget(
 	xfs_inode_t	**ipp,
 	xfs_daddr_t	bno)
 {
-	struct inode	*inode;
 	xfs_inode_t	*ip;
 	int		error;
+	xfs_perag_t	*pag;
+	xfs_agino_t	agino;
 
-	XFS_STATS_INC(xs_ig_attempts);
+	/* the radix tree exists only in inode capable AGs */
+	if (XFS_INO_TO_AGNO(mp, ino) >= mp->m_maxagi)
+		return EINVAL;
 
-retry:
-	inode = iget_locked(mp->m_super, ino);
-	if (!inode)
-		/* If we got no inode we are out of memory */
-		return ENOMEM;
+	/* get the perag structure and ensure that it's inode capable */
+	pag = xfs_get_perag(mp, ino);
+	if (!pag->pagi_inodeok)
+		return EINVAL;
+	ASSERT(pag->pag_ici_init);
+	agino = XFS_INO_TO_AGINO(mp, ino);
 
-	if (inode->i_state & I_NEW) {
-		XFS_STATS_INC(vn_active);
-		XFS_STATS_INC(vn_alloc);
-
-		error = xfs_iget_core(inode, mp, tp, ino, flags,
-				lock_flags, ipp, bno);
-		if (error) {
-			make_bad_inode(inode);
-			if (inode->i_state & I_NEW)
-				unlock_new_inode(inode);
-			iput(inode);
-		}
-		return error;
+again:
+	error = 0;
+	read_lock(&pag->pag_ici_lock);
+	ip = radix_tree_lookup(&pag->pag_ici_root, agino);
+
+	if (ip) {
+		error = xfs_iget_cache_hit(pag, ip, flags, lock_flags);
+		if (error)
+			goto out_error_or_again;
+	} else {
+		read_unlock(&pag->pag_ici_lock);
+		XFS_STATS_INC(xs_ig_missed);
+
+		error = xfs_iget_cache_miss(mp, pag, tp, ino, &ip, bno,
+							flags, lock_flags);
+		if (error)
+			goto out_error_or_again;
 	}
+	xfs_put_perag(mp, pag);
 
+	*ipp = ip;
+
+	ASSERT(ip->i_df.if_ext_max ==
+	       XFS_IFORK_DSIZE(ip) / sizeof(xfs_bmbt_rec_t));
 	/*
-	 * If the inode is not fully constructed due to
-	 * filehandle mismatches wait for the inode to go
-	 * away and try again.
-	 *
-	 * iget_locked will call __wait_on_freeing_inode
-	 * to wait for the inode to go away.
+	 * If we have a real type for an on-disk inode, we can set ops(&unlock)
+	 * now.	 If it's a new inode being created, xfs_ialloc will handle it.
 	 */
-	if (is_bad_inode(inode)) {
-		iput(inode);
-		delay(1);
-		goto retry;
-	}
+	if (xfs_iflags_test(ip, XFS_INEW) && ip->i_d.di_mode != 0)
+		xfs_setup_inode(ip);
+	return 0;
 
-	ip = XFS_I(inode);
-	if (!ip) {
-		iput(inode);
+out_error_or_again:
+	if (error == EAGAIN) {
 		delay(1);
-		goto retry;
+		goto again;
 	}
-
-	if (lock_flags != 0)
-		xfs_ilock(ip, lock_flags);
-	XFS_STATS_INC(xs_ig_found);
-	*ipp = ip;
-	return 0;
+	xfs_put_perag(mp, pag);
+	return error;
 }
 
+
 /*
  * Look for the inode corresponding to the given ino in the hash table.
  * If it is there and its i_transp pointer matches tp, return it.
@@ -444,99 +449,109 @@ xfs_iput_new(
 	IRELE(ip);
 }
 
-
 /*
- * This routine embodies the part of the reclaim code that pulls
- * the inode from the inode hash table and the mount structure's
- * inode list.
- * This should only be called from xfs_reclaim().
+ * This is called free all the memory associated with an inode.
+ * It must free the inode itself and any buffers allocated for
+ * if_extents/if_data and if_broot.  It must also free the lock
+ * associated with the inode.
+ *
+ * Note: because we don't initialise everything on reallocation out
+ * of the zone, we must ensure we nullify everything correctly before
+ * freeing the structure.
  */
 void
-xfs_ireclaim(xfs_inode_t *ip)
+xfs_ireclaim(
+	struct xfs_inode	*ip)
 {
-	/*
-	 * Remove from old hash list and mount list.
-	 */
-	XFS_STATS_INC(xs_ig_reclaims);
+	struct xfs_mount	*mp = ip->i_mount;
+	struct xfs_perag	*pag;
 
-	xfs_iextract(ip);
-
-	/*
-	 * Here we do a spurious inode lock in order to coordinate with
-	 * xfs_sync().  This is because xfs_sync() references the inodes
-	 * in the mount list without taking references on the corresponding
-	 * vnodes.  We make that OK here by ensuring that we wait until
-	 * the inode is unlocked in xfs_sync() before we go ahead and
-	 * free it.  We get both the regular lock and the io lock because
-	 * the xfs_sync() code may need to drop the regular one but will
-	 * still hold the io lock.
-	 */
-	xfs_ilock(ip, XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL);
-
-	/*
-	 * Release dquots (and their references) if any. An inode may escape
-	 * xfs_inactive and get here via vn_alloc->vn_reclaim path.
-	 */
-	XFS_QM_DQDETACH(ip->i_mount, ip);
-
-	/*
-	 * Pull our behavior descriptor from the vnode chain.
-	 */
-	if (ip->i_vnode) {
-		ip->i_vnode->i_private = NULL;
-		ip->i_vnode = NULL;
-	}
+	XFS_STATS_INC(xs_ig_reclaims);
 
 	/*
-	 * Free all memory associated with the inode.
+	 * Remove the inode from the per-AG radix tree.  It doesn't matter
+	 * if it was never added to it because radix_tree_delete can deal
+	 * with that case just fine.
 	 */
-	xfs_iunlock(ip, XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL);
-	xfs_idestroy(ip);
-}
-
-/*
- * This routine removes an about-to-be-destroyed inode from
- * all of the lists in which it is located with the exception
- * of the behavior chain.
- */
-void
-xfs_iextract(
-	xfs_inode_t	*ip)
-{
-	xfs_mount_t	*mp = ip->i_mount;
-	xfs_perag_t	*pag = xfs_get_perag(mp, ip->i_ino);
-	xfs_inode_t	*iq;
-
+	pag = xfs_get_perag(mp, ip->i_ino);
 	write_lock(&pag->pag_ici_lock);
 	radix_tree_delete(&pag->pag_ici_root, XFS_INO_TO_AGINO(mp, ip->i_ino));
 	write_unlock(&pag->pag_ici_lock);
 	xfs_put_perag(mp, pag);
 
 	/*
-	 * Remove from mount's inode list.
+	 * Here we do an (almost) spurious inode lock in order to coordinate
+	 * with inode cache radix tree lookups.  This is because the lookup
+	 * can reference the inodes in the cache without taking references.
+	 *
+	 * We make that OK here by ensuring that we wait until the inode is
+	 * unlocked after the lookup before we go ahead and free it.  We get
+	 * both the ilock and the iolock because the code may need to drop the
+	 * ilock one but will still hold the iolock.
 	 */
-	XFS_MOUNT_ILOCK(mp);
-	ASSERT((ip->i_mnext != NULL) && (ip->i_mprev != NULL));
-	iq = ip->i_mnext;
-	iq->i_mprev = ip->i_mprev;
-	ip->i_mprev->i_mnext = iq;
-
+	xfs_ilock(ip, XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL);
 	/*
-	 * Fix up the head pointer if it points to the inode being deleted.
+	 * Release dquots (and their references) if any.
 	 */
-	if (mp->m_inodes == ip) {
-		if (ip == iq) {
-			mp->m_inodes = NULL;
-		} else {
-			mp->m_inodes = iq;
-		}
+	XFS_QM_DQDETACH(ip->i_mount, ip);
+	xfs_iunlock(ip, XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL);
+
+	switch (ip->i_d.di_mode & S_IFMT) {
+	case S_IFREG:
+	case S_IFDIR:
+	case S_IFLNK:
+		xfs_idestroy_fork(ip, XFS_DATA_FORK);
+		break;
 	}
 
-	/* Deal with the deleted inodes list */
-	list_del_init(&ip->i_reclaim);
+	if (ip->i_afp)
+		xfs_idestroy_fork(ip, XFS_ATTR_FORK);
 
-	mp->m_ireclaims++;
-	XFS_MOUNT_IUNLOCK(mp);
+#ifdef XFS_INODE_TRACE
+	ktrace_free(ip->i_trace);
+#endif
+#ifdef XFS_BMAP_TRACE
+	ktrace_free(ip->i_xtrace);
+#endif
+#ifdef XFS_BTREE_TRACE
+	ktrace_free(ip->i_btrace);
+#endif
+#ifdef XFS_RW_TRACE
+	ktrace_free(ip->i_rwtrace);
+#endif
+#ifdef XFS_ILOCK_TRACE
+	ktrace_free(ip->i_lock_trace);
+#endif
+#ifdef XFS_DIR2_TRACE
+	ktrace_free(ip->i_dir_trace);
+#endif
+	if (ip->i_itemp) {
+		/*
+		 * Only if we are shutting down the fs will we see an
+		 * inode still in the AIL. If it is there, we should remove
+		 * it to prevent a use-after-free from occurring.
+		 */
+		xfs_log_item_t	*lip = &ip->i_itemp->ili_item;
+		struct xfs_ail	*ailp = lip->li_ailp;
+
+		ASSERT(((lip->li_flags & XFS_LI_IN_AIL) == 0) ||
+				       XFS_FORCED_SHUTDOWN(ip->i_mount));
+		if (lip->li_flags & XFS_LI_IN_AIL) {
+			spin_lock(&ailp->xa_lock);
+			if (lip->li_flags & XFS_LI_IN_AIL)
+				xfs_trans_ail_delete(ailp, lip);
+			else
+				spin_unlock(&ailp->xa_lock);
+		}
+		xfs_inode_item_destroy(ip);
+		ip->i_itemp = NULL;
+	}
+	/* asserts to verify all state is correct here */
+	ASSERT(atomic_read(&ip->i_iocount) == 0);
+	ASSERT(atomic_read(&ip->i_pincount) == 0);
+	ASSERT(!spin_is_locked(&ip->i_flags_lock));
+	ASSERT(completion_done(&ip->i_flush));
+	kmem_zone_free(xfs_inode_zone, ip);
 }
 
 /*
@@ -737,7 +752,7 @@ xfs_iunlock(
 		 * it is in the AIL and anyone is waiting on it.  Don't do
 		 * this if the caller has asked us not to.
 		 */
-		xfs_trans_unlocked_item(ip->i_mount,
+		xfs_trans_unlocked_item(ip->i_itemp->ili_item.li_ailp,
 					(xfs_log_item_t*)(ip->i_itemp));
 	}
 	xfs_ilock_trace(ip, 3, lock_flags, (inst_t *)__return_address);
@@ -790,3 +805,51 @@ xfs_isilocked(
 }
 #endif
 
+#ifdef	XFS_INODE_TRACE
+
+#define KTRACE_ENTER(ip, vk, s, line, ra)			\
+	ktrace_enter((ip)->i_trace,				\
+/*  0 */		(void *)(__psint_t)(vk),		\
+/*  1 */		(void *)(s),				\
+/*  2 */		(void *)(__psint_t) line,		\
+/*  3 */		(void *)(__psint_t)atomic_read(&VFS_I(ip)->i_count), \
+/*  4 */		(void *)(ra),				\
+/*  5 */		NULL,					\
+/*  6 */		(void *)(__psint_t)current_cpu(),	\
+/*  7 */		(void *)(__psint_t)current_pid(),	\
+/*  8 */		(void *)__return_address,		\
+/*  9 */		NULL, NULL, NULL, NULL, NULL, NULL, NULL)
+
+/*
+ * Vnode tracing code.
+ */
+void
+_xfs_itrace_entry(xfs_inode_t *ip, const char *func, inst_t *ra)
+{
+	KTRACE_ENTER(ip, INODE_KTRACE_ENTRY, func, 0, ra);
+}
+
+void
+_xfs_itrace_exit(xfs_inode_t *ip, const char *func, inst_t *ra)
+{
+	KTRACE_ENTER(ip, INODE_KTRACE_EXIT, func, 0, ra);
+}
+
+void
+xfs_itrace_hold(xfs_inode_t *ip, char *file, int line, inst_t *ra)
+{
+	KTRACE_ENTER(ip, INODE_KTRACE_HOLD, file, line, ra);
+}
+
+void
+_xfs_itrace_ref(xfs_inode_t *ip, char *file, int line, inst_t *ra)
+{
+	KTRACE_ENTER(ip, INODE_KTRACE_REF, file, line, ra);
+}
+
+void
+xfs_itrace_rele(xfs_inode_t *ip, char *file, int line, inst_t *ra)
+{
+	KTRACE_ENTER(ip, INODE_KTRACE_RELE, file, line, ra);
+}
+#endif	/* XFS_INODE_TRACE */
diff --git a/fs/xfs/xfs_imap.h b/fs/xfs/xfs_imap.h
deleted file mode 100644
index d36450003983..000000000000
--- a/fs/xfs/xfs_imap.h
+++ /dev/null
@@ -1,40 +0,0 @@
-/*
- * Copyright (c) 2000,2005 Silicon Graphics, Inc.
- * All Rights Reserved.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it would be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write the Free Software Foundation,
- * Inc.,  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
- */
-#ifndef __XFS_IMAP_H__
-#define	__XFS_IMAP_H__
-
-/*
- * This is the structure passed to xfs_imap() to map
- * an inode number to its on disk location.
- */
-typedef struct xfs_imap {
-	xfs_daddr_t	im_blkno;	/* starting BB of inode chunk */
-	uint		im_len;		/* length in BBs of inode chunk */
-	xfs_agblock_t	im_agblkno;	/* logical block of inode chunk in ag */
-	ushort		im_ioffset;	/* inode offset in block in "inodes" */
-	ushort		im_boffset;	/* inode offset in block in bytes */
-} xfs_imap_t;
-
-#ifdef __KERNEL__
-struct xfs_mount;
-struct xfs_trans;
-int	xfs_imap(struct xfs_mount *, struct xfs_trans *, xfs_ino_t,
-		 xfs_imap_t *, uint);
-#endif
-
-#endif	/* __XFS_IMAP_H__ */
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index a391b955df01..063da344e185 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -23,7 +23,6 @@
 #include "xfs_bit.h"
 #include "xfs_log.h"
 #include "xfs_inum.h"
-#include "xfs_imap.h"
 #include "xfs_trans.h"
 #include "xfs_trans_priv.h"
 #include "xfs_sb.h"
@@ -41,6 +40,7 @@
 #include "xfs_buf_item.h"
 #include "xfs_inode_item.h"
 #include "xfs_btree.h"
+#include "xfs_btree_trace.h"
 #include "xfs_alloc.h"
 #include "xfs_ialloc.h"
 #include "xfs_bmap.h"
@@ -133,10 +133,10 @@ STATIC int
 xfs_imap_to_bp(
 	xfs_mount_t	*mp,
 	xfs_trans_t	*tp,
-	xfs_imap_t	*imap,
+	struct xfs_imap	*imap,
 	xfs_buf_t	**bpp,
 	uint		buf_flags,
-	uint		imap_flags)
+	uint		iget_flags)
 {
 	int		error;
 	int		i;
@@ -173,12 +173,12 @@ xfs_imap_to_bp(
 
 		dip = (xfs_dinode_t *)xfs_buf_offset(bp,
 					(i << mp->m_sb.sb_inodelog));
-		di_ok = be16_to_cpu(dip->di_core.di_magic) == XFS_DINODE_MAGIC &&
-			    XFS_DINODE_GOOD_VERSION(dip->di_core.di_version);
+		di_ok = be16_to_cpu(dip->di_magic) == XFS_DINODE_MAGIC &&
+			    XFS_DINODE_GOOD_VERSION(dip->di_version);
 		if (unlikely(XFS_TEST_ERROR(!di_ok, mp,
 						XFS_ERRTAG_ITOBP_INOTOBP,
 						XFS_RANDOM_ITOBP_INOTOBP))) {
-			if (imap_flags & XFS_IMAP_BULKSTAT) {
+			if (iget_flags & XFS_IGET_BULKSTAT) {
 				xfs_trans_brelse(tp, bp);
 				return XFS_ERROR(EINVAL);
 			}
@@ -190,7 +190,7 @@ xfs_imap_to_bp(
 					"daddr %lld #%d (magic=%x)",
 				XFS_BUFTARG_NAME(mp->m_ddev_targp),
 				(unsigned long long)imap->im_blkno, i,
-				be16_to_cpu(dip->di_core.di_magic));
+				be16_to_cpu(dip->di_magic));
 #endif
 			xfs_trans_brelse(tp, bp);
 			return XFS_ERROR(EFSCORRUPTED);
@@ -221,25 +221,26 @@ xfs_imap_to_bp(
  * Use xfs_imap() to determine the size and location of the
  * buffer to read from disk.
  */
-STATIC int
+int
 xfs_inotobp(
 	xfs_mount_t	*mp,
 	xfs_trans_t	*tp,
 	xfs_ino_t	ino,
 	xfs_dinode_t	**dipp,
 	xfs_buf_t	**bpp,
-	int		*offset)
+	int		*offset,
+	uint		imap_flags)
 {
-	xfs_imap_t	imap;
+	struct xfs_imap	imap;
 	xfs_buf_t	*bp;
 	int		error;
 
 	imap.im_blkno = 0;
-	error = xfs_imap(mp, tp, ino, &imap, XFS_IMAP_LOOKUP);
+	error = xfs_imap(mp, tp, ino, &imap, imap_flags);
 	if (error)
 		return error;
 
-	error = xfs_imap_to_bp(mp, tp, &imap, &bp, XFS_BUF_LOCK, 0);
+	error = xfs_imap_to_bp(mp, tp, &imap, &bp, XFS_BUF_LOCK, imap_flags);
 	if (error)
 		return error;
 
@@ -260,15 +261,11 @@ xfs_inotobp(
  * If a non-zero error is returned, then the contents of bpp and
  * dipp are undefined.
  *
- * If the inode is new and has not yet been initialized, use xfs_imap()
- * to determine the size and location of the buffer to read from disk.
- * If the inode has already been mapped to its buffer and read in once,
- * then use the mapping information stored in the inode rather than
- * calling xfs_imap().  This allows us to avoid the overhead of looking
- * at the inode btree for small block file systems (see xfs_dilocate()).
- * We can tell whether the inode has been mapped in before by comparing
- * its disk block address to 0.  Only uninitialized inodes will have
- * 0 for the disk block address.
+ * The inode is expected to already been mapped to its buffer and read
+ * in once, thus we can use the mapping information stored in the inode
+ * rather than calling xfs_imap().  This allows us to avoid the overhead
+ * of looking at the inode btree for small block file systems
+ * (see xfs_imap()).
  */
 int
 xfs_itobp(
@@ -277,40 +274,14 @@ xfs_itobp(
 	xfs_inode_t	*ip,
 	xfs_dinode_t	**dipp,
 	xfs_buf_t	**bpp,
-	xfs_daddr_t	bno,
-	uint		imap_flags,
 	uint		buf_flags)
 {
-	xfs_imap_t	imap;
 	xfs_buf_t	*bp;
 	int		error;
 
-	if (ip->i_blkno == (xfs_daddr_t)0) {
-		imap.im_blkno = bno;
-		error = xfs_imap(mp, tp, ip->i_ino, &imap,
-					XFS_IMAP_LOOKUP | imap_flags);
-		if (error)
-			return error;
+	ASSERT(ip->i_imap.im_blkno != 0);
 
-		/*
-		 * Fill in the fields in the inode that will be used to
-		 * map the inode to its buffer from now on.
-		 */
-		ip->i_blkno = imap.im_blkno;
-		ip->i_len = imap.im_len;
-		ip->i_boffset = imap.im_boffset;
-	} else {
-		/*
-		 * We've already mapped the inode once, so just use the
-		 * mapping that we saved the first time.
-		 */
-		imap.im_blkno = ip->i_blkno;
-		imap.im_len = ip->i_len;
-		imap.im_boffset = ip->i_boffset;
-	}
-	ASSERT(bno == 0 || bno == imap.im_blkno);
-
-	error = xfs_imap_to_bp(mp, tp, &imap, &bp, buf_flags, imap_flags);
+	error = xfs_imap_to_bp(mp, tp, &ip->i_imap, &bp, buf_flags, 0);
 	if (error)
 		return error;
 
@@ -321,7 +292,7 @@ xfs_itobp(
 		return EAGAIN;
 	}
 
-	*dipp = (xfs_dinode_t *)xfs_buf_offset(bp, imap.im_boffset);
+	*dipp = (xfs_dinode_t *)xfs_buf_offset(bp, ip->i_imap.im_boffset);
 	*bpp = bp;
 	return 0;
 }
@@ -348,26 +319,26 @@ xfs_iformat(
 		XFS_IFORK_DSIZE(ip) / (uint)sizeof(xfs_bmbt_rec_t);
 	error = 0;
 
-	if (unlikely(be32_to_cpu(dip->di_core.di_nextents) +
-		     be16_to_cpu(dip->di_core.di_anextents) >
-		     be64_to_cpu(dip->di_core.di_nblocks))) {
+	if (unlikely(be32_to_cpu(dip->di_nextents) +
+		     be16_to_cpu(dip->di_anextents) >
+		     be64_to_cpu(dip->di_nblocks))) {
 		xfs_fs_repair_cmn_err(CE_WARN, ip->i_mount,
 			"corrupt dinode %Lu, extent total = %d, nblocks = %Lu.",
 			(unsigned long long)ip->i_ino,
-			(int)(be32_to_cpu(dip->di_core.di_nextents) +
-			      be16_to_cpu(dip->di_core.di_anextents)),
+			(int)(be32_to_cpu(dip->di_nextents) +
+			      be16_to_cpu(dip->di_anextents)),
 			(unsigned long long)
-				be64_to_cpu(dip->di_core.di_nblocks));
+				be64_to_cpu(dip->di_nblocks));
 		XFS_CORRUPTION_ERROR("xfs_iformat(1)", XFS_ERRLEVEL_LOW,
 				     ip->i_mount, dip);
 		return XFS_ERROR(EFSCORRUPTED);
 	}
 
-	if (unlikely(dip->di_core.di_forkoff > ip->i_mount->m_sb.sb_inodesize)) {
+	if (unlikely(dip->di_forkoff > ip->i_mount->m_sb.sb_inodesize)) {
 		xfs_fs_repair_cmn_err(CE_WARN, ip->i_mount,
 			"corrupt dinode %Lu, forkoff = 0x%x.",
 			(unsigned long long)ip->i_ino,
-			dip->di_core.di_forkoff);
+			dip->di_forkoff);
 		XFS_CORRUPTION_ERROR("xfs_iformat(2)", XFS_ERRLEVEL_LOW,
 				     ip->i_mount, dip);
 		return XFS_ERROR(EFSCORRUPTED);
@@ -378,25 +349,25 @@ xfs_iformat(
 	case S_IFCHR:
 	case S_IFBLK:
 	case S_IFSOCK:
-		if (unlikely(dip->di_core.di_format != XFS_DINODE_FMT_DEV)) {
+		if (unlikely(dip->di_format != XFS_DINODE_FMT_DEV)) {
 			XFS_CORRUPTION_ERROR("xfs_iformat(3)", XFS_ERRLEVEL_LOW,
 					      ip->i_mount, dip);
 			return XFS_ERROR(EFSCORRUPTED);
 		}
 		ip->i_d.di_size = 0;
 		ip->i_size = 0;
-		ip->i_df.if_u2.if_rdev = be32_to_cpu(dip->di_u.di_dev);
+		ip->i_df.if_u2.if_rdev = xfs_dinode_get_rdev(dip);
 		break;
 
 	case S_IFREG:
 	case S_IFLNK:
 	case S_IFDIR:
-		switch (dip->di_core.di_format) {
+		switch (dip->di_format) {
 		case XFS_DINODE_FMT_LOCAL:
 			/*
 			 * no local regular files yet
 			 */
-			if (unlikely((be16_to_cpu(dip->di_core.di_mode) & S_IFMT) == S_IFREG)) {
+			if (unlikely((be16_to_cpu(dip->di_mode) & S_IFMT) == S_IFREG)) {
 				xfs_fs_repair_cmn_err(CE_WARN, ip->i_mount,
 					"corrupt inode %Lu "
 					"(local format for regular file).",
@@ -407,7 +378,7 @@ xfs_iformat(
 				return XFS_ERROR(EFSCORRUPTED);
 			}
 
-			di_size = be64_to_cpu(dip->di_core.di_size);
+			di_size = be64_to_cpu(dip->di_size);
 			if (unlikely(di_size > XFS_DFORK_DSIZE(dip, ip->i_mount))) {
 				xfs_fs_repair_cmn_err(CE_WARN, ip->i_mount,
 					"corrupt inode %Lu "
@@ -449,7 +420,7 @@ xfs_iformat(
 	ip->i_afp = kmem_zone_zalloc(xfs_ifork_zone, KM_SLEEP);
 	ip->i_afp->if_ext_max =
 		XFS_IFORK_ASIZE(ip) / (uint)sizeof(xfs_bmbt_rec_t);
-	switch (dip->di_core.di_aformat) {
+	switch (dip->di_aformat) {
 	case XFS_DINODE_FMT_LOCAL:
 		atp = (xfs_attr_shortform_t *)XFS_DFORK_APTR(dip);
 		size = be16_to_cpu(atp->hdr.totsize);
@@ -621,7 +592,7 @@ xfs_iformat_btree(
 	ifp = XFS_IFORK_PTR(ip, whichfork);
 	dfp = (xfs_bmdr_block_t *)XFS_DFORK_PTR(dip, whichfork);
 	size = XFS_BMAP_BROOT_SPACE(dfp);
-	nrecs = XFS_BMAP_BROOT_NUMRECS(dfp);
+	nrecs = be16_to_cpu(dfp->bb_numrecs);
 
 	/*
 	 * blow out if -- fork has less extents than can fit in
@@ -649,8 +620,9 @@ xfs_iformat_btree(
 	 * Copy and convert from the on-disk structure
 	 * to the in-memory structure.
 	 */
-	xfs_bmdr_to_bmbt(dfp, XFS_DFORK_SIZE(dip, ip->i_mount, whichfork),
-		ifp->if_broot, size);
+	xfs_bmdr_to_bmbt(ip->i_mount, dfp,
+			 XFS_DFORK_SIZE(dip, ip->i_mount, whichfork),
+			 ifp->if_broot, size);
 	ifp->if_flags &= ~XFS_IFEXTENTS;
 	ifp->if_flags |= XFS_IFBROOT;
 
@@ -660,7 +632,7 @@ xfs_iformat_btree(
 void
 xfs_dinode_from_disk(
 	xfs_icdinode_t		*to,
-	xfs_dinode_core_t	*from)
+	xfs_dinode_t		*from)
 {
 	to->di_magic = be16_to_cpu(from->di_magic);
 	to->di_mode = be16_to_cpu(from->di_mode);
@@ -694,7 +666,7 @@ xfs_dinode_from_disk(
 
 void
 xfs_dinode_to_disk(
-	xfs_dinode_core_t	*to,
+	xfs_dinode_t		*to,
 	xfs_icdinode_t		*from)
 {
 	to->di_magic = cpu_to_be16(from->di_magic);
@@ -781,93 +753,57 @@ uint
 xfs_dic2xflags(
 	xfs_dinode_t		*dip)
 {
-	xfs_dinode_core_t	*dic = &dip->di_core;
-
-	return _xfs_dic2xflags(be16_to_cpu(dic->di_flags)) |
+	return _xfs_dic2xflags(be16_to_cpu(dip->di_flags)) |
 				(XFS_DFORK_Q(dip) ? XFS_XFLAG_HASATTR : 0);
 }
 
 /*
- * Given a mount structure and an inode number, return a pointer
- * to a newly allocated in-core inode corresponding to the given
- * inode number.
- *
- * Initialize the inode's attributes and extent pointers if it
- * already has them (it will not if the inode has no links).
+ * Read the disk inode attributes into the in-core inode structure.
  */
 int
 xfs_iread(
 	xfs_mount_t	*mp,
 	xfs_trans_t	*tp,
-	xfs_ino_t	ino,
-	xfs_inode_t	**ipp,
+	xfs_inode_t	*ip,
 	xfs_daddr_t	bno,
-	uint		imap_flags)
+	uint		iget_flags)
 {
 	xfs_buf_t	*bp;
 	xfs_dinode_t	*dip;
-	xfs_inode_t	*ip;
 	int		error;
 
-	ASSERT(xfs_inode_zone != NULL);
-
-	ip = kmem_zone_zalloc(xfs_inode_zone, KM_SLEEP);
-	ip->i_ino = ino;
-	ip->i_mount = mp;
-	atomic_set(&ip->i_iocount, 0);
-	spin_lock_init(&ip->i_flags_lock);
-
 	/*
-	 * Get pointer's to the on-disk inode and the buffer containing it.
-	 * If the inode number refers to a block outside the file system
-	 * then xfs_itobp() will return NULL.  In this case we should
-	 * return NULL as well.  Set i_blkno to 0 so that xfs_itobp() will
-	 * know that this is a new incore inode.
+	 * Fill in the location information in the in-core inode.
 	 */
-	error = xfs_itobp(mp, tp, ip, &dip, &bp, bno, imap_flags, XFS_BUF_LOCK);
-	if (error) {
-		kmem_zone_free(xfs_inode_zone, ip);
+	ip->i_imap.im_blkno = bno;
+	error = xfs_imap(mp, tp, ip->i_ino, &ip->i_imap, iget_flags);
+	if (error)
 		return error;
-	}
+	ASSERT(bno == 0 || bno == ip->i_imap.im_blkno);
 
 	/*
-	 * Initialize inode's trace buffers.
-	 * Do this before xfs_iformat in case it adds entries.
+	 * Get pointers to the on-disk inode and the buffer containing it.
 	 */
-#ifdef	XFS_INODE_TRACE
-	ip->i_trace = ktrace_alloc(INODE_TRACE_SIZE, KM_NOFS);
-#endif
-#ifdef XFS_BMAP_TRACE
-	ip->i_xtrace = ktrace_alloc(XFS_BMAP_KTRACE_SIZE, KM_NOFS);
-#endif
-#ifdef XFS_BMBT_TRACE
-	ip->i_btrace = ktrace_alloc(XFS_BMBT_KTRACE_SIZE, KM_NOFS);
-#endif
-#ifdef XFS_RW_TRACE
-	ip->i_rwtrace = ktrace_alloc(XFS_RW_KTRACE_SIZE, KM_NOFS);
-#endif
-#ifdef XFS_ILOCK_TRACE
-	ip->i_lock_trace = ktrace_alloc(XFS_ILOCK_KTRACE_SIZE, KM_NOFS);
-#endif
-#ifdef XFS_DIR2_TRACE
-	ip->i_dir_trace = ktrace_alloc(XFS_DIR2_KTRACE_SIZE, KM_NOFS);
-#endif
+	error = xfs_imap_to_bp(mp, tp, &ip->i_imap, &bp,
+			       XFS_BUF_LOCK, iget_flags);
+	if (error)
+		return error;
+	dip = (xfs_dinode_t *)xfs_buf_offset(bp, ip->i_imap.im_boffset);
 
 	/*
 	 * If we got something that isn't an inode it means someone
 	 * (nfs or dmi) has a stale handle.
 	 */
-	if (be16_to_cpu(dip->di_core.di_magic) != XFS_DINODE_MAGIC) {
-		kmem_zone_free(xfs_inode_zone, ip);
-		xfs_trans_brelse(tp, bp);
+	if (be16_to_cpu(dip->di_magic) != XFS_DINODE_MAGIC) {
 #ifdef DEBUG
 		xfs_fs_cmn_err(CE_ALERT, mp, "xfs_iread: "
-				"dip->di_core.di_magic (0x%x) != "
+				"dip->di_magic (0x%x) != "
 				"XFS_DINODE_MAGIC (0x%x)",
-				be16_to_cpu(dip->di_core.di_magic),
+				be16_to_cpu(dip->di_magic),
 				XFS_DINODE_MAGIC);
 #endif /* DEBUG */
-		return XFS_ERROR(EINVAL);
+		error = XFS_ERROR(EINVAL);
+		goto out_brelse;
 	}
 
 	/*
@@ -877,24 +813,22 @@ xfs_iread(
 	 * specific information.
 	 * Otherwise, just get the truly permanent information.
 	 */
-	if (dip->di_core.di_mode) {
-		xfs_dinode_from_disk(&ip->i_d, &dip->di_core);
+	if (dip->di_mode) {
+		xfs_dinode_from_disk(&ip->i_d, dip);
 		error = xfs_iformat(ip, dip);
 		if (error)  {
-			kmem_zone_free(xfs_inode_zone, ip);
-			xfs_trans_brelse(tp, bp);
 #ifdef DEBUG
 			xfs_fs_cmn_err(CE_ALERT, mp, "xfs_iread: "
 					"xfs_iformat() returned error %d",
 					error);
 #endif /* DEBUG */
-			return error;
+			goto out_brelse;
 		}
 	} else {
-		ip->i_d.di_magic = be16_to_cpu(dip->di_core.di_magic);
-		ip->i_d.di_version = dip->di_core.di_version;
-		ip->i_d.di_gen = be32_to_cpu(dip->di_core.di_gen);
-		ip->i_d.di_flushiter = be16_to_cpu(dip->di_core.di_flushiter);
+		ip->i_d.di_magic = be16_to_cpu(dip->di_magic);
+		ip->i_d.di_version = dip->di_version;
+		ip->i_d.di_gen = be32_to_cpu(dip->di_gen);
+		ip->i_d.di_flushiter = be16_to_cpu(dip->di_flushiter);
 		/*
 		 * Make sure to pull in the mode here as well in
 		 * case the inode is released without being used.
@@ -911,8 +845,6 @@ xfs_iread(
 			XFS_IFORK_DSIZE(ip) / (uint)sizeof(xfs_bmbt_rec_t);
 	}
 
-	INIT_LIST_HEAD(&ip->i_reclaim);
-
 	/*
 	 * The inode format changed when we moved the link count and
 	 * made it 32 bits long.  If this is an old format inode,
@@ -924,7 +856,7 @@ xfs_iread(
 	 * the new format. We don't change the version number so that we
 	 * can distinguish this from a real new format inode.
 	 */
-	if (ip->i_d.di_version == XFS_DINODE_VERSION_1) {
+	if (ip->i_d.di_version == 1) {
 		ip->i_d.di_nlink = ip->i_d.di_onlink;
 		ip->i_d.di_onlink = 0;
 		ip->i_d.di_projid = 0;
@@ -953,9 +885,9 @@ xfs_iread(
 	 * to worry about the inode being changed just because we released
 	 * the buffer.
 	 */
+ out_brelse:
 	xfs_trans_brelse(tp, bp);
-	*ipp = ip;
-	return 0;
+	return error;
 }
 
 /*
@@ -1049,6 +981,7 @@ xfs_ialloc(
 	uint		flags;
 	int		error;
 	timespec_t	tv;
+	int		filestreams = 0;
 
 	/*
 	 * Call the space management code to pick
@@ -1056,9 +989,8 @@ xfs_ialloc(
 	 */
 	error = xfs_dialloc(tp, pip ? pip->i_ino : 0, mode, okalloc,
 			    ialloc_context, call_again, &ino);
-	if (error != 0) {
+	if (error)
 		return error;
-	}
 	if (*call_again || ino == NULLFSINO) {
 		*ipp = NULL;
 		return 0;
@@ -1072,9 +1004,8 @@ xfs_ialloc(
 	 */
 	error = xfs_trans_iget(tp->t_mountp, tp, ino,
 				XFS_IGET_CREATE, XFS_ILOCK_EXCL, &ip);
-	if (error != 0) {
+	if (error)
 		return error;
-	}
 	ASSERT(ip != NULL);
 
 	ip->i_d.di_mode = (__uint16_t)mode;
@@ -1093,8 +1024,8 @@ xfs_ialloc(
 	 * here rather than here and in the flush/logging code.
 	 */
 	if (xfs_sb_version_hasnlink(&tp->t_mountp->m_sb) &&
-	    ip->i_d.di_version == XFS_DINODE_VERSION_1) {
-		ip->i_d.di_version = XFS_DINODE_VERSION_2;
+	    ip->i_d.di_version == 1) {
+		ip->i_d.di_version = 2;
 		/*
 		 * We've already zeroed the old link count, the projid field,
 		 * and the pad field.
@@ -1104,7 +1035,7 @@ xfs_ialloc(
 	/*
 	 * Project ids won't be stored on disk if we are using a version 1 inode.
 	 */
-	if ((prid != 0) && (ip->i_d.di_version == XFS_DINODE_VERSION_1))
+	if ((prid != 0) && (ip->i_d.di_version == 1))
 		xfs_bump_ino_vers2(tp, ip);
 
 	if (pip && XFS_INHERIT_GID(pip)) {
@@ -1155,13 +1086,12 @@ xfs_ialloc(
 		flags |= XFS_ILOG_DEV;
 		break;
 	case S_IFREG:
-		if (pip && xfs_inode_is_filestream(pip)) {
-			error = xfs_filestream_associate(pip, ip);
-			if (error < 0)
-				return -error;
-			if (!error)
-				xfs_iflags_set(ip, XFS_IFILESTREAM);
-		}
+		/*
+		 * we can't set up filestreams until after the VFS inode
+		 * is set up properly.
+		 */
+		if (pip && xfs_inode_is_filestream(pip))
+			filestreams = 1;
 		/* fall through */
 	case S_IFDIR:
 		if (pip && (pip->i_d.di_flags & XFS_DIFLAG_ANY)) {
@@ -1227,6 +1157,15 @@ xfs_ialloc(
 	/* now that we have an i_mode we can setup inode ops and unlock */
 	xfs_setup_inode(ip);
 
+	/* now we have set up the vfs inode we can associate the filestream */
+	if (filestreams) {
+		error = xfs_filestream_associate(pip, ip);
+		if (error < 0)
+			return -error;
+		if (!error)
+			xfs_iflags_set(ip, XFS_IFILESTREAM);
+	}
+
 	*ipp = ip;
 	return 0;
 }
@@ -1383,8 +1322,8 @@ xfs_itrunc_trace(
  * direct I/O with the truncate operation.  Also, because we hold
  * the IOLOCK in exclusive mode, we prevent new direct I/Os from being
  * started until the truncate completes and drops the lock. Essentially,
- * the vn_iowait() call forms an I/O barrier that provides strict ordering
- * between direct I/Os and the truncate operation.
+ * the xfs_ioend_wait() call forms an I/O barrier that provides strict
+ * ordering between direct I/Os and the truncate operation.
  *
  * The flags parameter can have either the value XFS_ITRUNC_DEFINITE
  * or XFS_ITRUNC_MAYBE.  The XFS_ITRUNC_MAYBE value should be used
@@ -1415,7 +1354,7 @@ xfs_itruncate_start(
 
 	/* wait for the completion of any pending DIOs */
 	if (new_size == 0 || new_size < ip->i_size)
-		vn_iowait(ip);
+		xfs_ioend_wait(ip);
 
 	/*
 	 * Call toss_pages or flushinval_pages to get rid of pages
@@ -1726,8 +1665,14 @@ xfs_itruncate_finish(
 		xfs_trans_ijoin(ntp, ip, XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL);
 		xfs_trans_ihold(ntp, ip);
 
-		if (!error)
-			error = xfs_trans_reserve(ntp, 0,
+		if (error)
+			return error;
+		/*
+		 * transaction commit worked ok so we can drop the extra ticket
+		 * reference that we gained in xfs_trans_dup()
+		 */
+		xfs_log_ticket_put(ntp->t_ticket);
+		error = xfs_trans_reserve(ntp, 0,
 					XFS_ITRUNCATE_LOG_RES(mp), 0,
 					XFS_TRANS_PERM_LOG_RES,
 					XFS_ITRUNCATE_LOG_COUNT);
@@ -1781,13 +1726,10 @@ xfs_iunlink(
 	xfs_dinode_t	*dip;
 	xfs_buf_t	*agibp;
 	xfs_buf_t	*ibp;
-	xfs_agnumber_t	agno;
-	xfs_daddr_t	agdaddr;
 	xfs_agino_t	agino;
 	short		bucket_index;
 	int		offset;
 	int		error;
-	int		agi_ok;
 
 	ASSERT(ip->i_d.di_nlink == 0);
 	ASSERT(ip->i_d.di_mode != 0);
@@ -1795,31 +1737,15 @@ xfs_iunlink(
 
 	mp = tp->t_mountp;
 
-	agno = XFS_INO_TO_AGNO(mp, ip->i_ino);
-	agdaddr = XFS_AG_DADDR(mp, agno, XFS_AGI_DADDR(mp));
-
 	/*
 	 * Get the agi buffer first.  It ensures lock ordering
 	 * on the list.
 	 */
-	error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp, agdaddr,
-				   XFS_FSS_TO_BB(mp, 1), 0, &agibp);
+	error = xfs_read_agi(mp, tp, XFS_INO_TO_AGNO(mp, ip->i_ino), &agibp);
 	if (error)
 		return error;
-
-	/*
-	 * Validate the magic number of the agi block.
-	 */
 	agi = XFS_BUF_TO_AGI(agibp);
-	agi_ok =
-		be32_to_cpu(agi->agi_magicnum) == XFS_AGI_MAGIC &&
-		XFS_AGI_GOOD_VERSION(be32_to_cpu(agi->agi_versionnum));
-	if (unlikely(XFS_TEST_ERROR(!agi_ok, mp, XFS_ERRTAG_IUNLINK,
-			XFS_RANDOM_IUNLINK))) {
-		XFS_CORRUPTION_ERROR("xfs_iunlink", XFS_ERRLEVEL_LOW, mp, agi);
-		xfs_trans_brelse(tp, agibp);
-		return XFS_ERROR(EFSCORRUPTED);
-	}
+
 	/*
 	 * Get the index into the agi hash table for the
 	 * list this inode will go on.
@@ -1837,14 +1763,14 @@ xfs_iunlink(
 		 * Here we put the head pointer into our next pointer,
 		 * and then we fall through to point the head at us.
 		 */
-		error = xfs_itobp(mp, tp, ip, &dip, &ibp, 0, 0, XFS_BUF_LOCK);
+		error = xfs_itobp(mp, tp, ip, &dip, &ibp, XFS_BUF_LOCK);
 		if (error)
 			return error;
 
 		ASSERT(be32_to_cpu(dip->di_next_unlinked) == NULLAGINO);
 		/* both on-disk, don't endian flip twice */
 		dip->di_next_unlinked = agi->agi_unlinked[bucket_index];
-		offset = ip->i_boffset +
+		offset = ip->i_imap.im_boffset +
 			offsetof(xfs_dinode_t, di_next_unlinked);
 		xfs_trans_inode_buf(tp, ibp);
 		xfs_trans_log_buf(tp, ibp, offset,
@@ -1879,7 +1805,6 @@ xfs_iunlink_remove(
 	xfs_buf_t	*agibp;
 	xfs_buf_t	*ibp;
 	xfs_agnumber_t	agno;
-	xfs_daddr_t	agdaddr;
 	xfs_agino_t	agino;
 	xfs_agino_t	next_agino;
 	xfs_buf_t	*last_ibp;
@@ -1887,45 +1812,20 @@ xfs_iunlink_remove(
 	short		bucket_index;
 	int		offset, last_offset = 0;
 	int		error;
-	int		agi_ok;
 
-	/*
-	 * First pull the on-disk inode from the AGI unlinked list.
-	 */
 	mp = tp->t_mountp;
-
 	agno = XFS_INO_TO_AGNO(mp, ip->i_ino);
-	agdaddr = XFS_AG_DADDR(mp, agno, XFS_AGI_DADDR(mp));
 
 	/*
 	 * Get the agi buffer first.  It ensures lock ordering
 	 * on the list.
 	 */
-	error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp, agdaddr,
-				   XFS_FSS_TO_BB(mp, 1), 0, &agibp);
-	if (error) {
-		cmn_err(CE_WARN,
-			"xfs_iunlink_remove: xfs_trans_read_buf()  returned an error %d on %s.  Returning error.",
-			error, mp->m_fsname);
+	error = xfs_read_agi(mp, tp, agno, &agibp);
+	if (error)
 		return error;
-	}
-	/*
-	 * Validate the magic number of the agi block.
-	 */
+
 	agi = XFS_BUF_TO_AGI(agibp);
-	agi_ok =
-		be32_to_cpu(agi->agi_magicnum) == XFS_AGI_MAGIC &&
-		XFS_AGI_GOOD_VERSION(be32_to_cpu(agi->agi_versionnum));
-	if (unlikely(XFS_TEST_ERROR(!agi_ok, mp, XFS_ERRTAG_IUNLINK_REMOVE,
-			XFS_RANDOM_IUNLINK_REMOVE))) {
-		XFS_CORRUPTION_ERROR("xfs_iunlink_remove", XFS_ERRLEVEL_LOW,
-				     mp, agi);
-		xfs_trans_brelse(tp, agibp);
-		cmn_err(CE_WARN,
-			"xfs_iunlink_remove: XFS_TEST_ERROR()  returned an error on %s.  Returning EFSCORRUPTED.",
-			 mp->m_fsname);
-		return XFS_ERROR(EFSCORRUPTED);
-	}
+
 	/*
 	 * Get the index into the agi hash table for the
 	 * list this inode will go on.
@@ -1945,7 +1845,7 @@ xfs_iunlink_remove(
 		 * of dealing with the buffer when there is no need to
 		 * change it.
 		 */
-		error = xfs_itobp(mp, tp, ip, &dip, &ibp, 0, 0, XFS_BUF_LOCK);
+		error = xfs_itobp(mp, tp, ip, &dip, &ibp, XFS_BUF_LOCK);
 		if (error) {
 			cmn_err(CE_WARN,
 				"xfs_iunlink_remove: xfs_itobp()  returned an error %d on %s.  Returning error.",
@@ -1956,7 +1856,7 @@ xfs_iunlink_remove(
 		ASSERT(next_agino != 0);
 		if (next_agino != NULLAGINO) {
 			dip->di_next_unlinked = cpu_to_be32(NULLAGINO);
-			offset = ip->i_boffset +
+			offset = ip->i_imap.im_boffset +
 				offsetof(xfs_dinode_t, di_next_unlinked);
 			xfs_trans_inode_buf(tp, ibp);
 			xfs_trans_log_buf(tp, ibp, offset,
@@ -1992,7 +1892,7 @@ xfs_iunlink_remove(
 			}
 			next_ino = XFS_AGINO_TO_INO(mp, agno, next_agino);
 			error = xfs_inotobp(mp, tp, next_ino, &last_dip,
-					    &last_ibp, &last_offset);
+					    &last_ibp, &last_offset, 0);
 			if (error) {
 				cmn_err(CE_WARN,
 			"xfs_iunlink_remove: xfs_inotobp()  returned an error %d on %s.  Returning error.",
@@ -2007,7 +1907,7 @@ xfs_iunlink_remove(
 		 * Now last_ibp points to the buffer previous to us on
 		 * the unlinked list.  Pull us from the list.
 		 */
-		error = xfs_itobp(mp, tp, ip, &dip, &ibp, 0, 0, XFS_BUF_LOCK);
+		error = xfs_itobp(mp, tp, ip, &dip, &ibp, XFS_BUF_LOCK);
 		if (error) {
 			cmn_err(CE_WARN,
 				"xfs_iunlink_remove: xfs_itobp()  returned an error %d on %s.  Returning error.",
@@ -2019,7 +1919,7 @@ xfs_iunlink_remove(
 		ASSERT(next_agino != agino);
 		if (next_agino != NULLAGINO) {
 			dip->di_next_unlinked = cpu_to_be32(NULLAGINO);
-			offset = ip->i_boffset +
+			offset = ip->i_imap.im_boffset +
 				offsetof(xfs_dinode_t, di_next_unlinked);
 			xfs_trans_inode_buf(tp, ibp);
 			xfs_trans_log_buf(tp, ibp, offset,
@@ -2160,9 +2060,9 @@ xfs_ifree_cluster(
 				iip = (xfs_inode_log_item_t *)lip;
 				ASSERT(iip->ili_logged == 1);
 				lip->li_cb = (void(*)(xfs_buf_t*,xfs_log_item_t*)) xfs_istale_done;
-				spin_lock(&mp->m_ail_lock);
-				iip->ili_flush_lsn = iip->ili_item.li_lsn;
-				spin_unlock(&mp->m_ail_lock);
+				xfs_trans_ail_copy_lsn(mp->m_ail,
+							&iip->ili_flush_lsn,
+							&iip->ili_item.li_lsn);
 				xfs_iflags_set(iip->ili_inode, XFS_ISTALE);
 				pre_flushed++;
 			}
@@ -2183,9 +2083,8 @@ xfs_ifree_cluster(
 			iip->ili_last_fields = iip->ili_format.ilf_fields;
 			iip->ili_format.ilf_fields = 0;
 			iip->ili_logged = 1;
-			spin_lock(&mp->m_ail_lock);
-			iip->ili_flush_lsn = iip->ili_item.li_lsn;
-			spin_unlock(&mp->m_ail_lock);
+			xfs_trans_ail_copy_lsn(mp->m_ail, &iip->ili_flush_lsn,
+						&iip->ili_item.li_lsn);
 
 			xfs_buf_attach_iodone(bp,
 				(void(*)(xfs_buf_t*,xfs_log_item_t*))
@@ -2263,7 +2162,7 @@ xfs_ifree(
 
 	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
 
-	error = xfs_itobp(ip->i_mount, tp, ip, &dip, &ibp, 0, 0, XFS_BUF_LOCK);
+	error = xfs_itobp(ip->i_mount, tp, ip, &dip, &ibp, XFS_BUF_LOCK);
 	if (error)
 		return error;
 
@@ -2279,7 +2178,7 @@ xfs_ifree(
 	* This is a temporary hack that would require a proper fix
 	* in the future.
 	*/
-	dip->di_core.di_mode = 0;
+	dip->di_mode = 0;
 
 	if (delete) {
 		xfs_ifree_cluster(ip, tp, first_ino);
@@ -2312,9 +2211,10 @@ xfs_iroot_realloc(
 	int			rec_diff,
 	int			whichfork)
 {
+	struct xfs_mount	*mp = ip->i_mount;
 	int			cur_max;
 	xfs_ifork_t		*ifp;
-	xfs_bmbt_block_t	*new_broot;
+	struct xfs_btree_block	*new_broot;
 	int			new_max;
 	size_t			new_size;
 	char			*np;
@@ -2335,8 +2235,7 @@ xfs_iroot_realloc(
 		 */
 		if (ifp->if_broot_bytes == 0) {
 			new_size = (size_t)XFS_BMAP_BROOT_SPACE_CALC(rec_diff);
-			ifp->if_broot = (xfs_bmbt_block_t*)kmem_alloc(new_size,
-								     KM_SLEEP);
+			ifp->if_broot = kmem_alloc(new_size, KM_SLEEP);
 			ifp->if_broot_bytes = (int)new_size;
 			return;
 		}
@@ -2347,18 +2246,16 @@ xfs_iroot_realloc(
 		 * location.  The records don't change location because
 		 * they are kept butted up against the btree block header.
 		 */
-		cur_max = XFS_BMAP_BROOT_MAXRECS(ifp->if_broot_bytes);
+		cur_max = xfs_bmbt_maxrecs(mp, ifp->if_broot_bytes, 0);
 		new_max = cur_max + rec_diff;
 		new_size = (size_t)XFS_BMAP_BROOT_SPACE_CALC(new_max);
-		ifp->if_broot = (xfs_bmbt_block_t *)
-		  kmem_realloc(ifp->if_broot,
-				new_size,
+		ifp->if_broot = kmem_realloc(ifp->if_broot, new_size,
 				(size_t)XFS_BMAP_BROOT_SPACE_CALC(cur_max), /* old size */
 				KM_SLEEP);
-		op = (char *)XFS_BMAP_BROOT_PTR_ADDR(ifp->if_broot, 1,
-						      ifp->if_broot_bytes);
-		np = (char *)XFS_BMAP_BROOT_PTR_ADDR(ifp->if_broot, 1,
-						      (int)new_size);
+		op = (char *)XFS_BMAP_BROOT_PTR_ADDR(mp, ifp->if_broot, 1,
+						     ifp->if_broot_bytes);
+		np = (char *)XFS_BMAP_BROOT_PTR_ADDR(mp, ifp->if_broot, 1,
+						     (int)new_size);
 		ifp->if_broot_bytes = (int)new_size;
 		ASSERT(ifp->if_broot_bytes <=
 			XFS_IFORK_SIZE(ip, whichfork) + XFS_BROOT_SIZE_ADJ);
@@ -2372,7 +2269,7 @@ xfs_iroot_realloc(
 	 * records, just get rid of the root and clear the status bit.
 	 */
 	ASSERT((ifp->if_broot != NULL) && (ifp->if_broot_bytes > 0));
-	cur_max = XFS_BMAP_BROOT_MAXRECS(ifp->if_broot_bytes);
+	cur_max = xfs_bmbt_maxrecs(mp, ifp->if_broot_bytes, 0);
 	new_max = cur_max + rec_diff;
 	ASSERT(new_max >= 0);
 	if (new_max > 0)
@@ -2380,11 +2277,11 @@ xfs_iroot_realloc(
 	else
 		new_size = 0;
 	if (new_size > 0) {
-		new_broot = (xfs_bmbt_block_t *)kmem_alloc(new_size, KM_SLEEP);
+		new_broot = kmem_alloc(new_size, KM_SLEEP);
 		/*
 		 * First copy over the btree block header.
 		 */
-		memcpy(new_broot, ifp->if_broot, sizeof(xfs_bmbt_block_t));
+		memcpy(new_broot, ifp->if_broot, XFS_BTREE_LBLOCK_LEN);
 	} else {
 		new_broot = NULL;
 		ifp->if_flags &= ~XFS_IFBROOT;
@@ -2397,18 +2294,16 @@ xfs_iroot_realloc(
 		/*
 		 * First copy the records.
 		 */
-		op = (char *)XFS_BMAP_BROOT_REC_ADDR(ifp->if_broot, 1,
-						     ifp->if_broot_bytes);
-		np = (char *)XFS_BMAP_BROOT_REC_ADDR(new_broot, 1,
-						     (int)new_size);
+		op = (char *)XFS_BMBT_REC_ADDR(mp, ifp->if_broot, 1);
+		np = (char *)XFS_BMBT_REC_ADDR(mp, new_broot, 1);
 		memcpy(np, op, new_max * (uint)sizeof(xfs_bmbt_rec_t));
 
 		/*
 		 * Then copy the pointers.
 		 */
-		op = (char *)XFS_BMAP_BROOT_PTR_ADDR(ifp->if_broot, 1,
+		op = (char *)XFS_BMAP_BROOT_PTR_ADDR(mp, ifp->if_broot, 1,
 						     ifp->if_broot_bytes);
-		np = (char *)XFS_BMAP_BROOT_PTR_ADDR(new_broot, 1,
+		np = (char *)XFS_BMAP_BROOT_PTR_ADDR(mp, new_broot, 1,
 						     (int)new_size);
 		memcpy(np, op, new_max * (uint)sizeof(xfs_dfsbno_t));
 	}
@@ -2511,64 +2406,6 @@ xfs_idata_realloc(
 	ASSERT(ifp->if_bytes <= XFS_IFORK_SIZE(ip, whichfork));
 }
 
-
-
-
-/*
- * Map inode to disk block and offset.
- *
- * mp -- the mount point structure for the current file system
- * tp -- the current transaction
- * ino -- the inode number of the inode to be located
- * imap -- this structure is filled in with the information necessary
- *	 to retrieve the given inode from disk
- * flags -- flags to pass to xfs_dilocate indicating whether or not
- *	 lookups in the inode btree were OK or not
- */
-int
-xfs_imap(
-	xfs_mount_t	*mp,
-	xfs_trans_t	*tp,
-	xfs_ino_t	ino,
-	xfs_imap_t	*imap,
-	uint		flags)
-{
-	xfs_fsblock_t	fsbno;
-	int		len;
-	int		off;
-	int		error;
-
-	fsbno = imap->im_blkno ?
-		XFS_DADDR_TO_FSB(mp, imap->im_blkno) : NULLFSBLOCK;
-	error = xfs_dilocate(mp, tp, ino, &fsbno, &len, &off, flags);
-	if (error)
-		return error;
-
-	imap->im_blkno = XFS_FSB_TO_DADDR(mp, fsbno);
-	imap->im_len = XFS_FSB_TO_BB(mp, len);
-	imap->im_agblkno = XFS_FSB_TO_AGBNO(mp, fsbno);
-	imap->im_ioffset = (ushort)off;
-	imap->im_boffset = (ushort)(off << mp->m_sb.sb_inodelog);
-
-	/*
-	 * If the inode number maps to a block outside the bounds
-	 * of the file system then return NULL rather than calling
-	 * read_buf and panicing when we get an error from the
-	 * driver.
-	 */
-	if ((imap->im_blkno + imap->im_len) >
-	    XFS_FSB_TO_BB(mp, mp->m_sb.sb_dblocks)) {
-		xfs_fs_cmn_err(CE_ALERT, mp, "xfs_imap: "
-			"(imap->im_blkno (0x%llx) + imap->im_len (0x%llx)) > "
-			" XFS_FSB_TO_BB(mp, mp->m_sb.sb_dblocks) (0x%llx)",
-			(unsigned long long) imap->im_blkno,
-			(unsigned long long) imap->im_len,
-			XFS_FSB_TO_BB(mp, mp->m_sb.sb_dblocks));
-		return EINVAL;
-	}
-	return 0;
-}
-
 void
 xfs_idestroy_fork(
 	xfs_inode_t	*ip,
@@ -2613,70 +2450,6 @@ xfs_idestroy_fork(
 }
 
 /*
- * This is called free all the memory associated with an inode.
- * It must free the inode itself and any buffers allocated for
- * if_extents/if_data and if_broot.  It must also free the lock
- * associated with the inode.
- */
-void
-xfs_idestroy(
-	xfs_inode_t	*ip)
-{
-	switch (ip->i_d.di_mode & S_IFMT) {
-	case S_IFREG:
-	case S_IFDIR:
-	case S_IFLNK:
-		xfs_idestroy_fork(ip, XFS_DATA_FORK);
-		break;
-	}
-	if (ip->i_afp)
-		xfs_idestroy_fork(ip, XFS_ATTR_FORK);
-	mrfree(&ip->i_lock);
-	mrfree(&ip->i_iolock);
-
-#ifdef XFS_INODE_TRACE
-	ktrace_free(ip->i_trace);
-#endif
-#ifdef XFS_BMAP_TRACE
-	ktrace_free(ip->i_xtrace);
-#endif
-#ifdef XFS_BMBT_TRACE
-	ktrace_free(ip->i_btrace);
-#endif
-#ifdef XFS_RW_TRACE
-	ktrace_free(ip->i_rwtrace);
-#endif
-#ifdef XFS_ILOCK_TRACE
-	ktrace_free(ip->i_lock_trace);
-#endif
-#ifdef XFS_DIR2_TRACE
-	ktrace_free(ip->i_dir_trace);
-#endif
-	if (ip->i_itemp) {
-		/*
-		 * Only if we are shutting down the fs will we see an
-		 * inode still in the AIL. If it is there, we should remove
-		 * it to prevent a use-after-free from occurring.
-		 */
-		xfs_mount_t	*mp = ip->i_mount;
-		xfs_log_item_t	*lip = &ip->i_itemp->ili_item;
-
-		ASSERT(((lip->li_flags & XFS_LI_IN_AIL) == 0) ||
-				       XFS_FORCED_SHUTDOWN(ip->i_mount));
-		if (lip->li_flags & XFS_LI_IN_AIL) {
-			spin_lock(&mp->m_ail_lock);
-			if (lip->li_flags & XFS_LI_IN_AIL)
-				xfs_trans_delete_ail(mp, lip);
-			else
-				spin_unlock(&mp->m_ail_lock);
-		}
-		xfs_inode_item_destroy(ip);
-	}
-	kmem_zone_free(xfs_inode_zone, ip);
-}
-
-
-/*
  * Increment the pin count of the given buffer.
  * This value is protected by ipinlock spinlock in the mount structure.
  */
@@ -2880,7 +2653,7 @@ xfs_iflush_fork(
 			ASSERT(ifp->if_broot_bytes <=
 			       (XFS_IFORK_SIZE(ip, whichfork) +
 				XFS_BROOT_SIZE_ADJ));
-			xfs_bmbt_to_bmdr(ifp->if_broot, ifp->if_broot_bytes,
+			xfs_bmbt_to_bmdr(mp, ifp->if_broot, ifp->if_broot_bytes,
 				(xfs_bmdr_block_t *)cp,
 				XFS_DFORK_SIZE(dip, mp, whichfork));
 		}
@@ -2889,15 +2662,16 @@ xfs_iflush_fork(
 	case XFS_DINODE_FMT_DEV:
 		if (iip->ili_format.ilf_fields & XFS_ILOG_DEV) {
 			ASSERT(whichfork == XFS_DATA_FORK);
-			dip->di_u.di_dev = cpu_to_be32(ip->i_df.if_u2.if_rdev);
+			xfs_dinode_put_rdev(dip, ip->i_df.if_u2.if_rdev);
 		}
 		break;
 
 	case XFS_DINODE_FMT_UUID:
 		if (iip->ili_format.ilf_fields & XFS_ILOG_UUID) {
 			ASSERT(whichfork == XFS_DATA_FORK);
-			memcpy(&dip->di_u.di_muuid, &ip->i_df.if_u2.if_uuid,
-				sizeof(uuid_t));
+			memcpy(XFS_DFORK_DPTR(dip),
+			       &ip->i_df.if_u2.if_uuid,
+			       sizeof(uuid_t));
 		}
 		break;
 
@@ -3172,7 +2946,7 @@ xfs_iflush(
 	/*
 	 * Get the buffer containing the on-disk inode.
 	 */
-	error = xfs_itobp(mp, NULL, ip, &dip, &bp, 0, 0,
+	error = xfs_itobp(mp, NULL, ip, &dip, &bp,
 				noblock ? XFS_BUF_TRYLOCK : XFS_BUF_LOCK);
 	if (error || !bp) {
 		xfs_ifunlock(ip);
@@ -3253,7 +3027,7 @@ xfs_iflush_int(
 	}
 
 	/* set *dip = inode's place in the buffer */
-	dip = (xfs_dinode_t *)xfs_buf_offset(bp, ip->i_boffset);
+	dip = (xfs_dinode_t *)xfs_buf_offset(bp, ip->i_imap.im_boffset);
 
 	/*
 	 * Clear i_update_core before copying out the data.
@@ -3275,11 +3049,11 @@ xfs_iflush_int(
 	 */
 	xfs_synchronize_atime(ip);
 
-	if (XFS_TEST_ERROR(be16_to_cpu(dip->di_core.di_magic) != XFS_DINODE_MAGIC,
+	if (XFS_TEST_ERROR(be16_to_cpu(dip->di_magic) != XFS_DINODE_MAGIC,
 			       mp, XFS_ERRTAG_IFLUSH_1, XFS_RANDOM_IFLUSH_1)) {
 		xfs_cmn_err(XFS_PTAG_IFLUSH, CE_ALERT, mp,
 		    "xfs_iflush: Bad inode %Lu magic number 0x%x, ptr 0x%p",
-			ip->i_ino, be16_to_cpu(dip->di_core.di_magic), dip);
+			ip->i_ino, be16_to_cpu(dip->di_magic), dip);
 		goto corrupt_out;
 	}
 	if (XFS_TEST_ERROR(ip->i_d.di_magic != XFS_DINODE_MAGIC,
@@ -3342,7 +3116,7 @@ xfs_iflush_int(
 	 * because if the inode is dirty at all the core must
 	 * be.
 	 */
-	xfs_dinode_to_disk(&dip->di_core, &ip->i_d);
+	xfs_dinode_to_disk(dip, &ip->i_d);
 
 	/* Wrap, we never let the log put out DI_MAX_FLUSH */
 	if (ip->i_d.di_flushiter == DI_MAX_FLUSH)
@@ -3354,28 +3128,27 @@ xfs_iflush_int(
 	 * convert back to the old inode format.  If the superblock version
 	 * has been updated, then make the conversion permanent.
 	 */
-	ASSERT(ip->i_d.di_version == XFS_DINODE_VERSION_1 ||
-	       xfs_sb_version_hasnlink(&mp->m_sb));
-	if (ip->i_d.di_version == XFS_DINODE_VERSION_1) {
+	ASSERT(ip->i_d.di_version == 1 || xfs_sb_version_hasnlink(&mp->m_sb));
+	if (ip->i_d.di_version == 1) {
 		if (!xfs_sb_version_hasnlink(&mp->m_sb)) {
 			/*
 			 * Convert it back.
 			 */
 			ASSERT(ip->i_d.di_nlink <= XFS_MAXLINK_1);
-			dip->di_core.di_onlink = cpu_to_be16(ip->i_d.di_nlink);
+			dip->di_onlink = cpu_to_be16(ip->i_d.di_nlink);
 		} else {
 			/*
 			 * The superblock version has already been bumped,
 			 * so just make the conversion to the new inode
 			 * format permanent.
 			 */
-			ip->i_d.di_version = XFS_DINODE_VERSION_2;
-			dip->di_core.di_version =  XFS_DINODE_VERSION_2;
+			ip->i_d.di_version = 2;
+			dip->di_version = 2;
 			ip->i_d.di_onlink = 0;
-			dip->di_core.di_onlink = 0;
+			dip->di_onlink = 0;
 			memset(&(ip->i_d.di_pad[0]), 0, sizeof(ip->i_d.di_pad));
-			memset(&(dip->di_core.di_pad[0]), 0,
-			      sizeof(dip->di_core.di_pad));
+			memset(&(dip->di_pad[0]), 0,
+			      sizeof(dip->di_pad));
 			ASSERT(ip->i_d.di_projid == 0);
 		}
 	}
@@ -3418,10 +3191,8 @@ xfs_iflush_int(
 		iip->ili_format.ilf_fields = 0;
 		iip->ili_logged = 1;
 
-		ASSERT(sizeof(xfs_lsn_t) == 8);	/* don't lock if it shrinks */
-		spin_lock(&mp->m_ail_lock);
-		iip->ili_flush_lsn = iip->ili_item.li_lsn;
-		spin_unlock(&mp->m_ail_lock);
+		xfs_trans_ail_copy_lsn(mp->m_ail, &iip->ili_flush_lsn,
+					&iip->ili_item.li_lsn);
 
 		/*
 		 * Attach the function xfs_iflush_done to the inode's
@@ -3459,41 +3230,6 @@ corrupt_out:
 }
 
 
-/*
- * Flush all inactive inodes in mp.
- */
-void
-xfs_iflush_all(
-	xfs_mount_t	*mp)
-{
-	xfs_inode_t	*ip;
-
- again:
-	XFS_MOUNT_ILOCK(mp);
-	ip = mp->m_inodes;
-	if (ip == NULL)
-		goto out;
-
-	do {
-		/* Make sure we skip markers inserted by sync */
-		if (ip->i_mount == NULL) {
-			ip = ip->i_mnext;
-			continue;
-		}
-
-		if (!VFS_I(ip)) {
-			XFS_MOUNT_IUNLOCK(mp);
-			xfs_finish_reclaim(ip, 0, XFS_IFLUSH_ASYNC);
-			goto again;
-		}
-
-		ASSERT(vn_count(VFS_I(ip)) == 0);
-
-		ip = ip->i_mnext;
-	} while (ip != mp->m_inodes);
- out:
-	XFS_MOUNT_IUNLOCK(mp);
-}
 
 #ifdef XFS_ILOCK_TRACE
 ktrace_t	*xfs_ilock_trace_buf;
diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h
index 1420c49674d7..558253e6fb43 100644
--- a/fs/xfs/xfs_inode.h
+++ b/fs/xfs/xfs_inode.h
@@ -19,8 +19,7 @@
 #define	__XFS_INODE_H__
 
 struct xfs_dinode;
-struct xfs_dinode_core;
-
+struct xfs_inode;
 
 /*
  * Fork identifiers.
@@ -63,7 +62,7 @@ typedef struct xfs_ext_irec {
 typedef struct xfs_ifork {
 	int			if_bytes;	/* bytes in if_u1 */
 	int			if_real_bytes;	/* bytes allocated in if_u1 */
-	xfs_bmbt_block_t	*if_broot;	/* file's incore btree root */
+	struct xfs_btree_block	*if_broot;	/* file's incore btree root */
 	short			if_broot_bytes;	/* bytes allocated for root */
 	unsigned char		if_flags;	/* per-fork flags */
 	unsigned char		if_ext_max;	/* max # of extent records */
@@ -84,52 +83,14 @@ typedef struct xfs_ifork {
 } xfs_ifork_t;
 
 /*
- * Flags for xfs_ichgtime().
- */
-#define	XFS_ICHGTIME_MOD	0x1	/* data fork modification timestamp */
-#define	XFS_ICHGTIME_CHG	0x2	/* inode field change timestamp */
-
-/*
- * Per-fork incore inode flags.
- */
-#define	XFS_IFINLINE	0x01	/* Inline data is read in */
-#define	XFS_IFEXTENTS	0x02	/* All extent pointers are read in */
-#define	XFS_IFBROOT	0x04	/* i_broot points to the bmap b-tree root */
-#define	XFS_IFEXTIREC	0x08	/* Indirection array of extent blocks */
-
-/*
- * Flags for xfs_itobp(), xfs_imap() and xfs_dilocate().
+ * Inode location information.  Stored in the inode and passed to
+ * xfs_imap_to_bp() to get a buffer and dinode for a given inode.
  */
-#define XFS_IMAP_LOOKUP		0x1
-#define XFS_IMAP_BULKSTAT	0x2
-
-#ifdef __KERNEL__
-struct bhv_desc;
-struct cred;
-struct ktrace;
-struct xfs_buf;
-struct xfs_bmap_free;
-struct xfs_bmbt_irec;
-struct xfs_bmbt_block;
-struct xfs_inode;
-struct xfs_inode_log_item;
-struct xfs_mount;
-struct xfs_trans;
-struct xfs_dquot;
-
-#if defined(XFS_ILOCK_TRACE)
-#define XFS_ILOCK_KTRACE_SIZE	32
-extern ktrace_t *xfs_ilock_trace_buf;
-extern void xfs_ilock_trace(struct xfs_inode *, int, unsigned int, inst_t *);
-#else
-#define	xfs_ilock_trace(i,n,f,ra)
-#endif
-
-typedef struct dm_attrs_s {
-	__uint32_t	da_dmevmask;	/* DMIG event mask */
-	__uint16_t	da_dmstate;	/* DMIG state info */
-	__uint16_t	da_pad;		/* DMIG extra padding */
-} dm_attrs_t;
+struct xfs_imap {
+	xfs_daddr_t	im_blkno;	/* starting BB of inode chunk */
+	ushort		im_len;		/* length in BBs of inode chunk */
+	ushort		im_boffset;	/* inode offset in block in bytes */
+};
 
 /*
  * This is the xfs in-core inode structure.
@@ -160,7 +121,7 @@ typedef struct xfs_ictimestamp {
 } xfs_ictimestamp_t;
 
 /*
- * NOTE:  This structure must be kept identical to struct xfs_dinode_core
+ * NOTE:  This structure must be kept identical to struct xfs_dinode
  * 	  in xfs_dinode.h except for the endianess annotations.
  */
 typedef struct xfs_icdinode {
@@ -191,27 +152,98 @@ typedef struct xfs_icdinode {
 	__uint32_t	di_gen;		/* generation number */
 } xfs_icdinode_t;
 
-typedef struct {
-	struct xfs_inode	*ip_mnext;	/* next inode in mount list */
-	struct xfs_inode	*ip_mprev;	/* ptr to prev inode */
-	struct xfs_mount	*ip_mount;	/* fs mount struct ptr */
-} xfs_iptr_t;
+/*
+ * Flags for xfs_ichgtime().
+ */
+#define	XFS_ICHGTIME_MOD	0x1	/* data fork modification timestamp */
+#define	XFS_ICHGTIME_CHG	0x2	/* inode field change timestamp */
+
+/*
+ * Per-fork incore inode flags.
+ */
+#define	XFS_IFINLINE	0x01	/* Inline data is read in */
+#define	XFS_IFEXTENTS	0x02	/* All extent pointers are read in */
+#define	XFS_IFBROOT	0x04	/* i_broot points to the bmap b-tree root */
+#define	XFS_IFEXTIREC	0x08	/* Indirection array of extent blocks */
+
+/*
+ * Fork handling.
+ */
+
+#define XFS_IFORK_Q(ip)			((ip)->i_d.di_forkoff != 0)
+#define XFS_IFORK_BOFF(ip)		((int)((ip)->i_d.di_forkoff << 3))
+
+#define XFS_IFORK_PTR(ip,w)		\
+	((w) == XFS_DATA_FORK ? \
+		&(ip)->i_df : \
+		(ip)->i_afp)
+#define XFS_IFORK_DSIZE(ip) \
+	(XFS_IFORK_Q(ip) ? \
+		XFS_IFORK_BOFF(ip) : \
+		XFS_LITINO((ip)->i_mount))
+#define XFS_IFORK_ASIZE(ip) \
+	(XFS_IFORK_Q(ip) ? \
+		XFS_LITINO((ip)->i_mount) - XFS_IFORK_BOFF(ip) : \
+		0)
+#define XFS_IFORK_SIZE(ip,w) \
+	((w) == XFS_DATA_FORK ? \
+		XFS_IFORK_DSIZE(ip) : \
+		XFS_IFORK_ASIZE(ip))
+#define XFS_IFORK_FORMAT(ip,w) \
+	((w) == XFS_DATA_FORK ? \
+		(ip)->i_d.di_format : \
+		(ip)->i_d.di_aformat)
+#define XFS_IFORK_FMT_SET(ip,w,n) \
+	((w) == XFS_DATA_FORK ? \
+		((ip)->i_d.di_format = (n)) : \
+		((ip)->i_d.di_aformat = (n)))
+#define XFS_IFORK_NEXTENTS(ip,w) \
+	((w) == XFS_DATA_FORK ? \
+		(ip)->i_d.di_nextents : \
+		(ip)->i_d.di_anextents)
+#define XFS_IFORK_NEXT_SET(ip,w,n) \
+	((w) == XFS_DATA_FORK ? \
+		((ip)->i_d.di_nextents = (n)) : \
+		((ip)->i_d.di_anextents = (n)))
+
+
+
+#ifdef __KERNEL__
+
+struct bhv_desc;
+struct cred;
+struct ktrace;
+struct xfs_buf;
+struct xfs_bmap_free;
+struct xfs_bmbt_irec;
+struct xfs_inode_log_item;
+struct xfs_mount;
+struct xfs_trans;
+struct xfs_dquot;
+
+#if defined(XFS_ILOCK_TRACE)
+#define XFS_ILOCK_KTRACE_SIZE	32
+extern ktrace_t *xfs_ilock_trace_buf;
+extern void xfs_ilock_trace(struct xfs_inode *, int, unsigned int, inst_t *);
+#else
+#define	xfs_ilock_trace(i,n,f,ra)
+#endif
+
+typedef struct dm_attrs_s {
+	__uint32_t	da_dmevmask;	/* DMIG event mask */
+	__uint16_t	da_dmstate;	/* DMIG state info */
+	__uint16_t	da_pad;		/* DMIG extra padding */
+} dm_attrs_t;
 
 typedef struct xfs_inode {
 	/* Inode linking and identification information. */
-	struct xfs_inode	*i_mnext;	/* next inode in mount list */
-	struct xfs_inode	*i_mprev;	/* ptr to prev inode */
 	struct xfs_mount	*i_mount;	/* fs mount struct ptr */
-	struct list_head	i_reclaim;	/* reclaim list */
-	struct inode		*i_vnode;	/* vnode backpointer */
 	struct xfs_dquot	*i_udquot;	/* user dquot */
 	struct xfs_dquot	*i_gdquot;	/* group dquot */
 
 	/* Inode location stuff */
 	xfs_ino_t		i_ino;		/* inode number (agno/agino)*/
-	xfs_daddr_t		i_blkno;	/* blkno of inode buffer */
-	ushort			i_len;		/* len of inode buffer */
-	ushort			i_boffset;	/* off of inode in buffer */
+	struct xfs_imap		i_imap;		/* location for xfs_imap() */
 
 	/* Extent information. */
 	xfs_ifork_t		*i_afp;		/* attribute fork pointer */
@@ -230,7 +262,6 @@ typedef struct xfs_inode {
 	unsigned short		i_flags;	/* see defined flags below */
 	unsigned char		i_update_core;	/* timestamps/size is dirty */
 	unsigned char		i_update_size;	/* di_size field is dirty */
-	unsigned int		i_gen;		/* generation count */
 	unsigned int		i_delayed_blks;	/* count of delay alloc blks */
 
 	xfs_icdinode_t		i_d;		/* most of ondisk inode */
@@ -238,6 +269,10 @@ typedef struct xfs_inode {
 	xfs_fsize_t		i_size;		/* in-memory size */
 	xfs_fsize_t		i_new_size;	/* size when write completes */
 	atomic_t		i_iocount;	/* outstanding I/O count */
+
+	/* VFS inode */
+	struct inode		i_vnode;	/* embedded VFS inode */
+
 	/* Trace buffers per inode. */
 #ifdef XFS_INODE_TRACE
 	struct ktrace		*i_trace;	/* general inode trace */
@@ -245,7 +280,7 @@ typedef struct xfs_inode {
 #ifdef XFS_BMAP_TRACE
 	struct ktrace		*i_xtrace;	/* inode extent list trace */
 #endif
-#ifdef XFS_BMBT_TRACE
+#ifdef XFS_BTREE_TRACE
 	struct ktrace		*i_btrace;	/* inode bmap btree trace */
 #endif
 #ifdef XFS_RW_TRACE
@@ -265,13 +300,30 @@ typedef struct xfs_inode {
 /* Convert from vfs inode to xfs inode */
 static inline struct xfs_inode *XFS_I(struct inode *inode)
 {
-	return (struct xfs_inode *)inode->i_private;
+	return container_of(inode, struct xfs_inode, i_vnode);
 }
 
 /* convert from xfs inode to vfs inode */
 static inline struct inode *VFS_I(struct xfs_inode *ip)
 {
-	return (struct inode *)ip->i_vnode;
+	return &ip->i_vnode;
+}
+
+/*
+ * Get rid of a partially initialized inode.
+ *
+ * We have to go through destroy_inode to make sure allocations
+ * from init_inode_always like the security data are undone.
+ *
+ * We mark the inode bad so that it takes the short cut in
+ * the reclaim path instead of going through the flush path
+ * which doesn't make sense for an inode that has never seen the
+ * light of day.
+ */
+static inline void xfs_destroy_inode(struct xfs_inode *ip)
+{
+	make_bad_inode(VFS_I(ip));
+	return destroy_inode(VFS_I(ip));
 }
 
 /*
@@ -327,65 +379,36 @@ xfs_iflags_test_and_clear(xfs_inode_t *ip, unsigned short flags)
 	spin_unlock(&ip->i_flags_lock);
 	return ret;
 }
-#endif	/* __KERNEL__ */
-
 
 /*
- * Fork handling.
+ * Manage the i_flush queue embedded in the inode.  This completion
+ * queue synchronizes processes attempting to flush the in-core
+ * inode back to disk.
  */
+static inline void xfs_iflock(xfs_inode_t *ip)
+{
+	wait_for_completion(&ip->i_flush);
+}
 
-#define XFS_IFORK_Q(ip)			((ip)->i_d.di_forkoff != 0)
-#define XFS_IFORK_BOFF(ip)		((int)((ip)->i_d.di_forkoff << 3))
-
-#define XFS_IFORK_PTR(ip,w)		\
-	((w) == XFS_DATA_FORK ? \
-		&(ip)->i_df : \
-		(ip)->i_afp)
-#define XFS_IFORK_DSIZE(ip) \
-	(XFS_IFORK_Q(ip) ? \
-		XFS_IFORK_BOFF(ip) : \
-		XFS_LITINO((ip)->i_mount))
-#define XFS_IFORK_ASIZE(ip) \
-	(XFS_IFORK_Q(ip) ? \
-		XFS_LITINO((ip)->i_mount) - XFS_IFORK_BOFF(ip) : \
-		0)
-#define XFS_IFORK_SIZE(ip,w) \
-	((w) == XFS_DATA_FORK ? \
-		XFS_IFORK_DSIZE(ip) : \
-		XFS_IFORK_ASIZE(ip))
-#define XFS_IFORK_FORMAT(ip,w) \
-	((w) == XFS_DATA_FORK ? \
-		(ip)->i_d.di_format : \
-		(ip)->i_d.di_aformat)
-#define XFS_IFORK_FMT_SET(ip,w,n) \
-	((w) == XFS_DATA_FORK ? \
-		((ip)->i_d.di_format = (n)) : \
-		((ip)->i_d.di_aformat = (n)))
-#define XFS_IFORK_NEXTENTS(ip,w) \
-	((w) == XFS_DATA_FORK ? \
-		(ip)->i_d.di_nextents : \
-		(ip)->i_d.di_anextents)
-#define XFS_IFORK_NEXT_SET(ip,w,n) \
-	((w) == XFS_DATA_FORK ? \
-		((ip)->i_d.di_nextents = (n)) : \
-		((ip)->i_d.di_anextents = (n)))
+static inline int xfs_iflock_nowait(xfs_inode_t *ip)
+{
+	return try_wait_for_completion(&ip->i_flush);
+}
 
-#ifdef __KERNEL__
+static inline void xfs_ifunlock(xfs_inode_t *ip)
+{
+	complete(&ip->i_flush);
+}
 
 /*
  * In-core inode flags.
  */
-#define XFS_IGRIO	0x0001  /* inode used for guaranteed rate i/o */
-#define XFS_IUIOSZ	0x0002  /* inode i/o sizes have been explicitly set */
-#define XFS_IQUIESCE    0x0004  /* we have started quiescing for this inode */
-#define XFS_IRECLAIM    0x0008  /* we have started reclaiming this inode    */
-#define XFS_ISTALE	0x0010	/* inode has been staled */
-#define XFS_IRECLAIMABLE 0x0020 /* inode can be reclaimed */
-#define XFS_INEW	0x0040
-#define XFS_IFILESTREAM	0x0080	/* inode is in a filestream directory */
-#define XFS_IMODIFIED	0x0100	/* XFS inode state possibly differs */
-				/* to the Linux inode state. */
-#define XFS_ITRUNCATED	0x0200	/* truncated down so flush-on-close */
+#define XFS_IRECLAIM    0x0001  /* we have started reclaiming this inode    */
+#define XFS_ISTALE	0x0002	/* inode has been staled */
+#define XFS_IRECLAIMABLE 0x0004 /* inode can be reclaimed */
+#define XFS_INEW	0x0008	/* inode has just been allocated */
+#define XFS_IFILESTREAM	0x0010	/* inode is in a filestream directory */
+#define XFS_ITRUNCATED	0x0020	/* truncated down so flush-on-close */
 
 /*
  * Flags for inode locking.
@@ -468,8 +491,6 @@ xfs_iflags_test_and_clear(xfs_inode_t *ip, unsigned short flags)
 /*
  * xfs_iget.c prototypes.
  */
-void		xfs_ihash_init(struct xfs_mount *);
-void		xfs_ihash_free(struct xfs_mount *);
 xfs_inode_t	*xfs_inode_incore(struct xfs_mount *, xfs_ino_t,
 				  struct xfs_trans *);
 int		xfs_iget(struct xfs_mount *, struct xfs_trans *, xfs_ino_t,
@@ -484,25 +505,15 @@ int		xfs_isilocked(xfs_inode_t *, uint);
 uint		xfs_ilock_map_shared(xfs_inode_t *);
 void		xfs_iunlock_map_shared(xfs_inode_t *, uint);
 void		xfs_ireclaim(xfs_inode_t *);
-int		xfs_finish_reclaim(xfs_inode_t *, int, int);
-int		xfs_finish_reclaim_all(struct xfs_mount *, int);
 
 /*
  * xfs_inode.c prototypes.
  */
-int		xfs_itobp(struct xfs_mount *, struct xfs_trans *,
-			  xfs_inode_t *, struct xfs_dinode **, struct xfs_buf **,
-			  xfs_daddr_t, uint, uint);
-int		xfs_iread(struct xfs_mount *, struct xfs_trans *, xfs_ino_t,
-			  xfs_inode_t **, xfs_daddr_t, uint);
-int		xfs_iread_extents(struct xfs_trans *, xfs_inode_t *, int);
+int		xfs_iread(struct xfs_mount *, struct xfs_trans *,
+			  struct xfs_inode *, xfs_daddr_t, uint);
 int		xfs_ialloc(struct xfs_trans *, xfs_inode_t *, mode_t,
 			   xfs_nlink_t, xfs_dev_t, struct cred *, xfs_prid_t,
 			   int, struct xfs_buf **, boolean_t *, xfs_inode_t **);
-void		xfs_dinode_from_disk(struct xfs_icdinode *,
-				     struct xfs_dinode_core *);
-void		xfs_dinode_to_disk(struct xfs_dinode_core *,
-				   struct xfs_icdinode *);
 
 uint		xfs_ip2xflags(struct xfs_inode *);
 uint		xfs_dic2xflags(struct xfs_dinode *);
@@ -513,17 +524,10 @@ int		xfs_itruncate_finish(struct xfs_trans **, xfs_inode_t *,
 				     xfs_fsize_t, int, int);
 int		xfs_iunlink(struct xfs_trans *, xfs_inode_t *);
 
-void		xfs_idestroy_fork(xfs_inode_t *, int);
-void		xfs_idestroy(xfs_inode_t *);
-void		xfs_idata_realloc(xfs_inode_t *, int, int);
-void		xfs_iextract(xfs_inode_t *);
 void		xfs_iext_realloc(xfs_inode_t *, int, int);
-void		xfs_iroot_realloc(xfs_inode_t *, int, int);
 void		xfs_ipin(xfs_inode_t *);
 void		xfs_iunpin(xfs_inode_t *);
-int		xfs_iextents_copy(xfs_inode_t *, xfs_bmbt_rec_t *, int);
 int		xfs_iflush(xfs_inode_t *, uint);
-void		xfs_iflush_all(struct xfs_mount *);
 void		xfs_ichgtime(xfs_inode_t *, int);
 xfs_fsize_t	xfs_file_last_byte(xfs_inode_t *);
 void		xfs_lock_inodes(xfs_inode_t **, int, uint);
@@ -532,6 +536,69 @@ void		xfs_lock_two_inodes(xfs_inode_t *, xfs_inode_t *, uint);
 void		xfs_synchronize_atime(xfs_inode_t *);
 void		xfs_mark_inode_dirty_sync(xfs_inode_t *);
 
+#if defined(XFS_INODE_TRACE)
+
+#define	INODE_TRACE_SIZE	16		/* number of trace entries */
+#define	INODE_KTRACE_ENTRY	1
+#define	INODE_KTRACE_EXIT	2
+#define	INODE_KTRACE_HOLD	3
+#define	INODE_KTRACE_REF	4
+#define	INODE_KTRACE_RELE	5
+
+extern void _xfs_itrace_entry(struct xfs_inode *, const char *, inst_t *);
+extern void _xfs_itrace_exit(struct xfs_inode *, const char *, inst_t *);
+extern void xfs_itrace_hold(struct xfs_inode *, char *, int, inst_t *);
+extern void _xfs_itrace_ref(struct xfs_inode *, char *, int, inst_t *);
+extern void xfs_itrace_rele(struct xfs_inode *, char *, int, inst_t *);
+#define xfs_itrace_entry(ip)	\
+	_xfs_itrace_entry(ip, __func__, (inst_t *)__return_address)
+#define xfs_itrace_exit(ip)	\
+	_xfs_itrace_exit(ip, __func__, (inst_t *)__return_address)
+#define xfs_itrace_exit_tag(ip, tag)	\
+	_xfs_itrace_exit(ip, tag, (inst_t *)__return_address)
+#define xfs_itrace_ref(ip)	\
+	_xfs_itrace_ref(ip, __FILE__, __LINE__, (inst_t *)__return_address)
+
+#else
+#define	xfs_itrace_entry(a)
+#define	xfs_itrace_exit(a)
+#define	xfs_itrace_exit_tag(a, b)
+#define	xfs_itrace_hold(a, b, c, d)
+#define	xfs_itrace_ref(a)
+#define	xfs_itrace_rele(a, b, c, d)
+#endif
+
+#define IHOLD(ip) \
+do { \
+	ASSERT(atomic_read(&VFS_I(ip)->i_count) > 0) ; \
+	atomic_inc(&(VFS_I(ip)->i_count)); \
+	xfs_itrace_hold((ip), __FILE__, __LINE__, (inst_t *)__return_address); \
+} while (0)
+
+#define IRELE(ip) \
+do { \
+	xfs_itrace_rele((ip), __FILE__, __LINE__, (inst_t *)__return_address); \
+	iput(VFS_I(ip)); \
+} while (0)
+
+#endif /* __KERNEL__ */
+
+int		xfs_inotobp(struct xfs_mount *, struct xfs_trans *,
+			    xfs_ino_t, struct xfs_dinode **,
+			    struct xfs_buf **, int *, uint);
+int		xfs_itobp(struct xfs_mount *, struct xfs_trans *,
+			  struct xfs_inode *, struct xfs_dinode **,
+			  struct xfs_buf **, uint);
+void		xfs_dinode_from_disk(struct xfs_icdinode *,
+				     struct xfs_dinode *);
+void		xfs_dinode_to_disk(struct xfs_dinode *,
+				   struct xfs_icdinode *);
+void		xfs_idestroy_fork(struct xfs_inode *, int);
+void		xfs_idata_realloc(struct xfs_inode *, int, int);
+void		xfs_iroot_realloc(struct xfs_inode *, int, int);
+int		xfs_iread_extents(struct xfs_trans *, struct xfs_inode *, int);
+int		xfs_iextents_copy(struct xfs_inode *, xfs_bmbt_rec_t *, int);
+
 xfs_bmbt_rec_host_t *xfs_iext_get_ext(xfs_ifork_t *, xfs_extnum_t);
 void		xfs_iext_insert(xfs_ifork_t *, xfs_extnum_t, xfs_extnum_t,
 				xfs_bmbt_irec_t *);
@@ -561,7 +628,8 @@ void		xfs_iext_irec_update_extoffs(xfs_ifork_t *, int, int);
 #define xfs_ipincount(ip)	((unsigned int) atomic_read(&ip->i_pincount))
 
 #ifdef DEBUG
-void		xfs_isize_check(struct xfs_mount *, xfs_inode_t *, xfs_fsize_t);
+void		xfs_isize_check(struct xfs_mount *, struct xfs_inode *,
+				xfs_fsize_t);
 #else	/* DEBUG */
 #define xfs_isize_check(mp, ip, isize)
 #endif	/* DEBUG */
@@ -576,26 +644,4 @@ extern struct kmem_zone	*xfs_ifork_zone;
 extern struct kmem_zone	*xfs_inode_zone;
 extern struct kmem_zone	*xfs_ili_zone;
 
-/*
- * Manage the i_flush queue embedded in the inode.  This completion
- * queue synchronizes processes attempting to flush the in-core
- * inode back to disk.
- */
-static inline void xfs_iflock(xfs_inode_t *ip)
-{
-	wait_for_completion(&ip->i_flush);
-}
-
-static inline int xfs_iflock_nowait(xfs_inode_t *ip)
-{
-	return try_wait_for_completion(&ip->i_flush);
-}
-
-static inline void xfs_ifunlock(xfs_inode_t *ip)
-{
-	complete(&ip->i_flush);
-}
-
-#endif	/* __KERNEL__ */
-
 #endif	/* __XFS_INODE_H__ */
diff --git a/fs/xfs/xfs_inode_item.c b/fs/xfs/xfs_inode_item.c
index 97c7452e2620..977c4aec587e 100644
--- a/fs/xfs/xfs_inode_item.c
+++ b/fs/xfs/xfs_inode_item.c
@@ -281,7 +281,7 @@ xfs_inode_item_format(
 	xfs_mark_inode_dirty_sync(ip);
 
 	vecp->i_addr = (xfs_caddr_t)&ip->i_d;
-	vecp->i_len  = sizeof(xfs_dinode_core_t);
+	vecp->i_len  = sizeof(struct xfs_icdinode);
 	XLOG_VEC_SET_TYPE(vecp, XLOG_REG_TYPE_ICORE);
 	vecp++;
 	nvecs++;
@@ -296,9 +296,8 @@ xfs_inode_item_format(
 	 * has a new version number, then we don't bother converting back.
 	 */
 	mp = ip->i_mount;
-	ASSERT(ip->i_d.di_version == XFS_DINODE_VERSION_1 ||
-	       xfs_sb_version_hasnlink(&mp->m_sb));
-	if (ip->i_d.di_version == XFS_DINODE_VERSION_1) {
+	ASSERT(ip->i_d.di_version == 1 || xfs_sb_version_hasnlink(&mp->m_sb));
+	if (ip->i_d.di_version == 1) {
 		if (!xfs_sb_version_hasnlink(&mp->m_sb)) {
 			/*
 			 * Convert it back.
@@ -311,7 +310,7 @@ xfs_inode_item_format(
 			 * so just make the conversion to the new inode
 			 * format permanent.
 			 */
-			ip->i_d.di_version = XFS_DINODE_VERSION_2;
+			ip->i_d.di_version = 2;
 			ip->i_d.di_onlink = 0;
 			memset(&(ip->i_d.di_pad[0]), 0, sizeof(ip->i_d.di_pad));
 		}
@@ -932,6 +931,7 @@ xfs_inode_item_init(
 	iip->ili_item.li_type = XFS_LI_INODE;
 	iip->ili_item.li_ops = &xfs_inode_item_ops;
 	iip->ili_item.li_mountp = mp;
+	iip->ili_item.li_ailp = mp->m_ail;
 	iip->ili_inode = ip;
 
 	/*
@@ -942,9 +942,9 @@ xfs_inode_item_init(
 
 	iip->ili_format.ilf_type = XFS_LI_INODE;
 	iip->ili_format.ilf_ino = ip->i_ino;
-	iip->ili_format.ilf_blkno = ip->i_blkno;
-	iip->ili_format.ilf_len = ip->i_len;
-	iip->ili_format.ilf_boffset = ip->i_boffset;
+	iip->ili_format.ilf_blkno = ip->i_imap.im_blkno;
+	iip->ili_format.ilf_len = ip->i_imap.im_len;
+	iip->ili_format.ilf_boffset = ip->i_imap.im_boffset;
 }
 
 /*
@@ -976,9 +976,8 @@ xfs_iflush_done(
 	xfs_buf_t		*bp,
 	xfs_inode_log_item_t	*iip)
 {
-	xfs_inode_t	*ip;
-
-	ip = iip->ili_inode;
+	xfs_inode_t		*ip = iip->ili_inode;
+	struct xfs_ail		*ailp = iip->ili_item.li_ailp;
 
 	/*
 	 * We only want to pull the item from the AIL if it is
@@ -991,15 +990,12 @@ xfs_iflush_done(
 	 */
 	if (iip->ili_logged &&
 	    (iip->ili_item.li_lsn == iip->ili_flush_lsn)) {
-		spin_lock(&ip->i_mount->m_ail_lock);
+		spin_lock(&ailp->xa_lock);
 		if (iip->ili_item.li_lsn == iip->ili_flush_lsn) {
-			/*
-			 * xfs_trans_delete_ail() drops the AIL lock.
-			 */
-			xfs_trans_delete_ail(ip->i_mount,
-					     (xfs_log_item_t*)iip);
+			/* xfs_trans_ail_delete() drops the AIL lock. */
+			xfs_trans_ail_delete(ailp, (xfs_log_item_t*)iip);
 		} else {
-			spin_unlock(&ip->i_mount->m_ail_lock);
+			spin_unlock(&ailp->xa_lock);
 		}
 	}
 
@@ -1031,21 +1027,20 @@ void
 xfs_iflush_abort(
 	xfs_inode_t		*ip)
 {
-	xfs_inode_log_item_t	*iip;
+	xfs_inode_log_item_t	*iip = ip->i_itemp;
 	xfs_mount_t		*mp;
 
 	iip = ip->i_itemp;
 	mp = ip->i_mount;
 	if (iip) {
+		struct xfs_ail	*ailp = iip->ili_item.li_ailp;
 		if (iip->ili_item.li_flags & XFS_LI_IN_AIL) {
-			spin_lock(&mp->m_ail_lock);
+			spin_lock(&ailp->xa_lock);
 			if (iip->ili_item.li_flags & XFS_LI_IN_AIL) {
-				/*
-				 * xfs_trans_delete_ail() drops the AIL lock.
-				 */
-				xfs_trans_delete_ail(mp, (xfs_log_item_t *)iip);
+				/* xfs_trans_ail_delete() drops the AIL lock. */
+				xfs_trans_ail_delete(ailp, (xfs_log_item_t *)iip);
 			} else
-				spin_unlock(&mp->m_ail_lock);
+				spin_unlock(&ailp->xa_lock);
 		}
 		iip->ili_logged = 0;
 		/*
diff --git a/fs/xfs/xfs_inode_item.h b/fs/xfs/xfs_inode_item.h
index 40513077ab36..1ff04cc323ad 100644
--- a/fs/xfs/xfs_inode_item.h
+++ b/fs/xfs/xfs_inode_item.h
@@ -112,6 +112,24 @@ typedef struct xfs_inode_log_format_64 {
 #define	XFS_ILI_IOLOCKED_ANY   (XFS_ILI_IOLOCKED_EXCL | XFS_ILI_IOLOCKED_SHARED)
 
 
+#define	XFS_ILOG_FBROOT(w)	xfs_ilog_fbroot(w)
+static inline int xfs_ilog_fbroot(int w)
+{
+	return (w == XFS_DATA_FORK ? XFS_ILOG_DBROOT : XFS_ILOG_ABROOT);
+}
+
+#define	XFS_ILOG_FEXT(w)	xfs_ilog_fext(w)
+static inline int xfs_ilog_fext(int w)
+{
+	return (w == XFS_DATA_FORK ? XFS_ILOG_DEXT : XFS_ILOG_AEXT);
+}
+
+#define	XFS_ILOG_FDATA(w)	xfs_ilog_fdata(w)
+static inline int xfs_ilog_fdata(int w)
+{
+	return (w == XFS_DATA_FORK ? XFS_ILOG_DDATA : XFS_ILOG_ADATA);
+}
+
 #ifdef __KERNEL__
 
 struct xfs_buf;
@@ -148,26 +166,6 @@ typedef struct xfs_inode_log_item {
 } xfs_inode_log_item_t;
 
 
-#define	XFS_ILOG_FDATA(w)	xfs_ilog_fdata(w)
-static inline int xfs_ilog_fdata(int w)
-{
-	return (w == XFS_DATA_FORK ? XFS_ILOG_DDATA : XFS_ILOG_ADATA);
-}
-
-#endif	/* __KERNEL__ */
-
-#define	XFS_ILOG_FBROOT(w)	xfs_ilog_fbroot(w)
-static inline int xfs_ilog_fbroot(int w)
-{
-	return (w == XFS_DATA_FORK ? XFS_ILOG_DBROOT : XFS_ILOG_ABROOT);
-}
-
-#define	XFS_ILOG_FEXT(w)	xfs_ilog_fext(w)
-static inline int xfs_ilog_fext(int w)
-{
-	return (w == XFS_DATA_FORK ? XFS_ILOG_DEXT : XFS_ILOG_AEXT);
-}
-
 static inline int xfs_inode_clean(xfs_inode_t *ip)
 {
 	return (!ip->i_itemp ||
@@ -175,9 +173,6 @@ static inline int xfs_inode_clean(xfs_inode_t *ip)
 	       !ip->i_update_core;
 }
 
-
-#ifdef __KERNEL__
-
 extern void xfs_inode_item_init(struct xfs_inode *, struct xfs_mount *);
 extern void xfs_inode_item_destroy(struct xfs_inode *);
 extern void xfs_iflush_done(struct xfs_buf *, xfs_inode_log_item_t *);
diff --git a/fs/xfs/xfs_itable.c b/fs/xfs/xfs_itable.c
index cf6754a3c5b3..e19d0a8d5618 100644
--- a/fs/xfs/xfs_itable.c
+++ b/fs/xfs/xfs_itable.c
@@ -69,7 +69,7 @@ xfs_bulkstat_one_iget(
 	}
 
 	ASSERT(ip != NULL);
-	ASSERT(ip->i_blkno != (xfs_daddr_t)0);
+	ASSERT(ip->i_imap.im_blkno != 0);
 
 	dic = &ip->i_d;
 
@@ -125,13 +125,9 @@ STATIC void
 xfs_bulkstat_one_dinode(
 	xfs_mount_t	*mp,		/* mount point for filesystem */
 	xfs_ino_t	ino,		/* inode number to get data for */
-	xfs_dinode_t	*dip,		/* dinode inode pointer */
+	xfs_dinode_t	*dic,		/* dinode inode pointer */
 	xfs_bstat_t	*buf)		/* return buffer */
 {
-	xfs_dinode_core_t *dic;		/* dinode core info pointer */
-
-	dic = &dip->di_core;
-
 	/*
 	 * The inode format changed when we moved the link count and
 	 * made it 32 bits long.  If this is an old format inode,
@@ -143,7 +139,7 @@ xfs_bulkstat_one_dinode(
 	 * the new format. We don't change the version number so that we
 	 * can distinguish this from a real new format inode.
 	 */
-	if (dic->di_version == XFS_DINODE_VERSION_1) {
+	if (dic->di_version == 1) {
 		buf->bs_nlink = be16_to_cpu(dic->di_onlink);
 		buf->bs_projid = 0;
 	} else {
@@ -162,7 +158,7 @@ xfs_bulkstat_one_dinode(
 	buf->bs_mtime.tv_nsec = be32_to_cpu(dic->di_mtime.t_nsec);
 	buf->bs_ctime.tv_sec = be32_to_cpu(dic->di_ctime.t_sec);
 	buf->bs_ctime.tv_nsec = be32_to_cpu(dic->di_ctime.t_nsec);
-	buf->bs_xflags = xfs_dic2xflags(dip);
+	buf->bs_xflags = xfs_dic2xflags(dic);
 	buf->bs_extsize = be32_to_cpu(dic->di_extsize) << mp->m_sb.sb_blocklog;
 	buf->bs_extents = be32_to_cpu(dic->di_nextents);
 	buf->bs_gen = be32_to_cpu(dic->di_gen);
@@ -173,7 +169,7 @@ xfs_bulkstat_one_dinode(
 
 	switch (dic->di_format) {
 	case XFS_DINODE_FMT_DEV:
-		buf->bs_rdev = be32_to_cpu(dip->di_u.di_dev);
+		buf->bs_rdev = xfs_dinode_get_rdev(dic);
 		buf->bs_blksize = BLKDEV_IOSIZE;
 		buf->bs_blocks = 0;
 		break;
@@ -192,27 +188,34 @@ xfs_bulkstat_one_dinode(
 	}
 }
 
+/* Return 0 on success or positive error */
 STATIC int
 xfs_bulkstat_one_fmt(
 	void			__user *ubuffer,
+	int			ubsize,
+	int			*ubused,
 	const xfs_bstat_t	*buffer)
 {
+	if (ubsize < sizeof(*buffer))
+		return XFS_ERROR(ENOMEM);
 	if (copy_to_user(ubuffer, buffer, sizeof(*buffer)))
-		return -EFAULT;
-	return sizeof(*buffer);
+		return XFS_ERROR(EFAULT);
+	if (ubused)
+		*ubused = sizeof(*buffer);
+	return 0;
 }
 
 /*
  * Return stat information for one inode.
  * Return 0 if ok, else errno.
  */
-int		       		/* error status */
-xfs_bulkstat_one(
+int		   	    		/* error status */
+xfs_bulkstat_one_int(
 	xfs_mount_t	*mp,		/* mount point for filesystem */
 	xfs_ino_t	ino,		/* inode number to get data for */
 	void		__user *buffer,	/* buffer to place output in */
 	int		ubsize,		/* size of buffer */
-	void		*private_data,	/* my private data */
+	bulkstat_one_fmt_pf formatter,	/* formatter, copy to user */
 	xfs_daddr_t	bno,		/* starting bno of inode cluster */
 	int		*ubused,	/* bytes used by me */
 	void		*dibuff,	/* on-disk inode buffer */
@@ -221,15 +224,12 @@ xfs_bulkstat_one(
 	xfs_bstat_t	*buf;		/* return buffer */
 	int		error = 0;	/* error value */
 	xfs_dinode_t	*dip;		/* dinode inode pointer */
-	bulkstat_one_fmt_pf formatter = private_data ? : xfs_bulkstat_one_fmt;
 
 	dip = (xfs_dinode_t *)dibuff;
 	*stat = BULKSTAT_RV_NOTHING;
 
 	if (!buffer || xfs_internal_inum(mp, ino))
 		return XFS_ERROR(EINVAL);
-	if (ubsize < sizeof(*buf))
-		return XFS_ERROR(ENOMEM);
 
 	buf = kmem_alloc(sizeof(*buf), KM_SLEEP);
 
@@ -244,21 +244,34 @@ xfs_bulkstat_one(
 		xfs_bulkstat_one_dinode(mp, ino, dip, buf);
 	}
 
-	error = formatter(buffer, buf);
-	if (error < 0)  {
-		error = EFAULT;
+	error = formatter(buffer, ubsize, ubused, buf);
+	if (error)
 		goto out_free;
-	}
 
 	*stat = BULKSTAT_RV_DIDONE;
-	if (ubused)
-		*ubused = error;
 
  out_free:
 	kmem_free(buf);
 	return error;
 }
 
+int
+xfs_bulkstat_one(
+	xfs_mount_t	*mp,		/* mount point for filesystem */
+	xfs_ino_t	ino,		/* inode number to get data for */
+	void		__user *buffer,	/* buffer to place output in */
+	int		ubsize,		/* size of buffer */
+	void		*private_data,	/* my private data */
+	xfs_daddr_t	bno,		/* starting bno of inode cluster */
+	int		*ubused,	/* bytes used by me */
+	void		*dibuff,	/* on-disk inode buffer */
+	int		*stat)		/* BULKSTAT_RV_... */
+{
+	return xfs_bulkstat_one_int(mp, ino, buffer, ubsize,
+				    xfs_bulkstat_one_fmt, bno,
+				    ubused, dibuff, stat);
+}
+
 /*
  * Test to see whether we can use the ondisk inode directly, based
  * on the given bulkstat flags, filling in dipp accordingly.
@@ -287,19 +300,19 @@ xfs_bulkstat_use_dinode(
 	 * to disk yet. This is a temporary hack that would require a proper
 	 * fix in the future.
 	 */
-	if (be16_to_cpu(dip->di_core.di_magic) != XFS_DINODE_MAGIC ||
-	    !XFS_DINODE_GOOD_VERSION(dip->di_core.di_version) ||
-	    !dip->di_core.di_mode)
+	if (be16_to_cpu(dip->di_magic) != XFS_DINODE_MAGIC ||
+	    !XFS_DINODE_GOOD_VERSION(dip->di_version) ||
+	    !dip->di_mode)
 		return 0;
 	if (flags & BULKSTAT_FG_QUICK) {
 		*dipp = dip;
 		return 1;
 	}
 	/* BULKSTAT_FG_INLINE: if attr fork is local, or not there, use it */
-	aformat = dip->di_core.di_aformat;
+	aformat = dip->di_aformat;
 	if ((XFS_DFORK_Q(dip) == 0) ||
 	    (aformat == XFS_DINODE_FMT_LOCAL) ||
-	    (aformat == XFS_DINODE_FMT_EXTENTS && !dip->di_core.di_anextents)) {
+	    (aformat == XFS_DINODE_FMT_EXTENTS && !dip->di_anextents)) {
 		*dipp = dip;
 		return 1;
 	}
@@ -359,7 +372,6 @@ xfs_bulkstat(
 	int			ubused;	/* bytes used by formatter */
 	xfs_buf_t		*bp;	/* ptr to on-disk inode cluster buf */
 	xfs_dinode_t		*dip;	/* ptr into bp for specific inode */
-	xfs_inode_t		*ip;	/* ptr to in-core inode struct */
 
 	/*
 	 * Get the last inode value, see if there's nothing to do.
@@ -416,8 +428,7 @@ xfs_bulkstat(
 		/*
 		 * Allocate and initialize a btree cursor for ialloc btree.
 		 */
-		cur = xfs_btree_init_cursor(mp, NULL, agbp, agno, XFS_BTNUM_INO,
-						(xfs_inode_t *)0, 0);
+		cur = xfs_inobt_init_cursor(mp, NULL, agbp, agno);
 		irbp = irbuf;
 		irbufend = irbuf + nirbuf;
 		end_of_ag = 0;
@@ -472,7 +483,7 @@ xfs_bulkstat(
 			 * In any case, increment to the next record.
 			 */
 			if (!error)
-				error = xfs_inobt_increment(cur, 0, &tmp);
+				error = xfs_btree_increment(cur, 0, &tmp);
 		} else {
 			/*
 			 * Start of ag.  Lookup the first inode chunk.
@@ -539,7 +550,7 @@ xfs_bulkstat(
 			 * Set agino to after this chunk and bump the cursor.
 			 */
 			agino = gino + XFS_INODES_PER_CHUNK;
-			error = xfs_inobt_increment(cur, 0, &tmp);
+			error = xfs_btree_increment(cur, 0, &tmp);
 			cond_resched();
 		}
 		/*
@@ -586,6 +597,8 @@ xfs_bulkstat(
 
 					if (flags & (BULKSTAT_FG_QUICK |
 						     BULKSTAT_FG_INLINE)) {
+						int offset;
+
 						ino = XFS_AGINO_TO_INO(mp, agno,
 								       agino);
 						bno = XFS_AGB_TO_DADDR(mp, agno,
@@ -594,21 +607,15 @@ xfs_bulkstat(
 						/*
 						 * Get the inode cluster buffer
 						 */
-						ASSERT(xfs_inode_zone != NULL);
-						ip = kmem_zone_zalloc(xfs_inode_zone,
-								      KM_SLEEP);
-						ip->i_ino = ino;
-						ip->i_mount = mp;
-						spin_lock_init(&ip->i_flags_lock);
 						if (bp)
 							xfs_buf_relse(bp);
-						error = xfs_itobp(mp, NULL, ip,
-								&dip, &bp, bno,
-								XFS_IMAP_BULKSTAT,
-								XFS_BUF_LOCK);
+
+						error = xfs_inotobp(mp, NULL, ino, &dip,
+								    &bp, &offset,
+								    XFS_IGET_BULKSTAT);
+
 						if (!error)
-							clustidx = ip->i_boffset / mp->m_sb.sb_inodesize;
-						kmem_zone_free(xfs_inode_zone, ip);
+							clustidx = offset / mp->m_sb.sb_inodesize;
 						if (XFS_TEST_ERROR(error != 0,
 								   mp, XFS_ERRTAG_BULKSTAT_READ_CHUNK,
 								   XFS_RANDOM_BULKSTAT_READ_CHUNK)) {
@@ -842,8 +849,7 @@ xfs_inumbers(
 				agino = 0;
 				continue;
 			}
-			cur = xfs_btree_init_cursor(mp, NULL, agbp, agno,
-				XFS_BTNUM_INO, (xfs_inode_t *)0, 0);
+			cur = xfs_inobt_init_cursor(mp, NULL, agbp, agno);
 			error = xfs_inobt_lookup_ge(cur, agino, 0, 0, &tmp);
 			if (error) {
 				xfs_btree_del_cursor(cur, XFS_BTREE_ERROR);
@@ -887,7 +893,7 @@ xfs_inumbers(
 			bufidx = 0;
 		}
 		if (left) {
-			error = xfs_inobt_increment(cur, 0, &tmp);
+			error = xfs_btree_increment(cur, 0, &tmp);
 			if (error) {
 				xfs_btree_del_cursor(cur, XFS_BTREE_ERROR);
 				cur = NULL;
diff --git a/fs/xfs/xfs_itable.h b/fs/xfs/xfs_itable.h
index a1f18fce9b70..1fb04e7deb61 100644
--- a/fs/xfs/xfs_itable.h
+++ b/fs/xfs/xfs_itable.h
@@ -71,9 +71,23 @@ xfs_bulkstat_single(
 
 typedef int (*bulkstat_one_fmt_pf)(  /* used size in bytes or negative error */
 	void			__user *ubuffer, /* buffer to write to */
+	int			ubsize,		 /* remaining user buffer sz */
+	int			*ubused,	 /* bytes used by formatter */
 	const xfs_bstat_t	*buffer);        /* buffer to read from */
 
 int
+xfs_bulkstat_one_int(
+	xfs_mount_t		*mp,
+	xfs_ino_t		ino,
+	void			__user *buffer,
+	int			ubsize,
+	bulkstat_one_fmt_pf	formatter,
+	xfs_daddr_t		bno,
+	int			*ubused,
+	void			*dibuff,
+	int			*stat);
+
+int
 xfs_bulkstat_one(
 	xfs_mount_t		*mp,
 	xfs_ino_t		ino,
diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c
index 3608a0f0a5f6..f4726f702a9e 100644
--- a/fs/xfs/xfs_log.c
+++ b/fs/xfs/xfs_log.c
@@ -100,12 +100,11 @@ STATIC void xlog_ungrant_log_space(xlog_t	 *log,
 
 
 /* local ticket functions */
-STATIC xlog_ticket_t	*xlog_ticket_get(xlog_t *log,
+STATIC xlog_ticket_t	*xlog_ticket_alloc(xlog_t *log,
 					 int	unit_bytes,
 					 int	count,
 					 char	clientid,
 					 uint	flags);
-STATIC void		xlog_ticket_put(xlog_t *log, xlog_ticket_t *ticket);
 
 #if defined(DEBUG)
 STATIC void	xlog_verify_dest_ptr(xlog_t *log, __psint_t ptr);
@@ -360,7 +359,7 @@ xfs_log_done(xfs_mount_t	*mp,
 		 */
 		xlog_trace_loggrant(log, ticket, "xfs_log_done: (non-permanent)");
 		xlog_ungrant_log_space(log, ticket);
-		xlog_ticket_put(log, ticket);
+		xfs_log_ticket_put(ticket);
 	} else {
 		xlog_trace_loggrant(log, ticket, "xfs_log_done: (permanent)");
 		xlog_regrant_reserve_log_space(log, ticket);
@@ -514,7 +513,7 @@ xfs_log_reserve(xfs_mount_t	 *mp,
 		retval = xlog_regrant_write_log_space(log, internal_ticket);
 	} else {
 		/* may sleep if need to allocate more tickets */
-		internal_ticket = xlog_ticket_get(log, unit_bytes, cnt,
+		internal_ticket = xlog_ticket_alloc(log, unit_bytes, cnt,
 						  client, flags);
 		if (!internal_ticket)
 			return XFS_ERROR(ENOMEM);
@@ -572,12 +571,12 @@ xfs_log_mount(
 	/*
 	 * Initialize the AIL now we have a log.
 	 */
-	spin_lock_init(&mp->m_ail_lock);
 	error = xfs_trans_ail_init(mp);
 	if (error) {
 		cmn_err(CE_WARN, "XFS: AIL initialisation failed: error %d", error);
 		goto error;
 	}
+	mp->m_log->l_ailp = mp->m_ail;
 
 	/*
 	 * skip log recovery on a norecovery mount.  pretend it all
@@ -730,8 +729,8 @@ xfs_log_unmount_write(xfs_mount_t *mp)
 		spin_lock(&log->l_icloglock);
 		iclog = log->l_iclog;
 		atomic_inc(&iclog->ic_refcnt);
-		spin_unlock(&log->l_icloglock);
 		xlog_state_want_sync(log, iclog);
+		spin_unlock(&log->l_icloglock);
 		error = xlog_state_release_iclog(log, iclog);
 
 		spin_lock(&log->l_icloglock);
@@ -749,7 +748,7 @@ xfs_log_unmount_write(xfs_mount_t *mp)
 		if (tic) {
 			xlog_trace_loggrant(log, tic, "unmount rec");
 			xlog_ungrant_log_space(log, tic);
-			xlog_ticket_put(log, tic);
+			xfs_log_ticket_put(tic);
 		}
 	} else {
 		/*
@@ -768,9 +767,9 @@ xfs_log_unmount_write(xfs_mount_t *mp)
 		spin_lock(&log->l_icloglock);
 		iclog = log->l_iclog;
 		atomic_inc(&iclog->ic_refcnt);
-		spin_unlock(&log->l_icloglock);
 
 		xlog_state_want_sync(log, iclog);
+		spin_unlock(&log->l_icloglock);
 		error =  xlog_state_release_iclog(log, iclog);
 
 		spin_lock(&log->l_icloglock);
@@ -906,7 +905,7 @@ xfs_log_move_tail(xfs_mount_t	*mp,
 int
 xfs_log_need_covered(xfs_mount_t *mp)
 {
-	int		needed = 0, gen;
+	int		needed = 0;
 	xlog_t		*log = mp->m_log;
 
 	if (!xfs_fs_writable(mp))
@@ -915,7 +914,7 @@ xfs_log_need_covered(xfs_mount_t *mp)
 	spin_lock(&log->l_icloglock);
 	if (((log->l_covered_state == XLOG_STATE_COVER_NEED) ||
 		(log->l_covered_state == XLOG_STATE_COVER_NEED2))
-			&& !xfs_trans_first_ail(mp, &gen)
+			&& !xfs_trans_ail_tail(log->l_ailp)
 			&& xlog_iclogs_empty(log)) {
 		if (log->l_covered_state == XLOG_STATE_COVER_NEED)
 			log->l_covered_state = XLOG_STATE_COVER_DONE;
@@ -952,7 +951,7 @@ xlog_assign_tail_lsn(xfs_mount_t *mp)
 	xfs_lsn_t tail_lsn;
 	xlog_t	  *log = mp->m_log;
 
-	tail_lsn = xfs_trans_tail_ail(mp);
+	tail_lsn = xfs_trans_ail_tail(mp->m_ail);
 	spin_lock(&log->l_grant_lock);
 	if (tail_lsn != 0) {
 		log->l_tail_lsn = tail_lsn;
@@ -1030,12 +1029,6 @@ xlog_iodone(xfs_buf_t *bp)
 	ASSERT(XFS_BUF_FSPRIVATE2(bp, unsigned long) == (unsigned long) 2);
 	XFS_BUF_SET_FSPRIVATE2(bp, (unsigned long)1);
 	aborted = 0;
-
-	/*
-	 * Some versions of cpp barf on the recursive definition of
-	 * ic_log -> hic_fields.ic_log and expand ic_log twice when
-	 * it is passed through two macros.  Workaround broken cpp.
-	 */
 	l = iclog->ic_log;
 
 	/*
@@ -1302,7 +1295,7 @@ xlog_alloc_log(xfs_mount_t	*mp,
 		XFS_BUF_SET_BDSTRAT_FUNC(bp, xlog_bdstrat_cb);
 		XFS_BUF_SET_FSPRIVATE2(bp, (unsigned long)1);
 		iclog->ic_bp = bp;
-		iclog->hic_data = bp->b_addr;
+		iclog->ic_data = bp->b_addr;
 #ifdef DEBUG
 		log->l_iclog_bak[i] = (xfs_caddr_t)&(iclog->ic_header);
 #endif
@@ -1322,7 +1315,7 @@ xlog_alloc_log(xfs_mount_t	*mp,
 		atomic_set(&iclog->ic_refcnt, 0);
 		spin_lock_init(&iclog->ic_callback_lock);
 		iclog->ic_callback_tail = &(iclog->ic_callback);
-		iclog->ic_datap = (char *)iclog->hic_data + log->l_iclog_hsize;
+		iclog->ic_datap = (char *)iclog->ic_data + log->l_iclog_hsize;
 
 		ASSERT(XFS_BUF_ISBUSY(iclog->ic_bp));
 		ASSERT(XFS_BUF_VALUSEMA(iclog->ic_bp) <= 0);
@@ -1446,7 +1439,7 @@ xlog_grant_push_ail(xfs_mount_t	*mp,
      */
     if (threshold_lsn &&
 	!XLOG_FORCED_SHUTDOWN(log))
-	    xfs_trans_push_ail(mp, threshold_lsn);
+	    xfs_trans_ail_push(log->l_ailp, threshold_lsn);
 }	/* xlog_grant_push_ail */
 
 
@@ -1991,7 +1984,9 @@ xlog_write(xfs_mount_t *	mp,
 		if (iclog->ic_size - log_offset <= sizeof(xlog_op_header_t)) {
 		    xlog_state_finish_copy(log, iclog, record_cnt, data_cnt);
 		    record_cnt = data_cnt = 0;
+		    spin_lock(&log->l_icloglock);
 		    xlog_state_want_sync(log, iclog);
+		    spin_unlock(&log->l_icloglock);
 		    if (commit_iclog) {
 			ASSERT(flags & XLOG_COMMIT_TRANS);
 			*commit_iclog = iclog;
@@ -3200,7 +3195,7 @@ try_again:
 STATIC void
 xlog_state_want_sync(xlog_t *log, xlog_in_core_t *iclog)
 {
-	spin_lock(&log->l_icloglock);
+	ASSERT(spin_is_locked(&log->l_icloglock));
 
 	if (iclog->ic_state == XLOG_STATE_ACTIVE) {
 		xlog_state_switch_iclogs(log, iclog, 0);
@@ -3208,10 +3203,7 @@ xlog_state_want_sync(xlog_t *log, xlog_in_core_t *iclog)
 		ASSERT(iclog->ic_state &
 			(XLOG_STATE_WANT_SYNC|XLOG_STATE_IOERROR));
 	}
-
-	spin_unlock(&log->l_icloglock);
-}	/* xlog_state_want_sync */
-
+}
 
 
 /*****************************************************************************
@@ -3222,22 +3214,33 @@ xlog_state_want_sync(xlog_t *log, xlog_in_core_t *iclog)
  */
 
 /*
- * Free a used ticket.
+ * Free a used ticket when it's refcount falls to zero.
  */
-STATIC void
-xlog_ticket_put(xlog_t		*log,
-		xlog_ticket_t	*ticket)
+void
+xfs_log_ticket_put(
+	xlog_ticket_t	*ticket)
 {
-	sv_destroy(&ticket->t_wait);
-	kmem_zone_free(xfs_log_ticket_zone, ticket);
-}	/* xlog_ticket_put */
+	ASSERT(atomic_read(&ticket->t_ref) > 0);
+	if (atomic_dec_and_test(&ticket->t_ref)) {
+		sv_destroy(&ticket->t_wait);
+		kmem_zone_free(xfs_log_ticket_zone, ticket);
+	}
+}
 
+xlog_ticket_t *
+xfs_log_ticket_get(
+	xlog_ticket_t	*ticket)
+{
+	ASSERT(atomic_read(&ticket->t_ref) > 0);
+	atomic_inc(&ticket->t_ref);
+	return ticket;
+}
 
 /*
  * Allocate and initialise a new log ticket.
  */
 STATIC xlog_ticket_t *
-xlog_ticket_get(xlog_t		*log,
+xlog_ticket_alloc(xlog_t		*log,
 		int		unit_bytes,
 		int		cnt,
 		char		client,
@@ -3308,6 +3311,7 @@ xlog_ticket_get(xlog_t		*log,
 		unit_bytes += 2*BBSIZE;
         }
 
+	atomic_set(&tic->t_ref, 1);
 	tic->t_unit_res		= unit_bytes;
 	tic->t_curr_res		= unit_bytes;
 	tic->t_cnt		= cnt;
@@ -3323,7 +3327,7 @@ xlog_ticket_get(xlog_t		*log,
 	xlog_tic_reset_res(tic);
 
 	return tic;
-}	/* xlog_ticket_get */
+}
 
 
 /******************************************************************************
@@ -3452,7 +3456,7 @@ xlog_verify_iclog(xlog_t	 *log,
 	ptr = iclog->ic_datap;
 	base_ptr = ptr;
 	ophead = (xlog_op_header_t *)ptr;
-	xhdr = (xlog_in_core_2_t *)&iclog->ic_header;
+	xhdr = iclog->ic_data;
 	for (i = 0; i < len; i++) {
 		ophead = (xlog_op_header_t *)ptr;
 
@@ -3558,7 +3562,8 @@ xfs_log_force_umount(
 	if (!log ||
 	    log->l_flags & XLOG_ACTIVE_RECOVERY) {
 		mp->m_flags |= XFS_MOUNT_FS_SHUTDOWN;
-		XFS_BUF_DONE(mp->m_sb_bp);
+		if (mp->m_sb_bp)
+			XFS_BUF_DONE(mp->m_sb_bp);
 		return 0;
 	}
 
@@ -3579,7 +3584,9 @@ xfs_log_force_umount(
 	spin_lock(&log->l_icloglock);
 	spin_lock(&log->l_grant_lock);
 	mp->m_flags |= XFS_MOUNT_FS_SHUTDOWN;
-	XFS_BUF_DONE(mp->m_sb_bp);
+	if (mp->m_sb_bp)
+		XFS_BUF_DONE(mp->m_sb_bp);
+
 	/*
 	 * This flag is sort of redundant because of the mount flag, but
 	 * it's good to maintain the separation between the log and the rest
diff --git a/fs/xfs/xfs_log.h b/fs/xfs/xfs_log.h
index d47b91f10822..8a3e84e900a3 100644
--- a/fs/xfs/xfs_log.h
+++ b/fs/xfs/xfs_log.h
@@ -134,6 +134,7 @@ typedef struct xfs_log_callback {
 #ifdef __KERNEL__
 /* Log manager interfaces */
 struct xfs_mount;
+struct xlog_ticket;
 xfs_lsn_t xfs_log_done(struct xfs_mount *mp,
 		       xfs_log_ticket_t ticket,
 		       void		**iclog,
@@ -177,6 +178,9 @@ int	  xfs_log_need_covered(struct xfs_mount *mp);
 
 void	  xlog_iodone(struct xfs_buf *);
 
+struct xlog_ticket * xfs_log_ticket_get(struct xlog_ticket *ticket);
+void	  xfs_log_ticket_put(struct xlog_ticket *ticket);
+
 #endif
 
 
diff --git a/fs/xfs/xfs_log_priv.h b/fs/xfs/xfs_log_priv.h
index e7d8f84443fa..654167be0efb 100644
--- a/fs/xfs/xfs_log_priv.h
+++ b/fs/xfs/xfs_log_priv.h
@@ -245,6 +245,7 @@ typedef struct xlog_ticket {
 	struct xlog_ticket *t_next;	 /*			         :4|8 */
 	struct xlog_ticket *t_prev;	 /*				 :4|8 */
 	xlog_tid_t	   t_tid;	 /* transaction identifier	 : 4  */
+	atomic_t	   t_ref;	 /* ticket reference count       : 4  */
 	int		   t_curr_res;	 /* current reservation in bytes : 4  */
 	int		   t_unit_res;	 /* unit reservation in bytes    : 4  */
 	char		   t_ocnt;	 /* original count		 : 1  */
@@ -309,6 +310,16 @@ typedef struct xlog_rec_ext_header {
 } xlog_rec_ext_header_t;
 
 #ifdef __KERNEL__
+
+/*
+ * Quite misnamed, because this union lays out the actual on-disk log buffer.
+ */
+typedef union xlog_in_core2 {
+	xlog_rec_header_t	hic_header;
+	xlog_rec_ext_header_t	hic_xheader;
+	char			hic_sector[XLOG_HEADER_SIZE];
+} xlog_in_core_2_t;
+
 /*
  * - A log record header is 512 bytes.  There is plenty of room to grow the
  *	xlog_rec_header_t into the reserved space.
@@ -338,7 +349,7 @@ typedef struct xlog_rec_ext_header {
  * We'll put all the read-only and l_icloglock fields in the first cacheline,
  * and move everything else out to subsequent cachelines.
  */
-typedef struct xlog_iclog_fields {
+typedef struct xlog_in_core {
 	sv_t			ic_force_wait;
 	sv_t			ic_write_wait;
 	struct xlog_in_core	*ic_next;
@@ -361,41 +372,11 @@ typedef struct xlog_iclog_fields {
 
 	/* reference counts need their own cacheline */
 	atomic_t		ic_refcnt ____cacheline_aligned_in_smp;
-} xlog_iclog_fields_t;
-
-typedef union xlog_in_core2 {
-	xlog_rec_header_t	hic_header;
-	xlog_rec_ext_header_t	hic_xheader;
-	char			hic_sector[XLOG_HEADER_SIZE];
-} xlog_in_core_2_t;
-
-typedef struct xlog_in_core {
-	xlog_iclog_fields_t	hic_fields;
-	xlog_in_core_2_t	*hic_data;
+	xlog_in_core_2_t	*ic_data;
+#define ic_header	ic_data->hic_header
 } xlog_in_core_t;
 
 /*
- * Defines to save our code from this glop.
- */
-#define	ic_force_wait	hic_fields.ic_force_wait
-#define ic_write_wait	hic_fields.ic_write_wait
-#define	ic_next		hic_fields.ic_next
-#define	ic_prev		hic_fields.ic_prev
-#define	ic_bp		hic_fields.ic_bp
-#define	ic_log		hic_fields.ic_log
-#define	ic_callback	hic_fields.ic_callback
-#define	ic_callback_lock hic_fields.ic_callback_lock
-#define	ic_callback_tail hic_fields.ic_callback_tail
-#define	ic_trace	hic_fields.ic_trace
-#define	ic_size		hic_fields.ic_size
-#define	ic_offset	hic_fields.ic_offset
-#define	ic_refcnt	hic_fields.ic_refcnt
-#define	ic_bwritecnt	hic_fields.ic_bwritecnt
-#define	ic_state	hic_fields.ic_state
-#define ic_datap	hic_fields.ic_datap
-#define ic_header	hic_data->hic_header
-
-/*
  * The reservation head lsn is not made up of a cycle number and block number.
  * Instead, it uses a cycle number and byte number.  Logs don't expect to
  * overflow 31 bits worth of byte offset, so using a byte number will mean
@@ -404,6 +385,7 @@ typedef struct xlog_in_core {
 typedef struct log {
 	/* The following fields don't need locking */
 	struct xfs_mount	*l_mp;	        /* mount point */
+	struct xfs_ail		*l_ailp;	/* AIL log is working with */
 	struct xfs_buf		*l_xbuf;        /* extra buffer for log
 						 * wrapping */
 	struct xfs_buftarg	*l_targ;        /* buftarg of log */
diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c
index 70e3ba32e6be..51412cced010 100644
--- a/fs/xfs/xfs_log_recover.c
+++ b/fs/xfs/xfs_log_recover.c
@@ -36,7 +36,6 @@
 #include "xfs_dinode.h"
 #include "xfs_inode.h"
 #include "xfs_inode_item.h"
-#include "xfs_imap.h"
 #include "xfs_alloc.h"
 #include "xfs_ialloc.h"
 #include "xfs_log_priv.h"
@@ -54,10 +53,8 @@ STATIC void	xlog_recover_insert_item_backq(xlog_recover_item_t **q,
 					       xlog_recover_item_t *item);
 #if defined(DEBUG)
 STATIC void	xlog_recover_check_summary(xlog_t *);
-STATIC void	xlog_recover_check_ail(xfs_mount_t *, xfs_log_item_t *, int);
 #else
 #define	xlog_recover_check_summary(log)
-#define	xlog_recover_check_ail(mp, lip, gen)
 #endif
 
 
@@ -2247,7 +2244,6 @@ xlog_recover_do_inode_trans(
 	xfs_inode_log_format_t	*in_f;
 	xfs_mount_t		*mp;
 	xfs_buf_t		*bp;
-	xfs_imap_t		imap;
 	xfs_dinode_t		*dip;
 	xfs_ino_t		ino;
 	int			len;
@@ -2275,54 +2271,35 @@ xlog_recover_do_inode_trans(
 	}
 	ino = in_f->ilf_ino;
 	mp = log->l_mp;
-	if (ITEM_TYPE(item) == XFS_LI_INODE) {
-		imap.im_blkno = (xfs_daddr_t)in_f->ilf_blkno;
-		imap.im_len = in_f->ilf_len;
-		imap.im_boffset = in_f->ilf_boffset;
-	} else {
-		/*
-		 * It's an old inode format record.  We don't know where
-		 * its cluster is located on disk, and we can't allow
-		 * xfs_imap() to figure it out because the inode btrees
-		 * are not ready to be used.  Therefore do not pass the
-		 * XFS_IMAP_LOOKUP flag to xfs_imap().  This will give
-		 * us only the single block in which the inode lives
-		 * rather than its cluster, so we must make sure to
-		 * invalidate the buffer when we write it out below.
-		 */
-		imap.im_blkno = 0;
-		error = xfs_imap(log->l_mp, NULL, ino, &imap, 0);
-		if (error)
-			goto error;
-	}
 
 	/*
 	 * Inode buffers can be freed, look out for it,
 	 * and do not replay the inode.
 	 */
-	if (xlog_check_buffer_cancelled(log, imap.im_blkno, imap.im_len, 0)) {
+	if (xlog_check_buffer_cancelled(log, in_f->ilf_blkno,
+					in_f->ilf_len, 0)) {
 		error = 0;
 		goto error;
 	}
 
-	bp = xfs_buf_read_flags(mp->m_ddev_targp, imap.im_blkno, imap.im_len,
-								XFS_BUF_LOCK);
+	bp = xfs_buf_read_flags(mp->m_ddev_targp, in_f->ilf_blkno,
+				in_f->ilf_len, XFS_BUF_LOCK);
 	if (XFS_BUF_ISERROR(bp)) {
 		xfs_ioerror_alert("xlog_recover_do..(read#2)", mp,
-				  bp, imap.im_blkno);
+				  bp, in_f->ilf_blkno);
 		error = XFS_BUF_GETERROR(bp);
 		xfs_buf_relse(bp);
 		goto error;
 	}
 	error = 0;
 	ASSERT(in_f->ilf_fields & XFS_ILOG_CORE);
-	dip = (xfs_dinode_t *)xfs_buf_offset(bp, imap.im_boffset);
+	dip = (xfs_dinode_t *)xfs_buf_offset(bp, in_f->ilf_boffset);
 
 	/*
 	 * Make sure the place we're flushing out to really looks
 	 * like an inode!
 	 */
-	if (unlikely(be16_to_cpu(dip->di_core.di_magic) != XFS_DINODE_MAGIC)) {
+	if (unlikely(be16_to_cpu(dip->di_magic) != XFS_DINODE_MAGIC)) {
 		xfs_buf_relse(bp);
 		xfs_fs_cmn_err(CE_ALERT, mp,
 			"xfs_inode_recover: Bad inode magic number, dino ptr = 0x%p, dino bp = 0x%p, ino = %Ld",
@@ -2345,12 +2322,12 @@ xlog_recover_do_inode_trans(
 	}
 
 	/* Skip replay when the on disk inode is newer than the log one */
-	if (dicp->di_flushiter < be16_to_cpu(dip->di_core.di_flushiter)) {
+	if (dicp->di_flushiter < be16_to_cpu(dip->di_flushiter)) {
 		/*
 		 * Deal with the wrap case, DI_MAX_FLUSH is less
 		 * than smaller numbers
 		 */
-		if (be16_to_cpu(dip->di_core.di_flushiter) == DI_MAX_FLUSH &&
+		if (be16_to_cpu(dip->di_flushiter) == DI_MAX_FLUSH &&
 		    dicp->di_flushiter < (DI_MAX_FLUSH >> 1)) {
 			/* do nothing */
 		} else {
@@ -2410,7 +2387,7 @@ xlog_recover_do_inode_trans(
 		error = EFSCORRUPTED;
 		goto error;
 	}
-	if (unlikely(item->ri_buf[1].i_len > sizeof(xfs_dinode_core_t))) {
+	if (unlikely(item->ri_buf[1].i_len > sizeof(struct xfs_icdinode))) {
 		XFS_CORRUPTION_ERROR("xlog_recover_do_inode_trans(7)",
 				     XFS_ERRLEVEL_LOW, mp, dicp);
 		xfs_buf_relse(bp);
@@ -2422,23 +2399,24 @@ xlog_recover_do_inode_trans(
 	}
 
 	/* The core is in in-core format */
-	xfs_dinode_to_disk(&dip->di_core,
-		(xfs_icdinode_t *)item->ri_buf[1].i_addr);
+	xfs_dinode_to_disk(dip, (xfs_icdinode_t *)item->ri_buf[1].i_addr);
 
 	/* the rest is in on-disk format */
-	if (item->ri_buf[1].i_len > sizeof(xfs_dinode_core_t)) {
-		memcpy((xfs_caddr_t) dip + sizeof(xfs_dinode_core_t),
-			item->ri_buf[1].i_addr + sizeof(xfs_dinode_core_t),
-			item->ri_buf[1].i_len  - sizeof(xfs_dinode_core_t));
+	if (item->ri_buf[1].i_len > sizeof(struct xfs_icdinode)) {
+		memcpy((xfs_caddr_t) dip + sizeof(struct xfs_icdinode),
+			item->ri_buf[1].i_addr + sizeof(struct xfs_icdinode),
+			item->ri_buf[1].i_len  - sizeof(struct xfs_icdinode));
 	}
 
 	fields = in_f->ilf_fields;
 	switch (fields & (XFS_ILOG_DEV | XFS_ILOG_UUID)) {
 	case XFS_ILOG_DEV:
-		dip->di_u.di_dev = cpu_to_be32(in_f->ilf_u.ilfu_rdev);
+		xfs_dinode_put_rdev(dip, in_f->ilf_u.ilfu_rdev);
 		break;
 	case XFS_ILOG_UUID:
-		dip->di_u.di_muuid = in_f->ilf_u.ilfu_uuid;
+		memcpy(XFS_DFORK_DPTR(dip),
+		       &in_f->ilf_u.ilfu_uuid,
+		       sizeof(uuid_t));
 		break;
 	}
 
@@ -2454,12 +2432,12 @@ xlog_recover_do_inode_trans(
 	switch (fields & XFS_ILOG_DFORK) {
 	case XFS_ILOG_DDATA:
 	case XFS_ILOG_DEXT:
-		memcpy(&dip->di_u, src, len);
+		memcpy(XFS_DFORK_DPTR(dip), src, len);
 		break;
 
 	case XFS_ILOG_DBROOT:
-		xfs_bmbt_to_bmdr((xfs_bmbt_block_t *)src, len,
-				 &(dip->di_u.di_bmbt),
+		xfs_bmbt_to_bmdr(mp, (struct xfs_btree_block *)src, len,
+				 (xfs_bmdr_block_t *)XFS_DFORK_DPTR(dip),
 				 XFS_DFORK_DSIZE(dip, mp));
 		break;
 
@@ -2496,8 +2474,8 @@ xlog_recover_do_inode_trans(
 
 		case XFS_ILOG_ABROOT:
 			dest = XFS_DFORK_APTR(dip);
-			xfs_bmbt_to_bmdr((xfs_bmbt_block_t *)src, len,
-					 (xfs_bmdr_block_t*)dest,
+			xfs_bmbt_to_bmdr(mp, (struct xfs_btree_block *)src,
+					 len, (xfs_bmdr_block_t*)dest,
 					 XFS_DFORK_ASIZE(dip, mp));
 			break;
 
@@ -2689,11 +2667,11 @@ xlog_recover_do_efi_trans(
 	efip->efi_next_extent = efi_formatp->efi_nextents;
 	efip->efi_flags |= XFS_EFI_COMMITTED;
 
-	spin_lock(&mp->m_ail_lock);
+	spin_lock(&log->l_ailp->xa_lock);
 	/*
-	 * xfs_trans_update_ail() drops the AIL lock.
+	 * xfs_trans_ail_update() drops the AIL lock.
 	 */
-	xfs_trans_update_ail(mp, (xfs_log_item_t *)efip, lsn);
+	xfs_trans_ail_update(log->l_ailp, (xfs_log_item_t *)efip, lsn);
 	return 0;
 }
 
@@ -2712,12 +2690,12 @@ xlog_recover_do_efd_trans(
 	xlog_recover_item_t	*item,
 	int			pass)
 {
-	xfs_mount_t		*mp;
 	xfs_efd_log_format_t	*efd_formatp;
 	xfs_efi_log_item_t	*efip = NULL;
 	xfs_log_item_t		*lip;
-	int			gen;
 	__uint64_t		efi_id;
+	struct xfs_ail_cursor	cur;
+	struct xfs_ail		*ailp = log->l_ailp;
 
 	if (pass == XLOG_RECOVER_PASS1) {
 		return;
@@ -2734,25 +2712,26 @@ xlog_recover_do_efd_trans(
 	 * Search for the efi with the id in the efd format structure
 	 * in the AIL.
 	 */
-	mp = log->l_mp;
-	spin_lock(&mp->m_ail_lock);
-	lip = xfs_trans_first_ail(mp, &gen);
+	spin_lock(&ailp->xa_lock);
+	lip = xfs_trans_ail_cursor_first(ailp, &cur, 0);
 	while (lip != NULL) {
 		if (lip->li_type == XFS_LI_EFI) {
 			efip = (xfs_efi_log_item_t *)lip;
 			if (efip->efi_format.efi_id == efi_id) {
 				/*
-				 * xfs_trans_delete_ail() drops the
+				 * xfs_trans_ail_delete() drops the
 				 * AIL lock.
 				 */
-				xfs_trans_delete_ail(mp, lip);
+				xfs_trans_ail_delete(ailp, lip);
 				xfs_efi_item_free(efip);
-				return;
+				spin_lock(&ailp->xa_lock);
+				break;
 			}
 		}
-		lip = xfs_trans_next_ail(mp, lip, &gen, NULL);
+		lip = xfs_trans_ail_cursor_next(ailp, &cur);
 	}
-	spin_unlock(&mp->m_ail_lock);
+	xfs_trans_ail_cursor_done(ailp, &cur);
+	spin_unlock(&ailp->xa_lock);
 }
 
 /*
@@ -3036,33 +3015,6 @@ abort_error:
 }
 
 /*
- * Verify that once we've encountered something other than an EFI
- * in the AIL that there are no more EFIs in the AIL.
- */
-#if defined(DEBUG)
-STATIC void
-xlog_recover_check_ail(
-	xfs_mount_t		*mp,
-	xfs_log_item_t		*lip,
-	int			gen)
-{
-	int			orig_gen = gen;
-
-	do {
-		ASSERT(lip->li_type != XFS_LI_EFI);
-		lip = xfs_trans_next_ail(mp, lip, &gen, NULL);
-		/*
-		 * The check will be bogus if we restart from the
-		 * beginning of the AIL, so ASSERT that we don't.
-		 * We never should since we're holding the AIL lock
-		 * the entire time.
-		 */
-		ASSERT(gen == orig_gen);
-	} while (lip != NULL);
-}
-#endif	/* DEBUG */
-
-/*
  * When this is called, all of the EFIs which did not have
  * corresponding EFDs should be in the AIL.  What we do now
  * is free the extents associated with each one.
@@ -3086,20 +3038,23 @@ xlog_recover_process_efis(
 {
 	xfs_log_item_t		*lip;
 	xfs_efi_log_item_t	*efip;
-	int			gen;
-	xfs_mount_t		*mp;
 	int			error = 0;
+	struct xfs_ail_cursor	cur;
+	struct xfs_ail		*ailp;
 
-	mp = log->l_mp;
-	spin_lock(&mp->m_ail_lock);
-
-	lip = xfs_trans_first_ail(mp, &gen);
+	ailp = log->l_ailp;
+	spin_lock(&ailp->xa_lock);
+	lip = xfs_trans_ail_cursor_first(ailp, &cur, 0);
 	while (lip != NULL) {
 		/*
 		 * We're done when we see something other than an EFI.
+		 * There should be no EFIs left in the AIL now.
 		 */
 		if (lip->li_type != XFS_LI_EFI) {
-			xlog_recover_check_ail(mp, lip, gen);
+#ifdef DEBUG
+			for (; lip; lip = xfs_trans_ail_cursor_next(ailp, &cur))
+				ASSERT(lip->li_type != XFS_LI_EFI);
+#endif
 			break;
 		}
 
@@ -3108,18 +3063,20 @@ xlog_recover_process_efis(
 		 */
 		efip = (xfs_efi_log_item_t *)lip;
 		if (efip->efi_flags & XFS_EFI_RECOVERED) {
-			lip = xfs_trans_next_ail(mp, lip, &gen, NULL);
+			lip = xfs_trans_ail_cursor_next(ailp, &cur);
 			continue;
 		}
 
-		spin_unlock(&mp->m_ail_lock);
-		error = xlog_recover_process_efi(mp, efip);
+		spin_unlock(&ailp->xa_lock);
+		error = xlog_recover_process_efi(log->l_mp, efip);
+		spin_lock(&ailp->xa_lock);
 		if (error)
-			return error;
-		spin_lock(&mp->m_ail_lock);
-		lip = xfs_trans_next_ail(mp, lip, &gen, NULL);
+			goto out;
+		lip = xfs_trans_ail_cursor_next(ailp, &cur);
 	}
-	spin_unlock(&mp->m_ail_lock);
+out:
+	xfs_trans_ail_cursor_done(ailp, &cur);
+	spin_unlock(&ailp->xa_lock);
 	return error;
 }
 
@@ -3140,19 +3097,16 @@ xlog_recover_clear_agi_bucket(
 	int		error;
 
 	tp = xfs_trans_alloc(mp, XFS_TRANS_CLEAR_AGI_BUCKET);
-	error = xfs_trans_reserve(tp, 0, XFS_CLEAR_AGI_BUCKET_LOG_RES(mp), 0, 0, 0);
-	if (!error)
-		error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp,
-				   XFS_AG_DADDR(mp, agno, XFS_AGI_DADDR(mp)),
-				   XFS_FSS_TO_BB(mp, 1), 0, &agibp);
+	error = xfs_trans_reserve(tp, 0, XFS_CLEAR_AGI_BUCKET_LOG_RES(mp),
+				  0, 0, 0);
 	if (error)
 		goto out_abort;
 
-	error = EINVAL;
-	agi = XFS_BUF_TO_AGI(agibp);
-	if (be32_to_cpu(agi->agi_magicnum) != XFS_AGI_MAGIC)
+	error = xfs_read_agi(mp, tp, agno, &agibp);
+	if (error)
 		goto out_abort;
 
+	agi = XFS_BUF_TO_AGI(agibp);
 	agi->agi_unlinked[bucket] = cpu_to_be32(NULLAGINO);
 	offset = offsetof(xfs_agi_t, agi_unlinked) +
 		 (sizeof(xfs_agino_t) * bucket);
@@ -3172,6 +3126,62 @@ out_error:
 	return;
 }
 
+STATIC xfs_agino_t
+xlog_recover_process_one_iunlink(
+	struct xfs_mount		*mp,
+	xfs_agnumber_t			agno,
+	xfs_agino_t			agino,
+	int				bucket)
+{
+	struct xfs_buf			*ibp;
+	struct xfs_dinode		*dip;
+	struct xfs_inode		*ip;
+	xfs_ino_t			ino;
+	int				error;
+
+	ino = XFS_AGINO_TO_INO(mp, agno, agino);
+	error = xfs_iget(mp, NULL, ino, 0, 0, &ip, 0);
+	if (error)
+		goto fail;
+
+	/*
+	 * Get the on disk inode to find the next inode in the bucket.
+	 */
+	error = xfs_itobp(mp, NULL, ip, &dip, &ibp, XFS_BUF_LOCK);
+	if (error)
+		goto fail_iput;
+
+	ASSERT(ip->i_d.di_nlink == 0);
+	ASSERT(ip->i_d.di_mode != 0);
+
+	/* setup for the next pass */
+	agino = be32_to_cpu(dip->di_next_unlinked);
+	xfs_buf_relse(ibp);
+
+	/*
+	 * Prevent any DMAPI event from being sent when the reference on
+	 * the inode is dropped.
+	 */
+	ip->i_d.di_dmevmask = 0;
+
+	IRELE(ip);
+	return agino;
+
+ fail_iput:
+	IRELE(ip);
+ fail:
+	/*
+	 * We can't read in the inode this bucket points to, or this inode
+	 * is messed up.  Just ditch this bucket of inodes.  We will lose
+	 * some inodes and space, but at least we won't hang.
+	 *
+	 * Call xlog_recover_clear_agi_bucket() to perform a transaction to
+	 * clear the inode pointer in the bucket.
+	 */
+	xlog_recover_clear_agi_bucket(mp, agno, bucket);
+	return NULLAGINO;
+}
+
 /*
  * xlog_iunlink_recover
  *
@@ -3192,11 +3202,7 @@ xlog_recover_process_iunlinks(
 	xfs_agnumber_t	agno;
 	xfs_agi_t	*agi;
 	xfs_buf_t	*agibp;
-	xfs_buf_t	*ibp;
-	xfs_dinode_t	*dip;
-	xfs_inode_t	*ip;
 	xfs_agino_t	agino;
-	xfs_ino_t	ino;
 	int		bucket;
 	int		error;
 	uint		mp_dmevmask;
@@ -3213,22 +3219,21 @@ xlog_recover_process_iunlinks(
 		/*
 		 * Find the agi for this ag.
 		 */
-		agibp = xfs_buf_read(mp->m_ddev_targp,
-				XFS_AG_DADDR(mp, agno, XFS_AGI_DADDR(mp)),
-				XFS_FSS_TO_BB(mp, 1), 0);
-		if (XFS_BUF_ISERROR(agibp)) {
-			xfs_ioerror_alert("xlog_recover_process_iunlinks(#1)",
-				log->l_mp, agibp,
-				XFS_AG_DADDR(mp, agno, XFS_AGI_DADDR(mp)));
+		error = xfs_read_agi(mp, NULL, agno, &agibp);
+		if (error) {
+			/*
+			 * AGI is b0rked. Don't process it.
+			 *
+			 * We should probably mark the filesystem as corrupt
+			 * after we've recovered all the ag's we can....
+			 */
+			continue;
 		}
 		agi = XFS_BUF_TO_AGI(agibp);
-		ASSERT(XFS_AGI_MAGIC == be32_to_cpu(agi->agi_magicnum));
 
 		for (bucket = 0; bucket < XFS_AGI_UNLINKED_BUCKETS; bucket++) {
-
 			agino = be32_to_cpu(agi->agi_unlinked[bucket]);
 			while (agino != NULLAGINO) {
-
 				/*
 				 * Release the agi buffer so that it can
 				 * be acquired in the normal course of the
@@ -3236,87 +3241,17 @@ xlog_recover_process_iunlinks(
 				 */
 				xfs_buf_relse(agibp);
 
-				ino = XFS_AGINO_TO_INO(mp, agno, agino);
-				error = xfs_iget(mp, NULL, ino, 0, 0, &ip, 0);
-				ASSERT(error || (ip != NULL));
-
-				if (!error) {
-					/*
-					 * Get the on disk inode to find the
-					 * next inode in the bucket.
-					 */
-					error = xfs_itobp(mp, NULL, ip, &dip,
-							&ibp, 0, 0,
-							XFS_BUF_LOCK);
-					ASSERT(error || (dip != NULL));
-				}
-
-				if (!error) {
-					ASSERT(ip->i_d.di_nlink == 0);
-
-					/* setup for the next pass */
-					agino = be32_to_cpu(
-							dip->di_next_unlinked);
-					xfs_buf_relse(ibp);
-					/*
-					 * Prevent any DMAPI event from
-					 * being sent when the
-					 * reference on the inode is
-					 * dropped.
-					 */
-					ip->i_d.di_dmevmask = 0;
-
-					/*
-					 * If this is a new inode, handle
-					 * it specially.  Otherwise,
-					 * just drop our reference to the
-					 * inode.  If there are no
-					 * other references, this will
-					 * send the inode to
-					 * xfs_inactive() which will
-					 * truncate the file and free
-					 * the inode.
-					 */
-					if (ip->i_d.di_mode == 0)
-						xfs_iput_new(ip, 0);
-					else
-						IRELE(ip);
-				} else {
-					/*
-					 * We can't read in the inode
-					 * this bucket points to, or
-					 * this inode is messed up.  Just
-					 * ditch this bucket of inodes.  We
-					 * will lose some inodes and space,
-					 * but at least we won't hang.  Call
-					 * xlog_recover_clear_agi_bucket()
-					 * to perform a transaction to clear
-					 * the inode pointer in the bucket.
-					 */
-					xlog_recover_clear_agi_bucket(mp, agno,
-							bucket);
-
-					agino = NULLAGINO;
-				}
+				agino = xlog_recover_process_one_iunlink(mp,
+							agno, agino, bucket);
 
 				/*
 				 * Reacquire the agibuffer and continue around
-				 * the loop.
+				 * the loop. This should never fail as we know
+				 * the buffer was good earlier on.
 				 */
-				agibp = xfs_buf_read(mp->m_ddev_targp,
-						XFS_AG_DADDR(mp, agno,
-							XFS_AGI_DADDR(mp)),
-						XFS_FSS_TO_BB(mp, 1), 0);
-				if (XFS_BUF_ISERROR(agibp)) {
-					xfs_ioerror_alert(
-				"xlog_recover_process_iunlinks(#2)",
-						log->l_mp, agibp,
-						XFS_AG_DADDR(mp, agno,
-							XFS_AGI_DADDR(mp)));
-				}
+				error = xfs_read_agi(mp, NULL, agno, &agibp);
+				ASSERT(error == 0);
 				agi = XFS_BUF_TO_AGI(agibp);
-				ASSERT(XFS_AGI_MAGIC == be32_to_cpu(
-					agi->agi_magicnum));
 			}
 		}
 
@@ -3367,7 +3302,6 @@ xlog_pack_data(
 	int			size = iclog->ic_offset + roundoff;
 	__be32			cycle_lsn;
 	xfs_caddr_t		dp;
-	xlog_in_core_2_t	*xhdr;
 
 	xlog_pack_data_checksum(log, iclog, size);
 
@@ -3382,7 +3316,8 @@ xlog_pack_data(
 	}
 
 	if (xfs_sb_version_haslogv2(&log->l_mp->m_sb)) {
-		xhdr = (xlog_in_core_2_t *)&iclog->ic_header;
+		xlog_in_core_2_t *xhdr = iclog->ic_data;
+
 		for ( ; i < BTOBB(size); i++) {
 			j = i / (XLOG_HEADER_CYCLE_SIZE / BBSIZE);
 			k = i % (XLOG_HEADER_CYCLE_SIZE / BBSIZE);
@@ -3440,7 +3375,6 @@ xlog_unpack_data(
 	xlog_t			*log)
 {
 	int			i, j, k;
-	xlog_in_core_2_t	*xhdr;
 
 	for (i = 0; i < BTOBB(be32_to_cpu(rhead->h_len)) &&
 		  i < (XLOG_HEADER_CYCLE_SIZE / BBSIZE); i++) {
@@ -3449,7 +3383,7 @@ xlog_unpack_data(
 	}
 
 	if (xfs_sb_version_haslogv2(&log->l_mp->m_sb)) {
-		xhdr = (xlog_in_core_2_t *)rhead;
+		xlog_in_core_2_t *xhdr = (xlog_in_core_2_t *)rhead;
 		for ( ; i < BTOBB(be32_to_cpu(rhead->h_len)); i++) {
 			j = i / (XLOG_HEADER_CYCLE_SIZE / BBSIZE);
 			k = i % (XLOG_HEADER_CYCLE_SIZE / BBSIZE);
@@ -4003,11 +3937,8 @@ xlog_recover_check_summary(
 {
 	xfs_mount_t	*mp;
 	xfs_agf_t	*agfp;
-	xfs_agi_t	*agip;
 	xfs_buf_t	*agfbp;
 	xfs_buf_t	*agibp;
-	xfs_daddr_t	agfdaddr;
-	xfs_daddr_t	agidaddr;
 	xfs_buf_t	*sbbp;
 #ifdef XFS_LOUD_RECOVERY
 	xfs_sb_t	*sbp;
@@ -4016,6 +3947,7 @@ xlog_recover_check_summary(
 	__uint64_t	freeblks;
 	__uint64_t	itotal;
 	__uint64_t	ifree;
+	int		error;
 
 	mp = log->l_mp;
 
@@ -4023,37 +3955,27 @@ xlog_recover_check_summary(
 	itotal = 0LL;
 	ifree = 0LL;
 	for (agno = 0; agno < mp->m_sb.sb_agcount; agno++) {
-		agfdaddr = XFS_AG_DADDR(mp, agno, XFS_AGF_DADDR(mp));
-		agfbp = xfs_buf_read(mp->m_ddev_targp, agfdaddr,
-				XFS_FSS_TO_BB(mp, 1), 0);
-		if (XFS_BUF_ISERROR(agfbp)) {
-			xfs_ioerror_alert("xlog_recover_check_summary(agf)",
-						mp, agfbp, agfdaddr);
-		}
-		agfp = XFS_BUF_TO_AGF(agfbp);
-		ASSERT(XFS_AGF_MAGIC == be32_to_cpu(agfp->agf_magicnum));
-		ASSERT(XFS_AGF_GOOD_VERSION(be32_to_cpu(agfp->agf_versionnum)));
-		ASSERT(be32_to_cpu(agfp->agf_seqno) == agno);
-
-		freeblks += be32_to_cpu(agfp->agf_freeblks) +
-			    be32_to_cpu(agfp->agf_flcount);
-		xfs_buf_relse(agfbp);
-
-		agidaddr = XFS_AG_DADDR(mp, agno, XFS_AGI_DADDR(mp));
-		agibp = xfs_buf_read(mp->m_ddev_targp, agidaddr,
-				XFS_FSS_TO_BB(mp, 1), 0);
-		if (XFS_BUF_ISERROR(agibp)) {
-			xfs_ioerror_alert("xlog_recover_check_summary(agi)",
-					  mp, agibp, agidaddr);
+		error = xfs_read_agf(mp, NULL, agno, 0, &agfbp);
+		if (error) {
+			xfs_fs_cmn_err(CE_ALERT, mp,
+					"xlog_recover_check_summary(agf)"
+					"agf read failed agno %d error %d",
+							agno, error);
+		} else {
+			agfp = XFS_BUF_TO_AGF(agfbp);
+			freeblks += be32_to_cpu(agfp->agf_freeblks) +
+				    be32_to_cpu(agfp->agf_flcount);
+			xfs_buf_relse(agfbp);
 		}
-		agip = XFS_BUF_TO_AGI(agibp);
-		ASSERT(XFS_AGI_MAGIC == be32_to_cpu(agip->agi_magicnum));
-		ASSERT(XFS_AGI_GOOD_VERSION(be32_to_cpu(agip->agi_versionnum)));
-		ASSERT(be32_to_cpu(agip->agi_seqno) == agno);
 
-		itotal += be32_to_cpu(agip->agi_count);
-		ifree += be32_to_cpu(agip->agi_freecount);
-		xfs_buf_relse(agibp);
+		error = xfs_read_agi(mp, NULL, agno, &agibp);
+		if (!error) {
+			struct xfs_agi	*agi = XFS_BUF_TO_AGI(agibp);
+
+			itotal += be32_to_cpu(agi->agi_count);
+			ifree += be32_to_cpu(agi->agi_freecount);
+			xfs_buf_relse(agibp);
+		}
 	}
 
 	sbbp = xfs_getsb(mp, 0);
diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
index 15f5dd22fbb2..3c97c6463a4e 100644
--- a/fs/xfs/xfs_mount.c
+++ b/fs/xfs/xfs_mount.c
@@ -567,8 +567,6 @@ xfs_readsb(xfs_mount_t *mp, int flags)
 STATIC void
 xfs_mount_common(xfs_mount_t *mp, xfs_sb_t *sbp)
 {
-	int	i;
-
 	mp->m_agfrotor = mp->m_agirotor = 0;
 	spin_lock_init(&mp->m_agirotor_lock);
 	mp->m_maxagi = mp->m_sb.sb_agcount;
@@ -577,12 +575,10 @@ xfs_mount_common(xfs_mount_t *mp, xfs_sb_t *sbp)
 	mp->m_sectbb_log = sbp->sb_sectlog - BBSHIFT;
 	mp->m_agno_log = xfs_highbit32(sbp->sb_agcount - 1) + 1;
 	mp->m_agino_log = sbp->sb_inopblog + sbp->sb_agblklog;
-	mp->m_litino = sbp->sb_inodesize -
-		((uint)sizeof(xfs_dinode_core_t) + (uint)sizeof(xfs_agino_t));
+	mp->m_litino = sbp->sb_inodesize - sizeof(struct xfs_dinode);
 	mp->m_blockmask = sbp->sb_blocksize - 1;
 	mp->m_blockwsize = sbp->sb_blocksize >> XFS_WORDLOG;
 	mp->m_blockwmask = mp->m_blockwsize - 1;
-	INIT_LIST_HEAD(&mp->m_del_inodes);
 
 	/*
 	 * Setup for attributes, in case they get created.
@@ -605,24 +601,20 @@ xfs_mount_common(xfs_mount_t *mp, xfs_sb_t *sbp)
 	}
 	ASSERT(mp->m_attroffset < XFS_LITINO(mp));
 
-	for (i = 0; i < 2; i++) {
-		mp->m_alloc_mxr[i] = XFS_BTREE_BLOCK_MAXRECS(sbp->sb_blocksize,
-			xfs_alloc, i == 0);
-		mp->m_alloc_mnr[i] = XFS_BTREE_BLOCK_MINRECS(sbp->sb_blocksize,
-			xfs_alloc, i == 0);
-	}
-	for (i = 0; i < 2; i++) {
-		mp->m_bmap_dmxr[i] = XFS_BTREE_BLOCK_MAXRECS(sbp->sb_blocksize,
-			xfs_bmbt, i == 0);
-		mp->m_bmap_dmnr[i] = XFS_BTREE_BLOCK_MINRECS(sbp->sb_blocksize,
-			xfs_bmbt, i == 0);
-	}
-	for (i = 0; i < 2; i++) {
-		mp->m_inobt_mxr[i] = XFS_BTREE_BLOCK_MAXRECS(sbp->sb_blocksize,
-			xfs_inobt, i == 0);
-		mp->m_inobt_mnr[i] = XFS_BTREE_BLOCK_MINRECS(sbp->sb_blocksize,
-			xfs_inobt, i == 0);
-	}
+	mp->m_alloc_mxr[0] = xfs_allocbt_maxrecs(mp, sbp->sb_blocksize, 1);
+	mp->m_alloc_mxr[1] = xfs_allocbt_maxrecs(mp, sbp->sb_blocksize, 0);
+	mp->m_alloc_mnr[0] = mp->m_alloc_mxr[0] / 2;
+	mp->m_alloc_mnr[1] = mp->m_alloc_mxr[1] / 2;
+
+	mp->m_inobt_mxr[0] = xfs_inobt_maxrecs(mp, sbp->sb_blocksize, 1);
+	mp->m_inobt_mxr[1] = xfs_inobt_maxrecs(mp, sbp->sb_blocksize, 0);
+	mp->m_inobt_mnr[0] = mp->m_inobt_mxr[0] / 2;
+	mp->m_inobt_mnr[1] = mp->m_inobt_mxr[1] / 2;
+
+	mp->m_bmap_dmxr[0] = xfs_bmbt_maxrecs(mp, sbp->sb_blocksize, 1);
+	mp->m_bmap_dmxr[1] = xfs_bmbt_maxrecs(mp, sbp->sb_blocksize, 0);
+	mp->m_bmap_dmnr[0] = mp->m_bmap_dmxr[0] / 2;
+	mp->m_bmap_dmnr[1] = mp->m_bmap_dmxr[1] / 2;
 
 	mp->m_bsize = XFS_FSB_TO_BB(mp, 1);
 	mp->m_ialloc_inos = (int)MAX((__uint16_t)XFS_INODES_PER_CHUNK,
@@ -1228,6 +1220,16 @@ xfs_unmountfs(
 	__uint64_t		resblks;
 	int			error;
 
+	/*
+	 * Release dquot that rootinode, rbmino and rsumino might be holding,
+	 * and release the quota inodes.
+	 */
+	XFS_QM_UNMOUNT(mp);
+
+	if (mp->m_rbmip)
+		IRELE(mp->m_rbmip);
+	if (mp->m_rsumip)
+		IRELE(mp->m_rsumip);
 	IRELE(mp->m_rootip);
 
 	/*
@@ -1241,7 +1243,7 @@ xfs_unmountfs(
 	 * need to force the log first.
 	 */
 	xfs_log_force(mp, (xfs_lsn_t)0, XFS_LOG_FORCE | XFS_LOG_SYNC);
-	xfs_iflush_all(mp);
+	xfs_reclaim_inodes(mp, 0, XFS_IFLUSH_ASYNC);
 
 	XFS_QM_DQPURGEALL(mp, XFS_QMOPT_QUOTALL | XFS_QMOPT_UMOUNTING);
 
@@ -1288,11 +1290,6 @@ xfs_unmountfs(
 	xfs_unmountfs_wait(mp); 		/* wait for async bufs */
 	xfs_log_unmount(mp);			/* Done! No more fs ops. */
 
-	/*
-	 * All inodes from this mount point should be freed.
-	 */
-	ASSERT(mp->m_inodes == NULL);
-
 	if ((mp->m_flags & XFS_MOUNT_NOUUID) == 0)
 		uuid_table_remove(&mp->m_sb.sb_uuid);
 
@@ -1365,24 +1362,6 @@ xfs_log_sbcount(
 	return error;
 }
 
-STATIC void
-xfs_mark_shared_ro(
-	xfs_mount_t	*mp,
-	xfs_buf_t	*bp)
-{
-	xfs_dsb_t	*sb = XFS_BUF_TO_SBP(bp);
-	__uint16_t	version;
-
-	if (!(sb->sb_flags & XFS_SBF_READONLY))
-		sb->sb_flags |= XFS_SBF_READONLY;
-
-	version = be16_to_cpu(sb->sb_versionnum);
-	if ((version & XFS_SB_VERSION_NUMBITS) != XFS_SB_VERSION_4 ||
-	    !(version & XFS_SB_VERSION_SHAREDBIT))
-		version |= XFS_SB_VERSION_SHAREDBIT;
-	sb->sb_versionnum = cpu_to_be16(version);
-}
-
 int
 xfs_unmountfs_writesb(xfs_mount_t *mp)
 {
@@ -1398,12 +1377,6 @@ xfs_unmountfs_writesb(xfs_mount_t *mp)
 
 		sbp = xfs_getsb(mp, 0);
 
-		/*
-		 * mark shared-readonly if desired
-		 */
-		if (mp->m_mk_sharedro)
-			xfs_mark_shared_ro(mp, sbp);
-
 		XFS_BUF_UNDONE(sbp);
 		XFS_BUF_UNREAD(sbp);
 		XFS_BUF_UNDELAYWRITE(sbp);
@@ -1415,8 +1388,6 @@ xfs_unmountfs_writesb(xfs_mount_t *mp)
 		if (error)
 			xfs_ioerror_alert("xfs_unmountfs_writesb",
 					  mp, sbp, XFS_BUF_ADDR(sbp));
-		if (error && mp->m_mk_sharedro)
-			xfs_fs_cmn_err(CE_ALERT, mp, "Superblock write error detected while unmounting.  Filesystem may not be marked shared readonly");
 		xfs_buf_relse(sbp);
 	}
 	return error;
diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h
index f3c1024b1241..ae5da88ace20 100644
--- a/fs/xfs/xfs_mount.h
+++ b/fs/xfs/xfs_mount.h
@@ -18,6 +18,7 @@
 #ifndef __XFS_MOUNT_H__
 #define	__XFS_MOUNT_H__
 
+#include "xfs_sync.h"
 
 typedef struct xfs_trans_reservations {
 	uint	tr_write;	/* extent alloc trans */
@@ -44,14 +45,14 @@ typedef struct xfs_trans_reservations {
 } xfs_trans_reservations_t;
 
 #ifndef __KERNEL__
-/*
- * Moved here from xfs_ag.h to avoid reordering header files
- */
+
 #define XFS_DADDR_TO_AGNO(mp,d) \
 	((xfs_agnumber_t)(XFS_BB_TO_FSBT(mp, d) / (mp)->m_sb.sb_agblocks))
 #define XFS_DADDR_TO_AGBNO(mp,d) \
 	((xfs_agblock_t)(XFS_BB_TO_FSBT(mp, d) % (mp)->m_sb.sb_agblocks))
-#else
+
+#else /* __KERNEL__ */
+
 struct cred;
 struct log;
 struct xfs_mount_args;
@@ -62,6 +63,7 @@ struct xfs_extdelta;
 struct xfs_swapext;
 struct xfs_mru_cache;
 struct xfs_nameops;
+struct xfs_ail;
 
 /*
  * Prototypes and functions for the Data Migration subsystem.
@@ -115,7 +117,7 @@ struct xfs_quotainfo;
 
 typedef int	(*xfs_qminit_t)(struct xfs_mount *, uint *, uint *);
 typedef int	(*xfs_qmmount_t)(struct xfs_mount *, uint, uint);
-typedef int	(*xfs_qmunmount_t)(struct xfs_mount *);
+typedef void	(*xfs_qmunmount_t)(struct xfs_mount *);
 typedef void	(*xfs_qmdone_t)(struct xfs_mount *);
 typedef void	(*xfs_dqrele_t)(struct xfs_dquot *);
 typedef int	(*xfs_dqattach_t)(struct xfs_inode *, uint);
@@ -132,7 +134,7 @@ typedef struct xfs_dquot * (*xfs_dqvopchown_t)(
 			struct xfs_dquot **, struct xfs_dquot *);
 typedef int	(*xfs_dqvopchownresv_t)(struct xfs_trans *, struct xfs_inode *,
 			struct xfs_dquot *, struct xfs_dquot *, uint);
-typedef void	(*xfs_dqstatvfs_t)(struct xfs_inode *, bhv_statvfs_t *);
+typedef void	(*xfs_dqstatvfs_t)(struct xfs_inode *, struct kstatfs *);
 typedef int	(*xfs_dqsync_t)(struct xfs_mount *, int flags);
 typedef int	(*xfs_quotactl_t)(struct xfs_mount *, int, int, xfs_caddr_t);
 
@@ -223,18 +225,10 @@ extern void	xfs_icsb_sync_counters_locked(struct xfs_mount *, int);
 #define xfs_icsb_sync_counters_locked(mp, flags) do { } while (0)
 #endif
 
-typedef struct xfs_ail {
-	struct list_head	xa_ail;
-	uint			xa_gen;
-	struct task_struct	*xa_task;
-	xfs_lsn_t		xa_target;
-} xfs_ail_t;
-
 typedef struct xfs_mount {
 	struct super_block	*m_super;
 	xfs_tid_t		m_tid;		/* next unused tid for fs */
-	spinlock_t		m_ail_lock;	/* fs AIL mutex */
-	xfs_ail_t		m_ail;		/* fs active log item list */
+	struct xfs_ail		*m_ail;		/* fs active log item list */
 	xfs_sb_t		m_sb;		/* copy of fs superblock */
 	spinlock_t		m_sb_lock;	/* sb counter lock */
 	struct xfs_buf		*m_sb_bp;	/* buffer for superblock */
@@ -247,10 +241,6 @@ typedef struct xfs_mount {
 	xfs_agnumber_t		m_agirotor;	/* last ag dir inode alloced */
 	spinlock_t		m_agirotor_lock;/* .. and lock protecting it */
 	xfs_agnumber_t		m_maxagi;	/* highest inode alloc group */
-	struct xfs_inode	*m_inodes;	/* active inode list */
-	struct list_head	m_del_inodes;	/* inodes to reclaim */
-	mutex_t			m_ilock;	/* inode list mutex */
-	uint			m_ireclaims;	/* count of calls to reclaim*/
 	uint			m_readio_log;	/* min read size log bytes */
 	uint			m_readio_blocks; /* min read size blocks */
 	uint			m_writeio_log;	/* min write size log bytes */
@@ -267,7 +257,6 @@ typedef struct xfs_mount {
 	xfs_buftarg_t		*m_ddev_targp;	/* saves taking the address */
 	xfs_buftarg_t		*m_logdev_targp;/* ptr to log device */
 	xfs_buftarg_t		*m_rtdev_targp;	/* ptr to rt device */
-	__uint8_t		m_dircook_elog;	/* log d-cookie entry bits */
 	__uint8_t		m_blkbit_log;	/* blocklog + NBBY */
 	__uint8_t		m_blkbb_log;	/* blocklog - BBSHIFT */
 	__uint8_t		m_agno_log;	/* log #ag's */
@@ -276,12 +265,12 @@ typedef struct xfs_mount {
 	uint			m_blockmask;	/* sb_blocksize-1 */
 	uint			m_blockwsize;	/* sb_blocksize in words */
 	uint			m_blockwmask;	/* blockwsize-1 */
-	uint			m_alloc_mxr[2];	/* XFS_ALLOC_BLOCK_MAXRECS */
-	uint			m_alloc_mnr[2];	/* XFS_ALLOC_BLOCK_MINRECS */
-	uint			m_bmap_dmxr[2];	/* XFS_BMAP_BLOCK_DMAXRECS */
-	uint			m_bmap_dmnr[2];	/* XFS_BMAP_BLOCK_DMINRECS */
-	uint			m_inobt_mxr[2];	/* XFS_INOBT_BLOCK_MAXRECS */
-	uint			m_inobt_mnr[2];	/* XFS_INOBT_BLOCK_MINRECS */
+	uint			m_alloc_mxr[2];	/* max alloc btree records */
+	uint			m_alloc_mnr[2];	/* min alloc btree records */
+	uint			m_bmap_dmxr[2];	/* max bmap btree records */
+	uint			m_bmap_dmnr[2];	/* min bmap btree records */
+	uint			m_inobt_mxr[2];	/* max inobt btree records */
+	uint			m_inobt_mnr[2];	/* min inobt btree records */
 	uint			m_ag_maxlevels;	/* XFS_AG_MAXLEVELS */
 	uint			m_bm_maxlevels[2]; /* XFS_BM_MAXLEVELS */
 	uint			m_in_maxlevels;	/* XFS_IN_MAXLEVELS */
@@ -312,9 +301,6 @@ typedef struct xfs_mount {
 	int			m_sinoalign;	/* stripe unit inode alignment */
 	int			m_attr_magicpct;/* 37% of the blocksize */
 	int			m_dir_magicpct;	/* 37% of the dir blocksize */
-	__uint8_t		m_mk_sharedro;	/* mark shared ro on unmount */
-	__uint8_t		m_inode_quiesce;/* call quiesce on new inodes.
-						   field governed by m_ilock */
 	__uint8_t		m_sectbb_log;	/* sectlog - BBSHIFT */
 	const struct xfs_nameops *m_dirnameops;	/* vector of dir name ops */
 	int			m_dirblksize;	/* directory block sz--bytes */
@@ -362,7 +348,6 @@ typedef struct xfs_mount {
 #define XFS_MOUNT_ATTR2		(1ULL << 8)	/* allow use of attr2 format */
 #define XFS_MOUNT_GRPID		(1ULL << 9)	/* group-ID assigned from directory */
 #define XFS_MOUNT_NORECOVERY	(1ULL << 10)	/* no recovery - dirty fs */
-#define XFS_MOUNT_SHARED	(1ULL << 11)	/* shared mount */
 #define XFS_MOUNT_DFLT_IOSIZE	(1ULL << 12)	/* set default i/o size */
 #define XFS_MOUNT_OSYNCISOSYNC	(1ULL << 13)	/* o_sync is REALLY o_sync */
 						/* osyncisdsync is now default*/
@@ -439,6 +424,16 @@ void xfs_do_force_shutdown(struct xfs_mount *mp, int flags, char *fname,
 #define xfs_force_shutdown(m,f)	\
 	xfs_do_force_shutdown(m, f, __FILE__, __LINE__)
 
+#define SHUTDOWN_META_IO_ERROR	0x0001	/* write attempt to metadata failed */
+#define SHUTDOWN_LOG_IO_ERROR	0x0002	/* write attempt to the log failed */
+#define SHUTDOWN_FORCE_UMOUNT	0x0004	/* shutdown from a forced unmount */
+#define SHUTDOWN_CORRUPT_INCORE	0x0008	/* corrupt in-memory data structures */
+#define SHUTDOWN_REMOTE_REQ	0x0010	/* shutdown came from remote cell */
+#define SHUTDOWN_DEVICE_REQ	0x0020	/* failed all paths to the device */
+
+#define xfs_test_for_freeze(mp)		((mp)->m_super->s_frozen)
+#define xfs_wait_for_freeze(mp,l)	vfs_check_frozen((mp)->m_super, (l))
+
 /*
  * Flags for xfs_mountfs
  */
@@ -508,14 +503,12 @@ typedef struct xfs_mod_sb {
 #define	XFS_MOUNT_ILOCK(mp)	mutex_lock(&((mp)->m_ilock))
 #define	XFS_MOUNT_IUNLOCK(mp)	mutex_unlock(&((mp)->m_ilock))
 
-extern void	xfs_mod_sb(xfs_trans_t *, __int64_t);
 extern int	xfs_log_sbcount(xfs_mount_t *, uint);
 extern int	xfs_mountfs(xfs_mount_t *mp);
 extern void	xfs_mountfs_check_barriers(xfs_mount_t *mp);
 
 extern void	xfs_unmountfs(xfs_mount_t *);
 extern int	xfs_unmountfs_writesb(xfs_mount_t *);
-extern int	xfs_unmount_flush(xfs_mount_t *, int);
 extern int	xfs_mod_incore_sb(xfs_mount_t *, xfs_sb_field_t, int64_t, int);
 extern int	xfs_mod_incore_sb_unlocked(xfs_mount_t *, xfs_sb_field_t,
 			int64_t, int);
@@ -525,20 +518,20 @@ extern struct xfs_buf *xfs_getsb(xfs_mount_t *, int);
 extern int	xfs_readsb(xfs_mount_t *, int);
 extern void	xfs_freesb(xfs_mount_t *);
 extern int	xfs_fs_writable(xfs_mount_t *);
-extern int	xfs_syncsub(xfs_mount_t *, int, int *);
-extern int	xfs_sync_inodes(xfs_mount_t *, int, int *);
-extern xfs_agnumber_t	xfs_initialize_perag(xfs_mount_t *, xfs_agnumber_t);
-extern void	xfs_sb_from_disk(struct xfs_sb *, struct xfs_dsb *);
-extern void	xfs_sb_to_disk(struct xfs_dsb *, struct xfs_sb *, __int64_t);
 extern int	xfs_sb_validate_fsb_count(struct xfs_sb *, __uint64_t);
 
-extern int	xfs_dmops_get(struct xfs_mount *, struct xfs_mount_args *);
+extern int	xfs_dmops_get(struct xfs_mount *);
 extern void	xfs_dmops_put(struct xfs_mount *);
-extern int	xfs_qmops_get(struct xfs_mount *, struct xfs_mount_args *);
+extern int	xfs_qmops_get(struct xfs_mount *);
 extern void	xfs_qmops_put(struct xfs_mount *);
 
 extern struct xfs_dmops xfs_dmcore_xfs;
 
 #endif	/* __KERNEL__ */
 
+extern void	xfs_mod_sb(struct xfs_trans *, __int64_t);
+extern xfs_agnumber_t	xfs_initialize_perag(struct xfs_mount *, xfs_agnumber_t);
+extern void	xfs_sb_from_disk(struct xfs_sb *, struct xfs_dsb *);
+extern void	xfs_sb_to_disk(struct xfs_dsb *, struct xfs_sb *, __int64_t);
+
 #endif	/* __XFS_MOUNT_H__ */
diff --git a/fs/xfs/xfs_qmops.c b/fs/xfs/xfs_qmops.c
index a294e58db8dd..27f80581520a 100644
--- a/fs/xfs/xfs_qmops.c
+++ b/fs/xfs/xfs_qmops.c
@@ -28,7 +28,6 @@
 #include "xfs_mount.h"
 #include "xfs_quota.h"
 #include "xfs_error.h"
-#include "xfs_clnt.h"
 
 
 STATIC struct xfs_dquot *
@@ -131,9 +130,9 @@ static struct xfs_qmops xfs_qmcore_stub = {
 };
 
 int
-xfs_qmops_get(struct xfs_mount *mp, struct xfs_mount_args *args)
+xfs_qmops_get(struct xfs_mount *mp)
 {
-	if (args->flags & (XFSMNT_UQUOTA | XFSMNT_PQUOTA | XFSMNT_GQUOTA)) {
+	if (XFS_IS_QUOTA_RUNNING(mp)) {
 #ifdef CONFIG_XFS_QUOTA
 		mp->m_qm_ops = &xfs_qmcore_xfs;
 #else
diff --git a/fs/xfs/xfs_quota.h b/fs/xfs/xfs_quota.h
index 12c4ec775af8..48965ecaa155 100644
--- a/fs/xfs/xfs_quota.h
+++ b/fs/xfs/xfs_quota.h
@@ -84,11 +84,9 @@ typedef struct xfs_dqblk {
 #define XFS_DQ_USER		0x0001		/* a user quota */
 #define XFS_DQ_PROJ		0x0002		/* project quota */
 #define XFS_DQ_GROUP		0x0004		/* a group quota */
-#define XFS_DQ_FLOCKED		0x0008		/* flush lock taken */
-#define XFS_DQ_DIRTY		0x0010		/* dquot is dirty */
-#define XFS_DQ_WANT		0x0020		/* for lookup/reclaim race */
-#define XFS_DQ_INACTIVE		0x0040		/* dq off mplist & hashlist */
-#define XFS_DQ_MARKER		0x0080		/* sentinel */
+#define XFS_DQ_DIRTY		0x0008		/* dquot is dirty */
+#define XFS_DQ_WANT		0x0010		/* for lookup/reclaim race */
+#define XFS_DQ_INACTIVE		0x0020		/* dq off mplist & hashlist */
 
 #define XFS_DQ_ALLTYPES		(XFS_DQ_USER|XFS_DQ_PROJ|XFS_DQ_GROUP)
 
diff --git a/fs/xfs/xfs_rename.c b/fs/xfs/xfs_rename.c
index d700dacdb10e..10642fcbb1f7 100644
--- a/fs/xfs/xfs_rename.c
+++ b/fs/xfs/xfs_rename.c
@@ -212,7 +212,7 @@ xfs_rename(
 	if (unlikely((target_dp->i_d.di_flags & XFS_DIFLAG_PROJINHERIT) &&
 		     (target_dp->i_d.di_projid != src_ip->i_d.di_projid))) {
 		error = XFS_ERROR(EXDEV);
-		xfs_rename_unlock4(inodes, XFS_ILOCK_SHARED);
+		xfs_rename_unlock4(inodes, XFS_ILOCK_EXCL);
 		xfs_trans_cancel(tp, cancel_flags);
 		goto std_return;
 	}
@@ -367,19 +367,11 @@ xfs_rename(
 					&first_block, &free_list, spaceres);
 	if (error)
 		goto abort_return;
-	xfs_ichgtime(src_dp, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
 
-	/*
-	 * Update the generation counts on all the directory inodes
-	 * that we're modifying.
-	 */
-	src_dp->i_gen++;
+	xfs_ichgtime(src_dp, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
 	xfs_trans_log_inode(tp, src_dp, XFS_ILOG_CORE);
-
-	if (new_parent) {
-		target_dp->i_gen++;
+	if (new_parent)
 		xfs_trans_log_inode(tp, target_dp, XFS_ILOG_CORE);
-	}
 
 	/*
 	 * If this is a synchronous mount, make sure that the
diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c
index e2f68de16159..edf12c7b834c 100644
--- a/fs/xfs/xfs_rtalloc.c
+++ b/fs/xfs/xfs_rtalloc.c
@@ -85,7 +85,6 @@ xfs_growfs_rt_alloc(
 {
 	xfs_fileoff_t	bno;		/* block number in file */
 	xfs_buf_t	*bp;		/* temporary buffer for zeroing */
-	int		cancelflags;	/* flags for xfs_trans_cancel */
 	int		committed;	/* transaction committed flag */
 	xfs_daddr_t	d;		/* disk block address */
 	int		error;		/* error return value */
@@ -96,15 +95,16 @@ xfs_growfs_rt_alloc(
 	xfs_bmbt_irec_t	map;		/* block map output */
 	int		nmap;		/* number of block maps */
 	int		resblks;	/* space reservation */
-	xfs_trans_t	*tp;		/* transaction pointer */
 
 	/*
 	 * Allocate space to the file, as necessary.
 	 */
 	while (oblocks < nblocks) {
+		int		cancelflags = 0;
+		xfs_trans_t	*tp;
+
 		tp = xfs_trans_alloc(mp, XFS_TRANS_GROWFSRT_ALLOC);
 		resblks = XFS_GROWFSRT_SPACE_RES(mp, nblocks - oblocks);
-		cancelflags = 0;
 		/*
 		 * Reserve space & log for one extent added to the file.
 		 */
@@ -171,7 +171,9 @@ xfs_growfs_rt_alloc(
 				mp->m_bsize, 0);
 			if (bp == NULL) {
 				error = XFS_ERROR(EIO);
-				goto error_cancel;
+error_cancel:
+				xfs_trans_cancel(tp, cancelflags);
+				goto error;
 			}
 			memset(XFS_BUF_PTR(bp), 0, mp->m_sb.sb_blocksize);
 			xfs_trans_log_buf(tp, bp, 0, mp->m_sb.sb_blocksize - 1);
@@ -188,8 +190,6 @@ xfs_growfs_rt_alloc(
 		oblocks = map.br_startoff + map.br_blockcount;
 	}
 	return 0;
-error_cancel:
-	xfs_trans_cancel(tp, cancelflags);
 error:
 	return error;
 }
@@ -1856,7 +1856,6 @@ xfs_growfs_rt(
 {
 	xfs_rtblock_t	bmbno;		/* bitmap block number */
 	xfs_buf_t	*bp;		/* temporary buffer */
-	int		cancelflags;	/* flags for xfs_trans_cancel */
 	int		error;		/* error return value */
 	xfs_inode_t	*ip;		/* bitmap inode, used as lock */
 	xfs_mount_t	*nmp;		/* new (fake) mount structure */
@@ -1872,13 +1871,13 @@ xfs_growfs_rt(
 	xfs_extlen_t	rsumblocks;	/* current number of rt summary blks */
 	xfs_sb_t	*sbp;		/* old superblock */
 	xfs_fsblock_t	sumbno;		/* summary block number */
-	xfs_trans_t	*tp;		/* transaction pointer */
 
 	sbp = &mp->m_sb;
-	cancelflags = 0;
 	/*
 	 * Initial error checking.
 	 */
+	if (!capable(CAP_SYS_ADMIN))
+		return XFS_ERROR(EPERM);
 	if (mp->m_rtdev_targp == NULL || mp->m_rbmip == NULL ||
 	    (nrblocks = in->newblocks) <= sbp->sb_rblocks ||
 	    (sbp->sb_rblocks && (in->extsize != sbp->sb_rextsize)))
@@ -1942,6 +1941,9 @@ xfs_growfs_rt(
 		     ((sbp->sb_rextents & ((1 << mp->m_blkbit_log) - 1)) != 0);
 	     bmbno < nrbmblocks;
 	     bmbno++) {
+		xfs_trans_t	*tp;
+		int		cancelflags = 0;
+
 		*nmp = *mp;
 		nsbp = &nmp->m_sb;
 		/*
@@ -1967,16 +1969,15 @@ xfs_growfs_rt(
 		 * Start a transaction, get the log reservation.
 		 */
 		tp = xfs_trans_alloc(mp, XFS_TRANS_GROWFSRT_FREE);
-		cancelflags = 0;
 		if ((error = xfs_trans_reserve(tp, 0,
 				XFS_GROWRTFREE_LOG_RES(nmp), 0, 0, 0)))
-			break;
+			goto error_cancel;
 		/*
 		 * Lock out other callers by grabbing the bitmap inode lock.
 		 */
 		if ((error = xfs_trans_iget(mp, tp, mp->m_sb.sb_rbmino, 0,
 						XFS_ILOCK_EXCL, &ip)))
-			break;
+			goto error_cancel;
 		ASSERT(ip == mp->m_rbmip);
 		/*
 		 * Update the bitmap inode's size.
@@ -1990,7 +1991,7 @@ xfs_growfs_rt(
 		 */
 		if ((error = xfs_trans_iget(mp, tp, mp->m_sb.sb_rsumino, 0,
 						XFS_ILOCK_EXCL, &ip)))
-			break;
+			goto error_cancel;
 		ASSERT(ip == mp->m_rsumip);
 		/*
 		 * Update the summary inode's size.
@@ -2005,7 +2006,7 @@ xfs_growfs_rt(
 		    mp->m_rsumlevels != nmp->m_rsumlevels) {
 			error = xfs_rtcopy_summary(mp, nmp, tp);
 			if (error)
-				break;
+				goto error_cancel;
 		}
 		/*
 		 * Update superblock fields.
@@ -2031,8 +2032,11 @@ xfs_growfs_rt(
 		bp = NULL;
 		error = xfs_rtfree_range(nmp, tp, sbp->sb_rextents,
 			nsbp->sb_rextents - sbp->sb_rextents, &bp, &sumbno);
-		if (error)
+		if (error) {
+error_cancel:
+			xfs_trans_cancel(tp, cancelflags);
 			break;
+		}
 		/*
 		 * Mark more blocks free in the superblock.
 		 */
@@ -2045,15 +2049,10 @@ xfs_growfs_rt(
 		mp->m_rsumsize = nrsumsize;
 
 		error = xfs_trans_commit(tp, 0);
-		if (error) {
-			tp = NULL;
+		if (error)
 			break;
-		}
 	}
 
-	if (error && tp)
-		xfs_trans_cancel(tp, cancelflags);
-
 	/*
 	 * Free the fake mp structure.
 	 */
diff --git a/fs/xfs/xfs_sb.h b/fs/xfs/xfs_sb.h
index 3f8cf1587f4c..e123c1499b4c 100644
--- a/fs/xfs/xfs_sb.h
+++ b/fs/xfs/xfs_sb.h
@@ -296,30 +296,34 @@ typedef enum {
 
 #define	XFS_SB_VERSION_NUM(sbp)	((sbp)->sb_versionnum & XFS_SB_VERSION_NUMBITS)
 
-#ifdef __KERNEL__
 static inline int xfs_sb_good_version(xfs_sb_t *sbp)
 {
-	return (((sbp->sb_versionnum >= XFS_SB_VERSION_1) && \
-		  (sbp->sb_versionnum <= XFS_SB_VERSION_3)) || \
-		   ((XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_4) && \
-		    !((sbp->sb_versionnum & ~XFS_SB_VERSION_OKREALBITS) || \
-		      ((sbp->sb_versionnum & XFS_SB_VERSION_MOREBITSBIT) && \
-		       (sbp->sb_features2 & ~XFS_SB_VERSION2_OKREALBITS))) && \
-	  	    (sbp->sb_shared_vn <= XFS_SB_MAX_SHARED_VN)));
-}
+	/* We always support version 1-3 */
+	if (sbp->sb_versionnum >= XFS_SB_VERSION_1 &&
+	    sbp->sb_versionnum <= XFS_SB_VERSION_3)
+		return 1;
+
+	/* We support version 4 if all feature bits are supported */
+	if (XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_4) {
+		if ((sbp->sb_versionnum & ~XFS_SB_VERSION_OKREALBITS) ||
+		    ((sbp->sb_versionnum & XFS_SB_VERSION_MOREBITSBIT) &&
+		     (sbp->sb_features2 & ~XFS_SB_VERSION2_OKREALBITS)))
+			return 0;
+
+#ifdef __KERNEL__
+		if (sbp->sb_shared_vn > XFS_SB_MAX_SHARED_VN)
+			return 0;
 #else
-static inline int xfs_sb_good_version(xfs_sb_t *sbp)
-{
-	return (((sbp->sb_versionnum >= XFS_SB_VERSION_1) && \
-		  (sbp->sb_versionnum <= XFS_SB_VERSION_3)) || \
-		   ((XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_4) && \
-		    !((sbp->sb_versionnum & ~XFS_SB_VERSION_OKREALBITS) || \
-		      ((sbp->sb_versionnum & XFS_SB_VERSION_MOREBITSBIT) && \
-		       (sbp->sb_features2 & ~XFS_SB_VERSION2_OKREALBITS))) && \
-		  (!(sbp->sb_versionnum & XFS_SB_VERSION_SHAREDBIT) || \
-		   (sbp->sb_shared_vn <= XFS_SB_MAX_SHARED_VN))));
+		if ((sbp->sb_versionnum & XFS_SB_VERSION_SHAREDBIT) &&
+		    sbp->sb_shared_vn > XFS_SB_MAX_SHARED_VN)
+			return 0;
+#endif
+
+		return 1;
+	}
+
+	return 0;
 }
-#endif /* __KERNEL__ */
 
 /*
  * Detect a mismatched features2 field.  Older kernels read/wrote
@@ -332,123 +336,127 @@ static inline int xfs_sb_has_mismatched_features2(xfs_sb_t *sbp)
 
 static inline unsigned xfs_sb_version_tonew(unsigned v)
 {
-	return ((((v) == XFS_SB_VERSION_1) ? \
-		0 : \
-		(((v) == XFS_SB_VERSION_2) ? \
-			XFS_SB_VERSION_ATTRBIT : \
-			(XFS_SB_VERSION_ATTRBIT | XFS_SB_VERSION_NLINKBIT))) | \
-		XFS_SB_VERSION_4);
+	if (v == XFS_SB_VERSION_1)
+		return XFS_SB_VERSION_4;
+
+	if (v == XFS_SB_VERSION_2)
+		return XFS_SB_VERSION_4 | XFS_SB_VERSION_ATTRBIT;
+
+	return XFS_SB_VERSION_4 | XFS_SB_VERSION_ATTRBIT |
+		XFS_SB_VERSION_NLINKBIT;
 }
 
 static inline unsigned xfs_sb_version_toold(unsigned v)
 {
-	return (((v) & (XFS_SB_VERSION_QUOTABIT | XFS_SB_VERSION_ALIGNBIT)) ? \
-		0 : \
-		(((v) & XFS_SB_VERSION_NLINKBIT) ? \
-			XFS_SB_VERSION_3 : \
-			(((v) & XFS_SB_VERSION_ATTRBIT) ?  \
-				XFS_SB_VERSION_2 : \
-				XFS_SB_VERSION_1)));
+	if (v & (XFS_SB_VERSION_QUOTABIT | XFS_SB_VERSION_ALIGNBIT))
+		return 0;
+	if (v & XFS_SB_VERSION_NLINKBIT)
+		return XFS_SB_VERSION_3;
+	if (v & XFS_SB_VERSION_ATTRBIT)
+		return XFS_SB_VERSION_2;
+	return XFS_SB_VERSION_1;
 }
 
 static inline int xfs_sb_version_hasattr(xfs_sb_t *sbp)
 {
-	return ((sbp)->sb_versionnum == XFS_SB_VERSION_2) || \
-		 ((sbp)->sb_versionnum == XFS_SB_VERSION_3) || \
-		 ((XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_4) && \
-		  ((sbp)->sb_versionnum & XFS_SB_VERSION_ATTRBIT));
+	return sbp->sb_versionnum == XFS_SB_VERSION_2 ||
+		sbp->sb_versionnum == XFS_SB_VERSION_3 ||
+		(XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_4 &&
+		 (sbp->sb_versionnum & XFS_SB_VERSION_ATTRBIT));
 }
 
 static inline void xfs_sb_version_addattr(xfs_sb_t *sbp)
 {
-	(sbp)->sb_versionnum = (((sbp)->sb_versionnum == XFS_SB_VERSION_1) ? \
-		XFS_SB_VERSION_2 : \
-		((XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_4) ? \
-			((sbp)->sb_versionnum | XFS_SB_VERSION_ATTRBIT) : \
-			(XFS_SB_VERSION_4 | XFS_SB_VERSION_ATTRBIT)));
+	if (sbp->sb_versionnum == XFS_SB_VERSION_1)
+		sbp->sb_versionnum = XFS_SB_VERSION_2;
+	else if (XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_4)
+		sbp->sb_versionnum |= XFS_SB_VERSION_ATTRBIT;
+	else
+		sbp->sb_versionnum = XFS_SB_VERSION_4 | XFS_SB_VERSION_ATTRBIT;
 }
 
 static inline int xfs_sb_version_hasnlink(xfs_sb_t *sbp)
 {
-	return ((sbp)->sb_versionnum == XFS_SB_VERSION_3) || \
-		 ((XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_4) && \
-		  ((sbp)->sb_versionnum & XFS_SB_VERSION_NLINKBIT));
+	return sbp->sb_versionnum == XFS_SB_VERSION_3 ||
+		 (XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_4 &&
+		  (sbp->sb_versionnum & XFS_SB_VERSION_NLINKBIT));
 }
 
 static inline void xfs_sb_version_addnlink(xfs_sb_t *sbp)
 {
-	(sbp)->sb_versionnum = ((sbp)->sb_versionnum <= XFS_SB_VERSION_2 ? \
-		XFS_SB_VERSION_3 : \
-		((sbp)->sb_versionnum | XFS_SB_VERSION_NLINKBIT));
+	if (sbp->sb_versionnum <= XFS_SB_VERSION_2)
+		sbp->sb_versionnum = XFS_SB_VERSION_3;
+	else
+		sbp->sb_versionnum |= XFS_SB_VERSION_NLINKBIT;
 }
 
 static inline int xfs_sb_version_hasquota(xfs_sb_t *sbp)
 {
-	return (XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_4) && \
-		((sbp)->sb_versionnum & XFS_SB_VERSION_QUOTABIT);
+	return XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_4 &&
+		(sbp->sb_versionnum & XFS_SB_VERSION_QUOTABIT);
 }
 
 static inline void xfs_sb_version_addquota(xfs_sb_t *sbp)
 {
-	(sbp)->sb_versionnum = \
-		 (XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_4 ? \
-			((sbp)->sb_versionnum | XFS_SB_VERSION_QUOTABIT) : \
-			(xfs_sb_version_tonew((sbp)->sb_versionnum) | \
-			 XFS_SB_VERSION_QUOTABIT));
+	if (XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_4)
+		sbp->sb_versionnum |= XFS_SB_VERSION_QUOTABIT;
+	else
+		sbp->sb_versionnum = xfs_sb_version_tonew(sbp->sb_versionnum) |
+					XFS_SB_VERSION_QUOTABIT;
 }
 
 static inline int xfs_sb_version_hasalign(xfs_sb_t *sbp)
 {
-	return (XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_4) && \
-		((sbp)->sb_versionnum & XFS_SB_VERSION_ALIGNBIT);
+	return XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_4 &&
+		(sbp->sb_versionnum & XFS_SB_VERSION_ALIGNBIT);
 }
 
 static inline int xfs_sb_version_hasdalign(xfs_sb_t *sbp)
 {
-	return (XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_4) && \
-		((sbp)->sb_versionnum & XFS_SB_VERSION_DALIGNBIT);
+	return XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_4 &&
+		(sbp->sb_versionnum & XFS_SB_VERSION_DALIGNBIT);
 }
 
 static inline int xfs_sb_version_hasshared(xfs_sb_t *sbp)
 {
-	return (XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_4) && \
-		((sbp)->sb_versionnum & XFS_SB_VERSION_SHAREDBIT);
+	return XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_4 &&
+		(sbp->sb_versionnum & XFS_SB_VERSION_SHAREDBIT);
 }
 
 static inline int xfs_sb_version_hasdirv2(xfs_sb_t *sbp)
 {
-	return (XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_4) && \
-		((sbp)->sb_versionnum & XFS_SB_VERSION_DIRV2BIT);
+	return XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_4 &&
+		(sbp->sb_versionnum & XFS_SB_VERSION_DIRV2BIT);
 }
 
 static inline int xfs_sb_version_haslogv2(xfs_sb_t *sbp)
 {
-	return (XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_4) && \
-		((sbp)->sb_versionnum & XFS_SB_VERSION_LOGV2BIT);
+	return XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_4 &&
+		(sbp->sb_versionnum & XFS_SB_VERSION_LOGV2BIT);
 }
 
 static inline int xfs_sb_version_hasextflgbit(xfs_sb_t *sbp)
 {
-	return (XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_4) && \
-		((sbp)->sb_versionnum & XFS_SB_VERSION_EXTFLGBIT);
+	return XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_4 &&
+		(sbp->sb_versionnum & XFS_SB_VERSION_EXTFLGBIT);
 }
 
 static inline int xfs_sb_version_hassector(xfs_sb_t *sbp)
 {
-	return (XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_4) && \
-		((sbp)->sb_versionnum & XFS_SB_VERSION_SECTORBIT);
+	return XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_4 &&
+		(sbp->sb_versionnum & XFS_SB_VERSION_SECTORBIT);
 }
 
 static inline int xfs_sb_version_hasasciici(xfs_sb_t *sbp)
 {
-	return (XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_4) && \
+	return XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_4 &&
 		(sbp->sb_versionnum & XFS_SB_VERSION_BORGBIT);
 }
 
 static inline int xfs_sb_version_hasmorebits(xfs_sb_t *sbp)
 {
-	return (XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_4) && \
-		((sbp)->sb_versionnum & XFS_SB_VERSION_MOREBITSBIT);
+	return XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_4 &&
+		(sbp->sb_versionnum & XFS_SB_VERSION_MOREBITSBIT);
 }
 
 /*
@@ -463,22 +471,20 @@ static inline int xfs_sb_version_hasmorebits(xfs_sb_t *sbp)
 
 static inline int xfs_sb_version_haslazysbcount(xfs_sb_t *sbp)
 {
-	return (xfs_sb_version_hasmorebits(sbp) &&	\
-		((sbp)->sb_features2 & XFS_SB_VERSION2_LAZYSBCOUNTBIT));
+	return xfs_sb_version_hasmorebits(sbp) &&
+		(sbp->sb_features2 & XFS_SB_VERSION2_LAZYSBCOUNTBIT);
 }
 
 static inline int xfs_sb_version_hasattr2(xfs_sb_t *sbp)
 {
-	return (xfs_sb_version_hasmorebits(sbp)) &&	\
-		((sbp)->sb_features2 & XFS_SB_VERSION2_ATTR2BIT);
+	return xfs_sb_version_hasmorebits(sbp) &&
+		(sbp->sb_features2 & XFS_SB_VERSION2_ATTR2BIT);
 }
 
 static inline void xfs_sb_version_addattr2(xfs_sb_t *sbp)
 {
-	((sbp)->sb_versionnum =	\
-		((sbp)->sb_versionnum | XFS_SB_VERSION_MOREBITSBIT),	\
-	((sbp)->sb_features2 =	\
-		((sbp)->sb_features2 | XFS_SB_VERSION2_ATTR2BIT)));
+	sbp->sb_versionnum |= XFS_SB_VERSION_MOREBITSBIT;
+	sbp->sb_features2 |= XFS_SB_VERSION2_ATTR2BIT;
 }
 
 static inline void xfs_sb_version_removeattr2(xfs_sb_t *sbp)
diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c
index 4e1c22a23be5..8570b826fedd 100644
--- a/fs/xfs/xfs_trans.c
+++ b/fs/xfs/xfs_trans.c
@@ -290,7 +290,7 @@ xfs_trans_dup(
 	ASSERT(tp->t_ticket != NULL);
 
 	ntp->t_flags = XFS_TRANS_PERM_LOG_RES | (tp->t_flags & XFS_TRANS_RESERVE);
-	ntp->t_ticket = tp->t_ticket;
+	ntp->t_ticket = xfs_log_ticket_get(tp->t_ticket);
 	ntp->t_blk_res = tp->t_blk_res - tp->t_blk_res_used;
 	tp->t_blk_res = tp->t_blk_res_used;
 	ntp->t_rtx_res = tp->t_rtx_res - tp->t_rtx_res_used;
@@ -1260,6 +1260,13 @@ xfs_trans_roll(
 	trans = *tpp;
 
 	/*
+	 * transaction commit worked ok so we can drop the extra ticket
+	 * reference that we gained in xfs_trans_dup()
+	 */
+	xfs_log_ticket_put(trans->t_ticket);
+
+
+	/*
 	 * Reserve space in the log for th next transaction.
 	 * This also pushes items in the "AIL", the list of logged items,
 	 * out to disk if they are taking up space at the tail of the log
@@ -1383,11 +1390,12 @@ xfs_trans_chunk_committed(
 	xfs_log_item_desc_t	*lidp;
 	xfs_log_item_t		*lip;
 	xfs_lsn_t		item_lsn;
-	struct xfs_mount	*mp;
 	int			i;
 
 	lidp = licp->lic_descs;
 	for (i = 0; i < licp->lic_unused; i++, lidp++) {
+		struct xfs_ail		*ailp;
+
 		if (xfs_lic_isfree(licp, i)) {
 			continue;
 		}
@@ -1424,19 +1432,19 @@ xfs_trans_chunk_committed(
 		 * This would cause the earlier transaction to fail
 		 * the test below.
 		 */
-		mp = lip->li_mountp;
-		spin_lock(&mp->m_ail_lock);
+		ailp = lip->li_ailp;
+		spin_lock(&ailp->xa_lock);
 		if (XFS_LSN_CMP(item_lsn, lip->li_lsn) > 0) {
 			/*
 			 * This will set the item's lsn to item_lsn
 			 * and update the position of the item in
 			 * the AIL.
 			 *
-			 * xfs_trans_update_ail() drops the AIL lock.
+			 * xfs_trans_ail_update() drops the AIL lock.
 			 */
-			xfs_trans_update_ail(mp, lip, item_lsn);
+			xfs_trans_ail_update(ailp, lip, item_lsn);
 		} else {
-			spin_unlock(&mp->m_ail_lock);
+			spin_unlock(&ailp->xa_lock);
 		}
 
 		/*
diff --git a/fs/xfs/xfs_trans.h b/fs/xfs/xfs_trans.h
index 74c80bd2b0ec..d6fe4a88d79f 100644
--- a/fs/xfs/xfs_trans.h
+++ b/fs/xfs/xfs_trans.h
@@ -18,6 +18,8 @@
 #ifndef	__XFS_TRANS_H__
 #define	__XFS_TRANS_H__
 
+struct xfs_log_item;
+
 /*
  * This is the structure written in the log at the head of
  * every transaction. It identifies the type and id of the
@@ -98,76 +100,6 @@ typedef struct xfs_trans_header {
 #define	XFS_TRANS_TYPE_MAX		41
 /* new transaction types need to be reflected in xfs_logprint(8) */
 
-
-#ifdef __KERNEL__
-struct xfs_buf;
-struct xfs_buftarg;
-struct xfs_efd_log_item;
-struct xfs_efi_log_item;
-struct xfs_inode;
-struct xfs_item_ops;
-struct xfs_log_iovec;
-struct xfs_log_item;
-struct xfs_log_item_desc;
-struct xfs_mount;
-struct xfs_trans;
-struct xfs_dquot_acct;
-
-typedef struct xfs_log_item {
-	struct list_head		li_ail;		/* AIL pointers */
-	xfs_lsn_t			li_lsn;		/* last on-disk lsn */
-	struct xfs_log_item_desc	*li_desc;	/* ptr to current desc*/
-	struct xfs_mount		*li_mountp;	/* ptr to fs mount */
-	uint				li_type;	/* item type */
-	uint				li_flags;	/* misc flags */
-	struct xfs_log_item		*li_bio_list;	/* buffer item list */
-	void				(*li_cb)(struct xfs_buf *,
-						 struct xfs_log_item *);
-							/* buffer item iodone */
-							/* callback func */
-	struct xfs_item_ops		*li_ops;	/* function list */
-} xfs_log_item_t;
-
-#define	XFS_LI_IN_AIL	0x1
-#define XFS_LI_ABORTED	0x2
-
-typedef struct xfs_item_ops {
-	uint (*iop_size)(xfs_log_item_t *);
-	void (*iop_format)(xfs_log_item_t *, struct xfs_log_iovec *);
-	void (*iop_pin)(xfs_log_item_t *);
-	void (*iop_unpin)(xfs_log_item_t *, int);
-	void (*iop_unpin_remove)(xfs_log_item_t *, struct xfs_trans *);
-	uint (*iop_trylock)(xfs_log_item_t *);
-	void (*iop_unlock)(xfs_log_item_t *);
-	xfs_lsn_t (*iop_committed)(xfs_log_item_t *, xfs_lsn_t);
-	void (*iop_push)(xfs_log_item_t *);
-	void (*iop_pushbuf)(xfs_log_item_t *);
-	void (*iop_committing)(xfs_log_item_t *, xfs_lsn_t);
-} xfs_item_ops_t;
-
-#define IOP_SIZE(ip)		(*(ip)->li_ops->iop_size)(ip)
-#define IOP_FORMAT(ip,vp)	(*(ip)->li_ops->iop_format)(ip, vp)
-#define IOP_PIN(ip)		(*(ip)->li_ops->iop_pin)(ip)
-#define IOP_UNPIN(ip, flags)	(*(ip)->li_ops->iop_unpin)(ip, flags)
-#define IOP_UNPIN_REMOVE(ip,tp) (*(ip)->li_ops->iop_unpin_remove)(ip, tp)
-#define IOP_TRYLOCK(ip)		(*(ip)->li_ops->iop_trylock)(ip)
-#define IOP_UNLOCK(ip)		(*(ip)->li_ops->iop_unlock)(ip)
-#define IOP_COMMITTED(ip, lsn)	(*(ip)->li_ops->iop_committed)(ip, lsn)
-#define IOP_PUSH(ip)		(*(ip)->li_ops->iop_push)(ip)
-#define IOP_PUSHBUF(ip)		(*(ip)->li_ops->iop_pushbuf)(ip)
-#define IOP_COMMITTING(ip, lsn) (*(ip)->li_ops->iop_committing)(ip, lsn)
-
-/*
- * Return values for the IOP_TRYLOCK() routines.
- */
-#define	XFS_ITEM_SUCCESS	0
-#define	XFS_ITEM_PINNED		1
-#define	XFS_ITEM_LOCKED		2
-#define	XFS_ITEM_FLUSHING	3
-#define XFS_ITEM_PUSHBUF	4
-
-#endif	/* __KERNEL__ */
-
 /*
  * This structure is used to track log items associated with
  * a transaction.  It points to the log item and keeps some
@@ -176,7 +108,7 @@ typedef struct xfs_item_ops {
  * once we get to commit processing (see xfs_trans_commit()).
  */
 typedef struct xfs_log_item_desc {
-	xfs_log_item_t	*lid_item;
+	struct xfs_log_item	*lid_item;
 	ushort		lid_size;
 	unsigned char	lid_flags;
 	unsigned char	lid_index;
@@ -276,94 +208,6 @@ xfs_lic_desc_to_chunk(xfs_log_item_desc_t *dp)
 		(xfs_caddr_t)(((xfs_log_item_chunk_t*)0)->lic_descs));
 }
 
-#ifdef __KERNEL__
-/*
- * This structure is used to maintain a list of block ranges that have been
- * freed in the transaction.  The ranges are listed in the perag[] busy list
- * between when they're freed and the transaction is committed to disk.
- */
-
-typedef struct xfs_log_busy_slot {
-	xfs_agnumber_t		lbc_ag;
-	ushort			lbc_idx;	/* index in perag.busy[] */
-} xfs_log_busy_slot_t;
-
-#define XFS_LBC_NUM_SLOTS	31
-typedef struct xfs_log_busy_chunk {
-	struct xfs_log_busy_chunk	*lbc_next;
-	uint				lbc_free;	/* free slots bitmask */
-	ushort				lbc_unused;	/* first unused */
-	xfs_log_busy_slot_t		lbc_busy[XFS_LBC_NUM_SLOTS];
-} xfs_log_busy_chunk_t;
-
-#define	XFS_LBC_MAX_SLOT	(XFS_LBC_NUM_SLOTS - 1)
-#define	XFS_LBC_FREEMASK	((1U << XFS_LBC_NUM_SLOTS) - 1)
-
-#define	XFS_LBC_INIT(cp)	((cp)->lbc_free = XFS_LBC_FREEMASK)
-#define	XFS_LBC_CLAIM(cp, slot)	((cp)->lbc_free &= ~(1 << (slot)))
-#define	XFS_LBC_SLOT(cp, slot)	(&((cp)->lbc_busy[(slot)]))
-#define	XFS_LBC_VACANCY(cp)	(((cp)->lbc_free) & XFS_LBC_FREEMASK)
-#define	XFS_LBC_ISFREE(cp, slot) ((cp)->lbc_free & (1 << (slot)))
-
-/*
- * This is the type of function which can be given to xfs_trans_callback()
- * to be called upon the transaction's commit to disk.
- */
-typedef void (*xfs_trans_callback_t)(struct xfs_trans *, void *);
-
-/*
- * This is the structure maintained for every active transaction.
- */
-typedef struct xfs_trans {
-	unsigned int		t_magic;	/* magic number */
-	xfs_log_callback_t	t_logcb;	/* log callback struct */
-	unsigned int		t_type;		/* transaction type */
-	unsigned int		t_log_res;	/* amt of log space resvd */
-	unsigned int		t_log_count;	/* count for perm log res */
-	unsigned int		t_blk_res;	/* # of blocks resvd */
-	unsigned int		t_blk_res_used;	/* # of resvd blocks used */
-	unsigned int		t_rtx_res;	/* # of rt extents resvd */
-	unsigned int		t_rtx_res_used;	/* # of resvd rt extents used */
-	xfs_log_ticket_t	t_ticket;	/* log mgr ticket */
-	xfs_lsn_t		t_lsn;		/* log seq num of start of
-						 * transaction. */
-	xfs_lsn_t		t_commit_lsn;	/* log seq num of end of
-						 * transaction. */
-	struct xfs_mount	*t_mountp;	/* ptr to fs mount struct */
-	struct xfs_dquot_acct   *t_dqinfo;	/* acctg info for dquots */
-	xfs_trans_callback_t	t_callback;	/* transaction callback */
-	void			*t_callarg;	/* callback arg */
-	unsigned int		t_flags;	/* misc flags */
-	int64_t			t_icount_delta;	/* superblock icount change */
-	int64_t			t_ifree_delta;	/* superblock ifree change */
-	int64_t			t_fdblocks_delta; /* superblock fdblocks chg */
-	int64_t			t_res_fdblocks_delta; /* on-disk only chg */
-	int64_t			t_frextents_delta;/* superblock freextents chg*/
-	int64_t			t_res_frextents_delta; /* on-disk only chg */
-#ifdef DEBUG
-	int64_t			t_ag_freeblks_delta; /* debugging counter */
-	int64_t			t_ag_flist_delta; /* debugging counter */
-	int64_t			t_ag_btree_delta; /* debugging counter */
-#endif
-	int64_t			t_dblocks_delta;/* superblock dblocks change */
-	int64_t			t_agcount_delta;/* superblock agcount change */
-	int64_t			t_imaxpct_delta;/* superblock imaxpct change */
-	int64_t			t_rextsize_delta;/* superblock rextsize chg */
-	int64_t			t_rbmblocks_delta;/* superblock rbmblocks chg */
-	int64_t			t_rblocks_delta;/* superblock rblocks change */
-	int64_t			t_rextents_delta;/* superblocks rextents chg */
-	int64_t			t_rextslog_delta;/* superblocks rextslog chg */
-	unsigned int		t_items_free;	/* log item descs free */
-	xfs_log_item_chunk_t	t_items;	/* first log item desc chunk */
-	xfs_trans_header_t	t_header;	/* header for in-log trans */
-	unsigned int		t_busy_free;	/* busy descs free */
-	xfs_log_busy_chunk_t	t_busy;		/* busy/async free blocks */
-	unsigned long		t_pflags;	/* saved process flags state */
-} xfs_trans_t;
-
-#endif	/* __KERNEL__ */
-
-
 #define	XFS_TRANS_MAGIC		0x5452414E	/* 'TRAN' */
 /*
  * Values for t_flags.
@@ -906,6 +750,157 @@ typedef struct xfs_trans {
 #define	XFS_DQUOT_REF		1
 
 #ifdef __KERNEL__
+
+struct xfs_buf;
+struct xfs_buftarg;
+struct xfs_efd_log_item;
+struct xfs_efi_log_item;
+struct xfs_inode;
+struct xfs_item_ops;
+struct xfs_log_iovec;
+struct xfs_log_item_desc;
+struct xfs_mount;
+struct xfs_trans;
+struct xfs_dquot_acct;
+
+typedef struct xfs_log_item {
+	struct list_head		li_ail;		/* AIL pointers */
+	xfs_lsn_t			li_lsn;		/* last on-disk lsn */
+	struct xfs_log_item_desc	*li_desc;	/* ptr to current desc*/
+	struct xfs_mount		*li_mountp;	/* ptr to fs mount */
+	struct xfs_ail			*li_ailp;	/* ptr to AIL */
+	uint				li_type;	/* item type */
+	uint				li_flags;	/* misc flags */
+	struct xfs_log_item		*li_bio_list;	/* buffer item list */
+	void				(*li_cb)(struct xfs_buf *,
+						 struct xfs_log_item *);
+							/* buffer item iodone */
+							/* callback func */
+	struct xfs_item_ops		*li_ops;	/* function list */
+} xfs_log_item_t;
+
+#define	XFS_LI_IN_AIL	0x1
+#define XFS_LI_ABORTED	0x2
+
+typedef struct xfs_item_ops {
+	uint (*iop_size)(xfs_log_item_t *);
+	void (*iop_format)(xfs_log_item_t *, struct xfs_log_iovec *);
+	void (*iop_pin)(xfs_log_item_t *);
+	void (*iop_unpin)(xfs_log_item_t *, int);
+	void (*iop_unpin_remove)(xfs_log_item_t *, struct xfs_trans *);
+	uint (*iop_trylock)(xfs_log_item_t *);
+	void (*iop_unlock)(xfs_log_item_t *);
+	xfs_lsn_t (*iop_committed)(xfs_log_item_t *, xfs_lsn_t);
+	void (*iop_push)(xfs_log_item_t *);
+	void (*iop_pushbuf)(xfs_log_item_t *);
+	void (*iop_committing)(xfs_log_item_t *, xfs_lsn_t);
+} xfs_item_ops_t;
+
+#define IOP_SIZE(ip)		(*(ip)->li_ops->iop_size)(ip)
+#define IOP_FORMAT(ip,vp)	(*(ip)->li_ops->iop_format)(ip, vp)
+#define IOP_PIN(ip)		(*(ip)->li_ops->iop_pin)(ip)
+#define IOP_UNPIN(ip, flags)	(*(ip)->li_ops->iop_unpin)(ip, flags)
+#define IOP_UNPIN_REMOVE(ip,tp) (*(ip)->li_ops->iop_unpin_remove)(ip, tp)
+#define IOP_TRYLOCK(ip)		(*(ip)->li_ops->iop_trylock)(ip)
+#define IOP_UNLOCK(ip)		(*(ip)->li_ops->iop_unlock)(ip)
+#define IOP_COMMITTED(ip, lsn)	(*(ip)->li_ops->iop_committed)(ip, lsn)
+#define IOP_PUSH(ip)		(*(ip)->li_ops->iop_push)(ip)
+#define IOP_PUSHBUF(ip)		(*(ip)->li_ops->iop_pushbuf)(ip)
+#define IOP_COMMITTING(ip, lsn) (*(ip)->li_ops->iop_committing)(ip, lsn)
+
+/*
+ * Return values for the IOP_TRYLOCK() routines.
+ */
+#define	XFS_ITEM_SUCCESS	0
+#define	XFS_ITEM_PINNED		1
+#define	XFS_ITEM_LOCKED		2
+#define	XFS_ITEM_FLUSHING	3
+#define XFS_ITEM_PUSHBUF	4
+
+/*
+ * This structure is used to maintain a list of block ranges that have been
+ * freed in the transaction.  The ranges are listed in the perag[] busy list
+ * between when they're freed and the transaction is committed to disk.
+ */
+
+typedef struct xfs_log_busy_slot {
+	xfs_agnumber_t		lbc_ag;
+	ushort			lbc_idx;	/* index in perag.busy[] */
+} xfs_log_busy_slot_t;
+
+#define XFS_LBC_NUM_SLOTS	31
+typedef struct xfs_log_busy_chunk {
+	struct xfs_log_busy_chunk	*lbc_next;
+	uint				lbc_free;	/* free slots bitmask */
+	ushort				lbc_unused;	/* first unused */
+	xfs_log_busy_slot_t		lbc_busy[XFS_LBC_NUM_SLOTS];
+} xfs_log_busy_chunk_t;
+
+#define	XFS_LBC_MAX_SLOT	(XFS_LBC_NUM_SLOTS - 1)
+#define	XFS_LBC_FREEMASK	((1U << XFS_LBC_NUM_SLOTS) - 1)
+
+#define	XFS_LBC_INIT(cp)	((cp)->lbc_free = XFS_LBC_FREEMASK)
+#define	XFS_LBC_CLAIM(cp, slot)	((cp)->lbc_free &= ~(1 << (slot)))
+#define	XFS_LBC_SLOT(cp, slot)	(&((cp)->lbc_busy[(slot)]))
+#define	XFS_LBC_VACANCY(cp)	(((cp)->lbc_free) & XFS_LBC_FREEMASK)
+#define	XFS_LBC_ISFREE(cp, slot) ((cp)->lbc_free & (1 << (slot)))
+
+/*
+ * This is the type of function which can be given to xfs_trans_callback()
+ * to be called upon the transaction's commit to disk.
+ */
+typedef void (*xfs_trans_callback_t)(struct xfs_trans *, void *);
+
+/*
+ * This is the structure maintained for every active transaction.
+ */
+typedef struct xfs_trans {
+	unsigned int		t_magic;	/* magic number */
+	xfs_log_callback_t	t_logcb;	/* log callback struct */
+	unsigned int		t_type;		/* transaction type */
+	unsigned int		t_log_res;	/* amt of log space resvd */
+	unsigned int		t_log_count;	/* count for perm log res */
+	unsigned int		t_blk_res;	/* # of blocks resvd */
+	unsigned int		t_blk_res_used;	/* # of resvd blocks used */
+	unsigned int		t_rtx_res;	/* # of rt extents resvd */
+	unsigned int		t_rtx_res_used;	/* # of resvd rt extents used */
+	xfs_log_ticket_t	t_ticket;	/* log mgr ticket */
+	xfs_lsn_t		t_lsn;		/* log seq num of start of
+						 * transaction. */
+	xfs_lsn_t		t_commit_lsn;	/* log seq num of end of
+						 * transaction. */
+	struct xfs_mount	*t_mountp;	/* ptr to fs mount struct */
+	struct xfs_dquot_acct   *t_dqinfo;	/* acctg info for dquots */
+	xfs_trans_callback_t	t_callback;	/* transaction callback */
+	void			*t_callarg;	/* callback arg */
+	unsigned int		t_flags;	/* misc flags */
+	int64_t			t_icount_delta;	/* superblock icount change */
+	int64_t			t_ifree_delta;	/* superblock ifree change */
+	int64_t			t_fdblocks_delta; /* superblock fdblocks chg */
+	int64_t			t_res_fdblocks_delta; /* on-disk only chg */
+	int64_t			t_frextents_delta;/* superblock freextents chg*/
+	int64_t			t_res_frextents_delta; /* on-disk only chg */
+#ifdef DEBUG
+	int64_t			t_ag_freeblks_delta; /* debugging counter */
+	int64_t			t_ag_flist_delta; /* debugging counter */
+	int64_t			t_ag_btree_delta; /* debugging counter */
+#endif
+	int64_t			t_dblocks_delta;/* superblock dblocks change */
+	int64_t			t_agcount_delta;/* superblock agcount change */
+	int64_t			t_imaxpct_delta;/* superblock imaxpct change */
+	int64_t			t_rextsize_delta;/* superblock rextsize chg */
+	int64_t			t_rbmblocks_delta;/* superblock rbmblocks chg */
+	int64_t			t_rblocks_delta;/* superblock rblocks change */
+	int64_t			t_rextents_delta;/* superblocks rextents chg */
+	int64_t			t_rextslog_delta;/* superblocks rextslog chg */
+	unsigned int		t_items_free;	/* log item descs free */
+	xfs_log_item_chunk_t	t_items;	/* first log item desc chunk */
+	xfs_trans_header_t	t_header;	/* header for in-log trans */
+	unsigned int		t_busy_free;	/* busy descs free */
+	xfs_log_busy_chunk_t	t_busy;		/* busy/async free blocks */
+	unsigned long		t_pflags;	/* saved process flags state */
+} xfs_trans_t;
+
 /*
  * XFS transaction mechanism exported interfaces that are
  * actually macros.
@@ -928,7 +923,6 @@ typedef struct xfs_trans {
 /*
  * XFS transaction mechanism exported interfaces.
  */
-void		xfs_trans_init(struct xfs_mount *);
 xfs_trans_t	*xfs_trans_alloc(struct xfs_mount *, uint);
 xfs_trans_t	*_xfs_trans_alloc(struct xfs_mount *, uint);
 xfs_trans_t	*xfs_trans_dup(xfs_trans_t *);
@@ -975,13 +969,8 @@ int		_xfs_trans_commit(xfs_trans_t *,
 				  int *);
 #define xfs_trans_commit(tp, flags)	_xfs_trans_commit(tp, flags, NULL)
 void		xfs_trans_cancel(xfs_trans_t *, int);
-int		xfs_trans_roll(struct xfs_trans **, struct xfs_inode *);
 int		xfs_trans_ail_init(struct xfs_mount *);
 void		xfs_trans_ail_destroy(struct xfs_mount *);
-void		xfs_trans_push_ail(struct xfs_mount *, xfs_lsn_t);
-xfs_lsn_t	xfs_trans_tail_ail(struct xfs_mount *);
-void		xfs_trans_unlocked_item(struct xfs_mount *,
-					xfs_log_item_t *);
 xfs_log_busy_slot_t *xfs_trans_add_busy(xfs_trans_t *tp,
 					xfs_agnumber_t ag,
 					xfs_extlen_t idx);
@@ -990,4 +979,7 @@ extern kmem_zone_t	*xfs_trans_zone;
 
 #endif	/* __KERNEL__ */
 
+void		xfs_trans_init(struct xfs_mount *);
+int		xfs_trans_roll(struct xfs_trans **, struct xfs_inode *);
+
 #endif	/* __XFS_TRANS_H__ */
diff --git a/fs/xfs/xfs_trans_ail.c b/fs/xfs/xfs_trans_ail.c
index 1f77c00af566..2d47f10f8bed 100644
--- a/fs/xfs/xfs_trans_ail.c
+++ b/fs/xfs/xfs_trans_ail.c
@@ -1,5 +1,6 @@
 /*
  * Copyright (c) 2000-2002,2005 Silicon Graphics, Inc.
+ * Copyright (c) 2008 Dave Chinner
  * All Rights Reserved.
  *
  * This program is free software; you can redistribute it and/or
@@ -28,13 +29,13 @@
 #include "xfs_trans_priv.h"
 #include "xfs_error.h"
 
-STATIC void xfs_ail_insert(xfs_ail_t *, xfs_log_item_t *);
-STATIC xfs_log_item_t * xfs_ail_delete(xfs_ail_t *, xfs_log_item_t *);
-STATIC xfs_log_item_t * xfs_ail_min(xfs_ail_t *);
-STATIC xfs_log_item_t * xfs_ail_next(xfs_ail_t *, xfs_log_item_t *);
+STATIC void xfs_ail_insert(struct xfs_ail *, xfs_log_item_t *);
+STATIC xfs_log_item_t * xfs_ail_delete(struct xfs_ail *, xfs_log_item_t *);
+STATIC xfs_log_item_t * xfs_ail_min(struct xfs_ail *);
+STATIC xfs_log_item_t * xfs_ail_next(struct xfs_ail *, xfs_log_item_t *);
 
 #ifdef DEBUG
-STATIC void xfs_ail_check(xfs_ail_t *, xfs_log_item_t *);
+STATIC void xfs_ail_check(struct xfs_ail *, xfs_log_item_t *);
 #else
 #define	xfs_ail_check(a,l)
 #endif /* DEBUG */
@@ -50,20 +51,20 @@ STATIC void xfs_ail_check(xfs_ail_t *, xfs_log_item_t *);
  * lsn of the last item in the AIL.
  */
 xfs_lsn_t
-xfs_trans_tail_ail(
-	xfs_mount_t	*mp)
+xfs_trans_ail_tail(
+	struct xfs_ail	*ailp)
 {
 	xfs_lsn_t	lsn;
 	xfs_log_item_t	*lip;
 
-	spin_lock(&mp->m_ail_lock);
-	lip = xfs_ail_min(&mp->m_ail);
+	spin_lock(&ailp->xa_lock);
+	lip = xfs_ail_min(ailp);
 	if (lip == NULL) {
 		lsn = (xfs_lsn_t)0;
 	} else {
 		lsn = lip->li_lsn;
 	}
-	spin_unlock(&mp->m_ail_lock);
+	spin_unlock(&ailp->xa_lock);
 
 	return lsn;
 }
@@ -85,16 +86,125 @@ xfs_trans_tail_ail(
  * any of the objects, so the lock is not needed.
  */
 void
-xfs_trans_push_ail(
-	xfs_mount_t		*mp,
-	xfs_lsn_t		threshold_lsn)
+xfs_trans_ail_push(
+	struct xfs_ail	*ailp,
+	xfs_lsn_t	threshold_lsn)
 {
-	xfs_log_item_t		*lip;
+	xfs_log_item_t	*lip;
+
+	lip = xfs_ail_min(ailp);
+	if (lip && !XFS_FORCED_SHUTDOWN(ailp->xa_mount)) {
+		if (XFS_LSN_CMP(threshold_lsn, ailp->xa_target) > 0)
+			xfsaild_wakeup(ailp, threshold_lsn);
+	}
+}
+
+/*
+ * AIL traversal cursor initialisation.
+ *
+ * The cursor keeps track of where our current traversal is up
+ * to by tracking the next ƣtem in the list for us. However, for
+ * this to be safe, removing an object from the AIL needs to invalidate
+ * any cursor that points to it. hence the traversal cursor needs to
+ * be linked to the struct xfs_ail so that deletion can search all the
+ * active cursors for invalidation.
+ *
+ * We don't link the push cursor because it is embedded in the struct
+ * xfs_ail and hence easily findable.
+ */
+STATIC void
+xfs_trans_ail_cursor_init(
+	struct xfs_ail		*ailp,
+	struct xfs_ail_cursor	*cur)
+{
+	cur->item = NULL;
+	if (cur == &ailp->xa_cursors)
+		return;
+
+	cur->next = ailp->xa_cursors.next;
+	ailp->xa_cursors.next = cur;
+}
+
+/*
+ * Set the cursor to the next item, because when we look
+ * up the cursor the current item may have been freed.
+ */
+STATIC void
+xfs_trans_ail_cursor_set(
+	struct xfs_ail		*ailp,
+	struct xfs_ail_cursor	*cur,
+	struct xfs_log_item	*lip)
+{
+	if (lip)
+		cur->item = xfs_ail_next(ailp, lip);
+}
+
+/*
+ * Get the next item in the traversal and advance the cursor.
+ * If the cursor was invalidated (inidicated by a lip of 1),
+ * restart the traversal.
+ */
+struct xfs_log_item *
+xfs_trans_ail_cursor_next(
+	struct xfs_ail		*ailp,
+	struct xfs_ail_cursor	*cur)
+{
+	struct xfs_log_item	*lip = cur->item;
+
+	if ((__psint_t)lip & 1)
+		lip = xfs_ail_min(ailp);
+	xfs_trans_ail_cursor_set(ailp, cur, lip);
+	return lip;
+}
+
+/*
+ * Now that the traversal is complete, we need to remove the cursor
+ * from the list of traversing cursors. Avoid removing the embedded
+ * push cursor, but use the fact it is alway present to make the
+ * list deletion simple.
+ */
+void
+xfs_trans_ail_cursor_done(
+	struct xfs_ail		*ailp,
+	struct xfs_ail_cursor	*done)
+{
+	struct xfs_ail_cursor	*prev = NULL;
+	struct xfs_ail_cursor	*cur;
+
+	done->item = NULL;
+	if (done == &ailp->xa_cursors)
+		return;
+	prev = &ailp->xa_cursors;
+	for (cur = prev->next; cur; prev = cur, cur = prev->next) {
+		if (cur == done) {
+			prev->next = cur->next;
+			break;
+		}
+	}
+	ASSERT(cur);
+}
+
+/*
+ * Invalidate any cursor that is pointing to this item. This is
+ * called when an item is removed from the AIL. Any cursor pointing
+ * to this object is now invalid and the traversal needs to be
+ * terminated so it doesn't reference a freed object. We set the
+ * cursor item to a value of 1 so we can distinguish between an
+ * invalidation and the end of the list when getting the next item
+ * from the cursor.
+ */
+STATIC void
+xfs_trans_ail_cursor_clear(
+	struct xfs_ail		*ailp,
+	struct xfs_log_item	*lip)
+{
+	struct xfs_ail_cursor	*cur;
 
-	lip = xfs_ail_min(&mp->m_ail);
-	if (lip && !XFS_FORCED_SHUTDOWN(mp)) {
-		if (XFS_LSN_CMP(threshold_lsn, mp->m_ail.xa_target) > 0)
-			xfsaild_wakeup(mp, threshold_lsn);
+	/* need to search all cursors */
+	for (cur = &ailp->xa_cursors; cur; cur = cur->next) {
+		if (cur->item == lip)
+			cur->item = (struct xfs_log_item *)
+					((__psint_t)cur->item | 1);
 	}
 }
 
@@ -103,25 +213,27 @@ xfs_trans_push_ail(
  * Return the current tree generation number for use
  * in calls to xfs_trans_next_ail().
  */
-STATIC xfs_log_item_t *
-xfs_trans_first_push_ail(
-	xfs_mount_t	*mp,
-	int		*gen,
-	xfs_lsn_t	lsn)
+xfs_log_item_t *
+xfs_trans_ail_cursor_first(
+	struct xfs_ail		*ailp,
+	struct xfs_ail_cursor	*cur,
+	xfs_lsn_t		lsn)
 {
-	xfs_log_item_t	*lip;
+	xfs_log_item_t		*lip;
 
-	lip = xfs_ail_min(&mp->m_ail);
-	*gen = (int)mp->m_ail.xa_gen;
+	xfs_trans_ail_cursor_init(ailp, cur);
+	lip = xfs_ail_min(ailp);
 	if (lsn == 0)
-		return lip;
+		goto out;
 
-	list_for_each_entry(lip, &mp->m_ail.xa_ail, li_ail) {
+	list_for_each_entry(lip, &ailp->xa_ail, li_ail) {
 		if (XFS_LSN_CMP(lip->li_lsn, lsn) >= 0)
-			return lip;
+			goto out;
 	}
-
-	return NULL;
+	lip = NULL;
+out:
+	xfs_trans_ail_cursor_set(ailp, cur, lip);
+	return lip;
 }
 
 /*
@@ -129,29 +241,29 @@ xfs_trans_first_push_ail(
  */
 long
 xfsaild_push(
-	xfs_mount_t	*mp,
+	struct xfs_ail	*ailp,
 	xfs_lsn_t	*last_lsn)
 {
 	long		tout = 1000; /* milliseconds */
 	xfs_lsn_t	last_pushed_lsn = *last_lsn;
-	xfs_lsn_t	target =  mp->m_ail.xa_target;
+	xfs_lsn_t	target =  ailp->xa_target;
 	xfs_lsn_t	lsn;
 	xfs_log_item_t	*lip;
-	int		gen;
-	int		restarts;
 	int		flush_log, count, stuck;
+	xfs_mount_t	*mp = ailp->xa_mount;
+	struct xfs_ail_cursor	*cur = &ailp->xa_cursors;
 
-#define	XFS_TRANS_PUSH_AIL_RESTARTS	10
-
-	spin_lock(&mp->m_ail_lock);
-	lip = xfs_trans_first_push_ail(mp, &gen, *last_lsn);
+	spin_lock(&ailp->xa_lock);
+	xfs_trans_ail_cursor_init(ailp, cur);
+	lip = xfs_trans_ail_cursor_first(ailp, cur, *last_lsn);
 	if (!lip || XFS_FORCED_SHUTDOWN(mp)) {
 		/*
 		 * AIL is empty or our push has reached the end.
 		 */
-		spin_unlock(&mp->m_ail_lock);
+		xfs_trans_ail_cursor_done(ailp, cur);
+		spin_unlock(&ailp->xa_lock);
 		last_pushed_lsn = 0;
-		goto out;
+		return tout;
 	}
 
 	XFS_STATS_INC(xs_push_ail);
@@ -169,7 +281,7 @@ xfsaild_push(
 	 */
 	tout = 10;
 	lsn = lip->li_lsn;
-	flush_log = stuck = count = restarts = 0;
+	flush_log = stuck = count = 0;
 	while ((XFS_LSN_CMP(lip->li_lsn, target) < 0)) {
 		int	lock_result;
 		/*
@@ -184,7 +296,7 @@ xfsaild_push(
 		 * skip to the next item in the list.
 		 */
 		lock_result = IOP_TRYLOCK(lip);
-		spin_unlock(&mp->m_ail_lock);
+		spin_unlock(&ailp->xa_lock);
 		switch (lock_result) {
 		case XFS_ITEM_SUCCESS:
 			XFS_STATS_INC(xs_push_ail_success);
@@ -221,7 +333,7 @@ xfsaild_push(
 			break;
 		}
 
-		spin_lock(&mp->m_ail_lock);
+		spin_lock(&ailp->xa_lock);
 		/* should we bother continuing? */
 		if (XFS_FORCED_SHUTDOWN(mp))
 			break;
@@ -244,14 +356,13 @@ xfsaild_push(
 		if (stuck > 100)
 			break;
 
-		lip = xfs_trans_next_ail(mp, lip, &gen, &restarts);
+		lip = xfs_trans_ail_cursor_next(ailp, cur);
 		if (lip == NULL)
 			break;
-		if (restarts > XFS_TRANS_PUSH_AIL_RESTARTS)
-			break;
 		lsn = lip->li_lsn;
 	}
-	spin_unlock(&mp->m_ail_lock);
+	xfs_trans_ail_cursor_done(ailp, cur);
+	spin_unlock(&ailp->xa_lock);
 
 	if (flush_log) {
 		/*
@@ -274,8 +385,7 @@ xfsaild_push(
 		 */
 		tout += 20;
 		last_pushed_lsn = 0;
-	} else if ((restarts > XFS_TRANS_PUSH_AIL_RESTARTS) ||
-		   ((stuck * 100) / count > 90)) {
+	} else if ((stuck * 100) / count > 90) {
 		/*
 		 * Either there is a lot of contention on the AIL or we
 		 * are stuck due to operations in progress. "Stuck" in this
@@ -287,7 +397,6 @@ xfsaild_push(
 		 */
 		tout += 10;
 	}
-out:
 	*last_lsn = last_pushed_lsn;
 	return tout;
 }	/* xfsaild_push */
@@ -303,7 +412,7 @@ out:
  */
 void
 xfs_trans_unlocked_item(
-	xfs_mount_t	*mp,
+	struct xfs_ail	*ailp,
 	xfs_log_item_t	*lip)
 {
 	xfs_log_item_t	*min_lip;
@@ -315,7 +424,7 @@ xfs_trans_unlocked_item(
 	 * over some potentially valid data.
 	 */
 	if (!(lip->li_flags & XFS_LI_IN_AIL) ||
-	    XFS_FORCED_SHUTDOWN(mp)) {
+	    XFS_FORCED_SHUTDOWN(ailp->xa_mount)) {
 		return;
 	}
 
@@ -331,10 +440,10 @@ xfs_trans_unlocked_item(
 	 * the call to xfs_log_move_tail() doesn't do anything if there's
 	 * not enough free space to wake people up so we're safe calling it.
 	 */
-	min_lip = xfs_ail_min(&mp->m_ail);
+	min_lip = xfs_ail_min(ailp);
 
 	if (min_lip == lip)
-		xfs_log_move_tail(mp, 1);
+		xfs_log_move_tail(ailp->xa_mount, 1);
 }	/* xfs_trans_unlocked_item */
 
 
@@ -347,41 +456,37 @@ xfs_trans_unlocked_item(
  * we move in the AIL is the minimum one, update the tail lsn in the
  * log manager.
  *
- * Increment the AIL's generation count to indicate that the tree
- * has changed.
- *
  * This function must be called with the AIL lock held.  The lock
  * is dropped before returning.
  */
 void
-xfs_trans_update_ail(
-	xfs_mount_t	*mp,
+xfs_trans_ail_update(
+	struct xfs_ail	*ailp,
 	xfs_log_item_t	*lip,
-	xfs_lsn_t	lsn) __releases(mp->m_ail_lock)
+	xfs_lsn_t	lsn) __releases(ailp->xa_lock)
 {
-	xfs_log_item_t		*dlip=NULL;
+	xfs_log_item_t		*dlip = NULL;
 	xfs_log_item_t		*mlip;	/* ptr to minimum lip */
 
-	mlip = xfs_ail_min(&mp->m_ail);
+	mlip = xfs_ail_min(ailp);
 
 	if (lip->li_flags & XFS_LI_IN_AIL) {
-		dlip = xfs_ail_delete(&mp->m_ail, lip);
+		dlip = xfs_ail_delete(ailp, lip);
 		ASSERT(dlip == lip);
+		xfs_trans_ail_cursor_clear(ailp, dlip);
 	} else {
 		lip->li_flags |= XFS_LI_IN_AIL;
 	}
 
 	lip->li_lsn = lsn;
-
-	xfs_ail_insert(&mp->m_ail, lip);
-	mp->m_ail.xa_gen++;
+	xfs_ail_insert(ailp, lip);
 
 	if (mlip == dlip) {
-		mlip = xfs_ail_min(&mp->m_ail);
-		spin_unlock(&mp->m_ail_lock);
-		xfs_log_move_tail(mp, mlip->li_lsn);
+		mlip = xfs_ail_min(ailp);
+		spin_unlock(&ailp->xa_lock);
+		xfs_log_move_tail(ailp->xa_mount, mlip->li_lsn);
 	} else {
-		spin_unlock(&mp->m_ail_lock);
+		spin_unlock(&ailp->xa_lock);
 	}
 
 
@@ -403,29 +508,30 @@ xfs_trans_update_ail(
  * is dropped before returning.
  */
 void
-xfs_trans_delete_ail(
-	xfs_mount_t	*mp,
-	xfs_log_item_t	*lip) __releases(mp->m_ail_lock)
+xfs_trans_ail_delete(
+	struct xfs_ail	*ailp,
+	xfs_log_item_t	*lip) __releases(ailp->xa_lock)
 {
 	xfs_log_item_t		*dlip;
 	xfs_log_item_t		*mlip;
 
 	if (lip->li_flags & XFS_LI_IN_AIL) {
-		mlip = xfs_ail_min(&mp->m_ail);
-		dlip = xfs_ail_delete(&mp->m_ail, lip);
+		mlip = xfs_ail_min(ailp);
+		dlip = xfs_ail_delete(ailp, lip);
 		ASSERT(dlip == lip);
+		xfs_trans_ail_cursor_clear(ailp, dlip);
 
 
 		lip->li_flags &= ~XFS_LI_IN_AIL;
 		lip->li_lsn = 0;
-		mp->m_ail.xa_gen++;
 
 		if (mlip == dlip) {
-			mlip = xfs_ail_min(&mp->m_ail);
-			spin_unlock(&mp->m_ail_lock);
-			xfs_log_move_tail(mp, (mlip ? mlip->li_lsn : 0));
+			mlip = xfs_ail_min(ailp);
+			spin_unlock(&ailp->xa_lock);
+			xfs_log_move_tail(ailp->xa_mount,
+						(mlip ? mlip->li_lsn : 0));
 		} else {
-			spin_unlock(&mp->m_ail_lock);
+			spin_unlock(&ailp->xa_lock);
 		}
 	}
 	else {
@@ -433,13 +539,13 @@ xfs_trans_delete_ail(
 		 * If the file system is not being shutdown, we are in
 		 * serious trouble if we get to this stage.
 		 */
-		if (XFS_FORCED_SHUTDOWN(mp))
-			spin_unlock(&mp->m_ail_lock);
-		else {
+		struct xfs_mount	*mp = ailp->xa_mount;
+
+		spin_unlock(&ailp->xa_lock);
+		if (!XFS_FORCED_SHUTDOWN(mp)) {
 			xfs_cmn_err(XFS_PTAG_AILDELETE, CE_ALERT, mp,
 		"%s: attempting to delete a log item that is not in the AIL",
 					__func__);
-			spin_unlock(&mp->m_ail_lock);
 			xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE);
 		}
 	}
@@ -448,56 +554,6 @@ xfs_trans_delete_ail(
 
 
 /*
- * Return the item in the AIL with the smallest lsn.
- * Return the current tree generation number for use
- * in calls to xfs_trans_next_ail().
- */
-xfs_log_item_t *
-xfs_trans_first_ail(
-	xfs_mount_t	*mp,
-	int		*gen)
-{
-	xfs_log_item_t	*lip;
-
-	lip = xfs_ail_min(&mp->m_ail);
-	*gen = (int)mp->m_ail.xa_gen;
-
-	return lip;
-}
-
-/*
- * If the generation count of the tree has not changed since the
- * caller last took something from the AIL, then return the elmt
- * in the tree which follows the one given.  If the count has changed,
- * then return the minimum elmt of the AIL and bump the restarts counter
- * if one is given.
- */
-xfs_log_item_t *
-xfs_trans_next_ail(
-	xfs_mount_t	*mp,
-	xfs_log_item_t	*lip,
-	int		*gen,
-	int		*restarts)
-{
-	xfs_log_item_t	*nlip;
-
-	ASSERT(mp && lip && gen);
-	if (mp->m_ail.xa_gen == *gen) {
-		nlip = xfs_ail_next(&mp->m_ail, lip);
-	} else {
-		nlip = xfs_ail_min(&mp->m_ail);
-		*gen = (int)mp->m_ail.xa_gen;
-		if (restarts != NULL) {
-			XFS_STATS_INC(xs_push_ail_restarts);
-			(*restarts)++;
-		}
-	}
-
-	return (nlip);
-}
-
-
-/*
  * The active item list (AIL) is a doubly linked list of log
  * items sorted by ascending lsn.  The base of the list is
  * a forw/back pointer pair embedded in the xfs mount structure.
@@ -515,15 +571,35 @@ int
 xfs_trans_ail_init(
 	xfs_mount_t	*mp)
 {
-	INIT_LIST_HEAD(&mp->m_ail.xa_ail);
-	return xfsaild_start(mp);
+	struct xfs_ail	*ailp;
+	int		error;
+
+	ailp = kmem_zalloc(sizeof(struct xfs_ail), KM_MAYFAIL);
+	if (!ailp)
+		return ENOMEM;
+
+	ailp->xa_mount = mp;
+	INIT_LIST_HEAD(&ailp->xa_ail);
+	spin_lock_init(&ailp->xa_lock);
+	error = xfsaild_start(ailp);
+	if (error)
+		goto out_free_ailp;
+	mp->m_ail = ailp;
+	return 0;
+
+out_free_ailp:
+	kmem_free(ailp);
+	return error;
 }
 
 void
 xfs_trans_ail_destroy(
 	xfs_mount_t	*mp)
 {
-	xfsaild_stop(mp);
+	struct xfs_ail	*ailp = mp->m_ail;
+
+	xfsaild_stop(ailp);
+	kmem_free(ailp);
 }
 
 /*
@@ -534,7 +610,7 @@ xfs_trans_ail_destroy(
  */
 STATIC void
 xfs_ail_insert(
-	xfs_ail_t	*ailp,
+	struct xfs_ail	*ailp,
 	xfs_log_item_t	*lip)
 /* ARGSUSED */
 {
@@ -568,7 +644,7 @@ xfs_ail_insert(
 /*ARGSUSED*/
 STATIC xfs_log_item_t *
 xfs_ail_delete(
-	xfs_ail_t	*ailp,
+	struct xfs_ail	*ailp,
 	xfs_log_item_t	*lip)
 /* ARGSUSED */
 {
@@ -585,7 +661,7 @@ xfs_ail_delete(
  */
 STATIC xfs_log_item_t *
 xfs_ail_min(
-	xfs_ail_t	*ailp)
+	struct xfs_ail	*ailp)
 /* ARGSUSED */
 {
 	if (list_empty(&ailp->xa_ail))
@@ -601,7 +677,7 @@ xfs_ail_min(
  */
 STATIC xfs_log_item_t *
 xfs_ail_next(
-	xfs_ail_t	*ailp,
+	struct xfs_ail	*ailp,
 	xfs_log_item_t	*lip)
 /* ARGSUSED */
 {
@@ -617,7 +693,7 @@ xfs_ail_next(
  */
 STATIC void
 xfs_ail_check(
-	xfs_ail_t 	*ailp,
+	struct xfs_ail	*ailp,
 	xfs_log_item_t	*lip)
 {
 	xfs_log_item_t	*prev_lip;
diff --git a/fs/xfs/xfs_trans_buf.c b/fs/xfs/xfs_trans_buf.c
index 4e855b5ced66..8ee2f8c8b0a6 100644
--- a/fs/xfs/xfs_trans_buf.c
+++ b/fs/xfs/xfs_trans_buf.c
@@ -527,9 +527,8 @@ xfs_trans_brelse(xfs_trans_t	*tp,
 			lip = XFS_BUF_FSPRIVATE(bp, xfs_log_item_t *);
 			if (lip->li_type == XFS_LI_BUF) {
 				bip = XFS_BUF_FSPRIVATE(bp,xfs_buf_log_item_t*);
-				xfs_trans_unlocked_item(
-						bip->bli_item.li_mountp,
-						lip);
+				xfs_trans_unlocked_item(bip->bli_item.li_ailp,
+							lip);
 			}
 		}
 		xfs_buf_relse(bp);
@@ -626,7 +625,7 @@ xfs_trans_brelse(xfs_trans_t	*tp,
 	 * tell the AIL that the buffer is being unlocked.
 	 */
 	if (bip != NULL) {
-		xfs_trans_unlocked_item(bip->bli_item.li_mountp,
+		xfs_trans_unlocked_item(bip->bli_item.li_ailp,
 					(xfs_log_item_t*)bip);
 	}
 
diff --git a/fs/xfs/xfs_trans_inode.c b/fs/xfs/xfs_trans_inode.c
index 2a1c0f071f91..23d276af2e0c 100644
--- a/fs/xfs/xfs_trans_inode.c
+++ b/fs/xfs/xfs_trans_inode.c
@@ -85,7 +85,6 @@ xfs_trans_iget(
 {
 	int			error;
 	xfs_inode_t		*ip;
-	xfs_inode_log_item_t	*iip;
 
 	/*
 	 * If the transaction pointer is NULL, just call the normal
@@ -138,34 +137,7 @@ xfs_trans_iget(
 	}
 	ASSERT(ip != NULL);
 
-	/*
-	 * Get a log_item_desc to point at the new item.
-	 */
-	if (ip->i_itemp == NULL)
-		xfs_inode_item_init(ip, mp);
-	iip = ip->i_itemp;
-	(void) xfs_trans_add_item(tp, (xfs_log_item_t *)(iip));
-
-	xfs_trans_inode_broot_debug(ip);
-
-	/*
-	 * If the IO lock has been acquired, mark that in
-	 * the inode log item so we'll know to unlock it
-	 * when the transaction commits.
-	 */
-	ASSERT(iip->ili_flags == 0);
-	if (lock_flags & XFS_IOLOCK_EXCL) {
-		iip->ili_flags |= XFS_ILI_IOLOCKED_EXCL;
-	} else if (lock_flags & XFS_IOLOCK_SHARED) {
-		iip->ili_flags |= XFS_ILI_IOLOCKED_SHARED;
-	}
-
-	/*
-	 * Initialize i_transp so we can find it with xfs_inode_incore()
-	 * above.
-	 */
-	ip->i_transp = tp;
-
+	xfs_trans_ijoin(tp, ip, lock_flags);
 	*ipp = ip;
 	return 0;
 }
diff --git a/fs/xfs/xfs_trans_item.c b/fs/xfs/xfs_trans_item.c
index 3c666e8317f8..e110bf57d7f4 100644
--- a/fs/xfs/xfs_trans_item.c
+++ b/fs/xfs/xfs_trans_item.c
@@ -22,6 +22,14 @@
 #include "xfs_inum.h"
 #include "xfs_trans.h"
 #include "xfs_trans_priv.h"
+/* XXX: from here down needed until struct xfs_trans has it's own ailp */
+#include "xfs_bit.h"
+#include "xfs_buf_item.h"
+#include "xfs_sb.h"
+#include "xfs_ag.h"
+#include "xfs_dir2.h"
+#include "xfs_dmapi.h"
+#include "xfs_mount.h"
 
 STATIC int	xfs_trans_unlock_chunk(xfs_log_item_chunk_t *,
 					int, int, xfs_lsn_t);
@@ -79,6 +87,7 @@ xfs_trans_add_item(xfs_trans_t *tp, xfs_log_item_t *lip)
 		lidp->lid_size = 0;
 		lip->li_desc = lidp;
 		lip->li_mountp = tp->t_mountp;
+		lip->li_ailp = tp->t_mountp->m_ail;
 		return lidp;
 	}
 
@@ -120,6 +129,7 @@ xfs_trans_add_item(xfs_trans_t *tp, xfs_log_item_t *lip)
 	lidp->lid_size = 0;
 	lip->li_desc = lidp;
 	lip->li_mountp = tp->t_mountp;
+	lip->li_ailp = tp->t_mountp->m_ail;
 	return lidp;
 }
 
diff --git a/fs/xfs/xfs_trans_priv.h b/fs/xfs/xfs_trans_priv.h
index 3c748c456ed4..73e2ad397432 100644
--- a/fs/xfs/xfs_trans_priv.h
+++ b/fs/xfs/xfs_trans_priv.h
@@ -44,25 +44,93 @@ xfs_log_busy_slot_t		*xfs_trans_add_busy(xfs_trans_t *tp,
 						    xfs_extlen_t idx);
 
 /*
- * From xfs_trans_ail.c
+ * AIL traversal cursor.
+ *
+ * Rather than using a generation number for detecting changes in the ail, use
+ * a cursor that is protected by the ail lock. The aild cursor exists in the
+ * struct xfs_ail, but other traversals can declare it on the stack and link it
+ * to the ail list.
+ *
+ * When an object is deleted from or moved int the AIL, the cursor list is
+ * searched to see if the object is a designated cursor item. If it is, it is
+ * deleted from the cursor so that the next time the cursor is used traversal
+ * will return to the start.
+ *
+ * This means a traversal colliding with a removal will cause a restart of the
+ * list scan, rather than any insertion or deletion anywhere in the list. The
+ * low bit of the item pointer is set if the cursor has been invalidated so
+ * that we can tell the difference between invalidation and reaching the end
+ * of the list to trigger traversal restarts.
  */
-void			xfs_trans_update_ail(struct xfs_mount *mp,
-				     struct xfs_log_item *lip, xfs_lsn_t lsn)
-				     __releases(mp->m_ail_lock);
-void			xfs_trans_delete_ail(struct xfs_mount *mp,
-				     struct xfs_log_item *lip)
-				     __releases(mp->m_ail_lock);
-struct xfs_log_item	*xfs_trans_first_ail(struct xfs_mount *, int *);
-struct xfs_log_item	*xfs_trans_next_ail(struct xfs_mount *,
-				     struct xfs_log_item *, int *, int *);
+struct xfs_ail_cursor {
+	struct xfs_ail_cursor	*next;
+	struct xfs_log_item	*item;
+};
 
+/*
+ * Private AIL structures.
+ *
+ * Eventually we need to drive the locking in here as well.
+ */
+struct xfs_ail {
+	struct xfs_mount	*xa_mount;
+	struct list_head	xa_ail;
+	uint			xa_gen;
+	struct task_struct	*xa_task;
+	xfs_lsn_t		xa_target;
+	struct xfs_ail_cursor	xa_cursors;
+	spinlock_t		xa_lock;
+};
 
 /*
- * AIL push thread support
+ * From xfs_trans_ail.c
  */
-long	xfsaild_push(struct xfs_mount *, xfs_lsn_t *);
-void	xfsaild_wakeup(struct xfs_mount *, xfs_lsn_t);
-int	xfsaild_start(struct xfs_mount *);
-void	xfsaild_stop(struct xfs_mount *);
+void			xfs_trans_ail_update(struct xfs_ail *ailp,
+					struct xfs_log_item *lip, xfs_lsn_t lsn)
+					__releases(ailp->xa_lock);
+void			xfs_trans_ail_delete(struct xfs_ail *ailp,
+					struct xfs_log_item *lip)
+					__releases(ailp->xa_lock);
+void			xfs_trans_ail_push(struct xfs_ail *, xfs_lsn_t);
+void			xfs_trans_unlocked_item(struct xfs_ail *,
+					xfs_log_item_t *);
+
+xfs_lsn_t		xfs_trans_ail_tail(struct xfs_ail *ailp);
+
+struct xfs_log_item	*xfs_trans_ail_cursor_first(struct xfs_ail *ailp,
+					struct xfs_ail_cursor *cur,
+					xfs_lsn_t lsn);
+struct xfs_log_item	*xfs_trans_ail_cursor_next(struct xfs_ail *ailp,
+					struct xfs_ail_cursor *cur);
+void			xfs_trans_ail_cursor_done(struct xfs_ail *ailp,
+					struct xfs_ail_cursor *cur);
+
+long	xfsaild_push(struct xfs_ail *, xfs_lsn_t *);
+void	xfsaild_wakeup(struct xfs_ail *, xfs_lsn_t);
+int	xfsaild_start(struct xfs_ail *);
+void	xfsaild_stop(struct xfs_ail *);
 
+#if BITS_PER_LONG != 64
+static inline void
+xfs_trans_ail_copy_lsn(
+	struct xfs_ail	*ailp,
+	xfs_lsn_t	*dst,
+	xfs_lsn_t	*src)
+{
+	ASSERT(sizeof(xfs_lsn_t) == 8);	/* don't lock if it shrinks */
+	spin_lock(&ailp->xa_lock);
+	*dst = *src;
+	spin_unlock(&ailp->xa_lock);
+}
+#else
+static inline void
+xfs_trans_ail_copy_lsn(
+	struct xfs_ail	*ailp,
+	xfs_lsn_t	*dst,
+	xfs_lsn_t	*src)
+{
+	ASSERT(sizeof(xfs_lsn_t) == 8);
+	*dst = *src;
+}
+#endif
 #endif	/* __XFS_TRANS_PRIV_H__ */
diff --git a/fs/xfs/xfs_utils.c b/fs/xfs/xfs_utils.c
index 35d4d414bcc2..fcc2285d03ed 100644
--- a/fs/xfs/xfs_utils.c
+++ b/fs/xfs/xfs_utils.c
@@ -172,6 +172,12 @@ xfs_dir_ialloc(
 			*ipp = NULL;
 			return code;
 		}
+
+		/*
+		 * transaction commit worked ok so we can drop the extra ticket
+		 * reference that we gained in xfs_trans_dup()
+		 */
+		xfs_log_ticket_put(tp->t_ticket);
 		code = xfs_trans_reserve(tp, 0, log_res, 0,
 					 XFS_TRANS_PERM_LOG_RES, log_count);
 		/*
@@ -268,9 +274,9 @@ xfs_bump_ino_vers2(
 	xfs_mount_t	*mp;
 
 	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
-	ASSERT(ip->i_d.di_version == XFS_DINODE_VERSION_1);
+	ASSERT(ip->i_d.di_version == 1);
 
-	ip->i_d.di_version = XFS_DINODE_VERSION_2;
+	ip->i_d.di_version = 2;
 	ip->i_d.di_onlink = 0;
 	memset(&(ip->i_d.di_pad[0]), 0, sizeof(ip->i_d.di_pad));
 	mp = tp->t_mountp;
@@ -302,7 +308,7 @@ xfs_bumplink(
 	ASSERT(ip->i_d.di_nlink > 0);
 	ip->i_d.di_nlink++;
 	inc_nlink(VFS_I(ip));
-	if ((ip->i_d.di_version == XFS_DINODE_VERSION_1) &&
+	if ((ip->i_d.di_version == 1) &&
 	    (ip->i_d.di_nlink > XFS_MAXLINK_1)) {
 		/*
 		 * The inode has increased its number of links beyond
diff --git a/fs/xfs/xfs_vfsops.c b/fs/xfs/xfs_vfsops.c
deleted file mode 100644
index 439dd3939dda..000000000000
--- a/fs/xfs/xfs_vfsops.c
+++ /dev/null
@@ -1,757 +0,0 @@
-/*
- * Copyright (c) 2000-2005 Silicon Graphics, Inc.
- * All Rights Reserved.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it would be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write the Free Software Foundation,
- * Inc.,  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
- */
-#include "xfs.h"
-#include "xfs_fs.h"
-#include "xfs_types.h"
-#include "xfs_bit.h"
-#include "xfs_log.h"
-#include "xfs_inum.h"
-#include "xfs_trans.h"
-#include "xfs_sb.h"
-#include "xfs_ag.h"
-#include "xfs_dir2.h"
-#include "xfs_dmapi.h"
-#include "xfs_mount.h"
-#include "xfs_da_btree.h"
-#include "xfs_bmap_btree.h"
-#include "xfs_ialloc_btree.h"
-#include "xfs_alloc_btree.h"
-#include "xfs_dir2_sf.h"
-#include "xfs_attr_sf.h"
-#include "xfs_dinode.h"
-#include "xfs_inode.h"
-#include "xfs_inode_item.h"
-#include "xfs_btree.h"
-#include "xfs_alloc.h"
-#include "xfs_ialloc.h"
-#include "xfs_quota.h"
-#include "xfs_error.h"
-#include "xfs_bmap.h"
-#include "xfs_rw.h"
-#include "xfs_buf_item.h"
-#include "xfs_log_priv.h"
-#include "xfs_dir2_trace.h"
-#include "xfs_extfree_item.h"
-#include "xfs_acl.h"
-#include "xfs_attr.h"
-#include "xfs_clnt.h"
-#include "xfs_mru_cache.h"
-#include "xfs_filestream.h"
-#include "xfs_fsops.h"
-#include "xfs_vnodeops.h"
-#include "xfs_vfsops.h"
-#include "xfs_utils.h"
-
-
-STATIC void
-xfs_quiesce_fs(
-	xfs_mount_t		*mp)
-{
-	int			count = 0, pincount;
-
-	xfs_flush_buftarg(mp->m_ddev_targp, 0);
-	xfs_finish_reclaim_all(mp, 0);
-
-	/* This loop must run at least twice.
-	 * The first instance of the loop will flush
-	 * most meta data but that will generate more
-	 * meta data (typically directory updates).
-	 * Which then must be flushed and logged before
-	 * we can write the unmount record.
-	 */
-	do {
-		xfs_syncsub(mp, SYNC_INODE_QUIESCE, NULL);
-		pincount = xfs_flush_buftarg(mp->m_ddev_targp, 1);
-		if (!pincount) {
-			delay(50);
-			count++;
-		}
-	} while (count < 2);
-}
-
-/*
- * Second stage of a quiesce. The data is already synced, now we have to take
- * care of the metadata. New transactions are already blocked, so we need to
- * wait for any remaining transactions to drain out before proceding.
- */
-void
-xfs_attr_quiesce(
-	xfs_mount_t	*mp)
-{
-	int	error = 0;
-
-	/* wait for all modifications to complete */
-	while (atomic_read(&mp->m_active_trans) > 0)
-		delay(100);
-
-	/* flush inodes and push all remaining buffers out to disk */
-	xfs_quiesce_fs(mp);
-
-	ASSERT_ALWAYS(atomic_read(&mp->m_active_trans) == 0);
-
-	/* Push the superblock and write an unmount record */
-	error = xfs_log_sbcount(mp, 1);
-	if (error)
-		xfs_fs_cmn_err(CE_WARN, mp,
-				"xfs_attr_quiesce: failed to log sb changes. "
-				"Frozen image may not be consistent.");
-	xfs_log_unmount_write(mp);
-	xfs_unmountfs_writesb(mp);
-}
-
-/*
- * xfs_unmount_flush implements a set of flush operation on special
- * inodes, which are needed as a separate set of operations so that
- * they can be called as part of relocation process.
- */
-int
-xfs_unmount_flush(
-	xfs_mount_t	*mp,		/* Mount structure we are getting
-					   rid of. */
-	int             relocation)	/* Called from vfs relocation. */
-{
-	xfs_inode_t	*rip = mp->m_rootip;
-	xfs_inode_t	*rbmip;
-	xfs_inode_t	*rsumip = NULL;
-	int		error;
-
-	xfs_ilock(rip, XFS_ILOCK_EXCL | XFS_ILOCK_PARENT);
-	xfs_iflock(rip);
-
-	/*
-	 * Flush out the real time inodes.
-	 */
-	if ((rbmip = mp->m_rbmip) != NULL) {
-		xfs_ilock(rbmip, XFS_ILOCK_EXCL);
-		xfs_iflock(rbmip);
-		error = xfs_iflush(rbmip, XFS_IFLUSH_SYNC);
-		xfs_iunlock(rbmip, XFS_ILOCK_EXCL);
-
-		if (error == EFSCORRUPTED)
-			goto fscorrupt_out;
-
-		ASSERT(vn_count(VFS_I(rbmip)) == 1);
-
-		rsumip = mp->m_rsumip;
-		xfs_ilock(rsumip, XFS_ILOCK_EXCL);
-		xfs_iflock(rsumip);
-		error = xfs_iflush(rsumip, XFS_IFLUSH_SYNC);
-		xfs_iunlock(rsumip, XFS_ILOCK_EXCL);
-
-		if (error == EFSCORRUPTED)
-			goto fscorrupt_out;
-
-		ASSERT(vn_count(VFS_I(rsumip)) == 1);
-	}
-
-	/*
-	 * Synchronously flush root inode to disk
-	 */
-	error = xfs_iflush(rip, XFS_IFLUSH_SYNC);
-	if (error == EFSCORRUPTED)
-		goto fscorrupt_out2;
-
-	if (vn_count(VFS_I(rip)) != 1 && !relocation) {
-		xfs_iunlock(rip, XFS_ILOCK_EXCL);
-		return XFS_ERROR(EBUSY);
-	}
-
-	/*
-	 * Release dquot that rootinode, rbmino and rsumino might be holding,
-	 * flush and purge the quota inodes.
-	 */
-	error = XFS_QM_UNMOUNT(mp);
-	if (error == EFSCORRUPTED)
-		goto fscorrupt_out2;
-
-	if (rbmip) {
-		IRELE(rbmip);
-		IRELE(rsumip);
-	}
-
-	xfs_iunlock(rip, XFS_ILOCK_EXCL);
-	return 0;
-
-fscorrupt_out:
-	xfs_ifunlock(rip);
-
-fscorrupt_out2:
-	xfs_iunlock(rip, XFS_ILOCK_EXCL);
-
-	return XFS_ERROR(EFSCORRUPTED);
-}
-
-/*
- * xfs_sync flushes any pending I/O to file system vfsp.
- *
- * This routine is called by vfs_sync() to make sure that things make it
- * out to disk eventually, on sync() system calls to flush out everything,
- * and when the file system is unmounted.  For the vfs_sync() case, all
- * we really need to do is sync out the log to make all of our meta-data
- * updates permanent (except for timestamps).  For calls from pflushd(),
- * dirty pages are kept moving by calling pdflush() on the inodes
- * containing them.  We also flush the inodes that we can lock without
- * sleeping and the superblock if we can lock it without sleeping from
- * vfs_sync() so that items at the tail of the log are always moving out.
- *
- * Flags:
- *      SYNC_BDFLUSH - We're being called from vfs_sync() so we don't want
- *		       to sleep if we can help it.  All we really need
- *		       to do is ensure that the log is synced at least
- *		       periodically.  We also push the inodes and
- *		       superblock if we can lock them without sleeping
- *			and they are not pinned.
- *      SYNC_ATTR    - We need to flush the inodes.  If SYNC_BDFLUSH is not
- *		       set, then we really want to lock each inode and flush
- *		       it.
- *      SYNC_WAIT    - All the flushes that take place in this call should
- *		       be synchronous.
- *      SYNC_DELWRI  - This tells us to push dirty pages associated with
- *		       inodes.  SYNC_WAIT and SYNC_BDFLUSH are used to
- *		       determine if they should be flushed sync, async, or
- *		       delwri.
- *      SYNC_CLOSE   - This flag is passed when the system is being
- *		       unmounted.  We should sync and invalidate everything.
- *      SYNC_FSDATA  - This indicates that the caller would like to make
- *		       sure the superblock is safe on disk.  We can ensure
- *		       this by simply making sure the log gets flushed
- *		       if SYNC_BDFLUSH is set, and by actually writing it
- *		       out otherwise.
- *	SYNC_IOWAIT  - The caller wants us to wait for all data I/O to complete
- *		       before we return (including direct I/O). Forms the drain
- *		       side of the write barrier needed to safely quiesce the
- *		       filesystem.
- *
- */
-int
-xfs_sync(
-	xfs_mount_t	*mp,
-	int		flags)
-{
-	int		error;
-
-	/*
-	 * Get the Quota Manager to flush the dquots.
-	 *
-	 * If XFS quota support is not enabled or this filesystem
-	 * instance does not use quotas XFS_QM_DQSYNC will always
-	 * return zero.
-	 */
-	error = XFS_QM_DQSYNC(mp, flags);
-	if (error) {
-		/*
-		 * If we got an IO error, we will be shutting down.
-		 * So, there's nothing more for us to do here.
-		 */
-		ASSERT(error != EIO || XFS_FORCED_SHUTDOWN(mp));
-		if (XFS_FORCED_SHUTDOWN(mp))
-			return XFS_ERROR(error);
-	}
-
-	if (flags & SYNC_IOWAIT)
-		xfs_filestream_flush(mp);
-
-	return xfs_syncsub(mp, flags, NULL);
-}
-
-/*
- * xfs sync routine for internal use
- *
- * This routine supports all of the flags defined for the generic vfs_sync
- * interface as explained above under xfs_sync.
- *
- */
-int
-xfs_sync_inodes(
-	xfs_mount_t	*mp,
-	int		flags,
-	int             *bypassed)
-{
-	xfs_inode_t	*ip = NULL;
-	struct inode	*vp = NULL;
-	int		error;
-	int		last_error;
-	uint64_t	fflag;
-	uint		lock_flags;
-	uint		base_lock_flags;
-	boolean_t	mount_locked;
-	boolean_t	vnode_refed;
-	int		preempt;
-	xfs_iptr_t	*ipointer;
-#ifdef DEBUG
-	boolean_t	ipointer_in = B_FALSE;
-
-#define IPOINTER_SET	ipointer_in = B_TRUE
-#define IPOINTER_CLR	ipointer_in = B_FALSE
-#else
-#define IPOINTER_SET
-#define IPOINTER_CLR
-#endif
-
-
-/* Insert a marker record into the inode list after inode ip. The list
- * must be locked when this is called. After the call the list will no
- * longer be locked.
- */
-#define IPOINTER_INSERT(ip, mp)	{ \
-		ASSERT(ipointer_in == B_FALSE); \
-		ipointer->ip_mnext = ip->i_mnext; \
-		ipointer->ip_mprev = ip; \
-		ip->i_mnext = (xfs_inode_t *)ipointer; \
-		ipointer->ip_mnext->i_mprev = (xfs_inode_t *)ipointer; \
-		preempt = 0; \
-		XFS_MOUNT_IUNLOCK(mp); \
-		mount_locked = B_FALSE; \
-		IPOINTER_SET; \
-	}
-
-/* Remove the marker from the inode list. If the marker was the only item
- * in the list then there are no remaining inodes and we should zero out
- * the whole list. If we are the current head of the list then move the head
- * past us.
- */
-#define IPOINTER_REMOVE(ip, mp)	{ \
-		ASSERT(ipointer_in == B_TRUE); \
-		if (ipointer->ip_mnext != (xfs_inode_t *)ipointer) { \
-			ip = ipointer->ip_mnext; \
-			ip->i_mprev = ipointer->ip_mprev; \
-			ipointer->ip_mprev->i_mnext = ip; \
-			if (mp->m_inodes == (xfs_inode_t *)ipointer) { \
-				mp->m_inodes = ip; \
-			} \
-		} else { \
-			ASSERT(mp->m_inodes == (xfs_inode_t *)ipointer); \
-			mp->m_inodes = NULL; \
-			ip = NULL; \
-		} \
-		IPOINTER_CLR; \
-	}
-
-#define XFS_PREEMPT_MASK	0x7f
-
-	ASSERT(!(flags & SYNC_BDFLUSH));
-
-	if (bypassed)
-		*bypassed = 0;
-	if (mp->m_flags & XFS_MOUNT_RDONLY)
-		return 0;
-	error = 0;
-	last_error = 0;
-	preempt = 0;
-
-	/* Allocate a reference marker */
-	ipointer = (xfs_iptr_t *)kmem_zalloc(sizeof(xfs_iptr_t), KM_SLEEP);
-
-	fflag = XFS_B_ASYNC;		/* default is don't wait */
-	if (flags & SYNC_DELWRI)
-		fflag = XFS_B_DELWRI;
-	if (flags & SYNC_WAIT)
-		fflag = 0;		/* synchronous overrides all */
-
-	base_lock_flags = XFS_ILOCK_SHARED;
-	if (flags & (SYNC_DELWRI | SYNC_CLOSE)) {
-		/*
-		 * We need the I/O lock if we're going to call any of
-		 * the flush/inval routines.
-		 */
-		base_lock_flags |= XFS_IOLOCK_SHARED;
-	}
-
-	XFS_MOUNT_ILOCK(mp);
-
-	ip = mp->m_inodes;
-
-	mount_locked = B_TRUE;
-	vnode_refed  = B_FALSE;
-
-	IPOINTER_CLR;
-
-	do {
-		ASSERT(ipointer_in == B_FALSE);
-		ASSERT(vnode_refed == B_FALSE);
-
-		lock_flags = base_lock_flags;
-
-		/*
-		 * There were no inodes in the list, just break out
-		 * of the loop.
-		 */
-		if (ip == NULL) {
-			break;
-		}
-
-		/*
-		 * We found another sync thread marker - skip it
-		 */
-		if (ip->i_mount == NULL) {
-			ip = ip->i_mnext;
-			continue;
-		}
-
-		vp = VFS_I(ip);
-
-		/*
-		 * If the vnode is gone then this is being torn down,
-		 * call reclaim if it is flushed, else let regular flush
-		 * code deal with it later in the loop.
-		 */
-
-		if (vp == NULL) {
-			/* Skip ones already in reclaim */
-			if (ip->i_flags & XFS_IRECLAIM) {
-				ip = ip->i_mnext;
-				continue;
-			}
-			if (xfs_ilock_nowait(ip, XFS_ILOCK_EXCL) == 0) {
-				ip = ip->i_mnext;
-			} else if ((xfs_ipincount(ip) == 0) &&
-				    xfs_iflock_nowait(ip)) {
-				IPOINTER_INSERT(ip, mp);
-
-				xfs_finish_reclaim(ip, 1,
-						XFS_IFLUSH_DELWRI_ELSE_ASYNC);
-
-				XFS_MOUNT_ILOCK(mp);
-				mount_locked = B_TRUE;
-				IPOINTER_REMOVE(ip, mp);
-			} else {
-				xfs_iunlock(ip, XFS_ILOCK_EXCL);
-				ip = ip->i_mnext;
-			}
-			continue;
-		}
-
-		if (VN_BAD(vp)) {
-			ip = ip->i_mnext;
-			continue;
-		}
-
-		if (XFS_FORCED_SHUTDOWN(mp) && !(flags & SYNC_CLOSE)) {
-			XFS_MOUNT_IUNLOCK(mp);
-			kmem_free(ipointer);
-			return 0;
-		}
-
-		/*
-		 * Try to lock without sleeping.  We're out of order with
-		 * the inode list lock here, so if we fail we need to drop
-		 * the mount lock and try again.  If we're called from
-		 * bdflush() here, then don't bother.
-		 *
-		 * The inode lock here actually coordinates with the
-		 * almost spurious inode lock in xfs_ireclaim() to prevent
-		 * the vnode we handle here without a reference from
-		 * being freed while we reference it.  If we lock the inode
-		 * while it's on the mount list here, then the spurious inode
-		 * lock in xfs_ireclaim() after the inode is pulled from
-		 * the mount list will sleep until we release it here.
-		 * This keeps the vnode from being freed while we reference
-		 * it.
-		 */
-		if (xfs_ilock_nowait(ip, lock_flags) == 0) {
-			if (vp == NULL) {
-				ip = ip->i_mnext;
-				continue;
-			}
-
-			vp = vn_grab(vp);
-			if (vp == NULL) {
-				ip = ip->i_mnext;
-				continue;
-			}
-
-			IPOINTER_INSERT(ip, mp);
-			xfs_ilock(ip, lock_flags);
-
-			ASSERT(vp == VFS_I(ip));
-			ASSERT(ip->i_mount == mp);
-
-			vnode_refed = B_TRUE;
-		}
-
-		/* From here on in the loop we may have a marker record
-		 * in the inode list.
-		 */
-
-		/*
-		 * If we have to flush data or wait for I/O completion
-		 * we need to drop the ilock that we currently hold.
-		 * If we need to drop the lock, insert a marker if we
-		 * have not already done so.
-		 */
-		if ((flags & (SYNC_CLOSE|SYNC_IOWAIT)) ||
-		    ((flags & SYNC_DELWRI) && VN_DIRTY(vp))) {
-			if (mount_locked) {
-				IPOINTER_INSERT(ip, mp);
-			}
-			xfs_iunlock(ip, XFS_ILOCK_SHARED);
-
-			if (flags & SYNC_CLOSE) {
-				/* Shutdown case. Flush and invalidate. */
-				if (XFS_FORCED_SHUTDOWN(mp))
-					xfs_tosspages(ip, 0, -1,
-							     FI_REMAPF);
-				else
-					error = xfs_flushinval_pages(ip,
-							0, -1, FI_REMAPF);
-			} else if ((flags & SYNC_DELWRI) && VN_DIRTY(vp)) {
-				error = xfs_flush_pages(ip, 0,
-							-1, fflag, FI_NONE);
-			}
-
-			/*
-			 * When freezing, we need to wait ensure all I/O (including direct
-			 * I/O) is complete to ensure no further data modification can take
-			 * place after this point
-			 */
-			if (flags & SYNC_IOWAIT)
-				vn_iowait(ip);
-
-			xfs_ilock(ip, XFS_ILOCK_SHARED);
-		}
-
-		if ((flags & SYNC_ATTR) &&
-		    (ip->i_update_core ||
-		     (ip->i_itemp && ip->i_itemp->ili_format.ilf_fields))) {
-			if (mount_locked)
-				IPOINTER_INSERT(ip, mp);
-
-			if (flags & SYNC_WAIT) {
-				xfs_iflock(ip);
-				error = xfs_iflush(ip, XFS_IFLUSH_SYNC);
-
-			/*
-			 * If we can't acquire the flush lock, then the inode
-			 * is already being flushed so don't bother waiting.
-			 *
-			 * If we can lock it then do a delwri flush so we can
-			 * combine multiple inode flushes in each disk write.
-			 */
-			} else if (xfs_iflock_nowait(ip)) {
-				error = xfs_iflush(ip, XFS_IFLUSH_DELWRI);
-			} else if (bypassed) {
-				(*bypassed)++;
-			}
-		}
-
-		if (lock_flags != 0) {
-			xfs_iunlock(ip, lock_flags);
-		}
-
-		if (vnode_refed) {
-			/*
-			 * If we had to take a reference on the vnode
-			 * above, then wait until after we've unlocked
-			 * the inode to release the reference.  This is
-			 * because we can be already holding the inode
-			 * lock when IRELE() calls xfs_inactive().
-			 *
-			 * Make sure to drop the mount lock before calling
-			 * IRELE() so that we don't trip over ourselves if
-			 * we have to go for the mount lock again in the
-			 * inactive code.
-			 */
-			if (mount_locked) {
-				IPOINTER_INSERT(ip, mp);
-			}
-
-			IRELE(ip);
-
-			vnode_refed = B_FALSE;
-		}
-
-		if (error) {
-			last_error = error;
-		}
-
-		/*
-		 * bail out if the filesystem is corrupted.
-		 */
-		if (error == EFSCORRUPTED)  {
-			if (!mount_locked) {
-				XFS_MOUNT_ILOCK(mp);
-				IPOINTER_REMOVE(ip, mp);
-			}
-			XFS_MOUNT_IUNLOCK(mp);
-			ASSERT(ipointer_in == B_FALSE);
-			kmem_free(ipointer);
-			return XFS_ERROR(error);
-		}
-
-		/* Let other threads have a chance at the mount lock
-		 * if we have looped many times without dropping the
-		 * lock.
-		 */
-		if ((++preempt & XFS_PREEMPT_MASK) == 0) {
-			if (mount_locked) {
-				IPOINTER_INSERT(ip, mp);
-			}
-		}
-
-		if (mount_locked == B_FALSE) {
-			XFS_MOUNT_ILOCK(mp);
-			mount_locked = B_TRUE;
-			IPOINTER_REMOVE(ip, mp);
-			continue;
-		}
-
-		ASSERT(ipointer_in == B_FALSE);
-		ip = ip->i_mnext;
-
-	} while (ip != mp->m_inodes);
-
-	XFS_MOUNT_IUNLOCK(mp);
-
-	ASSERT(ipointer_in == B_FALSE);
-
-	kmem_free(ipointer);
-	return XFS_ERROR(last_error);
-}
-
-/*
- * xfs sync routine for internal use
- *
- * This routine supports all of the flags defined for the generic vfs_sync
- * interface as explained above under xfs_sync.
- *
- */
-int
-xfs_syncsub(
-	xfs_mount_t	*mp,
-	int		flags,
-	int             *bypassed)
-{
-	int		error = 0;
-	int		last_error = 0;
-	uint		log_flags = XFS_LOG_FORCE;
-	xfs_buf_t	*bp;
-	xfs_buf_log_item_t	*bip;
-
-	/*
-	 * Sync out the log.  This ensures that the log is periodically
-	 * flushed even if there is not enough activity to fill it up.
-	 */
-	if (flags & SYNC_WAIT)
-		log_flags |= XFS_LOG_SYNC;
-
-	xfs_log_force(mp, (xfs_lsn_t)0, log_flags);
-
-	if (flags & (SYNC_ATTR|SYNC_DELWRI)) {
-		if (flags & SYNC_BDFLUSH)
-			xfs_finish_reclaim_all(mp, 1);
-		else
-			error = xfs_sync_inodes(mp, flags, bypassed);
-	}
-
-	/*
-	 * Flushing out dirty data above probably generated more
-	 * log activity, so if this isn't vfs_sync() then flush
-	 * the log again.
-	 */
-	if (flags & SYNC_DELWRI) {
-		xfs_log_force(mp, (xfs_lsn_t)0, log_flags);
-	}
-
-	if (flags & SYNC_FSDATA) {
-		/*
-		 * If this is vfs_sync() then only sync the superblock
-		 * if we can lock it without sleeping and it is not pinned.
-		 */
-		if (flags & SYNC_BDFLUSH) {
-			bp = xfs_getsb(mp, XFS_BUF_TRYLOCK);
-			if (bp != NULL) {
-				bip = XFS_BUF_FSPRIVATE(bp,xfs_buf_log_item_t*);
-				if ((bip != NULL) &&
-				    xfs_buf_item_dirty(bip)) {
-					if (!(XFS_BUF_ISPINNED(bp))) {
-						XFS_BUF_ASYNC(bp);
-						error = xfs_bwrite(mp, bp);
-					} else {
-						xfs_buf_relse(bp);
-					}
-				} else {
-					xfs_buf_relse(bp);
-				}
-			}
-		} else {
-			bp = xfs_getsb(mp, 0);
-			/*
-			 * If the buffer is pinned then push on the log so
-			 * we won't get stuck waiting in the write for
-			 * someone, maybe ourselves, to flush the log.
-			 * Even though we just pushed the log above, we
-			 * did not have the superblock buffer locked at
-			 * that point so it can become pinned in between
-			 * there and here.
-			 */
-			if (XFS_BUF_ISPINNED(bp))
-				xfs_log_force(mp, (xfs_lsn_t)0, XFS_LOG_FORCE);
-			if (flags & SYNC_WAIT)
-				XFS_BUF_UNASYNC(bp);
-			else
-				XFS_BUF_ASYNC(bp);
-			error = xfs_bwrite(mp, bp);
-		}
-		if (error) {
-			last_error = error;
-		}
-	}
-
-	/*
-	 * Now check to see if the log needs a "dummy" transaction.
-	 */
-	if (!(flags & SYNC_REMOUNT) && xfs_log_need_covered(mp)) {
-		xfs_trans_t *tp;
-		xfs_inode_t *ip;
-
-		/*
-		 * Put a dummy transaction in the log to tell
-		 * recovery that all others are OK.
-		 */
-		tp = xfs_trans_alloc(mp, XFS_TRANS_DUMMY1);
-		if ((error = xfs_trans_reserve(tp, 0,
-				XFS_ICHANGE_LOG_RES(mp),
-				0, 0, 0)))  {
-			xfs_trans_cancel(tp, 0);
-			return error;
-		}
-
-		ip = mp->m_rootip;
-		xfs_ilock(ip, XFS_ILOCK_EXCL);
-
-		xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
-		xfs_trans_ihold(tp, ip);
-		xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
-		error = xfs_trans_commit(tp, 0);
-		xfs_iunlock(ip, XFS_ILOCK_EXCL);
-		xfs_log_force(mp, (xfs_lsn_t)0, log_flags);
-	}
-
-	/*
-	 * When shutting down, we need to insure that the AIL is pushed
-	 * to disk or the filesystem can appear corrupt from the PROM.
-	 */
-	if ((flags & (SYNC_CLOSE|SYNC_WAIT)) == (SYNC_CLOSE|SYNC_WAIT)) {
-		XFS_bflush(mp->m_ddev_targp);
-		if (mp->m_rtdev_targp) {
-			XFS_bflush(mp->m_rtdev_targp);
-		}
-	}
-
-	return XFS_ERROR(last_error);
-}
diff --git a/fs/xfs/xfs_vfsops.h b/fs/xfs/xfs_vfsops.h
deleted file mode 100644
index a74b05087da4..000000000000
--- a/fs/xfs/xfs_vfsops.h
+++ /dev/null
@@ -1,16 +0,0 @@
-#ifndef _XFS_VFSOPS_H
-#define _XFS_VFSOPS_H 1
-
-struct cred;
-struct xfs_fid;
-struct inode;
-struct kstatfs;
-struct xfs_mount;
-struct xfs_mount_args;
-
-int xfs_sync(struct xfs_mount *mp, int flags);
-void xfs_do_force_shutdown(struct xfs_mount *mp, int flags, char *fname,
-		int lnnum);
-void xfs_attr_quiesce(struct xfs_mount *mp);
-
-#endif /* _XFS_VFSOPS_H */
diff --git a/fs/xfs/xfs_vnodeops.c b/fs/xfs/xfs_vnodeops.c
index 8b6812f66a15..4547608b46c4 100644
--- a/fs/xfs/xfs_vnodeops.c
+++ b/fs/xfs/xfs_vnodeops.c
@@ -54,33 +54,10 @@
 #include "xfs_vnodeops.h"
 
 int
-xfs_open(
-	xfs_inode_t	*ip)
-{
-	int		mode;
-
-	if (XFS_FORCED_SHUTDOWN(ip->i_mount))
-		return XFS_ERROR(EIO);
-
-	/*
-	 * If it's a directory with any blocks, read-ahead block 0
-	 * as we're almost certain to have the next operation be a read there.
-	 */
-	if (S_ISDIR(ip->i_d.di_mode) && ip->i_d.di_nextents > 0) {
-		mode = xfs_ilock_map_shared(ip);
-		if (ip->i_d.di_nextents > 0)
-			(void)xfs_da_reada_buf(NULL, ip, 0, XFS_DATA_FORK);
-		xfs_iunlock(ip, mode);
-	}
-	return 0;
-}
-
-int
 xfs_setattr(
 	struct xfs_inode	*ip,
 	struct iattr		*iattr,
-	int			flags,
-	cred_t			*credp)
+	int			flags)
 {
 	xfs_mount_t		*mp = ip->i_mount;
 	struct inode		*inode = VFS_I(ip);
@@ -233,10 +210,6 @@ xfs_setattr(
 
 	/*
 	 * Change file ownership.  Must be the owner or privileged.
-	 * If the system was configured with the "restricted_chown"
-	 * option, the owner is not permitted to give away the file,
-	 * and can change the group id only to a group of which he
-	 * or she is a member.
 	 */
 	if (mask & (ATTR_UID|ATTR_GID)) {
 		/*
@@ -260,9 +233,8 @@ xfs_setattr(
 		 * shall be equal to either the group ID or one of the
 		 * supplementary group IDs of the calling process.
 		 */
-		if (restricted_chown &&
-		    (iuid != uid || (igid != gid &&
-				     !in_group_p((gid_t)gid))) &&
+		if ((iuid != uid ||
+		     (igid != gid && !in_group_p((gid_t)gid))) &&
 		    !capable(CAP_CHOWN)) {
 			code = XFS_ERROR(EPERM);
 			goto error_return;
@@ -366,7 +338,7 @@ xfs_setattr(
 		}
 
 		/* wait for all I/O to complete */
-		vn_iowait(ip);
+		xfs_ioend_wait(ip);
 
 		if (!code)
 			code = xfs_itruncate_data(ip, iattr->ia_size);
@@ -456,10 +428,6 @@ xfs_setattr(
 
 	/*
 	 * Change file ownership.  Must be the owner or privileged.
-	 * If the system was configured with the "restricted_chown"
-	 * option, the owner is not permitted to give away the file,
-	 * and can change the group id only to a group of which he
-	 * or she is a member.
 	 */
 	if (mask & (ATTR_UID|ATTR_GID)) {
 		/*
@@ -713,7 +681,7 @@ xfs_fsync(
 		return XFS_ERROR(EIO);
 
 	/* capture size updates in I/O completion before writing the inode. */
-	error = filemap_fdatawait(VFS_I(ip)->i_mapping);
+	error = xfs_wait_on_pages(ip, 0, -1);
 	if (error)
 		return XFS_ERROR(error);
 
@@ -1029,6 +997,12 @@ xfs_inactive_symlink_rmt(
 		goto error0;
 	}
 	/*
+	 * transaction commit worked ok so we can drop the extra ticket
+	 * reference that we gained in xfs_trans_dup()
+	 */
+	xfs_log_ticket_put(tp->t_ticket);
+
+	/*
 	 * Remove the memory for extent descriptions (just bookkeeping).
 	 */
 	if (ip->i_df.if_bytes)
@@ -1625,8 +1599,6 @@ xfs_create(
 		xfs_trans_set_sync(tp);
 	}
 
-	dp->i_gen++;
-
 	/*
 	 * Attach the dquot(s) to the inodes and modify them incore.
 	 * These ids of the inode couldn't have changed since the new
@@ -1993,13 +1965,6 @@ xfs_remove(
 	}
 	xfs_ichgtime(dp, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
 
-	/*
-	 * Bump the in memory generation count on the parent
-	 * directory so that other can know that it has changed.
-	 */
-	dp->i_gen++;
-	xfs_trans_log_inode(tp, dp, XFS_ILOG_CORE);
-
 	if (is_dir) {
 		/*
 		 * Drop the link from ip's "..".
@@ -2009,7 +1974,7 @@ xfs_remove(
 			goto out_bmap_cancel;
 
 		/*
-		 * Drop the link from dp to ip.
+		 * Drop the "." link from ip to self.
 		 */
 		error = xfs_droplink(tp, ip);
 		if (error)
@@ -2017,14 +1982,14 @@ xfs_remove(
 	} else {
 		/*
 		 * When removing a non-directory we need to log the parent
-		 * inode here for the i_gen update.  For a directory this is
-		 * done implicitly by the xfs_droplink call for the ".." entry.
+		 * inode here.  For a directory this is done implicitly
+		 * by the xfs_droplink call for the ".." entry.
 		 */
 		xfs_trans_log_inode(tp, dp, XFS_ILOG_CORE);
 	}
 
 	/*
-	 * Drop the "." link from ip to self.
+	 * Drop the link from dp to ip.
 	 */
 	error = xfs_droplink(tp, ip);
 	if (error)
@@ -2178,7 +2143,6 @@ xfs_link(
 	if (error)
 		goto abort_return;
 	xfs_ichgtime(tdp, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
-	tdp->i_gen++;
 	xfs_trans_log_inode(tp, tdp, XFS_ILOG_CORE);
 
 	error = xfs_bumplink(tp, sip);
@@ -2355,18 +2319,10 @@ xfs_mkdir(
 	}
 	xfs_ichgtime(dp, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
 
-	/*
-	 * Bump the in memory version number of the parent directory
-	 * so that other processes accessing it will recognize that
-	 * the directory has changed.
-	 */
-	dp->i_gen++;
-
 	error = xfs_dir_init(tp, cdp, dp);
 	if (error)
 		goto error2;
 
-	cdp->i_gen = 1;
 	error = xfs_bumplink(tp, dp);
 	if (error)
 		goto error2;
@@ -2653,13 +2609,6 @@ xfs_symlink(
 	xfs_trans_log_inode(tp, dp, XFS_ILOG_CORE);
 
 	/*
-	 * Bump the in memory version number of the parent directory
-	 * so that other processes accessing it will recognize that
-	 * the directory has changed.
-	 */
-	dp->i_gen++;
-
-	/*
 	 * If this is a synchronous mount, make sure that the
 	 * symlink transaction goes to disk before returning to
 	 * the user.
@@ -2809,7 +2758,7 @@ xfs_reclaim(
 		return 0;
 	}
 
-	vn_iowait(ip);
+	xfs_ioend_wait(ip);
 
 	ASSERT(XFS_FORCED_SHUTDOWN(ip->i_mount) || ip->i_delayed_blks == 0);
 
@@ -2833,122 +2782,10 @@ xfs_reclaim(
 	if (!ip->i_update_core && (ip->i_itemp == NULL)) {
 		xfs_ilock(ip, XFS_ILOCK_EXCL);
 		xfs_iflock(ip);
-		return xfs_finish_reclaim(ip, 1, XFS_IFLUSH_DELWRI_ELSE_SYNC);
-	} else {
-		xfs_mount_t	*mp = ip->i_mount;
-
-		/* Protect sync and unpin from us */
-		XFS_MOUNT_ILOCK(mp);
-		spin_lock(&ip->i_flags_lock);
-		__xfs_iflags_set(ip, XFS_IRECLAIMABLE);
-		VFS_I(ip)->i_private = NULL;
-		ip->i_vnode = NULL;
-		spin_unlock(&ip->i_flags_lock);
-		list_add_tail(&ip->i_reclaim, &mp->m_del_inodes);
-		XFS_MOUNT_IUNLOCK(mp);
-	}
-	return 0;
-}
-
-int
-xfs_finish_reclaim(
-	xfs_inode_t	*ip,
-	int		locked,
-	int		sync_mode)
-{
-	xfs_perag_t	*pag = xfs_get_perag(ip->i_mount, ip->i_ino);
-	struct inode	*vp = VFS_I(ip);
-
-	if (vp && VN_BAD(vp))
-		goto reclaim;
-
-	/* The hash lock here protects a thread in xfs_iget_core from
-	 * racing with us on linking the inode back with a vnode.
-	 * Once we have the XFS_IRECLAIM flag set it will not touch
-	 * us.
-	 */
-	write_lock(&pag->pag_ici_lock);
-	spin_lock(&ip->i_flags_lock);
-	if (__xfs_iflags_test(ip, XFS_IRECLAIM) ||
-	    (!__xfs_iflags_test(ip, XFS_IRECLAIMABLE) && vp == NULL)) {
-		spin_unlock(&ip->i_flags_lock);
-		write_unlock(&pag->pag_ici_lock);
-		if (locked) {
-			xfs_ifunlock(ip);
-			xfs_iunlock(ip, XFS_ILOCK_EXCL);
-		}
-		return 1;
-	}
-	__xfs_iflags_set(ip, XFS_IRECLAIM);
-	spin_unlock(&ip->i_flags_lock);
-	write_unlock(&pag->pag_ici_lock);
-	xfs_put_perag(ip->i_mount, pag);
-
-	/*
-	 * If the inode is still dirty, then flush it out.  If the inode
-	 * is not in the AIL, then it will be OK to flush it delwri as
-	 * long as xfs_iflush() does not keep any references to the inode.
-	 * We leave that decision up to xfs_iflush() since it has the
-	 * knowledge of whether it's OK to simply do a delwri flush of
-	 * the inode or whether we need to wait until the inode is
-	 * pulled from the AIL.
-	 * We get the flush lock regardless, though, just to make sure
-	 * we don't free it while it is being flushed.
-	 */
-	if (!locked) {
-		xfs_ilock(ip, XFS_ILOCK_EXCL);
-		xfs_iflock(ip);
-	}
-
-	/*
-	 * In the case of a forced shutdown we rely on xfs_iflush() to
-	 * wait for the inode to be unpinned before returning an error.
-	 */
-	if (xfs_iflush(ip, sync_mode) == 0) {
-		/* synchronize with xfs_iflush_done */
-		xfs_iflock(ip);
-		xfs_ifunlock(ip);
-	}
-
-	xfs_iunlock(ip, XFS_ILOCK_EXCL);
-
- reclaim:
-	xfs_ireclaim(ip);
-	return 0;
-}
-
-int
-xfs_finish_reclaim_all(xfs_mount_t *mp, int noblock)
-{
-	int		purged;
-	xfs_inode_t	*ip, *n;
-	int		done = 0;
-
-	while (!done) {
-		purged = 0;
-		XFS_MOUNT_ILOCK(mp);
-		list_for_each_entry_safe(ip, n, &mp->m_del_inodes, i_reclaim) {
-			if (noblock) {
-				if (xfs_ilock_nowait(ip, XFS_ILOCK_EXCL) == 0)
-					continue;
-				if (xfs_ipincount(ip) ||
-				    !xfs_iflock_nowait(ip)) {
-					xfs_iunlock(ip, XFS_ILOCK_EXCL);
-					continue;
-				}
-			}
-			XFS_MOUNT_IUNLOCK(mp);
-			if (xfs_finish_reclaim(ip, noblock,
-					XFS_IFLUSH_DELWRI_ELSE_ASYNC))
-				delay(1);
-			purged = 1;
-			break;
-		}
-
-		done = !purged;
+		xfs_iflags_set(ip, XFS_IRECLAIMABLE);
+		return xfs_reclaim_inode(ip, 1, XFS_IFLUSH_DELWRI_ELSE_SYNC);
 	}
-
-	XFS_MOUNT_IUNLOCK(mp);
+	xfs_inode_set_reclaim_tag(ip);
 	return 0;
 }
 
@@ -3197,6 +3034,8 @@ xfs_zero_remaining_bytes(
 	bp = xfs_buf_get_noaddr(mp->m_sb.sb_blocksize,
 				XFS_IS_REALTIME_INODE(ip) ?
 				mp->m_rtdev_targp : mp->m_ddev_targp);
+	if (!bp)
+		return XFS_ERROR(ENOMEM);
 
 	for (offset = startoff; offset <= endoff; offset = lastoffset + 1) {
 		offset_fsb = XFS_B_TO_FSBT(mp, offset);
@@ -3312,7 +3151,8 @@ xfs_free_file_space(
 		need_iolock = 0;
 	if (need_iolock) {
 		xfs_ilock(ip, XFS_IOLOCK_EXCL);
-		vn_iowait(ip);	/* wait for the completion of any pending DIOs */
+		/* wait for the completion of any pending DIOs */
+		xfs_ioend_wait(ip);
 	}
 
 	rounding = max_t(uint, 1 << mp->m_sb.sb_blocklog, PAGE_CACHE_SIZE);
@@ -3474,7 +3314,6 @@ xfs_change_file_space(
 	int		cmd,
 	xfs_flock64_t	*bf,
 	xfs_off_t	offset,
-	cred_t		*credp,
 	int		attr_flags)
 {
 	xfs_mount_t	*mp = ip->i_mount;
@@ -3562,7 +3401,7 @@ xfs_change_file_space(
 		iattr.ia_valid = ATTR_SIZE;
 		iattr.ia_size = startoffset;
 
-		error = xfs_setattr(ip, &iattr, attr_flags, credp);
+		error = xfs_setattr(ip, &iattr, attr_flags);
 
 		if (error)
 			return error;
diff --git a/fs/xfs/xfs_vnodeops.h b/fs/xfs/xfs_vnodeops.h
index e932a96bec54..2a45b00ad32e 100644
--- a/fs/xfs/xfs_vnodeops.h
+++ b/fs/xfs/xfs_vnodeops.h
@@ -14,9 +14,7 @@ struct xfs_inode;
 struct xfs_iomap;
 
 
-int xfs_open(struct xfs_inode *ip);
-int xfs_setattr(struct xfs_inode *ip, struct iattr *vap, int flags,
-		struct cred *credp);
+int xfs_setattr(struct xfs_inode *ip, struct iattr *vap, int flags);
 #define	XFS_ATTR_DMI		0x01	/* invocation from a DMI function */
 #define	XFS_ATTR_NONBLOCK	0x02	/* return EAGAIN if operation would block */
 #define XFS_ATTR_NOLOCK		0x04	/* Don't grab any conflicting locks */
@@ -44,8 +42,7 @@ int xfs_inode_flush(struct xfs_inode *ip, int flags);
 int xfs_set_dmattrs(struct xfs_inode *ip, u_int evmask, u_int16_t state);
 int xfs_reclaim(struct xfs_inode *ip);
 int xfs_change_file_space(struct xfs_inode *ip, int cmd,
-		xfs_flock64_t *bf, xfs_off_t offset,
-		struct cred *credp, int	attr_flags);
+		xfs_flock64_t *bf, xfs_off_t offset, int attr_flags);
 int xfs_rename(struct xfs_inode *src_dp, struct xfs_name *src_name,
 		struct xfs_inode *src_ip, struct xfs_inode *target_dp,
 		struct xfs_name *target_name, struct xfs_inode *target_ip);
@@ -78,5 +75,6 @@ int xfs_flushinval_pages(struct xfs_inode *ip, xfs_off_t first,
 		xfs_off_t last, int fiopt);
 int xfs_flush_pages(struct xfs_inode *ip, xfs_off_t first,
 		xfs_off_t last, uint64_t flags, int fiopt);
+int xfs_wait_on_pages(struct xfs_inode *ip, xfs_off_t first, xfs_off_t last);
 
 #endif /* _XFS_VNODEOPS_H */
diff --git a/include/acpi/acconfig.h b/include/acpi/acconfig.h
index 29feee27f0ea..c9a573eb2142 100644
--- a/include/acpi/acconfig.h
+++ b/include/acpi/acconfig.h
@@ -63,7 +63,7 @@
 
 /* Current ACPICA subsystem version in YYYYMMDD format */
 
-#define ACPI_CA_VERSION                 0x20080926
+#define ACPI_CA_VERSION                 0x20081031
 
 /*
  * OS name, used for the _OS object.  The _OS object is essentially obsolete,
@@ -119,6 +119,10 @@
 
 #define ACPI_ROOT_TABLE_SIZE_INCREMENT  4
 
+/* Maximum number of While() loop iterations before forced abort */
+
+#define ACPI_MAX_LOOP_ITERATIONS        0xFFFF
+
 /******************************************************************************
  *
  * ACPI Specification constants (Do not change unless the specification changes)
diff --git a/include/acpi/acexcep.h b/include/acpi/acexcep.h
index 84f5cb242863..a1ae1057d2ef 100644
--- a/include/acpi/acexcep.h
+++ b/include/acpi/acexcep.h
@@ -153,8 +153,9 @@
 #define AE_AML_CIRCULAR_REFERENCE       (acpi_status) (0x001E | AE_CODE_AML)
 #define AE_AML_BAD_RESOURCE_LENGTH      (acpi_status) (0x001F | AE_CODE_AML)
 #define AE_AML_ILLEGAL_ADDRESS          (acpi_status) (0x0020 | AE_CODE_AML)
+#define AE_AML_INFINITE_LOOP            (acpi_status) (0x0021 | AE_CODE_AML)
 
-#define AE_CODE_AML_MAX                 0x0020
+#define AE_CODE_AML_MAX                 0x0021
 
 /*
  * Internal exceptions used for control
@@ -267,6 +268,7 @@ char const *acpi_gbl_exception_names_aml[] = {
 	"AE_AML_CIRCULAR_REFERENCE",
 	"AE_AML_BAD_RESOURCE_LENGTH",
 	"AE_AML_ILLEGAL_ADDRESS",
+	"AE_AML_INFINITE_LOOP"
 };
 
 char const *acpi_gbl_exception_names_ctrl[] = {
diff --git a/include/acpi/acglobal.h b/include/acpi/acglobal.h
index 15dda46b70d1..77d73a498bfb 100644
--- a/include/acpi/acglobal.h
+++ b/include/acpi/acglobal.h
@@ -140,6 +140,7 @@ ACPI_EXTERN u32 acpi_gbl_trace_flags;
  */
 ACPI_EXTERN struct acpi_internal_rsdt acpi_gbl_root_table_list;
 ACPI_EXTERN struct acpi_table_fadt acpi_gbl_FADT;
+ACPI_EXTERN struct acpi_table_facs *acpi_gbl_FACS;
 extern u8 acpi_gbl_permanent_mmap;
 
 /* These addresses are calculated from FADT address values */
diff --git a/include/acpi/aclocal.h b/include/acpi/aclocal.h
index ecab527cf78e..0323fa9aa3e6 100644
--- a/include/acpi/aclocal.h
+++ b/include/acpi/aclocal.h
@@ -566,6 +566,7 @@ struct acpi_control_state {
 	union acpi_parse_object *predicate_op;
 	u8 *aml_predicate_start;	/* Start of if/while predicate */
 	u8 *package_end;	/* End of if/while block */
+	u32 loop_count;		/* While() loop counter */
 };
 
 /*
diff --git a/include/acpi/acnamesp.h b/include/acpi/acnamesp.h
index db4e6f677855..46cb5b46d280 100644
--- a/include/acpi/acnamesp.h
+++ b/include/acpi/acnamesp.h
@@ -182,7 +182,9 @@ acpi_status acpi_ns_evaluate(struct acpi_evaluate_info *info);
  */
 acpi_status
 acpi_ns_check_predefined_names(struct acpi_namespace_node *node,
-			       union acpi_operand_object *return_object);
+			       u32 user_param_count,
+			       acpi_status return_status,
+			       union acpi_operand_object **return_object);
 
 const union acpi_predefined_info *acpi_ns_check_for_predefined_name(struct
 								    acpi_namespace_node
@@ -191,6 +193,7 @@ const union acpi_predefined_info *acpi_ns_check_for_predefined_name(struct
 void
 acpi_ns_check_parameter_count(char *pathname,
 			      struct acpi_namespace_node *node,
+			      u32 user_param_count,
 			      const union acpi_predefined_info *info);
 
 /*
diff --git a/include/acpi/acpixf.h b/include/acpi/acpixf.h
index 33bc0e3b1954..c9b903f3625a 100644
--- a/include/acpi/acpixf.h
+++ b/include/acpi/acpixf.h
@@ -320,12 +320,10 @@ acpi_status acpi_get_register_unlocked(u32 register_id, u32 *return_value);
 acpi_status acpi_set_register(u32 register_id, u32 value);
 
 acpi_status
-acpi_set_firmware_waking_vector(acpi_physical_address physical_address);
+acpi_set_firmware_waking_vector(u32 physical_address);
 
-#ifdef ACPI_FUTURE_USAGE
 acpi_status
-acpi_get_firmware_waking_vector(acpi_physical_address * physical_address);
-#endif
+acpi_set_firmware_waking_vector64(u64 physical_address);
 
 acpi_status
 acpi_get_sleep_type_data(u8 sleep_state, u8 * slp_typ_a, u8 * slp_typ_b);
diff --git a/include/acpi/actables.h b/include/acpi/actables.h
index 0cbe1b9ab522..7ce6e33c7f78 100644
--- a/include/acpi/actables.h
+++ b/include/acpi/actables.h
@@ -94,6 +94,8 @@ void acpi_tb_set_table_loaded_flag(u32 table_index, u8 is_loaded);
 /*
  * tbutils - table manager utilities
  */
+acpi_status acpi_tb_initialize_facs(void);
+
 u8 acpi_tb_tables_loaded(void);
 
 void
diff --git a/include/acpi/actypes.h b/include/acpi/actypes.h
index 7220361790b3..a9719d69e72e 100644
--- a/include/acpi/actypes.h
+++ b/include/acpi/actypes.h
@@ -291,7 +291,7 @@ typedef u32 acpi_physical_address;
 #endif
 
 /*
- * Mescellaneous types
+ * Miscellaneous types
  */
 typedef u32 acpi_status;	/* All ACPI Exceptions */
 typedef u32 acpi_name;		/* 4-byte ACPI name */
@@ -319,7 +319,7 @@ struct uint32_struct {
 #define acpi_semaphore                  void *
 
 /*
- * Acpi integer width. In ACPI version 1, integers are 32 bits.  In ACPI
+ * Acpi integer width. In ACPI version 1, integers are 32 bits. In ACPI
  * version 2, integers are 64 bits. Note that this pertains to the ACPI integer
  * type only, not other integers used in the implementation of the ACPI CA
  * subsystem.
@@ -414,7 +414,7 @@ typedef unsigned long long acpi_integer;
 #define ACPI_NOTIFY_MAX                 0x0B
 
 /*
- * Types associated with ACPI names and objects.  The first group of
+ * Types associated with ACPI names and objects. The first group of
  * values (up to ACPI_TYPE_EXTERNAL_MAX) correspond to the definition
  * of the ACPI object_type() operator (See the ACPI Spec). Therefore,
  * only add to the first group if the spec changes.
@@ -787,7 +787,7 @@ acpi_status(*acpi_exception_handler) (acpi_status aml_status,
 				      u16 opcode,
 				      u32 aml_offset, void *context);
 
-/* Table Event handler (Load, load_table etc) and types */
+/* Table Event handler (Load, load_table, etc.) and types */
 
 typedef
 acpi_status(*acpi_tbl_handler) (u32 event, void *table, void *context);
diff --git a/include/asm-generic/bug.h b/include/asm-generic/bug.h
index 12c07c1866b2..b8ba6941f587 100644
--- a/include/asm-generic/bug.h
+++ b/include/asm-generic/bug.h
@@ -33,15 +33,14 @@ struct bug_entry {
 
 #ifndef __WARN
 #ifndef __ASSEMBLY__
-extern void warn_on_slowpath(const char *file, const int line);
 extern void warn_slowpath(const char *file, const int line,
 		const char *fmt, ...) __attribute__((format(printf, 3, 4)));
 #define WANT_WARN_ON_SLOWPATH
 #endif
-#define __WARN() warn_on_slowpath(__FILE__, __LINE__)
-#define __WARN_printf(arg...) warn_slowpath(__FILE__, __LINE__, arg)
+#define __WARN()		warn_slowpath(__FILE__, __LINE__, NULL)
+#define __WARN_printf(arg...)	warn_slowpath(__FILE__, __LINE__, arg)
 #else
-#define __WARN_printf(arg...) do { printk(arg); __WARN(); } while (0)
+#define __WARN_printf(arg...)	do { printk(arg); __WARN(); } while (0)
 #endif
 
 #ifndef WARN_ON
diff --git a/include/asm-generic/memory_model.h b/include/asm-generic/memory_model.h
index 18546d8eb78e..36fa286adad5 100644
--- a/include/asm-generic/memory_model.h
+++ b/include/asm-generic/memory_model.h
@@ -49,7 +49,7 @@
 
 /* memmap is virtually contigious.  */
 #define __pfn_to_page(pfn)	(vmemmap + (pfn))
-#define __page_to_pfn(page)	((page) - vmemmap)
+#define __page_to_pfn(page)	(unsigned long)((page) - vmemmap)
 
 #elif defined(CONFIG_SPARSEMEM)
 /*
diff --git a/include/asm-generic/percpu.h b/include/asm-generic/percpu.h
index b0e63c672ebd..1c02250353ee 100644
--- a/include/asm-generic/percpu.h
+++ b/include/asm-generic/percpu.h
@@ -45,7 +45,12 @@ extern unsigned long __per_cpu_offset[NR_CPUS];
  * Only S390 provides its own means of moving the pointer.
  */
 #ifndef SHIFT_PERCPU_PTR
-#define SHIFT_PERCPU_PTR(__p, __offset)	RELOC_HIDE((__p), (__offset))
+# ifdef CONFIG_HAVE_ZERO_BASED_PER_CPU
+#  define SHIFT_PERCPU_PTR(__p, __offset) \
+	((__typeof(__p))(((void *)(__p)) + (__offset)))
+# else
+#  define SHIFT_PERCPU_PTR(__p, __offset)	RELOC_HIDE((__p), (__offset))
+# endif /* CONFIG_HAVE_ZERO_BASED_PER_CPU */
 #endif
 
 /*
@@ -70,6 +75,10 @@ extern void setup_per_cpu_areas(void);
 #define per_cpu(var, cpu)			(*((void)(cpu), &per_cpu_var(var)))
 #define __get_cpu_var(var)			per_cpu_var(var)
 #define __raw_get_cpu_var(var)			per_cpu_var(var)
+#ifndef SHIFT_PERCPU_PTR
+# define SHIFT_PERCPU_PTR(__p, __offset)		(__p)
+#endif
+#define per_cpu_offset(x)			0L
 
 #endif	/* SMP */
 
diff --git a/include/asm-generic/sections.h b/include/asm-generic/sections.h
index 79a7ff925bf8..51c15f3a14a5 100644
--- a/include/asm-generic/sections.h
+++ b/include/asm-generic/sections.h
@@ -9,7 +9,17 @@ extern char __bss_start[], __bss_stop[];
 extern char __init_begin[], __init_end[];
 extern char _sinittext[], _einittext[];
 extern char _end[];
+#ifdef CONFIG_HAVE_ZERO_BASED_PER_CPU
+extern char __per_cpu_load[];
+extern char ____per_cpu_size[];
+#define __per_cpu_size ((unsigned long)&____per_cpu_size)
+#define __per_cpu_start ((char *)0)
+#define __per_cpu_end ((char *)__per_cpu_size)
+#else
 extern char __per_cpu_start[], __per_cpu_end[];
+#define __per_cpu_load __per_cpu_start
+#define __per_cpu_size (__per_cpu_end - __per_cpu_start)
+#endif
 extern char __kprobes_text_start[], __kprobes_text_end[];
 extern char __initdata_begin[], __initdata_end[];
 extern char __start_rodata[], __end_rodata[];
diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index 80744606bad1..30536c3b1976 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -45,6 +45,22 @@
 #define MCOUNT_REC()
 #endif
 
+#ifdef CONFIG_TRACE_BRANCH_PROFILING
+#define LIKELY_PROFILE()	VMLINUX_SYMBOL(__start_annotated_branch_profile) = .; \
+				*(_ftrace_annotated_branch)			      \
+				VMLINUX_SYMBOL(__stop_annotated_branch_profile) = .;
+#else
+#define LIKELY_PROFILE()
+#endif
+
+#ifdef CONFIG_PROFILE_ALL_BRANCHES
+#define BRANCH_PROFILE()	VMLINUX_SYMBOL(__start_branch_profile) = .;   \
+				*(_ftrace_branch)			      \
+				VMLINUX_SYMBOL(__stop_branch_profile) = .;
+#else
+#define BRANCH_PROFILE()
+#endif
+
 /* .data section */
 #define DATA_DATA							\
 	*(.data)							\
@@ -60,9 +76,12 @@
 	VMLINUX_SYMBOL(__start___markers) = .;				\
 	*(__markers)							\
 	VMLINUX_SYMBOL(__stop___markers) = .;				\
+	. = ALIGN(32);							\
 	VMLINUX_SYMBOL(__start___tracepoints) = .;			\
 	*(__tracepoints)						\
-	VMLINUX_SYMBOL(__stop___tracepoints) = .;
+	VMLINUX_SYMBOL(__stop___tracepoints) = .;			\
+	LIKELY_PROFILE()		       				\
+	BRANCH_PROFILE()
 
 #define RO_DATA(align)							\
 	. = ALIGN((align));						\
@@ -401,6 +420,21 @@
   	*(.initcall7.init)						\
   	*(.initcall7s.init)
 
+#ifdef CONFIG_HAVE_ZERO_BASED_PER_CPU
+#define PERCPU(align)							\
+	. = ALIGN(align);						\
+	percpu : { } :percpu						\
+	__per_cpu_load = .;						\
+	.data.percpu 0 : AT(__per_cpu_load - LOAD_OFFSET) {		\
+		*(.data.percpu.first)					\
+		*(.data.percpu.shared_aligned)				\
+		*(.data.percpu)						\
+		*(.data.percpu.page_aligned)				\
+		____per_cpu_size = .;					\
+	}								\
+	. = __per_cpu_load + ____per_cpu_size;				\
+	data : { } :data
+#else
 #define PERCPU(align)							\
 	. = ALIGN(align);						\
 	VMLINUX_SYMBOL(__per_cpu_start) = .;				\
@@ -410,3 +444,4 @@
 		*(.data.percpu.shared_aligned)				\
 	}								\
 	VMLINUX_SYMBOL(__per_cpu_end) = .;
+#endif
diff --git a/include/asm-m32r/system.h b/include/asm-m32r/system.h
index 70a57c8c002b..c980f5ba8de7 100644
--- a/include/asm-m32r/system.h
+++ b/include/asm-m32r/system.h
@@ -23,7 +23,7 @@
  */
 
 #if defined(CONFIG_FRAME_POINTER) || \
-	!defined(CONFIG_SCHED_NO_NO_OMIT_FRAME_POINTER)
+	!defined(CONFIG_SCHED_OMIT_FRAME_POINTER)
 #define M32R_PUSH_FP "	push fp\n"
 #define M32R_POP_FP  "	pop  fp\n"
 #else
diff --git a/include/asm-m68k/byteorder.h b/include/asm-m68k/byteorder.h
index 81d420b35c80..b354acdafec8 100644
--- a/include/asm-m68k/byteorder.h
+++ b/include/asm-m68k/byteorder.h
@@ -4,22 +4,16 @@
 #include <asm/types.h>
 #include <linux/compiler.h>
 
-#ifdef __GNUC__
+#define __BIG_ENDIAN
+#define __SWAB_64_THRU_32__
 
-static __inline__ __attribute_const__ __u32 ___arch__swab32(__u32 val)
+static inline __attribute_const__ __u32 __arch_swab32(__u32 val)
 {
 	__asm__("rolw #8,%0; swap %0; rolw #8,%0" : "=d" (val) : "0" (val));
 	return val;
 }
-#define __arch__swab32(x) ___arch__swab32(x)
+#define __arch_swab32 __arch_swab32
 
-#endif
-
-#if defined(__GNUC__) && !defined(__STRICT_ANSI__) || defined(__KERNEL__)
-#  define __BYTEORDER_HAS_U64__
-#  define __SWAB_64_THRU_32__
-#endif
-
-#include <linux/byteorder/big_endian.h>
+#include <linux/byteorder.h>
 
 #endif /* _M68K_BYTEORDER_H */
diff --git a/include/asm-m68k/machw.h b/include/asm-m68k/machw.h
index 35624998291c..2b4de0c2ce4a 100644
--- a/include/asm-m68k/machw.h
+++ b/include/asm-m68k/machw.h
@@ -26,28 +26,6 @@
 #include <linux/types.h>
 
 #if 0
-/* Mac SCSI Controller 5380 */
-
-#define	MAC_5380_BAS	(0x50F10000) /* This is definitely wrong!! */
-struct MAC_5380 {
-	u_char	scsi_data;
-	u_char	char_dummy1;
-	u_char	scsi_icr;
-	u_char	char_dummy2;
-	u_char	scsi_mode;
-	u_char	char_dummy3;
-	u_char	scsi_tcr;
-	u_char	char_dummy4;
-	u_char	scsi_idstat;
-	u_char	char_dummy5;
-	u_char	scsi_dmastat;
-	u_char	char_dummy6;
-	u_char	scsi_targrcv;
-	u_char	char_dummy7;
-	u_char	scsi_inircv;
-};
-#define	mac_scsi       ((*(volatile struct MAC_5380 *)MAC_5380_BAS))
-
 /*
 ** SCC Z8530
 */
diff --git a/include/asm-x86/stackprotector.h b/include/asm-x86/stackprotector.h
new file mode 100644
index 000000000000..3baf7ad89be1
--- /dev/null
+++ b/include/asm-x86/stackprotector.h
@@ -0,0 +1,38 @@
+#ifndef _ASM_STACKPROTECTOR_H
+#define _ASM_STACKPROTECTOR_H 1
+
+#include <asm/tsc.h>
+
+/*
+ * Initialize the stackprotector canary value.
+ *
+ * NOTE: this must only be called from functions that never return,
+ * and it must always be inlined.
+ */
+static __always_inline void boot_init_stack_canary(void)
+{
+	u64 canary;
+	u64 tsc;
+
+	/*
+	 * If we're the non-boot CPU, nothing set the PDA stack
+	 * canary up for us - and if we are the boot CPU we have
+	 * a 0 stack canary. This is a good place for updating
+	 * it, as we wont ever return from this function (so the
+	 * invalid canaries already on the stack wont ever
+	 * trigger).
+	 *
+	 * We both use the random pool and the current TSC as a source
+	 * of randomness. The TSC only matters for very early init,
+	 * there it already has some randomness on most systems. Later
+	 * on during the bootup the random pool has true entropy too.
+	 */
+	get_random_bytes(&canary, sizeof(canary));
+	tsc = __native_read_tsc();
+	canary += tsc + (tsc << 32UL);
+
+	current->stack_canary = canary;
+	write_pda(stack_canary, canary);
+}
+
+#endif
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index fba8051fb297..dfa0a5356c53 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -270,6 +270,7 @@ int acpi_check_mem_region(resource_size_t start, resource_size_t n,
 #ifdef CONFIG_PM_SLEEP
 void __init acpi_no_s4_hw_signature(void);
 void __init acpi_old_suspend_ordering(void);
+void __init acpi_s4_no_nvs(void);
 #endif /* CONFIG_PM_SLEEP */
 #else	/* CONFIG_ACPI */
 
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index a135256b272c..031a315c0509 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -662,6 +662,7 @@ extern unsigned long blk_max_low_pfn, blk_max_pfn;
  * default timeout for SG_IO if none specified
  */
 #define BLK_DEFAULT_SG_TIMEOUT	(60 * HZ)
+#define BLK_MIN_SG_TIMEOUT	(7 * HZ)
 
 #ifdef CONFIG_BOUNCE
 extern int init_emergency_isa_pool(void);
@@ -786,6 +787,8 @@ static inline void blk_run_address_space(struct address_space *mapping)
 		blk_run_backing_dev(mapping->backing_dev_info, NULL);
 }
 
+extern void blkdev_dequeue_request(struct request *req);
+
 /*
  * blk_end_request() and friends.
  * __blk_end_request() and end_request() must be called with
@@ -820,11 +823,6 @@ extern void blk_update_request(struct request *rq, int error,
 extern unsigned int blk_rq_bytes(struct request *rq);
 extern unsigned int blk_rq_cur_bytes(struct request *rq);
 
-static inline void blkdev_dequeue_request(struct request *req)
-{
-	elv_dequeue_request(req->q, req);
-}
-
 /*
  * Access functions for manipulating queue properties
  */
@@ -921,6 +919,8 @@ extern void blk_set_cmd_filter_defaults(struct blk_cmd_filter *filter);
 
 #define MAX_SEGMENT_SIZE	65536
 
+#define BLK_SEG_BOUNDARY_MASK	0xFFFFFFFFUL
+
 #define blkdev_entry_to_request(entry) list_entry((entry), struct request, queuelist)
 
 static inline int queue_hardsect_size(struct request_queue *q)
diff --git a/include/linux/bottom_half.h b/include/linux/bottom_half.h
index 777dbf695d44..27b1bcffe408 100644
--- a/include/linux/bottom_half.h
+++ b/include/linux/bottom_half.h
@@ -2,7 +2,6 @@
 #define _LINUX_BH_H
 
 extern void local_bh_disable(void);
-extern void __local_bh_enable(void);
 extern void _local_bh_enable(void);
 extern void local_bh_enable(void);
 extern void local_bh_enable_ip(unsigned long ip);
diff --git a/include/linux/can/core.h b/include/linux/can/core.h
index e9ca210ffa5b..f50785ad4781 100644
--- a/include/linux/can/core.h
+++ b/include/linux/can/core.h
@@ -19,7 +19,7 @@
 #include <linux/skbuff.h>
 #include <linux/netdevice.h>
 
-#define CAN_VERSION "20071116"
+#define CAN_VERSION "20081130"
 
 /* increment this number each time you change some user-space interface */
 #define CAN_ABI_VERSION "8"
diff --git a/include/linux/cdev.h b/include/linux/cdev.h
index fb4591977b03..9c3b17e7f916 100644
--- a/include/linux/cdev.h
+++ b/include/linux/cdev.h
@@ -16,6 +16,7 @@ struct cdev {
 	struct list_head list;
 	dev_t dev;
 	unsigned int count;
+	void (*release)(struct cdev *);
 };
 
 void cdev_init(struct cdev *, const struct file_operations *);
diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index 98115d9d04da..ea7c6be354b7 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -59,8 +59,88 @@ extern void __chk_io_ptr(const volatile void __iomem *);
  * specific implementations come from the above header files
  */
 
-#define likely(x)	__builtin_expect(!!(x), 1)
-#define unlikely(x)	__builtin_expect(!!(x), 0)
+struct ftrace_branch_data {
+	const char *func;
+	const char *file;
+	unsigned line;
+	union {
+		struct {
+			unsigned long correct;
+			unsigned long incorrect;
+		};
+		struct {
+			unsigned long miss;
+			unsigned long hit;
+		};
+	};
+};
+
+/*
+ * Note: DISABLE_BRANCH_PROFILING can be used by special lowlevel code
+ * to disable branch tracing on a per file basis.
+ */
+#if defined(CONFIG_TRACE_BRANCH_PROFILING) && !defined(DISABLE_BRANCH_PROFILING)
+void ftrace_likely_update(struct ftrace_branch_data *f, int val, int expect);
+
+#define likely_notrace(x)	__builtin_expect(!!(x), 1)
+#define unlikely_notrace(x)	__builtin_expect(!!(x), 0)
+
+#define __branch_check__(x, expect) ({					\
+			int ______r;					\
+			static struct ftrace_branch_data		\
+				__attribute__((__aligned__(4)))		\
+				__attribute__((section("_ftrace_annotated_branch"))) \
+				______f = {				\
+				.func = __func__,			\
+				.file = __FILE__,			\
+				.line = __LINE__,			\
+			};						\
+			______r = likely_notrace(x);			\
+			ftrace_likely_update(&______f, ______r, expect); \
+			______r;					\
+		})
+
+/*
+ * Using __builtin_constant_p(x) to ignore cases where the return
+ * value is always the same.  This idea is taken from a similar patch
+ * written by Daniel Walker.
+ */
+# ifndef likely
+#  define likely(x)	(__builtin_constant_p(x) ? !!(x) : __branch_check__(x, 1))
+# endif
+# ifndef unlikely
+#  define unlikely(x)	(__builtin_constant_p(x) ? !!(x) : __branch_check__(x, 0))
+# endif
+
+#ifdef CONFIG_PROFILE_ALL_BRANCHES
+/*
+ * "Define 'is'", Bill Clinton
+ * "Define 'if'", Steven Rostedt
+ */
+#define if(cond) if (__builtin_constant_p((cond)) ? !!(cond) :		\
+	({								\
+		int ______r;						\
+		static struct ftrace_branch_data			\
+			__attribute__((__aligned__(4)))			\
+			__attribute__((section("_ftrace_branch")))	\
+			______f = {					\
+				.func = __func__,			\
+				.file = __FILE__,			\
+				.line = __LINE__,			\
+			};						\
+		______r = !!(cond);					\
+		if (______r)						\
+			______f.hit++;					\
+		else							\
+			______f.miss++;					\
+		______r;						\
+	}))
+#endif /* CONFIG_PROFILE_ALL_BRANCHES */
+
+#else
+# define likely(x)	__builtin_expect(!!(x), 1)
+# define unlikely(x)	__builtin_expect(!!(x), 0)
+#endif
 
 /* Optimization barrier */
 #ifndef barrier
diff --git a/include/linux/debug_locks.h b/include/linux/debug_locks.h
index 4aaa4afb1cb9..096476f1fb35 100644
--- a/include/linux/debug_locks.h
+++ b/include/linux/debug_locks.h
@@ -17,7 +17,7 @@ extern int debug_locks_off(void);
 ({									\
 	int __ret = 0;							\
 									\
-	if (unlikely(c)) {						\
+	if (!oops_in_progress && unlikely(c)) {				\
 		if (debug_locks_off() && !debug_locks_silent)		\
 			WARN_ON(1);					\
 		__ret = 1;						\
diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h
index c17fd334e574..79c4000442d4 100644
--- a/include/linux/device-mapper.h
+++ b/include/linux/device-mapper.h
@@ -45,6 +45,8 @@ typedef void (*dm_dtr_fn) (struct dm_target *ti);
  */
 typedef int (*dm_map_fn) (struct dm_target *ti, struct bio *bio,
 			  union map_info *map_context);
+typedef int (*dm_map_request_fn) (struct dm_target *ti, struct request *clone,
+				  union map_info *map_context);
 
 /*
  * Returns:
@@ -57,6 +59,9 @@ typedef int (*dm_map_fn) (struct dm_target *ti, struct bio *bio,
 typedef int (*dm_endio_fn) (struct dm_target *ti,
 			    struct bio *bio, int error,
 			    union map_info *map_context);
+typedef int (*dm_request_endio_fn) (struct dm_target *ti,
+				    struct request *clone, int error,
+				    union map_info *map_context);
 
 typedef void (*dm_flush_fn) (struct dm_target *ti);
 typedef void (*dm_presuspend_fn) (struct dm_target *ti);
@@ -75,6 +80,13 @@ typedef int (*dm_ioctl_fn) (struct dm_target *ti, unsigned int cmd,
 typedef int (*dm_merge_fn) (struct dm_target *ti, struct bvec_merge_data *bvm,
 			    struct bio_vec *biovec, int max_size);
 
+/*
+ * Returns:
+ *    0: The target can handle the next I/O immediately.
+ *    1: The target can't handle the next I/O immediately.
+ */
+typedef int (*dm_busy_fn) (struct dm_target *ti);
+
 void dm_error(const char *message);
 
 /*
@@ -100,14 +112,23 @@ void dm_put_device(struct dm_target *ti, struct dm_dev *d);
 /*
  * Information about a target type
  */
+
+/*
+ * Target features
+ */
+#define DM_TARGET_SUPPORTS_BARRIERS 0x00000001
+
 struct target_type {
+	uint64_t features;
 	const char *name;
 	struct module *module;
 	unsigned version[3];
 	dm_ctr_fn ctr;
 	dm_dtr_fn dtr;
 	dm_map_fn map;
+	dm_map_request_fn map_rq;
 	dm_endio_fn end_io;
+	dm_request_endio_fn rq_end_io;
 	dm_flush_fn flush;
 	dm_presuspend_fn presuspend;
 	dm_postsuspend_fn postsuspend;
@@ -117,6 +138,7 @@ struct target_type {
 	dm_message_fn message;
 	dm_ioctl_fn ioctl;
 	dm_merge_fn merge;
+	dm_busy_fn busy;
 };
 
 struct io_restrictions {
@@ -157,7 +179,7 @@ struct dm_target {
 };
 
 int dm_register_target(struct target_type *t);
-int dm_unregister_target(struct target_type *t);
+void dm_unregister_target(struct target_type *t);
 
 
 /*-----------------------------------------------------------------
@@ -276,6 +298,9 @@ void *dm_vcalloc(unsigned long nmemb, unsigned long elem_size);
  *---------------------------------------------------------------*/
 #define DM_NAME "device-mapper"
 
+#define DMCRIT(f, arg...) \
+	printk(KERN_CRIT DM_NAME ": " DM_MSG_PREFIX ": " f "\n", ## arg)
+
 #define DMERR(f, arg...) \
 	printk(KERN_ERR DM_NAME ": " DM_MSG_PREFIX ": " f "\n", ## arg)
 #define DMERR_LIMIT(f, arg...) \
diff --git a/include/linux/device.h b/include/linux/device.h
index 1a3686d15f98..4e14fad41430 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -65,7 +65,7 @@ struct bus_type {
 	int (*resume_early)(struct device *dev);
 	int (*resume)(struct device *dev);
 
-	struct pm_ext_ops *pm;
+	struct dev_pm_ops *pm;
 
 	struct bus_type_private *p;
 };
@@ -133,7 +133,7 @@ struct device_driver {
 	int (*resume) (struct device *dev);
 	struct attribute_group **groups;
 
-	struct pm_ops *pm;
+	struct dev_pm_ops *pm;
 
 	struct driver_private *p;
 };
@@ -198,7 +198,7 @@ struct class {
 	int (*suspend)(struct device *dev, pm_message_t state);
 	int (*resume)(struct device *dev);
 
-	struct pm_ops *pm;
+	struct dev_pm_ops *pm;
 	struct class_private *p;
 };
 
@@ -291,7 +291,7 @@ struct device_type {
 	int (*suspend)(struct device *dev, pm_message_t state);
 	int (*resume)(struct device *dev);
 
-	struct pm_ops *pm;
+	struct dev_pm_ops *pm;
 };
 
 /* interface for exporting device attributes */
@@ -373,9 +373,9 @@ struct device {
 
 	struct kobject kobj;
 	char	bus_id[BUS_ID_SIZE];	/* position on parent bus */
+	unsigned		uevent_suppress:1;
 	const char		*init_name; /* initial name of the device */
 	struct device_type	*type;
-	unsigned		uevent_suppress:1;
 
 	struct semaphore	sem;	/* semaphore to synchronize calls to
 					 * its driver.
@@ -408,12 +408,13 @@ struct device {
 	/* arch specific additions */
 	struct dev_archdata	archdata;
 
+	dev_t			devt;	/* dev_t, creates the sysfs "dev" */
+
 	spinlock_t		devres_lock;
 	struct list_head	devres_head;
 
 	struct klist_node	knode_class;
 	struct class		*class;
-	dev_t			devt;	/* dev_t, creates the sysfs "dev" */
 	struct attribute_group	**groups;	/* optional groups */
 
 	void	(*release)(struct device *dev);
diff --git a/include/linux/dmi.h b/include/linux/dmi.h
index e5084eb5943a..2bfda178f274 100644
--- a/include/linux/dmi.h
+++ b/include/linux/dmi.h
@@ -44,6 +44,7 @@ extern const struct dmi_device * dmi_find_device(int type, const char *name,
 extern void dmi_scan_machine(void);
 extern int dmi_get_year(int field);
 extern int dmi_name_in_vendors(const char *str);
+extern int dmi_name_in_serial(const char *str);
 extern int dmi_available;
 extern int dmi_walk(void (*decode)(const struct dmi_header *));
 
@@ -56,6 +57,7 @@ static inline const struct dmi_device * dmi_find_device(int type, const char *na
 static inline void dmi_scan_machine(void) { return; }
 static inline int dmi_get_year(int year) { return 0; }
 static inline int dmi_name_in_vendors(const char *s) { return 0; }
+static inline int dmi_name_in_serial(const char *s) { return 0; }
 #define dmi_available 0
 static inline int dmi_walk(void (*decode)(const struct dmi_header *))
 	{ return -1; }
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 0dcdd9458f4b..a6addeb40644 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -63,23 +63,24 @@ extern int dir_notify_enable;
 #define MAY_ACCESS 16
 #define MAY_OPEN 32
 
-#define FMODE_READ ((__force fmode_t)1)
-#define FMODE_WRITE ((__force fmode_t)2)
-
-/* Internal kernel extensions */
-#define FMODE_LSEEK	((__force fmode_t)4)
-#define FMODE_PREAD	((__force fmode_t)8)
-#define FMODE_PWRITE	FMODE_PREAD	/* These go hand in hand */
-
-/* File is being opened for execution. Primary users of this flag are
-   distributed filesystems that can use it to achieve correct ETXTBUSY
-   behavior for cross-node execution/opening_for_writing of files */
-#define FMODE_EXEC	((__force fmode_t)16)
-
-#define FMODE_NDELAY	((__force fmode_t)32)
-#define FMODE_EXCL	((__force fmode_t)64)
+/* file is open for reading */
+#define FMODE_READ		((__force fmode_t)1)
+/* file is open for writing */
+#define FMODE_WRITE		((__force fmode_t)2)
+/* file is seekable */
+#define FMODE_LSEEK		((__force fmode_t)4)
+/* file can be accessed using pread/pwrite */
+#define FMODE_PREAD		((__force fmode_t)8)
+#define FMODE_PWRITE		FMODE_PREAD	/* These go hand in hand */
+/* File is opened for execution with sys_execve / sys_uselib */
+#define FMODE_EXEC		((__force fmode_t)16)
+/* File is opened with O_NDELAY (only set for block devices) */
+#define FMODE_NDELAY		((__force fmode_t)32)
+/* File is opened with O_EXCL (only set for block devices) */
+#define FMODE_EXCL		((__force fmode_t)64)
+/* File is opened using open(.., 3, ..) and is writeable only for ioctls
+   (specialy hack for floppy.c) */
 #define FMODE_WRITE_IOCTL	((__force fmode_t)128)
-#define FMODE_NDELAY_NOW	((__force fmode_t)256)
 
 #define RW_MASK		1
 #define RWA_MASK	2
@@ -1874,7 +1875,9 @@ extern loff_t default_llseek(struct file *file, loff_t offset, int origin);
 
 extern loff_t vfs_llseek(struct file *file, loff_t offset, int origin);
 
+extern struct inode * inode_init_always(struct super_block *, struct inode *);
 extern void inode_init_once(struct inode *);
+extern void inode_add_to_lists(struct super_block *, struct inode *);
 extern void iput(struct inode *);
 extern struct inode * igrab(struct inode *);
 extern ino_t iunique(struct super_block *, ino_t);
diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index 703eb53cfa2b..7854d87b97b2 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -23,6 +23,45 @@ struct ftrace_ops {
 	struct ftrace_ops *next;
 };
 
+extern int function_trace_stop;
+
+/*
+ * Type of the current tracing.
+ */
+enum ftrace_tracing_type_t {
+	FTRACE_TYPE_ENTER = 0, /* Hook the call of the function */
+	FTRACE_TYPE_RETURN,	/* Hook the return of the function */
+};
+
+/* Current tracing type, default is FTRACE_TYPE_ENTER */
+extern enum ftrace_tracing_type_t ftrace_tracing_type;
+
+/**
+ * ftrace_stop - stop function tracer.
+ *
+ * A quick way to stop the function tracer. Note this an on off switch,
+ * it is not something that is recursive like preempt_disable.
+ * This does not disable the calling of mcount, it only stops the
+ * calling of functions from mcount.
+ */
+static inline void ftrace_stop(void)
+{
+	function_trace_stop = 1;
+}
+
+/**
+ * ftrace_start - start the function tracer.
+ *
+ * This function is the inverse of ftrace_stop. This does not enable
+ * the function tracing if the function tracer is disabled. This only
+ * sets the function tracer flag to continue calling the functions
+ * from mcount.
+ */
+static inline void ftrace_start(void)
+{
+	function_trace_stop = 0;
+}
+
 /*
  * The ftrace_ops must be a static and should also
  * be read_mostly.  These functions do modify read_mostly variables
@@ -41,9 +80,13 @@ extern void ftrace_stub(unsigned long a0, unsigned long a1);
 # define unregister_ftrace_function(ops) do { } while (0)
 # define clear_ftrace_function(ops) do { } while (0)
 static inline void ftrace_kill(void) { }
+static inline void ftrace_stop(void) { }
+static inline void ftrace_start(void) { }
 #endif /* CONFIG_FUNCTION_TRACER */
 
 #ifdef CONFIG_DYNAMIC_FTRACE
+/* asm/ftrace.h must be defined for archs supporting dynamic ftrace */
+#include <asm/ftrace.h>
 
 enum {
 	FTRACE_FL_FREE		= (1 << 0),
@@ -59,6 +102,7 @@ struct dyn_ftrace {
 	struct list_head	list;
 	unsigned long		ip; /* address of mcount call-site */
 	unsigned long		flags;
+	struct dyn_arch_ftrace	arch;
 };
 
 int ftrace_force_update(void);
@@ -66,19 +110,43 @@ void ftrace_set_filter(unsigned char *buf, int len, int reset);
 
 /* defined in arch */
 extern int ftrace_ip_converted(unsigned long ip);
-extern unsigned char *ftrace_nop_replace(void);
-extern unsigned char *ftrace_call_replace(unsigned long ip, unsigned long addr);
 extern int ftrace_dyn_arch_init(void *data);
 extern int ftrace_update_ftrace_func(ftrace_func_t func);
 extern void ftrace_caller(void);
 extern void ftrace_call(void);
 extern void mcount_call(void);
+#ifdef CONFIG_FUNCTION_RET_TRACER
+extern void ftrace_return_caller(void);
+#endif
+
+/**
+ * ftrace_make_nop - convert code into top
+ * @mod: module structure if called by module load initialization
+ * @rec: the mcount call site record
+ * @addr: the address that the call site should be calling
+ *
+ * This is a very sensitive operation and great care needs
+ * to be taken by the arch.  The operation should carefully
+ * read the location, check to see if what is read is indeed
+ * what we expect it to be, and then on success of the compare,
+ * it should write to the location.
+ *
+ * The code segment at @rec->ip should be a caller to @addr
+ *
+ * Return must be:
+ *  0 on success
+ *  -EFAULT on error reading the location
+ *  -EINVAL on a failed compare of the contents
+ *  -EPERM  on error writing to the location
+ * Any other value will be considered a failure.
+ */
+extern int ftrace_make_nop(struct module *mod,
+			   struct dyn_ftrace *rec, unsigned long addr);
 
 /**
- * ftrace_modify_code - modify code segment
- * @ip: the address of the code segment
- * @old_code: the contents of what is expected to be there
- * @new_code: the code to patch in
+ * ftrace_make_call - convert a nop call site into a call to addr
+ * @rec: the mcount call site record
+ * @addr: the address that the call site should call
  *
  * This is a very sensitive operation and great care needs
  * to be taken by the arch.  The operation should carefully
@@ -86,6 +154,8 @@ extern void mcount_call(void);
  * what we expect it to be, and then on success of the compare,
  * it should write to the location.
  *
+ * The code segment at @rec->ip should be a nop
+ *
  * Return must be:
  *  0 on success
  *  -EFAULT on error reading the location
@@ -93,8 +163,11 @@ extern void mcount_call(void);
  *  -EPERM  on error writing to the location
  * Any other value will be considered a failure.
  */
-extern int ftrace_modify_code(unsigned long ip, unsigned char *old_code,
-			      unsigned char *new_code);
+extern int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr);
+
+
+/* May be defined in arch */
+extern int ftrace_arch_read_dyn_info(char *buf, int size);
 
 extern int skip_trace(unsigned long ip);
 
@@ -102,7 +175,6 @@ extern void ftrace_release(void *start, unsigned long size);
 
 extern void ftrace_disable_daemon(void);
 extern void ftrace_enable_daemon(void);
-
 #else
 # define skip_trace(ip)				({ 0; })
 # define ftrace_force_update()			({ 0; })
@@ -181,6 +253,12 @@ static inline void __ftrace_enabled_restore(int enabled)
 #endif
 
 #ifdef CONFIG_TRACING
+extern int ftrace_dump_on_oops;
+
+extern void tracing_start(void);
+extern void tracing_stop(void);
+extern void ftrace_off_permanent(void);
+
 extern void
 ftrace_special(unsigned long arg1, unsigned long arg2, unsigned long arg3);
 
@@ -211,6 +289,9 @@ ftrace_special(unsigned long arg1, unsigned long arg2, unsigned long arg3) { }
 static inline int
 ftrace_printk(const char *fmt, ...) __attribute__ ((format (printf, 1, 0)));
 
+static inline void tracing_start(void) { }
+static inline void tracing_stop(void) { }
+static inline void ftrace_off_permanent(void) { }
 static inline int
 ftrace_printk(const char *fmt, ...)
 {
@@ -221,33 +302,44 @@ static inline void ftrace_dump(void) { }
 
 #ifdef CONFIG_FTRACE_MCOUNT_RECORD
 extern void ftrace_init(void);
-extern void ftrace_init_module(unsigned long *start, unsigned long *end);
+extern void ftrace_init_module(struct module *mod,
+			       unsigned long *start, unsigned long *end);
 #else
 static inline void ftrace_init(void) { }
 static inline void
-ftrace_init_module(unsigned long *start, unsigned long *end) { }
+ftrace_init_module(struct module *mod,
+		   unsigned long *start, unsigned long *end) { }
 #endif
 
 
-struct boot_trace {
-	pid_t			caller;
-	char			func[KSYM_NAME_LEN];
-	int			result;
-	unsigned long long	duration;		/* usecs */
-	ktime_t			calltime;
-	ktime_t			rettime;
+/*
+ * Structure that defines a return function trace.
+ */
+struct ftrace_retfunc {
+	unsigned long ret; /* Return address */
+	unsigned long func; /* Current function */
+	unsigned long long calltime;
+	unsigned long long rettime;
+	/* Number of functions that overran the depth limit for current task */
+	unsigned long overrun;
 };
 
-#ifdef CONFIG_BOOT_TRACER
-extern void trace_boot(struct boot_trace *it, initcall_t fn);
-extern void start_boot_trace(void);
-extern void stop_boot_trace(void);
-#else
-static inline void trace_boot(struct boot_trace *it, initcall_t fn) { }
-static inline void start_boot_trace(void) { }
-static inline void stop_boot_trace(void) { }
-#endif
+#ifdef CONFIG_FUNCTION_RET_TRACER
+#define FTRACE_RETFUNC_DEPTH 50
+#define FTRACE_RETSTACK_ALLOC_SIZE 32
+/* Type of a callback handler of tracing return function */
+typedef void (*trace_function_return_t)(struct ftrace_retfunc *);
 
+extern int register_ftrace_return(trace_function_return_t func);
+/* The current handler in use */
+extern trace_function_return_t ftrace_function_return;
+extern void unregister_ftrace_return(void);
 
+extern void ftrace_retfunc_init_task(struct task_struct *t);
+extern void ftrace_retfunc_exit_task(struct task_struct *t);
+#else
+static inline void ftrace_retfunc_init_task(struct task_struct *t) { }
+static inline void ftrace_retfunc_exit_task(struct task_struct *t) { }
+#endif
 
 #endif /* _LINUX_FTRACE_H */
diff --git a/include/linux/ftrace_irq.h b/include/linux/ftrace_irq.h
new file mode 100644
index 000000000000..0b4df55d7a74
--- /dev/null
+++ b/include/linux/ftrace_irq.h
@@ -0,0 +1,13 @@
+#ifndef _LINUX_FTRACE_IRQ_H
+#define _LINUX_FTRACE_IRQ_H
+
+
+#if defined(CONFIG_DYNAMIC_FTRACE) || defined(CONFIG_FUNCTION_RET_TRACER)
+extern void ftrace_nmi_enter(void);
+extern void ftrace_nmi_exit(void);
+#else
+static inline void ftrace_nmi_enter(void) { }
+static inline void ftrace_nmi_exit(void) { }
+#endif
+
+#endif /* _LINUX_FTRACE_IRQ_H */
diff --git a/include/linux/futex.h b/include/linux/futex.h
index 586ab56a3ec3..3bf5bb5a34f9 100644
--- a/include/linux/futex.h
+++ b/include/linux/futex.h
@@ -25,7 +25,8 @@ union ktime;
 #define FUTEX_WAKE_BITSET	10
 
 #define FUTEX_PRIVATE_FLAG	128
-#define FUTEX_CMD_MASK		~FUTEX_PRIVATE_FLAG
+#define FUTEX_CLOCK_REALTIME	256
+#define FUTEX_CMD_MASK		~(FUTEX_PRIVATE_FLAG | FUTEX_CLOCK_REALTIME)
 
 #define FUTEX_WAIT_PRIVATE	(FUTEX_WAIT | FUTEX_PRIVATE_FLAG)
 #define FUTEX_WAKE_PRIVATE	(FUTEX_WAKE | FUTEX_PRIVATE_FLAG)
@@ -164,6 +165,8 @@ union futex_key {
 	} both;
 };
 
+#define FUTEX_KEY_INIT (union futex_key) { .both = { .ptr = NULL } }
+
 #ifdef CONFIG_FUTEX
 extern void exit_robust_list(struct task_struct *curr);
 extern void exit_pi_state_list(struct task_struct *curr);
diff --git a/include/linux/hardirq.h b/include/linux/hardirq.h
index 181006cc94a0..89a56d79e4c6 100644
--- a/include/linux/hardirq.h
+++ b/include/linux/hardirq.h
@@ -4,6 +4,7 @@
 #include <linux/preempt.h>
 #include <linux/smp_lock.h>
 #include <linux/lockdep.h>
+#include <linux/ftrace_irq.h>
 #include <asm/hardirq.h>
 #include <asm/system.h>
 
@@ -161,7 +162,17 @@ extern void irq_enter(void);
  */
 extern void irq_exit(void);
 
-#define nmi_enter()		do { lockdep_off(); __irq_enter(); } while (0)
-#define nmi_exit()		do { __irq_exit(); lockdep_on(); } while (0)
+#define nmi_enter()				\
+	do {					\
+		ftrace_nmi_enter();		\
+		lockdep_off();			\
+		__irq_enter();			\
+	} while (0)
+#define nmi_exit()				\
+	do {					\
+		__irq_exit();			\
+		lockdep_on();			\
+		ftrace_nmi_exit();		\
+	} while (0)
 
 #endif /* LINUX_HARDIRQ_H */
diff --git a/include/linux/hid.h b/include/linux/hid.h
index e5780f8c934a..215035bbb288 100644
--- a/include/linux/hid.h
+++ b/include/linux/hid.h
@@ -403,15 +403,6 @@ struct hid_output_fifo {
 #define HID_STAT_ADDED		1
 #define HID_STAT_PARSED		2
 
-#define HID_CTRL_RUNNING	1
-#define HID_OUT_RUNNING		2
-#define HID_IN_RUNNING		3
-#define HID_RESET_PENDING	4
-#define HID_SUSPENDED		5
-#define HID_CLEAR_HALT		6
-#define HID_DISCONNECTED	7
-#define HID_STARTED		8
-
 struct hid_input {
 	struct list_head list;
 	struct hid_report *report;
@@ -540,6 +531,8 @@ struct hid_usage_id {
  * @name: driver name (e.g. "Footech_bar-wheel")
  * @id_table: which devices is this driver for (must be non-NULL for probe
  * 	      to be called)
+ * @dyn_list: list of dynamically added device ids
+ * @dyn_lock: lock protecting @dyn_list
  * @probe: new device inserted
  * @remove: device removed (NULL if not a hot-plug capable driver)
  * @report_table: on which reports to call raw_event (NULL means all)
@@ -567,6 +560,9 @@ struct hid_driver {
 	char *name;
 	const struct hid_device_id *id_table;
 
+	struct list_head dyn_list;
+	spinlock_t dyn_lock;
+
 	int (*probe)(struct hid_device *dev, const struct hid_device_id *id);
 	void (*remove)(struct hid_device *dev);
 
diff --git a/include/linux/hidraw.h b/include/linux/hidraw.h
index dbb5c8c374f0..dd8d69269176 100644
--- a/include/linux/hidraw.h
+++ b/include/linux/hidraw.h
@@ -33,6 +33,8 @@ struct hidraw_devinfo {
 #define HIDIOCGRDESCSIZE	_IOR('H', 0x01, int)
 #define HIDIOCGRDESC		_IOR('H', 0x02, struct hidraw_report_descriptor)
 #define HIDIOCGRAWINFO		_IOR('H', 0x03, struct hidraw_devinfo)
+#define HIDIOCGRAWNAME(len)     _IOC(_IOC_READ, 'H', 0x04, len)
+#define HIDIOCGRAWPHYS(len)     _IOC(_IOC_READ, 'H', 0x05, len)
 
 #define HIDRAW_FIRST_MINOR 0
 #define HIDRAW_MAX_DEVICES 64
diff --git a/include/linux/i2c.h b/include/linux/i2c.h
index 33a5992d4936..20873d402467 100644
--- a/include/linux/i2c.h
+++ b/include/linux/i2c.h
@@ -393,11 +393,7 @@ static inline void i2c_set_adapdata(struct i2c_adapter *dev, void *data)
 #define I2C_CLASS_TV_ANALOG	(1<<1)	/* bttv + friends */
 #define I2C_CLASS_TV_DIGITAL	(1<<2)	/* dvb cards */
 #define I2C_CLASS_DDC		(1<<3)	/* DDC bus on graphics adapters */
-#define I2C_CLASS_CAM_ANALOG	(1<<4)	/* camera with analog CCD */
-#define I2C_CLASS_CAM_DIGITAL	(1<<5)	/* most webcams */
-#define I2C_CLASS_SOUND		(1<<6)	/* sound devices */
 #define I2C_CLASS_SPD		(1<<7)	/* SPD EEPROMs and similar */
-#define I2C_CLASS_ALL		(UINT_MAX) /* all of the above */
 
 /* i2c_client_address_data is the struct for holding default client
  * addresses for a driver and for the parameters supplied on the
diff --git a/include/linux/init.h b/include/linux/init.h
index 68cb0265d009..0eb83c92805c 100644
--- a/include/linux/init.h
+++ b/include/linux/init.h
@@ -147,6 +147,7 @@ extern int do_one_initcall(initcall_t fn);
 extern char __initdata boot_command_line[];
 extern char *saved_command_line;
 extern unsigned int reset_devices;
+extern int initmem_now_dynamic;
 
 /* used by init/main.c */
 void setup_arch(char **);
diff --git a/include/linux/ioport.h b/include/linux/ioport.h
index 041e95aac2bf..f6bb2ca8e3ba 100644
--- a/include/linux/ioport.h
+++ b/include/linux/ioport.h
@@ -49,6 +49,7 @@ struct resource_list {
 #define IORESOURCE_SIZEALIGN	0x00020000	/* size indicates alignment */
 #define IORESOURCE_STARTALIGN	0x00040000	/* start field is alignment */
 
+#define IORESOURCE_EXCLUSIVE	0x08000000	/* Userland may not map this resource */
 #define IORESOURCE_DISABLED	0x10000000
 #define IORESOURCE_UNSET	0x20000000
 #define IORESOURCE_AUTO		0x40000000
@@ -133,13 +134,16 @@ static inline unsigned long resource_type(struct resource *res)
 }
 
 /* Convenience shorthand with allocation */
-#define request_region(start,n,name)	__request_region(&ioport_resource, (start), (n), (name))
-#define request_mem_region(start,n,name) __request_region(&iomem_resource, (start), (n), (name))
+#define request_region(start,n,name)	__request_region(&ioport_resource, (start), (n), (name), 0)
+#define __request_mem_region(start,n,name, excl) __request_region(&iomem_resource, (start), (n), (name), excl)
+#define request_mem_region(start,n,name) __request_region(&iomem_resource, (start), (n), (name), 0)
+#define request_mem_region_exclusive(start,n,name) \
+	__request_region(&iomem_resource, (start), (n), (name), IORESOURCE_EXCLUSIVE)
 #define rename_region(region, newname) do { (region)->name = (newname); } while (0)
 
 extern struct resource * __request_region(struct resource *,
 					resource_size_t start,
-					resource_size_t n, const char *name);
+					resource_size_t n, const char *name, int relaxed);
 
 /* Compatibility cruft */
 #define release_region(start,n)	__release_region(&ioport_resource, (start), (n))
@@ -175,6 +179,7 @@ extern struct resource * __devm_request_region(struct device *dev,
 extern void __devm_release_region(struct device *dev, struct resource *parent,
 				  resource_size_t start, resource_size_t n);
 extern int iomem_map_sanity_check(resource_size_t addr, unsigned long size);
+extern int iomem_is_exclusive(u64 addr);
 
 #endif /* __ASSEMBLY__ */
 #endif	/* _LINUX_IOPORT_H */
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index dc7e0d0a6474..269df5a17b30 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -141,6 +141,15 @@ extern int _cond_resched(void);
 		(__x < 0) ? -__x : __x;		\
 	})
 
+#ifdef CONFIG_PROVE_LOCKING
+void might_fault(void);
+#else
+static inline void might_fault(void)
+{
+	might_sleep();
+}
+#endif
+
 extern struct atomic_notifier_head panic_notifier_list;
 extern long (*panic_blink)(long time);
 NORET_TYPE void panic(const char * fmt, ...)
@@ -188,6 +197,8 @@ extern unsigned long long memparse(const char *ptr, char **retptr);
 extern int core_kernel_text(unsigned long addr);
 extern int __kernel_text_address(unsigned long addr);
 extern int kernel_text_address(unsigned long addr);
+extern int func_ptr_is_kernel_text(void *ptr);
+
 struct pid;
 extern struct pid *session_of_pgrp(struct pid *pgrp);
 
diff --git a/include/linux/kexec.h b/include/linux/kexec.h
index 17f76fc05173..adc34f2c6eff 100644
--- a/include/linux/kexec.h
+++ b/include/linux/kexec.h
@@ -100,6 +100,10 @@ struct kimage {
 #define KEXEC_TYPE_DEFAULT 0
 #define KEXEC_TYPE_CRASH   1
 	unsigned int preserve_context : 1;
+
+#ifdef ARCH_HAS_KIMAGE_ARCH
+	struct kimage_arch arch;
+#endif
 };
 
 
diff --git a/include/linux/klist.h b/include/linux/klist.h
index 8ea98db223e5..d5a27af9dba5 100644
--- a/include/linux/klist.h
+++ b/include/linux/klist.h
@@ -13,7 +13,6 @@
 #define _LINUX_KLIST_H
 
 #include <linux/spinlock.h>
-#include <linux/completion.h>
 #include <linux/kref.h>
 #include <linux/list.h>
 
@@ -41,7 +40,6 @@ struct klist_node {
 	void			*n_klist;	/* never access directly */
 	struct list_head	n_node;
 	struct kref		n_ref;
-	struct completion	n_removed;
 };
 
 extern void klist_add_tail(struct klist_node *n, struct klist *k);
diff --git a/include/linux/libata.h b/include/linux/libata.h
index ed3f26eb5df1..3449de597eff 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -213,10 +213,11 @@ enum {
 	ATA_PFLAG_FROZEN	= (1 << 2), /* port is frozen */
 	ATA_PFLAG_RECOVERED	= (1 << 3), /* recovery action performed */
 	ATA_PFLAG_LOADING	= (1 << 4), /* boot/loading probe */
-	ATA_PFLAG_UNLOADING	= (1 << 5), /* module is unloading */
 	ATA_PFLAG_SCSI_HOTPLUG	= (1 << 6), /* SCSI hotplug scheduled */
 	ATA_PFLAG_INITIALIZING	= (1 << 7), /* being initialized, don't touch */
 	ATA_PFLAG_RESETTING	= (1 << 8), /* reset in progress */
+	ATA_PFLAG_UNLOADING	= (1 << 9), /* driver is being unloaded */
+	ATA_PFLAG_UNLOADED	= (1 << 10), /* driver is unloaded */
 
 	ATA_PFLAG_SUSPENDED	= (1 << 17), /* port is suspended (power) */
 	ATA_PFLAG_PM_PENDING	= (1 << 18), /* PM operation pending */
@@ -1285,26 +1286,62 @@ static inline int ata_link_active(struct ata_link *link)
 	return ata_tag_valid(link->active_tag) || link->sactive;
 }
 
-extern struct ata_link *__ata_port_next_link(struct ata_port *ap,
-					     struct ata_link *link,
-					     bool dev_only);
+/*
+ * Iterators
+ *
+ * ATA_LITER_* constants are used to select link iteration mode and
+ * ATA_DITER_* device iteration mode.
+ *
+ * For a custom iteration directly using ata_{link|dev}_next(), if
+ * @link or @dev, respectively, is NULL, the first element is
+ * returned.  @dev and @link can be any valid device or link and the
+ * next element according to the iteration mode will be returned.
+ * After the last element, NULL is returned.
+ */
+enum ata_link_iter_mode {
+	ATA_LITER_EDGE,		/* if present, PMP links only; otherwise,
+				 * host link.  no slave link */
+	ATA_LITER_HOST_FIRST,	/* host link followed by PMP or slave links */
+	ATA_LITER_PMP_FIRST,	/* PMP links followed by host link,
+				 * slave link still comes after host link */
+};
 
-#define __ata_port_for_each_link(link, ap) \
-	for ((link) = __ata_port_next_link((ap), NULL, false); (link); \
-	     (link) = __ata_port_next_link((ap), (link), false))
+enum ata_dev_iter_mode {
+	ATA_DITER_ENABLED,
+	ATA_DITER_ENABLED_REVERSE,
+	ATA_DITER_ALL,
+	ATA_DITER_ALL_REVERSE,
+};
 
-#define ata_port_for_each_link(link, ap) \
-	for ((link) = __ata_port_next_link((ap), NULL, true); (link); \
-	     (link) = __ata_port_next_link((ap), (link), true))
+extern struct ata_link *ata_link_next(struct ata_link *link,
+				      struct ata_port *ap,
+				      enum ata_link_iter_mode mode);
 
-#define ata_link_for_each_dev(dev, link) \
-	for ((dev) = (link)->device; \
-	     (dev) < (link)->device + ata_link_max_devices(link) || ((dev) = NULL); \
-	     (dev)++)
+extern struct ata_device *ata_dev_next(struct ata_device *dev,
+				       struct ata_link *link,
+				       enum ata_dev_iter_mode mode);
+
+/*
+ * Shortcut notation for iterations
+ *
+ * ata_for_each_link() iterates over each link of @ap according to
+ * @mode.  @link points to the current link in the loop.  @link is
+ * NULL after loop termination.  ata_for_each_dev() works the same way
+ * except that it iterates over each device of @link.
+ *
+ * Note that the mode prefixes ATA_{L|D}ITER_ shouldn't need to be
+ * specified when using the following shorthand notations.  Only the
+ * mode itself (EDGE, HOST_FIRST, ENABLED, etc...) should be
+ * specified.  This not only increases brevity but also makes it
+ * impossible to use ATA_LITER_* for device iteration or vice-versa.
+ */
+#define ata_for_each_link(link, ap, mode) \
+	for ((link) = ata_link_next(NULL, (ap), ATA_LITER_##mode); (link); \
+	     (link) = ata_link_next((link), (ap), ATA_LITER_##mode))
 
-#define ata_link_for_each_dev_reverse(dev, link) \
-	for ((dev) = (link)->device + ata_link_max_devices(link) - 1; \
-	     (dev) >= (link)->device || ((dev) = NULL); (dev)--)
+#define ata_for_each_dev(dev, link, mode) \
+	for ((dev) = ata_dev_next(NULL, (link), ATA_DITER_##mode); (dev); \
+	     (dev) = ata_dev_next((dev), (link), ATA_DITER_##mode))
 
 /**
  *	ata_ncq_enabled - Test whether NCQ is enabled
diff --git a/include/linux/linkage.h b/include/linux/linkage.h
index 9fd1f859021b..fee9e59649c1 100644
--- a/include/linux/linkage.h
+++ b/include/linux/linkage.h
@@ -64,14 +64,6 @@
 	name:
 #endif
 
-#define KPROBE_ENTRY(name) \
-  .pushsection .kprobes.text, "ax"; \
-  ENTRY(name)
-
-#define KPROBE_END(name) \
-  END(name);		 \
-  .popsection
-
 #ifndef END
 #define END(name) \
   .size name, .-name
diff --git a/include/linux/lockd/lockd.h b/include/linux/lockd/lockd.h
index b56d5aa9b194..2cf696a36119 100644
--- a/include/linux/lockd/lockd.h
+++ b/include/linux/lockd/lockd.h
@@ -64,9 +64,6 @@ struct nlm_host {
 	struct list_head	h_granted;	/* Locks in GRANTED state */
 	struct list_head	h_reclaim;	/* Locks in RECLAIM state */
 	struct nsm_handle *	h_nsmhandle;	/* NSM status handle */
-
-	char			h_addrbuf[48],	/* address eyecatchers */
-				h_srcaddrbuf[48];
 };
 
 struct nsm_handle {
diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h
index 29aec6e10020..8956daf64abd 100644
--- a/include/linux/lockdep.h
+++ b/include/linux/lockdep.h
@@ -73,6 +73,8 @@ struct lock_class_key {
 	struct lockdep_subclass_key	subkeys[MAX_LOCKDEP_SUBCLASSES];
 };
 
+#define LOCKSTAT_POINTS		4
+
 /*
  * The lock-class itself:
  */
@@ -119,7 +121,8 @@ struct lock_class {
 	int				name_version;
 
 #ifdef CONFIG_LOCK_STAT
-	unsigned long			contention_point[4];
+	unsigned long			contention_point[LOCKSTAT_POINTS];
+	unsigned long			contending_point[LOCKSTAT_POINTS];
 #endif
 };
 
@@ -144,6 +147,7 @@ enum bounce_type {
 
 struct lock_class_stats {
 	unsigned long			contention_point[4];
+	unsigned long			contending_point[4];
 	struct lock_time		read_waittime;
 	struct lock_time		write_waittime;
 	struct lock_time		read_holdtime;
@@ -165,6 +169,7 @@ struct lockdep_map {
 	const char			*name;
 #ifdef CONFIG_LOCK_STAT
 	int				cpu;
+	unsigned long			ip;
 #endif
 };
 
@@ -356,7 +361,7 @@ struct lock_class_key { };
 #ifdef CONFIG_LOCK_STAT
 
 extern void lock_contended(struct lockdep_map *lock, unsigned long ip);
-extern void lock_acquired(struct lockdep_map *lock);
+extern void lock_acquired(struct lockdep_map *lock, unsigned long ip);
 
 #define LOCK_CONTENDED(_lock, try, lock)			\
 do {								\
@@ -364,13 +369,13 @@ do {								\
 		lock_contended(&(_lock)->dep_map, _RET_IP_);	\
 		lock(_lock);					\
 	}							\
-	lock_acquired(&(_lock)->dep_map);			\
+	lock_acquired(&(_lock)->dep_map, _RET_IP_);			\
 } while (0)
 
 #else /* CONFIG_LOCK_STAT */
 
 #define lock_contended(lockdep_map, ip) do {} while (0)
-#define lock_acquired(lockdep_map) do {} while (0)
+#define lock_acquired(lockdep_map, ip) do {} while (0)
 
 #define LOCK_CONTENDED(_lock, try, lock) \
 	lock(_lock)
@@ -481,4 +486,22 @@ static inline void print_irqtrace_events(struct task_struct *curr)
 # define lock_map_release(l)			do { } while (0)
 #endif
 
+#ifdef CONFIG_PROVE_LOCKING
+# define might_lock(lock) 						\
+do {									\
+	typecheck(struct lockdep_map *, &(lock)->dep_map);		\
+	lock_acquire(&(lock)->dep_map, 0, 0, 0, 2, NULL, _THIS_IP_);	\
+	lock_release(&(lock)->dep_map, 0, _THIS_IP_);			\
+} while (0)
+# define might_lock_read(lock) 						\
+do {									\
+	typecheck(struct lockdep_map *, &(lock)->dep_map);		\
+	lock_acquire(&(lock)->dep_map, 0, 0, 1, 2, NULL, _THIS_IP_);	\
+	lock_release(&(lock)->dep_map, 0, _THIS_IP_);			\
+} while (0)
+#else
+# define might_lock(lock) do { } while (0)
+# define might_lock_read(lock) do { } while (0)
+#endif
+
 #endif /* __LINUX_LOCKDEP_H */
diff --git a/include/linux/magic.h b/include/linux/magic.h
index f7f3fdddbef0..a07aa79593b7 100644
--- a/include/linux/magic.h
+++ b/include/linux/magic.h
@@ -46,4 +46,5 @@
 #define FUTEXFS_SUPER_MAGIC	0xBAD1DEA
 #define INOTIFYFS_SUPER_MAGIC	0x2BAD1DEA
 
+#define STACK_END_MAGIC		0x57AC6E9D
 #endif /* __LINUX_MAGIC_H__ */
diff --git a/include/linux/marker.h b/include/linux/marker.h
index 889196c7fbb1..34c14bc957f5 100644
--- a/include/linux/marker.h
+++ b/include/linux/marker.h
@@ -12,6 +12,7 @@
  * See the file COPYING for more details.
  */
 
+#include <stdarg.h>
 #include <linux/types.h>
 
 struct module;
@@ -48,10 +49,28 @@ struct marker {
 	void (*call)(const struct marker *mdata, void *call_private, ...);
 	struct marker_probe_closure single;
 	struct marker_probe_closure *multi;
+	const char *tp_name;	/* Optional tracepoint name */
+	void *tp_cb;		/* Optional tracepoint callback */
 } __attribute__((aligned(8)));
 
 #ifdef CONFIG_MARKERS
 
+#define _DEFINE_MARKER(name, tp_name_str, tp_cb, format)		\
+		static const char __mstrtab_##name[]			\
+		__attribute__((section("__markers_strings")))		\
+		= #name "\0" format;					\
+		static struct marker __mark_##name			\
+		__attribute__((section("__markers"), aligned(8))) =	\
+		{ __mstrtab_##name, &__mstrtab_##name[sizeof(#name)],	\
+		  0, 0, marker_probe_cb, { __mark_empty_function, NULL},\
+		  NULL, tp_name_str, tp_cb }
+
+#define DEFINE_MARKER(name, format)					\
+		_DEFINE_MARKER(name, NULL, NULL, format)
+
+#define DEFINE_MARKER_TP(name, tp_name, tp_cb, format)			\
+		_DEFINE_MARKER(name, #tp_name, tp_cb, format)
+
 /*
  * Note : the empty asm volatile with read constraint is used here instead of a
  * "used" attribute to fix a gcc 4.1.x bug.
@@ -65,14 +84,7 @@ struct marker {
  */
 #define __trace_mark(generic, name, call_private, format, args...)	\
 	do {								\
-		static const char __mstrtab_##name[]			\
-		__attribute__((section("__markers_strings")))		\
-		= #name "\0" format;					\
-		static struct marker __mark_##name			\
-		__attribute__((section("__markers"), aligned(8))) =	\
-		{ __mstrtab_##name, &__mstrtab_##name[sizeof(#name)],	\
-		0, 0, marker_probe_cb,					\
-		{ __mark_empty_function, NULL}, NULL };			\
+		DEFINE_MARKER(name, format);				\
 		__mark_check_format(format, ## args);			\
 		if (unlikely(__mark_##name.state)) {			\
 			(*__mark_##name.call)				\
@@ -80,14 +92,39 @@ struct marker {
 		}							\
 	} while (0)
 
+#define __trace_mark_tp(name, call_private, tp_name, tp_cb, format, args...) \
+	do {								\
+		void __check_tp_type(void)				\
+		{							\
+			register_trace_##tp_name(tp_cb);		\
+		}							\
+		DEFINE_MARKER_TP(name, tp_name, tp_cb, format);		\
+		__mark_check_format(format, ## args);			\
+		(*__mark_##name.call)(&__mark_##name, call_private,	\
+					## args);			\
+	} while (0)
+
 extern void marker_update_probe_range(struct marker *begin,
 	struct marker *end);
+
+#define GET_MARKER(name)	(__mark_##name)
+
 #else /* !CONFIG_MARKERS */
+#define DEFINE_MARKER(name, tp_name, tp_cb, format)
 #define __trace_mark(generic, name, call_private, format, args...) \
 		__mark_check_format(format, ## args)
+#define __trace_mark_tp(name, call_private, tp_name, tp_cb, format, args...) \
+	do {								\
+		void __check_tp_type(void)				\
+		{							\
+			register_trace_##tp_name(tp_cb);		\
+		}							\
+		__mark_check_format(format, ## args);			\
+	} while (0)
 static inline void marker_update_probe_range(struct marker *begin,
 	struct marker *end)
 { }
+#define GET_MARKER(name)
 #endif /* CONFIG_MARKERS */
 
 /**
@@ -117,6 +154,20 @@ static inline void marker_update_probe_range(struct marker *begin,
 	__trace_mark(1, name, NULL, format, ## args)
 
 /**
+ * trace_mark_tp - Marker in a tracepoint callback
+ * @name: marker name, not quoted.
+ * @tp_name: tracepoint name, not quoted.
+ * @tp_cb: tracepoint callback. Should have an associated global symbol so it
+ *         is not optimized away by the compiler (should not be static).
+ * @format: format string
+ * @args...: variable argument list
+ *
+ * Places a marker in a tracepoint callback.
+ */
+#define trace_mark_tp(name, tp_name, tp_cb, format, args...)	\
+	__trace_mark_tp(name, NULL, tp_name, tp_cb, format, ## args)
+
+/**
  * MARK_NOARGS - Format string for a marker with no argument.
  */
 #define MARK_NOARGS " "
@@ -136,8 +187,6 @@ extern marker_probe_func __mark_empty_function;
 
 extern void marker_probe_cb(const struct marker *mdata,
 	void *call_private, ...);
-extern void marker_probe_cb_noarg(const struct marker *mdata,
-	void *call_private, ...);
 
 /*
  * Connect a probe to a marker.
diff --git a/include/linux/mtd/concat.h b/include/linux/mtd/concat.h
index c02f3d264ecf..e80c674daeb3 100644
--- a/include/linux/mtd/concat.h
+++ b/include/linux/mtd/concat.h
@@ -13,7 +13,7 @@
 struct mtd_info *mtd_concat_create(
     struct mtd_info *subdev[],  /* subdevices to concatenate */
     int num_devs,               /* number of subdevices      */
-    char *name);                /* name for the new device   */
+    const char *name);          /* name for the new device   */
 
 void mtd_concat_destroy(struct mtd_info *mtd);
 
diff --git a/include/linux/mutex.h b/include/linux/mutex.h
index bc6da10ceee0..7a0e5c4f8072 100644
--- a/include/linux/mutex.h
+++ b/include/linux/mutex.h
@@ -144,6 +144,8 @@ extern int __must_check mutex_lock_killable(struct mutex *lock);
 /*
  * NOTE: mutex_trylock() follows the spin_trylock() convention,
  *       not the down_trylock() convention!
+ *
+ * Returns 1 if the mutex has been acquired successfully, and 0 on contention.
  */
 extern int mutex_trylock(struct mutex *lock);
 extern void mutex_unlock(struct mutex *lock);
diff --git a/include/linux/nfsd/nfsfh.h b/include/linux/nfsd/nfsfh.h
index d1941cb965e9..b2e093870bc6 100644
--- a/include/linux/nfsd/nfsfh.h
+++ b/include/linux/nfsd/nfsfh.h
@@ -68,6 +68,10 @@ struct nfs_fhbase_old {
  *     1  - 4 byte user specified identifier
  *     2  - 4 byte major, 4 byte minor, 4 byte inode number - DEPRECATED
  *     3  - 4 byte device id, encoded for user-space, 4 byte inode number
+ *     4  - 4 byte inode number and 4 byte uuid
+ *     5  - 8 byte uuid
+ *     6  - 16 byte uuid
+ *     7  - 8 byte inode number and 16 byte uuid
  *
  * The fileid_type identified how the file within the filesystem is encoded.
  * This is (will be) passed to, and set by, the underlying filesystem if it supports
diff --git a/include/linux/of.h b/include/linux/of.h
index e2488f5e7cb2..6a7efa242f5e 100644
--- a/include/linux/of.h
+++ b/include/linux/of.h
@@ -57,6 +57,12 @@ extern struct device_node *of_get_next_child(const struct device_node *node,
 	for (child = of_get_next_child(parent, NULL); child != NULL; \
 	     child = of_get_next_child(parent, child))
 
+extern struct device_node *of_find_node_with_property(
+	struct device_node *from, const char *prop_name);
+#define for_each_node_with_property(dn, prop_name) \
+	for (dn = of_find_node_with_property(NULL, prop_name); dn; \
+	     dn = of_find_node_with_property(dn, prop_name))
+
 extern struct property *of_find_property(const struct device_node *np,
 					 const char *name,
 					 int *lenp);
diff --git a/include/linux/of_gpio.h b/include/linux/of_gpio.h
index 67db101d0eb8..e25abf610cb6 100644
--- a/include/linux/of_gpio.h
+++ b/include/linux/of_gpio.h
@@ -14,9 +14,22 @@
 #ifndef __LINUX_OF_GPIO_H
 #define __LINUX_OF_GPIO_H
 
+#include <linux/compiler.h>
+#include <linux/kernel.h>
 #include <linux/errno.h>
 #include <linux/gpio.h>
 
+struct device_node;
+
+/*
+ * This is Linux-specific flags. By default controllers' and Linux' mapping
+ * match, but GPIO controllers are free to translate their own flags to
+ * Linux-specific in their .xlate callback. Though, 1:1 mapping is recommended.
+ */
+enum of_gpio_flags {
+	OF_GPIO_ACTIVE_LOW = 0x1,
+};
+
 #ifdef CONFIG_OF_GPIO
 
 /*
@@ -26,7 +39,7 @@ struct of_gpio_chip {
 	struct gpio_chip gc;
 	int gpio_cells;
 	int (*xlate)(struct of_gpio_chip *of_gc, struct device_node *np,
-		     const void *gpio_spec);
+		     const void *gpio_spec, enum of_gpio_flags *flags);
 };
 
 static inline struct of_gpio_chip *to_of_gpio_chip(struct gpio_chip *gc)
@@ -50,20 +63,37 @@ static inline struct of_mm_gpio_chip *to_of_mm_gpio_chip(struct gpio_chip *gc)
 	return container_of(of_gc, struct of_mm_gpio_chip, of_gc);
 }
 
-extern int of_get_gpio(struct device_node *np, int index);
+extern int of_get_gpio_flags(struct device_node *np, int index,
+			     enum of_gpio_flags *flags);
+
 extern int of_mm_gpiochip_add(struct device_node *np,
 			      struct of_mm_gpio_chip *mm_gc);
 extern int of_gpio_simple_xlate(struct of_gpio_chip *of_gc,
 				struct device_node *np,
-				const void *gpio_spec);
+				const void *gpio_spec,
+				enum of_gpio_flags *flags);
 #else
 
 /* Drivers may not strictly depend on the GPIO support, so let them link. */
-static inline int of_get_gpio(struct device_node *np, int index)
+static inline int of_get_gpio_flags(struct device_node *np, int index,
+				    enum of_gpio_flags *flags)
 {
 	return -ENOSYS;
 }
 
 #endif /* CONFIG_OF_GPIO */
 
+/**
+ * of_get_gpio - Get a GPIO number to use with GPIO API
+ * @np:		device node to get GPIO from
+ * @index:	index of the GPIO
+ *
+ * Returns GPIO number to use with Linux generic GPIO API, or one of the errno
+ * value on the error condition.
+ */
+static inline int of_get_gpio(struct device_node *np, int index)
+{
+	return of_get_gpio_flags(np, index, NULL);
+}
+
 #endif /* __LINUX_OF_GPIO_H */
diff --git a/include/linux/of_platform.h b/include/linux/of_platform.h
index a8efcfeea732..3d327b67d7e2 100644
--- a/include/linux/of_platform.h
+++ b/include/linux/of_platform.h
@@ -26,8 +26,7 @@ extern struct bus_type of_platform_bus_type;
 
 /*
  * An of_platform_driver driver is attached to a basic of_device on
- * the "platform bus" (of_platform_bus_type) (or ISA, EBUS and SBUS
- * busses on sparc).
+ * the "platform bus" (of_platform_bus_type).
  */
 struct of_platform_driver
 {
diff --git a/include/linux/oxu210hp.h b/include/linux/oxu210hp.h
new file mode 100644
index 000000000000..0bf96eae5389
--- /dev/null
+++ b/include/linux/oxu210hp.h
@@ -0,0 +1,7 @@
+/* platform data for the OXU210HP HCD */
+
+struct oxu210hp_platform_data {
+	unsigned int bus16:1;
+	unsigned int use_hcd_otg:1;
+	unsigned int use_hcd_sph:1;
+};
diff --git a/include/linux/pci-acpi.h b/include/linux/pci-acpi.h
index 8837928fbf33..871e096e0fbc 100644
--- a/include/linux/pci-acpi.h
+++ b/include/linux/pci-acpi.h
@@ -8,6 +8,8 @@
 #ifndef _PCI_ACPI_H_
 #define _PCI_ACPI_H_
 
+#include <linux/acpi.h>
+
 #define OSC_QUERY_TYPE			0
 #define OSC_SUPPORT_TYPE 		1
 #define OSC_CONTROL_TYPE		2
@@ -48,15 +50,7 @@
 
 #ifdef CONFIG_ACPI
 extern acpi_status pci_osc_control_set(acpi_handle handle, u32 flags);
-extern acpi_status __pci_osc_support_set(u32 flags, const char *hid);
-static inline acpi_status pci_osc_support_set(u32 flags)
-{
-	return __pci_osc_support_set(flags, PCI_ROOT_HID_STRING);
-}
-static inline acpi_status pcie_osc_support_set(u32 flags)
-{
-	return __pci_osc_support_set(flags, PCI_EXPRESS_ROOT_HID_STRING);
-}
+int pci_acpi_osc_support(acpi_handle handle, u32 flags);
 static inline acpi_handle acpi_find_root_bridge_handle(struct pci_dev *pdev)
 {
 	/* Find root host bridge */
@@ -73,8 +67,6 @@ typedef u32 		acpi_status;
 #endif    
 static inline acpi_status pci_osc_control_set(acpi_handle handle, u32 flags)
 {return AE_ERROR;}
-static inline acpi_status pci_osc_support_set(u32 flags) {return AE_ERROR;} 
-static inline acpi_status pcie_osc_support_set(u32 flags) {return AE_ERROR;}
 static inline acpi_handle acpi_find_root_bridge_handle(struct pci_dev *pdev)
 { return NULL; }
 #endif
diff --git a/include/linux/pci.h b/include/linux/pci.h
index feb4657bb043..bfcb39ca8879 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -134,6 +134,11 @@ enum pci_dev_flags {
 	PCI_DEV_FLAGS_NO_D3 = (__force pci_dev_flags_t) 2,
 };
 
+enum pci_irq_reroute_variant {
+	INTEL_IRQ_REROUTE_VARIANT = 1,
+	MAX_IRQ_REROUTE_VARIANTS = 3
+};
+
 typedef unsigned short __bitwise pci_bus_flags_t;
 enum pci_bus_flags {
 	PCI_BUS_FLAGS_NO_MSI   = (__force pci_bus_flags_t) 1,
@@ -218,6 +223,7 @@ struct pci_dev {
 	unsigned int	no_msi:1;	/* device may not use msi */
 	unsigned int	block_ucfg_access:1;	/* userspace config space access is blocked */
 	unsigned int	broken_parity_status:1;	/* Device generates false positive parity */
+	unsigned int	irq_reroute_variant:2;	/* device needs IRQ rerouting variant */
 	unsigned int 	msi_enabled:1;
 	unsigned int	msix_enabled:1;
 	unsigned int	ari_enabled:1;	/* ARI forwarding */
@@ -415,7 +421,6 @@ struct pci_driver {
 	int  (*resume_early) (struct pci_dev *dev);
 	int  (*resume) (struct pci_dev *dev);	                /* Device woken up */
 	void (*shutdown) (struct pci_dev *dev);
-	struct pm_ext_ops *pm;
 	struct pci_error_handlers *err_handler;
 	struct device_driver	driver;
 	struct pci_dynids dynids;
@@ -681,10 +686,13 @@ void pci_fixup_irqs(u8 (*)(struct pci_dev *, u8 *),
 		    int (*)(struct pci_dev *, u8, u8));
 #define HAVE_PCI_REQ_REGIONS	2
 int __must_check pci_request_regions(struct pci_dev *, const char *);
+int __must_check pci_request_regions_exclusive(struct pci_dev *, const char *);
 void pci_release_regions(struct pci_dev *);
 int __must_check pci_request_region(struct pci_dev *, int, const char *);
+int __must_check pci_request_region_exclusive(struct pci_dev *, int, const char *);
 void pci_release_region(struct pci_dev *, int);
 int pci_request_selected_regions(struct pci_dev *, int, const char *);
+int pci_request_selected_regions_exclusive(struct pci_dev *, int, const char *);
 void pci_release_selected_regions(struct pci_dev *, int);
 
 /* drivers/pci/bus.c */
@@ -774,6 +782,10 @@ static inline void msi_remove_pci_irq_vectors(struct pci_dev *dev)
 
 static inline void pci_restore_msi_state(struct pci_dev *dev)
 { }
+static inline int pci_msi_enabled(void)
+{
+	return 0;
+}
 #else
 extern int pci_enable_msi(struct pci_dev *dev);
 extern void pci_msi_shutdown(struct pci_dev *dev);
@@ -784,6 +796,16 @@ extern void pci_msix_shutdown(struct pci_dev *dev);
 extern void pci_disable_msix(struct pci_dev *dev);
 extern void msi_remove_pci_irq_vectors(struct pci_dev *dev);
 extern void pci_restore_msi_state(struct pci_dev *dev);
+extern int pci_msi_enabled(void);
+#endif
+
+#ifndef CONFIG_PCIEASPM
+static inline int pcie_aspm_enabled(void)
+{
+	return 0;
+}
+#else
+extern int pcie_aspm_enabled(void);
 #endif
 
 #ifdef CONFIG_HT_IRQ
@@ -1135,6 +1157,8 @@ static inline void pci_mmcfg_early_init(void) { }
 static inline void pci_mmcfg_late_init(void) { }
 #endif
 
+int pci_ext_cfg_avail(struct pci_dev *dev);
+
 #ifdef CONFIG_HAS_IOMEM
 static inline void __iomem *pci_ioremap_bar(struct pci_dev *pdev, int bar)
 {
diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h
index 1800f1d6e40d..b6e694454280 100644
--- a/include/linux/pci_ids.h
+++ b/include/linux/pci_ids.h
@@ -2304,6 +2304,10 @@
 #define PCI_DEVICE_ID_INTEL_PXH_0	0x0329
 #define PCI_DEVICE_ID_INTEL_PXH_1	0x032A
 #define PCI_DEVICE_ID_INTEL_PXHV	0x032C
+#define PCI_DEVICE_ID_INTEL_80332_0	0x0330
+#define PCI_DEVICE_ID_INTEL_80332_1	0x0332
+#define PCI_DEVICE_ID_INTEL_80333_0	0x0370
+#define PCI_DEVICE_ID_INTEL_80333_1	0x0372
 #define PCI_DEVICE_ID_INTEL_82375	0x0482
 #define PCI_DEVICE_ID_INTEL_82424	0x0483
 #define PCI_DEVICE_ID_INTEL_82378	0x0484
@@ -2376,6 +2380,7 @@
 #define PCI_DEVICE_ID_INTEL_ESB_4	0x25a4
 #define PCI_DEVICE_ID_INTEL_ESB_5	0x25a6
 #define PCI_DEVICE_ID_INTEL_ESB_9	0x25ab
+#define PCI_DEVICE_ID_INTEL_ESB_10	0x25ac
 #define PCI_DEVICE_ID_INTEL_82820_HB	0x2500
 #define PCI_DEVICE_ID_INTEL_82820_UP_HB	0x2501
 #define PCI_DEVICE_ID_INTEL_82850_HB	0x2530
diff --git a/include/linux/pci_regs.h b/include/linux/pci_regs.h
index e5effd47ed74..7766488470e4 100644
--- a/include/linux/pci_regs.h
+++ b/include/linux/pci_regs.h
@@ -210,6 +210,7 @@
 #define  PCI_CAP_ID_AGP3	0x0E	/* AGP Target PCI-PCI bridge */
 #define  PCI_CAP_ID_EXP 	0x10	/* PCI Express */
 #define  PCI_CAP_ID_MSIX	0x11	/* MSI-X */
+#define  PCI_CAP_ID_AF		0x13	/* PCI Advanced Features */
 #define PCI_CAP_LIST_NEXT	1	/* Next capability in the list */
 #define PCI_CAP_FLAGS		2	/* Capability defined flags (16 bits) */
 #define PCI_CAP_SIZEOF		4
@@ -316,6 +317,17 @@
 #define  PCI_CHSWP_EXT		0x40	/* ENUM# status - extraction */
 #define  PCI_CHSWP_INS		0x80	/* ENUM# status - insertion */
 
+/* PCI Advanced Feature registers */
+
+#define PCI_AF_LENGTH		2
+#define PCI_AF_CAP		3
+#define  PCI_AF_CAP_TP		0x01
+#define  PCI_AF_CAP_FLR		0x02
+#define PCI_AF_CTRL		4
+#define  PCI_AF_CTRL_FLR	0x01
+#define PCI_AF_STATUS		5
+#define  PCI_AF_STATUS_TP	0x01
+
 /* PCI-X registers */
 
 #define PCI_X_CMD		2	/* Modes & Features */
diff --git a/include/linux/percpu.h b/include/linux/percpu.h
index 9f2a3751873a..e1f87085d39a 100644
--- a/include/linux/percpu.h
+++ b/include/linux/percpu.h
@@ -27,7 +27,18 @@
 #define DEFINE_PER_CPU_PAGE_ALIGNED(type, name)			\
 	__attribute__((__section__(".data.percpu.page_aligned")))	\
 	PER_CPU_ATTRIBUTES __typeof__(type) per_cpu__##name
+
+#ifdef CONFIG_HAVE_ZERO_BASED_PER_CPU
+#define DEFINE_PER_CPU_FIRST(type, name)				\
+	__attribute__((__section__(".data.percpu.first")))		\
+	PER_CPU_ATTRIBUTES __typeof__(type) per_cpu__##name
 #else
+#define DEFINE_PER_CPU_FIRST(type, name)				\
+	DEFINE_PER_CPU(type, name)
+#endif
+
+#else /* !CONFIG_SMP */
+
 #define DEFINE_PER_CPU(type, name)					\
 	PER_CPU_ATTRIBUTES __typeof__(type) per_cpu__##name
 
@@ -36,7 +47,11 @@
 
 #define DEFINE_PER_CPU_PAGE_ALIGNED(type, name)		      \
 	DEFINE_PER_CPU(type, name)
-#endif
+
+#define DEFINE_PER_CPU_FIRST(type, name)				\
+	DEFINE_PER_CPU(type, name)
+
+#endif /* !CONFIG_SMP */
 
 #define EXPORT_PER_CPU_SYMBOL(var) EXPORT_SYMBOL(per_cpu__##var)
 #define EXPORT_PER_CPU_SYMBOL_GPL(var) EXPORT_SYMBOL_GPL(per_cpu__##var)
diff --git a/include/linux/platform_device.h b/include/linux/platform_device.h
index 4b8cc6a32479..9a342699c607 100644
--- a/include/linux/platform_device.h
+++ b/include/linux/platform_device.h
@@ -55,7 +55,6 @@ struct platform_driver {
 	int (*suspend_late)(struct platform_device *, pm_message_t state);
 	int (*resume_early)(struct platform_device *);
 	int (*resume)(struct platform_device *);
-	struct pm_ext_ops *pm;
 	struct device_driver driver;
 };
 
diff --git a/include/linux/pm.h b/include/linux/pm.h
index 42de4003c4ee..de2e0a8f6728 100644
--- a/include/linux/pm.h
+++ b/include/linux/pm.h
@@ -41,7 +41,7 @@ typedef struct pm_message {
 } pm_message_t;
 
 /**
- * struct pm_ops - device PM callbacks
+ * struct dev_pm_ops - device PM callbacks
  *
  * Several driver power state transitions are externally visible, affecting
  * the state of pending I/O queues and (for drivers that touch hardware)
@@ -126,46 +126,6 @@ typedef struct pm_message {
  *	On most platforms, there are no restrictions on availability of
  *	resources like clocks during @restore().
  *
- * All of the above callbacks, except for @complete(), return error codes.
- * However, the error codes returned by the resume operations, @resume(),
- * @thaw(), and @restore(), do not cause the PM core to abort the resume
- * transition during which they are returned.  The error codes returned in
- * that cases are only printed by the PM core to the system logs for debugging
- * purposes.  Still, it is recommended that drivers only return error codes
- * from their resume methods in case of an unrecoverable failure (i.e. when the
- * device being handled refuses to resume and becomes unusable) to allow us to
- * modify the PM core in the future, so that it can avoid attempting to handle
- * devices that failed to resume and their children.
- *
- * It is allowed to unregister devices while the above callbacks are being
- * executed.  However, it is not allowed to unregister a device from within any
- * of its own callbacks.
- */
-
-struct pm_ops {
-	int (*prepare)(struct device *dev);
-	void (*complete)(struct device *dev);
-	int (*suspend)(struct device *dev);
-	int (*resume)(struct device *dev);
-	int (*freeze)(struct device *dev);
-	int (*thaw)(struct device *dev);
-	int (*poweroff)(struct device *dev);
-	int (*restore)(struct device *dev);
-};
-
-/**
- * struct pm_ext_ops - extended device PM callbacks
- *
- * Some devices require certain operations related to suspend and hibernation
- * to be carried out with interrupts disabled.  Thus, 'struct pm_ext_ops' below
- * is defined, adding callbacks to be executed with interrupts disabled to
- * 'struct pm_ops'.
- *
- * The following callbacks included in 'struct pm_ext_ops' are executed with
- * the nonboot CPUs switched off and with interrupts disabled on the only
- * functional CPU.  They also are executed with the PM core list of devices
- * locked, so they must NOT unregister any devices.
- *
  * @suspend_noirq: Complete the operations of ->suspend() by carrying out any
  *	actions required for suspending the device that need interrupts to be
  *	disabled
@@ -190,18 +150,32 @@ struct pm_ops {
  *	actions required for restoring the operations of the device that need
  *	interrupts to be disabled
  *
- * All of the above callbacks return error codes, but the error codes returned
- * by the resume operations, @resume_noirq(), @thaw_noirq(), and
- * @restore_noirq(), do not cause the PM core to abort the resume transition
- * during which they are returned.  The error codes returned in that cases are
- * only printed by the PM core to the system logs for debugging purposes.
- * Still, as stated above, it is recommended that drivers only return error
- * codes from their resume methods if the device being handled fails to resume
- * and is not usable any more.
+ * All of the above callbacks, except for @complete(), return error codes.
+ * However, the error codes returned by the resume operations, @resume(),
+ * @thaw(), @restore(), @resume_noirq(), @thaw_noirq(), and @restore_noirq() do
+ * not cause the PM core to abort the resume transition during which they are
+ * returned.  The error codes returned in that cases are only printed by the PM
+ * core to the system logs for debugging purposes.  Still, it is recommended
+ * that drivers only return error codes from their resume methods in case of an
+ * unrecoverable failure (i.e. when the device being handled refuses to resume
+ * and becomes unusable) to allow us to modify the PM core in the future, so
+ * that it can avoid attempting to handle devices that failed to resume and
+ * their children.
+ *
+ * It is allowed to unregister devices while the above callbacks are being
+ * executed.  However, it is not allowed to unregister a device from within any
+ * of its own callbacks.
  */
 
-struct pm_ext_ops {
-	struct pm_ops base;
+struct dev_pm_ops {
+	int (*prepare)(struct device *dev);
+	void (*complete)(struct device *dev);
+	int (*suspend)(struct device *dev);
+	int (*resume)(struct device *dev);
+	int (*freeze)(struct device *dev);
+	int (*thaw)(struct device *dev);
+	int (*poweroff)(struct device *dev);
+	int (*restore)(struct device *dev);
 	int (*suspend_noirq)(struct device *dev);
 	int (*resume_noirq)(struct device *dev);
 	int (*freeze_noirq)(struct device *dev);
@@ -278,7 +252,7 @@ struct pm_ext_ops {
 #define PM_EVENT_SLEEP		(PM_EVENT_SUSPEND | PM_EVENT_HIBERNATE)
 #define PM_EVENT_USER_SUSPEND	(PM_EVENT_USER | PM_EVENT_SUSPEND)
 #define PM_EVENT_USER_RESUME	(PM_EVENT_USER | PM_EVENT_RESUME)
-#define PM_EVENT_REMOTE_WAKEUP	(PM_EVENT_REMOTE | PM_EVENT_RESUME)
+#define PM_EVENT_REMOTE_RESUME	(PM_EVENT_REMOTE | PM_EVENT_RESUME)
 #define PM_EVENT_AUTO_SUSPEND	(PM_EVENT_AUTO | PM_EVENT_SUSPEND)
 #define PM_EVENT_AUTO_RESUME	(PM_EVENT_AUTO | PM_EVENT_RESUME)
 
@@ -291,15 +265,15 @@ struct pm_ext_ops {
 #define PMSG_THAW	((struct pm_message){ .event = PM_EVENT_THAW, })
 #define PMSG_RESTORE	((struct pm_message){ .event = PM_EVENT_RESTORE, })
 #define PMSG_RECOVER	((struct pm_message){ .event = PM_EVENT_RECOVER, })
-#define PMSG_USER_SUSPEND	((struct pm_messge) \
+#define PMSG_USER_SUSPEND	((struct pm_message) \
 					{ .event = PM_EVENT_USER_SUSPEND, })
-#define PMSG_USER_RESUME	((struct pm_messge) \
+#define PMSG_USER_RESUME	((struct pm_message) \
 					{ .event = PM_EVENT_USER_RESUME, })
-#define PMSG_REMOTE_RESUME	((struct pm_messge) \
+#define PMSG_REMOTE_RESUME	((struct pm_message) \
 					{ .event = PM_EVENT_REMOTE_RESUME, })
-#define PMSG_AUTO_SUSPEND	((struct pm_messge) \
+#define PMSG_AUTO_SUSPEND	((struct pm_message) \
 					{ .event = PM_EVENT_AUTO_SUSPEND, })
-#define PMSG_AUTO_RESUME		((struct pm_messge) \
+#define PMSG_AUTO_RESUME	((struct pm_message) \
 					{ .event = PM_EVENT_AUTO_RESUME, })
 
 /**
diff --git a/include/linux/poison.h b/include/linux/poison.h
index 9f31683728fd..603d3bda31d9 100644
--- a/include/linux/poison.h
+++ b/include/linux/poison.h
@@ -2,13 +2,25 @@
 #define _LINUX_POISON_H
 
 /********** include/linux/list.h **********/
+
+/*
+ * Architectures might want to move the poison pointer offset
+ * into some well-recognized area such as 0xdead000000000000,
+ * that is also not mappable by user-space exploits:
+ */
+#ifdef CONFIG_ILLEGAL_POINTER_VALUE
+# define POISON_POINTER_DELTA CONFIG_ILLEGAL_POINTER_VALUE
+#else
+# define POISON_POINTER_DELTA 0
+#endif
+
 /*
  * These are non-NULL pointers that will result in page faults
  * under normal circumstances, used to verify that nobody uses
  * non-initialized list entries.
  */
-#define LIST_POISON1  ((void *) 0x00100100)
-#define LIST_POISON2  ((void *) 0x00200200)
+#define LIST_POISON1  ((void *) 0x00100100 + POISON_POINTER_DELTA)
+#define LIST_POISON2  ((void *) 0x00200200 + POISON_POINTER_DELTA)
 
 /********** include/linux/timer.h **********/
 /*
diff --git a/include/linux/rcuclassic.h b/include/linux/rcuclassic.h
index 5f89b62e6983..301dda829e37 100644
--- a/include/linux/rcuclassic.h
+++ b/include/linux/rcuclassic.h
@@ -41,7 +41,7 @@
 #include <linux/seqlock.h>
 
 #ifdef CONFIG_RCU_CPU_STALL_DETECTOR
-#define RCU_SECONDS_TILL_STALL_CHECK	( 3 * HZ) /* for rcp->jiffies_stall */
+#define RCU_SECONDS_TILL_STALL_CHECK	(10 * HZ) /* for rcp->jiffies_stall */
 #define RCU_SECONDS_TILL_STALL_RECHECK	(30 * HZ) /* for rcp->jiffies_stall */
 #endif /* #ifdef CONFIG_RCU_CPU_STALL_DETECTOR */
 
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 86f1f5e43e33..895dc9c1088c 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -142,6 +142,7 @@ struct rcu_head {
  * on the write-side to insure proper synchronization.
  */
 #define rcu_read_lock_sched() preempt_disable()
+#define rcu_read_lock_sched_notrace() preempt_disable_notrace()
 
 /*
  * rcu_read_unlock_sched - marks the end of a RCU-classic critical section
@@ -149,6 +150,7 @@ struct rcu_head {
  * See rcu_read_lock_sched for more information.
  */
 #define rcu_read_unlock_sched() preempt_enable()
+#define rcu_read_unlock_sched_notrace() preempt_enable_notrace()
 
 
 
diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h
index e097c2e6b6dc..3bb87a753fa3 100644
--- a/include/linux/ring_buffer.h
+++ b/include/linux/ring_buffer.h
@@ -122,6 +122,7 @@ void ring_buffer_normalize_time_stamp(int cpu, u64 *ts);
 
 void tracing_on(void);
 void tracing_off(void);
+void tracing_off_permanent(void);
 
 enum ring_buffer_flags {
 	RB_FL_OVERWRITE		= 1 << 0,
diff --git a/include/linux/rio_drv.h b/include/linux/rio_drv.h
index 90987b7bcc1b..32c0547ffafc 100644
--- a/include/linux/rio_drv.h
+++ b/include/linux/rio_drv.h
@@ -427,9 +427,9 @@ void rio_dev_put(struct rio_dev *);
  * Get the unique RIO device identifier. Returns the device
  * identifier string.
  */
-static inline char *rio_name(struct rio_dev *rdev)
+static inline const char *rio_name(struct rio_dev *rdev)
 {
-	return rdev->dev.bus_id;
+	return dev_name(&rdev->dev);
 }
 
 /**
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 55e30d114477..9fa6b3bead7c 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -259,8 +259,6 @@ static inline int select_nohz_load_balancer(int cpu)
 }
 #endif
 
-extern unsigned long rt_needs_cpu(int cpu);
-
 /*
  * Only dump TASK_* tasks. (0 for all tasks)
  */
@@ -1139,10 +1137,9 @@ struct task_struct {
 	pid_t pid;
 	pid_t tgid;
 
-#ifdef CONFIG_CC_STACKPROTECTOR
 	/* Canary value for the -fstack-protector gcc feature */
 	unsigned long stack_canary;
-#endif
+
 	/* 
 	 * pointers to (original) parent process, youngest child, younger sibling,
 	 * older sibling, respectively.  (p->father can be replaced with 
@@ -1356,6 +1353,17 @@ struct task_struct {
 	unsigned long default_timer_slack_ns;
 
 	struct list_head	*scm_work_list;
+#ifdef CONFIG_FUNCTION_RET_TRACER
+	/* Index of current stored adress in ret_stack */
+	int curr_ret_stack;
+	/* Stack of return addresses for return function tracing */
+	struct ftrace_ret_stack	*ret_stack;
+	/*
+	 * Number of functions that haven't been traced
+	 * because of depth overrun.
+	 */
+	atomic_t trace_overrun;
+#endif
 };
 
 /*
@@ -2028,6 +2036,19 @@ static inline int object_is_on_stack(void *obj)
 
 extern void thread_info_cache_init(void);
 
+#ifdef CONFIG_DEBUG_STACK_USAGE
+static inline unsigned long stack_not_used(struct task_struct *p)
+{
+	unsigned long *n = end_of_stack(p);
+
+	do { 	/* Skip over canary */
+		n++;
+	} while (!*n);
+
+	return (unsigned long)n - (unsigned long)end_of_stack(p);
+}
+#endif
+
 /* set thread flags in other task's structures
  * - see asm/thread_info.h for TIF_xxxx flags available
  */
@@ -2224,6 +2245,7 @@ extern void normalize_rt_tasks(void);
 extern struct task_group init_task_group;
 #ifdef CONFIG_USER_SCHED
 extern struct task_group root_task_group;
+extern void set_tg_uid(struct user_struct *user);
 #endif
 
 extern struct task_group *sched_create_group(struct task_group *parent);
diff --git a/include/linux/seq_file.h b/include/linux/seq_file.h
index dc50bcc282a8..b3dfa72f13b9 100644
--- a/include/linux/seq_file.h
+++ b/include/linux/seq_file.h
@@ -34,6 +34,7 @@ struct seq_operations {
 
 #define SEQ_SKIP 1
 
+char *mangle_path(char *s, char *p, char *esc);
 int seq_open(struct file *, const struct seq_operations *);
 ssize_t seq_read(struct file *, char __user *, size_t, loff_t *);
 loff_t seq_lseek(struct file *, loff_t, int);
diff --git a/include/linux/stackprotector.h b/include/linux/stackprotector.h
new file mode 100644
index 000000000000..6f3e54c704c0
--- /dev/null
+++ b/include/linux/stackprotector.h
@@ -0,0 +1,16 @@
+#ifndef _LINUX_STACKPROTECTOR_H
+#define _LINUX_STACKPROTECTOR_H 1
+
+#include <linux/compiler.h>
+#include <linux/sched.h>
+#include <linux/random.h>
+
+#ifdef CONFIG_CC_STACKPROTECTOR
+# include <asm/stackprotector.h>
+#else
+static inline void boot_init_stack_canary(void)
+{
+}
+#endif
+
+#endif
diff --git a/include/linux/stacktrace.h b/include/linux/stacktrace.h
index b106fd8e0d5c..1a8cecc4f38c 100644
--- a/include/linux/stacktrace.h
+++ b/include/linux/stacktrace.h
@@ -15,9 +15,17 @@ extern void save_stack_trace_tsk(struct task_struct *tsk,
 				struct stack_trace *trace);
 
 extern void print_stack_trace(struct stack_trace *trace, int spaces);
+
+#ifdef CONFIG_USER_STACKTRACE_SUPPORT
+extern void save_stack_trace_user(struct stack_trace *trace);
+#else
+# define save_stack_trace_user(trace)              do { } while (0)
+#endif
+
 #else
 # define save_stack_trace(trace)			do { } while (0)
 # define save_stack_trace_tsk(tsk, trace)		do { } while (0)
+# define save_stack_trace_user(trace)			do { } while (0)
 # define print_stack_trace(trace, spaces)		do { } while (0)
 #endif
 
diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h
index 3afe7fb403b2..3435d24bfe55 100644
--- a/include/linux/sunrpc/svc.h
+++ b/include/linux/sunrpc/svc.h
@@ -58,10 +58,13 @@ struct svc_serv {
 	struct svc_stat *	sv_stats;	/* RPC statistics */
 	spinlock_t		sv_lock;
 	unsigned int		sv_nrthreads;	/* # of server threads */
+	unsigned int		sv_maxconn;	/* max connections allowed or
+						 * '0' causing max to be based
+						 * on number of threads. */
+
 	unsigned int		sv_max_payload;	/* datagram payload size */
 	unsigned int		sv_max_mesg;	/* max_payload + 1 page for overheads */
 	unsigned int		sv_xdrsize;	/* XDR buffer size */
-
 	struct list_head	sv_permsocks;	/* all permanent sockets */
 	struct list_head	sv_tempsocks;	/* all temporary sockets */
 	int			sv_tmpcnt;	/* count of temporary sockets */
diff --git a/include/linux/suspend.h b/include/linux/suspend.h
index 2ce8207686e2..2b409c44db83 100644
--- a/include/linux/suspend.h
+++ b/include/linux/suspend.h
@@ -232,6 +232,11 @@ extern unsigned long get_safe_page(gfp_t gfp_mask);
 
 extern void hibernation_set_ops(struct platform_hibernation_ops *ops);
 extern int hibernate(void);
+extern int hibernate_nvs_register(unsigned long start, unsigned long size);
+extern int hibernate_nvs_alloc(void);
+extern void hibernate_nvs_free(void);
+extern void hibernate_nvs_save(void);
+extern void hibernate_nvs_restore(void);
 #else /* CONFIG_HIBERNATION */
 static inline int swsusp_page_is_forbidden(struct page *p) { return 0; }
 static inline void swsusp_set_page_free(struct page *p) {}
@@ -239,6 +244,14 @@ static inline void swsusp_unset_page_free(struct page *p) {}
 
 static inline void hibernation_set_ops(struct platform_hibernation_ops *ops) {}
 static inline int hibernate(void) { return -ENOSYS; }
+static inline int hibernate_nvs_register(unsigned long a, unsigned long b)
+{
+	return 0;
+}
+static inline int hibernate_nvs_alloc(void) { return 0; }
+static inline void hibernate_nvs_free(void) {}
+static inline void hibernate_nvs_save(void) {}
+static inline void hibernate_nvs_restore(void) {}
 #endif /* CONFIG_HIBERNATION */
 
 #ifdef CONFIG_PM_SLEEP
diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h
index c5bb39c7a770..757005458366 100644
--- a/include/linux/tracepoint.h
+++ b/include/linux/tracepoint.h
@@ -24,8 +24,12 @@ struct tracepoint {
 	const char *name;		/* Tracepoint name */
 	int state;			/* State. */
 	void **funcs;
-} __attribute__((aligned(8)));
-
+} __attribute__((aligned(32)));		/*
+					 * Aligned on 32 bytes because it is
+					 * globally visible and gcc happily
+					 * align these on the structure size.
+					 * Keep in sync with vmlinux.lds.h.
+					 */
 
 #define TPPROTO(args...)	args
 #define TPARGS(args...)		args
@@ -40,14 +44,14 @@ struct tracepoint {
 	do {								\
 		void **it_func;						\
 									\
-		rcu_read_lock_sched();					\
+		rcu_read_lock_sched_notrace();				\
 		it_func = rcu_dereference((tp)->funcs);			\
 		if (it_func) {						\
 			do {						\
 				((void(*)(proto))(*it_func))(args);	\
 			} while (*(++it_func));				\
 		}							\
-		rcu_read_unlock_sched();				\
+		rcu_read_unlock_sched_notrace();			\
 	} while (0)
 
 /*
@@ -55,35 +59,40 @@ struct tracepoint {
  * not add unwanted padding between the beginning of the section and the
  * structure. Force alignment to the same alignment as the section start.
  */
-#define DEFINE_TRACE(name, proto, args)					\
+#define DECLARE_TRACE(name, proto, args)				\
+	extern struct tracepoint __tracepoint_##name;			\
 	static inline void trace_##name(proto)				\
 	{								\
-		static const char __tpstrtab_##name[]			\
-		__attribute__((section("__tracepoints_strings")))	\
-		= #name ":" #proto;					\
-		static struct tracepoint __tracepoint_##name		\
-		__attribute__((section("__tracepoints"), aligned(8))) =	\
-		{ __tpstrtab_##name, 0, NULL };				\
 		if (unlikely(__tracepoint_##name.state))		\
 			__DO_TRACE(&__tracepoint_##name,		\
 				TPPROTO(proto), TPARGS(args));		\
 	}								\
 	static inline int register_trace_##name(void (*probe)(proto))	\
 	{								\
-		return tracepoint_probe_register(#name ":" #proto,	\
-			(void *)probe);					\
+		return tracepoint_probe_register(#name, (void *)probe);	\
 	}								\
-	static inline void unregister_trace_##name(void (*probe)(proto))\
+	static inline int unregister_trace_##name(void (*probe)(proto))	\
 	{								\
-		tracepoint_probe_unregister(#name ":" #proto,		\
-			(void *)probe);					\
+		return tracepoint_probe_unregister(#name, (void *)probe);\
 	}
 
+#define DEFINE_TRACE(name)						\
+	static const char __tpstrtab_##name[]				\
+	__attribute__((section("__tracepoints_strings"))) = #name;	\
+	struct tracepoint __tracepoint_##name				\
+	__attribute__((section("__tracepoints"), aligned(32))) =	\
+		{ __tpstrtab_##name, 0, NULL }
+
+#define EXPORT_TRACEPOINT_SYMBOL_GPL(name)				\
+	EXPORT_SYMBOL_GPL(__tracepoint_##name)
+#define EXPORT_TRACEPOINT_SYMBOL(name)					\
+	EXPORT_SYMBOL(__tracepoint_##name)
+
 extern void tracepoint_update_probe_range(struct tracepoint *begin,
 	struct tracepoint *end);
 
 #else /* !CONFIG_TRACEPOINTS */
-#define DEFINE_TRACE(name, proto, args)			\
+#define DECLARE_TRACE(name, proto, args)				\
 	static inline void _do_trace_##name(struct tracepoint *tp, proto) \
 	{ }								\
 	static inline void trace_##name(proto)				\
@@ -92,8 +101,14 @@ extern void tracepoint_update_probe_range(struct tracepoint *begin,
 	{								\
 		return -ENOSYS;						\
 	}								\
-	static inline void unregister_trace_##name(void (*probe)(proto))\
-	{ }
+	static inline int unregister_trace_##name(void (*probe)(proto))	\
+	{								\
+		return -ENOSYS;						\
+	}
+
+#define DEFINE_TRACE(name)
+#define EXPORT_TRACEPOINT_SYMBOL_GPL(name)
+#define EXPORT_TRACEPOINT_SYMBOL(name)
 
 static inline void tracepoint_update_probe_range(struct tracepoint *begin,
 	struct tracepoint *end)
@@ -112,6 +127,10 @@ extern int tracepoint_probe_register(const char *name, void *probe);
  */
 extern int tracepoint_probe_unregister(const char *name, void *probe);
 
+extern int tracepoint_probe_register_noupdate(const char *name, void *probe);
+extern int tracepoint_probe_unregister_noupdate(const char *name, void *probe);
+extern void tracepoint_probe_update_all(void);
+
 struct tracepoint_iter {
 	struct module *module;
 	struct tracepoint *tracepoint;
diff --git a/include/linux/tty.h b/include/linux/tty.h
index 3b8121d4e36f..eaec37c9d83d 100644
--- a/include/linux/tty.h
+++ b/include/linux/tty.h
@@ -325,7 +325,7 @@ extern struct class *tty_class;
  *	go away
  */
 
-extern inline struct tty_struct *tty_kref_get(struct tty_struct *tty)
+static inline struct tty_struct *tty_kref_get(struct tty_struct *tty)
 {
 	if (tty)
 		kref_get(&tty->kref);
diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h
index fec6decfb983..6b58367d145e 100644
--- a/include/linux/uaccess.h
+++ b/include/linux/uaccess.h
@@ -78,7 +78,7 @@ static inline unsigned long __copy_from_user_nocache(void *to,
 							\
 		set_fs(KERNEL_DS);			\
 		pagefault_disable();			\
-		ret = __get_user(retval, (__force typeof(retval) __user *)(addr));		\
+		ret = __copy_from_user_inatomic(&(retval), (__force typeof(retval) __user *)(addr), sizeof(retval));		\
 		pagefault_enable();			\
 		set_fs(old_fs);				\
 		ret;					\
diff --git a/include/linux/usb.h b/include/linux/usb.h
index f72aa51f7bcd..74d0b9990c73 100644
--- a/include/linux/usb.h
+++ b/include/linux/usb.h
@@ -120,6 +120,11 @@ enum usb_interface_condition {
  *	to the sysfs representation for that device.
  * @pm_usage_cnt: PM usage counter for this interface; autosuspend is not
  *	allowed unless the counter is 0.
+ * @reset_ws: Used for scheduling resets from atomic context.
+ * @reset_running: set to 1 if the interface is currently running a
+ *      queued reset so that usb_cancel_queued_reset() doesn't try to
+ *      remove from the workqueue when running inside the worker
+ *      thread. See __usb_queue_reset_device().
  *
  * USB device drivers attach to interfaces on a physical device.  Each
  * interface encapsulates a single high level function, such as feeding
@@ -168,10 +173,12 @@ struct usb_interface {
 	unsigned needs_remote_wakeup:1;	/* driver requires remote wakeup */
 	unsigned needs_altsetting0:1;	/* switch to altsetting 0 is pending */
 	unsigned needs_binding:1;	/* needs delayed unbind/rebind */
+	unsigned reset_running:1;
 
 	struct device dev;		/* interface specific device info */
 	struct device *usb_dev;
 	int pm_usage_cnt;		/* usage counter for autosuspend */
+	struct work_struct reset_ws;	/* for resets in atomic context */
 };
 #define	to_usb_interface(d) container_of(d, struct usb_interface, dev)
 #define	interface_to_usbdev(intf) \
@@ -329,7 +336,7 @@ struct usb_bus {
 #endif
 	struct device *dev;		/* device for this bus */
 
-#if defined(CONFIG_USB_MON)
+#if defined(CONFIG_USB_MON) || defined(CONFIG_USB_MON_MODULE)
 	struct mon_bus *mon_bus;	/* non-null when associated */
 	int monitored;			/* non-zero when monitored */
 #endif
@@ -398,6 +405,7 @@ struct usb_tt;
  * @urbnum: number of URBs submitted for the whole device
  * @active_duration: total time device is not suspended
  * @autosuspend: for delayed autosuspends
+ * @autoresume: for autoresumes requested while in_interrupt
  * @pm_mutex: protects PM operations
  * @last_busy: time of last use
  * @autosuspend_delay: in jiffies
@@ -476,6 +484,7 @@ struct usb_device {
 
 #ifdef CONFIG_PM
 	struct delayed_work autosuspend;
+	struct work_struct autoresume;
 	struct mutex pm_mutex;
 
 	unsigned long last_busy;
@@ -505,6 +514,7 @@ extern int usb_lock_device_for_reset(struct usb_device *udev,
 
 /* USB port reset for device reinitialization */
 extern int usb_reset_device(struct usb_device *dev);
+extern void usb_queue_reset_device(struct usb_interface *dev);
 
 extern struct usb_device *usb_find_device(u16 vendor_id, u16 product_id);
 
@@ -513,6 +523,8 @@ extern struct usb_device *usb_find_device(u16 vendor_id, u16 product_id);
 extern int usb_autopm_set_interface(struct usb_interface *intf);
 extern int usb_autopm_get_interface(struct usb_interface *intf);
 extern void usb_autopm_put_interface(struct usb_interface *intf);
+extern int usb_autopm_get_interface_async(struct usb_interface *intf);
+extern void usb_autopm_put_interface_async(struct usb_interface *intf);
 
 static inline void usb_autopm_enable(struct usb_interface *intf)
 {
@@ -539,8 +551,13 @@ static inline int usb_autopm_set_interface(struct usb_interface *intf)
 static inline int usb_autopm_get_interface(struct usb_interface *intf)
 { return 0; }
 
+static inline int usb_autopm_get_interface_async(struct usb_interface *intf)
+{ return 0; }
+
 static inline void usb_autopm_put_interface(struct usb_interface *intf)
 { }
+static inline void usb_autopm_put_interface_async(struct usb_interface *intf)
+{ }
 static inline void usb_autopm_enable(struct usb_interface *intf)
 { }
 static inline void usb_autopm_disable(struct usb_interface *intf)
@@ -1050,7 +1067,7 @@ struct usb_device_driver {
 	void (*disconnect) (struct usb_device *udev);
 
 	int (*suspend) (struct usb_device *udev, pm_message_t message);
-	int (*resume) (struct usb_device *udev);
+	int (*resume) (struct usb_device *udev, pm_message_t message);
 	struct usbdrv_wrap drvwrap;
 	unsigned int supports_autosuspend:1;
 };
diff --git a/include/linux/usb/association.h b/include/linux/usb/association.h
index 07c5e3cf5898..0a4a18b3c1bb 100644
--- a/include/linux/usb/association.h
+++ b/include/linux/usb/association.h
@@ -28,17 +28,17 @@ struct wusb_am_attr {
 };
 
 /* Different fields defined by the spec */
-#define WUSB_AR_AssociationTypeId	{ .id = 0x0000, .len =  2 }
-#define WUSB_AR_AssociationSubTypeId	{ .id = 0x0001, .len =  2 }
-#define WUSB_AR_Length			{ .id = 0x0002, .len =  4 }
-#define WUSB_AR_AssociationStatus	{ .id = 0x0004, .len =  4 }
-#define WUSB_AR_LangID			{ .id = 0x0008, .len =  2 }
-#define WUSB_AR_DeviceFriendlyName	{ .id = 0x000b, .len = 64 } /* max */
-#define WUSB_AR_HostFriendlyName	{ .id = 0x000c, .len = 64 } /* max */
-#define WUSB_AR_CHID			{ .id = 0x1000, .len = 16 }
-#define WUSB_AR_CDID			{ .id = 0x1001, .len = 16 }
-#define WUSB_AR_ConnectionContext	{ .id = 0x1002, .len = 48 }
-#define WUSB_AR_BandGroups		{ .id = 0x1004, .len =  2 }
+#define WUSB_AR_AssociationTypeId	{ .id = cpu_to_le16(0x0000), .len = cpu_to_le16(2) }
+#define WUSB_AR_AssociationSubTypeId	{ .id = cpu_to_le16(0x0001), .len = cpu_to_le16(2) }
+#define WUSB_AR_Length			{ .id = cpu_to_le16(0x0002), .len = cpu_to_le16(4) }
+#define WUSB_AR_AssociationStatus	{ .id = cpu_to_le16(0x0004), .len = cpu_to_le16(4) }
+#define WUSB_AR_LangID			{ .id = cpu_to_le16(0x0008), .len = cpu_to_le16(2) }
+#define WUSB_AR_DeviceFriendlyName	{ .id = cpu_to_le16(0x000b), .len = cpu_to_le16(64) } /* max */
+#define WUSB_AR_HostFriendlyName	{ .id = cpu_to_le16(0x000c), .len = cpu_to_le16(64) } /* max */
+#define WUSB_AR_CHID			{ .id = cpu_to_le16(0x1000), .len = cpu_to_le16(16) }
+#define WUSB_AR_CDID			{ .id = cpu_to_le16(0x1001), .len = cpu_to_le16(16) }
+#define WUSB_AR_ConnectionContext	{ .id = cpu_to_le16(0x1002), .len = cpu_to_le16(48) }
+#define WUSB_AR_BandGroups		{ .id = cpu_to_le16(0x1004), .len = cpu_to_le16(2) }
 
 /* CBAF Control Requests (AMS1.0[T4-1] */
 enum {
diff --git a/include/linux/usb/gpio_vbus.h b/include/linux/usb/gpio_vbus.h
new file mode 100644
index 000000000000..d9f03ccc2d60
--- /dev/null
+++ b/include/linux/usb/gpio_vbus.h
@@ -0,0 +1,30 @@
+/*
+ * A simple GPIO VBUS sensing driver for B peripheral only devices
+ * with internal transceivers.
+ * Optionally D+ pullup can be controlled by a second GPIO.
+ *
+ * Copyright (c) 2008 Philipp Zabel <philipp.zabel@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+/**
+ * struct gpio_vbus_mach_info - configuration for gpio_vbus
+ * @gpio_vbus: VBUS sensing GPIO
+ * @gpio_pullup: optional D+ or D- pullup GPIO (else negative/invalid)
+ * @gpio_vbus_inverted: true if gpio_vbus is active low
+ * @gpio_pullup_inverted: true if gpio_pullup is active low
+ *
+ * The VBUS sensing GPIO should have a pulldown, which will normally be
+ * part of a resistor ladder turning a 4.0V-5.25V level on VBUS into a
+ * value the GPIO detects as active.  Some systems will use comparators.
+ */
+struct gpio_vbus_mach_info {
+	int gpio_vbus;
+	int gpio_pullup;
+	bool gpio_vbus_inverted;
+	bool gpio_pullup_inverted;
+};
diff --git a/include/linux/usb/otg.h b/include/linux/usb/otg.h
index 1db25d152ad8..94df4fe6c6c0 100644
--- a/include/linux/usb/otg.h
+++ b/include/linux/usb/otg.h
@@ -84,6 +84,7 @@ extern int otg_set_transceiver(struct otg_transceiver *);
 
 /* for usb host and peripheral controller drivers */
 extern struct otg_transceiver *otg_get_transceiver(void);
+extern void otg_put_transceiver(struct otg_transceiver *);
 
 static inline int
 otg_start_hnp(struct otg_transceiver *otg)
diff --git a/include/linux/usb_usual.h b/include/linux/usb_usual.h
index d9a3bbe38e6b..998e5cbbf29e 100644
--- a/include/linux/usb_usual.h
+++ b/include/linux/usb_usual.h
@@ -52,8 +52,9 @@
 	US_FLAG(MAX_SECTORS_MIN,0x00002000)			\
 		/* Sets max_sectors to arch min */		\
 	US_FLAG(BULK_IGNORE_TAG,0x00004000)			\
-		/* Ignore tag mismatch in bulk operations */
-
+		/* Ignore tag mismatch in bulk operations */    \
+	US_FLAG(SANE_SENSE,     0x00008000)
+		/* Sane Sense (> 18 bytes) */
 
 #define US_FLAG(name, value)	US_FL_##name = value ,
 enum { US_DO_ALL_FLAGS };
diff --git a/include/net/iucv/iucv.h b/include/net/iucv/iucv.h
index fd70adbb3566..5e310c8d8e2f 100644
--- a/include/net/iucv/iucv.h
+++ b/include/net/iucv/iucv.h
@@ -337,12 +337,35 @@ int iucv_message_purge(struct iucv_path *path, struct iucv_message *msg,
  * established paths. This function will deal with RMDATA messages
  * embedded in struct iucv_message as well.
  *
+ * Locking:	local_bh_enable/local_bh_disable
+ *
  * Returns the result from the CP IUCV call.
  */
 int iucv_message_receive(struct iucv_path *path, struct iucv_message *msg,
 			 u8 flags, void *buffer, size_t size, size_t *residual);
 
 /**
+ * __iucv_message_receive
+ * @path: address of iucv path structure
+ * @msg: address of iucv msg structure
+ * @flags: flags that affect how the message is received (IUCV_IPBUFLST)
+ * @buffer: address of data buffer or address of struct iucv_array
+ * @size: length of data buffer
+ * @residual:
+ *
+ * This function receives messages that are being sent to you over
+ * established paths. This function will deal with RMDATA messages
+ * embedded in struct iucv_message as well.
+ *
+ * Locking:	no locking.
+ *
+ * Returns the result from the CP IUCV call.
+ */
+int __iucv_message_receive(struct iucv_path *path, struct iucv_message *msg,
+			   u8 flags, void *buffer, size_t size,
+			   size_t *residual);
+
+/**
  * iucv_message_reject
  * @path: address of iucv path structure
  * @msg: address of iucv msg structure
@@ -386,12 +409,34 @@ int iucv_message_reply(struct iucv_path *path, struct iucv_message *msg,
  * transmitted is in a buffer and this is a one-way message and the
  * receiver will not reply to the message.
  *
+ * Locking:	local_bh_enable/local_bh_disable
+ *
  * Returns the result from the CP IUCV call.
  */
 int iucv_message_send(struct iucv_path *path, struct iucv_message *msg,
 		      u8 flags, u32 srccls, void *buffer, size_t size);
 
 /**
+ * __iucv_message_send
+ * @path: address of iucv path structure
+ * @msg: address of iucv msg structure
+ * @flags: how the message is sent (IUCV_IPRMDATA, IUCV_IPPRTY, IUCV_IPBUFLST)
+ * @srccls: source class of message
+ * @buffer: address of data buffer or address of struct iucv_array
+ * @size: length of send buffer
+ *
+ * This function transmits data to another application. Data to be
+ * transmitted is in a buffer and this is a one-way message and the
+ * receiver will not reply to the message.
+ *
+ * Locking:	no locking.
+ *
+ * Returns the result from the CP IUCV call.
+ */
+int __iucv_message_send(struct iucv_path *path, struct iucv_message *msg,
+			u8 flags, u32 srccls, void *buffer, size_t size);
+
+/**
  * iucv_message_send2way
  * @path: address of iucv path structure
  * @msg: address of iucv msg structure
diff --git a/include/trace/boot.h b/include/trace/boot.h
new file mode 100644
index 000000000000..6b54537eab02
--- /dev/null
+++ b/include/trace/boot.h
@@ -0,0 +1,56 @@
+#ifndef _LINUX_TRACE_BOOT_H
+#define _LINUX_TRACE_BOOT_H
+
+/*
+ * Structure which defines the trace of an initcall
+ * while it is called.
+ * You don't have to fill the func field since it is
+ * only used internally by the tracer.
+ */
+struct boot_trace_call {
+	pid_t			caller;
+	char			func[KSYM_NAME_LEN];
+};
+
+/*
+ * Structure which defines the trace of an initcall
+ * while it returns.
+ */
+struct boot_trace_ret {
+	char			func[KSYM_NAME_LEN];
+	int				result;
+	unsigned long long	duration;		/* nsecs */
+};
+
+#ifdef CONFIG_BOOT_TRACER
+/* Append the traces on the ring-buffer */
+extern void trace_boot_call(struct boot_trace_call *bt, initcall_t fn);
+extern void trace_boot_ret(struct boot_trace_ret *bt, initcall_t fn);
+
+/* Tells the tracer that smp_pre_initcall is finished.
+ * So we can start the tracing
+ */
+extern void start_boot_trace(void);
+
+/* Resume the tracing of other necessary events
+ * such as sched switches
+ */
+extern void enable_boot_trace(void);
+
+/* Suspend this tracing. Actually, only sched_switches tracing have
+ * to be suspended. Initcalls doesn't need it.)
+ */
+extern void disable_boot_trace(void);
+#else
+static inline
+void trace_boot_call(struct boot_trace_call *bt, initcall_t fn) { }
+
+static inline
+void trace_boot_ret(struct boot_trace_ret *bt, initcall_t fn) { }
+
+static inline void start_boot_trace(void) { }
+static inline void enable_boot_trace(void) { }
+static inline void disable_boot_trace(void) { }
+#endif /* CONFIG_BOOT_TRACER */
+
+#endif /* __LINUX_TRACE_BOOT_H */
diff --git a/include/trace/sched.h b/include/trace/sched.h
index ad47369d01b5..9b2854abf7e2 100644
--- a/include/trace/sched.h
+++ b/include/trace/sched.h
@@ -4,52 +4,52 @@
 #include <linux/sched.h>
 #include <linux/tracepoint.h>
 
-DEFINE_TRACE(sched_kthread_stop,
+DECLARE_TRACE(sched_kthread_stop,
 	TPPROTO(struct task_struct *t),
 		TPARGS(t));
 
-DEFINE_TRACE(sched_kthread_stop_ret,
+DECLARE_TRACE(sched_kthread_stop_ret,
 	TPPROTO(int ret),
 		TPARGS(ret));
 
-DEFINE_TRACE(sched_wait_task,
+DECLARE_TRACE(sched_wait_task,
 	TPPROTO(struct rq *rq, struct task_struct *p),
 		TPARGS(rq, p));
 
-DEFINE_TRACE(sched_wakeup,
+DECLARE_TRACE(sched_wakeup,
 	TPPROTO(struct rq *rq, struct task_struct *p),
 		TPARGS(rq, p));
 
-DEFINE_TRACE(sched_wakeup_new,
+DECLARE_TRACE(sched_wakeup_new,
 	TPPROTO(struct rq *rq, struct task_struct *p),
 		TPARGS(rq, p));
 
-DEFINE_TRACE(sched_switch,
+DECLARE_TRACE(sched_switch,
 	TPPROTO(struct rq *rq, struct task_struct *prev,
 		struct task_struct *next),
 		TPARGS(rq, prev, next));
 
-DEFINE_TRACE(sched_migrate_task,
+DECLARE_TRACE(sched_migrate_task,
 	TPPROTO(struct rq *rq, struct task_struct *p, int dest_cpu),
 		TPARGS(rq, p, dest_cpu));
 
-DEFINE_TRACE(sched_process_free,
+DECLARE_TRACE(sched_process_free,
 	TPPROTO(struct task_struct *p),
 		TPARGS(p));
 
-DEFINE_TRACE(sched_process_exit,
+DECLARE_TRACE(sched_process_exit,
 	TPPROTO(struct task_struct *p),
 		TPARGS(p));
 
-DEFINE_TRACE(sched_process_wait,
+DECLARE_TRACE(sched_process_wait,
 	TPPROTO(struct pid *pid),
 		TPARGS(pid));
 
-DEFINE_TRACE(sched_process_fork,
+DECLARE_TRACE(sched_process_fork,
 	TPPROTO(struct task_struct *parent, struct task_struct *child),
 		TPARGS(parent, child));
 
-DEFINE_TRACE(sched_signal_send,
+DECLARE_TRACE(sched_signal_send,
 	TPPROTO(int sig, struct task_struct *p),
 		TPARGS(sig, p));
 
diff --git a/init/Kconfig b/init/Kconfig
index f763762d544a..504a63467e93 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -423,27 +423,37 @@ config SYSFS_DEPRECATED
 	bool
 
 config SYSFS_DEPRECATED_V2
-	bool "Create deprecated sysfs files"
+	bool "Create deprecated sysfs layout for older userspace tools"
 	depends on SYSFS
 	default y
 	select SYSFS_DEPRECATED
 	help
-	  This option creates deprecated symlinks such as the
-	  "device"-link, the <subsystem>:<name>-link, and the
-	  "bus"-link. It may also add deprecated key in the
-	  uevent environment.
-	  None of these features or values should be used today, as
-	  they export driver core implementation details to userspace
-	  or export properties which can't be kept stable across kernel
-	  releases.
-
-	  If enabled, this option will also move any device structures
-	  that belong to a class, back into the /sys/class hierarchy, in
-	  order to support older versions of udev and some userspace
-	  programs.
-
-	  If you are using a distro with the most recent userspace
-	  packages, it should be safe to say N here.
+	  This option switches the layout of sysfs to the deprecated
+	  version.
+
+	  The current sysfs layout features a unified device tree at
+	  /sys/devices/, which is able to express a hierarchy between
+	  class devices. If the deprecated option is set to Y, the
+	  unified device tree is split into a bus device tree at
+	  /sys/devices/ and several individual class device trees at
+	  /sys/class/. The class and bus devices will be connected by
+	  "<subsystem>:<name>" and the "device" links. The "block"
+	  class devices, will not show up in /sys/class/block/. Some
+	  subsystems will suppress the creation of some devices which
+	  depend on the unified device tree.
+
+	  This option is not a pure compatibility option that can
+	  be safely enabled on newer distributions. It will change the
+	  layout of sysfs to the non-extensible deprecated version,
+	  and disable some features, which can not be exported without
+	  confusing older userspace tools. Since 2007/2008 all major
+	  distributions do not enable this option, and ship no tools which
+	  depend on the deprecated layout or this option.
+
+	  If you are using a new kernel on an older distribution, or use
+	  older userspace tools, you might need to say Y here. Do not say Y,
+	  if the original kernel, that came with your distribution, has
+	  this option set to N.
 
 config PROC_PID_CPUSET
 	bool "Include legacy /proc/<pid>/cpuset file"
@@ -808,6 +818,7 @@ config TRACEPOINTS
 
 config MARKERS
 	bool "Activate markers"
+	depends on TRACEPOINTS
 	help
 	  Place an empty function call at each marker site. Can be
 	  dynamically changed for a probe function.
diff --git a/init/main.c b/init/main.c
index 7e117a231af1..59414b5cf40d 100644
--- a/init/main.c
+++ b/init/main.c
@@ -14,6 +14,7 @@
 #include <linux/proc_fs.h>
 #include <linux/kernel.h>
 #include <linux/syscalls.h>
+#include <linux/stackprotector.h>
 #include <linux/string.h>
 #include <linux/ctype.h>
 #include <linux/delay.h>
@@ -63,6 +64,7 @@
 #include <linux/signal.h>
 #include <linux/idr.h>
 #include <linux/ftrace.h>
+#include <trace/boot.h>
 
 #include <asm/io.h>
 #include <asm/bugs.h>
@@ -553,6 +555,12 @@ asmlinkage void __init start_kernel(void)
 	unwind_init();
 	lockdep_init();
 	debug_objects_early_init();
+
+	/*
+	 * Set up the the initial canary ASAP:
+	 */
+	boot_init_stack_canary();
+
 	cgroup_init_early();
 
 	local_irq_disable();
@@ -703,31 +711,35 @@ core_param(initcall_debug, initcall_debug, bool, 0644);
 int do_one_initcall(initcall_t fn)
 {
 	int count = preempt_count();
-	ktime_t delta;
+	ktime_t calltime, delta, rettime;
 	char msgbuf[64];
-	struct boot_trace it;
+	struct boot_trace_call call;
+	struct boot_trace_ret ret;
 
 	if (initcall_debug) {
-		it.caller = task_pid_nr(current);
-		printk("calling  %pF @ %i\n", fn, it.caller);
-		it.calltime = ktime_get();
+		call.caller = task_pid_nr(current);
+		printk("calling  %pF @ %i\n", fn, call.caller);
+		calltime = ktime_get();
+		trace_boot_call(&call, fn);
+		enable_boot_trace();
 	}
 
-	it.result = fn();
+	ret.result = fn();
 
 	if (initcall_debug) {
-		it.rettime = ktime_get();
-		delta = ktime_sub(it.rettime, it.calltime);
-		it.duration = (unsigned long long) delta.tv64 >> 10;
+		disable_boot_trace();
+		rettime = ktime_get();
+		delta = ktime_sub(rettime, calltime);
+		ret.duration = (unsigned long long) ktime_to_ns(delta) >> 10;
+		trace_boot_ret(&ret, fn);
 		printk("initcall %pF returned %d after %Ld usecs\n", fn,
-			it.result, it.duration);
-		trace_boot(&it, fn);
+			ret.result, ret.duration);
 	}
 
 	msgbuf[0] = 0;
 
-	if (it.result && it.result != -ENODEV && initcall_debug)
-		sprintf(msgbuf, "error code %d ", it.result);
+	if (ret.result && ret.result != -ENODEV && initcall_debug)
+		sprintf(msgbuf, "error code %d ", ret.result);
 
 	if (preempt_count() != count) {
 		strlcat(msgbuf, "preemption imbalance ", sizeof(msgbuf));
@@ -741,7 +753,7 @@ int do_one_initcall(initcall_t fn)
 		printk("initcall %pF returned with %s\n", fn, msgbuf);
 	}
 
-	return it.result;
+	return ret.result;
 }
 
 
@@ -789,12 +801,21 @@ static void run_init_process(char *init_filename)
 	kernel_execve(init_filename, argv_init, envp_init);
 }
 
+/*
+ * __init/__init_data sections are turned into normal
+ * dynamically allocated memory later in boot.  When
+ * this is 0, the memory is for the __init purposes,
+ * when it it some other value, the memory is dynamic.
+ */
+int initmem_now_dynamic;
+
 /* This is a non __init function. Force it to be noinline otherwise gcc
  * makes it inline to init() and it becomes part of init.text section
  */
 static int noinline init_post(void)
 {
 	free_initmem();
+	initmem_now_dynamic = 1;
 	unlock_kernel();
 	mark_rodata_ro();
 	system_state = SYSTEM_RUNNING;
@@ -882,7 +903,7 @@ static int __init kernel_init(void * unused)
 	 * we're essentially up and running. Get rid of the
 	 * initmem segments and start the user-mode stuff..
 	 */
-	stop_boot_trace();
+
 	init_post();
 	return 0;
 }
diff --git a/kernel/Makefile b/kernel/Makefile
index 19fad003b19d..010ccb311166 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -19,7 +19,10 @@ CFLAGS_REMOVE_mutex-debug.o = -pg
 CFLAGS_REMOVE_rtmutex-debug.o = -pg
 CFLAGS_REMOVE_cgroup-debug.o = -pg
 CFLAGS_REMOVE_sched_clock.o = -pg
-CFLAGS_REMOVE_sched.o = -pg
+endif
+ifdef CONFIG_FUNCTION_RET_TRACER
+CFLAGS_REMOVE_extable.o = -pg # For __kernel_text_address()
+CFLAGS_REMOVE_module.o = -pg # For __module_text_address()
 endif
 
 obj-$(CONFIG_FREEZER) += freezer.o
@@ -90,7 +93,7 @@ obj-$(CONFIG_FUNCTION_TRACER) += trace/
 obj-$(CONFIG_TRACING) += trace/
 obj-$(CONFIG_SMP) += sched_cpupri.o
 
-ifneq ($(CONFIG_SCHED_NO_NO_OMIT_FRAME_POINTER),y)
+ifneq ($(CONFIG_SCHED_OMIT_FRAME_POINTER),y)
 # According to Alan Modra <alan@linuxcare.com.au>, the -fno-omit-frame-pointer is
 # needed for x86 only.  Why this used to be enabled for all architectures is beyond
 # me.  I suspect most platforms don't need this, but until we know that for sure
diff --git a/kernel/exit.c b/kernel/exit.c
index 2d8be7ebb0f7..cb240370193e 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -53,6 +53,10 @@
 #include <asm/pgtable.h>
 #include <asm/mmu_context.h>
 
+DEFINE_TRACE(sched_process_free);
+DEFINE_TRACE(sched_process_exit);
+DEFINE_TRACE(sched_process_wait);
+
 static void exit_mm(struct task_struct * tsk);
 
 static inline int task_detached(struct task_struct *p)
@@ -972,12 +976,9 @@ static void check_stack_usage(void)
 {
 	static DEFINE_SPINLOCK(low_water_lock);
 	static int lowest_to_date = THREAD_SIZE;
-	unsigned long *n = end_of_stack(current);
 	unsigned long free;
 
-	while (*n == 0)
-		n++;
-	free = (unsigned long)n - (unsigned long)end_of_stack(current);
+	free = stack_not_used(current);
 
 	if (free >= lowest_to_date)
 		return;
@@ -1123,7 +1124,6 @@ NORET_TYPE void do_exit(long code)
 	preempt_disable();
 	/* causes final put_task_struct in finish_task_switch(). */
 	tsk->state = TASK_DEAD;
-
 	schedule();
 	BUG();
 	/* Avoid "noreturn function does return".  */
@@ -1321,10 +1321,10 @@ static int wait_task_zombie(struct task_struct *p, int options,
 		 * group, which consolidates times for all threads in the
 		 * group including the group leader.
 		 */
+		thread_group_cputime(p, &cputime);
 		spin_lock_irq(&p->parent->sighand->siglock);
 		psig = p->parent->signal;
 		sig = p->signal;
-		thread_group_cputime(p, &cputime);
 		psig->cutime =
 			cputime_add(psig->cutime,
 			cputime_add(cputime.utime,
diff --git a/kernel/extable.c b/kernel/extable.c
index a26cb2e17023..adf0cc9c02d6 100644
--- a/kernel/extable.c
+++ b/kernel/extable.c
@@ -66,3 +66,19 @@ int kernel_text_address(unsigned long addr)
 		return 1;
 	return module_text_address(addr) != NULL;
 }
+
+/*
+ * On some architectures (PPC64, IA64) function pointers
+ * are actually only tokens to some data that then holds the
+ * real function address. As a result, to find if a function
+ * pointer is part of the kernel text, we need to do some
+ * special dereferencing first.
+ */
+int func_ptr_is_kernel_text(void *ptr)
+{
+	unsigned long addr;
+	addr = (unsigned long) dereference_function_descriptor(ptr);
+	if (core_kernel_text(addr))
+		return 1;
+	return module_text_address(addr) != NULL;
+}
diff --git a/kernel/fork.c b/kernel/fork.c
index 2a372a0e206f..b7786e6afd78 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -47,6 +47,7 @@
 #include <linux/mount.h>
 #include <linux/audit.h>
 #include <linux/memcontrol.h>
+#include <linux/ftrace.h>
 #include <linux/profile.h>
 #include <linux/rmap.h>
 #include <linux/acct.h>
@@ -60,6 +61,7 @@
 #include <linux/proc_fs.h>
 #include <linux/blkdev.h>
 #include <trace/sched.h>
+#include <linux/magic.h>
 
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
@@ -80,6 +82,8 @@ DEFINE_PER_CPU(unsigned long, process_counts) = 0;
 
 __cacheline_aligned DEFINE_RWLOCK(tasklist_lock);  /* outer */
 
+DEFINE_TRACE(sched_process_fork);
+
 int nr_processes(void)
 {
 	int cpu;
@@ -137,6 +141,7 @@ void free_task(struct task_struct *tsk)
 	prop_local_destroy_single(&tsk->dirties);
 	free_thread_info(tsk->stack);
 	rt_mutex_debug_task_free(tsk);
+	ftrace_retfunc_exit_task(tsk);
 	free_task_struct(tsk);
 }
 EXPORT_SYMBOL(free_task);
@@ -209,6 +214,8 @@ static struct task_struct *dup_task_struct(struct task_struct *orig)
 {
 	struct task_struct *tsk;
 	struct thread_info *ti;
+	unsigned long *stackend;
+
 	int err;
 
 	prepare_to_copy(orig);
@@ -234,6 +241,8 @@ static struct task_struct *dup_task_struct(struct task_struct *orig)
 		goto out;
 
 	setup_thread_stack(tsk, orig);
+	stackend = end_of_stack(tsk);
+	*stackend = STACK_END_MAGIC;	/* for overflow detection */
 
 #ifdef CONFIG_CC_STACKPROTECTOR
 	tsk->stack_canary = get_random_int();
@@ -1267,6 +1276,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	total_forks++;
 	spin_unlock(&current->sighand->siglock);
 	write_unlock_irq(&tasklist_lock);
+	ftrace_retfunc_init_task(p);
 	proc_fork_connector(p);
 	cgroup_post_fork(p);
 	return p;
diff --git a/kernel/futex.c b/kernel/futex.c
index 8af10027514b..ba0d3b83c091 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -123,24 +123,6 @@ struct futex_hash_bucket {
 static struct futex_hash_bucket futex_queues[1<<FUTEX_HASHBITS];
 
 /*
- * Take mm->mmap_sem, when futex is shared
- */
-static inline void futex_lock_mm(struct rw_semaphore *fshared)
-{
-	if (fshared)
-		down_read(fshared);
-}
-
-/*
- * Release mm->mmap_sem, when the futex is shared
- */
-static inline void futex_unlock_mm(struct rw_semaphore *fshared)
-{
-	if (fshared)
-		up_read(fshared);
-}
-
-/*
  * We hash on the keys returned from get_futex_key (see below).
  */
 static struct futex_hash_bucket *hash_futex(union futex_key *key)
@@ -161,6 +143,45 @@ static inline int match_futex(union futex_key *key1, union futex_key *key2)
 		&& key1->both.offset == key2->both.offset);
 }
 
+/*
+ * Take a reference to the resource addressed by a key.
+ * Can be called while holding spinlocks.
+ *
+ */
+static void get_futex_key_refs(union futex_key *key)
+{
+	if (!key->both.ptr)
+		return;
+
+	switch (key->both.offset & (FUT_OFF_INODE|FUT_OFF_MMSHARED)) {
+	case FUT_OFF_INODE:
+		atomic_inc(&key->shared.inode->i_count);
+		break;
+	case FUT_OFF_MMSHARED:
+		atomic_inc(&key->private.mm->mm_count);
+		break;
+	}
+}
+
+/*
+ * Drop a reference to the resource addressed by a key.
+ * The hash bucket spinlock must not be held.
+ */
+static void drop_futex_key_refs(union futex_key *key)
+{
+	if (!key->both.ptr)
+		return;
+
+	switch (key->both.offset & (FUT_OFF_INODE|FUT_OFF_MMSHARED)) {
+	case FUT_OFF_INODE:
+		iput(key->shared.inode);
+		break;
+	case FUT_OFF_MMSHARED:
+		mmdrop(key->private.mm);
+		break;
+	}
+}
+
 /**
  * get_futex_key - Get parameters which are the keys for a futex.
  * @uaddr: virtual address of the futex
@@ -179,12 +200,10 @@ static inline int match_futex(union futex_key *key1, union futex_key *key2)
  * For other futexes, it points to &current->mm->mmap_sem and
  * caller must have taken the reader lock. but NOT any spinlocks.
  */
-static int get_futex_key(u32 __user *uaddr, struct rw_semaphore *fshared,
-			 union futex_key *key)
+static int get_futex_key(u32 __user *uaddr, int fshared, union futex_key *key)
 {
 	unsigned long address = (unsigned long)uaddr;
 	struct mm_struct *mm = current->mm;
-	struct vm_area_struct *vma;
 	struct page *page;
 	int err;
 
@@ -208,100 +227,50 @@ static int get_futex_key(u32 __user *uaddr, struct rw_semaphore *fshared,
 			return -EFAULT;
 		key->private.mm = mm;
 		key->private.address = address;
+		get_futex_key_refs(key);
 		return 0;
 	}
-	/*
-	 * The futex is hashed differently depending on whether
-	 * it's in a shared or private mapping.  So check vma first.
-	 */
-	vma = find_extend_vma(mm, address);
-	if (unlikely(!vma))
-		return -EFAULT;
 
-	/*
-	 * Permissions.
-	 */
-	if (unlikely((vma->vm_flags & (VM_IO|VM_READ)) != VM_READ))
-		return (vma->vm_flags & VM_IO) ? -EPERM : -EACCES;
+again:
+	err = get_user_pages_fast(address, 1, 0, &page);
+	if (err < 0)
+		return err;
+
+	lock_page(page);
+	if (!page->mapping) {
+		unlock_page(page);
+		put_page(page);
+		goto again;
+	}
 
 	/*
 	 * Private mappings are handled in a simple way.
 	 *
 	 * NOTE: When userspace waits on a MAP_SHARED mapping, even if
 	 * it's a read-only handle, it's expected that futexes attach to
-	 * the object not the particular process.  Therefore we use
-	 * VM_MAYSHARE here, not VM_SHARED which is restricted to shared
-	 * mappings of _writable_ handles.
+	 * the object not the particular process.
 	 */
-	if (likely(!(vma->vm_flags & VM_MAYSHARE))) {
-		key->both.offset |= FUT_OFF_MMSHARED; /* reference taken on mm */
+	if (PageAnon(page)) {
+		key->both.offset |= FUT_OFF_MMSHARED; /* ref taken on mm */
 		key->private.mm = mm;
 		key->private.address = address;
-		return 0;
+	} else {
+		key->both.offset |= FUT_OFF_INODE; /* inode-based key */
+		key->shared.inode = page->mapping->host;
+		key->shared.pgoff = page->index;
 	}
 
-	/*
-	 * Linear file mappings are also simple.
-	 */
-	key->shared.inode = vma->vm_file->f_path.dentry->d_inode;
-	key->both.offset |= FUT_OFF_INODE; /* inode-based key. */
-	if (likely(!(vma->vm_flags & VM_NONLINEAR))) {
-		key->shared.pgoff = (((address - vma->vm_start) >> PAGE_SHIFT)
-				     + vma->vm_pgoff);
-		return 0;
-	}
+	get_futex_key_refs(key);
 
-	/*
-	 * We could walk the page table to read the non-linear
-	 * pte, and get the page index without fetching the page
-	 * from swap.  But that's a lot of code to duplicate here
-	 * for a rare case, so we simply fetch the page.
-	 */
-	err = get_user_pages(current, mm, address, 1, 0, 0, &page, NULL);
-	if (err >= 0) {
-		key->shared.pgoff =
-			page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT);
-		put_page(page);
-		return 0;
-	}
-	return err;
-}
-
-/*
- * Take a reference to the resource addressed by a key.
- * Can be called while holding spinlocks.
- *
- */
-static void get_futex_key_refs(union futex_key *key)
-{
-	if (key->both.ptr == NULL)
-		return;
-	switch (key->both.offset & (FUT_OFF_INODE|FUT_OFF_MMSHARED)) {
-		case FUT_OFF_INODE:
-			atomic_inc(&key->shared.inode->i_count);
-			break;
-		case FUT_OFF_MMSHARED:
-			atomic_inc(&key->private.mm->mm_count);
-			break;
-	}
+	unlock_page(page);
+	put_page(page);
+	return 0;
 }
 
-/*
- * Drop a reference to the resource addressed by a key.
- * The hash bucket spinlock must not be held.
- */
-static void drop_futex_key_refs(union futex_key *key)
+static inline
+void put_futex_key(int fshared, union futex_key *key)
 {
-	if (!key->both.ptr)
-		return;
-	switch (key->both.offset & (FUT_OFF_INODE|FUT_OFF_MMSHARED)) {
-		case FUT_OFF_INODE:
-			iput(key->shared.inode);
-			break;
-		case FUT_OFF_MMSHARED:
-			mmdrop(key->private.mm);
-			break;
-	}
+	drop_futex_key_refs(key);
 }
 
 static u32 cmpxchg_futex_value_locked(u32 __user *uaddr, u32 uval, u32 newval)
@@ -328,10 +297,8 @@ static int get_futex_value_locked(u32 *dest, u32 __user *from)
 
 /*
  * Fault handling.
- * if fshared is non NULL, current->mm->mmap_sem is already held
  */
-static int futex_handle_fault(unsigned long address,
-			      struct rw_semaphore *fshared, int attempt)
+static int futex_handle_fault(unsigned long address, int attempt)
 {
 	struct vm_area_struct * vma;
 	struct mm_struct *mm = current->mm;
@@ -340,8 +307,7 @@ static int futex_handle_fault(unsigned long address,
 	if (attempt > 2)
 		return ret;
 
-	if (!fshared)
-		down_read(&mm->mmap_sem);
+	down_read(&mm->mmap_sem);
 	vma = find_vma(mm, address);
 	if (vma && address >= vma->vm_start &&
 	    (vma->vm_flags & VM_WRITE)) {
@@ -361,8 +327,7 @@ static int futex_handle_fault(unsigned long address,
 				current->min_flt++;
 		}
 	}
-	if (!fshared)
-		up_read(&mm->mmap_sem);
+	up_read(&mm->mmap_sem);
 	return ret;
 }
 
@@ -385,6 +350,7 @@ static int refill_pi_state_cache(void)
 	/* pi_mutex gets initialized later */
 	pi_state->owner = NULL;
 	atomic_set(&pi_state->refcount, 1);
+	pi_state->key = FUTEX_KEY_INIT;
 
 	current->pi_state_cache = pi_state;
 
@@ -462,7 +428,7 @@ void exit_pi_state_list(struct task_struct *curr)
 	struct list_head *next, *head = &curr->pi_state_list;
 	struct futex_pi_state *pi_state;
 	struct futex_hash_bucket *hb;
-	union futex_key key;
+	union futex_key key = FUTEX_KEY_INIT;
 
 	if (!futex_cmpxchg_enabled)
 		return;
@@ -719,20 +685,17 @@ double_lock_hb(struct futex_hash_bucket *hb1, struct futex_hash_bucket *hb2)
  * Wake up all waiters hashed on the physical page that is mapped
  * to this virtual address:
  */
-static int futex_wake(u32 __user *uaddr, struct rw_semaphore *fshared,
-		      int nr_wake, u32 bitset)
+static int futex_wake(u32 __user *uaddr, int fshared, int nr_wake, u32 bitset)
 {
 	struct futex_hash_bucket *hb;
 	struct futex_q *this, *next;
 	struct plist_head *head;
-	union futex_key key;
+	union futex_key key = FUTEX_KEY_INIT;
 	int ret;
 
 	if (!bitset)
 		return -EINVAL;
 
-	futex_lock_mm(fshared);
-
 	ret = get_futex_key(uaddr, fshared, &key);
 	if (unlikely(ret != 0))
 		goto out;
@@ -760,7 +723,7 @@ static int futex_wake(u32 __user *uaddr, struct rw_semaphore *fshared,
 
 	spin_unlock(&hb->lock);
 out:
-	futex_unlock_mm(fshared);
+	put_futex_key(fshared, &key);
 	return ret;
 }
 
@@ -769,19 +732,16 @@ out:
  * to this virtual address:
  */
 static int
-futex_wake_op(u32 __user *uaddr1, struct rw_semaphore *fshared,
-	      u32 __user *uaddr2,
+futex_wake_op(u32 __user *uaddr1, int fshared, u32 __user *uaddr2,
 	      int nr_wake, int nr_wake2, int op)
 {
-	union futex_key key1, key2;
+	union futex_key key1 = FUTEX_KEY_INIT, key2 = FUTEX_KEY_INIT;
 	struct futex_hash_bucket *hb1, *hb2;
 	struct plist_head *head;
 	struct futex_q *this, *next;
 	int ret, op_ret, attempt = 0;
 
 retryfull:
-	futex_lock_mm(fshared);
-
 	ret = get_futex_key(uaddr1, fshared, &key1);
 	if (unlikely(ret != 0))
 		goto out;
@@ -826,18 +786,12 @@ retry:
 		 */
 		if (attempt++) {
 			ret = futex_handle_fault((unsigned long)uaddr2,
-						 fshared, attempt);
+						 attempt);
 			if (ret)
 				goto out;
 			goto retry;
 		}
 
-		/*
-		 * If we would have faulted, release mmap_sem,
-		 * fault it in and start all over again.
-		 */
-		futex_unlock_mm(fshared);
-
 		ret = get_user(dummy, uaddr2);
 		if (ret)
 			return ret;
@@ -873,7 +827,8 @@ retry:
 	if (hb1 != hb2)
 		spin_unlock(&hb2->lock);
 out:
-	futex_unlock_mm(fshared);
+	put_futex_key(fshared, &key2);
+	put_futex_key(fshared, &key1);
 
 	return ret;
 }
@@ -882,19 +837,16 @@ out:
  * Requeue all waiters hashed on one physical page to another
  * physical page.
  */
-static int futex_requeue(u32 __user *uaddr1, struct rw_semaphore *fshared,
-			 u32 __user *uaddr2,
+static int futex_requeue(u32 __user *uaddr1, int fshared, u32 __user *uaddr2,
 			 int nr_wake, int nr_requeue, u32 *cmpval)
 {
-	union futex_key key1, key2;
+	union futex_key key1 = FUTEX_KEY_INIT, key2 = FUTEX_KEY_INIT;
 	struct futex_hash_bucket *hb1, *hb2;
 	struct plist_head *head1;
 	struct futex_q *this, *next;
 	int ret, drop_count = 0;
 
  retry:
-	futex_lock_mm(fshared);
-
 	ret = get_futex_key(uaddr1, fshared, &key1);
 	if (unlikely(ret != 0))
 		goto out;
@@ -917,12 +869,6 @@ static int futex_requeue(u32 __user *uaddr1, struct rw_semaphore *fshared,
 			if (hb1 != hb2)
 				spin_unlock(&hb2->lock);
 
-			/*
-			 * If we would have faulted, release mmap_sem, fault
-			 * it in and start all over again.
-			 */
-			futex_unlock_mm(fshared);
-
 			ret = get_user(curval, uaddr1);
 
 			if (!ret)
@@ -974,7 +920,8 @@ out_unlock:
 		drop_futex_key_refs(&key1);
 
 out:
-	futex_unlock_mm(fshared);
+	put_futex_key(fshared, &key2);
+	put_futex_key(fshared, &key1);
 	return ret;
 }
 
@@ -1096,8 +1043,7 @@ static void unqueue_me_pi(struct futex_q *q)
  * private futexes.
  */
 static int fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q,
-				struct task_struct *newowner,
-				struct rw_semaphore *fshared)
+				struct task_struct *newowner, int fshared)
 {
 	u32 newtid = task_pid_vnr(newowner) | FUTEX_WAITERS;
 	struct futex_pi_state *pi_state = q->pi_state;
@@ -1176,7 +1122,7 @@ retry:
 handle_fault:
 	spin_unlock(q->lock_ptr);
 
-	ret = futex_handle_fault((unsigned long)uaddr, fshared, attempt++);
+	ret = futex_handle_fault((unsigned long)uaddr, attempt++);
 
 	spin_lock(q->lock_ptr);
 
@@ -1196,12 +1142,13 @@ handle_fault:
  * In case we must use restart_block to restart a futex_wait,
  * we encode in the 'flags' shared capability
  */
-#define FLAGS_SHARED  1
+#define FLAGS_SHARED		0x01
+#define FLAGS_CLOCKRT		0x02
 
 static long futex_wait_restart(struct restart_block *restart);
 
-static int futex_wait(u32 __user *uaddr, struct rw_semaphore *fshared,
-		      u32 val, ktime_t *abs_time, u32 bitset)
+static int futex_wait(u32 __user *uaddr, int fshared,
+		      u32 val, ktime_t *abs_time, u32 bitset, int clockrt)
 {
 	struct task_struct *curr = current;
 	DECLARE_WAITQUEUE(wait, curr);
@@ -1218,8 +1165,7 @@ static int futex_wait(u32 __user *uaddr, struct rw_semaphore *fshared,
 	q.pi_state = NULL;
 	q.bitset = bitset;
  retry:
-	futex_lock_mm(fshared);
-
+	q.key = FUTEX_KEY_INIT;
 	ret = get_futex_key(uaddr, fshared, &q.key);
 	if (unlikely(ret != 0))
 		goto out_release_sem;
@@ -1251,12 +1197,6 @@ static int futex_wait(u32 __user *uaddr, struct rw_semaphore *fshared,
 	if (unlikely(ret)) {
 		queue_unlock(&q, hb);
 
-		/*
-		 * If we would have faulted, release mmap_sem, fault it in and
-		 * start all over again.
-		 */
-		futex_unlock_mm(fshared);
-
 		ret = get_user(uval, uaddr);
 
 		if (!ret)
@@ -1271,12 +1211,6 @@ static int futex_wait(u32 __user *uaddr, struct rw_semaphore *fshared,
 	queue_me(&q, hb);
 
 	/*
-	 * Now the futex is queued and we have checked the data, we
-	 * don't want to hold mmap_sem while we sleep.
-	 */
-	futex_unlock_mm(fshared);
-
-	/*
 	 * There might have been scheduling since the queue_me(), as we
 	 * cannot hold a spinlock across the get_user() in case it
 	 * faults, and we cannot just set TASK_INTERRUPTIBLE state when
@@ -1300,8 +1234,10 @@ static int futex_wait(u32 __user *uaddr, struct rw_semaphore *fshared,
 			slack = current->timer_slack_ns;
 			if (rt_task(current))
 				slack = 0;
-			hrtimer_init_on_stack(&t.timer, CLOCK_MONOTONIC,
-						HRTIMER_MODE_ABS);
+			hrtimer_init_on_stack(&t.timer,
+					      clockrt ? CLOCK_REALTIME :
+					      CLOCK_MONOTONIC,
+					      HRTIMER_MODE_ABS);
 			hrtimer_init_sleeper(&t, current);
 			hrtimer_set_expires_range_ns(&t.timer, *abs_time, slack);
 
@@ -1356,6 +1292,8 @@ static int futex_wait(u32 __user *uaddr, struct rw_semaphore *fshared,
 
 		if (fshared)
 			restart->futex.flags |= FLAGS_SHARED;
+		if (clockrt)
+			restart->futex.flags |= FLAGS_CLOCKRT;
 		return -ERESTART_RESTARTBLOCK;
 	}
 
@@ -1363,7 +1301,7 @@ static int futex_wait(u32 __user *uaddr, struct rw_semaphore *fshared,
 	queue_unlock(&q, hb);
 
  out_release_sem:
-	futex_unlock_mm(fshared);
+	put_futex_key(fshared, &q.key);
 	return ret;
 }
 
@@ -1371,15 +1309,16 @@ static int futex_wait(u32 __user *uaddr, struct rw_semaphore *fshared,
 static long futex_wait_restart(struct restart_block *restart)
 {
 	u32 __user *uaddr = (u32 __user *)restart->futex.uaddr;
-	struct rw_semaphore *fshared = NULL;
+	int fshared = 0;
 	ktime_t t;
 
 	t.tv64 = restart->futex.time;
 	restart->fn = do_no_restart_syscall;
 	if (restart->futex.flags & FLAGS_SHARED)
-		fshared = &current->mm->mmap_sem;
+		fshared = 1;
 	return (long)futex_wait(uaddr, fshared, restart->futex.val, &t,
-				restart->futex.bitset);
+				restart->futex.bitset,
+				restart->futex.flags & FLAGS_CLOCKRT);
 }
 
 
@@ -1389,7 +1328,7 @@ static long futex_wait_restart(struct restart_block *restart)
  * if there are waiters then it will block, it does PI, etc. (Due to
  * races the kernel might see a 0 value of the futex too.)
  */
-static int futex_lock_pi(u32 __user *uaddr, struct rw_semaphore *fshared,
+static int futex_lock_pi(u32 __user *uaddr, int fshared,
 			 int detect, ktime_t *time, int trylock)
 {
 	struct hrtimer_sleeper timeout, *to = NULL;
@@ -1412,8 +1351,7 @@ static int futex_lock_pi(u32 __user *uaddr, struct rw_semaphore *fshared,
 
 	q.pi_state = NULL;
  retry:
-	futex_lock_mm(fshared);
-
+	q.key = FUTEX_KEY_INIT;
 	ret = get_futex_key(uaddr, fshared, &q.key);
 	if (unlikely(ret != 0))
 		goto out_release_sem;
@@ -1502,7 +1440,6 @@ static int futex_lock_pi(u32 __user *uaddr, struct rw_semaphore *fshared,
 			 * exit to complete.
 			 */
 			queue_unlock(&q, hb);
-			futex_unlock_mm(fshared);
 			cond_resched();
 			goto retry;
 
@@ -1534,12 +1471,6 @@ static int futex_lock_pi(u32 __user *uaddr, struct rw_semaphore *fshared,
 	 */
 	queue_me(&q, hb);
 
-	/*
-	 * Now the futex is queued and we have checked the data, we
-	 * don't want to hold mmap_sem while we sleep.
-	 */
-	futex_unlock_mm(fshared);
-
 	WARN_ON(!q.pi_state);
 	/*
 	 * Block on the PI mutex:
@@ -1552,7 +1483,6 @@ static int futex_lock_pi(u32 __user *uaddr, struct rw_semaphore *fshared,
 		ret = ret ? 0 : -EWOULDBLOCK;
 	}
 
-	futex_lock_mm(fshared);
 	spin_lock(q.lock_ptr);
 
 	if (!ret) {
@@ -1618,7 +1548,6 @@ static int futex_lock_pi(u32 __user *uaddr, struct rw_semaphore *fshared,
 
 	/* Unqueue and drop the lock */
 	unqueue_me_pi(&q);
-	futex_unlock_mm(fshared);
 
 	if (to)
 		destroy_hrtimer_on_stack(&to->timer);
@@ -1628,7 +1557,7 @@ static int futex_lock_pi(u32 __user *uaddr, struct rw_semaphore *fshared,
 	queue_unlock(&q, hb);
 
  out_release_sem:
-	futex_unlock_mm(fshared);
+	put_futex_key(fshared, &q.key);
 	if (to)
 		destroy_hrtimer_on_stack(&to->timer);
 	return ret;
@@ -1645,15 +1574,12 @@ static int futex_lock_pi(u32 __user *uaddr, struct rw_semaphore *fshared,
 	queue_unlock(&q, hb);
 
 	if (attempt++) {
-		ret = futex_handle_fault((unsigned long)uaddr, fshared,
-					 attempt);
+		ret = futex_handle_fault((unsigned long)uaddr, attempt);
 		if (ret)
 			goto out_release_sem;
 		goto retry_unlocked;
 	}
 
-	futex_unlock_mm(fshared);
-
 	ret = get_user(uval, uaddr);
 	if (!ret && (uval != -EFAULT))
 		goto retry;
@@ -1668,13 +1594,13 @@ static int futex_lock_pi(u32 __user *uaddr, struct rw_semaphore *fshared,
  * This is the in-kernel slowpath: we look up the PI state (if any),
  * and do the rt-mutex unlock.
  */
-static int futex_unlock_pi(u32 __user *uaddr, struct rw_semaphore *fshared)
+static int futex_unlock_pi(u32 __user *uaddr, int fshared)
 {
 	struct futex_hash_bucket *hb;
 	struct futex_q *this, *next;
 	u32 uval;
 	struct plist_head *head;
-	union futex_key key;
+	union futex_key key = FUTEX_KEY_INIT;
 	int ret, attempt = 0;
 
 retry:
@@ -1685,10 +1611,6 @@ retry:
 	 */
 	if ((uval & FUTEX_TID_MASK) != task_pid_vnr(current))
 		return -EPERM;
-	/*
-	 * First take all the futex related locks:
-	 */
-	futex_lock_mm(fshared);
 
 	ret = get_futex_key(uaddr, fshared, &key);
 	if (unlikely(ret != 0))
@@ -1747,7 +1669,7 @@ retry_unlocked:
 out_unlock:
 	spin_unlock(&hb->lock);
 out:
-	futex_unlock_mm(fshared);
+	put_futex_key(fshared, &key);
 
 	return ret;
 
@@ -1763,16 +1685,13 @@ pi_faulted:
 	spin_unlock(&hb->lock);
 
 	if (attempt++) {
-		ret = futex_handle_fault((unsigned long)uaddr, fshared,
-					 attempt);
+		ret = futex_handle_fault((unsigned long)uaddr, attempt);
 		if (ret)
 			goto out;
 		uval = 0;
 		goto retry_unlocked;
 	}
 
-	futex_unlock_mm(fshared);
-
 	ret = get_user(uval, uaddr);
 	if (!ret && (uval != -EFAULT))
 		goto retry;
@@ -1898,8 +1817,7 @@ retry:
 		 * PI futexes happens in exit_pi_state():
 		 */
 		if (!pi && (uval & FUTEX_WAITERS))
-			futex_wake(uaddr, &curr->mm->mmap_sem, 1,
-				   FUTEX_BITSET_MATCH_ANY);
+			futex_wake(uaddr, 1, 1, FUTEX_BITSET_MATCH_ANY);
 	}
 	return 0;
 }
@@ -1993,18 +1911,22 @@ void exit_robust_list(struct task_struct *curr)
 long do_futex(u32 __user *uaddr, int op, u32 val, ktime_t *timeout,
 		u32 __user *uaddr2, u32 val2, u32 val3)
 {
-	int ret = -ENOSYS;
+	int clockrt, ret = -ENOSYS;
 	int cmd = op & FUTEX_CMD_MASK;
-	struct rw_semaphore *fshared = NULL;
+	int fshared = 0;
 
 	if (!(op & FUTEX_PRIVATE_FLAG))
-		fshared = &current->mm->mmap_sem;
+		fshared = 1;
+
+	clockrt = op & FUTEX_CLOCK_REALTIME;
+	if (clockrt && cmd != FUTEX_WAIT_BITSET)
+		return -ENOSYS;
 
 	switch (cmd) {
 	case FUTEX_WAIT:
 		val3 = FUTEX_BITSET_MATCH_ANY;
 	case FUTEX_WAIT_BITSET:
-		ret = futex_wait(uaddr, fshared, val, timeout, val3);
+		ret = futex_wait(uaddr, fshared, val, timeout, val3, clockrt);
 		break;
 	case FUTEX_WAKE:
 		val3 = FUTEX_BITSET_MATCH_ANY;
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 801addda3c43..e9d1c8205a3b 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -673,6 +673,18 @@ int request_irq(unsigned int irq, irq_handler_t handler,
 	struct irq_desc *desc;
 	int retval;
 
+	/*
+	 * handle_IRQ_event() always ignores IRQF_DISABLED except for
+	 * the _first_ irqaction (sigh).  That can cause oopsing, but
+	 * the behavior is classified as "will not fix" so we need to
+	 * start nudging drivers away from using that idiom.
+	 */
+	if ((irqflags & (IRQF_SHARED|IRQF_DISABLED))
+			== (IRQF_SHARED|IRQF_DISABLED))
+		pr_warning("IRQ %d/%s: IRQF_DISABLED is not "
+				"guaranteed on shared IRQs\n",
+				irq, devname);
+
 #ifdef CONFIG_LOCKDEP
 	/*
 	 * Lockdep wants atomic interrupt handlers:
diff --git a/kernel/ksysfs.c b/kernel/ksysfs.c
index 08dd8ed86c77..528dd78e7e7e 100644
--- a/kernel/ksysfs.c
+++ b/kernel/ksysfs.c
@@ -24,7 +24,7 @@ static struct kobj_attribute _name##_attr = __ATTR_RO(_name)
 static struct kobj_attribute _name##_attr = \
 	__ATTR(_name, 0644, _name##_show, _name##_store)
 
-#if defined(CONFIG_HOTPLUG) && defined(CONFIG_NET)
+#if defined(CONFIG_HOTPLUG)
 /* current uevent sequence number */
 static ssize_t uevent_seqnum_show(struct kobject *kobj,
 				  struct kobj_attribute *attr, char *buf)
@@ -137,7 +137,7 @@ struct kobject *kernel_kobj;
 EXPORT_SYMBOL_GPL(kernel_kobj);
 
 static struct attribute * kernel_attrs[] = {
-#if defined(CONFIG_HOTPLUG) && defined(CONFIG_NET)
+#if defined(CONFIG_HOTPLUG)
 	&uevent_seqnum_attr.attr,
 	&uevent_helper_attr.attr,
 #endif
diff --git a/kernel/kthread.c b/kernel/kthread.c
index 8e7a7ce3ed0a..4fbc456f393d 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -21,6 +21,9 @@ static DEFINE_SPINLOCK(kthread_create_lock);
 static LIST_HEAD(kthread_create_list);
 struct task_struct *kthreadd_task;
 
+DEFINE_TRACE(sched_kthread_stop);
+DEFINE_TRACE(sched_kthread_stop_ret);
+
 struct kthread_create_info
 {
 	/* Information passed to kthread() from kthreadd. */
diff --git a/kernel/lockdep.c b/kernel/lockdep.c
index 46a404173db2..670aba87888d 100644
--- a/kernel/lockdep.c
+++ b/kernel/lockdep.c
@@ -136,16 +136,16 @@ static inline struct lock_class *hlock_class(struct held_lock *hlock)
 #ifdef CONFIG_LOCK_STAT
 static DEFINE_PER_CPU(struct lock_class_stats[MAX_LOCKDEP_KEYS], lock_stats);
 
-static int lock_contention_point(struct lock_class *class, unsigned long ip)
+static int lock_point(unsigned long points[], unsigned long ip)
 {
 	int i;
 
-	for (i = 0; i < ARRAY_SIZE(class->contention_point); i++) {
-		if (class->contention_point[i] == 0) {
-			class->contention_point[i] = ip;
+	for (i = 0; i < LOCKSTAT_POINTS; i++) {
+		if (points[i] == 0) {
+			points[i] = ip;
 			break;
 		}
-		if (class->contention_point[i] == ip)
+		if (points[i] == ip)
 			break;
 	}
 
@@ -185,6 +185,9 @@ struct lock_class_stats lock_stats(struct lock_class *class)
 		for (i = 0; i < ARRAY_SIZE(stats.contention_point); i++)
 			stats.contention_point[i] += pcs->contention_point[i];
 
+		for (i = 0; i < ARRAY_SIZE(stats.contending_point); i++)
+			stats.contending_point[i] += pcs->contending_point[i];
+
 		lock_time_add(&pcs->read_waittime, &stats.read_waittime);
 		lock_time_add(&pcs->write_waittime, &stats.write_waittime);
 
@@ -209,6 +212,7 @@ void clear_lock_stats(struct lock_class *class)
 		memset(cpu_stats, 0, sizeof(struct lock_class_stats));
 	}
 	memset(class->contention_point, 0, sizeof(class->contention_point));
+	memset(class->contending_point, 0, sizeof(class->contending_point));
 }
 
 static struct lock_class_stats *get_lock_stats(struct lock_class *class)
@@ -576,7 +580,8 @@ static void print_lock_class_header(struct lock_class *class, int depth)
 /*
  * printk all lock dependencies starting at <entry>:
  */
-static void print_lock_dependencies(struct lock_class *class, int depth)
+static void __used
+print_lock_dependencies(struct lock_class *class, int depth)
 {
 	struct lock_list *entry;
 
@@ -638,8 +643,8 @@ static int static_obj(void *obj)
 	 * percpu var?
 	 */
 	for_each_possible_cpu(i) {
-		start = (unsigned long) &__per_cpu_start + per_cpu_offset(i);
-		end   = (unsigned long) &__per_cpu_start + PERCPU_ENOUGH_ROOM
+		start = (unsigned long) __per_cpu_start + per_cpu_offset(i);
+		end   = (unsigned long) __per_cpu_start + PERCPU_ENOUGH_ROOM
 					+ per_cpu_offset(i);
 
 		if ((addr >= start) && (addr < end))
@@ -2999,7 +3004,7 @@ __lock_contended(struct lockdep_map *lock, unsigned long ip)
 	struct held_lock *hlock, *prev_hlock;
 	struct lock_class_stats *stats;
 	unsigned int depth;
-	int i, point;
+	int i, contention_point, contending_point;
 
 	depth = curr->lockdep_depth;
 	if (DEBUG_LOCKS_WARN_ON(!depth))
@@ -3023,18 +3028,22 @@ __lock_contended(struct lockdep_map *lock, unsigned long ip)
 found_it:
 	hlock->waittime_stamp = sched_clock();
 
-	point = lock_contention_point(hlock_class(hlock), ip);
+	contention_point = lock_point(hlock_class(hlock)->contention_point, ip);
+	contending_point = lock_point(hlock_class(hlock)->contending_point,
+				      lock->ip);
 
 	stats = get_lock_stats(hlock_class(hlock));
-	if (point < ARRAY_SIZE(stats->contention_point))
-		stats->contention_point[point]++;
+	if (contention_point < LOCKSTAT_POINTS)
+		stats->contention_point[contention_point]++;
+	if (contending_point < LOCKSTAT_POINTS)
+		stats->contending_point[contending_point]++;
 	if (lock->cpu != smp_processor_id())
 		stats->bounces[bounce_contended + !!hlock->read]++;
 	put_lock_stats(stats);
 }
 
 static void
-__lock_acquired(struct lockdep_map *lock)
+__lock_acquired(struct lockdep_map *lock, unsigned long ip)
 {
 	struct task_struct *curr = current;
 	struct held_lock *hlock, *prev_hlock;
@@ -3083,6 +3092,7 @@ found_it:
 	put_lock_stats(stats);
 
 	lock->cpu = cpu;
+	lock->ip = ip;
 }
 
 void lock_contended(struct lockdep_map *lock, unsigned long ip)
@@ -3104,7 +3114,7 @@ void lock_contended(struct lockdep_map *lock, unsigned long ip)
 }
 EXPORT_SYMBOL_GPL(lock_contended);
 
-void lock_acquired(struct lockdep_map *lock)
+void lock_acquired(struct lockdep_map *lock, unsigned long ip)
 {
 	unsigned long flags;
 
@@ -3117,7 +3127,7 @@ void lock_acquired(struct lockdep_map *lock)
 	raw_local_irq_save(flags);
 	check_flags(flags);
 	current->lockdep_recursion = 1;
-	__lock_acquired(lock);
+	__lock_acquired(lock, ip);
 	current->lockdep_recursion = 0;
 	raw_local_irq_restore(flags);
 }
diff --git a/kernel/lockdep_proc.c b/kernel/lockdep_proc.c
index 20dbcbf9c7dd..13716b813896 100644
--- a/kernel/lockdep_proc.c
+++ b/kernel/lockdep_proc.c
@@ -470,11 +470,12 @@ static void seq_line(struct seq_file *m, char c, int offset, int length)
 
 static void snprint_time(char *buf, size_t bufsiz, s64 nr)
 {
-	unsigned long rem;
+	s64 div;
+	s32 rem;
 
 	nr += 5; /* for display rounding */
-	rem = do_div(nr, 1000); /* XXX: do_div_signed */
-	snprintf(buf, bufsiz, "%lld.%02d", (long long)nr, (int)rem/10);
+	div = div_s64_rem(nr, 1000, &rem);
+	snprintf(buf, bufsiz, "%lld.%02d", (long long)div, (int)rem/10);
 }
 
 static void seq_time(struct seq_file *m, s64 time)
@@ -556,7 +557,7 @@ static void seq_stats(struct seq_file *m, struct lock_stat_data *data)
 	if (stats->read_holdtime.nr)
 		namelen += 2;
 
-	for (i = 0; i < ARRAY_SIZE(class->contention_point); i++) {
+	for (i = 0; i < LOCKSTAT_POINTS; i++) {
 		char sym[KSYM_SYMBOL_LEN];
 		char ip[32];
 
@@ -573,6 +574,23 @@ static void seq_stats(struct seq_file *m, struct lock_stat_data *data)
 				stats->contention_point[i],
 				ip, sym);
 	}
+	for (i = 0; i < LOCKSTAT_POINTS; i++) {
+		char sym[KSYM_SYMBOL_LEN];
+		char ip[32];
+
+		if (class->contending_point[i] == 0)
+			break;
+
+		if (!i)
+			seq_line(m, '-', 40-namelen, namelen);
+
+		sprint_symbol(sym, class->contending_point[i]);
+		snprintf(ip, sizeof(ip), "[<%p>]",
+				(void *)class->contending_point[i]);
+		seq_printf(m, "%40s %14lu %29s %s\n", name,
+				stats->contending_point[i],
+				ip, sym);
+	}
 	if (i) {
 		seq_puts(m, "\n");
 		seq_line(m, '.', 0, 40 + 1 + 10 * (14 + 1));
@@ -582,7 +600,7 @@ static void seq_stats(struct seq_file *m, struct lock_stat_data *data)
 
 static void seq_header(struct seq_file *m)
 {
-	seq_printf(m, "lock_stat version 0.2\n");
+	seq_printf(m, "lock_stat version 0.3\n");
 	seq_line(m, '-', 0, 40 + 1 + 10 * (14 + 1));
 	seq_printf(m, "%40s %14s %14s %14s %14s %14s %14s %14s %14s "
 			"%14s %14s\n",
diff --git a/kernel/marker.c b/kernel/marker.c
index e9c6b2bc9400..ea54f2647868 100644
--- a/kernel/marker.c
+++ b/kernel/marker.c
@@ -43,6 +43,7 @@ static DEFINE_MUTEX(markers_mutex);
  */
 #define MARKER_HASH_BITS 6
 #define MARKER_TABLE_SIZE (1 << MARKER_HASH_BITS)
+static struct hlist_head marker_table[MARKER_TABLE_SIZE];
 
 /*
  * Note about RCU :
@@ -64,11 +65,10 @@ struct marker_entry {
 	void *oldptr;
 	int rcu_pending;
 	unsigned char ptype:1;
+	unsigned char format_allocated:1;
 	char name[0];	/* Contains name'\0'format'\0' */
 };
 
-static struct hlist_head marker_table[MARKER_TABLE_SIZE];
-
 /**
  * __mark_empty_function - Empty probe callback
  * @probe_private: probe private data
@@ -81,7 +81,7 @@ static struct hlist_head marker_table[MARKER_TABLE_SIZE];
  * though the function pointer change and the marker enabling are two distinct
  * operations that modifies the execution flow of preemptible code.
  */
-void __mark_empty_function(void *probe_private, void *call_private,
+notrace void __mark_empty_function(void *probe_private, void *call_private,
 	const char *fmt, va_list *args)
 {
 }
@@ -97,7 +97,8 @@ EXPORT_SYMBOL_GPL(__mark_empty_function);
  * need to put a full smp_rmb() in this branch. This is why we do not use
  * rcu_dereference() for the pointer read.
  */
-void marker_probe_cb(const struct marker *mdata, void *call_private, ...)
+notrace void marker_probe_cb(const struct marker *mdata,
+		void *call_private, ...)
 {
 	va_list args;
 	char ptype;
@@ -107,7 +108,7 @@ void marker_probe_cb(const struct marker *mdata, void *call_private, ...)
 	 * sure the teardown of the callbacks can be done correctly when they
 	 * are in modules and they insure RCU read coherency.
 	 */
-	rcu_read_lock_sched();
+	rcu_read_lock_sched_notrace();
 	ptype = mdata->ptype;
 	if (likely(!ptype)) {
 		marker_probe_func *func;
@@ -145,7 +146,7 @@ void marker_probe_cb(const struct marker *mdata, void *call_private, ...)
 			va_end(args);
 		}
 	}
-	rcu_read_unlock_sched();
+	rcu_read_unlock_sched_notrace();
 }
 EXPORT_SYMBOL_GPL(marker_probe_cb);
 
@@ -157,12 +158,13 @@ EXPORT_SYMBOL_GPL(marker_probe_cb);
  *
  * Should be connected to markers "MARK_NOARGS".
  */
-void marker_probe_cb_noarg(const struct marker *mdata, void *call_private, ...)
+static notrace void marker_probe_cb_noarg(const struct marker *mdata,
+		void *call_private, ...)
 {
 	va_list args;	/* not initialized */
 	char ptype;
 
-	rcu_read_lock_sched();
+	rcu_read_lock_sched_notrace();
 	ptype = mdata->ptype;
 	if (likely(!ptype)) {
 		marker_probe_func *func;
@@ -195,9 +197,8 @@ void marker_probe_cb_noarg(const struct marker *mdata, void *call_private, ...)
 			multi[i].func(multi[i].probe_private, call_private,
 				mdata->format, &args);
 	}
-	rcu_read_unlock_sched();
+	rcu_read_unlock_sched_notrace();
 }
-EXPORT_SYMBOL_GPL(marker_probe_cb_noarg);
 
 static void free_old_closure(struct rcu_head *head)
 {
@@ -416,6 +417,7 @@ static struct marker_entry *add_marker(const char *name, const char *format)
 	e->single.probe_private = NULL;
 	e->multi = NULL;
 	e->ptype = 0;
+	e->format_allocated = 0;
 	e->refcount = 0;
 	e->rcu_pending = 0;
 	hlist_add_head(&e->hlist, head);
@@ -447,6 +449,8 @@ static int remove_marker(const char *name)
 	if (e->single.func != __mark_empty_function)
 		return -EBUSY;
 	hlist_del(&e->hlist);
+	if (e->format_allocated)
+		kfree(e->format);
 	/* Make sure the call_rcu has been executed */
 	if (e->rcu_pending)
 		rcu_barrier_sched();
@@ -457,57 +461,34 @@ static int remove_marker(const char *name)
 /*
  * Set the mark_entry format to the format found in the element.
  */
-static int marker_set_format(struct marker_entry **entry, const char *format)
+static int marker_set_format(struct marker_entry *entry, const char *format)
 {
-	struct marker_entry *e;
-	size_t name_len = strlen((*entry)->name) + 1;
-	size_t format_len = strlen(format) + 1;
-
-
-	e = kmalloc(sizeof(struct marker_entry) + name_len + format_len,
-			GFP_KERNEL);
-	if (!e)
+	entry->format = kstrdup(format, GFP_KERNEL);
+	if (!entry->format)
 		return -ENOMEM;
-	memcpy(&e->name[0], (*entry)->name, name_len);
-	e->format = &e->name[name_len];
-	memcpy(e->format, format, format_len);
-	if (strcmp(e->format, MARK_NOARGS) == 0)
-		e->call = marker_probe_cb_noarg;
-	else
-		e->call = marker_probe_cb;
-	e->single = (*entry)->single;
-	e->multi = (*entry)->multi;
-	e->ptype = (*entry)->ptype;
-	e->refcount = (*entry)->refcount;
-	e->rcu_pending = 0;
-	hlist_add_before(&e->hlist, &(*entry)->hlist);
-	hlist_del(&(*entry)->hlist);
-	/* Make sure the call_rcu has been executed */
-	if ((*entry)->rcu_pending)
-		rcu_barrier_sched();
-	kfree(*entry);
-	*entry = e;
+	entry->format_allocated = 1;
+
 	trace_mark(core_marker_format, "name %s format %s",
-			e->name, e->format);
+			entry->name, entry->format);
 	return 0;
 }
 
 /*
  * Sets the probe callback corresponding to one marker.
  */
-static int set_marker(struct marker_entry **entry, struct marker *elem,
+static int set_marker(struct marker_entry *entry, struct marker *elem,
 		int active)
 {
-	int ret;
-	WARN_ON(strcmp((*entry)->name, elem->name) != 0);
+	int ret = 0;
+	WARN_ON(strcmp(entry->name, elem->name) != 0);
 
-	if ((*entry)->format) {
-		if (strcmp((*entry)->format, elem->format) != 0) {
+	if (entry->format) {
+		if (strcmp(entry->format, elem->format) != 0) {
 			printk(KERN_NOTICE
 				"Format mismatch for probe %s "
 				"(%s), marker (%s)\n",
-				(*entry)->name,
-				(*entry)->format,
+				entry->name,
+				entry->format,
 				elem->format);
 			return -EPERM;
 		}
@@ -523,37 +504,67 @@ static int set_marker(struct marker_entry **entry, struct marker *elem,
 	 * pass from a "safe" callback (with argument) to an "unsafe"
 	 * callback (does not set arguments).
 	 */
-	elem->call = (*entry)->call;
+	elem->call = entry->call;
 	/*
 	 * Sanity check :
 	 * We only update the single probe private data when the ptr is
 	 * set to a _non_ single probe! (0 -> 1 and N -> 1, N != 1)
 	 */
 	WARN_ON(elem->single.func != __mark_empty_function
-		&& elem->single.probe_private
-		!= (*entry)->single.probe_private &&
-		!elem->ptype);
-	elem->single.probe_private = (*entry)->single.probe_private;
+		&& elem->single.probe_private != entry->single.probe_private
+		&& !elem->ptype);
+	elem->single.probe_private = entry->single.probe_private;
 	/*
 	 * Make sure the private data is valid when we update the
 	 * single probe ptr.
 	 */
 	smp_wmb();
-	elem->single.func = (*entry)->single.func;
+	elem->single.func = entry->single.func;
 	/*
 	 * We also make sure that the new probe callbacks array is consistent
 	 * before setting a pointer to it.
 	 */
-	rcu_assign_pointer(elem->multi, (*entry)->multi);
+	rcu_assign_pointer(elem->multi, entry->multi);
 	/*
 	 * Update the function or multi probe array pointer before setting the
 	 * ptype.
 	 */
 	smp_wmb();
-	elem->ptype = (*entry)->ptype;
+	elem->ptype = entry->ptype;
+
+	if (elem->tp_name && (active ^ elem->state)) {
+		WARN_ON(!elem->tp_cb);
+		/*
+		 * It is ok to directly call the probe registration because type
+		 * checking has been done in the __trace_mark_tp() macro.
+		 */
+
+		if (active) {
+			/*
+			 * try_module_get should always succeed because we hold
+			 * lock_module() to get the tp_cb address.
+			 */
+			ret = try_module_get(__module_text_address(
+				(unsigned long)elem->tp_cb));
+			BUG_ON(!ret);
+			ret = tracepoint_probe_register_noupdate(
+				elem->tp_name,
+				elem->tp_cb);
+		} else {
+			ret = tracepoint_probe_unregister_noupdate(
+				elem->tp_name,
+				elem->tp_cb);
+			/*
+			 * tracepoint_probe_update_all() must be called
+			 * before the module containing tp_cb is unloaded.
+			 */
+			module_put(__module_text_address(
+				(unsigned long)elem->tp_cb));
+		}
+	}
 	elem->state = active;
 
-	return 0;
+	return ret;
 }
 
 /*
@@ -564,7 +575,24 @@ static int set_marker(struct marker_entry **entry, struct marker *elem,
  */
 static void disable_marker(struct marker *elem)
 {
+	int ret;
+
 	/* leave "call" as is. It is known statically. */
+	if (elem->tp_name && elem->state) {
+		WARN_ON(!elem->tp_cb);
+		/*
+		 * It is ok to directly call the probe registration because type
+		 * checking has been done in the __trace_mark_tp() macro.
+		 */
+		ret = tracepoint_probe_unregister_noupdate(elem->tp_name,
+			elem->tp_cb);
+		WARN_ON(ret);
+		/*
+		 * tracepoint_probe_update_all() must be called
+		 * before the module containing tp_cb is unloaded.
+		 */
+		module_put(__module_text_address((unsigned long)elem->tp_cb));
+	}
 	elem->state = 0;
 	elem->single.func = __mark_empty_function;
 	/* Update the function before setting the ptype */
@@ -594,8 +622,7 @@ void marker_update_probe_range(struct marker *begin,
 	for (iter = begin; iter < end; iter++) {
 		mark_entry = get_marker(iter->name);
 		if (mark_entry) {
-			set_marker(&mark_entry, iter,
-					!!mark_entry->refcount);
+			set_marker(mark_entry, iter, !!mark_entry->refcount);
 			/*
 			 * ignore error, continue
 			 */
@@ -629,6 +656,7 @@ static void marker_update_probes(void)
 	marker_update_probe_range(__start___markers, __stop___markers);
 	/* Markers in modules. */
 	module_update_markers();
+	tracepoint_probe_update_all();
 }
 
 /**
@@ -657,7 +685,7 @@ int marker_probe_register(const char *name, const char *format,
 			ret = PTR_ERR(entry);
 	} else if (format) {
 		if (!entry->format)
-			ret = marker_set_format(&entry, format);
+			ret = marker_set_format(entry, format);
 		else if (strcmp(entry->format, format))
 			ret = -EPERM;
 	}
@@ -676,10 +704,11 @@ int marker_probe_register(const char *name, const char *format,
 		goto end;
 	}
 	mutex_unlock(&markers_mutex);
-	marker_update_probes();		/* may update entry */
+	marker_update_probes();
 	mutex_lock(&markers_mutex);
 	entry = get_marker(name);
-	WARN_ON(!entry);
+	if (!entry)
+		goto end;
 	if (entry->rcu_pending)
 		rcu_barrier_sched();
 	entry->oldptr = old;
@@ -720,7 +749,7 @@ int marker_probe_unregister(const char *name,
 		rcu_barrier_sched();
 	old = marker_entry_remove_probe(entry, probe, probe_private);
 	mutex_unlock(&markers_mutex);
-	marker_update_probes();		/* may update entry */
+	marker_update_probes();
 	mutex_lock(&markers_mutex);
 	entry = get_marker(name);
 	if (!entry)
@@ -801,10 +830,11 @@ int marker_probe_unregister_private_data(marker_probe_func *probe,
 		rcu_barrier_sched();
 	old = marker_entry_remove_probe(entry, NULL, probe_private);
 	mutex_unlock(&markers_mutex);
-	marker_update_probes();		/* may update entry */
+	marker_update_probes();
 	mutex_lock(&markers_mutex);
 	entry = get_marker_from_private_data(probe, probe_private);
-	WARN_ON(!entry);
+	if (!entry)
+		goto end;
 	if (entry->rcu_pending)
 		rcu_barrier_sched();
 	entry->oldptr = old;
@@ -848,8 +878,6 @@ void *marker_get_private_data(const char *name, marker_probe_func *probe,
 			if (!e->ptype) {
 				if (num == 0 && e->single.func == probe)
 					return e->single.probe_private;
-				else
-					break;
 			} else {
 				struct marker_probe_closure *closure;
 				int match = 0;
@@ -861,8 +889,42 @@ void *marker_get_private_data(const char *name, marker_probe_func *probe,
 						return closure[i].probe_private;
 				}
 			}
+			break;
 		}
 	}
 	return ERR_PTR(-ENOENT);
 }
 EXPORT_SYMBOL_GPL(marker_get_private_data);
+
+#ifdef CONFIG_MODULES
+
+int marker_module_notify(struct notifier_block *self,
+			 unsigned long val, void *data)
+{
+	struct module *mod = data;
+
+	switch (val) {
+	case MODULE_STATE_COMING:
+		marker_update_probe_range(mod->markers,
+			mod->markers + mod->num_markers);
+		break;
+	case MODULE_STATE_GOING:
+		marker_update_probe_range(mod->markers,
+			mod->markers + mod->num_markers);
+		break;
+	}
+	return 0;
+}
+
+struct notifier_block marker_module_nb = {
+	.notifier_call = marker_module_notify,
+	.priority = 0,
+};
+
+static int init_markers(void)
+{
+	return register_module_notifier(&marker_module_nb);
+}
+__initcall(init_markers);
+
+#endif /* CONFIG_MODULES */
diff --git a/kernel/module.c b/kernel/module.c
index 1f4cc00e0c20..f5cd963e8cc4 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -47,6 +47,7 @@
 #include <linux/rculist.h>
 #include <asm/uaccess.h>
 #include <asm/cacheflush.h>
+#include <asm/sections.h>
 #include <linux/license.h>
 #include <asm/sections.h>
 #include <linux/tracepoint.h>
@@ -416,7 +417,7 @@ static void *percpu_modalloc(unsigned long size, unsigned long align,
 		align = PAGE_SIZE;
 	}
 
-	ptr = __per_cpu_start;
+	ptr = __per_cpu_load;
 	for (i = 0; i < pcpu_num_used; ptr += block_size(pcpu_size[i]), i++) {
 		/* Extra for alignment requirement. */
 		extra = ALIGN((unsigned long)ptr, align) - (unsigned long)ptr;
@@ -451,7 +452,7 @@ static void *percpu_modalloc(unsigned long size, unsigned long align,
 static void percpu_modfree(void *freeme)
 {
 	unsigned int i;
-	void *ptr = __per_cpu_start + block_size(pcpu_size[0]);
+	void *ptr = __per_cpu_load + block_size(pcpu_size[0]);
 
 	/* First entry is core kernel percpu data. */
 	for (i = 1; i < pcpu_num_used; ptr += block_size(pcpu_size[i]), i++) {
@@ -502,7 +503,7 @@ static int percpu_modinit(void)
 	pcpu_size = kmalloc(sizeof(pcpu_size[0]) * pcpu_num_allocated,
 			    GFP_KERNEL);
 	/* Static in-kernel percpu data (used). */
-	pcpu_size[0] = -(__per_cpu_end-__per_cpu_start);
+	pcpu_size[0] = -__per_cpu_size;
 	/* Free room. */
 	pcpu_size[1] = PERCPU_ENOUGH_ROOM + pcpu_size[0];
 	if (pcpu_size[1] < 0) {
@@ -2184,24 +2185,15 @@ static noinline struct module *load_module(void __user *umod,
 		struct mod_debug *debug;
 		unsigned int num_debug;
 
-#ifdef CONFIG_MARKERS
-		marker_update_probe_range(mod->markers,
-			mod->markers + mod->num_markers);
-#endif
 		debug = section_objs(hdr, sechdrs, secstrings, "__verbose",
 				     sizeof(*debug), &num_debug);
 		dynamic_printk_setup(debug, num_debug);
-
-#ifdef CONFIG_TRACEPOINTS
-		tracepoint_update_probe_range(mod->tracepoints,
-			mod->tracepoints + mod->num_tracepoints);
-#endif
 	}
 
 	/* sechdrs[0].sh_size is always zero */
 	mseg = section_objs(hdr, sechdrs, secstrings, "__mcount_loc",
 			    sizeof(*mseg), &num_mcount);
-	ftrace_init_module(mseg, mseg + num_mcount);
+	ftrace_init_module(mod, mseg, mseg + num_mcount);
 
 	err = module_finalize(hdr, sechdrs, mod);
 	if (err < 0)
diff --git a/kernel/mutex.c b/kernel/mutex.c
index 12c779dc65d4..4f45d4b658ef 100644
--- a/kernel/mutex.c
+++ b/kernel/mutex.c
@@ -59,7 +59,7 @@ EXPORT_SYMBOL(__mutex_init);
  * We also put the fastpath first in the kernel image, to make sure the
  * branch is predicted by the CPU as default-untaken.
  */
-static void noinline __sched
+static __used noinline void __sched
 __mutex_lock_slowpath(atomic_t *lock_count);
 
 /***
@@ -96,7 +96,7 @@ void inline __sched mutex_lock(struct mutex *lock)
 EXPORT_SYMBOL(mutex_lock);
 #endif
 
-static noinline void __sched __mutex_unlock_slowpath(atomic_t *lock_count);
+static __used noinline void __sched __mutex_unlock_slowpath(atomic_t *lock_count);
 
 /***
  * mutex_unlock - release the mutex
@@ -184,7 +184,7 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
 	}
 
 done:
-	lock_acquired(&lock->dep_map);
+	lock_acquired(&lock->dep_map, ip);
 	/* got the lock - rejoice! */
 	mutex_remove_waiter(lock, &waiter, task_thread_info(task));
 	debug_mutex_set_owner(lock, task_thread_info(task));
@@ -268,7 +268,7 @@ __mutex_unlock_common_slowpath(atomic_t *lock_count, int nested)
 /*
  * Release the lock, slowpath:
  */
-static noinline void
+static __used noinline void
 __mutex_unlock_slowpath(atomic_t *lock_count)
 {
 	__mutex_unlock_common_slowpath(lock_count, 1);
@@ -313,7 +313,7 @@ int __sched mutex_lock_killable(struct mutex *lock)
 }
 EXPORT_SYMBOL(mutex_lock_killable);
 
-static noinline void __sched
+static __used noinline void __sched
 __mutex_lock_slowpath(atomic_t *lock_count)
 {
 	struct mutex *lock = container_of(lock_count, struct mutex, count);
diff --git a/kernel/notifier.c b/kernel/notifier.c
index 4282c0a40a57..61d5aa5eced3 100644
--- a/kernel/notifier.c
+++ b/kernel/notifier.c
@@ -82,6 +82,14 @@ static int __kprobes notifier_call_chain(struct notifier_block **nl,
 
 	while (nb && nr_to_call) {
 		next_nb = rcu_dereference(nb->next);
+
+#ifdef CONFIG_DEBUG_NOTIFIERS
+		if (unlikely(!func_ptr_is_kernel_text(nb->notifier_call))) {
+			WARN(1, "Invalid notifier called!");
+			nb = next_nb;
+			continue;
+		}
+#endif
 		ret = nb->notifier_call(nb, val, v);
 
 		if (nr_calls)
diff --git a/kernel/panic.c b/kernel/panic.c
index 4d5088355bfe..3a0b0898690a 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -21,6 +21,7 @@
 #include <linux/debug_locks.h>
 #include <linux/random.h>
 #include <linux/kallsyms.h>
+#include <linux/dmi.h>
 
 int panic_on_oops;
 static unsigned long tainted_mask;
@@ -73,6 +74,9 @@ NORET_TYPE void panic(const char * fmt, ...)
 	vsnprintf(buf, sizeof(buf), fmt, args);
 	va_end(args);
 	printk(KERN_EMERG "Kernel panic - not syncing: %s\n",buf);
+#ifdef CONFIG_DEBUG_BUGVERBOSE
+	dump_stack();
+#endif
 	bust_spinlocks(0);
 
 	/*
@@ -321,36 +325,27 @@ void oops_exit(void)
 }
 
 #ifdef WANT_WARN_ON_SLOWPATH
-void warn_on_slowpath(const char *file, int line)
-{
-	char function[KSYM_SYMBOL_LEN];
-	unsigned long caller = (unsigned long) __builtin_return_address(0);
-	sprint_symbol(function, caller);
-
-	printk(KERN_WARNING "------------[ cut here ]------------\n");
-	printk(KERN_WARNING "WARNING: at %s:%d %s()\n", file,
-		line, function);
-	print_modules();
-	dump_stack();
-	print_oops_end_marker();
-	add_taint(TAINT_WARN);
-}
-EXPORT_SYMBOL(warn_on_slowpath);
-
-
 void warn_slowpath(const char *file, int line, const char *fmt, ...)
 {
 	va_list args;
 	char function[KSYM_SYMBOL_LEN];
 	unsigned long caller = (unsigned long)__builtin_return_address(0);
+	const char *board;
+
 	sprint_symbol(function, caller);
 
 	printk(KERN_WARNING "------------[ cut here ]------------\n");
 	printk(KERN_WARNING "WARNING: at %s:%d %s()\n", file,
 		line, function);
-	va_start(args, fmt);
-	vprintk(fmt, args);
-	va_end(args);
+	board = dmi_get_system_info(DMI_PRODUCT_NAME);
+	if (board)
+		printk(KERN_WARNING "Hardware name: %s\n", board);
+
+	if (fmt) {
+		va_start(args, fmt);
+		vprintk(fmt, args);
+		va_end(args);
+	}
 
 	print_modules();
 	dump_stack();
@@ -361,15 +356,22 @@ EXPORT_SYMBOL(warn_slowpath);
 #endif
 
 #ifdef CONFIG_CC_STACKPROTECTOR
+
+#ifndef GCC_HAS_SP
+#warning You have selected the CONFIG_CC_STACKPROTECTOR option, but the gcc used does not support this.
+#endif
+
 /*
  * Called when gcc's -fstack-protector feature is used, and
  * gcc detects corruption of the on-stack canary value
  */
 void __stack_chk_fail(void)
 {
-	panic("stack-protector: Kernel stack is corrupted");
+	panic("stack-protector: Kernel stack is corrupted in: %p\n",
+		__builtin_return_address(0));
 }
 EXPORT_SYMBOL(__stack_chk_fail);
+
 #endif
 
 core_param(panic, panic_timeout, int, 0644);
diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c
index 895337b16a24..157de3a47832 100644
--- a/kernel/posix-cpu-timers.c
+++ b/kernel/posix-cpu-timers.c
@@ -58,21 +58,21 @@ void thread_group_cputime(
 	struct task_struct *tsk,
 	struct task_cputime *times)
 {
-	struct signal_struct *sig;
+	struct task_cputime *totals, *tot;
 	int i;
-	struct task_cputime *tot;
 
-	sig = tsk->signal;
-	if (unlikely(!sig) || !sig->cputime.totals) {
+	totals = tsk->signal->cputime.totals;
+	if (!totals) {
 		times->utime = tsk->utime;
 		times->stime = tsk->stime;
 		times->sum_exec_runtime = tsk->se.sum_exec_runtime;
 		return;
 	}
+
 	times->stime = times->utime = cputime_zero;
 	times->sum_exec_runtime = 0;
 	for_each_possible_cpu(i) {
-		tot = per_cpu_ptr(tsk->signal->cputime.totals, i);
+		tot = per_cpu_ptr(totals, i);
 		times->utime = cputime_add(times->utime, tot->utime);
 		times->stime = cputime_add(times->stime, tot->stime);
 		times->sum_exec_runtime += tot->sum_exec_runtime;
@@ -311,7 +311,7 @@ static int cpu_clock_sample_group(const clockid_t which_clock,
 	struct task_cputime cputime;
 
 	thread_group_cputime(p, &cputime);
-	switch (which_clock) {
+	switch (CPUCLOCK_WHICH(which_clock)) {
 	default:
 		return -EINVAL;
 	case CPUCLOCK_PROF:
diff --git a/kernel/power/disk.c b/kernel/power/disk.c
index c9d74083746f..45e8541ab7e3 100644
--- a/kernel/power/disk.c
+++ b/kernel/power/disk.c
@@ -22,7 +22,6 @@
 #include <linux/console.h>
 #include <linux/cpu.h>
 #include <linux/freezer.h>
-#include <linux/ftrace.h>
 
 #include "power.h"
 
@@ -257,19 +256,18 @@ static int create_image(int platform_mode)
 
 int hibernation_snapshot(int platform_mode)
 {
-	int error, ftrace_save;
+	int error;
 
-	/* Free memory before shutting down devices. */
-	error = swsusp_shrink_memory();
+	error = platform_begin(platform_mode);
 	if (error)
 		return error;
 
-	error = platform_begin(platform_mode);
+	/* Free memory before shutting down devices. */
+	error = swsusp_shrink_memory();
 	if (error)
 		goto Close;
 
 	suspend_console();
-	ftrace_save = __ftrace_enabled_save();
 	error = device_suspend(PMSG_FREEZE);
 	if (error)
 		goto Recover_platform;
@@ -299,7 +297,6 @@ int hibernation_snapshot(int platform_mode)
  Resume_devices:
 	device_resume(in_suspend ?
 		(error ? PMSG_RECOVER : PMSG_THAW) : PMSG_RESTORE);
-	__ftrace_enabled_restore(ftrace_save);
 	resume_console();
  Close:
 	platform_end(platform_mode);
@@ -370,11 +367,10 @@ static int resume_target_kernel(void)
 
 int hibernation_restore(int platform_mode)
 {
-	int error, ftrace_save;
+	int error;
 
 	pm_prepare_console();
 	suspend_console();
-	ftrace_save = __ftrace_enabled_save();
 	error = device_suspend(PMSG_QUIESCE);
 	if (error)
 		goto Finish;
@@ -389,7 +385,6 @@ int hibernation_restore(int platform_mode)
 	platform_restore_cleanup(platform_mode);
 	device_resume(PMSG_RECOVER);
  Finish:
-	__ftrace_enabled_restore(ftrace_save);
 	resume_console();
 	pm_restore_console();
 	return error;
@@ -402,7 +397,7 @@ int hibernation_restore(int platform_mode)
 
 int hibernation_platform_enter(void)
 {
-	int error, ftrace_save;
+	int error;
 
 	if (!hibernation_ops)
 		return -ENOSYS;
@@ -417,7 +412,6 @@ int hibernation_platform_enter(void)
 		goto Close;
 
 	suspend_console();
-	ftrace_save = __ftrace_enabled_save();
 	error = device_suspend(PMSG_HIBERNATE);
 	if (error) {
 		if (hibernation_ops->recover)
@@ -452,7 +446,6 @@ int hibernation_platform_enter(void)
 	hibernation_ops->finish();
  Resume_devices:
 	device_resume(PMSG_RESTORE);
-	__ftrace_enabled_restore(ftrace_save);
 	resume_console();
  Close:
 	hibernation_ops->end();
diff --git a/kernel/power/main.c b/kernel/power/main.c
index b8f7ce9473e8..239988873971 100644
--- a/kernel/power/main.c
+++ b/kernel/power/main.c
@@ -22,7 +22,6 @@
 #include <linux/freezer.h>
 #include <linux/vmstat.h>
 #include <linux/syscalls.h>
-#include <linux/ftrace.h>
 
 #include "power.h"
 
@@ -317,7 +316,7 @@ static int suspend_enter(suspend_state_t state)
  */
 int suspend_devices_and_enter(suspend_state_t state)
 {
-	int error, ftrace_save;
+	int error;
 
 	if (!suspend_ops)
 		return -ENOSYS;
@@ -328,7 +327,6 @@ int suspend_devices_and_enter(suspend_state_t state)
 			goto Close;
 	}
 	suspend_console();
-	ftrace_save = __ftrace_enabled_save();
 	suspend_test_start();
 	error = device_suspend(PMSG_SUSPEND);
 	if (error) {
@@ -360,7 +358,6 @@ int suspend_devices_and_enter(suspend_state_t state)
 	suspend_test_start();
 	device_resume(PMSG_RESUME);
 	suspend_test_finish("resume devices");
-	__ftrace_enabled_restore(ftrace_save);
 	resume_console();
  Close:
 	if (suspend_ops->end)
@@ -618,7 +615,7 @@ static void __init test_wakealarm(struct rtc_device *rtc, suspend_state_t state)
 	/* this may fail if the RTC hasn't been initialized */
 	status = rtc_read_time(rtc, &alm.time);
 	if (status < 0) {
-		printk(err_readtime, rtc->dev.bus_id, status);
+		printk(err_readtime, dev_name(&rtc->dev), status);
 		return;
 	}
 	rtc_tm_to_time(&alm.time, &now);
@@ -629,7 +626,7 @@ static void __init test_wakealarm(struct rtc_device *rtc, suspend_state_t state)
 
 	status = rtc_set_alarm(rtc, &alm);
 	if (status < 0) {
-		printk(err_wakealarm, rtc->dev.bus_id, status);
+		printk(err_wakealarm, dev_name(&rtc->dev), status);
 		return;
 	}
 
@@ -663,7 +660,7 @@ static int __init has_wakealarm(struct device *dev, void *name_ptr)
 	if (!device_may_wakeup(candidate->dev.parent))
 		return 0;
 
-	*(char **)name_ptr = dev->bus_id;
+	*(const char **)name_ptr = dev_name(dev);
 	return 1;
 }
 
diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
index 5d2ab836e998..ec9f153b2fc2 100644
--- a/kernel/power/snapshot.c
+++ b/kernel/power/snapshot.c
@@ -25,6 +25,7 @@
 #include <linux/syscalls.h>
 #include <linux/console.h>
 #include <linux/highmem.h>
+#include <linux/list.h>
 
 #include <asm/uaccess.h>
 #include <asm/mmu_context.h>
@@ -192,12 +193,6 @@ static void *chain_alloc(struct chain_allocator *ca, unsigned int size)
 	return ret;
 }
 
-static void chain_free(struct chain_allocator *ca, int clear_page_nosave)
-{
-	free_list_of_pages(ca->chain, clear_page_nosave);
-	memset(ca, 0, sizeof(struct chain_allocator));
-}
-
 /**
  *	Data types related to memory bitmaps.
  *
@@ -233,7 +228,7 @@ static void chain_free(struct chain_allocator *ca, int clear_page_nosave)
 #define BM_BITS_PER_BLOCK	(PAGE_SIZE << 3)
 
 struct bm_block {
-	struct bm_block *next;		/* next element of the list */
+	struct list_head hook;	/* hook into a list of bitmap blocks */
 	unsigned long start_pfn;	/* pfn represented by the first bit */
 	unsigned long end_pfn;	/* pfn represented by the last bit plus 1 */
 	unsigned long *data;	/* bitmap representing pages */
@@ -244,24 +239,15 @@ static inline unsigned long bm_block_bits(struct bm_block *bb)
 	return bb->end_pfn - bb->start_pfn;
 }
 
-struct zone_bitmap {
-	struct zone_bitmap *next;	/* next element of the list */
-	unsigned long start_pfn;	/* minimal pfn in this zone */
-	unsigned long end_pfn;		/* maximal pfn in this zone plus 1 */
-	struct bm_block *bm_blocks;	/* list of bitmap blocks */
-	struct bm_block *cur_block;	/* recently used bitmap block */
-};
-
 /* strcut bm_position is used for browsing memory bitmaps */
 
 struct bm_position {
-	struct zone_bitmap *zone_bm;
 	struct bm_block *block;
 	int bit;
 };
 
 struct memory_bitmap {
-	struct zone_bitmap *zone_bm_list;	/* list of zone bitmaps */
+	struct list_head blocks;	/* list of bitmap blocks */
 	struct linked_page *p_list;	/* list of pages used to store zone
 					 * bitmap objects and bitmap block
 					 * objects
@@ -273,11 +259,7 @@ struct memory_bitmap {
 
 static void memory_bm_position_reset(struct memory_bitmap *bm)
 {
-	struct zone_bitmap *zone_bm;
-
-	zone_bm = bm->zone_bm_list;
-	bm->cur.zone_bm = zone_bm;
-	bm->cur.block = zone_bm->bm_blocks;
+	bm->cur.block = list_entry(bm->blocks.next, struct bm_block, hook);
 	bm->cur.bit = 0;
 }
 
@@ -285,151 +267,184 @@ static void memory_bm_free(struct memory_bitmap *bm, int clear_nosave_free);
 
 /**
  *	create_bm_block_list - create a list of block bitmap objects
+ *	@nr_blocks - number of blocks to allocate
+ *	@list - list to put the allocated blocks into
+ *	@ca - chain allocator to be used for allocating memory
  */
-
-static inline struct bm_block *
-create_bm_block_list(unsigned int nr_blocks, struct chain_allocator *ca)
+static int create_bm_block_list(unsigned long pages,
+				struct list_head *list,
+				struct chain_allocator *ca)
 {
-	struct bm_block *bblist = NULL;
+	unsigned int nr_blocks = DIV_ROUND_UP(pages, BM_BITS_PER_BLOCK);
 
 	while (nr_blocks-- > 0) {
 		struct bm_block *bb;
 
 		bb = chain_alloc(ca, sizeof(struct bm_block));
 		if (!bb)
-			return NULL;
-
-		bb->next = bblist;
-		bblist = bb;
+			return -ENOMEM;
+		list_add(&bb->hook, list);
 	}
-	return bblist;
+
+	return 0;
 }
 
+struct mem_extent {
+	struct list_head hook;
+	unsigned long start;
+	unsigned long end;
+};
+
 /**
- *	create_zone_bm_list - create a list of zone bitmap objects
+ *	free_mem_extents - free a list of memory extents
+ *	@list - list of extents to empty
  */
+static void free_mem_extents(struct list_head *list)
+{
+	struct mem_extent *ext, *aux;
 
-static inline struct zone_bitmap *
-create_zone_bm_list(unsigned int nr_zones, struct chain_allocator *ca)
+	list_for_each_entry_safe(ext, aux, list, hook) {
+		list_del(&ext->hook);
+		kfree(ext);
+	}
+}
+
+/**
+ *	create_mem_extents - create a list of memory extents representing
+ *	                     contiguous ranges of PFNs
+ *	@list - list to put the extents into
+ *	@gfp_mask - mask to use for memory allocations
+ */
+static int create_mem_extents(struct list_head *list, gfp_t gfp_mask)
 {
-	struct zone_bitmap *zbmlist = NULL;
+	struct zone *zone;
 
-	while (nr_zones-- > 0) {
-		struct zone_bitmap *zbm;
+	INIT_LIST_HEAD(list);
 
-		zbm = chain_alloc(ca, sizeof(struct zone_bitmap));
-		if (!zbm)
-			return NULL;
+	for_each_zone(zone) {
+		unsigned long zone_start, zone_end;
+		struct mem_extent *ext, *cur, *aux;
+
+		if (!populated_zone(zone))
+			continue;
 
-		zbm->next = zbmlist;
-		zbmlist = zbm;
+		zone_start = zone->zone_start_pfn;
+		zone_end = zone->zone_start_pfn + zone->spanned_pages;
+
+		list_for_each_entry(ext, list, hook)
+			if (zone_start <= ext->end)
+				break;
+
+		if (&ext->hook == list || zone_end < ext->start) {
+			/* New extent is necessary */
+			struct mem_extent *new_ext;
+
+			new_ext = kzalloc(sizeof(struct mem_extent), gfp_mask);
+			if (!new_ext) {
+				free_mem_extents(list);
+				return -ENOMEM;
+			}
+			new_ext->start = zone_start;
+			new_ext->end = zone_end;
+			list_add_tail(&new_ext->hook, &ext->hook);
+			continue;
+		}
+
+		/* Merge this zone's range of PFNs with the existing one */
+		if (zone_start < ext->start)
+			ext->start = zone_start;
+		if (zone_end > ext->end)
+			ext->end = zone_end;
+
+		/* More merging may be possible */
+		cur = ext;
+		list_for_each_entry_safe_continue(cur, aux, list, hook) {
+			if (zone_end < cur->start)
+				break;
+			if (zone_end < cur->end)
+				ext->end = cur->end;
+			list_del(&cur->hook);
+			kfree(cur);
+		}
 	}
-	return zbmlist;
+
+	return 0;
 }
 
 /**
   *	memory_bm_create - allocate memory for a memory bitmap
   */
-
 static int
 memory_bm_create(struct memory_bitmap *bm, gfp_t gfp_mask, int safe_needed)
 {
 	struct chain_allocator ca;
-	struct zone *zone;
-	struct zone_bitmap *zone_bm;
-	struct bm_block *bb;
-	unsigned int nr;
+	struct list_head mem_extents;
+	struct mem_extent *ext;
+	int error;
 
 	chain_init(&ca, gfp_mask, safe_needed);
+	INIT_LIST_HEAD(&bm->blocks);
 
-	/* Compute the number of zones */
-	nr = 0;
-	for_each_zone(zone)
-		if (populated_zone(zone))
-			nr++;
-
-	/* Allocate the list of zones bitmap objects */
-	zone_bm = create_zone_bm_list(nr, &ca);
-	bm->zone_bm_list = zone_bm;
-	if (!zone_bm) {
-		chain_free(&ca, PG_UNSAFE_CLEAR);
-		return -ENOMEM;
-	}
-
-	/* Initialize the zone bitmap objects */
-	for_each_zone(zone) {
-		unsigned long pfn;
+	error = create_mem_extents(&mem_extents, gfp_mask);
+	if (error)
+		return error;
 
-		if (!populated_zone(zone))
-			continue;
+	list_for_each_entry(ext, &mem_extents, hook) {
+		struct bm_block *bb;
+		unsigned long pfn = ext->start;
+		unsigned long pages = ext->end - ext->start;
 
-		zone_bm->start_pfn = zone->zone_start_pfn;
-		zone_bm->end_pfn = zone->zone_start_pfn + zone->spanned_pages;
-		/* Allocate the list of bitmap block objects */
-		nr = DIV_ROUND_UP(zone->spanned_pages, BM_BITS_PER_BLOCK);
-		bb = create_bm_block_list(nr, &ca);
-		zone_bm->bm_blocks = bb;
-		zone_bm->cur_block = bb;
-		if (!bb)
-			goto Free;
+		bb = list_entry(bm->blocks.prev, struct bm_block, hook);
 
-		nr = zone->spanned_pages;
-		pfn = zone->zone_start_pfn;
-		/* Initialize the bitmap block objects */
-		while (bb) {
-			unsigned long *ptr;
+		error = create_bm_block_list(pages, bm->blocks.prev, &ca);
+		if (error)
+			goto Error;
 
-			ptr = get_image_page(gfp_mask, safe_needed);
-			bb->data = ptr;
-			if (!ptr)
-				goto Free;
+		list_for_each_entry_continue(bb, &bm->blocks, hook) {
+			bb->data = get_image_page(gfp_mask, safe_needed);
+			if (!bb->data) {
+				error = -ENOMEM;
+				goto Error;
+			}
 
 			bb->start_pfn = pfn;
-			if (nr >= BM_BITS_PER_BLOCK) {
+			if (pages >= BM_BITS_PER_BLOCK) {
 				pfn += BM_BITS_PER_BLOCK;
-				nr -= BM_BITS_PER_BLOCK;
+				pages -= BM_BITS_PER_BLOCK;
 			} else {
 				/* This is executed only once in the loop */
-				pfn += nr;
+				pfn += pages;
 			}
 			bb->end_pfn = pfn;
-			bb = bb->next;
 		}
-		zone_bm = zone_bm->next;
 	}
+
 	bm->p_list = ca.chain;
 	memory_bm_position_reset(bm);
-	return 0;
+ Exit:
+	free_mem_extents(&mem_extents);
+	return error;
 
- Free:
+ Error:
 	bm->p_list = ca.chain;
 	memory_bm_free(bm, PG_UNSAFE_CLEAR);
-	return -ENOMEM;
+	goto Exit;
 }
 
 /**
   *	memory_bm_free - free memory occupied by the memory bitmap @bm
   */
-
 static void memory_bm_free(struct memory_bitmap *bm, int clear_nosave_free)
 {
-	struct zone_bitmap *zone_bm;
+	struct bm_block *bb;
 
-	/* Free the list of bit blocks for each zone_bitmap object */
-	zone_bm = bm->zone_bm_list;
-	while (zone_bm) {
-		struct bm_block *bb;
+	list_for_each_entry(bb, &bm->blocks, hook)
+		if (bb->data)
+			free_image_page(bb->data, clear_nosave_free);
 
-		bb = zone_bm->bm_blocks;
-		while (bb) {
-			if (bb->data)
-				free_image_page(bb->data, clear_nosave_free);
-			bb = bb->next;
-		}
-		zone_bm = zone_bm->next;
-	}
 	free_list_of_pages(bm->p_list, clear_nosave_free);
-	bm->zone_bm_list = NULL;
+
+	INIT_LIST_HEAD(&bm->blocks);
 }
 
 /**
@@ -437,38 +452,33 @@ static void memory_bm_free(struct memory_bitmap *bm, int clear_nosave_free)
  *	to given pfn.  The cur_zone_bm member of @bm and the cur_block member
  *	of @bm->cur_zone_bm are updated.
  */
-
 static int memory_bm_find_bit(struct memory_bitmap *bm, unsigned long pfn,
 				void **addr, unsigned int *bit_nr)
 {
-	struct zone_bitmap *zone_bm;
 	struct bm_block *bb;
 
-	/* Check if the pfn is from the current zone */
-	zone_bm = bm->cur.zone_bm;
-	if (pfn < zone_bm->start_pfn || pfn >= zone_bm->end_pfn) {
-		zone_bm = bm->zone_bm_list;
-		/* We don't assume that the zones are sorted by pfns */
-		while (pfn < zone_bm->start_pfn || pfn >= zone_bm->end_pfn) {
-			zone_bm = zone_bm->next;
-
-			if (!zone_bm)
-				return -EFAULT;
-		}
-		bm->cur.zone_bm = zone_bm;
-	}
-	/* Check if the pfn corresponds to the current bitmap block */
-	bb = zone_bm->cur_block;
+	/*
+	 * Check if the pfn corresponds to the current bitmap block and find
+	 * the block where it fits if this is not the case.
+	 */
+	bb = bm->cur.block;
 	if (pfn < bb->start_pfn)
-		bb = zone_bm->bm_blocks;
+		list_for_each_entry_continue_reverse(bb, &bm->blocks, hook)
+			if (pfn >= bb->start_pfn)
+				break;
 
-	while (pfn >= bb->end_pfn) {
-		bb = bb->next;
+	if (pfn >= bb->end_pfn)
+		list_for_each_entry_continue(bb, &bm->blocks, hook)
+			if (pfn >= bb->start_pfn && pfn < bb->end_pfn)
+				break;
 
-		BUG_ON(!bb);
-	}
-	zone_bm->cur_block = bb;
+	if (&bb->hook == &bm->blocks)
+		return -EFAULT;
+
+	/* The block has been found */
+	bm->cur.block = bb;
 	pfn -= bb->start_pfn;
+	bm->cur.bit = pfn + 1;
 	*bit_nr = pfn;
 	*addr = bb->data;
 	return 0;
@@ -519,6 +529,14 @@ static int memory_bm_test_bit(struct memory_bitmap *bm, unsigned long pfn)
 	return test_bit(bit, addr);
 }
 
+static bool memory_bm_pfn_present(struct memory_bitmap *bm, unsigned long pfn)
+{
+	void *addr;
+	unsigned int bit;
+
+	return !memory_bm_find_bit(bm, pfn, &addr, &bit);
+}
+
 /**
  *	memory_bm_next_pfn - find the pfn that corresponds to the next set bit
  *	in the bitmap @bm.  If the pfn cannot be found, BM_END_OF_MAP is
@@ -530,29 +548,21 @@ static int memory_bm_test_bit(struct memory_bitmap *bm, unsigned long pfn)
 
 static unsigned long memory_bm_next_pfn(struct memory_bitmap *bm)
 {
-	struct zone_bitmap *zone_bm;
 	struct bm_block *bb;
 	int bit;
 
+	bb = bm->cur.block;
 	do {
-		bb = bm->cur.block;
-		do {
-			bit = bm->cur.bit;
-			bit = find_next_bit(bb->data, bm_block_bits(bb), bit);
-			if (bit < bm_block_bits(bb))
-				goto Return_pfn;
-
-			bb = bb->next;
-			bm->cur.block = bb;
-			bm->cur.bit = 0;
-		} while (bb);
-		zone_bm = bm->cur.zone_bm->next;
-		if (zone_bm) {
-			bm->cur.zone_bm = zone_bm;
-			bm->cur.block = zone_bm->bm_blocks;
-			bm->cur.bit = 0;
-		}
-	} while (zone_bm);
+		bit = bm->cur.bit;
+		bit = find_next_bit(bb->data, bm_block_bits(bb), bit);
+		if (bit < bm_block_bits(bb))
+			goto Return_pfn;
+
+		bb = list_entry(bb->hook.next, struct bm_block, hook);
+		bm->cur.block = bb;
+		bm->cur.bit = 0;
+	} while (&bb->hook != &bm->blocks);
+
 	memory_bm_position_reset(bm);
 	return BM_END_OF_MAP;
 
@@ -808,8 +818,7 @@ static unsigned int count_free_highmem_pages(void)
  *	We should save the page if it isn't Nosave or NosaveFree, or Reserved,
  *	and it isn't a part of a free chunk of pages.
  */
-
-static struct page *saveable_highmem_page(unsigned long pfn)
+static struct page *saveable_highmem_page(struct zone *zone, unsigned long pfn)
 {
 	struct page *page;
 
@@ -817,6 +826,8 @@ static struct page *saveable_highmem_page(unsigned long pfn)
 		return NULL;
 
 	page = pfn_to_page(pfn);
+	if (page_zone(page) != zone)
+		return NULL;
 
 	BUG_ON(!PageHighMem(page));
 
@@ -846,13 +857,16 @@ unsigned int count_highmem_pages(void)
 		mark_free_pages(zone);
 		max_zone_pfn = zone->zone_start_pfn + zone->spanned_pages;
 		for (pfn = zone->zone_start_pfn; pfn < max_zone_pfn; pfn++)
-			if (saveable_highmem_page(pfn))
+			if (saveable_highmem_page(zone, pfn))
 				n++;
 	}
 	return n;
 }
 #else
-static inline void *saveable_highmem_page(unsigned long pfn) { return NULL; }
+static inline void *saveable_highmem_page(struct zone *z, unsigned long p)
+{
+	return NULL;
+}
 #endif /* CONFIG_HIGHMEM */
 
 /**
@@ -863,8 +877,7 @@ static inline void *saveable_highmem_page(unsigned long pfn) { return NULL; }
  *	of pages statically defined as 'unsaveable', and it isn't a part of
  *	a free chunk of pages.
  */
-
-static struct page *saveable_page(unsigned long pfn)
+static struct page *saveable_page(struct zone *zone, unsigned long pfn)
 {
 	struct page *page;
 
@@ -872,6 +885,8 @@ static struct page *saveable_page(unsigned long pfn)
 		return NULL;
 
 	page = pfn_to_page(pfn);
+	if (page_zone(page) != zone)
+		return NULL;
 
 	BUG_ON(PageHighMem(page));
 
@@ -903,7 +918,7 @@ unsigned int count_data_pages(void)
 		mark_free_pages(zone);
 		max_zone_pfn = zone->zone_start_pfn + zone->spanned_pages;
 		for (pfn = zone->zone_start_pfn; pfn < max_zone_pfn; pfn++)
-			if(saveable_page(pfn))
+			if (saveable_page(zone, pfn))
 				n++;
 	}
 	return n;
@@ -944,7 +959,7 @@ static inline struct page *
 page_is_saveable(struct zone *zone, unsigned long pfn)
 {
 	return is_highmem(zone) ?
-			saveable_highmem_page(pfn) : saveable_page(pfn);
+		saveable_highmem_page(zone, pfn) : saveable_page(zone, pfn);
 }
 
 static void copy_data_page(unsigned long dst_pfn, unsigned long src_pfn)
@@ -975,7 +990,7 @@ static void copy_data_page(unsigned long dst_pfn, unsigned long src_pfn)
 	}
 }
 #else
-#define page_is_saveable(zone, pfn)	saveable_page(pfn)
+#define page_is_saveable(zone, pfn)	saveable_page(zone, pfn)
 
 static inline void copy_data_page(unsigned long dst_pfn, unsigned long src_pfn)
 {
@@ -1459,9 +1474,7 @@ load_header(struct swsusp_info *info)
  *	unpack_orig_pfns - for each element of @buf[] (1 page at a time) set
  *	the corresponding bit in the memory bitmap @bm
  */
-
-static inline void
-unpack_orig_pfns(unsigned long *buf, struct memory_bitmap *bm)
+static int unpack_orig_pfns(unsigned long *buf, struct memory_bitmap *bm)
 {
 	int j;
 
@@ -1469,8 +1482,13 @@ unpack_orig_pfns(unsigned long *buf, struct memory_bitmap *bm)
 		if (unlikely(buf[j] == BM_END_OF_MAP))
 			break;
 
-		memory_bm_set_bit(bm, buf[j]);
+		if (memory_bm_pfn_present(bm, buf[j]))
+			memory_bm_set_bit(bm, buf[j]);
+		else
+			return -EFAULT;
 	}
+
+	return 0;
 }
 
 /* List of "safe" pages that may be used to store data loaded from the suspend
@@ -1608,7 +1626,7 @@ get_highmem_page_buffer(struct page *page, struct chain_allocator *ca)
 	pbe = chain_alloc(ca, sizeof(struct highmem_pbe));
 	if (!pbe) {
 		swsusp_free();
-		return NULL;
+		return ERR_PTR(-ENOMEM);
 	}
 	pbe->orig_page = page;
 	if (safe_highmem_pages > 0) {
@@ -1677,7 +1695,7 @@ prepare_highmem_image(struct memory_bitmap *bm, unsigned int *nr_highmem_p)
 static inline void *
 get_highmem_page_buffer(struct page *page, struct chain_allocator *ca)
 {
-	return NULL;
+	return ERR_PTR(-EINVAL);
 }
 
 static inline void copy_last_highmem_page(void) {}
@@ -1788,8 +1806,13 @@ prepare_image(struct memory_bitmap *new_bm, struct memory_bitmap *bm)
 static void *get_buffer(struct memory_bitmap *bm, struct chain_allocator *ca)
 {
 	struct pbe *pbe;
-	struct page *page = pfn_to_page(memory_bm_next_pfn(bm));
+	struct page *page;
+	unsigned long pfn = memory_bm_next_pfn(bm);
 
+	if (pfn == BM_END_OF_MAP)
+		return ERR_PTR(-EFAULT);
+
+	page = pfn_to_page(pfn);
 	if (PageHighMem(page))
 		return get_highmem_page_buffer(page, ca);
 
@@ -1805,7 +1828,7 @@ static void *get_buffer(struct memory_bitmap *bm, struct chain_allocator *ca)
 	pbe = chain_alloc(ca, sizeof(struct pbe));
 	if (!pbe) {
 		swsusp_free();
-		return NULL;
+		return ERR_PTR(-ENOMEM);
 	}
 	pbe->orig_address = page_address(page);
 	pbe->address = safe_pages_list;
@@ -1868,7 +1891,10 @@ int snapshot_write_next(struct snapshot_handle *handle, size_t count)
 				return error;
 
 		} else if (handle->prev <= nr_meta_pages) {
-			unpack_orig_pfns(buffer, &copy_bm);
+			error = unpack_orig_pfns(buffer, &copy_bm);
+			if (error)
+				return error;
+
 			if (handle->prev == nr_meta_pages) {
 				error = prepare_image(&orig_bm, &copy_bm);
 				if (error)
@@ -1879,12 +1905,14 @@ int snapshot_write_next(struct snapshot_handle *handle, size_t count)
 				restore_pblist = NULL;
 				handle->buffer = get_buffer(&orig_bm, &ca);
 				handle->sync_read = 0;
-				if (!handle->buffer)
-					return -ENOMEM;
+				if (IS_ERR(handle->buffer))
+					return PTR_ERR(handle->buffer);
 			}
 		} else {
 			copy_last_highmem_page();
 			handle->buffer = get_buffer(&orig_bm, &ca);
+			if (IS_ERR(handle->buffer))
+				return PTR_ERR(handle->buffer);
 			if (handle->buffer != buffer)
 				handle->sync_read = 0;
 		}
diff --git a/kernel/power/swap.c b/kernel/power/swap.c
index b7713b53d07a..6da14358537c 100644
--- a/kernel/power/swap.c
+++ b/kernel/power/swap.c
@@ -633,7 +633,7 @@ void swsusp_close(fmode_t mode)
 		return;
 	}
 
-	blkdev_put(resume_bdev, mode); /* move up */
+	blkdev_put(resume_bdev, mode);
 }
 
 static int swsusp_header_init(void)
diff --git a/kernel/power/swsusp.c b/kernel/power/swsusp.c
index 023ff2a31d89..a92c91451559 100644
--- a/kernel/power/swsusp.c
+++ b/kernel/power/swsusp.c
@@ -262,3 +262,125 @@ int swsusp_shrink_memory(void)
 
 	return 0;
 }
+
+/*
+ * Platforms, like ACPI, may want us to save some memory used by them during
+ * hibernation and to restore the contents of this memory during the subsequent
+ * resume.  The code below implements a mechanism allowing us to do that.
+ */
+
+struct nvs_page {
+	unsigned long phys_start;
+	unsigned int size;
+	void *kaddr;
+	void *data;
+	struct list_head node;
+};
+
+static LIST_HEAD(nvs_list);
+
+/**
+ *	hibernate_nvs_register - register platform NVS memory region to save
+ *	@start - physical address of the region
+ *	@size - size of the region
+ *
+ *	The NVS region need not be page-aligned (both ends) and we arrange
+ *	things so that the data from page-aligned addresses in this region will
+ *	be copied into separate RAM pages.
+ */
+int hibernate_nvs_register(unsigned long start, unsigned long size)
+{
+	struct nvs_page *entry, *next;
+
+	while (size > 0) {
+		unsigned int nr_bytes;
+
+		entry = kzalloc(sizeof(struct nvs_page), GFP_KERNEL);
+		if (!entry)
+			goto Error;
+
+		list_add_tail(&entry->node, &nvs_list);
+		entry->phys_start = start;
+		nr_bytes = PAGE_SIZE - (start & ~PAGE_MASK);
+		entry->size = (size < nr_bytes) ? size : nr_bytes;
+
+		start += entry->size;
+		size -= entry->size;
+	}
+	return 0;
+
+ Error:
+	list_for_each_entry_safe(entry, next, &nvs_list, node) {
+		list_del(&entry->node);
+		kfree(entry);
+	}
+	return -ENOMEM;
+}
+
+/**
+ *	hibernate_nvs_free - free data pages allocated for saving NVS regions
+ */
+void hibernate_nvs_free(void)
+{
+	struct nvs_page *entry;
+
+	list_for_each_entry(entry, &nvs_list, node)
+		if (entry->data) {
+			free_page((unsigned long)entry->data);
+			entry->data = NULL;
+			if (entry->kaddr) {
+				iounmap(entry->kaddr);
+				entry->kaddr = NULL;
+			}
+		}
+}
+
+/**
+ *	hibernate_nvs_alloc - allocate memory necessary for saving NVS regions
+ */
+int hibernate_nvs_alloc(void)
+{
+	struct nvs_page *entry;
+
+	list_for_each_entry(entry, &nvs_list, node) {
+		entry->data = (void *)__get_free_page(GFP_KERNEL);
+		if (!entry->data) {
+			hibernate_nvs_free();
+			return -ENOMEM;
+		}
+	}
+	return 0;
+}
+
+/**
+ *	hibernate_nvs_save - save NVS memory regions
+ */
+void hibernate_nvs_save(void)
+{
+	struct nvs_page *entry;
+
+	printk(KERN_INFO "PM: Saving platform NVS memory\n");
+
+	list_for_each_entry(entry, &nvs_list, node)
+		if (entry->data) {
+			entry->kaddr = ioremap(entry->phys_start, entry->size);
+			memcpy(entry->data, entry->kaddr, entry->size);
+		}
+}
+
+/**
+ *	hibernate_nvs_restore - restore NVS memory regions
+ *
+ *	This function is going to be called with interrupts disabled, so it
+ *	cannot iounmap the virtual addresses used to access the NVS region.
+ */
+void hibernate_nvs_restore(void)
+{
+	struct nvs_page *entry;
+
+	printk(KERN_INFO "PM: Restoring platform NVS memory\n");
+
+	list_for_each_entry(entry, &nvs_list, node)
+		if (entry->data)
+			memcpy(entry->kaddr, entry->data, entry->size);
+}
diff --git a/kernel/profile.c b/kernel/profile.c
index dc41827fbfee..60adefb59b5e 100644
--- a/kernel/profile.c
+++ b/kernel/profile.c
@@ -544,7 +544,7 @@ static const struct file_operations proc_profile_operations = {
 };
 
 #ifdef CONFIG_SMP
-static inline void profile_nop(void *unused)
+static void profile_nop(void *unused)
 {
 }
 
diff --git a/kernel/rcuclassic.c b/kernel/rcuclassic.c
index 37f72e551542..e503a002f330 100644
--- a/kernel/rcuclassic.c
+++ b/kernel/rcuclassic.c
@@ -191,7 +191,7 @@ static void print_other_cpu_stall(struct rcu_ctrlblk *rcp)
 
 	/* OK, time to rat on our buddy... */
 
-	printk(KERN_ERR "RCU detected CPU stalls:");
+	printk(KERN_ERR "INFO: RCU detected CPU stalls:");
 	for_each_possible_cpu(cpu) {
 		if (cpu_isset(cpu, rcp->cpumask))
 			printk(" %d", cpu);
@@ -204,7 +204,7 @@ static void print_cpu_stall(struct rcu_ctrlblk *rcp)
 {
 	unsigned long flags;
 
-	printk(KERN_ERR "RCU detected CPU %d stall (t=%lu/%lu jiffies)\n",
+	printk(KERN_ERR "INFO: RCU detected CPU %d stall (t=%lu/%lu jiffies)\n",
 			smp_processor_id(), jiffies,
 			jiffies - rcp->gp_start);
 	dump_stack();
diff --git a/kernel/resource.c b/kernel/resource.c
index 4337063663ef..c251b0f4dc6b 100644
--- a/kernel/resource.c
+++ b/kernel/resource.c
@@ -623,7 +623,7 @@ resource_size_t resource_alignment(struct resource *res)
  */
 struct resource * __request_region(struct resource *parent,
 				   resource_size_t start, resource_size_t n,
-				   const char *name)
+				   const char *name, int flags)
 {
 	struct resource *res = kzalloc(sizeof(*res), GFP_KERNEL);
 
@@ -634,6 +634,7 @@ struct resource * __request_region(struct resource *parent,
 	res->start = start;
 	res->end = start + n - 1;
 	res->flags = IORESOURCE_BUSY;
+	res->flags |= flags;
 
 	write_lock(&resource_lock);
 
@@ -679,7 +680,7 @@ int __check_region(struct resource *parent, resource_size_t start,
 {
 	struct resource * res;
 
-	res = __request_region(parent, start, n, "check-region");
+	res = __request_region(parent, start, n, "check-region", 0);
 	if (!res)
 		return -EBUSY;
 
@@ -776,7 +777,7 @@ struct resource * __devm_request_region(struct device *dev,
 	dr->start = start;
 	dr->n = n;
 
-	res = __request_region(parent, start, n, name);
+	res = __request_region(parent, start, n, name, 0);
 	if (res)
 		devres_add(dev, dr);
 	else
@@ -867,3 +868,57 @@ int iomem_map_sanity_check(resource_size_t addr, unsigned long size)
 
 	return err;
 }
+
+#ifdef CONFIG_STRICT_DEVMEM
+static int strict_iomem_checks = 1;
+#else
+static int strict_iomem_checks;
+#endif
+
+/*
+ * check if an address is reserved in the iomem resource tree
+ * returns 1 if reserved, 0 if not reserved.
+ */
+int iomem_is_exclusive(u64 addr)
+{
+	struct resource *p = &iomem_resource;
+	int err = 0;
+	loff_t l;
+	int size = PAGE_SIZE;
+
+	if (!strict_iomem_checks)
+		return 0;
+
+	addr = addr & PAGE_MASK;
+
+	read_lock(&resource_lock);
+	for (p = p->child; p ; p = r_next(NULL, p, &l)) {
+		/*
+		 * We can probably skip the resources without
+		 * IORESOURCE_IO attribute?
+		 */
+		if (p->start >= addr + size)
+			break;
+		if (p->end < addr)
+			continue;
+		if (p->flags & IORESOURCE_BUSY &&
+		     p->flags & IORESOURCE_EXCLUSIVE) {
+			err = 1;
+			break;
+		}
+	}
+	read_unlock(&resource_lock);
+
+	return err;
+}
+
+static int __init strict_iomem(char *str)
+{
+	if (strstr(str, "relaxed"))
+		strict_iomem_checks = 0;
+	if (strstr(str, "strict"))
+		strict_iomem_checks = 1;
+	return 1;
+}
+
+__setup("iomem=", strict_iomem);
diff --git a/kernel/sched.c b/kernel/sched.c
index b7480fb5c3dc..301154778693 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -118,6 +118,12 @@
  */
 #define RUNTIME_INF	((u64)~0ULL)
 
+DEFINE_TRACE(sched_wait_task);
+DEFINE_TRACE(sched_wakeup);
+DEFINE_TRACE(sched_wakeup_new);
+DEFINE_TRACE(sched_switch);
+DEFINE_TRACE(sched_migrate_task);
+
 #ifdef CONFIG_SMP
 /*
  * Divide a load by a sched group cpu_power : (load / sg->__cpu_power)
@@ -261,6 +267,10 @@ struct task_group {
 	struct cgroup_subsys_state css;
 #endif
 
+#ifdef CONFIG_USER_SCHED
+	uid_t uid;
+#endif
+
 #ifdef CONFIG_FAIR_GROUP_SCHED
 	/* schedulable entities of this group on each cpu */
 	struct sched_entity **se;
@@ -286,6 +296,12 @@ struct task_group {
 
 #ifdef CONFIG_USER_SCHED
 
+/* Helper function to pass uid information to create_sched_user() */
+void set_tg_uid(struct user_struct *user)
+{
+	user->tg->uid = user->uid;
+}
+
 /*
  * Root task group.
  * 	Every UID task group (including init_task_group aka UID-0) will
@@ -703,45 +719,18 @@ static __read_mostly char *sched_feat_names[] = {
 
 #undef SCHED_FEAT
 
-static int sched_feat_open(struct inode *inode, struct file *filp)
-{
-	filp->private_data = inode->i_private;
-	return 0;
-}
-
-static ssize_t
-sched_feat_read(struct file *filp, char __user *ubuf,
-		size_t cnt, loff_t *ppos)
+static int sched_feat_show(struct seq_file *m, void *v)
 {
-	char *buf;
-	int r = 0;
-	int len = 0;
 	int i;
 
 	for (i = 0; sched_feat_names[i]; i++) {
-		len += strlen(sched_feat_names[i]);
-		len += 4;
+		if (!(sysctl_sched_features & (1UL << i)))
+			seq_puts(m, "NO_");
+		seq_printf(m, "%s ", sched_feat_names[i]);
 	}
+	seq_puts(m, "\n");
 
-	buf = kmalloc(len + 2, GFP_KERNEL);
-	if (!buf)
-		return -ENOMEM;
-
-	for (i = 0; sched_feat_names[i]; i++) {
-		if (sysctl_sched_features & (1UL << i))
-			r += sprintf(buf + r, "%s ", sched_feat_names[i]);
-		else
-			r += sprintf(buf + r, "NO_%s ", sched_feat_names[i]);
-	}
-
-	r += sprintf(buf + r, "\n");
-	WARN_ON(r >= len + 2);
-
-	r = simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
-
-	kfree(buf);
-
-	return r;
+	return 0;
 }
 
 static ssize_t
@@ -786,10 +775,17 @@ sched_feat_write(struct file *filp, const char __user *ubuf,
 	return cnt;
 }
 
+static int sched_feat_open(struct inode *inode, struct file *filp)
+{
+	return single_open(filp, sched_feat_show, NULL);
+}
+
 static struct file_operations sched_feat_fops = {
-	.open	= sched_feat_open,
-	.read	= sched_feat_read,
-	.write	= sched_feat_write,
+	.open		= sched_feat_open,
+	.write		= sched_feat_write,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
 };
 
 static __init int sched_init_debug(void)
@@ -1474,27 +1470,13 @@ static void
 update_group_shares_cpu(struct task_group *tg, int cpu,
 			unsigned long sd_shares, unsigned long sd_rq_weight)
 {
-	int boost = 0;
 	unsigned long shares;
 	unsigned long rq_weight;
 
 	if (!tg->se[cpu])
 		return;
 
-	rq_weight = tg->cfs_rq[cpu]->load.weight;
-
-	/*
-	 * If there are currently no tasks on the cpu pretend there is one of
-	 * average load so that when a new task gets to run here it will not
-	 * get delayed by group starvation.
-	 */
-	if (!rq_weight) {
-		boost = 1;
-		rq_weight = NICE_0_LOAD;
-	}
-
-	if (unlikely(rq_weight > sd_rq_weight))
-		rq_weight = sd_rq_weight;
+	rq_weight = tg->cfs_rq[cpu]->rq_weight;
 
 	/*
 	 *           \Sum shares * rq_weight
@@ -1502,7 +1484,7 @@ update_group_shares_cpu(struct task_group *tg, int cpu,
 	 *               \Sum rq_weight
 	 *
 	 */
-	shares = (sd_shares * rq_weight) / (sd_rq_weight + 1);
+	shares = (sd_shares * rq_weight) / sd_rq_weight;
 	shares = clamp_t(unsigned long, shares, MIN_SHARES, MAX_SHARES);
 
 	if (abs(shares - tg->se[cpu]->load.weight) >
@@ -1511,11 +1493,7 @@ update_group_shares_cpu(struct task_group *tg, int cpu,
 		unsigned long flags;
 
 		spin_lock_irqsave(&rq->lock, flags);
-		/*
-		 * record the actual number of shares, not the boosted amount.
-		 */
-		tg->cfs_rq[cpu]->shares = boost ? 0 : shares;
-		tg->cfs_rq[cpu]->rq_weight = rq_weight;
+		tg->cfs_rq[cpu]->shares = shares;
 
 		__set_se_shares(tg->se[cpu], shares);
 		spin_unlock_irqrestore(&rq->lock, flags);
@@ -1529,13 +1507,23 @@ update_group_shares_cpu(struct task_group *tg, int cpu,
  */
 static int tg_shares_up(struct task_group *tg, void *data)
 {
-	unsigned long rq_weight = 0;
+	unsigned long weight, rq_weight = 0;
 	unsigned long shares = 0;
 	struct sched_domain *sd = data;
 	int i;
 
 	for_each_cpu_mask(i, sd->span) {
-		rq_weight += tg->cfs_rq[i]->load.weight;
+		/*
+		 * If there are currently no tasks on the cpu pretend there
+		 * is one of average load so that when a new task gets to
+		 * run here it will not get delayed by group starvation.
+		 */
+		weight = tg->cfs_rq[i]->load.weight;
+		if (!weight)
+			weight = NICE_0_LOAD;
+
+		tg->cfs_rq[i]->rq_weight = weight;
+		rq_weight += weight;
 		shares += tg->cfs_rq[i]->shares;
 	}
 
@@ -1545,9 +1533,6 @@ static int tg_shares_up(struct task_group *tg, void *data)
 	if (!sd->parent || !(sd->parent->flags & SD_LOAD_BALANCE))
 		shares = tg->shares;
 
-	if (!rq_weight)
-		rq_weight = cpus_weight(sd->span) * NICE_0_LOAD;
-
 	for_each_cpu_mask(i, sd->span)
 		update_group_shares_cpu(tg, i, shares, rq_weight);
 
@@ -1612,6 +1597,39 @@ static inline void update_shares_locked(struct rq *rq, struct sched_domain *sd)
 
 #endif
 
+/*
+ * double_lock_balance - lock the busiest runqueue, this_rq is locked already.
+ */
+static int double_lock_balance(struct rq *this_rq, struct rq *busiest)
+	__releases(this_rq->lock)
+	__acquires(busiest->lock)
+	__acquires(this_rq->lock)
+{
+	int ret = 0;
+
+	if (unlikely(!irqs_disabled())) {
+		/* printk() doesn't work good under rq->lock */
+		spin_unlock(&this_rq->lock);
+		BUG_ON(1);
+	}
+	if (unlikely(!spin_trylock(&busiest->lock))) {
+		if (busiest < this_rq) {
+			spin_unlock(&this_rq->lock);
+			spin_lock(&busiest->lock);
+			spin_lock_nested(&this_rq->lock, SINGLE_DEPTH_NESTING);
+			ret = 1;
+		} else
+			spin_lock_nested(&busiest->lock, SINGLE_DEPTH_NESTING);
+	}
+	return ret;
+}
+
+static inline void double_unlock_balance(struct rq *this_rq, struct rq *busiest)
+	__releases(busiest->lock)
+{
+	spin_unlock(&busiest->lock);
+	lock_set_subclass(&this_rq->lock.dep_map, 0, _RET_IP_);
+}
 #endif
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
@@ -2812,40 +2830,6 @@ static void double_rq_unlock(struct rq *rq1, struct rq *rq2)
 }
 
 /*
- * double_lock_balance - lock the busiest runqueue, this_rq is locked already.
- */
-static int double_lock_balance(struct rq *this_rq, struct rq *busiest)
-	__releases(this_rq->lock)
-	__acquires(busiest->lock)
-	__acquires(this_rq->lock)
-{
-	int ret = 0;
-
-	if (unlikely(!irqs_disabled())) {
-		/* printk() doesn't work good under rq->lock */
-		spin_unlock(&this_rq->lock);
-		BUG_ON(1);
-	}
-	if (unlikely(!spin_trylock(&busiest->lock))) {
-		if (busiest < this_rq) {
-			spin_unlock(&this_rq->lock);
-			spin_lock(&busiest->lock);
-			spin_lock_nested(&this_rq->lock, SINGLE_DEPTH_NESTING);
-			ret = 1;
-		} else
-			spin_lock_nested(&busiest->lock, SINGLE_DEPTH_NESTING);
-	}
-	return ret;
-}
-
-static void double_unlock_balance(struct rq *this_rq, struct rq *busiest)
-	__releases(busiest->lock)
-{
-	spin_unlock(&busiest->lock);
-	lock_set_subclass(&this_rq->lock.dep_map, 0, _RET_IP_);
-}
-
-/*
  * If dest_cpu is allowed for this process, migrate the task to it.
  * This is accomplished by forcing the cpu_allowed mask to only
  * allow dest_cpu, which will force the cpu onto dest_cpu. Then
@@ -4203,7 +4187,6 @@ void account_steal_time(struct task_struct *p, cputime_t steal)
 
 	if (p == rq->idle) {
 		p->stime = cputime_add(p->stime, steal);
-		account_group_system_time(p, steal);
 		if (atomic_read(&rq->nr_iowait) > 0)
 			cpustat->iowait = cputime64_add(cpustat->iowait, tmp);
 		else
@@ -4339,7 +4322,7 @@ void __kprobes sub_preempt_count(int val)
 	/*
 	 * Underflow?
 	 */
-	if (DEBUG_LOCKS_WARN_ON(val > preempt_count()))
+       if (DEBUG_LOCKS_WARN_ON(val > preempt_count() - (!!kernel_locked())))
 		return;
 	/*
 	 * Is the spinlock portion underflowing?
@@ -5805,12 +5788,7 @@ void sched_show_task(struct task_struct *p)
 		printk(KERN_CONT " %016lx ", thread_saved_pc(p));
 #endif
 #ifdef CONFIG_DEBUG_STACK_USAGE
-	{
-		unsigned long *n = end_of_stack(p);
-		while (!*n)
-			n++;
-		free = (unsigned long)n - (unsigned long)end_of_stack(p);
-	}
+	free = stack_not_used(p);
 #endif
 	printk(KERN_CONT "%5lu %5d %6d\n", free,
 		task_pid_nr(p), task_pid_nr(p->real_parent));
@@ -5896,6 +5874,7 @@ void __cpuinit init_idle(struct task_struct *idle, int cpu)
 	 * The idle tasks have their own, simple scheduling class:
 	 */
 	idle->sched_class = &idle_sched_class;
+	ftrace_retfunc_init_task(idle);
 }
 
 /*
@@ -6126,7 +6105,6 @@ static int __migrate_task_irq(struct task_struct *p, int src_cpu, int dest_cpu)
 
 /*
  * Figure out where task on dead CPU should go, use force if necessary.
- * NOTE: interrupts should be disabled by the caller
  */
 static void move_task_off_dead_cpu(int dead_cpu, struct task_struct *p)
 {
@@ -6636,28 +6614,6 @@ early_initcall(migration_init);
 
 #ifdef CONFIG_SCHED_DEBUG
 
-static inline const char *sd_level_to_string(enum sched_domain_level lvl)
-{
-	switch (lvl) {
-	case SD_LV_NONE:
-			return "NONE";
-	case SD_LV_SIBLING:
-			return "SIBLING";
-	case SD_LV_MC:
-			return "MC";
-	case SD_LV_CPU:
-			return "CPU";
-	case SD_LV_NODE:
-			return "NODE";
-	case SD_LV_ALLNODES:
-			return "ALLNODES";
-	case SD_LV_MAX:
-			return "MAX";
-
-	}
-	return "MAX";
-}
-
 static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level,
 				  cpumask_t *groupmask)
 {
@@ -6677,8 +6633,7 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level,
 		return -1;
 	}
 
-	printk(KERN_CONT "span %s level %s\n",
-		str, sd_level_to_string(sd->level));
+	printk(KERN_CONT "span %s level %s\n", str, sd->name);
 
 	if (!cpu_isset(cpu, sd->span)) {
 		printk(KERN_ERR "ERROR: domain->span does not contain "
@@ -7334,13 +7289,21 @@ struct allmasks {
 };
 
 #if	NR_CPUS > 128
-#define	SCHED_CPUMASK_ALLOC		1
-#define	SCHED_CPUMASK_FREE(v)		kfree(v)
-#define	SCHED_CPUMASK_DECLARE(v)	struct allmasks *v
+#define SCHED_CPUMASK_DECLARE(v)	struct allmasks *v
+static inline void sched_cpumask_alloc(struct allmasks **masks)
+{
+	*masks = kmalloc(sizeof(**masks), GFP_KERNEL);
+}
+static inline void sched_cpumask_free(struct allmasks *masks)
+{
+	kfree(masks);
+}
 #else
-#define	SCHED_CPUMASK_ALLOC		0
-#define	SCHED_CPUMASK_FREE(v)
-#define	SCHED_CPUMASK_DECLARE(v)	struct allmasks _v, *v = &_v
+#define SCHED_CPUMASK_DECLARE(v)	struct allmasks _v, *v = &_v
+static inline void sched_cpumask_alloc(struct allmasks **masks)
+{ }
+static inline void sched_cpumask_free(struct allmasks *masks)
+{ }
 #endif
 
 #define	SCHED_CPUMASK_VAR(v, a) 	cpumask_t *v = (cpumask_t *) \
@@ -7416,9 +7379,8 @@ static int __build_sched_domains(const cpumask_t *cpu_map,
 		return -ENOMEM;
 	}
 
-#if SCHED_CPUMASK_ALLOC
 	/* get space for all scratch cpumask variables */
-	allmasks = kmalloc(sizeof(*allmasks), GFP_KERNEL);
+	sched_cpumask_alloc(&allmasks);
 	if (!allmasks) {
 		printk(KERN_WARNING "Cannot alloc cpumask array\n");
 		kfree(rd);
@@ -7427,7 +7389,7 @@ static int __build_sched_domains(const cpumask_t *cpu_map,
 #endif
 		return -ENOMEM;
 	}
-#endif
+
 	tmpmask = (cpumask_t *)allmasks;
 
 
@@ -7681,13 +7643,13 @@ static int __build_sched_domains(const cpumask_t *cpu_map,
 		cpu_attach_domain(sd, rd, i);
 	}
 
-	SCHED_CPUMASK_FREE((void *)allmasks);
+	sched_cpumask_free(allmasks);
 	return 0;
 
 #ifdef CONFIG_NUMA
 error:
 	free_sched_groups(cpu_map, tmpmask);
-	SCHED_CPUMASK_FREE((void *)allmasks);
+	sched_cpumask_free(allmasks);
 	kfree(rd);
 	return -ENOMEM;
 #endif
@@ -7751,8 +7713,6 @@ static void detach_destroy_domains(const cpumask_t *cpu_map)
 	cpumask_t tmpmask;
 	int i;
 
-	unregister_sched_domain_sysctl();
-
 	for_each_cpu_mask_nr(i, *cpu_map)
 		cpu_attach_domain(NULL, &def_root_domain, i);
 	synchronize_sched();
@@ -7830,7 +7790,7 @@ match1:
 		ndoms_cur = 0;
 		doms_new = &fallback_doms;
 		cpus_andnot(doms_new[0], cpu_online_map, cpu_isolated_map);
-		dattr_new = NULL;
+		WARN_ON_ONCE(dattr_new);
 	}
 
 	/* Build new domains */
@@ -8490,7 +8450,7 @@ static
 int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent)
 {
 	struct cfs_rq *cfs_rq;
-	struct sched_entity *se, *parent_se;
+	struct sched_entity *se;
 	struct rq *rq;
 	int i;
 
@@ -8506,18 +8466,17 @@ int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent)
 	for_each_possible_cpu(i) {
 		rq = cpu_rq(i);
 
-		cfs_rq = kmalloc_node(sizeof(struct cfs_rq),
-				GFP_KERNEL|__GFP_ZERO, cpu_to_node(i));
+		cfs_rq = kzalloc_node(sizeof(struct cfs_rq),
+				      GFP_KERNEL, cpu_to_node(i));
 		if (!cfs_rq)
 			goto err;
 
-		se = kmalloc_node(sizeof(struct sched_entity),
-				GFP_KERNEL|__GFP_ZERO, cpu_to_node(i));
+		se = kzalloc_node(sizeof(struct sched_entity),
+				  GFP_KERNEL, cpu_to_node(i));
 		if (!se)
 			goto err;
 
-		parent_se = parent ? parent->se[i] : NULL;
-		init_tg_cfs_entry(tg, cfs_rq, se, i, 0, parent_se);
+		init_tg_cfs_entry(tg, cfs_rq, se, i, 0, parent->se[i]);
 	}
 
 	return 1;
@@ -8578,7 +8537,7 @@ static
 int alloc_rt_sched_group(struct task_group *tg, struct task_group *parent)
 {
 	struct rt_rq *rt_rq;
-	struct sched_rt_entity *rt_se, *parent_se;
+	struct sched_rt_entity *rt_se;
 	struct rq *rq;
 	int i;
 
@@ -8595,18 +8554,17 @@ int alloc_rt_sched_group(struct task_group *tg, struct task_group *parent)
 	for_each_possible_cpu(i) {
 		rq = cpu_rq(i);
 
-		rt_rq = kmalloc_node(sizeof(struct rt_rq),
-				GFP_KERNEL|__GFP_ZERO, cpu_to_node(i));
+		rt_rq = kzalloc_node(sizeof(struct rt_rq),
+				     GFP_KERNEL, cpu_to_node(i));
 		if (!rt_rq)
 			goto err;
 
-		rt_se = kmalloc_node(sizeof(struct sched_rt_entity),
-				GFP_KERNEL|__GFP_ZERO, cpu_to_node(i));
+		rt_se = kzalloc_node(sizeof(struct sched_rt_entity),
+				     GFP_KERNEL, cpu_to_node(i));
 		if (!rt_se)
 			goto err;
 
-		parent_se = parent ? parent->rt_se[i] : NULL;
-		init_tg_rt_entry(tg, rt_rq, rt_se, i, 0, parent_se);
+		init_tg_rt_entry(tg, rt_rq, rt_se, i, 0, parent->rt_se[i]);
 	}
 
 	return 1;
@@ -9249,11 +9207,12 @@ struct cgroup_subsys cpu_cgroup_subsys = {
  * (balbir@in.ibm.com).
  */
 
-/* track cpu usage of a group of tasks */
+/* track cpu usage of a group of tasks and its child groups */
 struct cpuacct {
 	struct cgroup_subsys_state css;
 	/* cpuusage holds pointer to a u64-type object on every cpu */
 	u64 *cpuusage;
+	struct cpuacct *parent;
 };
 
 struct cgroup_subsys cpuacct_subsys;
@@ -9287,6 +9246,9 @@ static struct cgroup_subsys_state *cpuacct_create(
 		return ERR_PTR(-ENOMEM);
 	}
 
+	if (cgrp->parent)
+		ca->parent = cgroup_ca(cgrp->parent);
+
 	return &ca->css;
 }
 
@@ -9366,14 +9328,16 @@ static int cpuacct_populate(struct cgroup_subsys *ss, struct cgroup *cgrp)
 static void cpuacct_charge(struct task_struct *tsk, u64 cputime)
 {
 	struct cpuacct *ca;
+	int cpu;
 
 	if (!cpuacct_subsys.active)
 		return;
 
+	cpu = task_cpu(tsk);
 	ca = task_ca(tsk);
-	if (ca) {
-		u64 *cpuusage = percpu_ptr(ca->cpuusage, task_cpu(tsk));
 
+	for (; ca; ca = ca->parent) {
+		u64 *cpuusage = percpu_ptr(ca->cpuusage, cpu);
 		*cpuusage += cputime;
 	}
 }
diff --git a/kernel/sched_debug.c b/kernel/sched_debug.c
index 26ed8e3d1c15..4293cfa9681d 100644
--- a/kernel/sched_debug.c
+++ b/kernel/sched_debug.c
@@ -53,6 +53,40 @@ static unsigned long nsec_low(unsigned long long nsec)
 
 #define SPLIT_NS(x) nsec_high(x), nsec_low(x)
 
+#ifdef CONFIG_FAIR_GROUP_SCHED
+static void print_cfs_group_stats(struct seq_file *m, int cpu,
+		struct task_group *tg)
+{
+	struct sched_entity *se = tg->se[cpu];
+	if (!se)
+		return;
+
+#define P(F) \
+	SEQ_printf(m, "  .%-30s: %lld\n", #F, (long long)F)
+#define PN(F) \
+	SEQ_printf(m, "  .%-30s: %lld.%06ld\n", #F, SPLIT_NS((long long)F))
+
+	PN(se->exec_start);
+	PN(se->vruntime);
+	PN(se->sum_exec_runtime);
+#ifdef CONFIG_SCHEDSTATS
+	PN(se->wait_start);
+	PN(se->sleep_start);
+	PN(se->block_start);
+	PN(se->sleep_max);
+	PN(se->block_max);
+	PN(se->exec_max);
+	PN(se->slice_max);
+	PN(se->wait_max);
+	PN(se->wait_sum);
+	P(se->wait_count);
+#endif
+	P(se->load.weight);
+#undef PN
+#undef P
+}
+#endif
+
 static void
 print_task(struct seq_file *m, struct rq *rq, struct task_struct *p)
 {
@@ -121,20 +155,19 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
 
 #if defined(CONFIG_CGROUP_SCHED) && defined(CONFIG_FAIR_GROUP_SCHED)
 	char path[128] = "";
-	struct cgroup *cgroup = NULL;
 	struct task_group *tg = cfs_rq->tg;
 
-	if (tg)
-		cgroup = tg->css.cgroup;
-
-	if (cgroup)
-		cgroup_path(cgroup, path, sizeof(path));
+	cgroup_path(tg->css.cgroup, path, sizeof(path));
 
 	SEQ_printf(m, "\ncfs_rq[%d]:%s\n", cpu, path);
+#elif defined(CONFIG_USER_SCHED) && defined(CONFIG_FAIR_GROUP_SCHED)
+	{
+		uid_t uid = cfs_rq->tg->uid;
+		SEQ_printf(m, "\ncfs_rq[%d] for UID: %u\n", cpu, uid);
+	}
 #else
 	SEQ_printf(m, "\ncfs_rq[%d]:\n", cpu);
 #endif
-
 	SEQ_printf(m, "  .%-30s: %Ld.%06ld\n", "exec_clock",
 			SPLIT_NS(cfs_rq->exec_clock));
 
@@ -168,6 +201,7 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
 #ifdef CONFIG_SMP
 	SEQ_printf(m, "  .%-30s: %lu\n", "shares", cfs_rq->shares);
 #endif
+	print_cfs_group_stats(m, cpu, cfs_rq->tg);
 #endif
 }
 
@@ -175,14 +209,9 @@ void print_rt_rq(struct seq_file *m, int cpu, struct rt_rq *rt_rq)
 {
 #if defined(CONFIG_CGROUP_SCHED) && defined(CONFIG_RT_GROUP_SCHED)
 	char path[128] = "";
-	struct cgroup *cgroup = NULL;
 	struct task_group *tg = rt_rq->tg;
 
-	if (tg)
-		cgroup = tg->css.cgroup;
-
-	if (cgroup)
-		cgroup_path(cgroup, path, sizeof(path));
+	cgroup_path(tg->css.cgroup, path, sizeof(path));
 
 	SEQ_printf(m, "\nrt_rq[%d]:%s\n", cpu, path);
 #else
@@ -272,7 +301,7 @@ static int sched_debug_show(struct seq_file *m, void *v)
 	u64 now = ktime_to_ns(ktime_get());
 	int cpu;
 
-	SEQ_printf(m, "Sched Debug Version: v0.07, %s %.*s\n",
+	SEQ_printf(m, "Sched Debug Version: v0.08, %s %.*s\n",
 		init_utsname()->release,
 		(int)strcspn(init_utsname()->version, " "),
 		init_utsname()->version);
diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c
index d9ba9d5f99d6..587a16e2a8f5 100644
--- a/kernel/sched_rt.c
+++ b/kernel/sched_rt.c
@@ -537,13 +537,13 @@ static void update_curr_rt(struct rq *rq)
 	for_each_sched_rt_entity(rt_se) {
 		rt_rq = rt_rq_of_se(rt_se);
 
-		spin_lock(&rt_rq->rt_runtime_lock);
 		if (sched_rt_runtime(rt_rq) != RUNTIME_INF) {
+			spin_lock(&rt_rq->rt_runtime_lock);
 			rt_rq->rt_time += delta_exec;
 			if (sched_rt_runtime_exceeded(rt_rq))
 				resched_task(curr);
+			spin_unlock(&rt_rq->rt_runtime_lock);
 		}
-		spin_unlock(&rt_rq->rt_runtime_lock);
 	}
 }
 
@@ -909,9 +909,6 @@ static void put_prev_task_rt(struct rq *rq, struct task_struct *p)
 /* Only try algorithms three times */
 #define RT_MAX_TRIES 3
 
-static int double_lock_balance(struct rq *this_rq, struct rq *busiest);
-static void double_unlock_balance(struct rq *this_rq, struct rq *busiest);
-
 static void deactivate_task(struct rq *rq, struct task_struct *p, int sleep);
 
 static int pick_rt_task(struct rq *rq, struct task_struct *p, int cpu)
diff --git a/kernel/signal.c b/kernel/signal.c
index 4530fc654455..e9afe63da24b 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -41,6 +41,8 @@
 
 static struct kmem_cache *sigqueue_cachep;
 
+DEFINE_TRACE(sched_signal_send);
+
 static void __user *sig_handler(struct task_struct *t, int sig)
 {
 	return t->sighand->action[sig - 1].sa.sa_handler;
diff --git a/kernel/softirq.c b/kernel/softirq.c
index e7c69a720d69..8d9934b4162a 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -102,20 +102,6 @@ void local_bh_disable(void)
 
 EXPORT_SYMBOL(local_bh_disable);
 
-void __local_bh_enable(void)
-{
-	WARN_ON_ONCE(in_irq());
-
-	/*
-	 * softirqs should never be enabled by __local_bh_enable(),
-	 * it always nests inside local_bh_enable() sections:
-	 */
-	WARN_ON_ONCE(softirq_count() == SOFTIRQ_OFFSET);
-
-	sub_preempt_count(SOFTIRQ_OFFSET);
-}
-EXPORT_SYMBOL_GPL(__local_bh_enable);
-
 /*
  * Special-case - softirqs can safely be enabled in
  * cond_resched_softirq(), or by __do_softirq(),
diff --git a/kernel/softlockup.c b/kernel/softlockup.c
index 3953e4aed733..1ab790c67b17 100644
--- a/kernel/softlockup.c
+++ b/kernel/softlockup.c
@@ -164,7 +164,7 @@ unsigned long __read_mostly sysctl_hung_task_check_count = 1024;
 /*
  * Zero means infinite timeout - no checking done:
  */
-unsigned long __read_mostly sysctl_hung_task_timeout_secs = 120;
+unsigned long __read_mostly sysctl_hung_task_timeout_secs = 480;
 
 unsigned long __read_mostly sysctl_hung_task_warnings = 10;
 
@@ -188,7 +188,7 @@ static void check_hung_task(struct task_struct *t, unsigned long now)
 	if ((long)(now - t->last_switch_timestamp) <
 					sysctl_hung_task_timeout_secs)
 		return;
-	if (sysctl_hung_task_warnings < 0)
+	if (!sysctl_hung_task_warnings)
 		return;
 	sysctl_hung_task_warnings--;
 
diff --git a/kernel/sys.c b/kernel/sys.c
index 31deba8f7d16..5fc3a0cfb994 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -858,8 +858,8 @@ void do_sys_times(struct tms *tms)
 	struct task_cputime cputime;
 	cputime_t cutime, cstime;
 
-	spin_lock_irq(&current->sighand->siglock);
 	thread_group_cputime(current, &cputime);
+	spin_lock_irq(&current->sighand->siglock);
 	cutime = current->signal->cutime;
 	cstime = current->signal->cstime;
 	spin_unlock_irq(&current->sighand->siglock);
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 3d56fe7570da..fb33a076d850 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -121,6 +121,10 @@ extern int sg_big_buff;
 #include <asm/system.h>
 #endif
 
+#ifdef CONFIG_SPARC64
+extern int sysctl_tsb_ratio;
+#endif
+
 #ifdef __hppa__
 extern int pwrsw_enabled;
 extern int unaligned_enabled;
@@ -451,6 +455,16 @@ static struct ctl_table kern_table[] = {
 		.proc_handler	= &proc_dointvec,
 	},
 #endif
+#ifdef CONFIG_SPARC64
+	{
+		.ctl_name	= CTL_UNNUMBERED,
+		.procname	= "tsb-ratio",
+		.data		= &sysctl_tsb_ratio,
+		.maxlen		= sizeof (int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec,
+	},
+#endif
 #ifdef __hppa__
 	{
 		.ctl_name	= KERN_HPPA_PWRSW,
@@ -487,6 +501,16 @@ static struct ctl_table kern_table[] = {
 		.proc_handler	= &ftrace_enable_sysctl,
 	},
 #endif
+#ifdef CONFIG_TRACING
+	{
+		.ctl_name	= CTL_UNNUMBERED,
+		.procname	= "ftrace_dump_on_oops",
+		.data		= &ftrace_dump_on_oops,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec,
+	},
+#endif
 #ifdef CONFIG_MODULES
 	{
 		.ctl_name	= KERN_MODPROBE,
diff --git a/kernel/sysctl_check.c b/kernel/sysctl_check.c
index c35da23ab8fb..fafeb48f27c0 100644
--- a/kernel/sysctl_check.c
+++ b/kernel/sysctl_check.c
@@ -730,7 +730,6 @@ static const struct trans_ctl_table trans_fs_quota_table[] = {
 };
 
 static const struct trans_ctl_table trans_fs_xfs_table[] = {
-	{ XFS_RESTRICT_CHOWN,	"restrict_chown" },
 	{ XFS_SGID_INHERIT,	"irix_sgid_inherit" },
 	{ XFS_SYMLINK_MODE,	"irix_symlink_mode" },
 	{ XFS_PANIC_MASK,	"panic_mask" },
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index e7acfb482a68..fa05e88aa76f 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -518,6 +518,28 @@ void update_wall_time(void)
 	/* correct the clock when NTP error is too big */
 	clocksource_adjust(offset);
 
+	/*
+	 * Since in the loop above, we accumulate any amount of time
+	 * in xtime_nsec over a second into xtime.tv_sec, its possible for
+	 * xtime_nsec to be fairly small after the loop. Further, if we're
+	 * slightly speeding the clocksource up in clocksource_adjust(),
+	 * its possible the required corrective factor to xtime_nsec could
+	 * cause it to underflow.
+	 *
+	 * Now, we cannot simply roll the accumulated second back, since
+	 * the NTP subsystem has been notified via second_overflow. So
+	 * instead we push xtime_nsec forward by the amount we underflowed,
+	 * and add that amount into the error.
+	 *
+	 * We'll correct this error next time through this function, when
+	 * xtime_nsec is not as small.
+	 */
+	if (unlikely((s64)clock->xtime_nsec < 0)) {
+		s64 neg = -(s64)clock->xtime_nsec;
+		clock->xtime_nsec = 0;
+		clock->error += neg << (NTP_SCALE_SHIFT - clock->shift);
+	}
+
 	/* store full nanoseconds into xtime after rounding it up and
 	 * add the remainder to the error difference.
 	 */
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index 33dbefd471e8..9cbf7761f498 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -3,12 +3,25 @@
 #  select HAVE_FUNCTION_TRACER:
 #
 
+config USER_STACKTRACE_SUPPORT
+	bool
+
 config NOP_TRACER
 	bool
 
 config HAVE_FUNCTION_TRACER
 	bool
 
+config HAVE_FUNCTION_RET_TRACER
+	bool
+
+config HAVE_FUNCTION_TRACE_MCOUNT_TEST
+	bool
+	help
+	 This gets selected when the arch tests the function_trace_stop
+	 variable at the mcount call site. Otherwise, this variable
+	 is tested by the called function.
+
 config HAVE_DYNAMIC_FTRACE
 	bool
 
@@ -47,6 +60,16 @@ config FUNCTION_TRACER
 	  (the bootup default), then the overhead of the instructions is very
 	  small and not measurable even in micro-benchmarks.
 
+config FUNCTION_RET_TRACER
+	bool "Kernel Function return Tracer"
+	depends on HAVE_FUNCTION_RET_TRACER
+	depends on FUNCTION_TRACER
+	help
+	  Enable the kernel to trace a function at its return.
+	  It's first purpose is to trace the duration of functions.
+	  This is done by setting the current return address on the thread
+	  info structure of the current task.
+
 config IRQSOFF_TRACER
 	bool "Interrupts-off Latency Tracer"
 	default n
@@ -138,6 +161,59 @@ config BOOT_TRACER
 	    selected, because the self-tests are an initcall as well and that
 	    would invalidate the boot trace. )
 
+config TRACE_BRANCH_PROFILING
+	bool "Trace likely/unlikely profiler"
+	depends on DEBUG_KERNEL
+	select TRACING
+	help
+	  This tracer profiles all the the likely and unlikely macros
+	  in the kernel. It will display the results in:
+
+	  /debugfs/tracing/profile_annotated_branch
+
+	  Note: this will add a significant overhead, only turn this
+	  on if you need to profile the system's use of these macros.
+
+	  Say N if unsure.
+
+config PROFILE_ALL_BRANCHES
+	bool "Profile all if conditionals"
+	depends on TRACE_BRANCH_PROFILING
+	help
+	  This tracer profiles all branch conditions. Every if ()
+	  taken in the kernel is recorded whether it hit or miss.
+	  The results will be displayed in:
+
+	  /debugfs/tracing/profile_branch
+
+	  This configuration, when enabled, will impose a great overhead
+	  on the system. This should only be enabled when the system
+	  is to be analyzed
+
+	  Say N if unsure.
+
+config TRACING_BRANCHES
+	bool
+	help
+	  Selected by tracers that will trace the likely and unlikely
+	  conditions. This prevents the tracers themselves from being
+	  profiled. Profiling the tracing infrastructure can only happen
+	  when the likelys and unlikelys are not being traced.
+
+config BRANCH_TRACER
+	bool "Trace likely/unlikely instances"
+	depends on TRACE_BRANCH_PROFILING
+	select TRACING_BRANCHES
+	help
+	  This traces the events of likely and unlikely condition
+	  calls in the kernel.  The difference between this and the
+	  "Trace likely/unlikely profiler" is that this is not a
+	  histogram of the callers, but actually places the calling
+	  events into a running trace buffer to see when and where the
+	  events happened, as well as their results.
+
+	  Say N if unsure.
+
 config STACK_TRACER
 	bool "Trace max stack"
 	depends on HAVE_FUNCTION_TRACER
diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile
index c8228b1a49e9..1a8c9259dc69 100644
--- a/kernel/trace/Makefile
+++ b/kernel/trace/Makefile
@@ -10,6 +10,11 @@ CFLAGS_trace_selftest_dynamic.o = -pg
 obj-y += trace_selftest_dynamic.o
 endif
 
+# If unlikely tracing is enabled, do not trace these files
+ifdef CONFIG_TRACING_BRANCHES
+KBUILD_CFLAGS += -DDISABLE_BRANCH_PROFILING
+endif
+
 obj-$(CONFIG_FUNCTION_TRACER) += libftrace.o
 obj-$(CONFIG_RING_BUFFER) += ring_buffer.o
 
@@ -24,5 +29,7 @@ obj-$(CONFIG_NOP_TRACER) += trace_nop.o
 obj-$(CONFIG_STACK_TRACER) += trace_stack.o
 obj-$(CONFIG_MMIOTRACE) += trace_mmiotrace.o
 obj-$(CONFIG_BOOT_TRACER) += trace_boot.o
+obj-$(CONFIG_FUNCTION_RET_TRACER) += trace_functions_return.o
+obj-$(CONFIG_TRACE_BRANCH_PROFILING) += trace_branch.o
 
 libftrace-y := ftrace.o
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 78db083390f0..53042f118f23 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -47,6 +47,12 @@
 int ftrace_enabled __read_mostly;
 static int last_ftrace_enabled;
 
+/* Quick disabling of function tracer. */
+int function_trace_stop;
+
+/* By default, current tracing type is normal tracing. */
+enum ftrace_tracing_type_t ftrace_tracing_type = FTRACE_TYPE_ENTER;
+
 /*
  * ftrace_disabled is set when an anomaly is discovered.
  * ftrace_disabled is much stronger than ftrace_enabled.
@@ -63,6 +69,7 @@ static struct ftrace_ops ftrace_list_end __read_mostly =
 
 static struct ftrace_ops *ftrace_list __read_mostly = &ftrace_list_end;
 ftrace_func_t ftrace_trace_function __read_mostly = ftrace_stub;
+ftrace_func_t __ftrace_trace_function __read_mostly = ftrace_stub;
 
 static void ftrace_list_func(unsigned long ip, unsigned long parent_ip)
 {
@@ -88,8 +95,23 @@ static void ftrace_list_func(unsigned long ip, unsigned long parent_ip)
 void clear_ftrace_function(void)
 {
 	ftrace_trace_function = ftrace_stub;
+	__ftrace_trace_function = ftrace_stub;
 }
 
+#ifndef CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST
+/*
+ * For those archs that do not test ftrace_trace_stop in their
+ * mcount call site, we need to do it from C.
+ */
+static void ftrace_test_stop_func(unsigned long ip, unsigned long parent_ip)
+{
+	if (function_trace_stop)
+		return;
+
+	__ftrace_trace_function(ip, parent_ip);
+}
+#endif
+
 static int __register_ftrace_function(struct ftrace_ops *ops)
 {
 	/* should not be called from interrupt context */
@@ -110,10 +132,18 @@ static int __register_ftrace_function(struct ftrace_ops *ops)
 		 * For one func, simply call it directly.
 		 * For more than one func, call the chain.
 		 */
+#ifdef CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST
 		if (ops->next == &ftrace_list_end)
 			ftrace_trace_function = ops->func;
 		else
 			ftrace_trace_function = ftrace_list_func;
+#else
+		if (ops->next == &ftrace_list_end)
+			__ftrace_trace_function = ops->func;
+		else
+			__ftrace_trace_function = ftrace_list_func;
+		ftrace_trace_function = ftrace_test_stop_func;
+#endif
 	}
 
 	spin_unlock(&ftrace_lock);
@@ -152,8 +182,7 @@ static int __unregister_ftrace_function(struct ftrace_ops *ops)
 
 	if (ftrace_enabled) {
 		/* If we only have one func left, then call that directly */
-		if (ftrace_list == &ftrace_list_end ||
-		    ftrace_list->next == &ftrace_list_end)
+		if (ftrace_list->next == &ftrace_list_end)
 			ftrace_trace_function = ftrace_list->func;
 	}
 
@@ -308,7 +337,7 @@ ftrace_record_ip(unsigned long ip)
 {
 	struct dyn_ftrace *rec;
 
-	if (!ftrace_enabled || ftrace_disabled)
+	if (ftrace_disabled)
 		return NULL;
 
 	rec = ftrace_alloc_dyn_node(ip);
@@ -322,14 +351,58 @@ ftrace_record_ip(unsigned long ip)
 	return rec;
 }
 
-#define FTRACE_ADDR ((long)(ftrace_caller))
+static void print_ip_ins(const char *fmt, unsigned char *p)
+{
+	int i;
+
+	printk(KERN_CONT "%s", fmt);
+
+	for (i = 0; i < MCOUNT_INSN_SIZE; i++)
+		printk(KERN_CONT "%s%02x", i ? ":" : "", p[i]);
+}
+
+static void ftrace_bug(int failed, unsigned long ip)
+{
+	switch (failed) {
+	case -EFAULT:
+		FTRACE_WARN_ON_ONCE(1);
+		pr_info("ftrace faulted on modifying ");
+		print_ip_sym(ip);
+		break;
+	case -EINVAL:
+		FTRACE_WARN_ON_ONCE(1);
+		pr_info("ftrace failed to modify ");
+		print_ip_sym(ip);
+		print_ip_ins(" actual: ", (unsigned char *)ip);
+		printk(KERN_CONT "\n");
+		break;
+	case -EPERM:
+		FTRACE_WARN_ON_ONCE(1);
+		pr_info("ftrace faulted on writing ");
+		print_ip_sym(ip);
+		break;
+	default:
+		FTRACE_WARN_ON_ONCE(1);
+		pr_info("ftrace faulted on unknown error ");
+		print_ip_sym(ip);
+	}
+}
+
 
 static int
-__ftrace_replace_code(struct dyn_ftrace *rec,
-		      unsigned char *nop, int enable)
+__ftrace_replace_code(struct dyn_ftrace *rec, int enable)
 {
 	unsigned long ip, fl;
-	unsigned char *call, *old, *new;
+	unsigned long ftrace_addr;
+
+#ifdef CONFIG_FUNCTION_RET_TRACER
+	if (ftrace_tracing_type == FTRACE_TYPE_ENTER)
+		ftrace_addr = (unsigned long)ftrace_caller;
+	else
+		ftrace_addr = (unsigned long)ftrace_return_caller;
+#else
+	ftrace_addr = (unsigned long)ftrace_caller;
+#endif
 
 	ip = rec->ip;
 
@@ -388,34 +461,28 @@ __ftrace_replace_code(struct dyn_ftrace *rec,
 		}
 	}
 
-	call = ftrace_call_replace(ip, FTRACE_ADDR);
-
-	if (rec->flags & FTRACE_FL_ENABLED) {
-		old = nop;
-		new = call;
-	} else {
-		old = call;
-		new = nop;
-	}
-
-	return ftrace_modify_code(ip, old, new);
+	if (rec->flags & FTRACE_FL_ENABLED)
+		return ftrace_make_call(rec, ftrace_addr);
+	else
+		return ftrace_make_nop(NULL, rec, ftrace_addr);
 }
 
 static void ftrace_replace_code(int enable)
 {
 	int i, failed;
-	unsigned char *nop = NULL;
 	struct dyn_ftrace *rec;
 	struct ftrace_page *pg;
 
-	nop = ftrace_nop_replace();
-
 	for (pg = ftrace_pages_start; pg; pg = pg->next) {
 		for (i = 0; i < pg->index; i++) {
 			rec = &pg->records[i];
 
-			/* don't modify code that has already faulted */
-			if (rec->flags & FTRACE_FL_FAILED)
+			/*
+			 * Skip over free records and records that have
+			 * failed.
+			 */
+			if (rec->flags & FTRACE_FL_FREE ||
+			    rec->flags & FTRACE_FL_FAILED)
 				continue;
 
 			/* ignore updates to this record's mcount site */
@@ -426,68 +493,30 @@ static void ftrace_replace_code(int enable)
 				unfreeze_record(rec);
 			}
 
-			failed = __ftrace_replace_code(rec, nop, enable);
+			failed = __ftrace_replace_code(rec, enable);
 			if (failed && (rec->flags & FTRACE_FL_CONVERTED)) {
 				rec->flags |= FTRACE_FL_FAILED;
 				if ((system_state == SYSTEM_BOOTING) ||
 				    !core_kernel_text(rec->ip)) {
 					ftrace_free_rec(rec);
-				}
+				} else
+					ftrace_bug(failed, rec->ip);
 			}
 		}
 	}
 }
 
-static void print_ip_ins(const char *fmt, unsigned char *p)
-{
-	int i;
-
-	printk(KERN_CONT "%s", fmt);
-
-	for (i = 0; i < MCOUNT_INSN_SIZE; i++)
-		printk(KERN_CONT "%s%02x", i ? ":" : "", p[i]);
-}
-
 static int
-ftrace_code_disable(struct dyn_ftrace *rec)
+ftrace_code_disable(struct module *mod, struct dyn_ftrace *rec)
 {
 	unsigned long ip;
-	unsigned char *nop, *call;
 	int ret;
 
 	ip = rec->ip;
 
-	nop = ftrace_nop_replace();
-	call = ftrace_call_replace(ip, mcount_addr);
-
-	ret = ftrace_modify_code(ip, call, nop);
+	ret = ftrace_make_nop(mod, rec, mcount_addr);
 	if (ret) {
-		switch (ret) {
-		case -EFAULT:
-			FTRACE_WARN_ON_ONCE(1);
-			pr_info("ftrace faulted on modifying ");
-			print_ip_sym(ip);
-			break;
-		case -EINVAL:
-			FTRACE_WARN_ON_ONCE(1);
-			pr_info("ftrace failed to modify ");
-			print_ip_sym(ip);
-			print_ip_ins(" expected: ", call);
-			print_ip_ins(" actual: ", (unsigned char *)ip);
-			print_ip_ins(" replace: ", nop);
-			printk(KERN_CONT "\n");
-			break;
-		case -EPERM:
-			FTRACE_WARN_ON_ONCE(1);
-			pr_info("ftrace faulted on writing ");
-			print_ip_sym(ip);
-			break;
-		default:
-			FTRACE_WARN_ON_ONCE(1);
-			pr_info("ftrace faulted on unknown error ");
-			print_ip_sym(ip);
-		}
-
+		ftrace_bug(ret, ip);
 		rec->flags |= FTRACE_FL_FAILED;
 		return 0;
 	}
@@ -515,7 +544,7 @@ static void ftrace_run_update_code(int command)
 }
 
 static ftrace_func_t saved_ftrace_func;
-static int ftrace_start;
+static int ftrace_start_up;
 static DEFINE_MUTEX(ftrace_start_lock);
 
 static void ftrace_startup(void)
@@ -526,7 +555,7 @@ static void ftrace_startup(void)
 		return;
 
 	mutex_lock(&ftrace_start_lock);
-	ftrace_start++;
+	ftrace_start_up++;
 	command |= FTRACE_ENABLE_CALLS;
 
 	if (saved_ftrace_func != ftrace_trace_function) {
@@ -550,8 +579,8 @@ static void ftrace_shutdown(void)
 		return;
 
 	mutex_lock(&ftrace_start_lock);
-	ftrace_start--;
-	if (!ftrace_start)
+	ftrace_start_up--;
+	if (!ftrace_start_up)
 		command |= FTRACE_DISABLE_CALLS;
 
 	if (saved_ftrace_func != ftrace_trace_function) {
@@ -577,8 +606,8 @@ static void ftrace_startup_sysctl(void)
 	mutex_lock(&ftrace_start_lock);
 	/* Force update next time */
 	saved_ftrace_func = NULL;
-	/* ftrace_start is true if we want ftrace running */
-	if (ftrace_start)
+	/* ftrace_start_up is true if we want ftrace running */
+	if (ftrace_start_up)
 		command |= FTRACE_ENABLE_CALLS;
 
 	ftrace_run_update_code(command);
@@ -593,8 +622,8 @@ static void ftrace_shutdown_sysctl(void)
 		return;
 
 	mutex_lock(&ftrace_start_lock);
-	/* ftrace_start is true if ftrace is running */
-	if (ftrace_start)
+	/* ftrace_start_up is true if ftrace is running */
+	if (ftrace_start_up)
 		command |= FTRACE_DISABLE_CALLS;
 
 	ftrace_run_update_code(command);
@@ -605,7 +634,7 @@ static cycle_t		ftrace_update_time;
 static unsigned long	ftrace_update_cnt;
 unsigned long		ftrace_update_tot_cnt;
 
-static int ftrace_update_code(void)
+static int ftrace_update_code(struct module *mod)
 {
 	struct dyn_ftrace *p, *t;
 	cycle_t start, stop;
@@ -622,7 +651,7 @@ static int ftrace_update_code(void)
 		list_del_init(&p->list);
 
 		/* convert record (i.e, patch mcount-call with NOP) */
-		if (ftrace_code_disable(p)) {
+		if (ftrace_code_disable(mod, p)) {
 			p->flags |= FTRACE_FL_CONVERTED;
 			ftrace_update_cnt++;
 		} else
@@ -1181,7 +1210,7 @@ ftrace_regex_release(struct inode *inode, struct file *file, int enable)
 
 	mutex_lock(&ftrace_sysctl_lock);
 	mutex_lock(&ftrace_start_lock);
-	if (ftrace_start && ftrace_enabled)
+	if (ftrace_start_up && ftrace_enabled)
 		ftrace_run_update_code(FTRACE_ENABLE_CALLS);
 	mutex_unlock(&ftrace_start_lock);
 	mutex_unlock(&ftrace_sysctl_lock);
@@ -1268,7 +1297,8 @@ static __init int ftrace_init_debugfs(void)
 
 fs_initcall(ftrace_init_debugfs);
 
-static int ftrace_convert_nops(unsigned long *start,
+static int ftrace_convert_nops(struct module *mod,
+			       unsigned long *start,
 			       unsigned long *end)
 {
 	unsigned long *p;
@@ -1279,23 +1309,32 @@ static int ftrace_convert_nops(unsigned long *start,
 	p = start;
 	while (p < end) {
 		addr = ftrace_call_adjust(*p++);
+		/*
+		 * Some architecture linkers will pad between
+		 * the different mcount_loc sections of different
+		 * object files to satisfy alignments.
+		 * Skip any NULL pointers.
+		 */
+		if (!addr)
+			continue;
 		ftrace_record_ip(addr);
 	}
 
 	/* disable interrupts to prevent kstop machine */
 	local_irq_save(flags);
-	ftrace_update_code();
+	ftrace_update_code(mod);
 	local_irq_restore(flags);
 	mutex_unlock(&ftrace_start_lock);
 
 	return 0;
 }
 
-void ftrace_init_module(unsigned long *start, unsigned long *end)
+void ftrace_init_module(struct module *mod,
+			unsigned long *start, unsigned long *end)
 {
 	if (ftrace_disabled || start == end)
 		return;
-	ftrace_convert_nops(start, end);
+	ftrace_convert_nops(mod, start, end);
 }
 
 extern unsigned long __start_mcount_loc[];
@@ -1325,7 +1364,8 @@ void __init ftrace_init(void)
 
 	last_ftrace_enabled = ftrace_enabled = 1;
 
-	ret = ftrace_convert_nops(__start_mcount_loc,
+	ret = ftrace_convert_nops(NULL,
+				  __start_mcount_loc,
 				  __stop_mcount_loc);
 
 	return;
@@ -1381,10 +1421,17 @@ int register_ftrace_function(struct ftrace_ops *ops)
 		return -1;
 
 	mutex_lock(&ftrace_sysctl_lock);
+
+	if (ftrace_tracing_type == FTRACE_TYPE_RETURN) {
+		ret = -EBUSY;
+		goto out;
+	}
+
 	ret = __register_ftrace_function(ops);
 	ftrace_startup();
-	mutex_unlock(&ftrace_sysctl_lock);
 
+out:
+	mutex_unlock(&ftrace_sysctl_lock);
 	return ret;
 }
 
@@ -1449,3 +1496,147 @@ ftrace_enable_sysctl(struct ctl_table *table, int write,
 	return ret;
 }
 
+#ifdef CONFIG_FUNCTION_RET_TRACER
+
+static atomic_t ftrace_retfunc_active;
+
+/* The callback that hooks the return of a function */
+trace_function_return_t ftrace_function_return =
+			(trace_function_return_t)ftrace_stub;
+
+
+/* Try to assign a return stack array on FTRACE_RETSTACK_ALLOC_SIZE tasks. */
+static int alloc_retstack_tasklist(struct ftrace_ret_stack **ret_stack_list)
+{
+	int i;
+	int ret = 0;
+	unsigned long flags;
+	int start = 0, end = FTRACE_RETSTACK_ALLOC_SIZE;
+	struct task_struct *g, *t;
+
+	for (i = 0; i < FTRACE_RETSTACK_ALLOC_SIZE; i++) {
+		ret_stack_list[i] = kmalloc(FTRACE_RETFUNC_DEPTH
+					* sizeof(struct ftrace_ret_stack),
+					GFP_KERNEL);
+		if (!ret_stack_list[i]) {
+			start = 0;
+			end = i;
+			ret = -ENOMEM;
+			goto free;
+		}
+	}
+
+	read_lock_irqsave(&tasklist_lock, flags);
+	do_each_thread(g, t) {
+		if (start == end) {
+			ret = -EAGAIN;
+			goto unlock;
+		}
+
+		if (t->ret_stack == NULL) {
+			t->ret_stack = ret_stack_list[start++];
+			t->curr_ret_stack = -1;
+			atomic_set(&t->trace_overrun, 0);
+		}
+	} while_each_thread(g, t);
+
+unlock:
+	read_unlock_irqrestore(&tasklist_lock, flags);
+free:
+	for (i = start; i < end; i++)
+		kfree(ret_stack_list[i]);
+	return ret;
+}
+
+/* Allocate a return stack for each task */
+static int start_return_tracing(void)
+{
+	struct ftrace_ret_stack **ret_stack_list;
+	int ret;
+
+	ret_stack_list = kmalloc(FTRACE_RETSTACK_ALLOC_SIZE *
+				sizeof(struct ftrace_ret_stack *),
+				GFP_KERNEL);
+
+	if (!ret_stack_list)
+		return -ENOMEM;
+
+	do {
+		ret = alloc_retstack_tasklist(ret_stack_list);
+	} while (ret == -EAGAIN);
+
+	kfree(ret_stack_list);
+	return ret;
+}
+
+int register_ftrace_return(trace_function_return_t func)
+{
+	int ret = 0;
+
+	mutex_lock(&ftrace_sysctl_lock);
+
+	/*
+	 * Don't launch return tracing if normal function
+	 * tracing is already running.
+	 */
+	if (ftrace_trace_function != ftrace_stub) {
+		ret = -EBUSY;
+		goto out;
+	}
+	atomic_inc(&ftrace_retfunc_active);
+	ret = start_return_tracing();
+	if (ret) {
+		atomic_dec(&ftrace_retfunc_active);
+		goto out;
+	}
+	ftrace_tracing_type = FTRACE_TYPE_RETURN;
+	ftrace_function_return = func;
+	ftrace_startup();
+
+out:
+	mutex_unlock(&ftrace_sysctl_lock);
+	return ret;
+}
+
+void unregister_ftrace_return(void)
+{
+	mutex_lock(&ftrace_sysctl_lock);
+
+	atomic_dec(&ftrace_retfunc_active);
+	ftrace_function_return = (trace_function_return_t)ftrace_stub;
+	ftrace_shutdown();
+	/* Restore normal tracing type */
+	ftrace_tracing_type = FTRACE_TYPE_ENTER;
+
+	mutex_unlock(&ftrace_sysctl_lock);
+}
+
+/* Allocate a return stack for newly created task */
+void ftrace_retfunc_init_task(struct task_struct *t)
+{
+	if (atomic_read(&ftrace_retfunc_active)) {
+		t->ret_stack = kmalloc(FTRACE_RETFUNC_DEPTH
+				* sizeof(struct ftrace_ret_stack),
+				GFP_KERNEL);
+		if (!t->ret_stack)
+			return;
+		t->curr_ret_stack = -1;
+		atomic_set(&t->trace_overrun, 0);
+	} else
+		t->ret_stack = NULL;
+}
+
+void ftrace_retfunc_exit_task(struct task_struct *t)
+{
+	struct ftrace_ret_stack	*ret_stack = t->ret_stack;
+
+	t->ret_stack = NULL;
+	/* NULL must become visible to IRQs before we free it: */
+	barrier();
+
+	kfree(ret_stack);
+}
+#endif
+
+
+
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 668bbb5ef2bd..e206951603c1 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -18,8 +18,46 @@
 
 #include "trace.h"
 
-/* Global flag to disable all recording to ring buffers */
-static int ring_buffers_off __read_mostly;
+/*
+ * A fast way to enable or disable all ring buffers is to
+ * call tracing_on or tracing_off. Turning off the ring buffers
+ * prevents all ring buffers from being recorded to.
+ * Turning this switch on, makes it OK to write to the
+ * ring buffer, if the ring buffer is enabled itself.
+ *
+ * There's three layers that must be on in order to write
+ * to the ring buffer.
+ *
+ * 1) This global flag must be set.
+ * 2) The ring buffer must be enabled for recording.
+ * 3) The per cpu buffer must be enabled for recording.
+ *
+ * In case of an anomaly, this global flag has a bit set that
+ * will permantly disable all ring buffers.
+ */
+
+/*
+ * Global flag to disable all recording to ring buffers
+ *  This has two bits: ON, DISABLED
+ *
+ *  ON   DISABLED
+ * ---- ----------
+ *   0      0        : ring buffers are off
+ *   1      0        : ring buffers are on
+ *   X      1        : ring buffers are permanently disabled
+ */
+
+enum {
+	RB_BUFFERS_ON_BIT	= 0,
+	RB_BUFFERS_DISABLED_BIT	= 1,
+};
+
+enum {
+	RB_BUFFERS_ON		= 1 << RB_BUFFERS_ON_BIT,
+	RB_BUFFERS_DISABLED	= 1 << RB_BUFFERS_DISABLED_BIT,
+};
+
+static long ring_buffer_flags __read_mostly = RB_BUFFERS_ON;
 
 /**
  * tracing_on - enable all tracing buffers
@@ -29,7 +67,7 @@ static int ring_buffers_off __read_mostly;
  */
 void tracing_on(void)
 {
-	ring_buffers_off = 0;
+	set_bit(RB_BUFFERS_ON_BIT, &ring_buffer_flags);
 }
 
 /**
@@ -42,9 +80,22 @@ void tracing_on(void)
  */
 void tracing_off(void)
 {
-	ring_buffers_off = 1;
+	clear_bit(RB_BUFFERS_ON_BIT, &ring_buffer_flags);
+}
+
+/**
+ * tracing_off_permanent - permanently disable ring buffers
+ *
+ * This function, once called, will disable all ring buffers
+ * permanenty.
+ */
+void tracing_off_permanent(void)
+{
+	set_bit(RB_BUFFERS_DISABLED_BIT, &ring_buffer_flags);
 }
 
+#include "trace.h"
+
 /* Up this if you want to test the TIME_EXTENTS and normalization */
 #define DEBUG_SHIFT 0
 
@@ -187,7 +238,8 @@ static inline int test_time_stamp(u64 delta)
 struct ring_buffer_per_cpu {
 	int				cpu;
 	struct ring_buffer		*buffer;
-	spinlock_t			lock;
+	spinlock_t			reader_lock; /* serialize readers */
+	raw_spinlock_t			lock;
 	struct lock_class_key		lock_key;
 	struct list_head		pages;
 	struct buffer_page		*head_page;	/* read from head */
@@ -221,32 +273,16 @@ struct ring_buffer_iter {
 	u64				read_stamp;
 };
 
+/* buffer may be either ring_buffer or ring_buffer_per_cpu */
 #define RB_WARN_ON(buffer, cond)				\
-	do {							\
-		if (unlikely(cond)) {				\
-			atomic_inc(&buffer->record_disabled);	\
-			WARN_ON(1);				\
-		}						\
-	} while (0)
-
-#define RB_WARN_ON_RET(buffer, cond)				\
-	do {							\
-		if (unlikely(cond)) {				\
-			atomic_inc(&buffer->record_disabled);	\
-			WARN_ON(1);				\
-			return -1;				\
-		}						\
-	} while (0)
-
-#define RB_WARN_ON_ONCE(buffer, cond)				\
-	do {							\
-		static int once;				\
-		if (unlikely(cond) && !once) {			\
-			once++;					\
+	({							\
+		int _____ret = unlikely(cond);			\
+		if (_____ret) {					\
 			atomic_inc(&buffer->record_disabled);	\
 			WARN_ON(1);				\
 		}						\
-	} while (0)
+		_____ret;					\
+	})
 
 /**
  * check_pages - integrity check of buffer pages
@@ -260,14 +296,18 @@ static int rb_check_pages(struct ring_buffer_per_cpu *cpu_buffer)
 	struct list_head *head = &cpu_buffer->pages;
 	struct buffer_page *page, *tmp;
 
-	RB_WARN_ON_RET(cpu_buffer, head->next->prev != head);
-	RB_WARN_ON_RET(cpu_buffer, head->prev->next != head);
+	if (RB_WARN_ON(cpu_buffer, head->next->prev != head))
+		return -1;
+	if (RB_WARN_ON(cpu_buffer, head->prev->next != head))
+		return -1;
 
 	list_for_each_entry_safe(page, tmp, head, list) {
-		RB_WARN_ON_RET(cpu_buffer,
-			       page->list.next->prev != &page->list);
-		RB_WARN_ON_RET(cpu_buffer,
-			       page->list.prev->next != &page->list);
+		if (RB_WARN_ON(cpu_buffer,
+			       page->list.next->prev != &page->list))
+			return -1;
+		if (RB_WARN_ON(cpu_buffer,
+			       page->list.prev->next != &page->list))
+			return -1;
 	}
 
 	return 0;
@@ -324,7 +364,8 @@ rb_allocate_cpu_buffer(struct ring_buffer *buffer, int cpu)
 
 	cpu_buffer->cpu = cpu;
 	cpu_buffer->buffer = buffer;
-	spin_lock_init(&cpu_buffer->lock);
+	spin_lock_init(&cpu_buffer->reader_lock);
+	cpu_buffer->lock = (raw_spinlock_t)__RAW_SPIN_LOCK_UNLOCKED;
 	INIT_LIST_HEAD(&cpu_buffer->pages);
 
 	page = kzalloc_node(ALIGN(sizeof(*page), cache_line_size()),
@@ -473,13 +514,15 @@ rb_remove_pages(struct ring_buffer_per_cpu *cpu_buffer, unsigned nr_pages)
 	synchronize_sched();
 
 	for (i = 0; i < nr_pages; i++) {
-		BUG_ON(list_empty(&cpu_buffer->pages));
+		if (RB_WARN_ON(cpu_buffer, list_empty(&cpu_buffer->pages)))
+			return;
 		p = cpu_buffer->pages.next;
 		page = list_entry(p, struct buffer_page, list);
 		list_del_init(&page->list);
 		free_buffer_page(page);
 	}
-	BUG_ON(list_empty(&cpu_buffer->pages));
+	if (RB_WARN_ON(cpu_buffer, list_empty(&cpu_buffer->pages)))
+		return;
 
 	rb_reset_cpu(cpu_buffer);
 
@@ -501,7 +544,8 @@ rb_insert_pages(struct ring_buffer_per_cpu *cpu_buffer,
 	synchronize_sched();
 
 	for (i = 0; i < nr_pages; i++) {
-		BUG_ON(list_empty(pages));
+		if (RB_WARN_ON(cpu_buffer, list_empty(pages)))
+			return;
 		p = pages->next;
 		page = list_entry(p, struct buffer_page, list);
 		list_del_init(&page->list);
@@ -562,7 +606,10 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size)
 	if (size < buffer_size) {
 
 		/* easy case, just free pages */
-		BUG_ON(nr_pages >= buffer->pages);
+		if (RB_WARN_ON(buffer, nr_pages >= buffer->pages)) {
+			mutex_unlock(&buffer->mutex);
+			return -1;
+		}
 
 		rm_pages = buffer->pages - nr_pages;
 
@@ -581,7 +628,11 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size)
 	 * add these pages to the cpu_buffers. Otherwise we just free
 	 * them all and return -ENOMEM;
 	 */
-	BUG_ON(nr_pages <= buffer->pages);
+	if (RB_WARN_ON(buffer, nr_pages <= buffer->pages)) {
+		mutex_unlock(&buffer->mutex);
+		return -1;
+	}
+
 	new_pages = nr_pages - buffer->pages;
 
 	for_each_buffer_cpu(buffer, cpu) {
@@ -604,7 +655,10 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size)
 		rb_insert_pages(cpu_buffer, &pages, new_pages);
 	}
 
-	BUG_ON(!list_empty(&pages));
+	if (RB_WARN_ON(buffer, !list_empty(&pages))) {
+		mutex_unlock(&buffer->mutex);
+		return -1;
+	}
 
  out:
 	buffer->pages = nr_pages;
@@ -693,7 +747,8 @@ static void rb_update_overflow(struct ring_buffer_per_cpu *cpu_buffer)
 	     head += rb_event_length(event)) {
 
 		event = __rb_page_index(cpu_buffer->head_page, head);
-		BUG_ON(rb_null_event(event));
+		if (RB_WARN_ON(cpu_buffer, rb_null_event(event)))
+			return;
 		/* Only count data entries */
 		if (event->type != RINGBUF_TYPE_DATA)
 			continue;
@@ -746,8 +801,9 @@ rb_set_commit_event(struct ring_buffer_per_cpu *cpu_buffer,
 	addr &= PAGE_MASK;
 
 	while (cpu_buffer->commit_page->page != (void *)addr) {
-		RB_WARN_ON(cpu_buffer,
-			   cpu_buffer->commit_page == cpu_buffer->tail_page);
+		if (RB_WARN_ON(cpu_buffer,
+			  cpu_buffer->commit_page == cpu_buffer->tail_page))
+			return;
 		cpu_buffer->commit_page->commit =
 			cpu_buffer->commit_page->write;
 		rb_inc_page(cpu_buffer, &cpu_buffer->commit_page);
@@ -894,7 +950,8 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
 	if (write > BUF_PAGE_SIZE) {
 		struct buffer_page *next_page = tail_page;
 
-		spin_lock_irqsave(&cpu_buffer->lock, flags);
+		local_irq_save(flags);
+		__raw_spin_lock(&cpu_buffer->lock);
 
 		rb_inc_page(cpu_buffer, &next_page);
 
@@ -902,7 +959,8 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
 		reader_page = cpu_buffer->reader_page;
 
 		/* we grabbed the lock before incrementing */
-		RB_WARN_ON(cpu_buffer, next_page == reader_page);
+		if (RB_WARN_ON(cpu_buffer, next_page == reader_page))
+			goto out_unlock;
 
 		/*
 		 * If for some reason, we had an interrupt storm that made
@@ -970,7 +1028,8 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
 			rb_set_commit_to_write(cpu_buffer);
 		}
 
-		spin_unlock_irqrestore(&cpu_buffer->lock, flags);
+		__raw_spin_unlock(&cpu_buffer->lock);
+		local_irq_restore(flags);
 
 		/* fail and let the caller try again */
 		return ERR_PTR(-EAGAIN);
@@ -978,7 +1037,8 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
 
 	/* We reserved something on the buffer */
 
-	BUG_ON(write > BUF_PAGE_SIZE);
+	if (RB_WARN_ON(cpu_buffer, write > BUF_PAGE_SIZE))
+		return NULL;
 
 	event = __rb_page_index(tail_page, tail);
 	rb_update_event(event, type, length);
@@ -993,7 +1053,8 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
 	return event;
 
  out_unlock:
-	spin_unlock_irqrestore(&cpu_buffer->lock, flags);
+	__raw_spin_unlock(&cpu_buffer->lock);
+	local_irq_restore(flags);
 	return NULL;
 }
 
@@ -1076,10 +1137,8 @@ rb_reserve_next_event(struct ring_buffer_per_cpu *cpu_buffer,
 	 * storm or we have something buggy.
 	 * Bail!
 	 */
-	if (unlikely(++nr_loops > 1000)) {
-		RB_WARN_ON(cpu_buffer, 1);
+	if (RB_WARN_ON(cpu_buffer, ++nr_loops > 1000))
 		return NULL;
-	}
 
 	ts = ring_buffer_time_stamp(cpu_buffer->cpu);
 
@@ -1175,15 +1234,14 @@ ring_buffer_lock_reserve(struct ring_buffer *buffer,
 	struct ring_buffer_event *event;
 	int cpu, resched;
 
-	if (ring_buffers_off)
+	if (ring_buffer_flags != RB_BUFFERS_ON)
 		return NULL;
 
 	if (atomic_read(&buffer->record_disabled))
 		return NULL;
 
 	/* If we are tracing schedule, we don't want to recurse */
-	resched = need_resched();
-	preempt_disable_notrace();
+	resched = ftrace_preempt_disable();
 
 	cpu = raw_smp_processor_id();
 
@@ -1214,10 +1272,7 @@ ring_buffer_lock_reserve(struct ring_buffer *buffer,
 	return event;
 
  out:
-	if (resched)
-		preempt_enable_no_resched_notrace();
-	else
-		preempt_enable_notrace();
+	ftrace_preempt_enable(resched);
 	return NULL;
 }
 
@@ -1259,12 +1314,9 @@ int ring_buffer_unlock_commit(struct ring_buffer *buffer,
 	/*
 	 * Only the last preempt count needs to restore preemption.
 	 */
-	if (preempt_count() == 1) {
-		if (per_cpu(rb_need_resched, cpu))
-			preempt_enable_no_resched_notrace();
-		else
-			preempt_enable_notrace();
-	} else
+	if (preempt_count() == 1)
+		ftrace_preempt_enable(per_cpu(rb_need_resched, cpu));
+	else
 		preempt_enable_no_resched_notrace();
 
 	return 0;
@@ -1294,14 +1346,13 @@ int ring_buffer_write(struct ring_buffer *buffer,
 	int ret = -EBUSY;
 	int cpu, resched;
 
-	if (ring_buffers_off)
+	if (ring_buffer_flags != RB_BUFFERS_ON)
 		return -EBUSY;
 
 	if (atomic_read(&buffer->record_disabled))
 		return -EBUSY;
 
-	resched = need_resched();
-	preempt_disable_notrace();
+	resched = ftrace_preempt_disable();
 
 	cpu = raw_smp_processor_id();
 
@@ -1327,10 +1378,7 @@ int ring_buffer_write(struct ring_buffer *buffer,
 
 	ret = 0;
  out:
-	if (resched)
-		preempt_enable_no_resched_notrace();
-	else
-		preempt_enable_notrace();
+	ftrace_preempt_enable(resched);
 
 	return ret;
 }
@@ -1489,14 +1537,7 @@ unsigned long ring_buffer_overruns(struct ring_buffer *buffer)
 	return overruns;
 }
 
-/**
- * ring_buffer_iter_reset - reset an iterator
- * @iter: The iterator to reset
- *
- * Resets the iterator, so that it will start from the beginning
- * again.
- */
-void ring_buffer_iter_reset(struct ring_buffer_iter *iter)
+static void rb_iter_reset(struct ring_buffer_iter *iter)
 {
 	struct ring_buffer_per_cpu *cpu_buffer = iter->cpu_buffer;
 
@@ -1515,6 +1556,23 @@ void ring_buffer_iter_reset(struct ring_buffer_iter *iter)
 }
 
 /**
+ * ring_buffer_iter_reset - reset an iterator
+ * @iter: The iterator to reset
+ *
+ * Resets the iterator, so that it will start from the beginning
+ * again.
+ */
+void ring_buffer_iter_reset(struct ring_buffer_iter *iter)
+{
+	struct ring_buffer_per_cpu *cpu_buffer = iter->cpu_buffer;
+	unsigned long flags;
+
+	spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
+	rb_iter_reset(iter);
+	spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
+}
+
+/**
  * ring_buffer_iter_empty - check if an iterator has no more to read
  * @iter: The iterator to check
  */
@@ -1597,7 +1655,8 @@ rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer)
 	unsigned long flags;
 	int nr_loops = 0;
 
-	spin_lock_irqsave(&cpu_buffer->lock, flags);
+	local_irq_save(flags);
+	__raw_spin_lock(&cpu_buffer->lock);
 
  again:
 	/*
@@ -1606,8 +1665,7 @@ rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer)
 	 * a case where we will loop three times. There should be no
 	 * reason to loop four times (that I know of).
 	 */
-	if (unlikely(++nr_loops > 3)) {
-		RB_WARN_ON(cpu_buffer, 1);
+	if (RB_WARN_ON(cpu_buffer, ++nr_loops > 3)) {
 		reader = NULL;
 		goto out;
 	}
@@ -1619,8 +1677,9 @@ rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer)
 		goto out;
 
 	/* Never should we have an index greater than the size */
-	RB_WARN_ON(cpu_buffer,
-		   cpu_buffer->reader_page->read > rb_page_size(reader));
+	if (RB_WARN_ON(cpu_buffer,
+		       cpu_buffer->reader_page->read > rb_page_size(reader)))
+		goto out;
 
 	/* check if we caught up to the tail */
 	reader = NULL;
@@ -1659,7 +1718,8 @@ rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer)
 	goto again;
 
  out:
-	spin_unlock_irqrestore(&cpu_buffer->lock, flags);
+	__raw_spin_unlock(&cpu_buffer->lock);
+	local_irq_restore(flags);
 
 	return reader;
 }
@@ -1673,7 +1733,8 @@ static void rb_advance_reader(struct ring_buffer_per_cpu *cpu_buffer)
 	reader = rb_get_reader_page(cpu_buffer);
 
 	/* This function should not be called when buffer is empty */
-	BUG_ON(!reader);
+	if (RB_WARN_ON(cpu_buffer, !reader))
+		return;
 
 	event = rb_reader_event(cpu_buffer);
 
@@ -1700,7 +1761,9 @@ static void rb_advance_iter(struct ring_buffer_iter *iter)
 	 * Check if we are at the end of the buffer.
 	 */
 	if (iter->head >= rb_page_size(iter->head_page)) {
-		BUG_ON(iter->head_page == cpu_buffer->commit_page);
+		if (RB_WARN_ON(buffer,
+			       iter->head_page == cpu_buffer->commit_page))
+			return;
 		rb_inc_iter(iter);
 		return;
 	}
@@ -1713,8 +1776,10 @@ static void rb_advance_iter(struct ring_buffer_iter *iter)
 	 * This should not be called to advance the header if we are
 	 * at the tail of the buffer.
 	 */
-	BUG_ON((iter->head_page == cpu_buffer->commit_page) &&
-	       (iter->head + length > rb_commit_index(cpu_buffer)));
+	if (RB_WARN_ON(cpu_buffer,
+		       (iter->head_page == cpu_buffer->commit_page) &&
+		       (iter->head + length > rb_commit_index(cpu_buffer))))
+		return;
 
 	rb_update_iter_read_stamp(iter, event);
 
@@ -1726,17 +1791,8 @@ static void rb_advance_iter(struct ring_buffer_iter *iter)
 		rb_advance_iter(iter);
 }
 
-/**
- * ring_buffer_peek - peek at the next event to be read
- * @buffer: The ring buffer to read
- * @cpu: The cpu to peak at
- * @ts: The timestamp counter of this event.
- *
- * This will return the event that will be read next, but does
- * not consume the data.
- */
-struct ring_buffer_event *
-ring_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts)
+static struct ring_buffer_event *
+rb_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts)
 {
 	struct ring_buffer_per_cpu *cpu_buffer;
 	struct ring_buffer_event *event;
@@ -1757,10 +1813,8 @@ ring_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts)
 	 * can have.  Nesting 10 deep of interrupts is clearly
 	 * an anomaly.
 	 */
-	if (unlikely(++nr_loops > 10)) {
-		RB_WARN_ON(cpu_buffer, 1);
+	if (RB_WARN_ON(cpu_buffer, ++nr_loops > 10))
 		return NULL;
-	}
 
 	reader = rb_get_reader_page(cpu_buffer);
 	if (!reader)
@@ -1798,16 +1852,8 @@ ring_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts)
 	return NULL;
 }
 
-/**
- * ring_buffer_iter_peek - peek at the next event to be read
- * @iter: The ring buffer iterator
- * @ts: The timestamp counter of this event.
- *
- * This will return the event that will be read next, but does
- * not increment the iterator.
- */
-struct ring_buffer_event *
-ring_buffer_iter_peek(struct ring_buffer_iter *iter, u64 *ts)
+static struct ring_buffer_event *
+rb_iter_peek(struct ring_buffer_iter *iter, u64 *ts)
 {
 	struct ring_buffer *buffer;
 	struct ring_buffer_per_cpu *cpu_buffer;
@@ -1829,10 +1875,8 @@ ring_buffer_iter_peek(struct ring_buffer_iter *iter, u64 *ts)
 	 * can have. Nesting 10 deep of interrupts is clearly
 	 * an anomaly.
 	 */
-	if (unlikely(++nr_loops > 10)) {
-		RB_WARN_ON(cpu_buffer, 1);
+	if (RB_WARN_ON(cpu_buffer, ++nr_loops > 10))
 		return NULL;
-	}
 
 	if (rb_per_cpu_empty(cpu_buffer))
 		return NULL;
@@ -1869,6 +1913,51 @@ ring_buffer_iter_peek(struct ring_buffer_iter *iter, u64 *ts)
 }
 
 /**
+ * ring_buffer_peek - peek at the next event to be read
+ * @buffer: The ring buffer to read
+ * @cpu: The cpu to peak at
+ * @ts: The timestamp counter of this event.
+ *
+ * This will return the event that will be read next, but does
+ * not consume the data.
+ */
+struct ring_buffer_event *
+ring_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts)
+{
+	struct ring_buffer_per_cpu *cpu_buffer = buffer->buffers[cpu];
+	struct ring_buffer_event *event;
+	unsigned long flags;
+
+	spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
+	event = rb_buffer_peek(buffer, cpu, ts);
+	spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
+
+	return event;
+}
+
+/**
+ * ring_buffer_iter_peek - peek at the next event to be read
+ * @iter: The ring buffer iterator
+ * @ts: The timestamp counter of this event.
+ *
+ * This will return the event that will be read next, but does
+ * not increment the iterator.
+ */
+struct ring_buffer_event *
+ring_buffer_iter_peek(struct ring_buffer_iter *iter, u64 *ts)
+{
+	struct ring_buffer_per_cpu *cpu_buffer = iter->cpu_buffer;
+	struct ring_buffer_event *event;
+	unsigned long flags;
+
+	spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
+	event = rb_iter_peek(iter, ts);
+	spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
+
+	return event;
+}
+
+/**
  * ring_buffer_consume - return an event and consume it
  * @buffer: The ring buffer to get the next event from
  *
@@ -1879,19 +1968,24 @@ ring_buffer_iter_peek(struct ring_buffer_iter *iter, u64 *ts)
 struct ring_buffer_event *
 ring_buffer_consume(struct ring_buffer *buffer, int cpu, u64 *ts)
 {
-	struct ring_buffer_per_cpu *cpu_buffer;
+	struct ring_buffer_per_cpu *cpu_buffer = buffer->buffers[cpu];
 	struct ring_buffer_event *event;
+	unsigned long flags;
 
 	if (!cpu_isset(cpu, buffer->cpumask))
 		return NULL;
 
-	event = ring_buffer_peek(buffer, cpu, ts);
+	spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
+
+	event = rb_buffer_peek(buffer, cpu, ts);
 	if (!event)
-		return NULL;
+		goto out;
 
-	cpu_buffer = buffer->buffers[cpu];
 	rb_advance_reader(cpu_buffer);
 
+ out:
+	spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
+
 	return event;
 }
 
@@ -1928,9 +2022,11 @@ ring_buffer_read_start(struct ring_buffer *buffer, int cpu)
 	atomic_inc(&cpu_buffer->record_disabled);
 	synchronize_sched();
 
-	spin_lock_irqsave(&cpu_buffer->lock, flags);
-	ring_buffer_iter_reset(iter);
-	spin_unlock_irqrestore(&cpu_buffer->lock, flags);
+	spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
+	__raw_spin_lock(&cpu_buffer->lock);
+	rb_iter_reset(iter);
+	__raw_spin_unlock(&cpu_buffer->lock);
+	spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
 
 	return iter;
 }
@@ -1962,12 +2058,17 @@ struct ring_buffer_event *
 ring_buffer_read(struct ring_buffer_iter *iter, u64 *ts)
 {
 	struct ring_buffer_event *event;
+	struct ring_buffer_per_cpu *cpu_buffer = iter->cpu_buffer;
+	unsigned long flags;
 
-	event = ring_buffer_iter_peek(iter, ts);
+	spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
+	event = rb_iter_peek(iter, ts);
 	if (!event)
-		return NULL;
+		goto out;
 
 	rb_advance_iter(iter);
+ out:
+	spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
 
 	return event;
 }
@@ -2016,11 +2117,15 @@ void ring_buffer_reset_cpu(struct ring_buffer *buffer, int cpu)
 	if (!cpu_isset(cpu, buffer->cpumask))
 		return;
 
-	spin_lock_irqsave(&cpu_buffer->lock, flags);
+	spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
+
+	__raw_spin_lock(&cpu_buffer->lock);
 
 	rb_reset_cpu(cpu_buffer);
 
-	spin_unlock_irqrestore(&cpu_buffer->lock, flags);
+	__raw_spin_unlock(&cpu_buffer->lock);
+
+	spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
 }
 
 /**
@@ -2122,12 +2227,14 @@ static ssize_t
 rb_simple_read(struct file *filp, char __user *ubuf,
 	       size_t cnt, loff_t *ppos)
 {
-	int *p = filp->private_data;
+	long *p = filp->private_data;
 	char buf[64];
 	int r;
 
-	/* !ring_buffers_off == tracing_on */
-	r = sprintf(buf, "%d\n", !*p);
+	if (test_bit(RB_BUFFERS_DISABLED_BIT, p))
+		r = sprintf(buf, "permanently disabled\n");
+	else
+		r = sprintf(buf, "%d\n", test_bit(RB_BUFFERS_ON_BIT, p));
 
 	return simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
 }
@@ -2136,7 +2243,7 @@ static ssize_t
 rb_simple_write(struct file *filp, const char __user *ubuf,
 		size_t cnt, loff_t *ppos)
 {
-	int *p = filp->private_data;
+	long *p = filp->private_data;
 	char buf[64];
 	long val;
 	int ret;
@@ -2153,8 +2260,10 @@ rb_simple_write(struct file *filp, const char __user *ubuf,
 	if (ret < 0)
 		return ret;
 
-	/* !ring_buffers_off == tracing_on */
-	*p = !val;
+	if (val)
+		set_bit(RB_BUFFERS_ON_BIT, p);
+	else
+		clear_bit(RB_BUFFERS_ON_BIT, p);
 
 	(*ppos)++;
 
@@ -2176,7 +2285,7 @@ static __init int rb_init_debugfs(void)
 	d_tracer = tracing_init_dentry();
 
 	entry = debugfs_create_file("tracing_on", 0644, d_tracer,
-				    &ring_buffers_off, &rb_simple_fops);
+				    &ring_buffer_flags, &rb_simple_fops);
 	if (!entry)
 		pr_warning("Could not create debugfs 'tracing_on' entry\n");
 
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index d86e3252f300..f0a4491f9b64 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -30,6 +30,7 @@
 #include <linux/gfp.h>
 #include <linux/fs.h>
 #include <linux/kprobes.h>
+#include <linux/seq_file.h>
 #include <linux/writeback.h>
 
 #include <linux/stacktrace.h>
@@ -43,6 +44,29 @@
 unsigned long __read_mostly	tracing_max_latency = (cycle_t)ULONG_MAX;
 unsigned long __read_mostly	tracing_thresh;
 
+/* For tracers that don't implement custom flags */
+static struct tracer_opt dummy_tracer_opt[] = {
+	{ }
+};
+
+static struct tracer_flags dummy_tracer_flags = {
+	.val = 0,
+	.opts = dummy_tracer_opt
+};
+
+static int dummy_set_flag(u32 old_flags, u32 bit, int set)
+{
+	return 0;
+}
+
+/*
+ * Kill all tracing for good (never come back).
+ * It is initialized to 1 but will turn to zero if the initialization
+ * of the tracer is successful. But that is the only place that sets
+ * this back to zero.
+ */
+int tracing_disabled = 1;
+
 static DEFINE_PER_CPU(local_t, ftrace_cpu_disabled);
 
 static inline void ftrace_disable_cpu(void)
@@ -62,7 +86,36 @@ static cpumask_t __read_mostly		tracing_buffer_mask;
 #define for_each_tracing_cpu(cpu)	\
 	for_each_cpu_mask(cpu, tracing_buffer_mask)
 
-static int tracing_disabled = 1;
+/*
+ * ftrace_dump_on_oops - variable to dump ftrace buffer on oops
+ *
+ * If there is an oops (or kernel panic) and the ftrace_dump_on_oops
+ * is set, then ftrace_dump is called. This will output the contents
+ * of the ftrace buffers to the console.  This is very useful for
+ * capturing traces that lead to crashes and outputing it to a
+ * serial console.
+ *
+ * It is default off, but you can enable it with either specifying
+ * "ftrace_dump_on_oops" in the kernel command line, or setting
+ * /proc/sys/kernel/ftrace_dump_on_oops to true.
+ */
+int ftrace_dump_on_oops;
+
+static int tracing_set_tracer(char *buf);
+
+static int __init set_ftrace(char *str)
+{
+	tracing_set_tracer(str);
+	return 1;
+}
+__setup("ftrace", set_ftrace);
+
+static int __init set_ftrace_dump_on_oops(char *str)
+{
+	ftrace_dump_on_oops = 1;
+	return 1;
+}
+__setup("ftrace_dump_on_oops", set_ftrace_dump_on_oops);
 
 long
 ns2usecs(cycle_t nsec)
@@ -112,6 +165,19 @@ static DEFINE_PER_CPU(struct trace_array_cpu, max_data);
 /* tracer_enabled is used to toggle activation of a tracer */
 static int			tracer_enabled = 1;
 
+/**
+ * tracing_is_enabled - return tracer_enabled status
+ *
+ * This function is used by other tracers to know the status
+ * of the tracer_enabled flag.  Tracers may use this function
+ * to know if it should enable their features when starting
+ * up. See irqsoff tracer for an example (start_irqsoff_tracer).
+ */
+int tracing_is_enabled(void)
+{
+	return tracer_enabled;
+}
+
 /* function tracing enabled */
 int				ftrace_function_enabled;
 
@@ -153,8 +219,9 @@ static DEFINE_MUTEX(trace_types_lock);
 /* trace_wait is a waitqueue for tasks blocked on trace_poll */
 static DECLARE_WAIT_QUEUE_HEAD(trace_wait);
 
-/* trace_flags holds iter_ctrl options */
-unsigned long trace_flags = TRACE_ITER_PRINT_PARENT;
+/* trace_flags holds trace_options default values */
+unsigned long trace_flags = TRACE_ITER_PRINT_PARENT | TRACE_ITER_PRINTK |
+	TRACE_ITER_ANNOTATE;
 
 /**
  * trace_wake_up - wake up tasks waiting for trace input
@@ -193,13 +260,6 @@ unsigned long nsecs_to_usecs(unsigned long nsecs)
 	return nsecs / 1000;
 }
 
-/*
- * TRACE_ITER_SYM_MASK masks the options in trace_flags that
- * control the output of kernel symbols.
- */
-#define TRACE_ITER_SYM_MASK \
-	(TRACE_ITER_PRINT_PARENT|TRACE_ITER_SYM_OFFSET|TRACE_ITER_SYM_ADDR)
-
 /* These must match the bit postions in trace_iterator_flags */
 static const char *trace_options[] = {
 	"print-parent",
@@ -213,6 +273,11 @@ static const char *trace_options[] = {
 	"stacktrace",
 	"sched-tree",
 	"ftrace_printk",
+	"ftrace_preempt",
+	"branch",
+	"annotate",
+	"userstacktrace",
+	"sym-userobj",
 	NULL
 };
 
@@ -359,6 +424,28 @@ trace_seq_putmem_hex(struct trace_seq *s, void *mem, size_t len)
 	return trace_seq_putmem(s, hex, j);
 }
 
+static int
+trace_seq_path(struct trace_seq *s, struct path *path)
+{
+	unsigned char *p;
+
+	if (s->len >= (PAGE_SIZE - 1))
+		return 0;
+	p = d_path(path, s->buffer + s->len, PAGE_SIZE - s->len);
+	if (!IS_ERR(p)) {
+		p = mangle_path(s->buffer + s->len, p, "\n");
+		if (p) {
+			s->len = p - s->buffer;
+			return 1;
+		}
+	} else {
+		s->buffer[s->len++] = '?';
+		return 1;
+	}
+
+	return 0;
+}
+
 static void
 trace_seq_reset(struct trace_seq *s)
 {
@@ -470,7 +557,15 @@ int register_tracer(struct tracer *type)
 		return -1;
 	}
 
+	/*
+	 * When this gets called we hold the BKL which means that
+	 * preemption is disabled. Various trace selftests however
+	 * need to disable and enable preemption for successful tests.
+	 * So we drop the BKL here and grab it after the tests again.
+	 */
+	unlock_kernel();
 	mutex_lock(&trace_types_lock);
+
 	for (t = trace_types; t; t = t->next) {
 		if (strcmp(type->name, t->name) == 0) {
 			/* already found */
@@ -481,11 +576,18 @@ int register_tracer(struct tracer *type)
 		}
 	}
 
+	if (!type->set_flag)
+		type->set_flag = &dummy_set_flag;
+	if (!type->flags)
+		type->flags = &dummy_tracer_flags;
+	else
+		if (!type->flags->opts)
+			type->flags->opts = dummy_tracer_opt;
+
 #ifdef CONFIG_FTRACE_STARTUP_TEST
 	if (type->selftest) {
 		struct tracer *saved_tracer = current_trace;
 		struct trace_array *tr = &global_trace;
-		int saved_ctrl = tr->ctrl;
 		int i;
 		/*
 		 * Run a selftest on this tracer.
@@ -494,25 +596,23 @@ int register_tracer(struct tracer *type)
 		 * internal tracing to verify that everything is in order.
 		 * If we fail, we do not register this tracer.
 		 */
-		for_each_tracing_cpu(i) {
+		for_each_tracing_cpu(i)
 			tracing_reset(tr, i);
-		}
+
 		current_trace = type;
-		tr->ctrl = 0;
 		/* the test is responsible for initializing and enabling */
 		pr_info("Testing tracer %s: ", type->name);
 		ret = type->selftest(type, tr);
 		/* the test is responsible for resetting too */
 		current_trace = saved_tracer;
-		tr->ctrl = saved_ctrl;
 		if (ret) {
 			printk(KERN_CONT "FAILED!\n");
 			goto out;
 		}
 		/* Only reset on passing, to avoid touching corrupted buffers */
-		for_each_tracing_cpu(i) {
+		for_each_tracing_cpu(i)
 			tracing_reset(tr, i);
-		}
+
 		printk(KERN_CONT "PASSED\n");
 	}
 #endif
@@ -525,6 +625,7 @@ int register_tracer(struct tracer *type)
 
  out:
 	mutex_unlock(&trace_types_lock);
+	lock_kernel();
 
 	return ret;
 }
@@ -581,6 +682,91 @@ static void trace_init_cmdlines(void)
 	cmdline_idx = 0;
 }
 
+static int trace_stop_count;
+static DEFINE_SPINLOCK(tracing_start_lock);
+
+/**
+ * ftrace_off_permanent - disable all ftrace code permanently
+ *
+ * This should only be called when a serious anomally has
+ * been detected.  This will turn off the function tracing,
+ * ring buffers, and other tracing utilites. It takes no
+ * locks and can be called from any context.
+ */
+void ftrace_off_permanent(void)
+{
+	tracing_disabled = 1;
+	ftrace_stop();
+	tracing_off_permanent();
+}
+
+/**
+ * tracing_start - quick start of the tracer
+ *
+ * If tracing is enabled but was stopped by tracing_stop,
+ * this will start the tracer back up.
+ */
+void tracing_start(void)
+{
+	struct ring_buffer *buffer;
+	unsigned long flags;
+
+	if (tracing_disabled)
+		return;
+
+	spin_lock_irqsave(&tracing_start_lock, flags);
+	if (--trace_stop_count)
+		goto out;
+
+	if (trace_stop_count < 0) {
+		/* Someone screwed up their debugging */
+		WARN_ON_ONCE(1);
+		trace_stop_count = 0;
+		goto out;
+	}
+
+
+	buffer = global_trace.buffer;
+	if (buffer)
+		ring_buffer_record_enable(buffer);
+
+	buffer = max_tr.buffer;
+	if (buffer)
+		ring_buffer_record_enable(buffer);
+
+	ftrace_start();
+ out:
+	spin_unlock_irqrestore(&tracing_start_lock, flags);
+}
+
+/**
+ * tracing_stop - quick stop of the tracer
+ *
+ * Light weight way to stop tracing. Use in conjunction with
+ * tracing_start.
+ */
+void tracing_stop(void)
+{
+	struct ring_buffer *buffer;
+	unsigned long flags;
+
+	ftrace_stop();
+	spin_lock_irqsave(&tracing_start_lock, flags);
+	if (trace_stop_count++)
+		goto out;
+
+	buffer = global_trace.buffer;
+	if (buffer)
+		ring_buffer_record_disable(buffer);
+
+	buffer = max_tr.buffer;
+	if (buffer)
+		ring_buffer_record_disable(buffer);
+
+ out:
+	spin_unlock_irqrestore(&tracing_start_lock, flags);
+}
+
 void trace_stop_cmdline_recording(void);
 
 static void trace_save_cmdline(struct task_struct *tsk)
@@ -655,6 +841,7 @@ tracing_generic_entry_update(struct trace_entry *entry, unsigned long flags,
 
 	entry->preempt_count		= pc & 0xff;
 	entry->pid			= (tsk) ? tsk->pid : 0;
+	entry->tgid               	= (tsk) ? tsk->tgid : 0;
 	entry->flags =
 #ifdef CONFIG_TRACE_IRQFLAGS_SUPPORT
 		(irqs_disabled_flags(flags) ? TRACE_FLAG_IRQS_OFF : 0) |
@@ -691,6 +878,36 @@ trace_function(struct trace_array *tr, struct trace_array_cpu *data,
 	ring_buffer_unlock_commit(tr->buffer, event, irq_flags);
 }
 
+#ifdef CONFIG_FUNCTION_RET_TRACER
+static void __trace_function_return(struct trace_array *tr,
+				struct trace_array_cpu *data,
+				struct ftrace_retfunc *trace,
+				unsigned long flags,
+				int pc)
+{
+	struct ring_buffer_event *event;
+	struct ftrace_ret_entry *entry;
+	unsigned long irq_flags;
+
+	if (unlikely(local_read(&__get_cpu_var(ftrace_cpu_disabled))))
+		return;
+
+	event = ring_buffer_lock_reserve(global_trace.buffer, sizeof(*entry),
+					 &irq_flags);
+	if (!event)
+		return;
+	entry	= ring_buffer_event_data(event);
+	tracing_generic_entry_update(&entry->ent, flags, pc);
+	entry->ent.type			= TRACE_FN_RET;
+	entry->ip			= trace->func;
+	entry->parent_ip	= trace->ret;
+	entry->rettime		= trace->rettime;
+	entry->calltime		= trace->calltime;
+	entry->overrun		= trace->overrun;
+	ring_buffer_unlock_commit(global_trace.buffer, event, irq_flags);
+}
+#endif
+
 void
 ftrace(struct trace_array *tr, struct trace_array_cpu *data,
        unsigned long ip, unsigned long parent_ip, unsigned long flags,
@@ -742,6 +959,46 @@ void __trace_stack(struct trace_array *tr,
 	ftrace_trace_stack(tr, data, flags, skip, preempt_count());
 }
 
+static void ftrace_trace_userstack(struct trace_array *tr,
+		   struct trace_array_cpu *data,
+		   unsigned long flags, int pc)
+{
+#ifdef CONFIG_STACKTRACE
+	struct ring_buffer_event *event;
+	struct userstack_entry *entry;
+	struct stack_trace trace;
+	unsigned long irq_flags;
+
+	if (!(trace_flags & TRACE_ITER_USERSTACKTRACE))
+		return;
+
+	event = ring_buffer_lock_reserve(tr->buffer, sizeof(*entry),
+					 &irq_flags);
+	if (!event)
+		return;
+	entry	= ring_buffer_event_data(event);
+	tracing_generic_entry_update(&entry->ent, flags, pc);
+	entry->ent.type		= TRACE_USER_STACK;
+
+	memset(&entry->caller, 0, sizeof(entry->caller));
+
+	trace.nr_entries	= 0;
+	trace.max_entries	= FTRACE_STACK_ENTRIES;
+	trace.skip		= 0;
+	trace.entries		= entry->caller;
+
+	save_stack_trace_user(&trace);
+	ring_buffer_unlock_commit(tr->buffer, event, irq_flags);
+#endif
+}
+
+void __trace_userstack(struct trace_array *tr,
+		   struct trace_array_cpu *data,
+		   unsigned long flags)
+{
+	ftrace_trace_userstack(tr, data, flags, preempt_count());
+}
+
 static void
 ftrace_trace_special(void *__tr, void *__data,
 		     unsigned long arg1, unsigned long arg2, unsigned long arg3,
@@ -765,6 +1022,7 @@ ftrace_trace_special(void *__tr, void *__data,
 	entry->arg3			= arg3;
 	ring_buffer_unlock_commit(tr->buffer, event, irq_flags);
 	ftrace_trace_stack(tr, data, irq_flags, 4, pc);
+	ftrace_trace_userstack(tr, data, irq_flags, pc);
 
 	trace_wake_up();
 }
@@ -803,6 +1061,7 @@ tracing_sched_switch_trace(struct trace_array *tr,
 	entry->next_cpu	= task_cpu(next);
 	ring_buffer_unlock_commit(tr->buffer, event, irq_flags);
 	ftrace_trace_stack(tr, data, flags, 5, pc);
+	ftrace_trace_userstack(tr, data, flags, pc);
 }
 
 void
@@ -832,6 +1091,7 @@ tracing_sched_wakeup_trace(struct trace_array *tr,
 	entry->next_cpu			= task_cpu(wakee);
 	ring_buffer_unlock_commit(tr->buffer, event, irq_flags);
 	ftrace_trace_stack(tr, data, flags, 6, pc);
+	ftrace_trace_userstack(tr, data, flags, pc);
 
 	trace_wake_up();
 }
@@ -841,26 +1101,28 @@ ftrace_special(unsigned long arg1, unsigned long arg2, unsigned long arg3)
 {
 	struct trace_array *tr = &global_trace;
 	struct trace_array_cpu *data;
+	unsigned long flags;
 	int cpu;
 	int pc;
 
-	if (tracing_disabled || !tr->ctrl)
+	if (tracing_disabled)
 		return;
 
 	pc = preempt_count();
-	preempt_disable_notrace();
+	local_irq_save(flags);
 	cpu = raw_smp_processor_id();
 	data = tr->data[cpu];
 
-	if (likely(!atomic_read(&data->disabled)))
+	if (likely(atomic_inc_return(&data->disabled) == 1))
 		ftrace_trace_special(tr, data, arg1, arg2, arg3, pc);
 
-	preempt_enable_notrace();
+	atomic_dec(&data->disabled);
+	local_irq_restore(flags);
 }
 
 #ifdef CONFIG_FUNCTION_TRACER
 static void
-function_trace_call(unsigned long ip, unsigned long parent_ip)
+function_trace_call_preempt_only(unsigned long ip, unsigned long parent_ip)
 {
 	struct trace_array *tr = &global_trace;
 	struct trace_array_cpu *data;
@@ -873,8 +1135,7 @@ function_trace_call(unsigned long ip, unsigned long parent_ip)
 		return;
 
 	pc = preempt_count();
-	resched = need_resched();
-	preempt_disable_notrace();
+	resched = ftrace_preempt_disable();
 	local_save_flags(flags);
 	cpu = raw_smp_processor_id();
 	data = tr->data[cpu];
@@ -884,11 +1145,62 @@ function_trace_call(unsigned long ip, unsigned long parent_ip)
 		trace_function(tr, data, ip, parent_ip, flags, pc);
 
 	atomic_dec(&data->disabled);
-	if (resched)
-		preempt_enable_no_resched_notrace();
-	else
-		preempt_enable_notrace();
+	ftrace_preempt_enable(resched);
+}
+
+static void
+function_trace_call(unsigned long ip, unsigned long parent_ip)
+{
+	struct trace_array *tr = &global_trace;
+	struct trace_array_cpu *data;
+	unsigned long flags;
+	long disabled;
+	int cpu;
+	int pc;
+
+	if (unlikely(!ftrace_function_enabled))
+		return;
+
+	/*
+	 * Need to use raw, since this must be called before the
+	 * recursive protection is performed.
+	 */
+	local_irq_save(flags);
+	cpu = raw_smp_processor_id();
+	data = tr->data[cpu];
+	disabled = atomic_inc_return(&data->disabled);
+
+	if (likely(disabled == 1)) {
+		pc = preempt_count();
+		trace_function(tr, data, ip, parent_ip, flags, pc);
+	}
+
+	atomic_dec(&data->disabled);
+	local_irq_restore(flags);
+}
+
+#ifdef CONFIG_FUNCTION_RET_TRACER
+void trace_function_return(struct ftrace_retfunc *trace)
+{
+	struct trace_array *tr = &global_trace;
+	struct trace_array_cpu *data;
+	unsigned long flags;
+	long disabled;
+	int cpu;
+	int pc;
+
+	raw_local_irq_save(flags);
+	cpu = raw_smp_processor_id();
+	data = tr->data[cpu];
+	disabled = atomic_inc_return(&data->disabled);
+	if (likely(disabled == 1)) {
+		pc = preempt_count();
+		__trace_function_return(tr, data, trace, flags, pc);
+	}
+	atomic_dec(&data->disabled);
+	raw_local_irq_restore(flags);
 }
+#endif /* CONFIG_FUNCTION_RET_TRACER */
 
 static struct ftrace_ops trace_ops __read_mostly =
 {
@@ -898,9 +1210,14 @@ static struct ftrace_ops trace_ops __read_mostly =
 void tracing_start_function_trace(void)
 {
 	ftrace_function_enabled = 0;
+
+	if (trace_flags & TRACE_ITER_PREEMPTONLY)
+		trace_ops.func = function_trace_call_preempt_only;
+	else
+		trace_ops.func = function_trace_call;
+
 	register_ftrace_function(&trace_ops);
-	if (tracer_enabled)
-		ftrace_function_enabled = 1;
+	ftrace_function_enabled = 1;
 }
 
 void tracing_stop_function_trace(void)
@@ -912,6 +1229,7 @@ void tracing_stop_function_trace(void)
 
 enum trace_file_type {
 	TRACE_FILE_LAT_FMT	= 1,
+	TRACE_FILE_ANNOTATE	= 2,
 };
 
 static void trace_iterator_increment(struct trace_iterator *iter, int cpu)
@@ -1047,10 +1365,6 @@ static void *s_start(struct seq_file *m, loff_t *pos)
 
 	atomic_inc(&trace_record_cmdline_disabled);
 
-	/* let the tracer grab locks here if needed */
-	if (current_trace->start)
-		current_trace->start(iter);
-
 	if (*pos != iter->pos) {
 		iter->ent = NULL;
 		iter->cpu = 0;
@@ -1077,14 +1391,7 @@ static void *s_start(struct seq_file *m, loff_t *pos)
 
 static void s_stop(struct seq_file *m, void *p)
 {
-	struct trace_iterator *iter = m->private;
-
 	atomic_dec(&trace_record_cmdline_disabled);
-
-	/* let the tracer release locks here if needed */
-	if (current_trace && current_trace == iter->trace && iter->trace->stop)
-		iter->trace->stop(iter);
-
 	mutex_unlock(&trace_types_lock);
 }
 
@@ -1143,7 +1450,7 @@ seq_print_sym_offset(struct trace_seq *s, const char *fmt,
 # define IP_FMT "%016lx"
 #endif
 
-static int
+int
 seq_print_ip_sym(struct trace_seq *s, unsigned long ip, unsigned long sym_flags)
 {
 	int ret;
@@ -1164,6 +1471,78 @@ seq_print_ip_sym(struct trace_seq *s, unsigned long ip, unsigned long sym_flags)
 	return ret;
 }
 
+static inline int seq_print_user_ip(struct trace_seq *s, struct mm_struct *mm,
+				    unsigned long ip, unsigned long sym_flags)
+{
+	struct file *file = NULL;
+	unsigned long vmstart = 0;
+	int ret = 1;
+
+	if (mm) {
+		const struct vm_area_struct *vma;
+
+		down_read(&mm->mmap_sem);
+		vma = find_vma(mm, ip);
+		if (vma) {
+			file = vma->vm_file;
+			vmstart = vma->vm_start;
+		}
+		if (file) {
+			ret = trace_seq_path(s, &file->f_path);
+			if (ret)
+				ret = trace_seq_printf(s, "[+0x%lx]", ip - vmstart);
+		}
+		up_read(&mm->mmap_sem);
+	}
+	if (ret && ((sym_flags & TRACE_ITER_SYM_ADDR) || !file))
+		ret = trace_seq_printf(s, " <" IP_FMT ">", ip);
+	return ret;
+}
+
+static int
+seq_print_userip_objs(const struct userstack_entry *entry, struct trace_seq *s,
+		      unsigned long sym_flags)
+{
+	struct mm_struct *mm = NULL;
+	int ret = 1;
+	unsigned int i;
+
+	if (trace_flags & TRACE_ITER_SYM_USEROBJ) {
+		struct task_struct *task;
+		/*
+		 * we do the lookup on the thread group leader,
+		 * since individual threads might have already quit!
+		 */
+		rcu_read_lock();
+		task = find_task_by_vpid(entry->ent.tgid);
+		if (task)
+			mm = get_task_mm(task);
+		rcu_read_unlock();
+	}
+
+	for (i = 0; i < FTRACE_STACK_ENTRIES; i++) {
+		unsigned long ip = entry->caller[i];
+
+		if (ip == ULONG_MAX || !ret)
+			break;
+		if (i && ret)
+			ret = trace_seq_puts(s, " <- ");
+		if (!ip) {
+			if (ret)
+				ret = trace_seq_puts(s, "??");
+			continue;
+		}
+		if (!ret)
+			break;
+		if (ret)
+			ret = seq_print_user_ip(s, mm, ip, sym_flags);
+	}
+
+	if (mm)
+		mmput(mm);
+	return ret;
+}
+
 static void print_lat_help_header(struct seq_file *m)
 {
 	seq_puts(m, "#                  _------=> CPU#            \n");
@@ -1338,6 +1717,23 @@ void trace_seq_print_cont(struct trace_seq *s, struct trace_iterator *iter)
 		trace_seq_putc(s, '\n');
 }
 
+static void test_cpu_buff_start(struct trace_iterator *iter)
+{
+	struct trace_seq *s = &iter->seq;
+
+	if (!(trace_flags & TRACE_ITER_ANNOTATE))
+		return;
+
+	if (!(iter->iter_flags & TRACE_FILE_ANNOTATE))
+		return;
+
+	if (cpu_isset(iter->cpu, iter->started))
+		return;
+
+	cpu_set(iter->cpu, iter->started);
+	trace_seq_printf(s, "##### CPU %u buffer started ####\n", iter->cpu);
+}
+
 static enum print_line_t
 print_lat_fmt(struct trace_iterator *iter, unsigned int trace_idx, int cpu)
 {
@@ -1357,6 +1753,8 @@ print_lat_fmt(struct trace_iterator *iter, unsigned int trace_idx, int cpu)
 	if (entry->type == TRACE_CONT)
 		return TRACE_TYPE_HANDLED;
 
+	test_cpu_buff_start(iter);
+
 	next_entry = find_next_entry(iter, NULL, &next_ts);
 	if (!next_entry)
 		next_ts = iter->ts;
@@ -1448,6 +1846,27 @@ print_lat_fmt(struct trace_iterator *iter, unsigned int trace_idx, int cpu)
 			trace_seq_print_cont(s, iter);
 		break;
 	}
+	case TRACE_BRANCH: {
+		struct trace_branch *field;
+
+		trace_assign_type(field, entry);
+
+		trace_seq_printf(s, "[%s] %s:%s:%d\n",
+				 field->correct ? "  ok  " : " MISS ",
+				 field->func,
+				 field->file,
+				 field->line);
+		break;
+	}
+	case TRACE_USER_STACK: {
+		struct userstack_entry *field;
+
+		trace_assign_type(field, entry);
+
+		seq_print_userip_objs(field, s, sym_flags);
+		trace_seq_putc(s, '\n');
+		break;
+	}
 	default:
 		trace_seq_printf(s, "Unknown type %d\n", entry->type);
 	}
@@ -1472,6 +1891,8 @@ static enum print_line_t print_trace_fmt(struct trace_iterator *iter)
 	if (entry->type == TRACE_CONT)
 		return TRACE_TYPE_HANDLED;
 
+	test_cpu_buff_start(iter);
+
 	comm = trace_find_cmdline(iter->ent->pid);
 
 	t = ns2usecs(iter->ts);
@@ -1581,6 +2002,35 @@ static enum print_line_t print_trace_fmt(struct trace_iterator *iter)
 			trace_seq_print_cont(s, iter);
 		break;
 	}
+	case TRACE_FN_RET: {
+		return print_return_function(iter);
+		break;
+	}
+	case TRACE_BRANCH: {
+		struct trace_branch *field;
+
+		trace_assign_type(field, entry);
+
+		trace_seq_printf(s, "[%s] %s:%s:%d\n",
+				 field->correct ? "  ok  " : " MISS ",
+				 field->func,
+				 field->file,
+				 field->line);
+		break;
+	}
+	case TRACE_USER_STACK: {
+		struct userstack_entry *field;
+
+		trace_assign_type(field, entry);
+
+		ret = seq_print_userip_objs(field, s, sym_flags);
+		if (!ret)
+			return TRACE_TYPE_PARTIAL_LINE;
+		ret = trace_seq_putc(s, '\n');
+		if (!ret)
+			return TRACE_TYPE_PARTIAL_LINE;
+		break;
+	}
 	}
 	return TRACE_TYPE_HANDLED;
 }
@@ -1640,6 +2090,7 @@ static enum print_line_t print_raw_fmt(struct trace_iterator *iter)
 		break;
 	}
 	case TRACE_SPECIAL:
+	case TRACE_USER_STACK:
 	case TRACE_STACK: {
 		struct special_entry *field;
 
@@ -1728,6 +2179,7 @@ static enum print_line_t print_hex_fmt(struct trace_iterator *iter)
 		break;
 	}
 	case TRACE_SPECIAL:
+	case TRACE_USER_STACK:
 	case TRACE_STACK: {
 		struct special_entry *field;
 
@@ -1782,6 +2234,7 @@ static enum print_line_t print_bin_fmt(struct trace_iterator *iter)
 		break;
 	}
 	case TRACE_SPECIAL:
+	case TRACE_USER_STACK:
 	case TRACE_STACK: {
 		struct special_entry *field;
 
@@ -1899,6 +2352,11 @@ __tracing_open(struct inode *inode, struct file *file, int *ret)
 	iter->trace = current_trace;
 	iter->pos = -1;
 
+	/* Annotate start of buffers if we had overruns */
+	if (ring_buffer_overruns(iter->tr->buffer))
+		iter->iter_flags |= TRACE_FILE_ANNOTATE;
+
+
 	for_each_tracing_cpu(cpu) {
 
 		iter->buffer_iter[cpu] =
@@ -1917,10 +2375,7 @@ __tracing_open(struct inode *inode, struct file *file, int *ret)
 	m->private = iter;
 
 	/* stop the trace while dumping */
-	if (iter->tr->ctrl) {
-		tracer_enabled = 0;
-		ftrace_function_enabled = 0;
-	}
+	tracing_stop();
 
 	if (iter->trace && iter->trace->open)
 			iter->trace->open(iter);
@@ -1966,14 +2421,7 @@ int tracing_release(struct inode *inode, struct file *file)
 		iter->trace->close(iter);
 
 	/* reenable tracing if it was previously enabled */
-	if (iter->tr->ctrl) {
-		tracer_enabled = 1;
-		/*
-		 * It is safe to enable function tracing even if it
-		 * isn't used
-		 */
-		ftrace_function_enabled = 1;
-	}
+	tracing_start();
 	mutex_unlock(&trace_types_lock);
 
 	seq_release(inode, file);
@@ -2189,13 +2637,16 @@ static struct file_operations tracing_cpumask_fops = {
 };
 
 static ssize_t
-tracing_iter_ctrl_read(struct file *filp, char __user *ubuf,
+tracing_trace_options_read(struct file *filp, char __user *ubuf,
 		       size_t cnt, loff_t *ppos)
 {
+	int i;
 	char *buf;
 	int r = 0;
 	int len = 0;
-	int i;
+	u32 tracer_flags = current_trace->flags->val;
+	struct tracer_opt *trace_opts = current_trace->flags->opts;
+
 
 	/* calulate max size */
 	for (i = 0; trace_options[i]; i++) {
@@ -2203,6 +2654,15 @@ tracing_iter_ctrl_read(struct file *filp, char __user *ubuf,
 		len += 3; /* "no" and space */
 	}
 
+	/*
+	 * Increase the size with names of options specific
+	 * of the current tracer.
+	 */
+	for (i = 0; trace_opts[i].name; i++) {
+		len += strlen(trace_opts[i].name);
+		len += 3; /* "no" and space */
+	}
+
 	/* +2 for \n and \0 */
 	buf = kmalloc(len + 2, GFP_KERNEL);
 	if (!buf)
@@ -2215,6 +2675,15 @@ tracing_iter_ctrl_read(struct file *filp, char __user *ubuf,
 			r += sprintf(buf + r, "no%s ", trace_options[i]);
 	}
 
+	for (i = 0; trace_opts[i].name; i++) {
+		if (tracer_flags & trace_opts[i].bit)
+			r += sprintf(buf + r, "%s ",
+				trace_opts[i].name);
+		else
+			r += sprintf(buf + r, "no%s ",
+				trace_opts[i].name);
+	}
+
 	r += sprintf(buf + r, "\n");
 	WARN_ON(r >= len + 2);
 
@@ -2225,13 +2694,48 @@ tracing_iter_ctrl_read(struct file *filp, char __user *ubuf,
 	return r;
 }
 
+/* Try to assign a tracer specific option */
+static int set_tracer_option(struct tracer *trace, char *cmp, int neg)
+{
+	struct tracer_flags *trace_flags = trace->flags;
+	struct tracer_opt *opts = NULL;
+	int ret = 0, i = 0;
+	int len;
+
+	for (i = 0; trace_flags->opts[i].name; i++) {
+		opts = &trace_flags->opts[i];
+		len = strlen(opts->name);
+
+		if (strncmp(cmp, opts->name, len) == 0) {
+			ret = trace->set_flag(trace_flags->val,
+				opts->bit, !neg);
+			break;
+		}
+	}
+	/* Not found */
+	if (!trace_flags->opts[i].name)
+		return -EINVAL;
+
+	/* Refused to handle */
+	if (ret)
+		return ret;
+
+	if (neg)
+		trace_flags->val &= ~opts->bit;
+	else
+		trace_flags->val |= opts->bit;
+
+	return 0;
+}
+
 static ssize_t
-tracing_iter_ctrl_write(struct file *filp, const char __user *ubuf,
+tracing_trace_options_write(struct file *filp, const char __user *ubuf,
 			size_t cnt, loff_t *ppos)
 {
 	char buf[64];
 	char *cmp = buf;
 	int neg = 0;
+	int ret;
 	int i;
 
 	if (cnt >= sizeof(buf))
@@ -2258,11 +2762,13 @@ tracing_iter_ctrl_write(struct file *filp, const char __user *ubuf,
 			break;
 		}
 	}
-	/*
-	 * If no option could be set, return an error:
-	 */
-	if (!trace_options[i])
-		return -EINVAL;
+
+	/* If no option could be set, test the specific tracer options */
+	if (!trace_options[i]) {
+		ret = set_tracer_option(current_trace, cmp, neg);
+		if (ret)
+			return ret;
+	}
 
 	filp->f_pos += cnt;
 
@@ -2271,8 +2777,8 @@ tracing_iter_ctrl_write(struct file *filp, const char __user *ubuf,
 
 static struct file_operations tracing_iter_fops = {
 	.open		= tracing_open_generic,
-	.read		= tracing_iter_ctrl_read,
-	.write		= tracing_iter_ctrl_write,
+	.read		= tracing_trace_options_read,
+	.write		= tracing_trace_options_write,
 };
 
 static const char readme_msg[] =
@@ -2286,9 +2792,9 @@ static const char readme_msg[] =
 	"# echo sched_switch > /debug/tracing/current_tracer\n"
 	"# cat /debug/tracing/current_tracer\n"
 	"sched_switch\n"
-	"# cat /debug/tracing/iter_ctrl\n"
+	"# cat /debug/tracing/trace_options\n"
 	"noprint-parent nosym-offset nosym-addr noverbose\n"
-	"# echo print-parent > /debug/tracing/iter_ctrl\n"
+	"# echo print-parent > /debug/tracing/trace_options\n"
 	"# echo 1 > /debug/tracing/tracing_enabled\n"
 	"# cat /debug/tracing/trace > /tmp/trace.txt\n"
 	"echo 0 > /debug/tracing/tracing_enabled\n"
@@ -2311,11 +2817,10 @@ static ssize_t
 tracing_ctrl_read(struct file *filp, char __user *ubuf,
 		  size_t cnt, loff_t *ppos)
 {
-	struct trace_array *tr = filp->private_data;
 	char buf[64];
 	int r;
 
-	r = sprintf(buf, "%ld\n", tr->ctrl);
+	r = sprintf(buf, "%u\n", tracer_enabled);
 	return simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
 }
 
@@ -2343,16 +2848,18 @@ tracing_ctrl_write(struct file *filp, const char __user *ubuf,
 	val = !!val;
 
 	mutex_lock(&trace_types_lock);
-	if (tr->ctrl ^ val) {
-		if (val)
+	if (tracer_enabled ^ val) {
+		if (val) {
 			tracer_enabled = 1;
-		else
+			if (current_trace->start)
+				current_trace->start(tr);
+			tracing_start();
+		} else {
 			tracer_enabled = 0;
-
-		tr->ctrl = val;
-
-		if (current_trace && current_trace->ctrl_update)
-			current_trace->ctrl_update(tr);
+			tracing_stop();
+			if (current_trace->stop)
+				current_trace->stop(tr);
+		}
 	}
 	mutex_unlock(&trace_types_lock);
 
@@ -2378,29 +2885,11 @@ tracing_set_trace_read(struct file *filp, char __user *ubuf,
 	return simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
 }
 
-static ssize_t
-tracing_set_trace_write(struct file *filp, const char __user *ubuf,
-			size_t cnt, loff_t *ppos)
+static int tracing_set_tracer(char *buf)
 {
 	struct trace_array *tr = &global_trace;
 	struct tracer *t;
-	char buf[max_tracer_type_len+1];
-	int i;
-	size_t ret;
-
-	ret = cnt;
-
-	if (cnt > max_tracer_type_len)
-		cnt = max_tracer_type_len;
-
-	if (copy_from_user(&buf, ubuf, cnt))
-		return -EFAULT;
-
-	buf[cnt] = 0;
-
-	/* strip ending whitespace. */
-	for (i = cnt - 1; i > 0 && isspace(buf[i]); i--)
-		buf[i] = 0;
+	int ret = 0;
 
 	mutex_lock(&trace_types_lock);
 	for (t = trace_types; t; t = t->next) {
@@ -2414,18 +2903,52 @@ tracing_set_trace_write(struct file *filp, const char __user *ubuf,
 	if (t == current_trace)
 		goto out;
 
+	trace_branch_disable();
 	if (current_trace && current_trace->reset)
 		current_trace->reset(tr);
 
 	current_trace = t;
-	if (t->init)
-		t->init(tr);
+	if (t->init) {
+		ret = t->init(tr);
+		if (ret)
+			goto out;
+	}
 
+	trace_branch_enable(tr);
  out:
 	mutex_unlock(&trace_types_lock);
 
-	if (ret > 0)
-		filp->f_pos += ret;
+	return ret;
+}
+
+static ssize_t
+tracing_set_trace_write(struct file *filp, const char __user *ubuf,
+			size_t cnt, loff_t *ppos)
+{
+	char buf[max_tracer_type_len+1];
+	int i;
+	size_t ret;
+	int err;
+
+	ret = cnt;
+
+	if (cnt > max_tracer_type_len)
+		cnt = max_tracer_type_len;
+
+	if (copy_from_user(&buf, ubuf, cnt))
+		return -EFAULT;
+
+	buf[cnt] = 0;
+
+	/* strip ending whitespace. */
+	for (i = cnt - 1; i > 0 && isspace(buf[i]); i--)
+		buf[i] = 0;
+
+	err = tracing_set_tracer(buf);
+	if (err)
+		return err;
+
+	filp->f_pos += ret;
 
 	return ret;
 }
@@ -2492,6 +3015,10 @@ static int tracing_open_pipe(struct inode *inode, struct file *filp)
 		return -ENOMEM;
 
 	mutex_lock(&trace_types_lock);
+
+	/* trace pipe does not show start of buffer */
+	cpus_setall(iter->started);
+
 	iter->tr = &global_trace;
 	iter->trace = current_trace;
 	filp->private_data = iter;
@@ -2667,7 +3194,7 @@ tracing_entries_read(struct file *filp, char __user *ubuf,
 	char buf[64];
 	int r;
 
-	r = sprintf(buf, "%lu\n", tr->entries);
+	r = sprintf(buf, "%lu\n", tr->entries >> 10);
 	return simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
 }
 
@@ -2678,7 +3205,6 @@ tracing_entries_write(struct file *filp, const char __user *ubuf,
 	unsigned long val;
 	char buf[64];
 	int ret, cpu;
-	struct trace_array *tr = filp->private_data;
 
 	if (cnt >= sizeof(buf))
 		return -EINVAL;
@@ -2698,12 +3224,7 @@ tracing_entries_write(struct file *filp, const char __user *ubuf,
 
 	mutex_lock(&trace_types_lock);
 
-	if (tr->ctrl) {
-		cnt = -EBUSY;
-		pr_info("ftrace: please disable tracing"
-			" before modifying buffer size\n");
-		goto out;
-	}
+	tracing_stop();
 
 	/* disable all cpu buffers */
 	for_each_tracing_cpu(cpu) {
@@ -2713,6 +3234,9 @@ tracing_entries_write(struct file *filp, const char __user *ubuf,
 			atomic_inc(&max_tr.data[cpu]->disabled);
 	}
 
+	/* value is in KB */
+	val <<= 10;
+
 	if (val != global_trace.entries) {
 		ret = ring_buffer_resize(global_trace.buffer, val);
 		if (ret < 0) {
@@ -2751,6 +3275,7 @@ tracing_entries_write(struct file *filp, const char __user *ubuf,
 			atomic_dec(&max_tr.data[cpu]->disabled);
 	}
 
+	tracing_start();
 	max_tr.entries = global_trace.entries;
 	mutex_unlock(&trace_types_lock);
 
@@ -2773,9 +3298,8 @@ tracing_mark_write(struct file *filp, const char __user *ubuf,
 {
 	char *buf;
 	char *end;
-	struct trace_array *tr = &global_trace;
 
-	if (!tr->ctrl || tracing_disabled)
+	if (tracing_disabled)
 		return -EINVAL;
 
 	if (cnt > TRACE_BUF_SIZE)
@@ -2841,22 +3365,38 @@ static struct file_operations tracing_mark_fops = {
 
 #ifdef CONFIG_DYNAMIC_FTRACE
 
+int __weak ftrace_arch_read_dyn_info(char *buf, int size)
+{
+	return 0;
+}
+
 static ssize_t
-tracing_read_long(struct file *filp, char __user *ubuf,
+tracing_read_dyn_info(struct file *filp, char __user *ubuf,
 		  size_t cnt, loff_t *ppos)
 {
+	static char ftrace_dyn_info_buffer[1024];
+	static DEFINE_MUTEX(dyn_info_mutex);
 	unsigned long *p = filp->private_data;
-	char buf[64];
+	char *buf = ftrace_dyn_info_buffer;
+	int size = ARRAY_SIZE(ftrace_dyn_info_buffer);
 	int r;
 
-	r = sprintf(buf, "%ld\n", *p);
+	mutex_lock(&dyn_info_mutex);
+	r = sprintf(buf, "%ld ", *p);
 
-	return simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
+	r += ftrace_arch_read_dyn_info(buf+r, (size-1)-r);
+	buf[r++] = '\n';
+
+	r = simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
+
+	mutex_unlock(&dyn_info_mutex);
+
+	return r;
 }
 
-static struct file_operations tracing_read_long_fops = {
+static struct file_operations tracing_dyn_info_fops = {
 	.open		= tracing_open_generic,
-	.read		= tracing_read_long,
+	.read		= tracing_read_dyn_info,
 };
 #endif
 
@@ -2897,10 +3437,10 @@ static __init int tracer_init_debugfs(void)
 	if (!entry)
 		pr_warning("Could not create debugfs 'tracing_enabled' entry\n");
 
-	entry = debugfs_create_file("iter_ctrl", 0644, d_tracer,
+	entry = debugfs_create_file("trace_options", 0644, d_tracer,
 				    NULL, &tracing_iter_fops);
 	if (!entry)
-		pr_warning("Could not create debugfs 'iter_ctrl' entry\n");
+		pr_warning("Could not create debugfs 'trace_options' entry\n");
 
 	entry = debugfs_create_file("tracing_cpumask", 0644, d_tracer,
 				    NULL, &tracing_cpumask_fops);
@@ -2950,11 +3490,11 @@ static __init int tracer_init_debugfs(void)
 		pr_warning("Could not create debugfs "
 			   "'trace_pipe' entry\n");
 
-	entry = debugfs_create_file("trace_entries", 0644, d_tracer,
+	entry = debugfs_create_file("buffer_size_kb", 0644, d_tracer,
 				    &global_trace, &tracing_entries_fops);
 	if (!entry)
 		pr_warning("Could not create debugfs "
-			   "'trace_entries' entry\n");
+			   "'buffer_size_kb' entry\n");
 
 	entry = debugfs_create_file("trace_marker", 0220, d_tracer,
 				    NULL, &tracing_mark_fops);
@@ -2965,7 +3505,7 @@ static __init int tracer_init_debugfs(void)
 #ifdef CONFIG_DYNAMIC_FTRACE
 	entry = debugfs_create_file("dyn_ftrace_total_info", 0444, d_tracer,
 				    &ftrace_update_tot_cnt,
-				    &tracing_read_long_fops);
+				    &tracing_dyn_info_fops);
 	if (!entry)
 		pr_warning("Could not create debugfs "
 			   "'dyn_ftrace_total_info' entry\n");
@@ -2988,7 +3528,7 @@ int trace_vprintk(unsigned long ip, const char *fmt, va_list args)
 	unsigned long flags, irq_flags;
 	int cpu, len = 0, size, pc;
 
-	if (!tr->ctrl || tracing_disabled)
+	if (tracing_disabled)
 		return 0;
 
 	pc = preempt_count();
@@ -3046,7 +3586,8 @@ EXPORT_SYMBOL_GPL(__ftrace_printk);
 static int trace_panic_handler(struct notifier_block *this,
 			       unsigned long event, void *unused)
 {
-	ftrace_dump();
+	if (ftrace_dump_on_oops)
+		ftrace_dump();
 	return NOTIFY_OK;
 }
 
@@ -3062,7 +3603,8 @@ static int trace_die_handler(struct notifier_block *self,
 {
 	switch (val) {
 	case DIE_OOPS:
-		ftrace_dump();
+		if (ftrace_dump_on_oops)
+			ftrace_dump();
 		break;
 	default:
 		break;
@@ -3103,7 +3645,6 @@ trace_printk_seq(struct trace_seq *s)
 	trace_seq_reset(s);
 }
 
-
 void ftrace_dump(void)
 {
 	static DEFINE_SPINLOCK(ftrace_dump_lock);
@@ -3128,6 +3669,9 @@ void ftrace_dump(void)
 		atomic_inc(&global_trace.data[cpu]->disabled);
 	}
 
+	/* don't look at user memory in panic mode */
+	trace_flags &= ~TRACE_ITER_SYM_USEROBJ;
+
 	printk(KERN_TRACE "Dumping ftrace buffer:\n");
 
 	iter.tr = &global_trace;
@@ -3221,7 +3765,6 @@ __init static int tracer_alloc_buffers(void)
 #endif
 
 	/* All seems OK, enable tracing */
-	global_trace.ctrl = tracer_enabled;
 	tracing_disabled = 0;
 
 	atomic_notifier_chain_register(&panic_notifier_list,
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 8465ad052707..28c15c2ebc22 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -8,6 +8,7 @@
 #include <linux/ring_buffer.h>
 #include <linux/mmiotrace.h>
 #include <linux/ftrace.h>
+#include <trace/boot.h>
 
 enum trace_type {
 	__TRACE_FIRST_TYPE = 0,
@@ -21,7 +22,11 @@ enum trace_type {
 	TRACE_SPECIAL,
 	TRACE_MMIO_RW,
 	TRACE_MMIO_MAP,
-	TRACE_BOOT,
+	TRACE_BRANCH,
+	TRACE_BOOT_CALL,
+	TRACE_BOOT_RET,
+	TRACE_FN_RET,
+	TRACE_USER_STACK,
 
 	__TRACE_LAST_TYPE
 };
@@ -38,6 +43,7 @@ struct trace_entry {
 	unsigned char		flags;
 	unsigned char		preempt_count;
 	int			pid;
+	int			tgid;
 };
 
 /*
@@ -48,6 +54,16 @@ struct ftrace_entry {
 	unsigned long		ip;
 	unsigned long		parent_ip;
 };
+
+/* Function return entry */
+struct ftrace_ret_entry {
+	struct trace_entry	ent;
+	unsigned long		ip;
+	unsigned long		parent_ip;
+	unsigned long long	calltime;
+	unsigned long long	rettime;
+	unsigned long		overrun;
+};
 extern struct tracer boot_tracer;
 
 /*
@@ -85,6 +101,11 @@ struct stack_entry {
 	unsigned long		caller[FTRACE_STACK_ENTRIES];
 };
 
+struct userstack_entry {
+	struct trace_entry	ent;
+	unsigned long		caller[FTRACE_STACK_ENTRIES];
+};
+
 /*
  * ftrace_printk entry:
  */
@@ -112,9 +133,24 @@ struct trace_mmiotrace_map {
 	struct mmiotrace_map	map;
 };
 
-struct trace_boot {
+struct trace_boot_call {
 	struct trace_entry	ent;
-	struct boot_trace	initcall;
+	struct boot_trace_call boot_call;
+};
+
+struct trace_boot_ret {
+	struct trace_entry	ent;
+	struct boot_trace_ret boot_ret;
+};
+
+#define TRACE_FUNC_SIZE 30
+#define TRACE_FILE_SIZE 20
+struct trace_branch {
+	struct trace_entry	ent;
+	unsigned	        line;
+	char			func[TRACE_FUNC_SIZE+1];
+	char			file[TRACE_FILE_SIZE+1];
+	char			correct;
 };
 
 /*
@@ -172,7 +208,6 @@ struct trace_iterator;
 struct trace_array {
 	struct ring_buffer	*buffer;
 	unsigned long		entries;
-	long			ctrl;
 	int			cpu;
 	cycle_t			time_start;
 	struct task_struct	*waiter;
@@ -212,13 +247,17 @@ extern void __ftrace_bad_type(void);
 		IF_ASSIGN(var, ent, struct ctx_switch_entry, 0);	\
 		IF_ASSIGN(var, ent, struct trace_field_cont, TRACE_CONT); \
 		IF_ASSIGN(var, ent, struct stack_entry, TRACE_STACK);	\
+		IF_ASSIGN(var, ent, struct userstack_entry, TRACE_USER_STACK);\
 		IF_ASSIGN(var, ent, struct print_entry, TRACE_PRINT);	\
 		IF_ASSIGN(var, ent, struct special_entry, 0);		\
 		IF_ASSIGN(var, ent, struct trace_mmiotrace_rw,		\
 			  TRACE_MMIO_RW);				\
 		IF_ASSIGN(var, ent, struct trace_mmiotrace_map,		\
 			  TRACE_MMIO_MAP);				\
-		IF_ASSIGN(var, ent, struct trace_boot, TRACE_BOOT);	\
+		IF_ASSIGN(var, ent, struct trace_boot_call, TRACE_BOOT_CALL);\
+		IF_ASSIGN(var, ent, struct trace_boot_ret, TRACE_BOOT_RET);\
+		IF_ASSIGN(var, ent, struct trace_branch, TRACE_BRANCH); \
+		IF_ASSIGN(var, ent, struct ftrace_ret_entry, TRACE_FN_RET);\
 		__ftrace_bad_type();					\
 	} while (0)
 
@@ -229,29 +268,55 @@ enum print_line_t {
 	TRACE_TYPE_UNHANDLED	= 2	/* Relay to other output functions */
 };
 
+
+/*
+ * An option specific to a tracer. This is a boolean value.
+ * The bit is the bit index that sets its value on the
+ * flags value in struct tracer_flags.
+ */
+struct tracer_opt {
+	const char 	*name; /* Will appear on the trace_options file */
+	u32 		bit; /* Mask assigned in val field in tracer_flags */
+};
+
+/*
+ * The set of specific options for a tracer. Your tracer
+ * have to set the initial value of the flags val.
+ */
+struct tracer_flags {
+	u32			val;
+	struct tracer_opt 	*opts;
+};
+
+/* Makes more easy to define a tracer opt */
+#define TRACER_OPT(s, b)	.name = #s, .bit = b
+
 /*
  * A specific tracer, represented by methods that operate on a trace array:
  */
 struct tracer {
 	const char		*name;
-	void			(*init)(struct trace_array *tr);
+	/* Your tracer should raise a warning if init fails */
+	int			(*init)(struct trace_array *tr);
 	void			(*reset)(struct trace_array *tr);
+	void			(*start)(struct trace_array *tr);
+	void			(*stop)(struct trace_array *tr);
 	void			(*open)(struct trace_iterator *iter);
 	void			(*pipe_open)(struct trace_iterator *iter);
 	void			(*close)(struct trace_iterator *iter);
-	void			(*start)(struct trace_iterator *iter);
-	void			(*stop)(struct trace_iterator *iter);
 	ssize_t			(*read)(struct trace_iterator *iter,
 					struct file *filp, char __user *ubuf,
 					size_t cnt, loff_t *ppos);
-	void			(*ctrl_update)(struct trace_array *tr);
 #ifdef CONFIG_FTRACE_STARTUP_TEST
 	int			(*selftest)(struct tracer *trace,
 					    struct trace_array *tr);
 #endif
 	enum print_line_t	(*print_line)(struct trace_iterator *iter);
+	/* If you handled the flag setting, return 0 */
+	int			(*set_flag)(u32 old_flags, u32 bit, int set);
 	struct tracer		*next;
 	int			print_max;
+	struct tracer_flags 	*flags;
 };
 
 struct trace_seq {
@@ -279,8 +344,11 @@ struct trace_iterator {
 	unsigned long		iter_flags;
 	loff_t			pos;
 	long			idx;
+
+	cpumask_t		started;
 };
 
+int tracing_is_enabled(void);
 void trace_wake_up(void);
 void tracing_reset(struct trace_array *tr, int cpu);
 int tracing_open_generic(struct inode *inode, struct file *filp);
@@ -320,9 +388,14 @@ void trace_function(struct trace_array *tr,
 		    unsigned long ip,
 		    unsigned long parent_ip,
 		    unsigned long flags, int pc);
+void
+trace_function_return(struct ftrace_retfunc *trace);
 
 void tracing_start_cmdline_record(void);
 void tracing_stop_cmdline_record(void);
+void tracing_sched_switch_assign_trace(struct trace_array *tr);
+void tracing_stop_sched_switch_record(void);
+void tracing_start_sched_switch_record(void);
 int register_tracer(struct tracer *type);
 void unregister_tracer(struct tracer *type);
 
@@ -383,12 +456,18 @@ extern int trace_selftest_startup_sched_switch(struct tracer *trace,
 					       struct trace_array *tr);
 extern int trace_selftest_startup_sysprof(struct tracer *trace,
 					       struct trace_array *tr);
+extern int trace_selftest_startup_branch(struct tracer *trace,
+					 struct trace_array *tr);
 #endif /* CONFIG_FTRACE_STARTUP_TEST */
 
 extern void *head_page(struct trace_array_cpu *data);
 extern int trace_seq_printf(struct trace_seq *s, const char *fmt, ...);
 extern void trace_seq_print_cont(struct trace_seq *s,
 				 struct trace_iterator *iter);
+
+extern int
+seq_print_ip_sym(struct trace_seq *s, unsigned long ip,
+		unsigned long sym_flags);
 extern ssize_t trace_seq_to_user(struct trace_seq *s, char __user *ubuf,
 				 size_t cnt);
 extern long ns2usecs(cycle_t nsec);
@@ -396,6 +475,17 @@ extern int trace_vprintk(unsigned long ip, const char *fmt, va_list args);
 
 extern unsigned long trace_flags;
 
+/* Standard output formatting function used for function return traces */
+#ifdef CONFIG_FUNCTION_RET_TRACER
+extern enum print_line_t print_return_function(struct trace_iterator *iter);
+#else
+static inline enum print_line_t
+print_return_function(struct trace_iterator *iter)
+{
+	return TRACE_TYPE_UNHANDLED;
+}
+#endif
+
 /*
  * trace_iterator_flags is an enumeration that defines bit
  * positions into trace_flags that controls the output.
@@ -415,8 +505,92 @@ enum trace_iterator_flags {
 	TRACE_ITER_STACKTRACE		= 0x100,
 	TRACE_ITER_SCHED_TREE		= 0x200,
 	TRACE_ITER_PRINTK		= 0x400,
+	TRACE_ITER_PREEMPTONLY		= 0x800,
+	TRACE_ITER_BRANCH		= 0x1000,
+	TRACE_ITER_ANNOTATE		= 0x2000,
+	TRACE_ITER_USERSTACKTRACE       = 0x4000,
+	TRACE_ITER_SYM_USEROBJ          = 0x8000
 };
 
+/*
+ * TRACE_ITER_SYM_MASK masks the options in trace_flags that
+ * control the output of kernel symbols.
+ */
+#define TRACE_ITER_SYM_MASK \
+	(TRACE_ITER_PRINT_PARENT|TRACE_ITER_SYM_OFFSET|TRACE_ITER_SYM_ADDR)
+
 extern struct tracer nop_trace;
 
+/**
+ * ftrace_preempt_disable - disable preemption scheduler safe
+ *
+ * When tracing can happen inside the scheduler, there exists
+ * cases that the tracing might happen before the need_resched
+ * flag is checked. If this happens and the tracer calls
+ * preempt_enable (after a disable), a schedule might take place
+ * causing an infinite recursion.
+ *
+ * To prevent this, we read the need_recshed flag before
+ * disabling preemption. When we want to enable preemption we
+ * check the flag, if it is set, then we call preempt_enable_no_resched.
+ * Otherwise, we call preempt_enable.
+ *
+ * The rational for doing the above is that if need resched is set
+ * and we have yet to reschedule, we are either in an atomic location
+ * (where we do not need to check for scheduling) or we are inside
+ * the scheduler and do not want to resched.
+ */
+static inline int ftrace_preempt_disable(void)
+{
+	int resched;
+
+	resched = need_resched();
+	preempt_disable_notrace();
+
+	return resched;
+}
+
+/**
+ * ftrace_preempt_enable - enable preemption scheduler safe
+ * @resched: the return value from ftrace_preempt_disable
+ *
+ * This is a scheduler safe way to enable preemption and not miss
+ * any preemption checks. The disabled saved the state of preemption.
+ * If resched is set, then we were either inside an atomic or
+ * are inside the scheduler (we would have already scheduled
+ * otherwise). In this case, we do not want to call normal
+ * preempt_enable, but preempt_enable_no_resched instead.
+ */
+static inline void ftrace_preempt_enable(int resched)
+{
+	if (resched)
+		preempt_enable_no_resched_notrace();
+	else
+		preempt_enable_notrace();
+}
+
+#ifdef CONFIG_BRANCH_TRACER
+extern int enable_branch_tracing(struct trace_array *tr);
+extern void disable_branch_tracing(void);
+static inline int trace_branch_enable(struct trace_array *tr)
+{
+	if (trace_flags & TRACE_ITER_BRANCH)
+		return enable_branch_tracing(tr);
+	return 0;
+}
+static inline void trace_branch_disable(void)
+{
+	/* due to races, always disable */
+	disable_branch_tracing();
+}
+#else
+static inline int trace_branch_enable(struct trace_array *tr)
+{
+	return 0;
+}
+static inline void trace_branch_disable(void)
+{
+}
+#endif /* CONFIG_BRANCH_TRACER */
+
 #endif /* _LINUX_KERNEL_TRACE_H */
diff --git a/kernel/trace/trace_boot.c b/kernel/trace/trace_boot.c
index d0a5e50eeff2..a4fa2c57e34e 100644
--- a/kernel/trace/trace_boot.c
+++ b/kernel/trace/trace_boot.c
@@ -13,73 +13,117 @@
 #include "trace.h"
 
 static struct trace_array *boot_trace;
-static int trace_boot_enabled;
+static bool pre_initcalls_finished;
 
-
-/* Should be started after do_pre_smp_initcalls() in init/main.c */
+/* Tells the boot tracer that the pre_smp_initcalls are finished.
+ * So we are ready .
+ * It doesn't enable sched events tracing however.
+ * You have to call enable_boot_trace to do so.
+ */
 void start_boot_trace(void)
 {
-	trace_boot_enabled = 1;
+	pre_initcalls_finished = true;
 }
 
-void stop_boot_trace(void)
+void enable_boot_trace(void)
 {
-	trace_boot_enabled = 0;
+	if (pre_initcalls_finished)
+		tracing_start_sched_switch_record();
 }
 
-void reset_boot_trace(struct trace_array *tr)
+void disable_boot_trace(void)
 {
-	stop_boot_trace();
+	if (pre_initcalls_finished)
+		tracing_stop_sched_switch_record();
 }
 
-static void boot_trace_init(struct trace_array *tr)
+static void reset_boot_trace(struct trace_array *tr)
 {
 	int cpu;
-	boot_trace = tr;
 
-	trace_boot_enabled = 0;
+	tr->time_start = ftrace_now(tr->cpu);
+
+	for_each_online_cpu(cpu)
+		tracing_reset(tr, cpu);
+}
+
+static int boot_trace_init(struct trace_array *tr)
+{
+	int cpu;
+	boot_trace = tr;
 
 	for_each_cpu_mask(cpu, cpu_possible_map)
 		tracing_reset(tr, cpu);
+
+	tracing_sched_switch_assign_trace(tr);
+	return 0;
 }
 
-static void boot_trace_ctrl_update(struct trace_array *tr)
+static enum print_line_t
+initcall_call_print_line(struct trace_iterator *iter)
 {
-	if (tr->ctrl)
-		start_boot_trace();
+	struct trace_entry *entry = iter->ent;
+	struct trace_seq *s = &iter->seq;
+	struct trace_boot_call *field;
+	struct boot_trace_call *call;
+	u64 ts;
+	unsigned long nsec_rem;
+	int ret;
+
+	trace_assign_type(field, entry);
+	call = &field->boot_call;
+	ts = iter->ts;
+	nsec_rem = do_div(ts, 1000000000);
+
+	ret = trace_seq_printf(s, "[%5ld.%09ld] calling  %s @ %i\n",
+			(unsigned long)ts, nsec_rem, call->func, call->caller);
+
+	if (!ret)
+		return TRACE_TYPE_PARTIAL_LINE;
 	else
-		stop_boot_trace();
+		return TRACE_TYPE_HANDLED;
 }
 
-static enum print_line_t initcall_print_line(struct trace_iterator *iter)
+static enum print_line_t
+initcall_ret_print_line(struct trace_iterator *iter)
 {
-	int ret;
 	struct trace_entry *entry = iter->ent;
-	struct trace_boot *field = (struct trace_boot *)entry;
-	struct boot_trace *it = &field->initcall;
 	struct trace_seq *s = &iter->seq;
-	struct timespec calltime = ktime_to_timespec(it->calltime);
-	struct timespec rettime = ktime_to_timespec(it->rettime);
-
-	if (entry->type == TRACE_BOOT) {
-		ret = trace_seq_printf(s, "[%5ld.%09ld] calling  %s @ %i\n",
-					  calltime.tv_sec,
-					  calltime.tv_nsec,
-					  it->func, it->caller);
-		if (!ret)
-			return TRACE_TYPE_PARTIAL_LINE;
-
-		ret = trace_seq_printf(s, "[%5ld.%09ld] initcall %s "
-					  "returned %d after %lld msecs\n",
-					  rettime.tv_sec,
-					  rettime.tv_nsec,
-					  it->func, it->result, it->duration);
-
-		if (!ret)
-			return TRACE_TYPE_PARTIAL_LINE;
+	struct trace_boot_ret *field;
+	struct boot_trace_ret *init_ret;
+	u64 ts;
+	unsigned long nsec_rem;
+	int ret;
+
+	trace_assign_type(field, entry);
+	init_ret = &field->boot_ret;
+	ts = iter->ts;
+	nsec_rem = do_div(ts, 1000000000);
+
+	ret = trace_seq_printf(s, "[%5ld.%09ld] initcall %s "
+			"returned %d after %llu msecs\n",
+			(unsigned long) ts,
+			nsec_rem,
+			init_ret->func, init_ret->result, init_ret->duration);
+
+	if (!ret)
+		return TRACE_TYPE_PARTIAL_LINE;
+	else
 		return TRACE_TYPE_HANDLED;
+}
+
+static enum print_line_t initcall_print_line(struct trace_iterator *iter)
+{
+	struct trace_entry *entry = iter->ent;
+
+	switch (entry->type) {
+	case TRACE_BOOT_CALL:
+		return initcall_call_print_line(iter);
+	case TRACE_BOOT_RET:
+		return initcall_ret_print_line(iter);
+	default:
+		return TRACE_TYPE_UNHANDLED;
 	}
-	return TRACE_TYPE_UNHANDLED;
 }
 
 struct tracer boot_tracer __read_mostly =
@@ -87,27 +131,53 @@ struct tracer boot_tracer __read_mostly =
 	.name		= "initcall",
 	.init		= boot_trace_init,
 	.reset		= reset_boot_trace,
-	.ctrl_update	= boot_trace_ctrl_update,
 	.print_line	= initcall_print_line,
 };
 
-void trace_boot(struct boot_trace *it, initcall_t fn)
+void trace_boot_call(struct boot_trace_call *bt, initcall_t fn)
 {
 	struct ring_buffer_event *event;
-	struct trace_boot *entry;
-	struct trace_array_cpu *data;
+	struct trace_boot_call *entry;
 	unsigned long irq_flags;
 	struct trace_array *tr = boot_trace;
 
-	if (!trace_boot_enabled)
+	if (!pre_initcalls_finished)
 		return;
 
 	/* Get its name now since this function could
 	 * disappear because it is in the .init section.
 	 */
-	sprint_symbol(it->func, (unsigned long)fn);
+	sprint_symbol(bt->func, (unsigned long)fn);
+	preempt_disable();
+
+	event = ring_buffer_lock_reserve(tr->buffer, sizeof(*entry),
+					 &irq_flags);
+	if (!event)
+		goto out;
+	entry	= ring_buffer_event_data(event);
+	tracing_generic_entry_update(&entry->ent, 0, 0);
+	entry->ent.type = TRACE_BOOT_CALL;
+	entry->boot_call = *bt;
+	ring_buffer_unlock_commit(tr->buffer, event, irq_flags);
+
+	trace_wake_up();
+
+ out:
+	preempt_enable();
+}
+
+void trace_boot_ret(struct boot_trace_ret *bt, initcall_t fn)
+{
+	struct ring_buffer_event *event;
+	struct trace_boot_ret *entry;
+	unsigned long irq_flags;
+	struct trace_array *tr = boot_trace;
+
+	if (!pre_initcalls_finished)
+		return;
+
+	sprint_symbol(bt->func, (unsigned long)fn);
 	preempt_disable();
-	data = tr->data[smp_processor_id()];
 
 	event = ring_buffer_lock_reserve(tr->buffer, sizeof(*entry),
 					 &irq_flags);
@@ -115,8 +185,8 @@ void trace_boot(struct boot_trace *it, initcall_t fn)
 		goto out;
 	entry	= ring_buffer_event_data(event);
 	tracing_generic_entry_update(&entry->ent, 0, 0);
-	entry->ent.type = TRACE_BOOT;
-	entry->initcall = *it;
+	entry->ent.type = TRACE_BOOT_RET;
+	entry->boot_ret = *bt;
 	ring_buffer_unlock_commit(tr->buffer, event, irq_flags);
 
 	trace_wake_up();
diff --git a/kernel/trace/trace_branch.c b/kernel/trace/trace_branch.c
new file mode 100644
index 000000000000..bc972753568d
--- /dev/null
+++ b/kernel/trace/trace_branch.c
@@ -0,0 +1,342 @@
+/*
+ * unlikely profiler
+ *
+ * Copyright (C) 2008 Steven Rostedt <srostedt@redhat.com>
+ */
+#include <linux/kallsyms.h>
+#include <linux/seq_file.h>
+#include <linux/spinlock.h>
+#include <linux/irqflags.h>
+#include <linux/debugfs.h>
+#include <linux/uaccess.h>
+#include <linux/module.h>
+#include <linux/ftrace.h>
+#include <linux/hash.h>
+#include <linux/fs.h>
+#include <asm/local.h>
+#include "trace.h"
+
+#ifdef CONFIG_BRANCH_TRACER
+
+static int branch_tracing_enabled __read_mostly;
+static DEFINE_MUTEX(branch_tracing_mutex);
+static struct trace_array *branch_tracer;
+
+static void
+probe_likely_condition(struct ftrace_branch_data *f, int val, int expect)
+{
+	struct trace_array *tr = branch_tracer;
+	struct ring_buffer_event *event;
+	struct trace_branch *entry;
+	unsigned long flags, irq_flags;
+	int cpu, pc;
+	const char *p;
+
+	/*
+	 * I would love to save just the ftrace_likely_data pointer, but
+	 * this code can also be used by modules. Ugly things can happen
+	 * if the module is unloaded, and then we go and read the
+	 * pointer.  This is slower, but much safer.
+	 */
+
+	if (unlikely(!tr))
+		return;
+
+	raw_local_irq_save(flags);
+	cpu = raw_smp_processor_id();
+	if (atomic_inc_return(&tr->data[cpu]->disabled) != 1)
+		goto out;
+
+	event = ring_buffer_lock_reserve(tr->buffer, sizeof(*entry),
+					 &irq_flags);
+	if (!event)
+		goto out;
+
+	pc = preempt_count();
+	entry	= ring_buffer_event_data(event);
+	tracing_generic_entry_update(&entry->ent, flags, pc);
+	entry->ent.type		= TRACE_BRANCH;
+
+	/* Strip off the path, only save the file */
+	p = f->file + strlen(f->file);
+	while (p >= f->file && *p != '/')
+		p--;
+	p++;
+
+	strncpy(entry->func, f->func, TRACE_FUNC_SIZE);
+	strncpy(entry->file, p, TRACE_FILE_SIZE);
+	entry->func[TRACE_FUNC_SIZE] = 0;
+	entry->file[TRACE_FILE_SIZE] = 0;
+	entry->line = f->line;
+	entry->correct = val == expect;
+
+	ring_buffer_unlock_commit(tr->buffer, event, irq_flags);
+
+ out:
+	atomic_dec(&tr->data[cpu]->disabled);
+	raw_local_irq_restore(flags);
+}
+
+static inline
+void trace_likely_condition(struct ftrace_branch_data *f, int val, int expect)
+{
+	if (!branch_tracing_enabled)
+		return;
+
+	probe_likely_condition(f, val, expect);
+}
+
+int enable_branch_tracing(struct trace_array *tr)
+{
+	int ret = 0;
+
+	mutex_lock(&branch_tracing_mutex);
+	branch_tracer = tr;
+	/*
+	 * Must be seen before enabling. The reader is a condition
+	 * where we do not need a matching rmb()
+	 */
+	smp_wmb();
+	branch_tracing_enabled++;
+	mutex_unlock(&branch_tracing_mutex);
+
+	return ret;
+}
+
+void disable_branch_tracing(void)
+{
+	mutex_lock(&branch_tracing_mutex);
+
+	if (!branch_tracing_enabled)
+		goto out_unlock;
+
+	branch_tracing_enabled--;
+
+ out_unlock:
+	mutex_unlock(&branch_tracing_mutex);
+}
+
+static void start_branch_trace(struct trace_array *tr)
+{
+	enable_branch_tracing(tr);
+}
+
+static void stop_branch_trace(struct trace_array *tr)
+{
+	disable_branch_tracing();
+}
+
+static int branch_trace_init(struct trace_array *tr)
+{
+	int cpu;
+
+	for_each_online_cpu(cpu)
+		tracing_reset(tr, cpu);
+
+	start_branch_trace(tr);
+	return 0;
+}
+
+static void branch_trace_reset(struct trace_array *tr)
+{
+	stop_branch_trace(tr);
+}
+
+struct tracer branch_trace __read_mostly =
+{
+	.name		= "branch",
+	.init		= branch_trace_init,
+	.reset		= branch_trace_reset,
+#ifdef CONFIG_FTRACE_SELFTEST
+	.selftest	= trace_selftest_startup_branch,
+#endif
+};
+
+__init static int init_branch_trace(void)
+{
+	return register_tracer(&branch_trace);
+}
+
+device_initcall(init_branch_trace);
+#else
+static inline
+void trace_likely_condition(struct ftrace_branch_data *f, int val, int expect)
+{
+}
+#endif /* CONFIG_BRANCH_TRACER */
+
+void ftrace_likely_update(struct ftrace_branch_data *f, int val, int expect)
+{
+	/*
+	 * I would love to have a trace point here instead, but the
+	 * trace point code is so inundated with unlikely and likely
+	 * conditions that the recursive nightmare that exists is too
+	 * much to try to get working. At least for now.
+	 */
+	trace_likely_condition(f, val, expect);
+
+	/* FIXME: Make this atomic! */
+	if (val == expect)
+		f->correct++;
+	else
+		f->incorrect++;
+}
+EXPORT_SYMBOL(ftrace_likely_update);
+
+struct ftrace_pointer {
+	void		*start;
+	void		*stop;
+	int		hit;
+};
+
+static void *
+t_next(struct seq_file *m, void *v, loff_t *pos)
+{
+	const struct ftrace_pointer *f = m->private;
+	struct ftrace_branch_data *p = v;
+
+	(*pos)++;
+
+	if (v == (void *)1)
+		return f->start;
+
+	++p;
+
+	if ((void *)p >= (void *)f->stop)
+		return NULL;
+
+	return p;
+}
+
+static void *t_start(struct seq_file *m, loff_t *pos)
+{
+	void *t = (void *)1;
+	loff_t l = 0;
+
+	for (; t && l < *pos; t = t_next(m, t, &l))
+		;
+
+	return t;
+}
+
+static void t_stop(struct seq_file *m, void *p)
+{
+}
+
+static int t_show(struct seq_file *m, void *v)
+{
+	const struct ftrace_pointer *fp = m->private;
+	struct ftrace_branch_data *p = v;
+	const char *f;
+	long percent;
+
+	if (v == (void *)1) {
+		if (fp->hit)
+			seq_printf(m, "   miss      hit    %% ");
+		else
+			seq_printf(m, " correct incorrect  %% ");
+		seq_printf(m, "       Function                "
+			      "  File              Line\n"
+			      " ------- ---------  - "
+			      "       --------                "
+			      "  ----              ----\n");
+		return 0;
+	}
+
+	/* Only print the file, not the path */
+	f = p->file + strlen(p->file);
+	while (f >= p->file && *f != '/')
+		f--;
+	f++;
+
+	/*
+	 * The miss is overlayed on correct, and hit on incorrect.
+	 */
+	if (p->correct) {
+		percent = p->incorrect * 100;
+		percent /= p->correct + p->incorrect;
+	} else
+		percent = p->incorrect ? 100 : -1;
+
+	seq_printf(m, "%8lu %8lu ",  p->correct, p->incorrect);
+	if (percent < 0)
+		seq_printf(m, "  X ");
+	else
+		seq_printf(m, "%3ld ", percent);
+	seq_printf(m, "%-30.30s %-20.20s %d\n", p->func, f, p->line);
+	return 0;
+}
+
+static struct seq_operations tracing_likely_seq_ops = {
+	.start		= t_start,
+	.next		= t_next,
+	.stop		= t_stop,
+	.show		= t_show,
+};
+
+static int tracing_branch_open(struct inode *inode, struct file *file)
+{
+	int ret;
+
+	ret = seq_open(file, &tracing_likely_seq_ops);
+	if (!ret) {
+		struct seq_file *m = file->private_data;
+		m->private = (void *)inode->i_private;
+	}
+
+	return ret;
+}
+
+static const struct file_operations tracing_branch_fops = {
+	.open		= tracing_branch_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+};
+
+#ifdef CONFIG_PROFILE_ALL_BRANCHES
+extern unsigned long __start_branch_profile[];
+extern unsigned long __stop_branch_profile[];
+
+static const struct ftrace_pointer ftrace_branch_pos = {
+	.start			= __start_branch_profile,
+	.stop			= __stop_branch_profile,
+	.hit			= 1,
+};
+
+#endif /* CONFIG_PROFILE_ALL_BRANCHES */
+
+extern unsigned long __start_annotated_branch_profile[];
+extern unsigned long __stop_annotated_branch_profile[];
+
+static const struct ftrace_pointer ftrace_annotated_branch_pos = {
+	.start			= __start_annotated_branch_profile,
+	.stop			= __stop_annotated_branch_profile,
+};
+
+static __init int ftrace_branch_init(void)
+{
+	struct dentry *d_tracer;
+	struct dentry *entry;
+
+	d_tracer = tracing_init_dentry();
+
+	entry = debugfs_create_file("profile_annotated_branch", 0444, d_tracer,
+				    (void *)&ftrace_annotated_branch_pos,
+				    &tracing_branch_fops);
+	if (!entry)
+		pr_warning("Could not create debugfs "
+			   "'profile_annotatet_branch' entry\n");
+
+#ifdef CONFIG_PROFILE_ALL_BRANCHES
+	entry = debugfs_create_file("profile_branch", 0444, d_tracer,
+				    (void *)&ftrace_branch_pos,
+				    &tracing_branch_fops);
+	if (!entry)
+		pr_warning("Could not create debugfs"
+			   " 'profile_branch' entry\n");
+#endif
+
+	return 0;
+}
+
+device_initcall(ftrace_branch_init);
diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c
index 0f85a64003d3..e74f6d0a3216 100644
--- a/kernel/trace/trace_functions.c
+++ b/kernel/trace/trace_functions.c
@@ -42,24 +42,20 @@ static void stop_function_trace(struct trace_array *tr)
 	tracing_stop_cmdline_record();
 }
 
-static void function_trace_init(struct trace_array *tr)
+static int function_trace_init(struct trace_array *tr)
 {
-	if (tr->ctrl)
-		start_function_trace(tr);
+	start_function_trace(tr);
+	return 0;
 }
 
 static void function_trace_reset(struct trace_array *tr)
 {
-	if (tr->ctrl)
-		stop_function_trace(tr);
+	stop_function_trace(tr);
 }
 
-static void function_trace_ctrl_update(struct trace_array *tr)
+static void function_trace_start(struct trace_array *tr)
 {
-	if (tr->ctrl)
-		start_function_trace(tr);
-	else
-		stop_function_trace(tr);
+	function_reset(tr);
 }
 
 static struct tracer function_trace __read_mostly =
@@ -67,7 +63,7 @@ static struct tracer function_trace __read_mostly =
 	.name	     = "function",
 	.init	     = function_trace_init,
 	.reset	     = function_trace_reset,
-	.ctrl_update = function_trace_ctrl_update,
+	.start	     = function_trace_start,
 #ifdef CONFIG_FTRACE_SELFTEST
 	.selftest    = trace_selftest_startup_function,
 #endif
diff --git a/kernel/trace/trace_functions_return.c b/kernel/trace/trace_functions_return.c
new file mode 100644
index 000000000000..e00d64509c9c
--- /dev/null
+++ b/kernel/trace/trace_functions_return.c
@@ -0,0 +1,98 @@
+/*
+ *
+ * Function return tracer.
+ * Copyright (c) 2008 Frederic Weisbecker <fweisbec@gmail.com>
+ * Mostly borrowed from function tracer which
+ * is Copyright (c) Steven Rostedt <srostedt@redhat.com>
+ *
+ */
+#include <linux/debugfs.h>
+#include <linux/uaccess.h>
+#include <linux/ftrace.h>
+#include <linux/fs.h>
+
+#include "trace.h"
+
+
+#define TRACE_RETURN_PRINT_OVERRUN	0x1
+static struct tracer_opt trace_opts[] = {
+	/* Display overruns or not */
+	{ TRACER_OPT(overrun, TRACE_RETURN_PRINT_OVERRUN) },
+	{ } /* Empty entry */
+};
+
+static struct tracer_flags tracer_flags = {
+	.val = 0, /* Don't display overruns by default */
+	.opts = trace_opts
+};
+
+
+static int return_trace_init(struct trace_array *tr)
+{
+	int cpu;
+	for_each_online_cpu(cpu)
+		tracing_reset(tr, cpu);
+
+	return register_ftrace_return(&trace_function_return);
+}
+
+static void return_trace_reset(struct trace_array *tr)
+{
+		unregister_ftrace_return();
+}
+
+
+enum print_line_t
+print_return_function(struct trace_iterator *iter)
+{
+	struct trace_seq *s = &iter->seq;
+	struct trace_entry *entry = iter->ent;
+	struct ftrace_ret_entry *field;
+	int ret;
+
+	if (entry->type == TRACE_FN_RET) {
+		trace_assign_type(field, entry);
+		ret = trace_seq_printf(s, "%pF -> ", (void *)field->parent_ip);
+		if (!ret)
+			return TRACE_TYPE_PARTIAL_LINE;
+
+		ret = seq_print_ip_sym(s, field->ip,
+					trace_flags & TRACE_ITER_SYM_MASK);
+		if (!ret)
+			return TRACE_TYPE_PARTIAL_LINE;
+
+		ret = trace_seq_printf(s, " (%llu ns)",
+					field->rettime - field->calltime);
+		if (!ret)
+			return TRACE_TYPE_PARTIAL_LINE;
+
+		if (tracer_flags.val & TRACE_RETURN_PRINT_OVERRUN) {
+			ret = trace_seq_printf(s, " (Overruns: %lu)",
+						field->overrun);
+			if (!ret)
+				return TRACE_TYPE_PARTIAL_LINE;
+		}
+
+		ret = trace_seq_printf(s, "\n");
+		if (!ret)
+			return TRACE_TYPE_PARTIAL_LINE;
+
+		return TRACE_TYPE_HANDLED;
+	}
+	return TRACE_TYPE_UNHANDLED;
+}
+
+static struct tracer return_trace __read_mostly = {
+	.name	     = "return",
+	.init	     = return_trace_init,
+	.reset	     = return_trace_reset,
+	.print_line = print_return_function,
+	.flags		= &tracer_flags,
+};
+
+static __init int init_return_trace(void)
+{
+	return register_tracer(&return_trace);
+}
+
+device_initcall(init_return_trace);
diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c
index 9c74071c10e0..7c2e326bbc8b 100644
--- a/kernel/trace/trace_irqsoff.c
+++ b/kernel/trace/trace_irqsoff.c
@@ -353,15 +353,28 @@ void trace_preempt_off(unsigned long a0, unsigned long a1)
 }
 #endif /* CONFIG_PREEMPT_TRACER */
 
+/*
+ * save_tracer_enabled is used to save the state of the tracer_enabled
+ * variable when we disable it when we open a trace output file.
+ */
+static int save_tracer_enabled;
+
 static void start_irqsoff_tracer(struct trace_array *tr)
 {
 	register_ftrace_function(&trace_ops);
-	tracer_enabled = 1;
+	if (tracing_is_enabled()) {
+		tracer_enabled = 1;
+		save_tracer_enabled = 1;
+	} else {
+		tracer_enabled = 0;
+		save_tracer_enabled = 0;
+	}
 }
 
 static void stop_irqsoff_tracer(struct trace_array *tr)
 {
 	tracer_enabled = 0;
+	save_tracer_enabled = 0;
 	unregister_ftrace_function(&trace_ops);
 }
 
@@ -370,53 +383,55 @@ static void __irqsoff_tracer_init(struct trace_array *tr)
 	irqsoff_trace = tr;
 	/* make sure that the tracer is visible */
 	smp_wmb();
-
-	if (tr->ctrl)
-		start_irqsoff_tracer(tr);
+	start_irqsoff_tracer(tr);
 }
 
 static void irqsoff_tracer_reset(struct trace_array *tr)
 {
-	if (tr->ctrl)
-		stop_irqsoff_tracer(tr);
+	stop_irqsoff_tracer(tr);
 }
 
-static void irqsoff_tracer_ctrl_update(struct trace_array *tr)
+static void irqsoff_tracer_start(struct trace_array *tr)
 {
-	if (tr->ctrl)
-		start_irqsoff_tracer(tr);
-	else
-		stop_irqsoff_tracer(tr);
+	tracer_enabled = 1;
+	save_tracer_enabled = 1;
+}
+
+static void irqsoff_tracer_stop(struct trace_array *tr)
+{
+	tracer_enabled = 0;
+	save_tracer_enabled = 0;
 }
 
 static void irqsoff_tracer_open(struct trace_iterator *iter)
 {
 	/* stop the trace while dumping */
-	if (iter->tr->ctrl)
-		stop_irqsoff_tracer(iter->tr);
+	tracer_enabled = 0;
 }
 
 static void irqsoff_tracer_close(struct trace_iterator *iter)
 {
-	if (iter->tr->ctrl)
-		start_irqsoff_tracer(iter->tr);
+	/* restart tracing */
+	tracer_enabled = save_tracer_enabled;
 }
 
 #ifdef CONFIG_IRQSOFF_TRACER
-static void irqsoff_tracer_init(struct trace_array *tr)
+static int irqsoff_tracer_init(struct trace_array *tr)
 {
 	trace_type = TRACER_IRQS_OFF;
 
 	__irqsoff_tracer_init(tr);
+	return 0;
 }
 static struct tracer irqsoff_tracer __read_mostly =
 {
 	.name		= "irqsoff",
 	.init		= irqsoff_tracer_init,
 	.reset		= irqsoff_tracer_reset,
+	.start		= irqsoff_tracer_start,
+	.stop		= irqsoff_tracer_stop,
 	.open		= irqsoff_tracer_open,
 	.close		= irqsoff_tracer_close,
-	.ctrl_update	= irqsoff_tracer_ctrl_update,
 	.print_max	= 1,
 #ifdef CONFIG_FTRACE_SELFTEST
 	.selftest    = trace_selftest_startup_irqsoff,
@@ -428,11 +443,12 @@ static struct tracer irqsoff_tracer __read_mostly =
 #endif
 
 #ifdef CONFIG_PREEMPT_TRACER
-static void preemptoff_tracer_init(struct trace_array *tr)
+static int preemptoff_tracer_init(struct trace_array *tr)
 {
 	trace_type = TRACER_PREEMPT_OFF;
 
 	__irqsoff_tracer_init(tr);
+	return 0;
 }
 
 static struct tracer preemptoff_tracer __read_mostly =
@@ -440,9 +456,10 @@ static struct tracer preemptoff_tracer __read_mostly =
 	.name		= "preemptoff",
 	.init		= preemptoff_tracer_init,
 	.reset		= irqsoff_tracer_reset,
+	.start		= irqsoff_tracer_start,
+	.stop		= irqsoff_tracer_stop,
 	.open		= irqsoff_tracer_open,
 	.close		= irqsoff_tracer_close,
-	.ctrl_update	= irqsoff_tracer_ctrl_update,
 	.print_max	= 1,
 #ifdef CONFIG_FTRACE_SELFTEST
 	.selftest    = trace_selftest_startup_preemptoff,
@@ -456,11 +473,12 @@ static struct tracer preemptoff_tracer __read_mostly =
 #if defined(CONFIG_IRQSOFF_TRACER) && \
 	defined(CONFIG_PREEMPT_TRACER)
 
-static void preemptirqsoff_tracer_init(struct trace_array *tr)
+static int preemptirqsoff_tracer_init(struct trace_array *tr)
 {
 	trace_type = TRACER_IRQS_OFF | TRACER_PREEMPT_OFF;
 
 	__irqsoff_tracer_init(tr);
+	return 0;
 }
 
 static struct tracer preemptirqsoff_tracer __read_mostly =
@@ -468,9 +486,10 @@ static struct tracer preemptirqsoff_tracer __read_mostly =
 	.name		= "preemptirqsoff",
 	.init		= preemptirqsoff_tracer_init,
 	.reset		= irqsoff_tracer_reset,
+	.start		= irqsoff_tracer_start,
+	.stop		= irqsoff_tracer_stop,
 	.open		= irqsoff_tracer_open,
 	.close		= irqsoff_tracer_close,
-	.ctrl_update	= irqsoff_tracer_ctrl_update,
 	.print_max	= 1,
 #ifdef CONFIG_FTRACE_SELFTEST
 	.selftest    = trace_selftest_startup_preemptirqsoff,
diff --git a/kernel/trace/trace_mmiotrace.c b/kernel/trace/trace_mmiotrace.c
index e62cbf78eab6..2a98a206acc2 100644
--- a/kernel/trace/trace_mmiotrace.c
+++ b/kernel/trace/trace_mmiotrace.c
@@ -32,34 +32,29 @@ static void mmio_reset_data(struct trace_array *tr)
 		tracing_reset(tr, cpu);
 }
 
-static void mmio_trace_init(struct trace_array *tr)
+static int mmio_trace_init(struct trace_array *tr)
 {
 	pr_debug("in %s\n", __func__);
 	mmio_trace_array = tr;
-	if (tr->ctrl) {
-		mmio_reset_data(tr);
-		enable_mmiotrace();
-	}
+
+	mmio_reset_data(tr);
+	enable_mmiotrace();
+	return 0;
 }
 
 static void mmio_trace_reset(struct trace_array *tr)
 {
 	pr_debug("in %s\n", __func__);
-	if (tr->ctrl)
-		disable_mmiotrace();
+
+	disable_mmiotrace();
 	mmio_reset_data(tr);
 	mmio_trace_array = NULL;
 }
 
-static void mmio_trace_ctrl_update(struct trace_array *tr)
+static void mmio_trace_start(struct trace_array *tr)
 {
 	pr_debug("in %s\n", __func__);
-	if (tr->ctrl) {
-		mmio_reset_data(tr);
-		enable_mmiotrace();
-	} else {
-		disable_mmiotrace();
-	}
+	mmio_reset_data(tr);
 }
 
 static int mmio_print_pcidev(struct trace_seq *s, const struct pci_dev *dev)
@@ -296,10 +291,10 @@ static struct tracer mmio_tracer __read_mostly =
 	.name		= "mmiotrace",
 	.init		= mmio_trace_init,
 	.reset		= mmio_trace_reset,
+	.start		= mmio_trace_start,
 	.pipe_open	= mmio_pipe_open,
 	.close		= mmio_close,
 	.read		= mmio_read,
-	.ctrl_update	= mmio_trace_ctrl_update,
 	.print_line	= mmio_print_line,
 };
 
diff --git a/kernel/trace/trace_nop.c b/kernel/trace/trace_nop.c
index 4592b4862515..b9767acd30ac 100644
--- a/kernel/trace/trace_nop.c
+++ b/kernel/trace/trace_nop.c
@@ -12,6 +12,27 @@
 
 #include "trace.h"
 
+/* Our two options */
+enum {
+	TRACE_NOP_OPT_ACCEPT = 0x1,
+	TRACE_NOP_OPT_REFUSE = 0x2
+};
+
+/* Options for the tracer (see trace_options file) */
+static struct tracer_opt nop_opts[] = {
+	/* Option that will be accepted by set_flag callback */
+	{ TRACER_OPT(test_nop_accept, TRACE_NOP_OPT_ACCEPT) },
+	/* Option that will be refused by set_flag callback */
+	{ TRACER_OPT(test_nop_refuse, TRACE_NOP_OPT_REFUSE) },
+	{ } /* Always set a last empty entry */
+};
+
+static struct tracer_flags nop_flags = {
+	/* You can check your flags value here when you want. */
+	.val = 0, /* By default: all flags disabled */
+	.opts = nop_opts
+};
+
 static struct trace_array	*ctx_trace;
 
 static void start_nop_trace(struct trace_array *tr)
@@ -24,7 +45,7 @@ static void stop_nop_trace(struct trace_array *tr)
 	/* Nothing to do! */
 }
 
-static void nop_trace_init(struct trace_array *tr)
+static int nop_trace_init(struct trace_array *tr)
 {
 	int cpu;
 	ctx_trace = tr;
@@ -32,33 +53,53 @@ static void nop_trace_init(struct trace_array *tr)
 	for_each_online_cpu(cpu)
 		tracing_reset(tr, cpu);
 
-	if (tr->ctrl)
-		start_nop_trace(tr);
+	start_nop_trace(tr);
+	return 0;
 }
 
 static void nop_trace_reset(struct trace_array *tr)
 {
-	if (tr->ctrl)
-		stop_nop_trace(tr);
+	stop_nop_trace(tr);
 }
 
-static void nop_trace_ctrl_update(struct trace_array *tr)
+/* It only serves as a signal handler and a callback to
+ * accept or refuse tthe setting of a flag.
+ * If you don't implement it, then the flag setting will be
+ * automatically accepted.
+ */
+static int nop_set_flag(u32 old_flags, u32 bit, int set)
 {
-	/* When starting a new trace, reset the buffers */
-	if (tr->ctrl)
-		start_nop_trace(tr);
-	else
-		stop_nop_trace(tr);
+	/*
+	 * Note that you don't need to update nop_flags.val yourself.
+	 * The tracing Api will do it automatically if you return 0
+	 */
+	if (bit == TRACE_NOP_OPT_ACCEPT) {
+		printk(KERN_DEBUG "nop_test_accept flag set to %d: we accept."
+			" Now cat trace_options to see the result\n",
+			set);
+		return 0;
+	}
+
+	if (bit == TRACE_NOP_OPT_REFUSE) {
+		printk(KERN_DEBUG "nop_test_refuse flag set to %d: we refuse."
+			"Now cat trace_options to see the result\n",
+			set);
+		return -EINVAL;
+	}
+
+	return 0;
 }
 
+
 struct tracer nop_trace __read_mostly =
 {
 	.name		= "nop",
 	.init		= nop_trace_init,
 	.reset		= nop_trace_reset,
-	.ctrl_update	= nop_trace_ctrl_update,
 #ifdef CONFIG_FTRACE_SELFTEST
 	.selftest	= trace_selftest_startup_nop,
 #endif
+	.flags		= &nop_flags,
+	.set_flag	= nop_set_flag
 };
 
diff --git a/kernel/trace/trace_sched_switch.c b/kernel/trace/trace_sched_switch.c
index b8f56beb1a62..863390557b44 100644
--- a/kernel/trace/trace_sched_switch.c
+++ b/kernel/trace/trace_sched_switch.c
@@ -16,7 +16,8 @@
 
 static struct trace_array	*ctx_trace;
 static int __read_mostly	tracer_enabled;
-static atomic_t			sched_ref;
+static int			sched_ref;
+static DEFINE_MUTEX(sched_register_mutex);
 
 static void
 probe_sched_switch(struct rq *__rq, struct task_struct *prev,
@@ -27,7 +28,7 @@ probe_sched_switch(struct rq *__rq, struct task_struct *prev,
 	int cpu;
 	int pc;
 
-	if (!atomic_read(&sched_ref))
+	if (!sched_ref)
 		return;
 
 	tracing_record_cmdline(prev);
@@ -123,20 +124,18 @@ static void tracing_sched_unregister(void)
 
 static void tracing_start_sched_switch(void)
 {
-	long ref;
-
-	ref = atomic_inc_return(&sched_ref);
-	if (ref == 1)
+	mutex_lock(&sched_register_mutex);
+	if (!(sched_ref++))
 		tracing_sched_register();
+	mutex_unlock(&sched_register_mutex);
 }
 
 static void tracing_stop_sched_switch(void)
 {
-	long ref;
-
-	ref = atomic_dec_and_test(&sched_ref);
-	if (ref)
+	mutex_lock(&sched_register_mutex);
+	if (!(--sched_ref))
 		tracing_sched_unregister();
+	mutex_unlock(&sched_register_mutex);
 }
 
 void tracing_start_cmdline_record(void)
@@ -149,40 +148,86 @@ void tracing_stop_cmdline_record(void)
 	tracing_stop_sched_switch();
 }
 
+/**
+ * tracing_start_sched_switch_record - start tracing context switches
+ *
+ * Turns on context switch tracing for a tracer.
+ */
+void tracing_start_sched_switch_record(void)
+{
+	if (unlikely(!ctx_trace)) {
+		WARN_ON(1);
+		return;
+	}
+
+	tracing_start_sched_switch();
+
+	mutex_lock(&sched_register_mutex);
+	tracer_enabled++;
+	mutex_unlock(&sched_register_mutex);
+}
+
+/**
+ * tracing_stop_sched_switch_record - start tracing context switches
+ *
+ * Turns off context switch tracing for a tracer.
+ */
+void tracing_stop_sched_switch_record(void)
+{
+	mutex_lock(&sched_register_mutex);
+	tracer_enabled--;
+	WARN_ON(tracer_enabled < 0);
+	mutex_unlock(&sched_register_mutex);
+
+	tracing_stop_sched_switch();
+}
+
+/**
+ * tracing_sched_switch_assign_trace - assign a trace array for ctx switch
+ * @tr: trace array pointer to assign
+ *
+ * Some tracers might want to record the context switches in their
+ * trace. This function lets those tracers assign the trace array
+ * to use.
+ */
+void tracing_sched_switch_assign_trace(struct trace_array *tr)
+{
+	ctx_trace = tr;
+}
+
 static void start_sched_trace(struct trace_array *tr)
 {
 	sched_switch_reset(tr);
-	tracing_start_cmdline_record();
-	tracer_enabled = 1;
+	tracing_start_sched_switch_record();
 }
 
 static void stop_sched_trace(struct trace_array *tr)
 {
-	tracer_enabled = 0;
-	tracing_stop_cmdline_record();
+	tracing_stop_sched_switch_record();
 }
 
-static void sched_switch_trace_init(struct trace_array *tr)
+static int sched_switch_trace_init(struct trace_array *tr)
 {
 	ctx_trace = tr;
-
-	if (tr->ctrl)
-		start_sched_trace(tr);
+	start_sched_trace(tr);
+	return 0;
 }
 
 static void sched_switch_trace_reset(struct trace_array *tr)
 {
-	if (tr->ctrl)
+	if (sched_ref)
 		stop_sched_trace(tr);
 }
 
-static void sched_switch_trace_ctrl_update(struct trace_array *tr)
+static void sched_switch_trace_start(struct trace_array *tr)
 {
-	/* When starting a new trace, reset the buffers */
-	if (tr->ctrl)
-		start_sched_trace(tr);
-	else
-		stop_sched_trace(tr);
+	sched_switch_reset(tr);
+	tracing_start_sched_switch();
+}
+
+static void sched_switch_trace_stop(struct trace_array *tr)
+{
+	tracing_stop_sched_switch();
 }
 
 static struct tracer sched_switch_trace __read_mostly =
@@ -190,7 +235,8 @@ static struct tracer sched_switch_trace __read_mostly =
 	.name		= "sched_switch",
 	.init		= sched_switch_trace_init,
 	.reset		= sched_switch_trace_reset,
-	.ctrl_update	= sched_switch_trace_ctrl_update,
+	.start		= sched_switch_trace_start,
+	.stop		= sched_switch_trace_stop,
 #ifdef CONFIG_FTRACE_SELFTEST
 	.selftest    = trace_selftest_startup_sched_switch,
 #endif
@@ -198,14 +244,6 @@ static struct tracer sched_switch_trace __read_mostly =
 
 __init static int init_sched_switch_trace(void)
 {
-	int ret = 0;
-
-	if (atomic_read(&sched_ref))
-		ret = tracing_sched_register();
-	if (ret) {
-		pr_info("error registering scheduler trace\n");
-		return ret;
-	}
 	return register_tracer(&sched_switch_trace);
 }
 device_initcall(init_sched_switch_trace);
diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c
index 3ae93f16b565..0067b49746c1 100644
--- a/kernel/trace/trace_sched_wakeup.c
+++ b/kernel/trace/trace_sched_wakeup.c
@@ -50,8 +50,7 @@ wakeup_tracer_call(unsigned long ip, unsigned long parent_ip)
 		return;
 
 	pc = preempt_count();
-	resched = need_resched();
-	preempt_disable_notrace();
+	resched = ftrace_preempt_disable();
 
 	cpu = raw_smp_processor_id();
 	data = tr->data[cpu];
@@ -81,15 +80,7 @@ wakeup_tracer_call(unsigned long ip, unsigned long parent_ip)
  out:
 	atomic_dec(&data->disabled);
 
-	/*
-	 * To prevent recursion from the scheduler, if the
-	 * resched flag was set before we entered, then
-	 * don't reschedule.
-	 */
-	if (resched)
-		preempt_enable_no_resched_notrace();
-	else
-		preempt_enable_notrace();
+	ftrace_preempt_enable(resched);
 }
 
 static struct ftrace_ops trace_ops __read_mostly =
@@ -271,6 +262,12 @@ out:
 	atomic_dec(&wakeup_trace->data[cpu]->disabled);
 }
 
+/*
+ * save_tracer_enabled is used to save the state of the tracer_enabled
+ * variable when we disable it when we open a trace output file.
+ */
+static int save_tracer_enabled;
+
 static void start_wakeup_tracer(struct trace_array *tr)
 {
 	int ret;
@@ -309,7 +306,13 @@ static void start_wakeup_tracer(struct trace_array *tr)
 
 	register_ftrace_function(&trace_ops);
 
-	tracer_enabled = 1;
+	if (tracing_is_enabled()) {
+		tracer_enabled = 1;
+		save_tracer_enabled = 1;
+	} else {
+		tracer_enabled = 0;
+		save_tracer_enabled = 0;
+	}
 
 	return;
 fail_deprobe_wake_new:
@@ -321,49 +324,53 @@ fail_deprobe:
 static void stop_wakeup_tracer(struct trace_array *tr)
 {
 	tracer_enabled = 0;
+	save_tracer_enabled = 0;
 	unregister_ftrace_function(&trace_ops);
 	unregister_trace_sched_switch(probe_wakeup_sched_switch);
 	unregister_trace_sched_wakeup_new(probe_wakeup);
 	unregister_trace_sched_wakeup(probe_wakeup);
 }
 
-static void wakeup_tracer_init(struct trace_array *tr)
+static int wakeup_tracer_init(struct trace_array *tr)
 {
 	wakeup_trace = tr;
-
-	if (tr->ctrl)
-		start_wakeup_tracer(tr);
+	start_wakeup_tracer(tr);
+	return 0;
 }
 
 static void wakeup_tracer_reset(struct trace_array *tr)
 {
-	if (tr->ctrl) {
-		stop_wakeup_tracer(tr);
-		/* make sure we put back any tasks we are tracing */
-		wakeup_reset(tr);
-	}
+	stop_wakeup_tracer(tr);
+	/* make sure we put back any tasks we are tracing */
+	wakeup_reset(tr);
+}
+
+static void wakeup_tracer_start(struct trace_array *tr)
+{
+	wakeup_reset(tr);
+	tracer_enabled = 1;
+	save_tracer_enabled = 1;
 }
 
-static void wakeup_tracer_ctrl_update(struct trace_array *tr)
+static void wakeup_tracer_stop(struct trace_array *tr)
 {
-	if (tr->ctrl)
-		start_wakeup_tracer(tr);
-	else
-		stop_wakeup_tracer(tr);
+	tracer_enabled = 0;
+	save_tracer_enabled = 0;
 }
 
 static void wakeup_tracer_open(struct trace_iterator *iter)
 {
 	/* stop the trace while dumping */
-	if (iter->tr->ctrl)
-		stop_wakeup_tracer(iter->tr);
+	tracer_enabled = 0;
 }
 
 static void wakeup_tracer_close(struct trace_iterator *iter)
 {
 	/* forget about any processes we were recording */
-	if (iter->tr->ctrl)
-		start_wakeup_tracer(iter->tr);
+	if (save_tracer_enabled) {
+		wakeup_reset(iter->tr);
+		tracer_enabled = 1;
+	}
 }
 
 static struct tracer wakeup_tracer __read_mostly =
@@ -371,9 +378,10 @@ static struct tracer wakeup_tracer __read_mostly =
 	.name		= "wakeup",
 	.init		= wakeup_tracer_init,
 	.reset		= wakeup_tracer_reset,
+	.start		= wakeup_tracer_start,
+	.stop		= wakeup_tracer_stop,
 	.open		= wakeup_tracer_open,
 	.close		= wakeup_tracer_close,
-	.ctrl_update	= wakeup_tracer_ctrl_update,
 	.print_max	= 1,
 #ifdef CONFIG_FTRACE_SELFTEST
 	.selftest    = trace_selftest_startup_wakeup,
diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c
index 90bc752a7580..88c8eb70f54a 100644
--- a/kernel/trace/trace_selftest.c
+++ b/kernel/trace/trace_selftest.c
@@ -13,6 +13,7 @@ static inline int trace_valid_entry(struct trace_entry *entry)
 	case TRACE_STACK:
 	case TRACE_PRINT:
 	case TRACE_SPECIAL:
+	case TRACE_BRANCH:
 		return 1;
 	}
 	return 0;
@@ -51,7 +52,7 @@ static int trace_test_buffer(struct trace_array *tr, unsigned long *count)
 	int cpu, ret = 0;
 
 	/* Don't allow flipping of max traces now */
-	raw_local_irq_save(flags);
+	local_irq_save(flags);
 	__raw_spin_lock(&ftrace_max_lock);
 
 	cnt = ring_buffer_entries(tr->buffer);
@@ -62,7 +63,7 @@ static int trace_test_buffer(struct trace_array *tr, unsigned long *count)
 			break;
 	}
 	__raw_spin_unlock(&ftrace_max_lock);
-	raw_local_irq_restore(flags);
+	local_irq_restore(flags);
 
 	if (count)
 		*count = cnt;
@@ -70,6 +71,11 @@ static int trace_test_buffer(struct trace_array *tr, unsigned long *count)
 	return ret;
 }
 
+static inline void warn_failed_init_tracer(struct tracer *trace, int init_ret)
+{
+	printk(KERN_WARNING "Failed to init %s tracer, init returned %d\n",
+		trace->name, init_ret);
+}
 #ifdef CONFIG_FUNCTION_TRACER
 
 #ifdef CONFIG_DYNAMIC_FTRACE
@@ -110,8 +116,11 @@ int trace_selftest_startup_dynamic_tracing(struct tracer *trace,
 	ftrace_set_filter(func_name, strlen(func_name), 1);
 
 	/* enable tracing */
-	tr->ctrl = 1;
-	trace->init(tr);
+	ret = trace->init(tr);
+	if (ret) {
+		warn_failed_init_tracer(trace, ret);
+		goto out;
+	}
 
 	/* Sleep for a 1/10 of a second */
 	msleep(100);
@@ -134,13 +143,13 @@ int trace_selftest_startup_dynamic_tracing(struct tracer *trace,
 	msleep(100);
 
 	/* stop the tracing. */
-	tr->ctrl = 0;
-	trace->ctrl_update(tr);
+	tracing_stop();
 	ftrace_enabled = 0;
 
 	/* check the trace buffer */
 	ret = trace_test_buffer(tr, &count);
 	trace->reset(tr);
+	tracing_start();
 
 	/* we should only have one item */
 	if (!ret && count != 1) {
@@ -148,6 +157,7 @@ int trace_selftest_startup_dynamic_tracing(struct tracer *trace,
 		ret = -1;
 		goto out;
 	}
+
  out:
 	ftrace_enabled = save_ftrace_enabled;
 	tracer_enabled = save_tracer_enabled;
@@ -180,18 +190,22 @@ trace_selftest_startup_function(struct tracer *trace, struct trace_array *tr)
 	ftrace_enabled = 1;
 	tracer_enabled = 1;
 
-	tr->ctrl = 1;
-	trace->init(tr);
+	ret = trace->init(tr);
+	if (ret) {
+		warn_failed_init_tracer(trace, ret);
+		goto out;
+	}
+
 	/* Sleep for a 1/10 of a second */
 	msleep(100);
 	/* stop the tracing. */
-	tr->ctrl = 0;
-	trace->ctrl_update(tr);
+	tracing_stop();
 	ftrace_enabled = 0;
 
 	/* check the trace buffer */
 	ret = trace_test_buffer(tr, &count);
 	trace->reset(tr);
+	tracing_start();
 
 	if (!ret && !count) {
 		printk(KERN_CONT ".. no entries found ..");
@@ -223,8 +237,12 @@ trace_selftest_startup_irqsoff(struct tracer *trace, struct trace_array *tr)
 	int ret;
 
 	/* start the tracing */
-	tr->ctrl = 1;
-	trace->init(tr);
+	ret = trace->init(tr);
+	if (ret) {
+		warn_failed_init_tracer(trace, ret);
+		return ret;
+	}
+
 	/* reset the max latency */
 	tracing_max_latency = 0;
 	/* disable interrupts for a bit */
@@ -232,13 +250,13 @@ trace_selftest_startup_irqsoff(struct tracer *trace, struct trace_array *tr)
 	udelay(100);
 	local_irq_enable();
 	/* stop the tracing. */
-	tr->ctrl = 0;
-	trace->ctrl_update(tr);
+	tracing_stop();
 	/* check both trace buffers */
 	ret = trace_test_buffer(tr, NULL);
 	if (!ret)
 		ret = trace_test_buffer(&max_tr, &count);
 	trace->reset(tr);
+	tracing_start();
 
 	if (!ret && !count) {
 		printk(KERN_CONT ".. no entries found ..");
@@ -259,9 +277,26 @@ trace_selftest_startup_preemptoff(struct tracer *trace, struct trace_array *tr)
 	unsigned long count;
 	int ret;
 
+	/*
+	 * Now that the big kernel lock is no longer preemptable,
+	 * and this is called with the BKL held, it will always
+	 * fail. If preemption is already disabled, simply
+	 * pass the test. When the BKL is removed, or becomes
+	 * preemptible again, we will once again test this,
+	 * so keep it in.
+	 */
+	if (preempt_count()) {
+		printk(KERN_CONT "can not test ... force ");
+		return 0;
+	}
+
 	/* start the tracing */
-	tr->ctrl = 1;
-	trace->init(tr);
+	ret = trace->init(tr);
+	if (ret) {
+		warn_failed_init_tracer(trace, ret);
+		return ret;
+	}
+
 	/* reset the max latency */
 	tracing_max_latency = 0;
 	/* disable preemption for a bit */
@@ -269,13 +304,13 @@ trace_selftest_startup_preemptoff(struct tracer *trace, struct trace_array *tr)
 	udelay(100);
 	preempt_enable();
 	/* stop the tracing. */
-	tr->ctrl = 0;
-	trace->ctrl_update(tr);
+	tracing_stop();
 	/* check both trace buffers */
 	ret = trace_test_buffer(tr, NULL);
 	if (!ret)
 		ret = trace_test_buffer(&max_tr, &count);
 	trace->reset(tr);
+	tracing_start();
 
 	if (!ret && !count) {
 		printk(KERN_CONT ".. no entries found ..");
@@ -296,9 +331,25 @@ trace_selftest_startup_preemptirqsoff(struct tracer *trace, struct trace_array *
 	unsigned long count;
 	int ret;
 
+	/*
+	 * Now that the big kernel lock is no longer preemptable,
+	 * and this is called with the BKL held, it will always
+	 * fail. If preemption is already disabled, simply
+	 * pass the test. When the BKL is removed, or becomes
+	 * preemptible again, we will once again test this,
+	 * so keep it in.
+	 */
+	if (preempt_count()) {
+		printk(KERN_CONT "can not test ... force ");
+		return 0;
+	}
+
 	/* start the tracing */
-	tr->ctrl = 1;
-	trace->init(tr);
+	ret = trace->init(tr);
+	if (ret) {
+		warn_failed_init_tracer(trace, ret);
+		goto out;
+	}
 
 	/* reset the max latency */
 	tracing_max_latency = 0;
@@ -312,27 +363,30 @@ trace_selftest_startup_preemptirqsoff(struct tracer *trace, struct trace_array *
 	local_irq_enable();
 
 	/* stop the tracing. */
-	tr->ctrl = 0;
-	trace->ctrl_update(tr);
+	tracing_stop();
 	/* check both trace buffers */
 	ret = trace_test_buffer(tr, NULL);
-	if (ret)
+	if (ret) {
+		tracing_start();
 		goto out;
+	}
 
 	ret = trace_test_buffer(&max_tr, &count);
-	if (ret)
+	if (ret) {
+		tracing_start();
 		goto out;
+	}
 
 	if (!ret && !count) {
 		printk(KERN_CONT ".. no entries found ..");
 		ret = -1;
+		tracing_start();
 		goto out;
 	}
 
 	/* do the test by disabling interrupts first this time */
 	tracing_max_latency = 0;
-	tr->ctrl = 1;
-	trace->ctrl_update(tr);
+	tracing_start();
 	preempt_disable();
 	local_irq_disable();
 	udelay(100);
@@ -341,8 +395,7 @@ trace_selftest_startup_preemptirqsoff(struct tracer *trace, struct trace_array *
 	local_irq_enable();
 
 	/* stop the tracing. */
-	tr->ctrl = 0;
-	trace->ctrl_update(tr);
+	tracing_stop();
 	/* check both trace buffers */
 	ret = trace_test_buffer(tr, NULL);
 	if (ret)
@@ -358,6 +411,7 @@ trace_selftest_startup_preemptirqsoff(struct tracer *trace, struct trace_array *
 
  out:
 	trace->reset(tr);
+	tracing_start();
 	tracing_max_latency = save_max;
 
 	return ret;
@@ -423,8 +477,12 @@ trace_selftest_startup_wakeup(struct tracer *trace, struct trace_array *tr)
 	wait_for_completion(&isrt);
 
 	/* start the tracing */
-	tr->ctrl = 1;
-	trace->init(tr);
+	ret = trace->init(tr);
+	if (ret) {
+		warn_failed_init_tracer(trace, ret);
+		return ret;
+	}
+
 	/* reset the max latency */
 	tracing_max_latency = 0;
 
@@ -448,8 +506,7 @@ trace_selftest_startup_wakeup(struct tracer *trace, struct trace_array *tr)
 	msleep(100);
 
 	/* stop the tracing. */
-	tr->ctrl = 0;
-	trace->ctrl_update(tr);
+	tracing_stop();
 	/* check both trace buffers */
 	ret = trace_test_buffer(tr, NULL);
 	if (!ret)
@@ -457,6 +514,7 @@ trace_selftest_startup_wakeup(struct tracer *trace, struct trace_array *tr)
 
 
 	trace->reset(tr);
+	tracing_start();
 
 	tracing_max_latency = save_max;
 
@@ -480,16 +538,20 @@ trace_selftest_startup_sched_switch(struct tracer *trace, struct trace_array *tr
 	int ret;
 
 	/* start the tracing */
-	tr->ctrl = 1;
-	trace->init(tr);
+	ret = trace->init(tr);
+	if (ret) {
+		warn_failed_init_tracer(trace, ret);
+		return ret;
+	}
+
 	/* Sleep for a 1/10 of a second */
 	msleep(100);
 	/* stop the tracing. */
-	tr->ctrl = 0;
-	trace->ctrl_update(tr);
+	tracing_stop();
 	/* check the trace buffer */
 	ret = trace_test_buffer(tr, &count);
 	trace->reset(tr);
+	tracing_start();
 
 	if (!ret && !count) {
 		printk(KERN_CONT ".. no entries found ..");
@@ -508,17 +570,48 @@ trace_selftest_startup_sysprof(struct tracer *trace, struct trace_array *tr)
 	int ret;
 
 	/* start the tracing */
-	tr->ctrl = 1;
-	trace->init(tr);
+	ret = trace->init(tr);
+	if (ret) {
+		warn_failed_init_tracer(trace, ret);
+		return 0;
+	}
+
 	/* Sleep for a 1/10 of a second */
 	msleep(100);
 	/* stop the tracing. */
-	tr->ctrl = 0;
-	trace->ctrl_update(tr);
+	tracing_stop();
 	/* check the trace buffer */
 	ret = trace_test_buffer(tr, &count);
 	trace->reset(tr);
+	tracing_start();
 
 	return ret;
 }
 #endif /* CONFIG_SYSPROF_TRACER */
+
+#ifdef CONFIG_BRANCH_TRACER
+int
+trace_selftest_startup_branch(struct tracer *trace, struct trace_array *tr)
+{
+	unsigned long count;
+	int ret;
+
+	/* start the tracing */
+	ret = trace->init(tr);
+	if (ret) {
+		warn_failed_init_tracer(trace, ret);
+		return ret;
+	}
+
+	/* Sleep for a 1/10 of a second */
+	msleep(100);
+	/* stop the tracing. */
+	tracing_stop();
+	/* check the trace buffer */
+	ret = trace_test_buffer(tr, &count);
+	trace->reset(tr);
+	tracing_start();
+
+	return ret;
+}
+#endif /* CONFIG_BRANCH_TRACER */
diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c
index 3bdb44bde4b7..fde3be15c642 100644
--- a/kernel/trace/trace_stack.c
+++ b/kernel/trace/trace_stack.c
@@ -107,8 +107,7 @@ stack_trace_call(unsigned long ip, unsigned long parent_ip)
 	if (unlikely(!ftrace_enabled || stack_trace_disabled))
 		return;
 
-	resched = need_resched();
-	preempt_disable_notrace();
+	resched = ftrace_preempt_disable();
 
 	cpu = raw_smp_processor_id();
 	/* no atomic needed, we only modify this variable by this cpu */
@@ -120,10 +119,7 @@ stack_trace_call(unsigned long ip, unsigned long parent_ip)
  out:
 	per_cpu(trace_active, cpu)--;
 	/* prevent recursion in schedule */
-	if (resched)
-		preempt_enable_no_resched_notrace();
-	else
-		preempt_enable_notrace();
+	ftrace_preempt_enable(resched);
 }
 
 static struct ftrace_ops trace_ops __read_mostly =
diff --git a/kernel/trace/trace_sysprof.c b/kernel/trace/trace_sysprof.c
index 9587d3bcba55..54960edb96d0 100644
--- a/kernel/trace/trace_sysprof.c
+++ b/kernel/trace/trace_sysprof.c
@@ -261,27 +261,17 @@ static void stop_stack_trace(struct trace_array *tr)
 	mutex_unlock(&sample_timer_lock);
 }
 
-static void stack_trace_init(struct trace_array *tr)
+static int stack_trace_init(struct trace_array *tr)
 {
 	sysprof_trace = tr;
 
-	if (tr->ctrl)
-		start_stack_trace(tr);
+	start_stack_trace(tr);
+	return 0;
 }
 
 static void stack_trace_reset(struct trace_array *tr)
 {
-	if (tr->ctrl)
-		stop_stack_trace(tr);
-}
-
-static void stack_trace_ctrl_update(struct trace_array *tr)
-{
-	/* When starting a new trace, reset the buffers */
-	if (tr->ctrl)
-		start_stack_trace(tr);
-	else
-		stop_stack_trace(tr);
+	stop_stack_trace(tr);
 }
 
 static struct tracer stack_trace __read_mostly =
@@ -289,7 +279,6 @@ static struct tracer stack_trace __read_mostly =
 	.name		= "sysprof",
 	.init		= stack_trace_init,
 	.reset		= stack_trace_reset,
-	.ctrl_update	= stack_trace_ctrl_update,
 #ifdef CONFIG_FTRACE_SELFTEST
 	.selftest    = trace_selftest_startup_sysprof,
 #endif
diff --git a/kernel/tracepoint.c b/kernel/tracepoint.c
index af8c85664882..79602740bbb5 100644
--- a/kernel/tracepoint.c
+++ b/kernel/tracepoint.c
@@ -43,6 +43,7 @@ static DEFINE_MUTEX(tracepoints_mutex);
  */
 #define TRACEPOINT_HASH_BITS 6
 #define TRACEPOINT_TABLE_SIZE (1 << TRACEPOINT_HASH_BITS)
+static struct hlist_head tracepoint_table[TRACEPOINT_TABLE_SIZE];
 
 /*
  * Note about RCU :
@@ -54,40 +55,43 @@ struct tracepoint_entry {
 	struct hlist_node hlist;
 	void **funcs;
 	int refcount;	/* Number of times armed. 0 if disarmed. */
-	struct rcu_head rcu;
-	void *oldptr;
-	unsigned char rcu_pending:1;
 	char name[0];
 };
 
-static struct hlist_head tracepoint_table[TRACEPOINT_TABLE_SIZE];
+struct tp_probes {
+	union {
+		struct rcu_head rcu;
+		struct list_head list;
+	} u;
+	void *probes[0];
+};
 
-static void free_old_closure(struct rcu_head *head)
+static inline void *allocate_probes(int count)
 {
-	struct tracepoint_entry *entry = container_of(head,
-		struct tracepoint_entry, rcu);
-	kfree(entry->oldptr);
-	/* Make sure we free the data before setting the pending flag to 0 */
-	smp_wmb();
-	entry->rcu_pending = 0;
+	struct tp_probes *p  = kmalloc(count * sizeof(void *)
+			+ sizeof(struct tp_probes), GFP_KERNEL);
+	return p == NULL ? NULL : p->probes;
 }
 
-static void tracepoint_entry_free_old(struct tracepoint_entry *entry, void *old)
+static void rcu_free_old_probes(struct rcu_head *head)
 {
-	if (!old)
-		return;
-	entry->oldptr = old;
-	entry->rcu_pending = 1;
-	/* write rcu_pending before calling the RCU callback */
-	smp_wmb();
-	call_rcu_sched(&entry->rcu, free_old_closure);
+	kfree(container_of(head, struct tp_probes, u.rcu));
+}
+
+static inline void release_probes(void *old)
+{
+	if (old) {
+		struct tp_probes *tp_probes = container_of(old,
+			struct tp_probes, probes[0]);
+		call_rcu_sched(&tp_probes->u.rcu, rcu_free_old_probes);
+	}
 }
 
 static void debug_print_probes(struct tracepoint_entry *entry)
 {
 	int i;
 
-	if (!tracepoint_debug)
+	if (!tracepoint_debug || !entry->funcs)
 		return;
 
 	for (i = 0; entry->funcs[i]; i++)
@@ -111,12 +115,13 @@ tracepoint_entry_add_probe(struct tracepoint_entry *entry, void *probe)
 				return ERR_PTR(-EEXIST);
 	}
 	/* + 2 : one for new probe, one for NULL func */
-	new = kzalloc((nr_probes + 2) * sizeof(void *), GFP_KERNEL);
+	new = allocate_probes(nr_probes + 2);
 	if (new == NULL)
 		return ERR_PTR(-ENOMEM);
 	if (old)
 		memcpy(new, old, nr_probes * sizeof(void *));
 	new[nr_probes] = probe;
+	new[nr_probes + 1] = NULL;
 	entry->refcount = nr_probes + 1;
 	entry->funcs = new;
 	debug_print_probes(entry);
@@ -132,7 +137,7 @@ tracepoint_entry_remove_probe(struct tracepoint_entry *entry, void *probe)
 	old = entry->funcs;
 
 	if (!old)
-		return NULL;
+		return ERR_PTR(-ENOENT);
 
 	debug_print_probes(entry);
 	/* (N -> M), (N > 1, M >= 0) probes */
@@ -151,13 +156,13 @@ tracepoint_entry_remove_probe(struct tracepoint_entry *entry, void *probe)
 		int j = 0;
 		/* N -> M, (N > 1, M > 0) */
 		/* + 1 for NULL */
-		new = kzalloc((nr_probes - nr_del + 1)
-			* sizeof(void *), GFP_KERNEL);
+		new = allocate_probes(nr_probes - nr_del + 1);
 		if (new == NULL)
 			return ERR_PTR(-ENOMEM);
 		for (i = 0; old[i]; i++)
 			if ((probe && old[i] != probe))
 				new[j++] = old[i];
+		new[nr_probes - nr_del] = NULL;
 		entry->refcount = nr_probes - nr_del;
 		entry->funcs = new;
 	}
@@ -215,7 +220,6 @@ static struct tracepoint_entry *add_tracepoint(const char *name)
 	memcpy(&e->name[0], name, name_len);
 	e->funcs = NULL;
 	e->refcount = 0;
-	e->rcu_pending = 0;
 	hlist_add_head(&e->hlist, head);
 	return e;
 }
@@ -224,32 +228,10 @@ static struct tracepoint_entry *add_tracepoint(const char *name)
  * Remove the tracepoint from the tracepoint hash table. Must be called with
  * mutex_lock held.
  */
-static int remove_tracepoint(const char *name)
+static inline void remove_tracepoint(struct tracepoint_entry *e)
 {
-	struct hlist_head *head;
-	struct hlist_node *node;
-	struct tracepoint_entry *e;
-	int found = 0;
-	size_t len = strlen(name) + 1;
-	u32 hash = jhash(name, len-1, 0);
-
-	head = &tracepoint_table[hash & (TRACEPOINT_TABLE_SIZE - 1)];
-	hlist_for_each_entry(e, node, head, hlist) {
-		if (!strcmp(name, e->name)) {
-			found = 1;
-			break;
-		}
-	}
-	if (!found)
-		return -ENOENT;
-	if (e->refcount)
-		return -EBUSY;
 	hlist_del(&e->hlist);
-	/* Make sure the call_rcu_sched has been executed */
-	if (e->rcu_pending)
-		rcu_barrier_sched();
 	kfree(e);
-	return 0;
 }
 
 /*
@@ -280,6 +262,7 @@ static void set_tracepoint(struct tracepoint_entry **entry,
 static void disable_tracepoint(struct tracepoint *elem)
 {
 	elem->state = 0;
+	rcu_assign_pointer(elem->funcs, NULL);
 }
 
 /**
@@ -320,6 +303,23 @@ static void tracepoint_update_probes(void)
 	module_update_tracepoints();
 }
 
+static void *tracepoint_add_probe(const char *name, void *probe)
+{
+	struct tracepoint_entry *entry;
+	void *old;
+
+	entry = get_tracepoint(name);
+	if (!entry) {
+		entry = add_tracepoint(name);
+		if (IS_ERR(entry))
+			return entry;
+	}
+	old = tracepoint_entry_add_probe(entry, probe);
+	if (IS_ERR(old) && !entry->refcount)
+		remove_tracepoint(entry);
+	return old;
+}
+
 /**
  * tracepoint_probe_register -  Connect a probe to a tracepoint
  * @name: tracepoint name
@@ -330,44 +330,36 @@ static void tracepoint_update_probes(void)
  */
 int tracepoint_probe_register(const char *name, void *probe)
 {
-	struct tracepoint_entry *entry;
-	int ret = 0;
 	void *old;
 
 	mutex_lock(&tracepoints_mutex);
-	entry = get_tracepoint(name);
-	if (!entry) {
-		entry = add_tracepoint(name);
-		if (IS_ERR(entry)) {
-			ret = PTR_ERR(entry);
-			goto end;
-		}
-	}
-	/*
-	 * If we detect that a call_rcu_sched is pending for this tracepoint,
-	 * make sure it's executed now.
-	 */
-	if (entry->rcu_pending)
-		rcu_barrier_sched();
-	old = tracepoint_entry_add_probe(entry, probe);
-	if (IS_ERR(old)) {
-		ret = PTR_ERR(old);
-		goto end;
-	}
+	old = tracepoint_add_probe(name, probe);
 	mutex_unlock(&tracepoints_mutex);
+	if (IS_ERR(old))
+		return PTR_ERR(old);
+
 	tracepoint_update_probes();		/* may update entry */
-	mutex_lock(&tracepoints_mutex);
-	entry = get_tracepoint(name);
-	WARN_ON(!entry);
-	if (entry->rcu_pending)
-		rcu_barrier_sched();
-	tracepoint_entry_free_old(entry, old);
-end:
-	mutex_unlock(&tracepoints_mutex);
-	return ret;
+	release_probes(old);
+	return 0;
 }
 EXPORT_SYMBOL_GPL(tracepoint_probe_register);
 
+static void *tracepoint_remove_probe(const char *name, void *probe)
+{
+	struct tracepoint_entry *entry;
+	void *old;
+
+	entry = get_tracepoint(name);
+	if (!entry)
+		return ERR_PTR(-ENOENT);
+	old = tracepoint_entry_remove_probe(entry, probe);
+	if (IS_ERR(old))
+		return old;
+	if (!entry->refcount)
+		remove_tracepoint(entry);
+	return old;
+}
+
 /**
  * tracepoint_probe_unregister -  Disconnect a probe from a tracepoint
  * @name: tracepoint name
@@ -380,38 +372,104 @@ EXPORT_SYMBOL_GPL(tracepoint_probe_register);
  */
 int tracepoint_probe_unregister(const char *name, void *probe)
 {
-	struct tracepoint_entry *entry;
 	void *old;
-	int ret = -ENOENT;
 
 	mutex_lock(&tracepoints_mutex);
-	entry = get_tracepoint(name);
-	if (!entry)
-		goto end;
-	if (entry->rcu_pending)
-		rcu_barrier_sched();
-	old = tracepoint_entry_remove_probe(entry, probe);
-	if (!old) {
-		printk(KERN_WARNING "Warning: Trying to unregister a probe"
-				    "that doesn't exist\n");
-		goto end;
-	}
+	old = tracepoint_remove_probe(name, probe);
 	mutex_unlock(&tracepoints_mutex);
+	if (IS_ERR(old))
+		return PTR_ERR(old);
+
 	tracepoint_update_probes();		/* may update entry */
+	release_probes(old);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(tracepoint_probe_unregister);
+
+static LIST_HEAD(old_probes);
+static int need_update;
+
+static void tracepoint_add_old_probes(void *old)
+{
+	need_update = 1;
+	if (old) {
+		struct tp_probes *tp_probes = container_of(old,
+			struct tp_probes, probes[0]);
+		list_add(&tp_probes->u.list, &old_probes);
+	}
+}
+
+/**
+ * tracepoint_probe_register_noupdate -  register a probe but not connect
+ * @name: tracepoint name
+ * @probe: probe handler
+ *
+ * caller must call tracepoint_probe_update_all()
+ */
+int tracepoint_probe_register_noupdate(const char *name, void *probe)
+{
+	void *old;
+
 	mutex_lock(&tracepoints_mutex);
-	entry = get_tracepoint(name);
-	if (!entry)
-		goto end;
-	if (entry->rcu_pending)
-		rcu_barrier_sched();
-	tracepoint_entry_free_old(entry, old);
-	remove_tracepoint(name);	/* Ignore busy error message */
-	ret = 0;
-end:
+	old = tracepoint_add_probe(name, probe);
+	if (IS_ERR(old)) {
+		mutex_unlock(&tracepoints_mutex);
+		return PTR_ERR(old);
+	}
+	tracepoint_add_old_probes(old);
 	mutex_unlock(&tracepoints_mutex);
-	return ret;
+	return 0;
 }
-EXPORT_SYMBOL_GPL(tracepoint_probe_unregister);
+EXPORT_SYMBOL_GPL(tracepoint_probe_register_noupdate);
+
+/**
+ * tracepoint_probe_unregister_noupdate -  remove a probe but not disconnect
+ * @name: tracepoint name
+ * @probe: probe function pointer
+ *
+ * caller must call tracepoint_probe_update_all()
+ */
+int tracepoint_probe_unregister_noupdate(const char *name, void *probe)
+{
+	void *old;
+
+	mutex_lock(&tracepoints_mutex);
+	old = tracepoint_remove_probe(name, probe);
+	if (IS_ERR(old)) {
+		mutex_unlock(&tracepoints_mutex);
+		return PTR_ERR(old);
+	}
+	tracepoint_add_old_probes(old);
+	mutex_unlock(&tracepoints_mutex);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(tracepoint_probe_unregister_noupdate);
+
+/**
+ * tracepoint_probe_update_all -  update tracepoints
+ */
+void tracepoint_probe_update_all(void)
+{
+	LIST_HEAD(release_probes);
+	struct tp_probes *pos, *next;
+
+	mutex_lock(&tracepoints_mutex);
+	if (!need_update) {
+		mutex_unlock(&tracepoints_mutex);
+		return;
+	}
+	if (!list_empty(&old_probes))
+		list_replace_init(&old_probes, &release_probes);
+	need_update = 0;
+	mutex_unlock(&tracepoints_mutex);
+
+	tracepoint_update_probes();
+	list_for_each_entry_safe(pos, next, &release_probes, u.list) {
+		list_del(&pos->u.list);
+		call_rcu_sched(&pos->u.rcu, rcu_free_old_probes);
+	}
+}
+EXPORT_SYMBOL_GPL(tracepoint_probe_update_all);
 
 /**
  * tracepoint_get_iter_range - Get a next tracepoint iterator given a range.
@@ -483,3 +541,36 @@ void tracepoint_iter_reset(struct tracepoint_iter *iter)
 	iter->tracepoint = NULL;
 }
 EXPORT_SYMBOL_GPL(tracepoint_iter_reset);
+
+#ifdef CONFIG_MODULES
+
+int tracepoint_module_notify(struct notifier_block *self,
+			     unsigned long val, void *data)
+{
+	struct module *mod = data;
+
+	switch (val) {
+	case MODULE_STATE_COMING:
+		tracepoint_update_probe_range(mod->tracepoints,
+			mod->tracepoints + mod->num_tracepoints);
+		break;
+	case MODULE_STATE_GOING:
+		tracepoint_update_probe_range(mod->tracepoints,
+			mod->tracepoints + mod->num_tracepoints);
+		break;
+	}
+	return 0;
+}
+
+struct notifier_block tracepoint_module_nb = {
+	.notifier_call = tracepoint_module_notify,
+	.priority = 0,
+};
+
+static int init_tracepoints(void)
+{
+	return register_module_notifier(&tracepoint_module_nb);
+}
+__initcall(init_tracepoints);
+
+#endif /* CONFIG_MODULES */
diff --git a/kernel/user.c b/kernel/user.c
index 39d6159fae43..cec2224bc9f5 100644
--- a/kernel/user.c
+++ b/kernel/user.c
@@ -101,6 +101,8 @@ static int sched_create_user(struct user_struct *up)
 	if (IS_ERR(up->tg))
 		rc = -ENOMEM;
 
+	set_tg_uid(up);
+
 	return rc;
 }
 
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index b0f239e443bc..71cd23a748c1 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -252,6 +252,14 @@ config DEBUG_OBJECTS_TIMERS
 	  timer routines to track the life time of timer objects and
 	  validate the timer operations.
 
+config DEBUG_OBJECTS_ENABLE_DEFAULT
+	int "debug_objects bootup default value (0-1)"
+        range 0 1
+        default "1"
+        depends on DEBUG_OBJECTS
+        help
+          Debug objects boot parameter default value
+
 config DEBUG_SLAB
 	bool "Debug slab memory allocations"
 	depends on DEBUG_KERNEL && SLAB
@@ -545,6 +553,16 @@ config DEBUG_SG
 
 	  If unsure, say N.
 
+config DEBUG_NOTIFIERS
+	bool "Debug notifier call chains"
+	depends on DEBUG_KERNEL
+	help
+	  Enable this to turn on sanity checking for notifier call chains.
+	  This is most useful for kernel developers to make sure that
+	  modules properly unregister themselves from notifier chains.
+	  This is a relatively cheap check but if you care about maximum
+	  performance, say N.
+
 config FRAME_POINTER
 	bool "Compile the kernel with frame pointers"
 	depends on DEBUG_KERNEL && \
diff --git a/lib/debugobjects.c b/lib/debugobjects.c
index e3ab374e1334..5d99be1fd988 100644
--- a/lib/debugobjects.c
+++ b/lib/debugobjects.c
@@ -45,7 +45,9 @@ static struct kmem_cache	*obj_cache;
 static int			debug_objects_maxchain __read_mostly;
 static int			debug_objects_fixups __read_mostly;
 static int			debug_objects_warnings __read_mostly;
-static int			debug_objects_enabled __read_mostly;
+static int			debug_objects_enabled __read_mostly
+				= CONFIG_DEBUG_OBJECTS_ENABLE_DEFAULT;
+
 static struct debug_obj_descr	*descr_test  __read_mostly;
 
 static int __init enable_object_debug(char *str)
diff --git a/lib/dynamic_printk.c b/lib/dynamic_printk.c
index d83660fd6fdd..d0fd0e4ed9a8 100644
--- a/lib/dynamic_printk.c
+++ b/lib/dynamic_printk.c
@@ -135,7 +135,7 @@ int unregister_dynamic_debug_module(char *mod_name)
 	nr_entries--;
 out:
 	up(&debug_list_mutex);
-	return 0;
+	return ret;
 }
 EXPORT_SYMBOL_GPL(unregister_dynamic_debug_module);
 
diff --git a/lib/klist.c b/lib/klist.c
index bbdd3015c2c7..573d6068a42e 100644
--- a/lib/klist.c
+++ b/lib/klist.c
@@ -36,6 +36,7 @@
 
 #include <linux/klist.h>
 #include <linux/module.h>
+#include <linux/sched.h>
 
 /*
  * Use the lowest bit of n_klist to mark deleted nodes and exclude
@@ -108,7 +109,6 @@ static void add_tail(struct klist *k, struct klist_node *n)
 static void klist_node_init(struct klist *k, struct klist_node *n)
 {
 	INIT_LIST_HEAD(&n->n_node);
-	init_completion(&n->n_removed);
 	kref_init(&n->n_ref);
 	knode_set_klist(n, k);
 	if (k->get)
@@ -171,13 +171,34 @@ void klist_add_before(struct klist_node *n, struct klist_node *pos)
 }
 EXPORT_SYMBOL_GPL(klist_add_before);
 
+struct klist_waiter {
+	struct list_head list;
+	struct klist_node *node;
+	struct task_struct *process;
+	int woken;
+};
+
+static DEFINE_SPINLOCK(klist_remove_lock);
+static LIST_HEAD(klist_remove_waiters);
+
 static void klist_release(struct kref *kref)
 {
+	struct klist_waiter *waiter, *tmp;
 	struct klist_node *n = container_of(kref, struct klist_node, n_ref);
 
 	WARN_ON(!knode_dead(n));
 	list_del(&n->n_node);
-	complete(&n->n_removed);
+	spin_lock(&klist_remove_lock);
+	list_for_each_entry_safe(waiter, tmp, &klist_remove_waiters, list) {
+		if (waiter->node != n)
+			continue;
+
+		waiter->woken = 1;
+		mb();
+		wake_up_process(waiter->process);
+		list_del(&waiter->list);
+	}
+	spin_unlock(&klist_remove_lock);
 	knode_set_klist(n, NULL);
 }
 
@@ -217,8 +238,24 @@ EXPORT_SYMBOL_GPL(klist_del);
  */
 void klist_remove(struct klist_node *n)
 {
+	struct klist_waiter waiter;
+
+	waiter.node = n;
+	waiter.process = current;
+	waiter.woken = 0;
+	spin_lock(&klist_remove_lock);
+	list_add(&waiter.list, &klist_remove_waiters);
+	spin_unlock(&klist_remove_lock);
+
 	klist_del(n);
-	wait_for_completion(&n->n_removed);
+
+	for (;;) {
+		set_current_state(TASK_UNINTERRUPTIBLE);
+		if (waiter.woken)
+			break;
+		schedule();
+	}
+	__set_current_state(TASK_RUNNING);
 }
 EXPORT_SYMBOL_GPL(klist_remove);
 
diff --git a/lib/kobject.c b/lib/kobject.c
index 0487d1f64806..2fded6d8ca54 100644
--- a/lib/kobject.c
+++ b/lib/kobject.c
@@ -17,6 +17,55 @@
 #include <linux/module.h>
 #include <linux/stat.h>
 #include <linux/slab.h>
+#include <linux/kallsyms.h>
+#include <asm-generic/sections.h>
+
+#ifdef CONFIG_X86_32
+static int ptr_in_range(void *ptr, void *start, void *end)
+{
+	/*
+	 * This should hopefully get rid of causing warnings
+	 * if the architecture did not set one of the section
+	 * variables up.
+	 */
+	if (start >= end)
+		return 0;
+
+	if ((ptr >= start) && (ptr < end))
+		return 1;
+	return 0;
+}
+
+static void verify_dynamic_kobject_allocation(struct kobject *kobj)
+{
+	char namebuf[KSYM_NAME_LEN];
+	const char *ret;
+
+	ret = kallsyms_lookup((unsigned long)kobj, NULL, NULL, NULL, namebuf);
+	/*
+	 * This is the X86_32-only part of this function.
+	 * This is here because it is valid to have a kobject
+	 * in an __init section, but only after those
+	 * sections have been freed back to the dynamic pool.
+	 */
+	if (!initmem_now_dynamic &&
+	    ptr_in_range(kobj, __init_begin, __init_end))
+		goto out;
+	if (!ret || !strlen(ret))
+		goto out;
+	pr_debug("---- begin silly warning ----\n");
+	pr_debug("This is a janitorial warning, not a kernel bug.\n");
+	pr_debug("The kobject '%s', at, or inside '%s'@(0x%p) is not "
+		 "dynamically allocated.\n", kobject_name(kobj), namebuf, kobj);
+	pr_debug("kobjects must be dynamically allocated, not static\n");
+	/* dump_stack(); */
+	pr_debug("---- end silly warning ----\n");
+out:
+	return;
+}
+#else
+static void verify_dynamic_kobject_allocation(struct kobject *kobj) { }
+#endif
 
 /*
  * populate_dir - populate directory with attributes.
@@ -282,6 +331,7 @@ void kobject_init(struct kobject *kobj, struct kobj_type *ktype)
 		       "object, something is seriously wrong.\n", kobj);
 		dump_stack();
 	}
+	verify_dynamic_kobject_allocation(kobj);
 
 	kobject_init_internal(kobj);
 	kobj->ktype = ktype;
diff --git a/lib/kobject_uevent.c b/lib/kobject_uevent.c
index 3f914725bda8..318328ddbd1c 100644
--- a/lib/kobject_uevent.c
+++ b/lib/kobject_uevent.c
@@ -165,7 +165,7 @@ int kobject_uevent_env(struct kobject *kobj, enum kobject_action action,
 	/* keys passed in from the caller */
 	if (envp_ext) {
 		for (i = 0; envp_ext[i]; i++) {
-			retval = add_uevent_var(env, envp_ext[i]);
+			retval = add_uevent_var(env, "%s", envp_ext[i]);
 			if (retval)
 				goto exit;
 		}
@@ -225,8 +225,10 @@ int kobject_uevent_env(struct kobject *kobj, enum kobject_action action,
 			}
 
 			NETLINK_CB(skb).dst_group = 1;
-			netlink_broadcast(uevent_sock, skb, 0, 1, GFP_KERNEL);
-		}
+			retval = netlink_broadcast(uevent_sock, skb, 0, 1,
+						   GFP_KERNEL);
+		} else
+			retval = -ENOMEM;
 	}
 #endif
 
diff --git a/lib/swiotlb.c b/lib/swiotlb.c
index 5f6c629a924d..96e8b1085b8e 100644
--- a/lib/swiotlb.c
+++ b/lib/swiotlb.c
@@ -533,7 +533,7 @@ swiotlb_full(struct device *dev, size_t size, int dir, int do_panic)
 	 * the damage, or panic when the transfer is too big.
 	 */
 	printk(KERN_ERR "DMA: Out of SW-IOMMU space for %zu bytes at "
-	       "device %s\n", size, dev ? dev->bus_id : "?");
+	       "device %s\n", size, dev ? dev_name(dev) : "?");
 
 	if (size > io_tlb_overflow && do_panic) {
 		if (dir == DMA_FROM_DEVICE || dir == DMA_BIDIRECTIONAL)
diff --git a/mm/memory.c b/mm/memory.c
index 164951c47305..fc031d68327e 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3049,3 +3049,18 @@ void print_vma_addr(char *prefix, unsigned long ip)
 	}
 	up_read(&current->mm->mmap_sem);
 }
+
+#ifdef CONFIG_PROVE_LOCKING
+void might_fault(void)
+{
+	might_sleep();
+	/*
+	 * it would be nicer only to annotate paths which are not under
+	 * pagefault_disable, however that requires a larger audit and
+	 * providing helpers like get_user_atomic.
+	 */
+	if (!in_atomic() && current->mm)
+		might_lock_read(&current->mm->mmap_sem);
+}
+EXPORT_SYMBOL(might_fault);
+#endif
diff --git a/net/atm/svc.c b/net/atm/svc.c
index de1e4f2f3a43..8fb54dc870b3 100644
--- a/net/atm/svc.c
+++ b/net/atm/svc.c
@@ -293,7 +293,10 @@ static int svc_listen(struct socket *sock,int backlog)
 		error = -EINVAL;
 		goto out;
 	}
-	vcc_insert_socket(sk);
+	if (test_bit(ATM_VF_LISTEN, &vcc->flags)) {
+		error = -EADDRINUSE;
+		goto out;
+        }
 	set_bit(ATM_VF_WAITING, &vcc->flags);
 	prepare_to_wait(sk->sk_sleep, &wait, TASK_UNINTERRUPTIBLE);
 	sigd_enq(vcc,as_listen,NULL,NULL,&vcc->local);
@@ -307,6 +310,7 @@ static int svc_listen(struct socket *sock,int backlog)
 		goto out;
 	}
 	set_bit(ATM_VF_LISTEN,&vcc->flags);
+	vcc_insert_socket(sk);
 	sk->sk_max_ack_backlog = backlog > 0 ? backlog : ATM_BACKLOG_DEFAULT;
 	error = -sk->sk_err;
 out:
diff --git a/net/can/af_can.c b/net/can/af_can.c
index 7d4d2b3c137e..3dadb338addd 100644
--- a/net/can/af_can.c
+++ b/net/can/af_can.c
@@ -319,23 +319,52 @@ static struct dev_rcv_lists *find_dev_rcv_lists(struct net_device *dev)
 	return n ? d : NULL;
 }
 
+/**
+ * find_rcv_list - determine optimal filterlist inside device filter struct
+ * @can_id: pointer to CAN identifier of a given can_filter
+ * @mask: pointer to CAN mask of a given can_filter
+ * @d: pointer to the device filter struct
+ *
+ * Description:
+ *  Returns the optimal filterlist to reduce the filter handling in the
+ *  receive path. This function is called by service functions that need
+ *  to register or unregister a can_filter in the filter lists.
+ *
+ *  A filter matches in general, when
+ *
+ *          <received_can_id> & mask == can_id & mask
+ *
+ *  so every bit set in the mask (even CAN_EFF_FLAG, CAN_RTR_FLAG) describe
+ *  relevant bits for the filter.
+ *
+ *  The filter can be inverted (CAN_INV_FILTER bit set in can_id) or it can
+ *  filter for error frames (CAN_ERR_FLAG bit set in mask). For error frames
+ *  there is a special filterlist and a special rx path filter handling.
+ *
+ * Return:
+ *  Pointer to optimal filterlist for the given can_id/mask pair.
+ *  Constistency checked mask.
+ *  Reduced can_id to have a preprocessed filter compare value.
+ */
 static struct hlist_head *find_rcv_list(canid_t *can_id, canid_t *mask,
 					struct dev_rcv_lists *d)
 {
 	canid_t inv = *can_id & CAN_INV_FILTER; /* save flag before masking */
 
-	/* filter error frames */
+	/* filter for error frames in extra filterlist */
 	if (*mask & CAN_ERR_FLAG) {
-		/* clear CAN_ERR_FLAG in list entry */
+		/* clear CAN_ERR_FLAG in filter entry */
 		*mask &= CAN_ERR_MASK;
 		return &d->rx[RX_ERR];
 	}
 
-	/* ensure valid values in can_mask */
-	if (*mask & CAN_EFF_FLAG)
-		*mask &= (CAN_EFF_MASK | CAN_EFF_FLAG | CAN_RTR_FLAG);
-	else
-		*mask &= (CAN_SFF_MASK | CAN_RTR_FLAG);
+	/* with cleared CAN_ERR_FLAG we have a simple mask/value filterpair */
+
+#define CAN_EFF_RTR_FLAGS (CAN_EFF_FLAG | CAN_RTR_FLAG)
+
+	/* ensure valid values in can_mask for 'SFF only' frame filtering */
+	if ((*mask & CAN_EFF_FLAG) && !(*can_id & CAN_EFF_FLAG))
+		*mask &= (CAN_SFF_MASK | CAN_EFF_RTR_FLAGS);
 
 	/* reduce condition testing at receive time */
 	*can_id &= *mask;
@@ -348,15 +377,19 @@ static struct hlist_head *find_rcv_list(canid_t *can_id, canid_t *mask,
 	if (!(*mask))
 		return &d->rx[RX_ALL];
 
-	/* use extra filterset for the subscription of exactly *ONE* can_id */
-	if (*can_id & CAN_EFF_FLAG) {
-		if (*mask == (CAN_EFF_MASK | CAN_EFF_FLAG)) {
-			/* RFC: a use-case for hash-tables in the future? */
-			return &d->rx[RX_EFF];
+	/* extra filterlists for the subscription of a single non-RTR can_id */
+	if (((*mask & CAN_EFF_RTR_FLAGS) == CAN_EFF_RTR_FLAGS)
+	    && !(*can_id & CAN_RTR_FLAG)) {
+
+		if (*can_id & CAN_EFF_FLAG) {
+			if (*mask == (CAN_EFF_MASK | CAN_EFF_RTR_FLAGS)) {
+				/* RFC: a future use-case for hash-tables? */
+				return &d->rx[RX_EFF];
+			}
+		} else {
+			if (*mask == (CAN_SFF_MASK | CAN_EFF_RTR_FLAGS))
+				return &d->rx_sff[*can_id];
 		}
-	} else {
-		if (*mask == CAN_SFF_MASK)
-			return &d->rx_sff[*can_id];
 	}
 
 	/* default: filter via can_id/can_mask */
@@ -589,7 +622,10 @@ static int can_rcv_filter(struct dev_rcv_lists *d, struct sk_buff *skb)
 		}
 	}
 
-	/* check CAN_ID specific entries */
+	/* check filterlists for single non-RTR can_ids */
+	if (can_id & CAN_RTR_FLAG)
+		return matches;
+
 	if (can_id & CAN_EFF_FLAG) {
 		hlist_for_each_entry_rcu(r, n, &d->rx[RX_EFF], list) {
 			if (r->can_id == can_id) {
diff --git a/net/can/bcm.c b/net/can/bcm.c
index d0dd382001e2..da0d426c0ce4 100644
--- a/net/can/bcm.c
+++ b/net/can/bcm.c
@@ -64,10 +64,11 @@
 #define BCM_CAN_DLC_MASK 0x0F /* clean private flags in can_dlc by masking */
 
 /* get best masking value for can_rx_register() for a given single can_id */
-#define REGMASK(id) ((id & CAN_RTR_FLAG) | ((id & CAN_EFF_FLAG) ? \
-			(CAN_EFF_MASK | CAN_EFF_FLAG) : CAN_SFF_MASK))
+#define REGMASK(id) ((id & CAN_EFF_FLAG) ? \
+		     (CAN_EFF_MASK | CAN_EFF_FLAG | CAN_RTR_FLAG) : \
+		     (CAN_SFF_MASK | CAN_EFF_FLAG | CAN_RTR_FLAG))
 
-#define CAN_BCM_VERSION "20080415"
+#define CAN_BCM_VERSION CAN_VERSION
 static __initdata const char banner[] = KERN_INFO
 	"can: broadcast manager protocol (rev " CAN_BCM_VERSION ")\n";
 
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 85b07eba1879..fe3b4bdfd251 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -722,8 +722,7 @@ static void tcp_queue_skb(struct sock *sk, struct sk_buff *skb)
 static void tcp_set_skb_tso_segs(struct sock *sk, struct sk_buff *skb,
 				 unsigned int mss_now)
 {
-	if (skb->len <= mss_now || !sk_can_gso(sk) ||
-	    tcp_urg_mode(tcp_sk(sk))) {
+	if (skb->len <= mss_now || !sk_can_gso(sk)) {
 		/* Avoid the costly divide in the normal
 		 * non-TSO case.
 		 */
@@ -1029,10 +1028,6 @@ unsigned int tcp_sync_mss(struct sock *sk, u32 pmtu)
 
 /* Compute the current effective MSS, taking SACKs and IP options,
  * and even PMTU discovery events into account.
- *
- * LARGESEND note: !tcp_urg_mode is overkill, only frames up to snd_up
- * cannot be large. However, taking into account rare use of URG, this
- * is not a big flaw.
  */
 unsigned int tcp_current_mss(struct sock *sk, int large_allowed)
 {
@@ -1047,7 +1042,7 @@ unsigned int tcp_current_mss(struct sock *sk, int large_allowed)
 
 	mss_now = tp->mss_cache;
 
-	if (large_allowed && sk_can_gso(sk) && !tcp_urg_mode(tp))
+	if (large_allowed && sk_can_gso(sk))
 		doing_tso = 1;
 
 	if (dst) {
@@ -1164,9 +1159,7 @@ static int tcp_init_tso_segs(struct sock *sk, struct sk_buff *skb,
 {
 	int tso_segs = tcp_skb_pcount(skb);
 
-	if (!tso_segs ||
-	    (tso_segs > 1 && (tcp_skb_mss(skb) != mss_now ||
-			      tcp_urg_mode(tcp_sk(sk))))) {
+	if (!tso_segs || (tso_segs > 1 && tcp_skb_mss(skb) != mss_now)) {
 		tcp_set_skb_tso_segs(sk, skb, mss_now);
 		tso_segs = tcp_skb_pcount(skb);
 	}
@@ -1519,6 +1512,10 @@ static int tcp_mtu_probe(struct sock *sk)
  * send_head.  This happens as incoming acks open up the remote
  * window for us.
  *
+ * LARGESEND note: !tcp_urg_mode is overkill, only frames between
+ * snd_up-64k-mss .. snd_up cannot be large. However, taking into
+ * account rare use of URG, this is not a big flaw.
+ *
  * Returns 1, if no segments are in flight and we have queued segments, but
  * cannot send anything now because of SWS or another problem.
  */
@@ -1570,7 +1567,7 @@ static int tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle)
 		}
 
 		limit = mss_now;
-		if (tso_segs > 1)
+		if (tso_segs > 1 && !tcp_urg_mode(tp))
 			limit = tcp_mss_split_point(sk, skb, mss_now,
 						    cwnd_quota);
 
@@ -1619,6 +1616,7 @@ void __tcp_push_pending_frames(struct sock *sk, unsigned int cur_mss,
  */
 void tcp_push_one(struct sock *sk, unsigned int mss_now)
 {
+	struct tcp_sock *tp = tcp_sk(sk);
 	struct sk_buff *skb = tcp_send_head(sk);
 	unsigned int tso_segs, cwnd_quota;
 
@@ -1633,7 +1631,7 @@ void tcp_push_one(struct sock *sk, unsigned int mss_now)
 		BUG_ON(!tso_segs);
 
 		limit = mss_now;
-		if (tso_segs > 1)
+		if (tso_segs > 1 && !tcp_urg_mode(tp))
 			limit = tcp_mss_split_point(sk, skb, mss_now,
 						    cwnd_quota);
 
diff --git a/net/ipv4/tcp_vegas.c b/net/ipv4/tcp_vegas.c
index 14504dada116..7cd22262de3a 100644
--- a/net/ipv4/tcp_vegas.c
+++ b/net/ipv4/tcp_vegas.c
@@ -326,6 +326,8 @@ static void tcp_vegas_cong_avoid(struct sock *sk, u32 ack, u32 in_flight)
 				tp->snd_cwnd = 2;
 			else if (tp->snd_cwnd > tp->snd_cwnd_clamp)
 				tp->snd_cwnd = tp->snd_cwnd_clamp;
+
+			tp->snd_ssthresh = tcp_current_ssthresh(sk);
 		}
 
 		/* Wipe the slate clean for the next RTT. */
diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c
index 29f7baa25110..af3192d2a5a3 100644
--- a/net/iucv/af_iucv.c
+++ b/net/iucv/af_iucv.c
@@ -8,6 +8,9 @@
  *  Author(s):	Jennifer Hunt <jenhunt@us.ibm.com>
  */
 
+#define KMSG_COMPONENT "af_iucv"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
 #include <linux/module.h>
 #include <linux/types.h>
 #include <linux/list.h>
@@ -616,6 +619,8 @@ static int iucv_sock_sendmsg(struct kiocb *iocb, struct socket *sock,
 	struct iucv_sock *iucv = iucv_sk(sk);
 	struct sk_buff *skb;
 	struct iucv_message txmsg;
+	char user_id[9];
+	char appl_id[9];
 	int err;
 
 	err = sock_error(sk);
@@ -651,8 +656,15 @@ static int iucv_sock_sendmsg(struct kiocb *iocb, struct socket *sock,
 		err = iucv_message_send(iucv->path, &txmsg, 0, 0,
 					(void *) skb->data, skb->len);
 		if (err) {
-			if (err == 3)
-				printk(KERN_ERR "AF_IUCV msg limit exceeded\n");
+			if (err == 3) {
+				user_id[8] = 0;
+				memcpy(user_id, iucv->dst_user_id, 8);
+				appl_id[8] = 0;
+				memcpy(appl_id, iucv->dst_name, 8);
+				pr_err("Application %s on z/VM guest %s"
+				       " exceeds message limit\n",
+				       user_id, appl_id);
+			}
 			skb_unlink(skb, &iucv->send_skb_q);
 			err = -EPIPE;
 			goto fail;
@@ -1190,7 +1202,8 @@ static int __init afiucv_init(void)
 	int err;
 
 	if (!MACHINE_IS_VM) {
-		printk(KERN_ERR "AF_IUCV connection needs VM as base\n");
+		pr_err("The af_iucv module cannot be loaded"
+		       " without z/VM\n");
 		err = -EPROTONOSUPPORT;
 		goto out;
 	}
diff --git a/net/iucv/iucv.c b/net/iucv/iucv.c
index d7b54b5bfa69..8f57d4f4328a 100644
--- a/net/iucv/iucv.c
+++ b/net/iucv/iucv.c
@@ -30,6 +30,9 @@
  * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
+#define KMSG_COMPONENT "iucv"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
 #include <linux/module.h>
 #include <linux/moduleparam.h>
 #include <linux/spinlock.h>
@@ -424,8 +427,8 @@ static void iucv_declare_cpu(void *data)
 			err = "Paging or storage error";
 			break;
 		}
-		printk(KERN_WARNING "iucv_register: iucv_declare_buffer "
-		       "on cpu %i returned error 0x%02x (%s)\n", cpu, rc, err);
+		pr_warning("Defining an interrupt buffer on CPU %i"
+			   " failed with 0x%02x (%s)\n", cpu, rc, err);
 		return;
 	}
 
@@ -957,7 +960,52 @@ int iucv_message_purge(struct iucv_path *path, struct iucv_message *msg,
 EXPORT_SYMBOL(iucv_message_purge);
 
 /**
- * iucv_message_receive
+ * iucv_message_receive_iprmdata
+ * @path: address of iucv path structure
+ * @msg: address of iucv msg structure
+ * @flags: how the message is received (IUCV_IPBUFLST)
+ * @buffer: address of data buffer or address of struct iucv_array
+ * @size: length of data buffer
+ * @residual:
+ *
+ * Internal function used by iucv_message_receive and __iucv_message_receive
+ * to receive RMDATA data stored in struct iucv_message.
+ */
+static int iucv_message_receive_iprmdata(struct iucv_path *path,
+					 struct iucv_message *msg,
+					 u8 flags, void *buffer,
+					 size_t size, size_t *residual)
+{
+	struct iucv_array *array;
+	u8 *rmmsg;
+	size_t copy;
+
+	/*
+	 * Message is 8 bytes long and has been stored to the
+	 * message descriptor itself.
+	 */
+	if (residual)
+		*residual = abs(size - 8);
+	rmmsg = msg->rmmsg;
+	if (flags & IUCV_IPBUFLST) {
+		/* Copy to struct iucv_array. */
+		size = (size < 8) ? size : 8;
+		for (array = buffer; size > 0; array++) {
+			copy = min_t(size_t, size, array->length);
+			memcpy((u8 *)(addr_t) array->address,
+				rmmsg, copy);
+			rmmsg += copy;
+			size -= copy;
+		}
+	} else {
+		/* Copy to direct buffer. */
+		memcpy(buffer, rmmsg, min_t(size_t, size, 8));
+	}
+	return 0;
+}
+
+/**
+ * __iucv_message_receive
  * @path: address of iucv path structure
  * @msg: address of iucv msg structure
  * @flags: how the message is received (IUCV_IPBUFLST)
@@ -969,44 +1017,19 @@ EXPORT_SYMBOL(iucv_message_purge);
  * established paths. This function will deal with RMDATA messages
  * embedded in struct iucv_message as well.
  *
+ * Locking:	no locking
+ *
  * Returns the result from the CP IUCV call.
  */
-int iucv_message_receive(struct iucv_path *path, struct iucv_message *msg,
-			 u8 flags, void *buffer, size_t size, size_t *residual)
+int __iucv_message_receive(struct iucv_path *path, struct iucv_message *msg,
+			   u8 flags, void *buffer, size_t size, size_t *residual)
 {
 	union iucv_param *parm;
-	struct iucv_array *array;
-	u8 *rmmsg;
-	size_t copy;
 	int rc;
 
-	if (msg->flags & IUCV_IPRMDATA) {
-		/*
-		 * Message is 8 bytes long and has been stored to the
-		 * message descriptor itself.
-		 */
-		rc = (size < 8) ? 5 : 0;
-		if (residual)
-			*residual = abs(size - 8);
-		rmmsg = msg->rmmsg;
-		if (flags & IUCV_IPBUFLST) {
-			/* Copy to struct iucv_array. */
-			size = (size < 8) ? size : 8;
-			for (array = buffer; size > 0; array++) {
-				copy = min_t(size_t, size, array->length);
-				memcpy((u8 *)(addr_t) array->address,
-				       rmmsg, copy);
-				rmmsg += copy;
-				size -= copy;
-			}
-		} else {
-			/* Copy to direct buffer. */
-			memcpy(buffer, rmmsg, min_t(size_t, size, 8));
-		}
-		return 0;
-	}
-
-	local_bh_disable();
+	if (msg->flags & IUCV_IPRMDATA)
+		return iucv_message_receive_iprmdata(path, msg, flags,
+						     buffer, size, residual);
 	parm = iucv_param[smp_processor_id()];
 	memset(parm, 0, sizeof(union iucv_param));
 	parm->db.ipbfadr1 = (u32)(addr_t) buffer;
@@ -1022,6 +1045,37 @@ int iucv_message_receive(struct iucv_path *path, struct iucv_message *msg,
 		if (residual)
 			*residual = parm->db.ipbfln1f;
 	}
+	return rc;
+}
+EXPORT_SYMBOL(__iucv_message_receive);
+
+/**
+ * iucv_message_receive
+ * @path: address of iucv path structure
+ * @msg: address of iucv msg structure
+ * @flags: how the message is received (IUCV_IPBUFLST)
+ * @buffer: address of data buffer or address of struct iucv_array
+ * @size: length of data buffer
+ * @residual:
+ *
+ * This function receives messages that are being sent to you over
+ * established paths. This function will deal with RMDATA messages
+ * embedded in struct iucv_message as well.
+ *
+ * Locking:	local_bh_enable/local_bh_disable
+ *
+ * Returns the result from the CP IUCV call.
+ */
+int iucv_message_receive(struct iucv_path *path, struct iucv_message *msg,
+			 u8 flags, void *buffer, size_t size, size_t *residual)
+{
+	int rc;
+
+	if (msg->flags & IUCV_IPRMDATA)
+		return iucv_message_receive_iprmdata(path, msg, flags,
+						     buffer, size, residual);
+	local_bh_disable();
+	rc = __iucv_message_receive(path, msg, flags, buffer, size, residual);
 	local_bh_enable();
 	return rc;
 }
@@ -1101,7 +1155,7 @@ int iucv_message_reply(struct iucv_path *path, struct iucv_message *msg,
 EXPORT_SYMBOL(iucv_message_reply);
 
 /**
- * iucv_message_send
+ * __iucv_message_send
  * @path: address of iucv path structure
  * @msg: address of iucv msg structure
  * @flags: how the message is sent (IUCV_IPRMDATA, IUCV_IPPRTY, IUCV_IPBUFLST)
@@ -1113,15 +1167,16 @@ EXPORT_SYMBOL(iucv_message_reply);
  * transmitted is in a buffer and this is a one-way message and the
  * receiver will not reply to the message.
  *
+ * Locking:	no locking
+ *
  * Returns the result from the CP IUCV call.
  */
-int iucv_message_send(struct iucv_path *path, struct iucv_message *msg,
+int __iucv_message_send(struct iucv_path *path, struct iucv_message *msg,
 		      u8 flags, u32 srccls, void *buffer, size_t size)
 {
 	union iucv_param *parm;
 	int rc;
 
-	local_bh_disable();
 	parm = iucv_param[smp_processor_id()];
 	memset(parm, 0, sizeof(union iucv_param));
 	if (flags & IUCV_IPRMDATA) {
@@ -1144,6 +1199,34 @@ int iucv_message_send(struct iucv_path *path, struct iucv_message *msg,
 	rc = iucv_call_b2f0(IUCV_SEND, parm);
 	if (!rc)
 		msg->id = parm->db.ipmsgid;
+	return rc;
+}
+EXPORT_SYMBOL(__iucv_message_send);
+
+/**
+ * iucv_message_send
+ * @path: address of iucv path structure
+ * @msg: address of iucv msg structure
+ * @flags: how the message is sent (IUCV_IPRMDATA, IUCV_IPPRTY, IUCV_IPBUFLST)
+ * @srccls: source class of message
+ * @buffer: address of send buffer or address of struct iucv_array
+ * @size: length of send buffer
+ *
+ * This function transmits data to another application. Data to be
+ * transmitted is in a buffer and this is a one-way message and the
+ * receiver will not reply to the message.
+ *
+ * Locking:	local_bh_enable/local_bh_disable
+ *
+ * Returns the result from the CP IUCV call.
+ */
+int iucv_message_send(struct iucv_path *path, struct iucv_message *msg,
+		      u8 flags, u32 srccls, void *buffer, size_t size)
+{
+	int rc;
+
+	local_bh_disable();
+	rc = __iucv_message_send(path, msg, flags, srccls, buffer, size);
 	local_bh_enable();
 	return rc;
 }
@@ -1572,7 +1655,7 @@ static void iucv_external_interrupt(u16 code)
 	BUG_ON(p->iptype  < 0x01 || p->iptype > 0x09);
 	work = kmalloc(sizeof(struct iucv_irq_list), GFP_ATOMIC);
 	if (!work) {
-		printk(KERN_WARNING "iucv_external_interrupt: out of memory\n");
+		pr_warning("iucv_external_interrupt: out of memory\n");
 		return;
 	}
 	memcpy(&work->data, p, sizeof(work->data));
diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c
index 7fef8ea1f5ec..d254446b85b5 100644
--- a/net/mac80211/sta_info.c
+++ b/net/mac80211/sta_info.c
@@ -99,7 +99,7 @@ struct sta_info *sta_info_get(struct ieee80211_local *local, const u8 *addr)
 
 	sta = rcu_dereference(local->sta_hash[STA_HASH(addr)]);
 	while (sta) {
-		if (compare_ether_addr(sta->sta.addr, addr) == 0)
+		if (memcmp(sta->sta.addr, addr, ETH_ALEN) == 0)
 			break;
 		sta = rcu_dereference(sta->hnext);
 	}
diff --git a/net/netlabel/netlabel_unlabeled.c b/net/netlabel/netlabel_unlabeled.c
index e8a5c32b0f10..90c8506a0aac 100644
--- a/net/netlabel/netlabel_unlabeled.c
+++ b/net/netlabel/netlabel_unlabeled.c
@@ -574,9 +574,10 @@ static int netlbl_unlhsh_remove_addr4(struct net *net,
 	list_entry = netlbl_af4list_remove(addr->s_addr, mask->s_addr,
 					   &iface->addr4_list);
 	spin_unlock(&netlbl_unlhsh_lock);
-	if (list_entry == NULL)
+	if (list_entry != NULL)
+		entry = netlbl_unlhsh_addr4_entry(list_entry);
+	else
 		ret_val = -ENOENT;
-	entry = netlbl_unlhsh_addr4_entry(list_entry);
 
 	audit_buf = netlbl_audit_start_common(AUDIT_MAC_UNLBL_STCDEL,
 					      audit_info);
@@ -634,9 +635,10 @@ static int netlbl_unlhsh_remove_addr6(struct net *net,
 	spin_lock(&netlbl_unlhsh_lock);
 	list_entry = netlbl_af6list_remove(addr, mask, &iface->addr6_list);
 	spin_unlock(&netlbl_unlhsh_lock);
-	if (list_entry == NULL)
+	if (list_entry != NULL)
+		entry = netlbl_unlhsh_addr6_entry(list_entry);
+	else
 		ret_val = -ENOENT;
-	entry = netlbl_unlhsh_addr6_entry(list_entry);
 
 	audit_buf = netlbl_audit_start_common(AUDIT_MAC_UNLBL_STCDEL,
 					      audit_info);
diff --git a/net/phonet/pn_netlink.c b/net/phonet/pn_netlink.c
index b1770d66bc8d..242fe8f8c322 100644
--- a/net/phonet/pn_netlink.c
+++ b/net/phonet/pn_netlink.c
@@ -123,6 +123,7 @@ nla_put_failure:
 
 static int getaddr_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
 {
+	struct net *net = sock_net(skb->sk);
 	struct phonet_device *pnd;
 	int dev_idx = 0, dev_start_idx = cb->args[0];
 	int addr_idx = 0, addr_start_idx = cb->args[1];
@@ -131,6 +132,8 @@ static int getaddr_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
 	list_for_each_entry(pnd, &pndevs.list, list) {
 		u8 addr;
 
+		if (!net_eq(dev_net(pnd->netdev), net))
+			continue;
 		if (dev_idx > dev_start_idx)
 			addr_start_idx = 0;
 		if (dev_idx++ < dev_start_idx)
diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c
index bf5b5cdafebf..3fe4f1004278 100644
--- a/net/sunrpc/svc_xprt.c
+++ b/net/sunrpc/svc_xprt.c
@@ -515,8 +515,10 @@ int svc_port_is_privileged(struct sockaddr *sin)
 }
 
 /*
- * Make sure that we don't have too many active connections.  If we
- * have, something must be dropped.
+ * Make sure that we don't have too many active connections. If we have,
+ * something must be dropped. It's not clear what will happen if we allow
+ * "too many" connections, but when dealing with network-facing software,
+ * we have to code defensively. Here we do that by imposing hard limits.
  *
  * There's no point in trying to do random drop here for DoS
  * prevention. The NFS clients does 1 reconnect in 15 seconds. An
@@ -525,19 +527,27 @@ int svc_port_is_privileged(struct sockaddr *sin)
  * The only somewhat efficient mechanism would be if drop old
  * connections from the same IP first. But right now we don't even
  * record the client IP in svc_sock.
+ *
+ * single-threaded services that expect a lot of clients will probably
+ * need to set sv_maxconn to override the default value which is based
+ * on the number of threads
  */
 static void svc_check_conn_limits(struct svc_serv *serv)
 {
-	if (serv->sv_tmpcnt > (serv->sv_nrthreads+3)*20) {
+	unsigned int limit = serv->sv_maxconn ? serv->sv_maxconn :
+				(serv->sv_nrthreads+3) * 20;
+
+	if (serv->sv_tmpcnt > limit) {
 		struct svc_xprt *xprt = NULL;
 		spin_lock_bh(&serv->sv_lock);
 		if (!list_empty(&serv->sv_tempsocks)) {
 			if (net_ratelimit()) {
 				/* Try to help the admin */
 				printk(KERN_NOTICE "%s: too many open  "
-				       "connections, consider increasing the "
-				       "number of nfsd threads\n",
-				       serv->sv_name);
+				       "connections, consider increasing %s\n",
+				       serv->sv_name, serv->sv_maxconn ?
+				       "the max number of connections." :
+				       "the number of threads.");
 			}
 			/*
 			 * Always select the oldest connection. It's not fair,
diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c
index 95293f549e9c..a1951dcc5776 100644
--- a/net/sunrpc/svcsock.c
+++ b/net/sunrpc/svcsock.c
@@ -1183,7 +1183,11 @@ int svc_addsock(struct svc_serv *serv,
 	else if (so->state > SS_UNCONNECTED)
 		err = -EISCONN;
 	else {
-		svsk = svc_setup_socket(serv, so, &err, SVC_SOCK_DEFAULTS);
+		if (!try_module_get(THIS_MODULE))
+			err = -ENOENT;
+		else
+			svsk = svc_setup_socket(serv, so, &err,
+						SVC_SOCK_DEFAULTS);
 		if (svsk) {
 			struct sockaddr_storage addr;
 			struct sockaddr *sin = (struct sockaddr *)&addr;
@@ -1196,7 +1200,8 @@ int svc_addsock(struct svc_serv *serv,
 			spin_unlock_bh(&serv->sv_lock);
 			svc_xprt_received(&svsk->sk_xprt);
 			err = 0;
-		}
+		} else
+			module_put(THIS_MODULE);
 	}
 	if (err) {
 		sockfd_put(so);
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 058f04f54b90..fb216c9adf86 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -817,6 +817,7 @@ int xfrm_policy_flush(u8 type, struct xfrm_audit *audit_info)
 				continue;
 			hlist_del(&pol->bydst);
 			hlist_del(&pol->byidx);
+			list_del(&pol->walk.all);
 			write_unlock_bh(&xfrm_policy_lock);
 
 			xfrm_audit_policy_delete(pol, 1, audit_info->loginuid,
diff --git a/samples/tracepoints/tp-samples-trace.h b/samples/tracepoints/tp-samples-trace.h
index 0216b55bd640..01724e04c556 100644
--- a/samples/tracepoints/tp-samples-trace.h
+++ b/samples/tracepoints/tp-samples-trace.h
@@ -4,10 +4,10 @@
 #include <linux/proc_fs.h>	/* for struct inode and struct file */
 #include <linux/tracepoint.h>
 
-DEFINE_TRACE(subsys_event,
+DECLARE_TRACE(subsys_event,
 	TPPROTO(struct inode *inode, struct file *file),
 	TPARGS(inode, file));
-DEFINE_TRACE(subsys_eventb,
+DECLARE_TRACE(subsys_eventb,
 	TPPROTO(void),
 	TPARGS());
 #endif
diff --git a/samples/tracepoints/tracepoint-probe-sample.c b/samples/tracepoints/tracepoint-probe-sample.c
index 55abfdda4bd4..e3a964889dc7 100644
--- a/samples/tracepoints/tracepoint-probe-sample.c
+++ b/samples/tracepoints/tracepoint-probe-sample.c
@@ -46,6 +46,7 @@ void __exit tp_sample_trace_exit(void)
 {
 	unregister_trace_subsys_eventb(probe_subsys_eventb);
 	unregister_trace_subsys_event(probe_subsys_event);
+	tracepoint_synchronize_unregister();
 }
 
 module_exit(tp_sample_trace_exit);
diff --git a/samples/tracepoints/tracepoint-probe-sample2.c b/samples/tracepoints/tracepoint-probe-sample2.c
index 5e9fcf4afffe..685a5acb4562 100644
--- a/samples/tracepoints/tracepoint-probe-sample2.c
+++ b/samples/tracepoints/tracepoint-probe-sample2.c
@@ -33,6 +33,7 @@ module_init(tp_sample_trace_init);
 void __exit tp_sample_trace_exit(void)
 {
 	unregister_trace_subsys_event(probe_subsys_event);
+	tracepoint_synchronize_unregister();
 }
 
 module_exit(tp_sample_trace_exit);
diff --git a/samples/tracepoints/tracepoint-sample.c b/samples/tracepoints/tracepoint-sample.c
index 4ae4b7fcc043..00d169792a3e 100644
--- a/samples/tracepoints/tracepoint-sample.c
+++ b/samples/tracepoints/tracepoint-sample.c
@@ -13,6 +13,9 @@
 #include <linux/proc_fs.h>
 #include "tp-samples-trace.h"
 
+DEFINE_TRACE(subsys_event);
+DEFINE_TRACE(subsys_eventb);
+
 struct proc_dir_entry *pentry_example;
 
 static int my_open(struct inode *inode, struct file *file)
diff --git a/scripts/Kbuild.include b/scripts/Kbuild.include
index 982dcae7bbe2..c29be8f90248 100644
--- a/scripts/Kbuild.include
+++ b/scripts/Kbuild.include
@@ -25,6 +25,13 @@ basetarget = $(basename $(notdir $@))
 escsq = $(subst $(squote),'\$(squote)',$1)
 
 ###
+# Easy method for doing a status message
+       kecho := :
+ quiet_kecho := echo
+silent_kecho := :
+kecho := $($(quiet)kecho)
+
+###
 # filechk is used to check if the content of a generated file is updated.
 # Sample usage:
 # define filechk_sample
@@ -39,22 +46,15 @@ escsq = $(subst $(squote),'\$(squote)',$1)
 # - If they are equal no change, and no timestamp update
 # - stdin is piped in from the first prerequisite ($<) so one has
 #   to specify a valid file as first prerequisite (often the kbuild file)
-       chk_filechk = :
- quiet_chk_filechk = echo '  CHK     $@'
-silent_chk_filechk = :
-       upd_filechk = :
- quiet_upd_filechk = echo '  UPD     $@'
-silent_upd_filechk = :
-
 define filechk
 	$(Q)set -e;				\
-	$($(quiet)chk_filechk);			\
+	$(kecho) '  CHK     $@';		\
 	mkdir -p $(dir $@);			\
 	$(filechk_$(1)) < $< > $@.tmp;		\
 	if [ -r $@ ] && cmp -s $@ $@.tmp; then	\
 		rm -f $@.tmp;			\
 	else					\
-		$($(quiet)upd_filechk);		\
+		$(kecho) '  UPD     $@';	\
 		mv -f $@.tmp $@;		\
 	fi
 endef
@@ -144,7 +144,9 @@ ld-option = $(call try-run,\
 build := -f $(if $(KBUILD_SRC),$(srctree)/)scripts/Makefile.build obj
 
 # Prefix -I with $(srctree) if it is not an absolute path.
-addtree = $(if $(filter-out -I/%,$(1)),$(patsubst -I%,-I$(srctree)/%,$(1))) $(1)
+# skip if -I has no parameter
+addtree = $(if $(patsubst -I%,%,$(1)), \
+$(if $(filter-out -I/%,$(1)),$(patsubst -I%,-I$(srctree)/%,$(1))) $(1))
 
 # Find all -I options and call addtree
 flags = $(foreach o,$($(1)),$(if $(filter -I%,$(o)),$(call addtree,$(o)),$(o)))
diff --git a/scripts/Makefile.build b/scripts/Makefile.build
index 468fbc9016c7..bf52e8d53174 100644
--- a/scripts/Makefile.build
+++ b/scripts/Makefile.build
@@ -153,12 +153,18 @@ $(obj)/%.i: $(src)/%.c FORCE
 
 quiet_cmd_cc_symtypes_c = SYM $(quiet_modtag) $@
 cmd_cc_symtypes_c	   = \
+		set -e;							\
 		$(CPP) -D__GENKSYMS__ $(c_flags) $<			\
-		| $(GENKSYMS) -T $@ >/dev/null;				\
+		| $(GENKSYMS) -T $@					\
+			      -r $(firstword $(wildcard			\
+				     $(@:.symtypes=.symref) /dev/null))	\
+			      $(if $(KBUILD_PRESERVE),-p)		\
+			      -a $(ARCH)				\
+		  >/dev/null;						\
 		test -s $@ || rm -f $@
 
 $(obj)/%.symtypes : $(src)/%.c FORCE
-	$(call if_changed_dep,cc_symtypes_c)
+	$(call cmd,cc_symtypes_c)
 
 # C (.c) files
 # The C file is compiled and updated dependency information is generated.
@@ -187,7 +193,11 @@ cmd_modversions =							\
 	if $(OBJDUMP) -h $(@D)/.tmp_$(@F) | grep -q __ksymtab; then	\
 		$(CPP) -D__GENKSYMS__ $(c_flags) $<			\
 		| $(GENKSYMS) $(if $(KBUILD_SYMTYPES),			\
-			      -T $(@D)/$(@F:.o=.symtypes)) -a $(ARCH)	\
+			           -T $(@:.o=.symtypes))		\
+			      -r $(firstword $(wildcard			\
+				     $(@:.o=.symref) /dev/null))	\
+			      $(if $(KBUILD_PRESERVE),-p)		\
+			      -a $(ARCH)				\
 		> $(@D)/.tmp_$(@F:.o=.ver);				\
 									\
 		$(LD) $(LDFLAGS) -r -o $@ $(@D)/.tmp_$(@F) 		\
@@ -198,16 +208,10 @@ cmd_modversions =							\
 	fi;
 endif
 
-ifdef CONFIG_64BIT
-arch_bits = 64
-else
-arch_bits = 32
-endif
-
 ifdef CONFIG_FTRACE_MCOUNT_RECORD
-cmd_record_mcount = perl $(srctree)/scripts/recordmcount.pl \
-	"$(ARCH)" "$(arch_bits)" "$(OBJDUMP)" "$(OBJCOPY)" "$(CC)" "$(LD)" \
-	"$(NM)" "$(RM)" "$(MV)" "$(@)";
+cmd_record_mcount = perl $(srctree)/scripts/recordmcount.pl "$(ARCH)" \
+	"$(if $(CONFIG_64BIT),64,32)" \
+	"$(OBJDUMP)" "$(OBJCOPY)" "$(CC)" "$(LD)" "$(NM)" "$(RM)" "$(MV)" "$(@)";
 endif
 
 define rule_cc_o_c
diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib
index b4ca38a21158..e06365775bdf 100644
--- a/scripts/Makefile.lib
+++ b/scripts/Makefile.lib
@@ -104,9 +104,11 @@ else
 debug_flags =
 endif
 
-orig_c_flags   = $(KBUILD_CFLAGS) $(ccflags-y) $(CFLAGS_$(basetarget).o)
+orig_c_flags   = $(KBUILD_CPPFLAGS) $(KBUILD_CFLAGS)                     \
+                 $(ccflags-y) $(CFLAGS_$(basetarget).o)
 _c_flags       = $(filter-out $(CFLAGS_REMOVE_$(basetarget).o), $(orig_c_flags))
-_a_flags       = $(KBUILD_AFLAGS) $(asflags-y) $(AFLAGS_$(basetarget).o)
+_a_flags       = $(KBUILD_CPPFLAGS) $(KBUILD_AFLAGS)                     \
+                 $(asflags-y) $(AFLAGS_$(basetarget).o)
 _cpp_flags     = $(KBUILD_CPPFLAGS) $(cppflags-y) $(CPPFLAGS_$(@F))
 
 # If building the kernel in a separate objtree expand all occurrences
@@ -127,15 +129,16 @@ __a_flags	=                          $(call flags,_a_flags)
 __cpp_flags     =                          $(call flags,_cpp_flags)
 endif
 
-c_flags        = -Wp,-MD,$(depfile) $(NOSTDINC_FLAGS) $(KBUILD_CPPFLAGS) \
-		 $(__c_flags) $(modkern_cflags) \
+c_flags        = -Wp,-MD,$(depfile) $(NOSTDINC_FLAGS) $(LINUXINCLUDE)     \
+		 $(__c_flags) $(modkern_cflags)                           \
 		 -D"KBUILD_STR(s)=\#s" $(basename_flags) $(modname_flags) \
 		  $(debug_flags)
 
-a_flags        = -Wp,-MD,$(depfile) $(NOSTDINC_FLAGS) $(KBUILD_CPPFLAGS) \
+a_flags        = -Wp,-MD,$(depfile) $(NOSTDINC_FLAGS) $(LINUXINCLUDE)     \
 		 $(__a_flags) $(modkern_aflags)
 
-cpp_flags      = -Wp,-MD,$(depfile) $(NOSTDINC_FLAGS) $(__cpp_flags)
+cpp_flags      = -Wp,-MD,$(depfile) $(NOSTDINC_FLAGS) $(LINUXINCLUDE)     \
+		 $(__cpp_flags)
 
 ld_flags       = $(LDFLAGS) $(ldflags-y)
 
diff --git a/scripts/bootgraph.pl b/scripts/bootgraph.pl
index d2c61efc216f..f0af9aa9b243 100644
--- a/scripts/bootgraph.pl
+++ b/scripts/bootgraph.pl
@@ -78,11 +78,13 @@ while (<>) {
 }
 
 if ($count == 0) {
-	print "No data found in the dmesg. Make sure that 'printk.time=1' and\n";
-	print "'initcall_debug' are passed on the kernel command line.\n\n";
-	print "Usage: \n";
-	print "      dmesg | perl scripts/bootgraph.pl > output.svg\n\n";
-	exit;
+    print STDERR <<END;
+No data found in the dmesg. Make sure that 'printk.time=1' and
+'initcall_debug' are passed on the kernel command line.
+Usage:
+      dmesg | perl scripts/bootgraph.pl > output.svg
+END
+    exit 1;
 }
 
 print "<?xml version=\"1.0\" standalone=\"no\"?> \n";
@@ -109,8 +111,8 @@ my $stylecounter = 0;
 my %rows;
 my $rowscount = 1;
 my @initcalls = sort { $start{$a} <=> $start{$b} } keys(%start);
-my $key;
-foreach $key (@initcalls) {
+
+foreach my $key (@initcalls) {
 	my $duration = $end{$key} - $start{$key};
 
 	if ($duration >= $threshold) {
diff --git a/scripts/decodecode b/scripts/decodecode
index 235d3938529d..4b00647814bc 100755
--- a/scripts/decodecode
+++ b/scripts/decodecode
@@ -7,7 +7,7 @@
 # AFLAGS=--32 decodecode < 386.oops
 
 cleanup() {
-	rm -f $T $T.s $T.o
+	rm -f $T $T.s $T.o $T.oo $T.aa  $T.aaa
 	exit 1
 }
 
@@ -44,21 +44,33 @@ if [ $marker -eq 0 ]; then
 	marker=`expr index "$code" "\("`
 fi
 
+touch $T.oo
 if [ $marker -ne 0 ]; then
-	beforemark=`echo "$code" | cut -c-$((${marker} - 1))`
+	echo All code >> $T.oo
+	echo ======== >> $T.oo
+	beforemark=`echo "$code"`
 	echo -n "	.byte 0x" > $T.s
-	echo $beforemark | sed -e 's/ /,0x/g' >> $T.s
-	as $AFLAGS -o $T.o $T.s
-	objdump -S $T.o
-	rm $T.o $T.s
+	echo $beforemark | sed -e 's/ /,0x/g' | sed -e 's/<//g' | sed -e 's/>//g' >> $T.s
+	as $AFLAGS -o $T.o $T.s &> /dev/null
+	objdump -S $T.o | grep -v "/tmp" | grep -v "Disassembly" | grep -v "\.text" | grep -v "^$" &> $T.ooo
+	cat $T.ooo >> $T.oo
+	rm -f $T.o $T.s  $T.ooo
 
 # and fix code at-and-after marker
 	code=`echo "$code" | cut -c$((${marker} + 1))-`
 fi
-
+echo Code starting with the faulting instruction  > $T.aa
+echo =========================================== >> $T.aa
 code=`echo $code | sed -e 's/ [<(]/ /;s/[>)] / /;s/ /,0x/g'`
 echo -n "	.byte 0x" > $T.s
 echo $code >> $T.s
-as $AFLAGS -o $T.o $T.s
-objdump -S $T.o
-rm $T $T.s $T.o
+as $AFLAGS -o $T.o $T.s &> /dev/null
+objdump -S $T.o | grep -v "Disassembly" | grep -v "/tmp" | grep -v "\.text" | grep -v "^$" &> $T.aaa
+cat $T.aaa >> $T.aa
+
+faultline=`cat $T.aaa | head -1 | cut -d":" -f2`
+
+cat $T.oo | sed -e "s/\($faultline\)/\*\1     <-- trapping instruction/g"
+echo
+cat $T.aa
+cleanup
diff --git a/scripts/extract-ikconfig b/scripts/extract-ikconfig
index 8187e6f0dc2f..72997c353cb3 100755
--- a/scripts/extract-ikconfig
+++ b/scripts/extract-ikconfig
@@ -8,8 +8,8 @@ test -e $binoffset || cc -o $binoffset ./scripts/binoffset.c || exit 1
 
 IKCFG_ST="0x49 0x4b 0x43 0x46 0x47 0x5f 0x53 0x54"
 IKCFG_ED="0x49 0x4b 0x43 0x46 0x47 0x5f 0x45 0x44"
-function dump_config {
-    typeset file="$1"
+dump_config() {
+    file="$1"
 
     start=`$binoffset $file $IKCFG_ST 2>/dev/null`
     [ "$?" != "0" ] && start="-1"
@@ -18,8 +18,8 @@ function dump_config {
     fi
     end=`$binoffset $file $IKCFG_ED 2>/dev/null`
 
-    let start="$start + 8"
-    let size="$end - $start"
+    start=`expr $start + 8`
+    size=`expr $end - $start`
 
     dd if="$file" ibs=1 skip="$start" count="$size" 2>/dev/null | zcat
 
diff --git a/scripts/genksyms/genksyms.c b/scripts/genksyms/genksyms.c
index c249274e005a..3a8297b5184c 100644
--- a/scripts/genksyms/genksyms.c
+++ b/scripts/genksyms/genksyms.c
@@ -42,7 +42,8 @@ static FILE *debugfile;
 int cur_line = 1;
 char *cur_filename;
 
-static int flag_debug, flag_dump_defs, flag_dump_types, flag_warnings;
+static int flag_debug, flag_dump_defs, flag_reference, flag_dump_types,
+	   flag_preserve, flag_warnings;
 static const char *arch = "";
 static const char *mod_prefix = "";
 
@@ -58,6 +59,8 @@ static const char *const symbol_type_name[] = {
 
 static int equal_list(struct string_list *a, struct string_list *b);
 static void print_list(FILE * f, struct string_list *list);
+static void print_location(void);
+static void print_type_name(enum symbol_type type, const char *name);
 
 /*----------------------------------------------------------------------*/
 
@@ -151,27 +154,83 @@ struct symbol *find_symbol(const char *name, enum symbol_type ns)
 
 	for (sym = symtab[h]; sym; sym = sym->hash_next)
 		if (map_to_ns(sym->type) == map_to_ns(ns) &&
-		    strcmp(name, sym->name) == 0)
+		    strcmp(name, sym->name) == 0 &&
+		    sym->is_declared)
 			break;
 
 	return sym;
 }
 
-struct symbol *add_symbol(const char *name, enum symbol_type type,
-			  struct string_list *defn, int is_extern)
+static int is_unknown_symbol(struct symbol *sym)
+{
+	struct string_list *defn;
+
+	return ((sym->type == SYM_STRUCT ||
+		 sym->type == SYM_UNION ||
+		 sym->type == SYM_ENUM) &&
+		(defn = sym->defn)  && defn->tag == SYM_NORMAL &&
+			strcmp(defn->string, "}") == 0 &&
+		(defn = defn->next) && defn->tag == SYM_NORMAL &&
+			strcmp(defn->string, "UNKNOWN") == 0 &&
+		(defn = defn->next) && defn->tag == SYM_NORMAL &&
+			strcmp(defn->string, "{") == 0);
+}
+
+struct symbol *__add_symbol(const char *name, enum symbol_type type,
+			    struct string_list *defn, int is_extern,
+			    int is_reference)
 {
 	unsigned long h = crc32(name) % HASH_BUCKETS;
 	struct symbol *sym;
+	enum symbol_status status = STATUS_UNCHANGED;
 
 	for (sym = symtab[h]; sym; sym = sym->hash_next) {
-		if (map_to_ns(sym->type) == map_to_ns(type)
-		    && strcmp(name, sym->name) == 0) {
-			if (!equal_list(sym->defn, defn))
+		if (map_to_ns(sym->type) == map_to_ns(type) &&
+		    strcmp(name, sym->name) == 0) {
+			if (is_reference)
+				/* fall through */ ;
+			else if (sym->type == type &&
+				 equal_list(sym->defn, defn)) {
+				if (!sym->is_declared && sym->is_override) {
+					print_location();
+					print_type_name(type, name);
+					fprintf(stderr, " modversion is "
+						"unchanged\n");
+				}
+				sym->is_declared = 1;
+				return sym;
+			} else if (!sym->is_declared) {
+				if (sym->is_override && flag_preserve) {
+					print_location();
+					fprintf(stderr, "ignoring ");
+					print_type_name(type, name);
+					fprintf(stderr, " modversion change\n");
+					sym->is_declared = 1;
+					return sym;
+				} else {
+					status = is_unknown_symbol(sym) ?
+						STATUS_DEFINED : STATUS_MODIFIED;
+				}
+			} else {
 				error_with_pos("redefinition of %s", name);
-			return sym;
+				return sym;
+			}
+			break;
 		}
 	}
 
+	if (sym) {
+		struct symbol **psym;
+
+		for (psym = &symtab[h]; *psym; psym = &(*psym)->hash_next) {
+			if (*psym == sym) {
+				*psym = sym->hash_next;
+				break;
+			}
+		}
+		--nsyms;
+	}
+
 	sym = xmalloc(sizeof(*sym));
 	sym->name = name;
 	sym->type = type;
@@ -183,6 +242,10 @@ struct symbol *add_symbol(const char *name, enum symbol_type type,
 	sym->hash_next = symtab[h];
 	symtab[h] = sym;
 
+	sym->is_declared = !is_reference;
+	sym->status = status;
+	sym->is_override = 0;
+
 	if (flag_debug) {
 		fprintf(debugfile, "Defn for %s %s == <",
 			symbol_type_name[type], name);
@@ -196,6 +259,18 @@ struct symbol *add_symbol(const char *name, enum symbol_type type,
 	return sym;
 }
 
+struct symbol *add_symbol(const char *name, enum symbol_type type,
+			  struct string_list *defn, int is_extern)
+{
+	return __add_symbol(name, type, defn, is_extern, 0);
+}
+
+struct symbol *add_reference_symbol(const char *name, enum symbol_type type,
+				    struct string_list *defn, int is_extern)
+{
+	return __add_symbol(name, type, defn, is_extern, 1);
+}
+
 /*----------------------------------------------------------------------*/
 
 void free_node(struct string_list *node)
@@ -236,6 +311,90 @@ static int equal_list(struct string_list *a, struct string_list *b)
 	return !a && !b;
 }
 
+#define ARRAY_SIZE(arr) (sizeof(arr) / sizeof((arr)[0]))
+
+struct string_list *read_node(FILE *f)
+{
+	char buffer[256];
+	struct string_list node = {
+		.string = buffer,
+		.tag = SYM_NORMAL };
+	int c;
+
+	while ((c = fgetc(f)) != EOF) {
+		if (c == ' ') {
+			if (node.string == buffer)
+				continue;
+			break;
+		} else if (c == '\n') {
+			if (node.string == buffer)
+				return NULL;
+			ungetc(c, f);
+			break;
+		}
+		if (node.string >= buffer + sizeof(buffer) - 1) {
+			fprintf(stderr, "Token too long\n");
+			exit(1);
+		}
+		*node.string++ = c;
+	}
+	if (node.string == buffer)
+		return NULL;
+	*node.string = 0;
+	node.string = buffer;
+
+	if (node.string[1] == '#') {
+		int n;
+
+		for (n = 0; n < ARRAY_SIZE(symbol_type_name); n++) {
+			if (node.string[0] == symbol_type_name[n][0]) {
+				node.tag = n;
+				node.string += 2;
+				return copy_node(&node);
+			}
+		}
+		fprintf(stderr, "Unknown type %c\n", node.string[0]);
+		exit(1);
+	}
+	return copy_node(&node);
+}
+
+static void read_reference(FILE *f)
+{
+	while (!feof(f)) {
+		struct string_list *defn = NULL;
+		struct string_list *sym, *def;
+		int is_extern = 0, is_override = 0;
+		struct symbol *subsym;
+
+		sym = read_node(f);
+		if (sym && sym->tag == SYM_NORMAL &&
+		    !strcmp(sym->string, "override")) {
+			is_override = 1;
+			free_node(sym);
+			sym = read_node(f);
+		}
+		if (!sym)
+			continue;
+		def = read_node(f);
+		if (def && def->tag == SYM_NORMAL &&
+		    !strcmp(def->string, "extern")) {
+			is_extern = 1;
+			free_node(def);
+			def = read_node(f);
+		}
+		while (def) {
+			def->next = defn;
+			defn = def;
+			def = read_node(f);
+		}
+		subsym = add_reference_symbol(xstrdup(sym->string), sym->tag,
+					      defn, is_extern);
+		subsym->is_override = is_override;
+		free_node(sym);
+	}
+}
+
 static void print_node(FILE * f, struct string_list *list)
 {
 	if (list->tag != SYM_NORMAL) {
@@ -311,6 +470,7 @@ static unsigned long expand_and_crc_sym(struct symbol *sym, unsigned long crc)
 
 		case SYM_TYPEDEF:
 			subsym = find_symbol(cur->string, cur->tag);
+			/* FIXME: Bad reference files can segfault here. */
 			if (subsym->expansion_trail) {
 				if (flag_dump_defs)
 					fprintf(debugfile, "%s ", cur->string);
@@ -347,9 +507,22 @@ static unsigned long expand_and_crc_sym(struct symbol *sym, unsigned long crc)
 				t = n;
 
 				n = xmalloc(sizeof(*n));
-				n->string = xstrdup("{ UNKNOWN }");
+				n->string = xstrdup("{");
 				n->tag = SYM_NORMAL;
 				n->next = t;
+				t = n;
+
+				n = xmalloc(sizeof(*n));
+				n->string = xstrdup("UNKNOWN");
+				n->tag = SYM_NORMAL;
+				n->next = t;
+				t = n;
+
+				n = xmalloc(sizeof(*n));
+				n->string = xstrdup("}");
+				n->tag = SYM_NORMAL;
+				n->next = t;
+				t = n;
 
 				subsym =
 				    add_symbol(cur->string, cur->tag, n, 0);
@@ -397,20 +570,42 @@ void export_symbol(const char *name)
 		error_with_pos("export undefined symbol %s", name);
 	else {
 		unsigned long crc;
+		int has_changed = 0;
 
 		if (flag_dump_defs)
 			fprintf(debugfile, "Export %s == <", name);
 
 		expansion_trail = (struct symbol *)-1L;
 
+		sym->expansion_trail = expansion_trail;
+		expansion_trail = sym;
 		crc = expand_and_crc_sym(sym, 0xffffffff) ^ 0xffffffff;
 
 		sym = expansion_trail;
 		while (sym != (struct symbol *)-1L) {
 			struct symbol *n = sym->expansion_trail;
+
+			if (sym->status != STATUS_UNCHANGED) {
+				if (!has_changed) {
+					print_location();
+					fprintf(stderr, "%s: %s: modversion "
+						"changed because of changes "
+						"in ", flag_preserve ? "error" :
+						       "warning", name);
+				} else
+					fprintf(stderr, ", ");
+				print_type_name(sym->type, sym->name);
+				if (sym->status == STATUS_DEFINED)
+					fprintf(stderr, " (became defined)");
+				has_changed = 1;
+				if (flag_preserve)
+					errors++;
+			}
 			sym->expansion_trail = 0;
 			sym = n;
 		}
+		if (has_changed)
+			fprintf(stderr, "\n");
 
 		if (flag_dump_defs)
 			fputs(">\n", debugfile);
@@ -421,13 +616,26 @@ void export_symbol(const char *name)
 }
 
 /*----------------------------------------------------------------------*/
+
+static void print_location(void)
+{
+	fprintf(stderr, "%s:%d: ", cur_filename ? : "<stdin>", cur_line);
+}
+
+static void print_type_name(enum symbol_type type, const char *name)
+{
+	if (type != SYM_NORMAL)
+		fprintf(stderr, "%s %s", symbol_type_name[type], name);
+	else
+		fprintf(stderr, "%s", name);
+}
+
 void error_with_pos(const char *fmt, ...)
 {
 	va_list args;
 
 	if (flag_warnings) {
-		fprintf(stderr, "%s:%d: ", cur_filename ? : "<stdin>",
-			cur_line);
+		print_location();
 
 		va_start(args, fmt);
 		vfprintf(stderr, fmt, args);
@@ -445,7 +653,9 @@ static void genksyms_usage(void)
 	      "  -a, --arch            Select architecture\n"
 	      "  -d, --debug           Increment the debug level (repeatable)\n"
 	      "  -D, --dump            Dump expanded symbol defs (for debugging only)\n"
-	      "  -T, --dump-types file Dump expanded types into file (for debugging only)\n"
+	      "  -r, --reference file  Read reference symbols from a file\n"
+	      "  -T, --dump-types file Dump expanded types into file\n"
+	      "  -p, --preserve        Preserve reference modversions or fail\n"
 	      "  -w, --warnings        Enable warnings\n"
 	      "  -q, --quiet           Disable warnings (default)\n"
 	      "  -h, --help            Print this message\n"
@@ -454,7 +664,9 @@ static void genksyms_usage(void)
 	      "  -a                    Select architecture\n"
 	      "  -d                    Increment the debug level (repeatable)\n"
 	      "  -D                    Dump expanded symbol defs (for debugging only)\n"
-	      "  -T file               Dump expanded types into file (for debugging only)\n"
+	      "  -r file               Read reference symbols from a file\n"
+	      "  -T file               Dump expanded types into file\n"
+	      "  -p                    Preserve reference modversions or fail\n"
 	      "  -w                    Enable warnings\n"
 	      "  -q                    Disable warnings (default)\n"
 	      "  -h                    Print this message\n"
@@ -465,7 +677,7 @@ static void genksyms_usage(void)
 
 int main(int argc, char **argv)
 {
-	FILE *dumpfile = NULL;
+	FILE *dumpfile = NULL, *ref_file = NULL;
 	int o;
 
 #ifdef __GNU_LIBRARY__
@@ -475,16 +687,18 @@ int main(int argc, char **argv)
 		{"warnings", 0, 0, 'w'},
 		{"quiet", 0, 0, 'q'},
 		{"dump", 0, 0, 'D'},
+		{"reference", 1, 0, 'r'},
 		{"dump-types", 1, 0, 'T'},
+		{"preserve", 0, 0, 'p'},
 		{"version", 0, 0, 'V'},
 		{"help", 0, 0, 'h'},
 		{0, 0, 0, 0}
 	};
 
-	while ((o = getopt_long(argc, argv, "a:dwqVDT:h",
+	while ((o = getopt_long(argc, argv, "a:dwqVDr:T:ph",
 				&long_opts[0], NULL)) != EOF)
 #else				/* __GNU_LIBRARY__ */
-	while ((o = getopt(argc, argv, "a:dwqVDT:h")) != EOF)
+	while ((o = getopt(argc, argv, "a:dwqVDr:T:ph")) != EOF)
 #endif				/* __GNU_LIBRARY__ */
 		switch (o) {
 		case 'a':
@@ -505,6 +719,14 @@ int main(int argc, char **argv)
 		case 'D':
 			flag_dump_defs = 1;
 			break;
+		case 'r':
+			flag_reference = 1;
+			ref_file = fopen(optarg, "r");
+			if (!ref_file) {
+				perror(optarg);
+				return 1;
+			}
+			break;
 		case 'T':
 			flag_dump_types = 1;
 			dumpfile = fopen(optarg, "w");
@@ -513,6 +735,9 @@ int main(int argc, char **argv)
 				return 1;
 			}
 			break;
+		case 'p':
+			flag_preserve = 1;
+			break;
 		case 'h':
 			genksyms_usage();
 			return 0;
@@ -533,12 +758,17 @@ int main(int argc, char **argv)
 		/* setlinebuf(debugfile); */
 	}
 
+	if (flag_reference)
+		read_reference(ref_file);
+
 	yyparse();
 
 	if (flag_dump_types && visited_symbols) {
 		while (visited_symbols != (struct symbol *)-1L) {
 			struct symbol *sym = visited_symbols;
 
+			if (sym->is_override)
+				fputs("override ", dumpfile);
 			if (sym->type != SYM_NORMAL) {
 				putc(symbol_type_name[sym->type][0], dumpfile);
 				putc('#', dumpfile);
diff --git a/scripts/genksyms/genksyms.h b/scripts/genksyms/genksyms.h
index 2668287aa498..25c4d40cefc1 100644
--- a/scripts/genksyms/genksyms.h
+++ b/scripts/genksyms/genksyms.h
@@ -29,6 +29,10 @@ enum symbol_type {
 	SYM_NORMAL, SYM_TYPEDEF, SYM_ENUM, SYM_STRUCT, SYM_UNION
 };
 
+enum symbol_status {
+	STATUS_UNCHANGED, STATUS_DEFINED, STATUS_MODIFIED
+};
+
 struct string_list {
 	struct string_list *next;
 	enum symbol_type tag;
@@ -43,6 +47,9 @@ struct symbol {
 	struct symbol *expansion_trail;
 	struct symbol *visited;
 	int is_extern;
+	int is_declared;
+	enum symbol_status status;
+	int is_override;
 };
 
 typedef struct string_list **yystype;
diff --git a/scripts/kconfig/lxdialog/check-lxdialog.sh b/scripts/kconfig/lxdialog/check-lxdialog.sh
index 5552154cbedb..fcef0f59d553 100644
--- a/scripts/kconfig/lxdialog/check-lxdialog.sh
+++ b/scripts/kconfig/lxdialog/check-lxdialog.sh
@@ -52,7 +52,7 @@ EOF
 }
 
 usage() {
-	printf "Usage: $0 [-check compiler options|-header|-library]\n"
+	printf "Usage: $0 [-check compiler options|-ccflags|-ldflags compiler options]\n"
 }
 
 if [ $# -eq 0 ]; then
diff --git a/scripts/mkcompile_h b/scripts/mkcompile_h
index a8740df07b09..6a12dd9f1181 100755
--- a/scripts/mkcompile_h
+++ b/scripts/mkcompile_h
@@ -4,6 +4,8 @@ SMP=$3
 PREEMPT=$4
 CC=$5
 
+vecho() { [ "${quiet}" = "silent_" ] || echo "$@" ; }
+
 # If compile.h exists already and we don't own autoconf.h
 # (i.e. we're not the same user who did make *config), don't
 # modify compile.h
@@ -11,7 +13,7 @@ CC=$5
 # do "compiled by root"
 
 if [ -r $TARGET -a ! -O include/linux/autoconf.h ]; then
-  echo "  SKIPPED $TARGET"
+  vecho "  SKIPPED $TARGET"
   exit 0
 fi
 
@@ -89,7 +91,7 @@ if [ -r $TARGET ] && \
       cmp -s .tmpver.1 .tmpver.2; then
    rm -f .tmpcompile
 else
-   echo "  UPD     $TARGET"
+   vecho "  UPD     $TARGET"
    mv -f .tmpcompile $TARGET
 fi
 rm -f .tmpver.1 .tmpver.2
diff --git a/scripts/mkmakefile b/scripts/mkmakefile
index e65d8b33faa4..67d59c7a18dc 100644
--- a/scripts/mkmakefile
+++ b/scripts/mkmakefile
@@ -17,7 +17,9 @@ if test -e $2/Makefile && ! grep -q Automatically $2/Makefile
 then
 	exit 0
 fi
-echo "  GEN     $2/Makefile"
+if [ "${quiet}" != "silent_" ]; then
+	echo "  GEN     $2/Makefile"
+fi
 
 cat << EOF > $2/Makefile
 # Automatically generated by $0: don't edit
diff --git a/scripts/package/Makefile b/scripts/package/Makefile
index 5e326078a4a2..c162409fb4e4 100644
--- a/scripts/package/Makefile
+++ b/scripts/package/Makefile
@@ -47,7 +47,7 @@ rpm-pkg rpm: $(objtree)/kernel.spec FORCE
 	set -e; \
 	mv -f $(objtree)/.tmp_version $(objtree)/.version
 
-	$(RPM) --target $(UTS_MACHINE) -ta ../$(KERNELPATH).tar.gz
+	$(RPM) $(RPMOPTS) --target $(UTS_MACHINE) -ta ../$(KERNELPATH).tar.gz
 	rm ../$(KERNELPATH).tar.gz
 
 clean-files := $(objtree)/kernel.spec
@@ -64,7 +64,8 @@ binrpm-pkg: $(objtree)/binkernel.spec FORCE
 	set -e; \
 	mv -f $(objtree)/.tmp_version $(objtree)/.version
 
-	$(RPM) --define "_builddir $(srctree)" --target $(UTS_MACHINE) -bb $<
+	$(RPM) $(RPMOPTS) --define "_builddir $(srctree)" --target \
+		$(UTS_MACHINE) -bb $<
 
 clean-files += $(objtree)/binkernel.spec
 
diff --git a/scripts/recordmcount.pl b/scripts/recordmcount.pl
index 6b9fe3eb8360..0197e2f6b544 100755
--- a/scripts/recordmcount.pl
+++ b/scripts/recordmcount.pl
@@ -130,10 +130,13 @@ my %weak;		# List of weak functions
 my %convert;		# List of local functions used that needs conversion
 
 my $type;
+my $nm_regex;		# Find the local functions (return function)
 my $section_regex;	# Find the start of a section
 my $function_regex;	# Find the name of a function
 			#    (return offset and func name)
 my $mcount_regex;	# Find the call site to mcount (return offset)
+my $alignment;		# The .align value to use for $mcount_section
+my $section_type;	# Section header plus possible alignment command
 
 if ($arch eq "x86") {
     if ($bits == 64) {
@@ -143,11 +146,21 @@ if ($arch eq "x86") {
     }
 }
 
+#
+# We base the defaults off of i386, the other archs may
+# feel free to change them in the below if statements.
+#
+$nm_regex = "^[0-9a-fA-F]+\\s+t\\s+(\\S+)";
+$section_regex = "Disassembly of section\\s+(\\S+):";
+$function_regex = "^([0-9a-fA-F]+)\\s+<(.*?)>:";
+$mcount_regex = "^\\s*([0-9a-fA-F]+):.*\\smcount\$";
+$section_type = '@progbits';
+$type = ".long";
+
 if ($arch eq "x86_64") {
-    $section_regex = "Disassembly of section\\s+(\\S+):";
-    $function_regex = "^([0-9a-fA-F]+)\\s+<(.*?)>:";
     $mcount_regex = "^\\s*([0-9a-fA-F]+):.*\\smcount([+-]0x[0-9a-zA-Z]+)?\$";
     $type = ".quad";
+    $alignment = 8;
 
     # force flags for this arch
     $ld .= " -m elf_x86_64";
@@ -156,10 +169,7 @@ if ($arch eq "x86_64") {
     $cc .= " -m64";
 
 } elsif ($arch eq "i386") {
-    $section_regex = "Disassembly of section\\s+(\\S+):";
-    $function_regex = "^([0-9a-fA-F]+)\\s+<(.*?)>:";
-    $mcount_regex = "^\\s*([0-9a-fA-F]+):.*\\smcount\$";
-    $type = ".long";
+    $alignment = 4;
 
     # force flags for this arch
     $ld .= " -m elf_i386";
@@ -167,6 +177,27 @@ if ($arch eq "x86_64") {
     $objcopy .= " -O elf32-i386";
     $cc .= " -m32";
 
+} elsif ($arch eq "sh") {
+    $alignment = 2;
+
+    # force flags for this arch
+    $ld .= " -m shlelf_linux";
+    $objcopy .= " -O elf32-sh-linux";
+    $cc .= " -m32";
+
+} elsif ($arch eq "powerpc") {
+    $nm_regex = "^[0-9a-fA-F]+\\s+t\\s+(\\.?\\S+)";
+    $function_regex = "^([0-9a-fA-F]+)\\s+<(\\.?.*?)>:";
+    $mcount_regex = "^\\s*([0-9a-fA-F]+):.*\\s\\.?_mcount\$";
+
+    if ($bits == 64) {
+	$type = ".quad";
+    }
+
+} elsif ($arch eq "arm") {
+    $alignment = 2;
+    $section_type = '%progbits';
+
 } else {
     die "Arch $arch is not supported with CONFIG_FTRACE_MCOUNT_RECORD";
 }
@@ -236,7 +267,7 @@ if (!$found_version) {
 #
 open (IN, "$nm $inputfile|") || die "error running $nm";
 while (<IN>) {
-    if (/^[0-9a-fA-F]+\s+t\s+(\S+)/) {
+    if (/$nm_regex/) {
 	$locals{$1} = 1;
     } elsif (/^[0-9a-fA-F]+\s+([wW])\s+(\S+)/) {
 	$weak{$2} = $1;
@@ -287,7 +318,8 @@ sub update_funcs
 	if (!$opened) {
 	    open(FILE, ">$mcount_s") || die "can't create $mcount_s\n";
 	    $opened = 1;
-	    print FILE "\t.section $mcount_section,\"a\",\@progbits\n";
+	    print FILE "\t.section $mcount_section,\"a\",$section_type\n";
+	    print FILE "\t.align $alignment\n" if (defined($alignment));
 	}
 	printf FILE "\t%s %s + %d\n", $type, $ref_func, $offsets[$i] - $offset;
     }
diff --git a/scripts/setlocalversion b/scripts/setlocalversion
index 72d233528ade..f6946cf99ce1 100755
--- a/scripts/setlocalversion
+++ b/scripts/setlocalversion
@@ -19,6 +19,11 @@ if head=`git rev-parse --verify --short HEAD 2>/dev/null`; then
 		fi
 	fi
 
+	# Is this git on svn?
+	if git config --get svn-remote.svn.url >/dev/null; then
+	        printf -- '-svn%s' "`git-svn find-rev $head`"
+	fi
+
 	# Are there uncommitted changes?
 	git update-index --refresh --unmerged > /dev/null
 	if git diff-index --name-only HEAD | grep -v "^scripts/package" \
@@ -51,7 +56,7 @@ if hgid=`hg id 2>/dev/null`; then
 fi
 
 # Check for svn and a svn repo.
-if rev=`svn info 2>/dev/null | grep '^Revision'`; then
+if rev=`svn info 2>/dev/null | grep '^Last Changed Rev'`; then
 	rev=`echo $rev | awk '{print $NF}'`
 	changes=`svn status 2>/dev/null | grep '^[AMD]' | wc -l`
 
diff --git a/scripts/tags.sh b/scripts/tags.sh
new file mode 100755
index 000000000000..47274dc5d823
--- /dev/null
+++ b/scripts/tags.sh
@@ -0,0 +1,160 @@
+#!/bin/sh
+# Generate tags or cscope files
+# Usage tags.sh <mode>
+#
+# mode may be any of: tags, TAGS, cscope
+#
+# Uses the following environment variables:
+# ARCH, SUBARCH, srctree, src, obj
+
+if [ $KBUILD_VERBOSE == 1 ]; then
+	set -x
+fi
+
+# This is a duplicate of RCS_FIND_IGNORE without escaped '()'
+ignore="( -name SCCS -o -name BitKeeper -o -name .svn -o \
+          -name CVS  -o -name .pc       -o -name .hg  -o \
+          -name .git )                                   \
+          -prune -o"
+
+# Do not use full path is we do not use O=.. builds
+if [ ${src} == ${obj} ]; then
+	tree=
+else
+	tree=${srctree}
+fi
+
+# find sources in arch/$ARCH
+find_arch_sources()
+{
+	find ${tree}arch/$1 $ignore -name $2 -print;
+}
+
+# find sources in arch/$1/include
+find_arch_include_sources()
+{
+	find ${tree}arch/$1/include $ignore -name $2 -print;
+}
+
+# find sources in include/
+find_include_sources()
+{
+	find ${tree}include $ignore -name config -prune -o -name $1 -print;
+}
+
+# find sources in rest of tree
+# we could benefit from a list of dirs to search in here
+find_other_sources()
+{
+	find ${tree}* $ignore \
+	     \( -name include -o -name arch -o -name '.tmp_*' \) -prune -o \
+	       -name $1 -print;
+}
+
+find_sources()
+{
+	find_arch_sources $1 $2
+	find_include_sources $2
+	find_other_sources $2
+}
+
+all_sources()
+{
+	find_sources $SRCARCH *.[chS]
+	if [ ! -z "$archinclude" ]; then
+		find_arch_include_sources $archinclude *.[chS]
+	fi
+}
+
+all_kconfigs()
+{
+	find_sources $SRCARCH "Kconfig*"
+}
+
+all_defconfigs()
+{
+	find_sources $SRCARCH "defconfig"
+}
+
+docscope()
+{
+	(echo \-k; echo \-q; all_sources) > cscope.files
+	cscope -b -f cscope.out
+}
+
+exuberant()
+{
+	all_sources > all
+	all_sources | xargs $1 -a                               \
+	-I __initdata,__exitdata,__acquires,__releases          \
+	-I __read_mostly,____cacheline_aligned                  \
+	-I ____cacheline_aligned_in_smp                         \
+	-I ____cacheline_internodealigned_in_smp                \
+	-I EXPORT_SYMBOL,EXPORT_SYMBOL_GPL                      \
+	--extra=+f --c-kinds=+px                                \
+	--regex-asm='/^ENTRY\(([^)]*)\).*/\1/'
+
+	all_kconfigs | xargs $1 -a                              \
+	--langdef=kconfig --language-force=kconfig              \
+	--regex-kconfig='/^[[:blank:]]*(menu|)config[[:blank:]]+([[:alnum:]_]+)/\2/'
+
+	all_kconfigs | xargs $1 -a                              \
+	--langdef=kconfig --language-force=kconfig              \
+	--regex-kconfig='/^[[:blank:]]*(menu|)config[[:blank:]]+([[:alnum:]_]+)/CONFIG_\2/'
+
+	all_defconfigs | xargs -r $1 -a                         \
+	--langdef=dotconfig --language-force=dotconfig          \
+	--regex-dotconfig='/^#?[[:blank:]]*(CONFIG_[[:alnum:]_]+)/\1/'
+
+}
+
+emacs()
+{
+	all_sources | xargs $1 -a
+
+	all_kconfigs | xargs $1 -a                              \
+	--regex='/^[ \t]*\(\(menu\)*config\)[ \t]+\([a-zA-Z0-9_]+\)/\3/'
+
+	all_kconfigs | xargs $1 -a                              \
+	--regex='/^[ \t]*\(\(menu\)*config\)[ \t]+\([a-zA-Z0-9_]+\)/CONFIG_\3/'
+
+	all_defconfigs | xargs -r $1 -a                         \
+	--regex='/^#?[ \t]?\(CONFIG_[a-zA-Z0-9_]+\)/\1/'
+}
+
+xtags()
+{
+	if $1 --version 2>&1 | grep -iq exuberant; then
+		exuberant $1
+	elif $1 --version 2>&1 | grep -iq emacs; then
+		emacs $1
+	else
+		all_sources | xargs $1 -a
+        fi
+}
+
+
+# Support um (which uses SUBARCH)
+if [ ${ARCH} == um ]; then
+	if [ $SUBARCH == i386 ]; then
+		archinclude=x86
+	elif [ $SUBARCH == x86_64 ]; then
+		archinclude=x86
+	else
+		archinclude=${SUBARCH}
+	fi
+fi
+
+case "$1" in
+	"cscope")
+		docscope
+		;;
+
+	"tags")
+		xtags ctags
+		;;
+
+	"TAGS")
+		xtags etags
+		;;
+esac
diff --git a/scripts/tracing/draw_functrace.py b/scripts/tracing/draw_functrace.py
new file mode 100644
index 000000000000..902f9a992620
--- /dev/null
+++ b/scripts/tracing/draw_functrace.py
@@ -0,0 +1,130 @@
+#!/usr/bin/python
+
+"""
+Copyright 2008 (c) Frederic Weisbecker <fweisbec@gmail.com>
+Licensed under the terms of the GNU GPL License version 2
+
+This script parses a trace provided by the function tracer in
+kernel/trace/trace_functions.c
+The resulted trace is processed into a tree to produce a more human
+view of the call stack by drawing textual but hierarchical tree of
+calls. Only the functions's names and the the call time are provided.
+
+Usage:
+	Be sure that you have CONFIG_FUNCTION_TRACER
+	# mkdir /debugfs
+	# mount -t debug debug /debug
+	# echo function > /debug/tracing/current_tracer
+	$ cat /debug/tracing/trace_pipe > ~/raw_trace_func
+	Wait some times but not too much, the script is a bit slow.
+	Break the pipe (Ctrl + Z)
+	$ scripts/draw_functrace.py < raw_trace_func > draw_functrace
+	Then you have your drawn trace in draw_functrace
+"""
+
+
+import sys, re
+
+class CallTree:
+	""" This class provides a tree representation of the functions
+		call stack. If a function has no parent in the kernel (interrupt,
+		syscall, kernel thread...) then it is attached to a virtual parent
+		called ROOT.
+	"""
+	ROOT = None
+
+	def __init__(self, func, time = None, parent = None):
+		self._func = func
+		self._time = time
+		if parent is None:
+			self._parent = CallTree.ROOT
+		else:
+			self._parent = parent
+		self._children = []
+
+	def calls(self, func, calltime):
+		""" If a function calls another one, call this method to insert it
+			into the tree at the appropriate place.
+			@return: A reference to the newly created child node.
+		"""
+		child = CallTree(func, calltime, self)
+		self._children.append(child)
+		return child
+
+	def getParent(self, func):
+		""" Retrieve the last parent of the current node that
+			has the name given by func. If this function is not
+			on a parent, then create it as new child of root
+			@return: A reference to the parent.
+		"""
+		tree = self
+		while tree != CallTree.ROOT and tree._func != func:
+			tree = tree._parent
+		if tree == CallTree.ROOT:
+			child = CallTree.ROOT.calls(func, None)
+			return child
+		return tree
+
+	def __repr__(self):
+		return self.__toString("", True)
+
+	def __toString(self, branch, lastChild):
+		if self._time is not None:
+			s = "%s----%s (%s)\n" % (branch, self._func, self._time)
+		else:
+			s = "%s----%s\n" % (branch, self._func)
+
+		i = 0
+		if lastChild:
+			branch = branch[:-1] + " "
+		while i < len(self._children):
+			if i != len(self._children) - 1:
+				s += "%s" % self._children[i].__toString(branch +\
+								"    |", False)
+			else:
+				s += "%s" % self._children[i].__toString(branch +\
+								"    |", True)
+			i += 1
+		return s
+
+class BrokenLineException(Exception):
+	"""If the last line is not complete because of the pipe breakage,
+	   we want to stop the processing and ignore this line.
+	"""
+	pass
+
+class CommentLineException(Exception):
+	""" If the line is a comment (as in the beginning of the trace file),
+	    just ignore it.
+	"""
+	pass
+
+
+def parseLine(line):
+	line = line.strip()
+	if line.startswith("#"):
+		raise CommentLineException
+	m = re.match("[^]]+?\\] +([0-9.]+): (\\w+) <-(\\w+)", line)
+	if m is None:
+		raise BrokenLineException
+	return (m.group(1), m.group(2), m.group(3))
+
+
+def main():
+	CallTree.ROOT = CallTree("Root (Nowhere)", None, None)
+	tree = CallTree.ROOT
+
+	for line in sys.stdin:
+		try:
+			calltime, callee, caller = parseLine(line)
+		except BrokenLineException:
+			break
+		except CommentLineException:
+			continue
+		tree = tree.getParent(caller)
+		tree = tree.calls(callee, calltime)
+
+	print CallTree.ROOT
+
+if __name__ == "__main__":
+	main()
diff --git a/sound/arm/pxa2xx-ac97-lib.c b/sound/arm/pxa2xx-ac97-lib.c
index 34c1d94f921e..ef6539eea579 100644
--- a/sound/arm/pxa2xx-ac97-lib.c
+++ b/sound/arm/pxa2xx-ac97-lib.c
@@ -22,7 +22,7 @@
 
 #include <asm/irq.h>
 #include <mach/hardware.h>
-#include <mach/pxa-regs.h>
+#include <mach/regs-ac97.h>
 #include <mach/pxa2xx-gpio.h>
 #include <mach/audio.h>
 
diff --git a/sound/arm/pxa2xx-ac97.c b/sound/arm/pxa2xx-ac97.c
index c2635beb4c88..85cf591d4e11 100644
--- a/sound/arm/pxa2xx-ac97.c
+++ b/sound/arm/pxa2xx-ac97.c
@@ -22,6 +22,7 @@
 
 #include <mach/hardware.h>
 #include <mach/pxa-regs.h>
+#include <mach/regs-ac97.h>
 #include <mach/audio.h>
 
 #include "pxa2xx-pcm.h"
diff --git a/sound/arm/pxa2xx-pcm.h b/sound/arm/pxa2xx-pcm.h
index 5c4a4d38a083..65f86b56ba42 100644
--- a/sound/arm/pxa2xx-pcm.h
+++ b/sound/arm/pxa2xx-pcm.h
@@ -9,7 +9,7 @@
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
  */
-#include <asm/dma.h>
+#include <mach/dma.h>
 
 struct pxa2xx_runtime_data {
 	int dma_ch;
diff --git a/sound/oss/waveartist.c b/sound/oss/waveartist.c
index c47842fad657..2c63bb9da74a 100644
--- a/sound/oss/waveartist.c
+++ b/sound/oss/waveartist.c
@@ -1483,16 +1483,14 @@ static void __exit unload_waveartist(struct address_info *hw)
 #define VNC_HANDSET_DETECT	0x40
 #define VNC_DISABLE_AUTOSWITCH	0x80
 
-extern spinlock_t gpio_lock;
-
 static inline void
 vnc_mute_spkr(wavnc_info *devc)
 {
 	unsigned long flags;
 
-	spin_lock_irqsave(&gpio_lock, flags);
-	cpld_modify(CPLD_UNMUTE, devc->spkr_mute_state ? 0 : CPLD_UNMUTE);
-	spin_unlock_irqrestore(&gpio_lock, flags);
+	spin_lock_irqsave(&nw_gpio_lock, flags);
+	nw_cpld_modify(CPLD_UNMUTE, devc->spkr_mute_state ? 0 : CPLD_UNMUTE);
+	spin_unlock_irqrestore(&nw_gpio_lock, flags);
 }
 
 static void
diff --git a/sound/soc/pxa/pxa2xx-ac97.c b/sound/soc/pxa/pxa2xx-ac97.c
index a7a3a9c5c6ff..5e727393cfd4 100644
--- a/sound/soc/pxa/pxa2xx-ac97.c
+++ b/sound/soc/pxa/pxa2xx-ac97.c
@@ -21,6 +21,7 @@
 
 #include <mach/hardware.h>
 #include <mach/pxa-regs.h>
+#include <mach/regs-ac97.h>
 
 #include "pxa2xx-pcm.h"
 #include "pxa2xx-ac97.h"
diff --git a/sound/soc/s3c24xx/s3c2443-ac97.c b/sound/soc/s3c24xx/s3c2443-ac97.c
index 19c5c3cf5d8c..c473a3b97b55 100644
--- a/sound/soc/s3c24xx/s3c2443-ac97.c
+++ b/sound/soc/s3c24xx/s3c2443-ac97.c
@@ -28,7 +28,7 @@
 #include <sound/soc.h>
 
 #include <mach/hardware.h>
-#include <asm/plat-s3c/regs-ac97.h>
+#include <plat/regs-ac97.h>
 #include <mach/regs-gpio.h>
 #include <mach/regs-clock.h>
 #include <mach/audio.h>
diff --git a/usr/gen_init_cpio.c b/usr/gen_init_cpio.c
index 7abc07f0fcd2..f1d3fe34176a 100644
--- a/usr/gen_init_cpio.c
+++ b/usr/gen_init_cpio.c
@@ -370,6 +370,30 @@ error:
 	return rc;
 }
 
+static char *cpio_replace_env(char *new_location)
+{
+       char expanded[PATH_MAX + 1];
+       char env_var[PATH_MAX + 1];
+       char *start;
+       char *end;
+
+       for (start = NULL; (start = strstr(new_location, "${")); ) {
+               end = strchr(start, '}');
+               if (start < end) {
+                       *env_var = *expanded = '\0';
+                       strncat(env_var, start + 2, end - start - 2);
+                       strncat(expanded, new_location, start - new_location);
+                       strncat(expanded, getenv(env_var), PATH_MAX);
+                       strncat(expanded, end + 1, PATH_MAX);
+                       strncpy(new_location, expanded, PATH_MAX);
+               } else
+                       break;
+       }
+
+       return new_location;
+}
+
+
 static int cpio_mkfile_line(const char *line)
 {
 	char name[PATH_MAX + 1];
@@ -415,7 +439,8 @@ static int cpio_mkfile_line(const char *line)
 	} else {
 		dname = name;
 	}
-	rc = cpio_mkfile(dname, location, mode, uid, gid, nlinks);
+	rc = cpio_mkfile(dname, cpio_replace_env(location),
+	                 mode, uid, gid, nlinks);
  fail:
 	if (dname_len) free(dname);
 	return rc;
@@ -439,6 +464,7 @@ void usage(const char *prog)
 		"\n"
 		"<name>       name of the file/dir/nod/etc in the archive\n"
 		"<location>   location of the file in the current filesystem\n"
+		"             expands shell variables quoted with ${}\n"
 		"<target>     link target\n"
 		"<mode>       mode/permissions of the file\n"
 		"<uid>        user id (0=root)\n"